43 files changed, 2306 insertions, 1544 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index a987aa1676b5..149e18ef1ab1 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -68,7 +68,7 @@ obj-$(CONFIG_USER_NS) += user_namespace.o
 obj-$(CONFIG_PID_NS) += pid_namespace.o
 obj-$(CONFIG_IKCONFIG) += configs.o
 obj-$(CONFIG_RESOURCE_COUNTERS) += res_counter.o
-obj-$(CONFIG_STOP_MACHINE) += stop_machine.o
+obj-$(CONFIG_SMP) += stop_machine.o
 obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o
 obj-$(CONFIG_AUDIT) += audit.o auditfilter.o audit_watch.o
 obj-$(CONFIG_AUDITSYSCALL) += auditsc.o
diff --git a/kernel/capability.c b/kernel/capability.c
index 9e4697e9b276..2f05303715a5 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -15,7 +15,6 @@
 #include <linux/syscalls.h>
 #include <linux/pid_namespace.h>
 #include <asm/uaccess.h>
-#include "cred-internals.h"
 
 /*
  * Leveraged for setting/resetting capabilities
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index e2769e13980c..4a07d057a265 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -3010,7 +3010,7 @@ static int cgroup_event_wake(wait_queue_t *wait, unsigned mode,
         unsigned long flags = (unsigned long)key;
 
         if (flags & POLLHUP) {
-                remove_wait_queue_locked(event->wqh, &event->wait);
+                __remove_wait_queue(event->wqh, &event->wait);
                 spin_lock(&cgrp->event_list_lock);
                 list_del(&event->list);
                 spin_unlock(&cgrp->event_list_lock);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 25bba73b1be3..545777574779 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -164,6 +164,7 @@ static inline void check_for_tasks(int cpu)
 }
 
 struct take_cpu_down_param {
+        struct task_struct *caller;
         unsigned long mod;
         void *hcpu;
 };
@@ -172,6 +173,7 @@ struct take_cpu_down_param {
 static int __ref take_cpu_down(void *_param)
 {
         struct take_cpu_down_param *param = _param;
+        unsigned int cpu = (unsigned long)param->hcpu;
         int err;
 
         /* Ensure this CPU doesn't handle any more interrupts. */
@@ -182,6 +184,8 @@ static int __ref take_cpu_down(void *_param)
         raw_notifier_call_chain(&cpu_chain, CPU_DYING | param->mod,
                                 param->hcpu);
 
+        if (task_cpu(param->caller) == cpu)
+                move_task_off_dead_cpu(cpu, param->caller);
         /* Force idle task to run as soon as we yield: it should
            immediately notice cpu is offline and die quickly. */
         sched_idle_next();
@@ -192,10 +196,10 @@ static int __ref take_cpu_down(void *_param)
 static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 {
         int err, nr_calls = 0;
-        cpumask_var_t old_allowed;
         void *hcpu = (void *)(long)cpu;
         unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
         struct take_cpu_down_param tcd_param = {
+                .caller = current,
                 .mod = mod,
                 .hcpu = hcpu,
         };
@@ -206,9 +210,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
         if (!cpu_online(cpu))
                 return -EINVAL;
 
-        if (!alloc_cpumask_var(&old_allowed, GFP_KERNEL))
-                return -ENOMEM;
-
         cpu_hotplug_begin();
         set_cpu_active(cpu, false);
         err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE | mod,
@@ -225,10 +226,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
                 goto out_release;
         }
 
-        /* Ensure that we are not runnable on dying cpu */
-        cpumask_copy(old_allowed, &current->cpus_allowed);
-        set_cpus_allowed_ptr(current, cpu_active_mask);
-
         err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
         if (err) {
                 set_cpu_active(cpu, true);
@@ -237,7 +234,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
                                             hcpu) == NOTIFY_BAD)
                         BUG();
 
-                goto out_allowed;
+                goto out_release;
         }
         BUG_ON(cpu_online(cpu));
 
@@ -255,8 +252,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 
         check_for_tasks(cpu);
 
-out_allowed:
-        set_cpus_allowed_ptr(current, old_allowed);
 out_release:
         cpu_hotplug_done();
         if (!err) {
@@ -264,7 +259,6 @@ out_release:
                                             hcpu) == NOTIFY_BAD)
                         BUG();
         }
-        free_cpumask_var(old_allowed);
         return err;
 }
 
@@ -272,9 +266,6 @@ int __ref cpu_down(unsigned int cpu)
 {
         int err;
 
-        err = stop_machine_create();
-        if (err)
-                return err;
         cpu_maps_update_begin();
 
         if (cpu_hotplug_disabled) {
@@ -286,7 +277,6 @@ int __ref cpu_down(unsigned int cpu)
 
 out:
         cpu_maps_update_done();
-        stop_machine_destroy();
         return err;
 }
 EXPORT_SYMBOL(cpu_down);
@@ -367,9 +357,6 @@ int disable_nonboot_cpus(void)
 {
         int cpu, first_cpu, error;
 
-        error = stop_machine_create();
-        if (error)
-                return error;
         cpu_maps_update_begin();
         first_cpu = cpumask_first(cpu_online_mask);
         /*
@@ -400,7 +387,6 @@ int disable_nonboot_cpus(void)
                 printk(KERN_ERR "Non-boot CPUs are not disabled\n");
         }
         cpu_maps_update_done();
-        stop_machine_destroy();
         return error;
 }
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index d10946748ec2..9a50c5f6e727 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2182,19 +2182,52 @@ void __init cpuset_init_smp(void)
 void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 {
         mutex_lock(&callback_mutex);
-        cpuset_cpus_allowed_locked(tsk, pmask);
+        task_lock(tsk);
+        guarantee_online_cpus(task_cs(tsk), pmask);
+        task_unlock(tsk);
         mutex_unlock(&callback_mutex);
 }
 
-/**
- * cpuset_cpus_allowed_locked - return cpus_allowed mask from a tasks cpuset.
- * Must be called with callback_mutex held.
- **/
-void cpuset_cpus_allowed_locked(struct task_struct *tsk, struct cpumask *pmask)
+int cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 {
-        task_lock(tsk);
-        guarantee_online_cpus(task_cs(tsk), pmask);
-        task_unlock(tsk);
+        const struct cpuset *cs;
+        int cpu;
+
+        rcu_read_lock();
+        cs = task_cs(tsk);
+        if (cs)
+                cpumask_copy(&tsk->cpus_allowed, cs->cpus_allowed);
+        rcu_read_unlock();
+
+        /*
+         * We own tsk->cpus_allowed, nobody can change it under us.
+         *
+         * But we used cs && cs->cpus_allowed lockless and thus can
+         * race with cgroup_attach_task() or update_cpumask() and get
+         * the wrong tsk->cpus_allowed. However, both cases imply the
+         * subsequent cpuset_change_cpumask()->set_cpus_allowed_ptr()
+         * which takes task_rq_lock().
+         *
+         * If we are called after it dropped the lock we must see all
+         * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary
+         * set any mask even if it is not right from task_cs() pov,
+         * the pending set_cpus_allowed_ptr() will fix things.
+         */
+
+        cpu = cpumask_any_and(&tsk->cpus_allowed, cpu_active_mask);
+        if (cpu >= nr_cpu_ids) {
+                /*
+                 * Either tsk->cpus_allowed is wrong (see above) or it
+                 * is actually empty. The latter case is only possible
+                 * if we are racing with remove_tasks_in_empty_cpuset().
+                 * Like above we can temporary set any mask and rely on
+                 * set_cpus_allowed_ptr() as synchronization point.
+                 */
+                cpumask_copy(&tsk->cpus_allowed, cpu_possible_mask);
+                cpu = cpumask_any(cpu_active_mask);
+        }
+
+        return cpu;
 }
 
 void cpuset_init_current_mems_allowed(void)
@@ -2383,22 +2416,6 @@ int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
 }
 
 /**
- * cpuset_lock - lock out any changes to cpuset structures
- *
- * The out of memory (oom) code needs to mutex_lock cpusets
- * from being changed while it scans the tasklist looking for a
- * task in an overlapping cpuset.  Expose callback_mutex via this
- * cpuset_lock() routine, so the oom code can lock it, before
- * locking the task list.  The tasklist_lock is a spinlock, so
- * must be taken inside callback_mutex.
- */
-
-void cpuset_lock(void)
-{
-        mutex_lock(&callback_mutex);
-}
-
-/**
  * cpuset_unlock - release lock on cpuset changes
  *
  * Undo the lock taken in a previous cpuset_lock() call.
diff --git a/kernel/cred-internals.h b/kernel/cred-internals.h
deleted file mode 100644
index 2dc4fc2d0bf1..000000000000
--- a/kernel/cred-internals.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* Internal credentials stuff
- *
- * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-
-/*
- * user.c
- */
-static inline void sched_switch_user(struct task_struct *p)
-{
-#ifdef CONFIG_USER_SCHED
-        sched_move_task(p);
-#endif  /* CONFIG_USER_SCHED */
-}
-
diff --git a/kernel/cred.c b/kernel/cred.c
index 62af1816c235..8f3672a58a1e 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -17,7 +17,6 @@
 #include <linux/init_task.h>
 #include <linux/security.h>
 #include <linux/cn_proc.h>
-#include "cred-internals.h"
 
 #if 0
 #define kdebug(FMT, ...) \
@@ -560,8 +559,6 @@ int commit_creds(struct cred *new)
                 atomic_dec(&old->user->processes);
         alter_cred_subscribers(old, -2);
 
-        sched_switch_user(task);
-
         /* send notifications */
         if (new->uid   != old->uid  ||
             new->euid  != old->euid ||
diff --git a/kernel/exit.c b/kernel/exit.c
index 7f2683a10ac4..eabca5a73a85 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -55,7 +55,6 @@
 #include <asm/unistd.h>
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
-#include "cred-internals.h"
 
 static void exit_mm(struct task_struct * tsk);
 
diff --git a/kernel/module.c b/kernel/module.c
index 1016b75b026a..e2564580f3f1 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -59,8 +59,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/module.h>
 
-EXPORT_TRACEPOINT_SYMBOL(module_get);
-
 #if 0
 #define DEBUGP printk
 #else
@@ -515,6 +513,9 @@ MODINFO_ATTR(srcversion);
 static char last_unloaded_module[MODULE_NAME_LEN+1];
 
 #ifdef CONFIG_MODULE_UNLOAD
+
+EXPORT_TRACEPOINT_SYMBOL(module_get);
+
 /* Init the unload section of the module. */
 static void module_unload_init(struct module *mod)
 {
@@ -723,16 +724,8 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
                 return -EFAULT;
         name[MODULE_NAME_LEN-1] = '\0';
 
-        /* Create stop_machine threads since free_module relies on
-         * a non-failing stop_machine call. */
-        ret = stop_machine_create();
-        if (ret)
-                return ret;
-
-        if (mutex_lock_interruptible(&module_mutex) != 0) {
-                ret = -EINTR;
-                goto out_stop;
-        }
+        if (mutex_lock_interruptible(&module_mutex) != 0)
+                return -EINTR;
 
         mod = find_module(name);
         if (!mod) {
@@ -792,8 +785,6 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 
  out:
         mutex_unlock(&module_mutex);
-out_stop:
-        stop_machine_destroy();
         return ret;
 }
 
@@ -867,8 +858,7 @@ void module_put(struct module *module)
                 smp_wmb(); /* see comment in module_refcount */
                 __this_cpu_inc(module->refptr->decs);
 
-                trace_module_put(module, _RET_IP_,
-                                 __this_cpu_read(module->refptr->decs));
+                trace_module_put(module, _RET_IP_);
                 /* Maybe they're waiting for us to drop reference? */
                 if (unlikely(!module_is_live(module)))
                         wake_up_process(module->waiter);
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 58df55bf83ed..2b676f3a0f26 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -669,7 +669,7 @@ static struct rcu_torture_ops sched_expedited_ops = {
         .sync           = synchronize_sched_expedited,
         .cb_barrier     = NULL,
         .fqs            = rcu_sched_force_quiescent_state,
-        .stats          = rcu_expedited_torture_stats,
+        .stats          = NULL,
         .irq_capable    = 1,
         .name           = "sched_expedited"
 };
diff --git a/kernel/sched.c b/kernel/sched.c
index b11b80a3eed3..78554dd0d1a4 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -55,9 +55,9 @@
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
 #include <linux/percpu.h>
-#include <linux/kthread.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/stop_machine.h>
 #include <linux/sysctl.h>
 #include <linux/syscalls.h>
 #include <linux/times.h>
@@ -503,8 +503,11 @@ struct rq {
         #define CPU_LOAD_IDX_MAX 5
         unsigned long cpu_load[CPU_LOAD_IDX_MAX];
 #ifdef CONFIG_NO_HZ
+        u64 nohz_stamp;
         unsigned char in_nohz_recently;
 #endif
+        unsigned int skip_clock_update;
+
         /* capture load from *all* tasks on this cpu: */
         struct load_weight load;
         unsigned long nr_load_updates;
@@ -546,15 +549,13 @@ struct rq {
         int post_schedule;
         int active_balance;
         int push_cpu;
+        struct cpu_stop_work active_balance_work;
         /* cpu of this runqueue: */
         int cpu;
         int online;
 
         unsigned long avg_load_per_task;
 
-        struct task_struct *migration_thread;
-        struct list_head migration_queue;
-
         u64 rt_avg;
         u64 age_stamp;
         u64 idle_stamp;
@@ -602,6 +603,13 @@ static inline
 void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 {
         rq->curr->sched_class->check_preempt_curr(rq, p, flags);
+
+        /*
+         * A queue event has occurred, and we're going to schedule.  In
+         * this case, we can save a useless back to back clock update.
+         */
+        if (test_tsk_need_resched(p))
+                rq->skip_clock_update = 1;
 }
 
 static inline int cpu_of(struct rq *rq)
@@ -636,7 +644,8 @@ static inline int cpu_of(struct rq *rq)
 
 inline void update_rq_clock(struct rq *rq)
 {
-        rq->clock = sched_clock_cpu(cpu_of(rq));
+        if (!rq->skip_clock_update)
+                rq->clock = sched_clock_cpu(cpu_of(rq));
 }
 
 /*
@@ -914,16 +923,12 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 #endif /* __ARCH_WANT_UNLOCKED_CTXSW */
 
 /*
- * Check whether the task is waking, we use this to synchronize against
- * ttwu() so that task_cpu() reports a stable number.
- *
- * We need to make an exception for PF_STARTING tasks because the fork
- * path might require task_rq_lock() to work, eg. it can call
- * set_cpus_allowed_ptr() from the cpuset clone_ns code.
+ * Check whether the task is waking, we use this to synchronize ->cpus_allowed
+ * against ttwu().
  */
 static inline int task_is_waking(struct task_struct *p)
 {
-        return unlikely((p->state == TASK_WAKING) && !(p->flags & PF_STARTING));
+        return unlikely(p->state == TASK_WAKING);
 }
 
 /*
@@ -936,11 +941,9 @@ static inline struct rq *__task_rq_lock(struct task_struct *p)
         struct rq *rq;
 
         for (;;) {
-                while (task_is_waking(p))
-                        cpu_relax();
                 rq = task_rq(p);
                 raw_spin_lock(&rq->lock);
-                if (likely(rq == task_rq(p) && !task_is_waking(p)))
+                if (likely(rq == task_rq(p)))
                         return rq;
                 raw_spin_unlock(&rq->lock);
         }
@@ -957,12 +960,10 @@ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
         struct rq *rq;
 
         for (;;) {
-                while (task_is_waking(p))
-                        cpu_relax();
                 local_irq_save(*flags);
                 rq = task_rq(p);
                 raw_spin_lock(&rq->lock);
-                if (likely(rq == task_rq(p) && !task_is_waking(p)))
+                if (likely(rq == task_rq(p)))
                         return rq;
                 raw_spin_unlock_irqrestore(&rq->lock, *flags);
         }
@@ -1239,6 +1240,17 @@ void wake_up_idle_cpu(int cpu)
         if (!tsk_is_polling(rq->idle))
                 smp_send_reschedule(cpu);
 }
+
+int nohz_ratelimit(int cpu)
+{
+        struct rq *rq = cpu_rq(cpu);
+        u64 diff = rq->clock - rq->nohz_stamp;
+
+        rq->nohz_stamp = rq->clock;
+
+        return diff < (NSEC_PER_SEC / HZ) >> 1;
+}
+
 #endif /* CONFIG_NO_HZ */
 
 static u64 sched_avg_period(void)
@@ -1781,8 +1793,6 @@ static void double_rq_lock(struct rq *rq1, struct rq *rq2)
                         raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
                 }
         }
-        update_rq_clock(rq1);
-        update_rq_clock(rq2);
 }
 
 /*
@@ -1813,7 +1823,7 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
 }
 #endif
 
-static void calc_load_account_active(struct rq *this_rq);
+static void calc_load_account_idle(struct rq *this_rq);
 static void update_sysctl(void);
 static int get_update_sysctl_factor(void);
 
@@ -1870,62 +1880,43 @@ static void set_load_weight(struct task_struct *p)
         p->se.load.inv_weight = prio_to_wmult[p->static_prio - MAX_RT_PRIO];
 }
 
-static void update_avg(u64 *avg, u64 sample)
+static void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 {
-        s64 diff = sample - *avg;
-        *avg += diff >> 3;
-}
-
-static void
-enqueue_task(struct rq *rq, struct task_struct *p, int wakeup, bool head)
-{
-        if (wakeup)
-                p->se.start_runtime = p->se.sum_exec_runtime;
-
+        update_rq_clock(rq);
         sched_info_queued(p);
-        p->sched_class->enqueue_task(rq, p, wakeup, head);
+        p->sched_class->enqueue_task(rq, p, flags);
         p->se.on_rq = 1;
 }
 
-static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep)
+static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 {
-        if (sleep) {
-                if (p->se.last_wakeup) {
-                        update_avg(&p->se.avg_overlap,
-                                p->se.sum_exec_runtime - p->se.last_wakeup);
-                        p->se.last_wakeup = 0;
-                } else {
-                        update_avg(&p->se.avg_wakeup,
-                                sysctl_sched_wakeup_granularity);
-                }
-        }
-
+        update_rq_clock(rq);
         sched_info_dequeued(p);
-        p->sched_class->dequeue_task(rq, p, sleep);
+        p->sched_class->dequeue_task(rq, p, flags);
         p->se.on_rq = 0;
 }
 
 /*
  * activate_task - move a task to the runqueue.
  */
-static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
+static void activate_task(struct rq *rq, struct task_struct *p, int flags)
 {
         if (task_contributes_to_load(p))
                 rq->nr_uninterruptible--;
 
-        enqueue_task(rq, p, wakeup, false);
+        enqueue_task(rq, p, flags);
         inc_nr_running(rq);
 }
 
 /*
  * deactivate_task - remove a task from the runqueue.
  */
-static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep)
+static void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 {
         if (task_contributes_to_load(p))
                 rq->nr_uninterruptible++;
 
-        dequeue_task(rq, p, sleep);
+        dequeue_task(rq, p, flags);
         dec_nr_running(rq);
 }
 
@@ -2054,21 +2045,18 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
         __set_task_cpu(p, new_cpu);
 }
 
-struct migration_req {
-        struct list_head list;
-
+struct migration_arg {
         struct task_struct *task;
         int dest_cpu;
-
-        struct completion done;
 };
 
+static int migration_cpu_stop(void *data);
+
 /*
  * The task's runqueue lock must be held.
  * Returns true if you have to wait for migration thread.
  */
-static int
-migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
+static bool migrate_task(struct task_struct *p, int dest_cpu)
 {
         struct rq *rq = task_rq(p);
 
@@ -2076,15 +2064,7 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
          * If the task is not on a runqueue (and not running), then
          * the next wake-up will properly place the task.
          */
-        if (!p->se.on_rq && !task_running(rq, p))
-                return 0;
-
-        init_completion(&req->done);
-        req->task = p;
-        req->dest_cpu = dest_cpu;
-        list_add(&req->list, &rq->migration_queue);
-
-        return 1;
+        return p->se.on_rq || task_running(rq, p);
 }
 
 /*
@@ -2142,7 +2122,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
                  * just go back and repeat.
                  */
                 rq = task_rq_lock(p, &flags);
-                trace_sched_wait_task(rq, p);
+                trace_sched_wait_task(p);
                 running = task_running(rq, p);
                 on_rq = p->se.on_rq;
                 ncsw = 0;
@@ -2240,6 +2220,9 @@ void task_oncpu_function_call(struct task_struct *p,
 }
 
 #ifdef CONFIG_SMP
+/*
+ * ->cpus_allowed is protected by either TASK_WAKING or rq->lock held.
+ */
 static int select_fallback_rq(int cpu, struct task_struct *p)
 {
         int dest_cpu;
@@ -2256,12 +2239,8 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
                 return dest_cpu;
 
         /* No more Mr. Nice Guy. */
-        if (dest_cpu >= nr_cpu_ids) {
-                rcu_read_lock();
-                cpuset_cpus_allowed_locked(p, &p->cpus_allowed);
-                rcu_read_unlock();
-                dest_cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed);
-
+        if (unlikely(dest_cpu >= nr_cpu_ids)) {
+                dest_cpu = cpuset_cpus_allowed_fallback(p);
                 /*
                  * Don't tell them about moving exiting tasks or
                  * kernel threads (both mm NULL), since they never
@@ -2278,17 +2257,12 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 }
 
 /*
- * Gets called from 3 sites (exec, fork, wakeup), since it is called without
- * holding rq->lock we need to ensure ->cpus_allowed is stable, this is done
- * by:
- *
- *  exec:           is unstable, retry loop
- *  fork & wake-up: serialize ->cpus_allowed against TASK_WAKING
+ * The caller (fork, wakeup) owns TASK_WAKING, ->cpus_allowed is stable.
  */
 static inline
-int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
+int select_task_rq(struct rq *rq, struct task_struct *p, int sd_flags, int wake_flags)
 {
-        int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags);
+        int cpu = p->sched_class->select_task_rq(rq, p, sd_flags, wake_flags);
 
         /*
          * In order not to call set_task_cpu() on a blocking task we need
@@ -2306,6 +2280,12 @@ int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
 
         return cpu;
 }
+
+static void update_avg(u64 *avg, u64 sample)
+{
+        s64 diff = sample - *avg;
+        *avg += diff >> 3;
+}
 #endif
 
 /***
@@ -2327,16 +2307,13 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 {
         int cpu, orig_cpu, this_cpu, success = 0;
         unsigned long flags;
+        unsigned long en_flags = ENQUEUE_WAKEUP;
         struct rq *rq;
 
-        if (!sched_feat(SYNC_WAKEUPS))
-                wake_flags &= ~WF_SYNC;
-
         this_cpu = get_cpu();
 
         smp_wmb();
         rq = task_rq_lock(p, &flags);
-        update_rq_clock(rq);
         if (!(p->state & state))
                 goto out;
 
@@ -2356,28 +2333,26 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
          *
          * First fix up the nr_uninterruptible count:
          */
-        if (task_contributes_to_load(p))
-                rq->nr_uninterruptible--;
+        if (task_contributes_to_load(p)) {
+                if (likely(cpu_online(orig_cpu)))
+                        rq->nr_uninterruptible--;
+                else
+                        this_rq()->nr_uninterruptible--;
+        }
         p->state = TASK_WAKING;
 
-        if (p->sched_class->task_waking)
+        if (p->sched_class->task_waking) {
                 p->sched_class->task_waking(rq, p);
+                en_flags |= ENQUEUE_WAKING;
+        }
 
-        __task_rq_unlock(rq);
-
-        cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
-        if (cpu != orig_cpu) {
-                /*
-                 * Since we migrate the task without holding any rq->lock,
-                 * we need to be careful with task_rq_lock(), since that
-                 * might end up locking an invalid rq.
-                 */
+        cpu = select_task_rq(rq, p, SD_BALANCE_WAKE, wake_flags);
+        if (cpu != orig_cpu)
                 set_task_cpu(p, cpu);
-        }
+        __task_rq_unlock(rq);
 
         rq = cpu_rq(cpu);
         raw_spin_lock(&rq->lock);
-        update_rq_clock(rq);
 
         /*
          * We migrated the task without holding either rq->lock, however
@@ -2405,36 +2380,20 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 
 out_activate:
 #endif /* CONFIG_SMP */
-        schedstat_inc(p, se.nr_wakeups);
+        schedstat_inc(p, se.statistics.nr_wakeups);
         if (wake_flags & WF_SYNC)
-                schedstat_inc(p, se.nr_wakeups_sync);
+                schedstat_inc(p, se.statistics.nr_wakeups_sync);
         if (orig_cpu != cpu)
-                schedstat_inc(p, se.nr_wakeups_migrate);
+                schedstat_inc(p, se.statistics.nr_wakeups_migrate);
         if (cpu == this_cpu)
-                schedstat_inc(p, se.nr_wakeups_local);
+                schedstat_inc(p, se.statistics.nr_wakeups_local);
         else
-                schedstat_inc(p, se.nr_wakeups_remote);
-        activate_task(rq, p, 1);
+                schedstat_inc(p, se.statistics.nr_wakeups_remote);
+        activate_task(rq, p, en_flags);
         success = 1;
 
-        /*
-         * Only attribute actual wakeups done by this task.
-         */
-        if (!in_interrupt()) {
-                struct sched_entity *se = &current->se;
-                u64 sample = se->sum_exec_runtime;
-
-                if (se->last_wakeup)
-                        sample -= se->last_wakeup;
-                else
-                        sample -= se->start_runtime;
-                update_avg(&se->avg_wakeup, sample);
-
-                se->last_wakeup = se->sum_exec_runtime;
-        }
-
 out_running:
-        trace_sched_wakeup(rq, p, success);
+        trace_sched_wakeup(p, success);
         check_preempt_curr(rq, p, wake_flags);
 
         p->state = TASK_RUNNING;
@@ -2494,42 +2453,9 @@ static void __sched_fork(struct task_struct *p)
         p->se.sum_exec_runtime          = 0;
         p->se.prev_sum_exec_runtime     = 0;
         p->se.nr_migrations             = 0;
-        p->se.last_wakeup               = 0;
-        p->se.avg_overlap               = 0;
-        p->se.start_runtime             = 0;
-        p->se.avg_wakeup                = sysctl_sched_wakeup_granularity;
 
 #ifdef CONFIG_SCHEDSTATS
-        p->se.wait_start                        = 0;
-        p->se.wait_max                          = 0;
-        p->se.wait_count                        = 0;
-        p->se.wait_sum                          = 0;
-
-        p->se.sleep_start                       = 0;
-        p->se.sleep_max                         = 0;
-        p->se.sum_sleep_runtime                 = 0;
-
-        p->se.block_start                       = 0;
-        p->se.block_max                         = 0;
-        p->se.exec_max                          = 0;
-        p->se.slice_max                         = 0;
-
-        p->se.nr_migrations_cold                = 0;
-        p->se.nr_failed_migrations_affine       = 0;
-        p->se.nr_failed_migrations_running      = 0;
-        p->se.nr_failed_migrations_hot          = 0;
-        p->se.nr_forced_migrations              = 0;
-
-        p->se.nr_wakeups                        = 0;
-        p->se.nr_wakeups_sync                   = 0;
-        p->se.nr_wakeups_migrate                = 0;
-        p->se.nr_wakeups_local                  = 0;
-        p->se.nr_wakeups_remote                 = 0;
-        p->se.nr_wakeups_affine                 = 0;
-        p->se.nr_wakeups_affine_attempts        = 0;
-        p->se.nr_wakeups_passive                = 0;
-        p->se.nr_wakeups_idle                   = 0;
-
+        memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
 
         INIT_LIST_HEAD(&p->rt.run_list);
@@ -2550,11 +2476,11 @@ void sched_fork(struct task_struct *p, int clone_flags)
 
         __sched_fork(p);
         /*
-         * We mark the process as waking here. This guarantees that
+         * We mark the process as running here. This guarantees that
          * nobody will actually run it, and a signal or other external
          * event cannot wake it up and insert it on the runqueue either.
          */
-        p->state = TASK_WAKING;
+        p->state = TASK_RUNNING;
 
         /*
          * Revert to default priority/policy on fork if requested.
@@ -2621,31 +2547,27 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
         int cpu __maybe_unused = get_cpu();
 
 #ifdef CONFIG_SMP
+        rq = task_rq_lock(p, &flags);
+        p->state = TASK_WAKING;
+
         /*
          * Fork balancing, do it here and not earlier because:
          *  - cpus_allowed can change in the fork path
          *  - any previously selected cpu might disappear through hotplug
          *
-         * We still have TASK_WAKING but PF_STARTING is gone now, meaning
-         * ->cpus_allowed is stable, we have preemption disabled, meaning
-         * cpu_online_mask is stable.
+         * We set TASK_WAKING so that select_task_rq() can drop rq->lock
+         * without people poking at ->cpus_allowed.
          */
-        cpu = select_task_rq(p, SD_BALANCE_FORK, 0);
+        cpu = select_task_rq(rq, p, SD_BALANCE_FORK, 0);
         set_task_cpu(p, cpu);
-#endif
 
-        /*
-         * Since the task is not on the rq and we still have TASK_WAKING set
-         * nobody else will migrate this task.
-         */
-        rq = cpu_rq(cpu);
-        raw_spin_lock_irqsave(&rq->lock, flags);
-
-        BUG_ON(p->state != TASK_WAKING);
         p->state = TASK_RUNNING;
-        update_rq_clock(rq);
+        task_rq_unlock(rq, &flags);
+#endif
+
+        rq = task_rq_lock(p, &flags);
         activate_task(rq, p, 0);
-        trace_sched_wakeup_new(rq, p, 1);
+        trace_sched_wakeup_new(p, 1);
         check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
         if (p->sched_class->task_woken)
@@ -2865,7 +2787,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
         struct mm_struct *mm, *oldmm;
 
         prepare_task_switch(rq, prev, next);
-        trace_sched_switch(rq, prev, next);
+        trace_sched_switch(prev, next);
         mm = next->mm;
         oldmm = prev->active_mm;
         /*
@@ -2982,6 +2904,61 @@ static unsigned long calc_load_update;
 unsigned long avenrun[3];
 EXPORT_SYMBOL(avenrun);
 
+static long calc_load_fold_active(struct rq *this_rq)
+{
+        long nr_active, delta = 0;
+
+        nr_active = this_rq->nr_running;
+        nr_active += (long) this_rq->nr_uninterruptible;
+
+        if (nr_active != this_rq->calc_load_active) {
+                delta = nr_active - this_rq->calc_load_active;
+                this_rq->calc_load_active = nr_active;
+        }
+
+        return delta;
+}
+
+#ifdef CONFIG_NO_HZ
+/*
+ * For NO_HZ we delay the active fold to the next LOAD_FREQ update.
+ *
+ * When making the ILB scale, we should try to pull this in as well.
+ */
+static atomic_long_t calc_load_tasks_idle;
+
+static void calc_load_account_idle(struct rq *this_rq)
+{
+        long delta;
+
+        delta = calc_load_fold_active(this_rq);
+        if (delta)
+                atomic_long_add(delta, &calc_load_tasks_idle);
+}
+
+static long calc_load_fold_idle(void)
+{
+        long delta = 0;
+
+        /*
+         * Its got a race, we don't care...
+         */
+        if (atomic_long_read(&calc_load_tasks_idle))
+                delta = atomic_long_xchg(&calc_load_tasks_idle, 0);
+
+        return delta;
+}
+#else
+static void calc_load_account_idle(struct rq *this_rq)
+{
+}
+
+static inline long calc_load_fold_idle(void)
+{
+        return 0;
+}
+#endif
+
 /**
  * get_avenrun - get the load average array
  * @loads:      pointer to dest load array
@@ -3028,20 +3005,22 @@ void calc_global_load(void)
 }
 
 /*
- * Either called from update_cpu_load() or from a cpu going idle
+ * Called from update_cpu_load() to periodically update this CPU's
+ * active count.
  */
 static void calc_load_account_active(struct rq *this_rq)
 {
-        long nr_active, delta;
+        long delta;
 
-        nr_active = this_rq->nr_running;
-        nr_active += (long) this_rq->nr_uninterruptible;
+        if (time_before(jiffies, this_rq->calc_load_update))
+                return;
 
-        if (nr_active != this_rq->calc_load_active) {
-                delta = nr_active - this_rq->calc_load_active;
-                this_rq->calc_load_active = nr_active;
+        delta  = calc_load_fold_active(this_rq);
+        delta += calc_load_fold_idle();
+        if (delta)
                 atomic_long_add(delta, &calc_load_tasks);
-        }
+
+        this_rq->calc_load_update += LOAD_FREQ;
 }
 
 /*
@@ -3073,10 +3052,7 @@ static void update_cpu_load(struct rq *this_rq)
                 this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i;
         }
 
-        if (time_after_eq(jiffies, this_rq->calc_load_update)) {
-                this_rq->calc_load_update += LOAD_FREQ;
-                calc_load_account_active(this_rq);
-        }
+        calc_load_account_active(this_rq);
 }
 
 #ifdef CONFIG_SMP
@@ -3088,44 +3064,27 @@ static void update_cpu_load(struct rq *this_rq)
 void sched_exec(void)
 {
         struct task_struct *p = current;
-        struct migration_req req;
-        int dest_cpu, this_cpu;
         unsigned long flags;
         struct rq *rq;
-
-again:
-        this_cpu = get_cpu();
-        dest_cpu = select_task_rq(p, SD_BALANCE_EXEC, 0);
-        if (dest_cpu == this_cpu) {
-                put_cpu();
-                return;
-        }
+        int dest_cpu;
 
         rq = task_rq_lock(p, &flags);
-        put_cpu();
+        dest_cpu = p->sched_class->select_task_rq(rq, p, SD_BALANCE_EXEC, 0);
+        if (dest_cpu == smp_processor_id())
+                goto unlock;
 
         /*
          * select_task_rq() can race against ->cpus_allowed
          */
-        if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed)
-            || unlikely(!cpu_active(dest_cpu))) {
-                task_rq_unlock(rq, &flags);
-                goto again;
-        }
+        if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) &&
+            likely(cpu_active(dest_cpu)) && migrate_task(p, dest_cpu)) {
+                struct migration_arg arg = { p, dest_cpu };
 
-        /* force the process onto the specified CPU */
-        if (migrate_task(p, dest_cpu, &req)) {
-                /* Need to wait for migration thread (might exit: take ref). */
-                struct task_struct *mt = rq->migration_thread;
-
-                get_task_struct(mt);
                 task_rq_unlock(rq, &flags);
-                wake_up_process(mt);
-                put_task_struct(mt);
-                wait_for_completion(&req.done);
-
+                stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
                 return;
         }
+unlock:
         task_rq_unlock(rq, &flags);
 }
 
@@ -3597,23 +3556,9 @@ static inline void schedule_debug(struct task_struct *prev)
 
 static void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
-        if (prev->state == TASK_RUNNING) {
-                u64 runtime = prev->se.sum_exec_runtime;
-
-                runtime -= prev->se.prev_sum_exec_runtime;
-                runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost);
-
-                /*
-                 * In order to avoid avg_overlap growing stale when we are
-                 * indeed overlapping and hence not getting put to sleep, grow
-                 * the avg_overlap on preemption.
-                 *
-                 * We use the average preemption runtime because that
-                 * correlates to the amount of cache footprint a task can
-                 * build up.
-                 */
-                update_avg(&prev->se.avg_overlap, runtime);
-        }
+        if (prev->se.on_rq)
+                update_rq_clock(rq);
+        rq->skip_clock_update = 0;
         prev->sched_class->put_prev_task(rq, prev);
 }
 
@@ -3676,14 +3621,13 @@ need_resched_nonpreemptible:
                 hrtick_clear(rq);
 
         raw_spin_lock_irq(&rq->lock);
-        update_rq_clock(rq);
         clear_tsk_need_resched(prev);
 
         if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
                 if (unlikely(signal_pending_state(prev->state, prev)))
                         prev->state = TASK_RUNNING;
                 else
-                        deactivate_task(rq, prev, 1);
+                        deactivate_task(rq, prev, DEQUEUE_SLEEP);
                 switch_count = &prev->nvcsw;
         }
 
@@ -4006,8 +3950,7 @@ do_wait_for_common(struct completion *x, long timeout, int state)
         if (!x->done) {
                 DECLARE_WAITQUEUE(wait, current);
 
-                wait.flags |= WQ_FLAG_EXCLUSIVE;
-                __add_wait_queue_tail(&x->wait, &wait);
+                __add_wait_queue_tail_exclusive(&x->wait, &wait);
                 do {
                         if (signal_pending_state(state, current)) {
                                 timeout = -ERESTARTSYS;
@@ -4233,7 +4176,6 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
         BUG_ON(prio < 0 || prio > MAX_PRIO);
 
         rq = task_rq_lock(p, &flags);
-        update_rq_clock(rq);
 
         oldprio = p->prio;
         prev_class = p->sched_class;
@@ -4254,7 +4196,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
         if (running)
                 p->sched_class->set_curr_task(rq);
         if (on_rq) {
-                enqueue_task(rq, p, 0, oldprio < prio);
+                enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
 
                 check_class_changed(rq, p, prev_class, oldprio, running);
         }
@@ -4276,7 +4218,6 @@ void set_user_nice(struct task_struct *p, long nice)
          * the task might be in the middle of scheduling on another CPU.
          */
         rq = task_rq_lock(p, &flags);
-        update_rq_clock(rq);
         /*
          * The RT priorities are set via sched_setscheduler(), but we still
          * allow the 'normal' nice value to be set - but as expected
@@ -4298,7 +4239,7 @@ void set_user_nice(struct task_struct *p, long nice)
         delta = p->prio - old_prio;
 
         if (on_rq) {
-                enqueue_task(rq, p, 0, false);
+                enqueue_task(rq, p, 0);
                 /*
                  * If the task increased its priority or is running and
                  * lowered its priority, then reschedule its CPU:
@@ -4559,7 +4500,6 @@ recheck:
                 raw_spin_unlock_irqrestore(&p->pi_lock, flags);
                 goto recheck;
         }
-        update_rq_clock(rq);
         on_rq = p->se.on_rq;
         running = task_current(rq, p);
         if (on_rq)
@@ -5296,17 +5236,15 @@ static inline void sched_init_granularity(void)
 /*
  * This is how migration works:
  *
- * 1) we queue a struct migration_req structure in the source CPU's
- *    runqueue and wake up that CPU's migration thread.
- * 2) we down() the locked semaphore => thread blocks.
- * 3) migration thread wakes up (implicitly it forces the migrated
- *    thread off the CPU)
- * 4) it gets the migration request and checks whether the migrated
- *    task is still in the wrong runqueue.
- * 5) if it's in the wrong runqueue then the migration thread removes
+ * 1) we invoke migration_cpu_stop() on the target CPU using
+ *    stop_one_cpu().
+ * 2) stopper starts to run (implicitly forcing the migrated thread
+ *    off the CPU)
+ * 3) it checks whether the migrated task is still in the wrong runqueue.
+ * 4) if it's in the wrong runqueue then the migration thread removes
  *    it and puts it into the right queue.
- * 6) migration thread up()s the semaphore.
- * 7) we wake up and the migration is done.
+ * 5) stopper completes and stop_one_cpu() returns and the migration
+ *    is done.
  */
 
 /*
@@ -5320,12 +5258,23 @@ static inline void sched_init_granularity(void)
  */
 int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 {
-        struct migration_req req;
         unsigned long flags;
         struct rq *rq;
+        unsigned int dest_cpu;
         int ret = 0;
 
+        /*
+         * Serialize against TASK_WAKING so that ttwu() and wunt() can
+         * drop the rq->lock and still rely on ->cpus_allowed.
+         */
+again:
+        while (task_is_waking(p))
+                cpu_relax();
         rq = task_rq_lock(p, &flags);
+        if (task_is_waking(p)) {
+                task_rq_unlock(rq, &flags);
+                goto again;
+        }
 
         if (!cpumask_intersects(new_mask, cpu_active_mask)) {
                 ret = -EINVAL;
@@ -5349,15 +5298,12 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
         if (cpumask_test_cpu(task_cpu(p), new_mask))
                 goto out;
 
-        if (migrate_task(p, cpumask_any_and(cpu_active_mask, new_mask), &req)) {
+        dest_cpu = cpumask_any_and(cpu_active_mask, new_mask);
+        if (migrate_task(p, dest_cpu)) {
+                struct migration_arg arg = { p, dest_cpu };
                 /* Need help from migration thread: drop lock and wait. */
-                struct task_struct *mt = rq->migration_thread;
-
-                get_task_struct(mt);
                 task_rq_unlock(rq, &flags);
-                wake_up_process(mt);
-                put_task_struct(mt);
-                wait_for_completion(&req.done);
+                stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
                 tlb_migrate_finish(p->mm);
                 return 0;
         }
@@ -5415,98 +5361,49 @@ fail:
         return ret;
 }
 
-#define RCU_MIGRATION_IDLE      0
-#define RCU_MIGRATION_NEED_QS   1
-#define RCU_MIGRATION_GOT_QS    2
-#define RCU_MIGRATION_MUST_SYNC 3
-
 /*
- * migration_thread - this is a highprio system thread that performs
- * thread migration by bumping thread off CPU then 'pushing' onto
- * another runqueue.
+ * migration_cpu_stop - this will be executed by a highprio stopper thread
+ * and performs thread migration by bumping thread off CPU then
+ * 'pushing' onto another runqueue.
  */
-static int migration_thread(void *data)
+static int migration_cpu_stop(void *data)
 {
-        int badcpu;
-        int cpu = (long)data;
-        struct rq *rq;
-
-        rq = cpu_rq(cpu);
-        BUG_ON(rq->migration_thread != current);
-
-        set_current_state(TASK_INTERRUPTIBLE);
-        while (!kthread_should_stop()) {
-                struct migration_req *req;
-                struct list_head *head;
-
-                raw_spin_lock_irq(&rq->lock);
-
-                if (cpu_is_offline(cpu)) {
-                        raw_spin_unlock_irq(&rq->lock);
-                        break;
-                }
-
-                if (rq->active_balance) {
-                        active_load_balance(rq, cpu);
-                        rq->active_balance = 0;
-                }
-
-                head = &rq->migration_queue;
-
-                if (list_empty(head)) {
-                        raw_spin_unlock_irq(&rq->lock);
-                        schedule();
-                        set_current_state(TASK_INTERRUPTIBLE);
-                        continue;
-                }
-                req = list_entry(head->next, struct migration_req, list);
-                list_del_init(head->next);
-
-                if (req->task != NULL) {
-                        raw_spin_unlock(&rq->lock);
-                        __migrate_task(req->task, cpu, req->dest_cpu);
-                } else if (likely(cpu == (badcpu = smp_processor_id()))) {
-                        req->dest_cpu = RCU_MIGRATION_GOT_QS;
-                        raw_spin_unlock(&rq->lock);
-                } else {
-                        req->dest_cpu = RCU_MIGRATION_MUST_SYNC;
-                        raw_spin_unlock(&rq->lock);
-                        WARN_ONCE(1, "migration_thread() on CPU %d, expected %d\n", badcpu, cpu);
-                }
-                local_irq_enable();
-
-                complete(&req->done);
-        }
-        __set_current_state(TASK_RUNNING);
-
-        return 0;
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-
-static int __migrate_task_irq(struct task_struct *p, int src_cpu, int dest_cpu)
-{
-        int ret;
+        struct migration_arg *arg = data;
 
+        /*
+         * The original target cpu might have gone down and we might
+         * be on another cpu but it doesn't matter.
+         */
         local_irq_disable();
-        ret = __migrate_task(p, src_cpu, dest_cpu);
+        __migrate_task(arg->task, raw_smp_processor_id(), arg->dest_cpu);
         local_irq_enable();
-        return ret;
+        return 0;
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
 /*
  * Figure out where task on dead CPU should go, use force if necessary.
  */
-static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
+void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
 {
-        int dest_cpu;
+        struct rq *rq = cpu_rq(dead_cpu);
+        int needs_cpu, uninitialized_var(dest_cpu);
+        unsigned long flags;
 
-again:
-        dest_cpu = select_fallback_rq(dead_cpu, p);
+        local_irq_save(flags);
 
-        /* It can have affinity changed while we were choosing. */
-        if (unlikely(!__migrate_task_irq(p, dead_cpu, dest_cpu)))
-                goto again;
+        raw_spin_lock(&rq->lock);
+        needs_cpu = (task_cpu(p) == dead_cpu) && (p->state != TASK_WAKING);
+        if (needs_cpu)
+                dest_cpu = select_fallback_rq(dead_cpu, p);
+        raw_spin_unlock(&rq->lock);
+        /*
+         * It can only fail if we race with set_cpus_allowed(),
+         * in the racer should migrate the task anyway.
+         */
+        if (needs_cpu)
+                __migrate_task(p, dead_cpu, dest_cpu);
+        local_irq_restore(flags);
 }
 
 /*
@@ -5570,7 +5467,6 @@ void sched_idle_next(void)
 
         __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
 
-        update_rq_clock(rq);
         activate_task(rq, p, 0);
 
         raw_spin_unlock_irqrestore(&rq->lock, flags);
@@ -5625,7 +5521,6 @@ static void migrate_dead_tasks(unsigned int dead_cpu)
         for ( ; ; ) {
                 if (!rq->nr_running)
                         break;
-                update_rq_clock(rq);
                 next = pick_next_task(rq);
                 if (!next)
                         break;
@@ -5848,35 +5743,20 @@ static void set_rq_offline(struct rq *rq)
 static int __cpuinit
 migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
-        struct task_struct *p;
         int cpu = (long)hcpu;
         unsigned long flags;
-        struct rq *rq;
+        struct rq *rq = cpu_rq(cpu);
 
         switch (action) {
 
         case CPU_UP_PREPARE:
         case CPU_UP_PREPARE_FROZEN:
-                p = kthread_create(migration_thread, hcpu, "migration/%d", cpu);
-                if (IS_ERR(p))
-                        return NOTIFY_BAD;
-                kthread_bind(p, cpu);
-                /* Must be high prio: stop_machine expects to yield to it. */
-                rq = task_rq_lock(p, &flags);
-                __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
-                task_rq_unlock(rq, &flags);
-                get_task_struct(p);
-                cpu_rq(cpu)->migration_thread = p;
                 rq->calc_load_update = calc_load_update;
                 break;
 
         case CPU_ONLINE:
         case CPU_ONLINE_FROZEN:
-                /* Strictly unnecessary, as first user will wake it. */
-                wake_up_process(cpu_rq(cpu)->migration_thread);
-
                 /* Update our root-domain */
-                rq = cpu_rq(cpu);
                 raw_spin_lock_irqsave(&rq->lock, flags);
                 if (rq->rd) {
                         BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
@@ -5887,61 +5767,24 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
                 break;
 
 #ifdef CONFIG_HOTPLUG_CPU
-        case CPU_UP_CANCELED:
-        case CPU_UP_CANCELED_FROZEN:
-                if (!cpu_rq(cpu)->migration_thread)
-                        break;
-                /* Unbind it from offline cpu so it can run. Fall thru. */
-                kthread_bind(cpu_rq(cpu)->migration_thread,
-                             cpumask_any(cpu_online_mask));
-                kthread_stop(cpu_rq(cpu)->migration_thread);
-                put_task_struct(cpu_rq(cpu)->migration_thread);
-                cpu_rq(cpu)->migration_thread = NULL;
-                break;
-
         case CPU_DEAD:
         case CPU_DEAD_FROZEN:
-                cpuset_lock(); /* around calls to cpuset_cpus_allowed_lock() */
                 migrate_live_tasks(cpu);
-                rq = cpu_rq(cpu);
-                kthread_stop(rq->migration_thread);
-                put_task_struct(rq->migration_thread);
-                rq->migration_thread = NULL;
                 /* Idle task back to normal (off runqueue, low prio) */
                 raw_spin_lock_irq(&rq->lock);
-                update_rq_clock(rq);
                 deactivate_task(rq, rq->idle, 0);
                 __setscheduler(rq, rq->idle, SCHED_NORMAL, 0);
                 rq->idle->sched_class = &idle_sched_class;
                 migrate_dead_tasks(cpu);
                 raw_spin_unlock_irq(&rq->lock);
-                cpuset_unlock();
                 migrate_nr_uninterruptible(rq);
                 BUG_ON(rq->nr_running != 0);
                 calc_global_load_remove(rq);
-                /*
-                 * No need to migrate the tasks: it was best-effort if
-                 * they didn't take sched_hotcpu_mutex. Just wake up
-                 * the requestors.
-                 */
-                raw_spin_lock_irq(&rq->lock);
-                while (!list_empty(&rq->migration_queue)) {
-                        struct migration_req *req;
-
-                        req = list_entry(rq->migration_queue.next,
-                                         struct migration_req, list);
-                        list_del_init(&req->list);
-                        raw_spin_unlock_irq(&rq->lock);
-                        complete(&req->done);
-                        raw_spin_lock_irq(&rq->lock);
-                }
-                raw_spin_unlock_irq(&rq->lock);
                 break;
 
         case CPU_DYING:
         case CPU_DYING_FROZEN:
                 /* Update our root-domain */
-                rq = cpu_rq(cpu);
                 raw_spin_lock_irqsave(&rq->lock, flags);
                 if (rq->rd) {
                         BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
@@ -6272,6 +6115,9 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
         struct rq *rq = cpu_rq(cpu);
         struct sched_domain *tmp;
 
+        for (tmp = sd; tmp; tmp = tmp->parent)
+                tmp->span_weight = cpumask_weight(sched_domain_span(tmp));
+
         /* Remove the sched domains which do not contribute to scheduling. */
         for (tmp = sd; tmp; ) {
                 struct sched_domain *parent = tmp->parent;
@@ -7755,10 +7601,8 @@ void __init sched_init(void)
                 rq->push_cpu = 0;
                 rq->cpu = i;
                 rq->online = 0;
-                rq->migration_thread = NULL;
                 rq->idle_stamp = 0;
                 rq->avg_idle = 2*sysctl_sched_migration_cost;
-                INIT_LIST_HEAD(&rq->migration_queue);
                 rq_attach_root(rq, &def_root_domain);
 #endif
                 init_rq_hrtick(rq);
@@ -7859,7 +7703,6 @@ 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)
                 deactivate_task(rq, p, 0);
@@ -7886,9 +7729,9 @@ void normalize_rt_tasks(void)
 
                 p->se.exec_start                = 0;
 #ifdef CONFIG_SCHEDSTATS
-                p->se.wait_start                = 0;
-                p->se.sleep_start               = 0;
-                p->se.block_start               = 0;
+                p->se.statistics.wait_start     = 0;
+                p->se.statistics.sleep_start    = 0;
+                p->se.statistics.block_start    = 0;
 #endif
 
                 if (!rt_task(p)) {
@@ -8221,8 +8064,6 @@ void sched_move_task(struct task_struct *tsk)
 
         rq = task_rq_lock(tsk, &flags);
 
-        update_rq_clock(rq);
-
         running = task_current(rq, tsk);
         on_rq = tsk->se.on_rq;
 
@@ -8241,7 +8082,7 @@ void sched_move_task(struct task_struct *tsk)
         if (unlikely(running))
                 tsk->sched_class->set_curr_task(rq);
         if (on_rq)
-                enqueue_task(rq, tsk, 0, false);
+                enqueue_task(rq, tsk, 0);
 
         task_rq_unlock(rq, &flags);
 }
@@ -9055,43 +8896,32 @@ struct cgroup_subsys cpuacct_subsys = {
 
 #ifndef CONFIG_SMP
 
-int rcu_expedited_torture_stats(char *page)
-{
-        return 0;
-}
-EXPORT_SYMBOL_GPL(rcu_expedited_torture_stats);
-
 void synchronize_sched_expedited(void)
 {
+        barrier();
 }
 EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
 
 #else /* #ifndef CONFIG_SMP */
 
-static DEFINE_PER_CPU(struct migration_req, rcu_migration_req);
-static DEFINE_MUTEX(rcu_sched_expedited_mutex);
-
-#define RCU_EXPEDITED_STATE_POST -2
-#define RCU_EXPEDITED_STATE_IDLE -1
-
-static int rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
+static atomic_t synchronize_sched_expedited_count = ATOMIC_INIT(0);
 
-int rcu_expedited_torture_stats(char *page)
+static int synchronize_sched_expedited_cpu_stop(void *data)
 {
-        int cnt = 0;
-        int cpu;
-
-        cnt += sprintf(&page[cnt], "state: %d /", rcu_expedited_state);
-        for_each_online_cpu(cpu) {
-                 cnt += sprintf(&page[cnt], " %d:%d",
-                                cpu, per_cpu(rcu_migration_req, cpu).dest_cpu);
-        }
-        cnt += sprintf(&page[cnt], "\n");
-        return cnt;
+        /*
+         * There must be a full memory barrier on each affected CPU
+         * between the time that try_stop_cpus() is called and the
+         * time that it returns.
+         *
+         * In the current initial implementation of cpu_stop, the
+         * above condition is already met when the control reaches
+         * this point and the following smp_mb() is not strictly
+         * necessary.  Do smp_mb() anyway for documentation and
+         * robustness against future implementation changes.
+         */
+        smp_mb(); /* See above comment block. */
+        return 0;
 }
-EXPORT_SYMBOL_GPL(rcu_expedited_torture_stats);
-
-static long synchronize_sched_expedited_count;
 
 /*
  * Wait for an rcu-sched grace period to elapse, but use "big hammer"
@@ -9105,18 +8935,14 @@ static long synchronize_sched_expedited_count;
  */
 void synchronize_sched_expedited(void)
 {
-        int cpu;
-        unsigned long flags;
-        bool need_full_sync = 0;
-        struct rq *rq;
-        struct migration_req *req;
-        long snap;
-        int trycount = 0;
+        int snap, trycount = 0;
 
         smp_mb();  /* ensure prior mod happens before capturing snap. */
-        snap = ACCESS_ONCE(synchronize_sched_expedited_count) + 1;
+        snap = atomic_read(&synchronize_sched_expedited_count) + 1;
         get_online_cpus();
-        while (!mutex_trylock(&rcu_sched_expedited_mutex)) {
+        while (try_stop_cpus(cpu_online_mask,
+                             synchronize_sched_expedited_cpu_stop,
+                             NULL) == -EAGAIN) {
                 put_online_cpus();
                 if (trycount++ < 10)
                         udelay(trycount * num_online_cpus());
@@ -9124,41 +8950,15 @@ void synchronize_sched_expedited(void)
                         synchronize_sched();
                         return;
                 }
-                if (ACCESS_ONCE(synchronize_sched_expedited_count) - snap > 0) {
+                if (atomic_read(&synchronize_sched_expedited_count) - snap > 0) {
                         smp_mb(); /* ensure test happens before caller kfree */
                         return;
                 }
                 get_online_cpus();
         }
-        rcu_expedited_state = RCU_EXPEDITED_STATE_POST;
-        for_each_online_cpu(cpu) {
-                rq = cpu_rq(cpu);
-                req = &per_cpu(rcu_migration_req, cpu);
-                init_completion(&req->done);
-                req->task = NULL;
-                req->dest_cpu = RCU_MIGRATION_NEED_QS;
-                raw_spin_lock_irqsave(&rq->lock, flags);
-                list_add(&req->list, &rq->migration_queue);
-                raw_spin_unlock_irqrestore(&rq->lock, flags);
-                wake_up_process(rq->migration_thread);
-        }
-        for_each_online_cpu(cpu) {
-                rcu_expedited_state = cpu;
-                req = &per_cpu(rcu_migration_req, cpu);
-                rq = cpu_rq(cpu);
-                wait_for_completion(&req->done);
-                raw_spin_lock_irqsave(&rq->lock, flags);
-                if (unlikely(req->dest_cpu == RCU_MIGRATION_MUST_SYNC))
-                        need_full_sync = 1;
-                req->dest_cpu = RCU_MIGRATION_IDLE;
-                raw_spin_unlock_irqrestore(&rq->lock, flags);
-        }
-        rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
-        synchronize_sched_expedited_count++;
-        mutex_unlock(&rcu_sched_expedited_mutex);
+        atomic_inc(&synchronize_sched_expedited_count);
+        smp_mb__after_atomic_inc(); /* ensure post-GP actions seen after GP. */
         put_online_cpus();
-        if (need_full_sync)
-                synchronize_sched();
 }
 EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
 
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 9b49db144037..9cf1baf6616a 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -70,16 +70,16 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu,
         PN(se->vruntime);
         PN(se->sum_exec_runtime);
 #ifdef CONFIG_SCHEDSTATS
-        PN(se->wait_start);
-        PN(se->sleep_start);
-        PN(se->block_start);
-        PN(se->sleep_max);
-        PN(se->block_max);
-        PN(se->exec_max);
-        PN(se->slice_max);
-        PN(se->wait_max);
-        PN(se->wait_sum);
-        P(se->wait_count);
+        PN(se->statistics.wait_start);
+        PN(se->statistics.sleep_start);
+        PN(se->statistics.block_start);
+        PN(se->statistics.sleep_max);
+        PN(se->statistics.block_max);
+        PN(se->statistics.exec_max);
+        PN(se->statistics.slice_max);
+        PN(se->statistics.wait_max);
+        PN(se->statistics.wait_sum);
+        P(se->statistics.wait_count);
 #endif
         P(se->load.weight);
 #undef PN
@@ -104,7 +104,7 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
         SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
                 SPLIT_NS(p->se.vruntime),
                 SPLIT_NS(p->se.sum_exec_runtime),
-                SPLIT_NS(p->se.sum_sleep_runtime));
+                SPLIT_NS(p->se.statistics.sum_sleep_runtime));
 #else
         SEQ_printf(m, "%15Ld %15Ld %15Ld.%06ld %15Ld.%06ld %15Ld.%06ld",
                 0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L);
@@ -173,11 +173,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
         task_group_path(tg, path, sizeof(path));
 
         SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path);
-#elif defined(CONFIG_USER_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED)
-        {
-                uid_t uid = cfs_rq->tg->uid;
-                SEQ_printf(m, "\ncfs_rq[%d] for UID: %u\n", cpu, uid);
-        }
 #else
         SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu);
 #endif
@@ -407,40 +402,38 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
         PN(se.exec_start);
         PN(se.vruntime);
         PN(se.sum_exec_runtime);
-        PN(se.avg_overlap);
-        PN(se.avg_wakeup);
 
         nr_switches = p->nvcsw + p->nivcsw;
 
 #ifdef CONFIG_SCHEDSTATS
-        PN(se.wait_start);
-        PN(se.sleep_start);
-        PN(se.block_start);
-        PN(se.sleep_max);
-        PN(se.block_max);
-        PN(se.exec_max);
-        PN(se.slice_max);
-        PN(se.wait_max);
-        PN(se.wait_sum);
-        P(se.wait_count);
-        PN(se.iowait_sum);
-        P(se.iowait_count);
+        PN(se.statistics.wait_start);
+        PN(se.statistics.sleep_start);
+        PN(se.statistics.block_start);
+        PN(se.statistics.sleep_max);
+        PN(se.statistics.block_max);
+        PN(se.statistics.exec_max);
+        PN(se.statistics.slice_max);
+        PN(se.statistics.wait_max);
+        PN(se.statistics.wait_sum);
+        P(se.statistics.wait_count);
+        PN(se.statistics.iowait_sum);
+        P(se.statistics.iowait_count);
         P(sched_info.bkl_count);
         P(se.nr_migrations);
-        P(se.nr_migrations_cold);
-        P(se.nr_failed_migrations_affine);
-        P(se.nr_failed_migrations_running);
-        P(se.nr_failed_migrations_hot);
-        P(se.nr_forced_migrations);
-        P(se.nr_wakeups);
-        P(se.nr_wakeups_sync);
-        P(se.nr_wakeups_migrate);
-        P(se.nr_wakeups_local);
-        P(se.nr_wakeups_remote);
-        P(se.nr_wakeups_affine);
-        P(se.nr_wakeups_affine_attempts);
-        P(se.nr_wakeups_passive);
-        P(se.nr_wakeups_idle);
+        P(se.statistics.nr_migrations_cold);
+        P(se.statistics.nr_failed_migrations_affine);
+        P(se.statistics.nr_failed_migrations_running);
+        P(se.statistics.nr_failed_migrations_hot);
+        P(se.statistics.nr_forced_migrations);
+        P(se.statistics.nr_wakeups);
+        P(se.statistics.nr_wakeups_sync);
+        P(se.statistics.nr_wakeups_migrate);
+        P(se.statistics.nr_wakeups_local);
+        P(se.statistics.nr_wakeups_remote);
+        P(se.statistics.nr_wakeups_affine);
+        P(se.statistics.nr_wakeups_affine_attempts);
+        P(se.statistics.nr_wakeups_passive);
+        P(se.statistics.nr_wakeups_idle);
 
         {
                 u64 avg_atom, avg_per_cpu;
@@ -491,31 +484,6 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 void proc_sched_set_task(struct task_struct *p)
 {
 #ifdef CONFIG_SCHEDSTATS
-        p->se.wait_max                          = 0;
-        p->se.wait_sum                          = 0;
-        p->se.wait_count                        = 0;
-        p->se.iowait_sum                        = 0;
-        p->se.iowait_count                      = 0;
-        p->se.sleep_max                         = 0;
-        p->se.sum_sleep_runtime                 = 0;
-        p->se.block_max                         = 0;
-        p->se.exec_max                          = 0;
-        p->se.slice_max                         = 0;
-        p->se.nr_migrations                     = 0;
-        p->se.nr_migrations_cold                = 0;
-        p->se.nr_failed_migrations_affine       = 0;
-        p->se.nr_failed_migrations_running      = 0;
-        p->se.nr_failed_migrations_hot          = 0;
-        p->se.nr_forced_migrations              = 0;
-        p->se.nr_wakeups                        = 0;
-        p->se.nr_wakeups_sync                   = 0;
-        p->se.nr_wakeups_migrate                = 0;
-        p->se.nr_wakeups_local                  = 0;
-        p->se.nr_wakeups_remote                 = 0;
-        p->se.nr_wakeups_affine                 = 0;
-        p->se.nr_wakeups_affine_attempts        = 0;
-        p->se.nr_wakeups_passive                = 0;
-        p->se.nr_wakeups_idle                   = 0;
-        p->sched_info.bkl_count                 = 0;
+        memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
 }
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 5a5ea2cd924f..217e4a9393e4 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -35,8 +35,8 @@
  * (to see the precise effective timeslice length of your workload,
  *  run vmstat and monitor the context-switches (cs) field)
  */
-unsigned int sysctl_sched_latency = 5000000ULL;
-unsigned int normalized_sysctl_sched_latency = 5000000ULL;
+unsigned int sysctl_sched_latency = 6000000ULL;
+unsigned int normalized_sysctl_sched_latency = 6000000ULL;
 
 /*
  * The initial- and re-scaling of tunables is configurable
@@ -52,15 +52,15 @@ enum sched_tunable_scaling sysctl_sched_tunable_scaling
 
 /*
  * Minimal preemption granularity for CPU-bound tasks:
- * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 2 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
-unsigned int sysctl_sched_min_granularity = 1000000ULL;
-unsigned int normalized_sysctl_sched_min_granularity = 1000000ULL;
+unsigned int sysctl_sched_min_granularity = 2000000ULL;
+unsigned int normalized_sysctl_sched_min_granularity = 2000000ULL;
 
 /*
  * is kept at sysctl_sched_latency / sysctl_sched_min_granularity
  */
-static unsigned int sched_nr_latency = 5;
+static unsigned int sched_nr_latency = 3;
 
 /*
  * After fork, child runs first. If set to 0 (default) then
@@ -505,7 +505,8 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 {
         unsigned long delta_exec_weighted;
 
-        schedstat_set(curr->exec_max, max((u64)delta_exec, curr->exec_max));
+        schedstat_set(curr->statistics.exec_max,
+                      max((u64)delta_exec, curr->statistics.exec_max));
 
         curr->sum_exec_runtime += delta_exec;
         schedstat_add(cfs_rq, exec_clock, delta_exec);
@@ -548,7 +549,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
 static inline void
 update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-        schedstat_set(se->wait_start, rq_of(cfs_rq)->clock);
+        schedstat_set(se->statistics.wait_start, rq_of(cfs_rq)->clock);
 }
 
 /*
@@ -567,18 +568,18 @@ static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static void
 update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-        schedstat_set(se->wait_max, max(se->wait_max,
-                        rq_of(cfs_rq)->clock - se->wait_start));
-        schedstat_set(se->wait_count, se->wait_count + 1);
-        schedstat_set(se->wait_sum, se->wait_sum +
-                        rq_of(cfs_rq)->clock - se->wait_start);
+        schedstat_set(se->statistics.wait_max, max(se->statistics.wait_max,
+                        rq_of(cfs_rq)->clock - se->statistics.wait_start));
+        schedstat_set(se->statistics.wait_count, se->statistics.wait_count + 1);
+        schedstat_set(se->statistics.wait_sum, se->statistics.wait_sum +
+                        rq_of(cfs_rq)->clock - se->statistics.wait_start);
 #ifdef CONFIG_SCHEDSTATS
         if (entity_is_task(se)) {
                 trace_sched_stat_wait(task_of(se),
-                        rq_of(cfs_rq)->clock - se->wait_start);
+                        rq_of(cfs_rq)->clock - se->statistics.wait_start);
         }
 #endif
-        schedstat_set(se->wait_start, 0);
+        schedstat_set(se->statistics.wait_start, 0);
 }
 
 static inline void
@@ -657,39 +658,39 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
         if (entity_is_task(se))
                 tsk = task_of(se);
 
-        if (se->sleep_start) {
-                u64 delta = rq_of(cfs_rq)->clock - se->sleep_start;
+        if (se->statistics.sleep_start) {
+                u64 delta = rq_of(cfs_rq)->clock - se->statistics.sleep_start;
 
                 if ((s64)delta < 0)
                         delta = 0;
 
-                if (unlikely(delta > se->sleep_max))
-                        se->sleep_max = delta;
+                if (unlikely(delta > se->statistics.sleep_max))
+                        se->statistics.sleep_max = delta;
 
-                se->sleep_start = 0;
-                se->sum_sleep_runtime += delta;
+                se->statistics.sleep_start = 0;
+                se->statistics.sum_sleep_runtime += delta;
 
                 if (tsk) {
                         account_scheduler_latency(tsk, delta >> 10, 1);
                         trace_sched_stat_sleep(tsk, delta);
                 }
         }
-        if (se->block_start) {
-                u64 delta = rq_of(cfs_rq)->clock - se->block_start;
+        if (se->statistics.block_start) {
+                u64 delta = rq_of(cfs_rq)->clock - se->statistics.block_start;
 
                 if ((s64)delta < 0)
                         delta = 0;
 
-                if (unlikely(delta > se->block_max))
-                        se->block_max = delta;
+                if (unlikely(delta > se->statistics.block_max))
+                        se->statistics.block_max = delta;
 
-                se->block_start = 0;
-                se->sum_sleep_runtime += delta;
+                se->statistics.block_start = 0;
+                se->statistics.sum_sleep_runtime += delta;
 
                 if (tsk) {
                         if (tsk->in_iowait) {
-                                se->iowait_sum += delta;
-                                se->iowait_count++;
+                                se->statistics.iowait_sum += delta;
+                                se->statistics.iowait_count++;
                                 trace_sched_stat_iowait(tsk, delta);
                         }
 
@@ -737,20 +738,10 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
                 vruntime += sched_vslice(cfs_rq, se);
 
         /* sleeps up to a single latency don't count. */
-        if (!initial && sched_feat(FAIR_SLEEPERS)) {
+        if (!initial) {
                 unsigned long thresh = sysctl_sched_latency;
 
                 /*
-                 * Convert the sleeper threshold into virtual time.
-                 * SCHED_IDLE is a special sub-class.  We care about
-                 * fairness only relative to other SCHED_IDLE tasks,
-                 * all of which have the same weight.
-                 */
-                if (sched_feat(NORMALIZED_SLEEPER) && (!entity_is_task(se) ||
-                                 task_of(se)->policy != SCHED_IDLE))
-                        thresh = calc_delta_fair(thresh, se);
-
-                /*
                  * Halve their sleep time's effect, to allow
                  * for a gentler effect of sleepers:
                  */
@@ -766,9 +757,6 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
         se->vruntime = vruntime;
 }
 
-#define ENQUEUE_WAKEUP  1
-#define ENQUEUE_MIGRATE 2
-
 static void
 enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
@@ -776,7 +764,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
          * Update the normalized vruntime before updating min_vruntime
          * through callig update_curr().
          */
-        if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_MIGRATE))
+        if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING))
                 se->vruntime += cfs_rq->min_vruntime;
 
         /*
@@ -812,7 +800,7 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 }
 
 static void
-dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
+dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
         /*
          * Update run-time statistics of the 'current'.
@@ -820,15 +808,15 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
         update_curr(cfs_rq);
 
         update_stats_dequeue(cfs_rq, se);
-        if (sleep) {
+        if (flags & DEQUEUE_SLEEP) {
 #ifdef CONFIG_SCHEDSTATS
                 if (entity_is_task(se)) {
                         struct task_struct *tsk = task_of(se);
 
                         if (tsk->state & TASK_INTERRUPTIBLE)
-                                se->sleep_start = rq_of(cfs_rq)->clock;
+                                se->statistics.sleep_start = rq_of(cfs_rq)->clock;
                         if (tsk->state & TASK_UNINTERRUPTIBLE)
-                                se->block_start = rq_of(cfs_rq)->clock;
+                                se->statistics.block_start = rq_of(cfs_rq)->clock;
                 }
 #endif
         }
@@ -845,7 +833,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
          * update can refer to the ->curr item and we need to reflect this
          * movement in our normalized position.
          */
-        if (!sleep)
+        if (!(flags & DEQUEUE_SLEEP))
                 se->vruntime -= cfs_rq->min_vruntime;
 }
 
@@ -912,7 +900,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
          * when there are only lesser-weight tasks around):
          */
         if (rq_of(cfs_rq)->load.weight >= 2*se->load.weight) {
-                se->slice_max = max(se->slice_max,
+                se->statistics.slice_max = max(se->statistics.slice_max,
                         se->sum_exec_runtime - se->prev_sum_exec_runtime);
         }
 #endif
@@ -1054,16 +1042,10 @@ static inline void hrtick_update(struct rq *rq)
  * then put the task into the rbtree:
  */
 static void
-enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup, bool head)
+enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
         struct cfs_rq *cfs_rq;
         struct sched_entity *se = &p->se;
-        int flags = 0;
-
-        if (wakeup)
-                flags |= ENQUEUE_WAKEUP;
-        if (p->state == TASK_WAKING)
-                flags |= ENQUEUE_MIGRATE;
 
         for_each_sched_entity(se) {
                 if (se->on_rq)
@@ -1081,18 +1063,18 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup, bool head)
  * decreased. We remove the task from the rbtree and
  * update the fair scheduling stats:
  */
-static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
+static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
         struct cfs_rq *cfs_rq;
         struct sched_entity *se = &p->se;
 
         for_each_sched_entity(se) {
                 cfs_rq = cfs_rq_of(se);
-                dequeue_entity(cfs_rq, se, sleep);
+                dequeue_entity(cfs_rq, se, flags);
                 /* Don't dequeue parent if it has other entities besides us */
                 if (cfs_rq->load.weight)
                         break;
-                sleep = 1;
+                flags |= DEQUEUE_SLEEP;
         }
 
         hrtick_update(rq);
@@ -1240,7 +1222,6 @@ static inline unsigned long effective_load(struct task_group *tg, int cpu,
 
 static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 {
-        struct task_struct *curr = current;
         unsigned long this_load, load;
         int idx, this_cpu, prev_cpu;
         unsigned long tl_per_task;
@@ -1255,18 +1236,6 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
         load      = source_load(prev_cpu, idx);
         this_load = target_load(this_cpu, idx);
 
-        if (sync) {
-               if (sched_feat(SYNC_LESS) &&
-                   (curr->se.avg_overlap > sysctl_sched_migration_cost ||
-                    p->se.avg_overlap > sysctl_sched_migration_cost))
-                       sync = 0;
-        } else {
-                if (sched_feat(SYNC_MORE) &&
-                    (curr->se.avg_overlap < sysctl_sched_migration_cost &&
-                     p->se.avg_overlap < sysctl_sched_migration_cost))
-                        sync = 1;
-        }
-
         /*
          * If sync wakeup then subtract the (maximum possible)
          * effect of the currently running task from the load
@@ -1306,7 +1275,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
         if (sync && balanced)
                 return 1;
 
-        schedstat_inc(p, se.nr_wakeups_affine_attempts);
+        schedstat_inc(p, se.statistics.nr_wakeups_affine_attempts);
         tl_per_task = cpu_avg_load_per_task(this_cpu);
 
         if (balanced ||
@@ -1318,7 +1287,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
                  * there is no bad imbalance.
                  */
                 schedstat_inc(sd, ttwu_move_affine);
-                schedstat_inc(p, se.nr_wakeups_affine);
+                schedstat_inc(p, se.statistics.nr_wakeups_affine);
 
                 return 1;
         }
@@ -1406,29 +1375,48 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 /*
  * Try and locate an idle CPU in the sched_domain.
  */
-static int
-select_idle_sibling(struct task_struct *p, struct sched_domain *sd, int target)
+static int select_idle_sibling(struct task_struct *p, int target)
 {
         int cpu = smp_processor_id();
         int prev_cpu = task_cpu(p);
+        struct sched_domain *sd;
         int i;
 
         /*
-         * If this domain spans both cpu and prev_cpu (see the SD_WAKE_AFFINE
-         * test in select_task_rq_fair) and the prev_cpu is idle then that's
-         * always a better target than the current cpu.
+         * If the task is going to be woken-up on this cpu and if it is
+         * already idle, then it is the right target.
          */
-        if (target == cpu && !cpu_rq(prev_cpu)->cfs.nr_running)
+        if (target == cpu && idle_cpu(cpu))
+                return cpu;
+
+        /*
+         * If the task is going to be woken-up on the cpu where it previously
+         * ran and if it is currently idle, then it the right target.
+         */
+        if (target == prev_cpu && idle_cpu(prev_cpu))
                 return prev_cpu;
 
         /*
-         * Otherwise, iterate the domain and find an elegible idle cpu.
+         * Otherwise, iterate the domains and find an elegible idle cpu.
          */
-        for_each_cpu_and(i, sched_domain_span(sd), &p->cpus_allowed) {
-                if (!cpu_rq(i)->cfs.nr_running) {
-                        target = i;
+        for_each_domain(target, sd) {
+                if (!(sd->flags & SD_SHARE_PKG_RESOURCES))
                         break;
+
+                for_each_cpu_and(i, sched_domain_span(sd), &p->cpus_allowed) {
+                        if (idle_cpu(i)) {
+                                target = i;
+                                break;
+                        }
                 }
+
+                /*
+                 * Lets stop looking for an idle sibling when we reached
+                 * the domain that spans the current cpu and prev_cpu.
+                 */
+                if (cpumask_test_cpu(cpu, sched_domain_span(sd)) &&
+                    cpumask_test_cpu(prev_cpu, sched_domain_span(sd)))
+                        break;
         }
 
         return target;
@@ -1445,7 +1433,8 @@ select_idle_sibling(struct task_struct *p, struct sched_domain *sd, int target)
  *
  * preempt must be disabled.
  */
-static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
+static int
+select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_flags)
 {
         struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
         int cpu = smp_processor_id();
@@ -1456,8 +1445,7 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
         int sync = wake_flags & WF_SYNC;
 
         if (sd_flag & SD_BALANCE_WAKE) {
-                if (sched_feat(AFFINE_WAKEUPS) &&
-                    cpumask_test_cpu(cpu, &p->cpus_allowed))
+                if (cpumask_test_cpu(cpu, &p->cpus_allowed))
                         want_affine = 1;
                 new_cpu = prev_cpu;
         }
@@ -1491,34 +1479,13 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
                 }
 
                 /*
-                 * While iterating the domains looking for a spanning
-                 * WAKE_AFFINE domain, adjust the affine target to any idle cpu
-                 * in cache sharing domains along the way.
+                 * If both cpu and prev_cpu are part of this domain,
+                 * cpu is a valid SD_WAKE_AFFINE target.
                  */
-                if (want_affine) {
-                        int target = -1;
-
-                        /*
-                         * If both cpu and prev_cpu are part of this domain,
-                         * cpu is a valid SD_WAKE_AFFINE target.
-                         */
-                        if (cpumask_test_cpu(prev_cpu, sched_domain_span(tmp)))
-                                target = cpu;
-
-                        /*
-                         * If there's an idle sibling in this domain, make that
-                         * the wake_affine target instead of the current cpu.
-                         */
-                        if (tmp->flags & SD_SHARE_PKG_RESOURCES)
-                                target = select_idle_sibling(p, tmp, target);
-
-                        if (target >= 0) {
-                                if (tmp->flags & SD_WAKE_AFFINE) {
-                                        affine_sd = tmp;
-                                        want_affine = 0;
-                                }
-                                cpu = target;
-                        }
+                if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
+                    cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
+                        affine_sd = tmp;
+                        want_affine = 0;
                 }
 
                 if (!want_sd && !want_affine)
@@ -1531,22 +1498,29 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
                         sd = tmp;
         }
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
         if (sched_feat(LB_SHARES_UPDATE)) {
                 /*
                  * Pick the largest domain to update shares over
                  */
                 tmp = sd;
-                if (affine_sd && (!tmp ||
-                                  cpumask_weight(sched_domain_span(affine_sd)) >
-                                  cpumask_weight(sched_domain_span(sd))))
+                if (affine_sd && (!tmp || affine_sd->span_weight > sd->span_weight))
                         tmp = affine_sd;
 
-                if (tmp)
+                if (tmp) {
+                        raw_spin_unlock(&rq->lock);
                         update_shares(tmp);
+                        raw_spin_lock(&rq->lock);
+                }
         }
+#endif
 
-        if (affine_sd && wake_affine(affine_sd, p, sync))
-                return cpu;
+        if (affine_sd) {
+                if (cpu == prev_cpu || wake_affine(affine_sd, p, sync))
+                        return select_idle_sibling(p, cpu);
+                else
+                        return select_idle_sibling(p, prev_cpu);
+        }
 
         while (sd) {
                 int load_idx = sd->forkexec_idx;
@@ -1576,10 +1550,10 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 
                 /* Now try balancing at a lower domain level of new_cpu */
                 cpu = new_cpu;
-                weight = cpumask_weight(sched_domain_span(sd));
+                weight = sd->span_weight;
                 sd = NULL;
                 for_each_domain(cpu, tmp) {
-                        if (weight <= cpumask_weight(sched_domain_span(tmp)))
+                        if (weight <= tmp->span_weight)
                                 break;
                         if (tmp->flags & sd_flag)
                                 sd = tmp;
@@ -1591,63 +1565,26 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 }
 #endif /* CONFIG_SMP */
 
-/*
- * Adaptive granularity
- *
- * se->avg_wakeup gives the average time a task runs until it does a wakeup,
- * with the limit of wakeup_gran -- when it never does a wakeup.
- *
- * So the smaller avg_wakeup is the faster we want this task to preempt,
- * but we don't want to treat the preemptee unfairly and therefore allow it
- * to run for at least the amount of time we'd like to run.
- *
- * NOTE: we use 2*avg_wakeup to increase the probability of actually doing one
- *
- * NOTE: we use *nr_running to scale with load, this nicely matches the
- *       degrading latency on load.
- */
-static unsigned long
-adaptive_gran(struct sched_entity *curr, struct sched_entity *se)
-{
-        u64 this_run = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
-        u64 expected_wakeup = 2*se->avg_wakeup * cfs_rq_of(se)->nr_running;
-        u64 gran = 0;
-
-        if (this_run < expected_wakeup)
-                gran = expected_wakeup - this_run;
-
-        return min_t(s64, gran, sysctl_sched_wakeup_granularity);
-}
-
 static unsigned long
 wakeup_gran(struct sched_entity *curr, struct sched_entity *se)
 {
         unsigned long gran = sysctl_sched_wakeup_granularity;
 
-        if (cfs_rq_of(curr)->curr && sched_feat(ADAPTIVE_GRAN))
-                gran = adaptive_gran(curr, se);
-
         /*
          * Since its curr running now, convert the gran from real-time
          * to virtual-time in his units.
+         *
+         * By using 'se' instead of 'curr' we penalize light tasks, so
+         * they get preempted easier. That is, if 'se' < 'curr' then
+         * the resulting gran will be larger, therefore penalizing the
+         * lighter, if otoh 'se' > 'curr' then the resulting gran will
+         * be smaller, again penalizing the lighter task.
+         *
+         * This is especially important for buddies when the leftmost
+         * task is higher priority than the buddy.
          */
-        if (sched_feat(ASYM_GRAN)) {
-                /*
-                 * By using 'se' instead of 'curr' we penalize light tasks, so
-                 * they get preempted easier. That is, if 'se' < 'curr' then
-                 * the resulting gran will be larger, therefore penalizing the
-                 * lighter, if otoh 'se' > 'curr' then the resulting gran will
-                 * be smaller, again penalizing the lighter task.
-                 *
-                 * This is especially important for buddies when the leftmost
-                 * task is higher priority than the buddy.
-                 */
-                if (unlikely(se->load.weight != NICE_0_LOAD))
-                        gran = calc_delta_fair(gran, se);
-        } else {
-                if (unlikely(curr->load.weight != NICE_0_LOAD))
-                        gran = calc_delta_fair(gran, curr);
-        }
+        if (unlikely(se->load.weight != NICE_0_LOAD))
+                gran = calc_delta_fair(gran, se);
 
         return gran;
 }
@@ -1705,7 +1642,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
         struct task_struct *curr = rq->curr;
         struct sched_entity *se = &curr->se, *pse = &p->se;
         struct cfs_rq *cfs_rq = task_cfs_rq(curr);
-        int sync = wake_flags & WF_SYNC;
         int scale = cfs_rq->nr_running >= sched_nr_latency;
 
         if (unlikely(rt_prio(p->prio)))
@@ -1738,14 +1674,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
         if (unlikely(curr->policy == SCHED_IDLE))
                 goto preempt;
 
-        if (sched_feat(WAKEUP_SYNC) && sync)
-                goto preempt;
-
-        if (sched_feat(WAKEUP_OVERLAP) &&
-                        se->avg_overlap < sysctl_sched_migration_cost &&
-                        pse->avg_overlap < sysctl_sched_migration_cost)
-                goto preempt;
-
         if (!sched_feat(WAKEUP_PREEMPT))
                 return;
 
@@ -1844,13 +1772,13 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
          * 3) are cache-hot on their current CPU.
          */
         if (!cpumask_test_cpu(this_cpu, &p->cpus_allowed)) {
-                schedstat_inc(p, se.nr_failed_migrations_affine);
+                schedstat_inc(p, se.statistics.nr_failed_migrations_affine);
                 return 0;
         }
         *all_pinned = 0;
 
         if (task_running(rq, p)) {
-                schedstat_inc(p, se.nr_failed_migrations_running);
+                schedstat_inc(p, se.statistics.nr_failed_migrations_running);
                 return 0;
         }
 
@@ -1866,14 +1794,14 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
 #ifdef CONFIG_SCHEDSTATS
                 if (tsk_cache_hot) {
                         schedstat_inc(sd, lb_hot_gained[idle]);
-                        schedstat_inc(p, se.nr_forced_migrations);
+                        schedstat_inc(p, se.statistics.nr_forced_migrations);
                 }
 #endif
                 return 1;
         }
 
         if (tsk_cache_hot) {
-                schedstat_inc(p, se.nr_failed_migrations_hot);
+                schedstat_inc(p, se.statistics.nr_failed_migrations_hot);
                 return 0;
         }
         return 1;
@@ -2311,7 +2239,7 @@ unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu)
 
 unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu)
 {
-        unsigned long weight = cpumask_weight(sched_domain_span(sd));
+        unsigned long weight = sd->span_weight;
         unsigned long smt_gain = sd->smt_gain;
 
         smt_gain /= weight;
@@ -2344,7 +2272,7 @@ unsigned long scale_rt_power(int cpu)
 
 static void update_cpu_power(struct sched_domain *sd, int cpu)
 {
-        unsigned long weight = cpumask_weight(sched_domain_span(sd));
+        unsigned long weight = sd->span_weight;
         unsigned long power = SCHED_LOAD_SCALE;
         struct sched_group *sdg = sd->groups;
 
@@ -2870,6 +2798,8 @@ static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle)
         return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2);
 }
 
+static int active_load_balance_cpu_stop(void *data);
+
 /*
  * Check this_cpu to ensure it is balanced within domain. Attempt to move
  * tasks if there is an imbalance.
@@ -2959,8 +2889,9 @@ redo:
                 if (need_active_balance(sd, sd_idle, idle)) {
                         raw_spin_lock_irqsave(&busiest->lock, flags);
 
-                        /* don't kick the migration_thread, if the curr
-                         * task on busiest cpu can't be moved to this_cpu
+                        /* don't kick the active_load_balance_cpu_stop,
+                         * if the curr task on busiest cpu can't be
+                         * moved to this_cpu
                          */
                         if (!cpumask_test_cpu(this_cpu,
                                               &busiest->curr->cpus_allowed)) {
@@ -2970,14 +2901,22 @@ redo:
                                 goto out_one_pinned;
                         }
 
+                        /*
+                         * ->active_balance synchronizes accesses to
+                         * ->active_balance_work.  Once set, it's cleared
+                         * only after active load balance is finished.
+                         */
                         if (!busiest->active_balance) {
                                 busiest->active_balance = 1;
                                 busiest->push_cpu = this_cpu;
                                 active_balance = 1;
                         }
                         raw_spin_unlock_irqrestore(&busiest->lock, flags);
+
                         if (active_balance)
-                                wake_up_process(busiest->migration_thread);
+                                stop_one_cpu_nowait(cpu_of(busiest),
+                                        active_load_balance_cpu_stop, busiest,
+                                        &busiest->active_balance_work);
 
                         /*
                          * We've kicked active balancing, reset the failure
@@ -3084,24 +3023,29 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 }
 
 /*
- * active_load_balance is run by migration threads. It pushes running tasks
- * off the busiest CPU onto idle CPUs. It requires at least 1 task to be
- * running on each physical CPU where possible, and avoids physical /
- * logical imbalances.
- *
- * Called with busiest_rq locked.
+ * active_load_balance_cpu_stop is run by cpu stopper. It pushes
+ * running tasks off the busiest CPU onto idle CPUs. It requires at
+ * least 1 task to be running on each physical CPU where possible, and
+ * avoids physical / logical imbalances.
  */
-static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
+static int active_load_balance_cpu_stop(void *data)
 {
+        struct rq *busiest_rq = data;
+        int busiest_cpu = cpu_of(busiest_rq);
         int target_cpu = busiest_rq->push_cpu;
+        struct rq *target_rq = cpu_rq(target_cpu);
         struct sched_domain *sd;
-        struct rq *target_rq;
+
+        raw_spin_lock_irq(&busiest_rq->lock);
+
+        /* make sure the requested cpu hasn't gone down in the meantime */
+        if (unlikely(busiest_cpu != smp_processor_id() ||
+                     !busiest_rq->active_balance))
+                goto out_unlock;
 
         /* Is there any task to move? */
         if (busiest_rq->nr_running <= 1)
-                return;
-
-        target_rq = cpu_rq(target_cpu);
+                goto out_unlock;
 
         /*
          * This condition is "impossible", if it occurs
@@ -3112,8 +3056,6 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
 
         /* move a task from busiest_rq to target_rq */
         double_lock_balance(busiest_rq, target_rq);
-        update_rq_clock(busiest_rq);
-        update_rq_clock(target_rq);
 
         /* Search for an sd spanning us and the target CPU. */
         for_each_domain(target_cpu, sd) {
@@ -3132,6 +3074,10 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
                         schedstat_inc(sd, alb_failed);
         }
         double_unlock_balance(busiest_rq, target_rq);
+out_unlock:
+        busiest_rq->active_balance = 0;
+        raw_spin_unlock_irq(&busiest_rq->lock);
+        return 0;
 }
 
 #ifdef CONFIG_NO_HZ
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index d5059fd761d9..83c66e8ad3ee 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -1,11 +1,4 @@
 /*
- * Disregards a certain amount of sleep time (sched_latency_ns) and
- * considers the task to be running during that period. This gives it
- * a service deficit on wakeup, allowing it to run sooner.
- */
-SCHED_FEAT(FAIR_SLEEPERS, 1)
-
-/*
  * Only give sleepers 50% of their service deficit. This allows
  * them to run sooner, but does not allow tons of sleepers to
  * rip the spread apart.
@@ -13,13 +6,6 @@ SCHED_FEAT(FAIR_SLEEPERS, 1)
 SCHED_FEAT(GENTLE_FAIR_SLEEPERS, 1)
 
 /*
- * By not normalizing the sleep time, heavy tasks get an effective
- * longer period, and lighter task an effective shorter period they
- * are considered running.
- */
-SCHED_FEAT(NORMALIZED_SLEEPER, 0)
-
-/*
  * Place new tasks ahead so that they do not starve already running
  * tasks
  */
@@ -31,37 +17,6 @@ SCHED_FEAT(START_DEBIT, 1)
 SCHED_FEAT(WAKEUP_PREEMPT, 1)
 
 /*
- * Compute wakeup_gran based on task behaviour, clipped to
- *  [0, sched_wakeup_gran_ns]
- */
-SCHED_FEAT(ADAPTIVE_GRAN, 1)
-
-/*
- * When converting the wakeup granularity to virtual time, do it such
- * that heavier tasks preempting a lighter task have an edge.
- */
-SCHED_FEAT(ASYM_GRAN, 1)
-
-/*
- * Always wakeup-preempt SYNC wakeups, see SYNC_WAKEUPS.
- */
-SCHED_FEAT(WAKEUP_SYNC, 0)
-
-/*
- * Wakeup preempt based on task behaviour. Tasks that do not overlap
- * don't get preempted.
- */
-SCHED_FEAT(WAKEUP_OVERLAP, 0)
-
-/*
- * Use the SYNC wakeup hint, pipes and the likes use this to indicate
- * the remote end is likely to consume the data we just wrote, and
- * therefore has cache benefit from being placed on the same cpu, see
- * also AFFINE_WAKEUPS.
- */
-SCHED_FEAT(SYNC_WAKEUPS, 1)
-
-/*
  * Based on load and program behaviour, see if it makes sense to place
  * a newly woken task on the same cpu as the task that woke it --
  * improve cache locality. Typically used with SYNC wakeups as
@@ -70,16 +25,6 @@ SCHED_FEAT(SYNC_WAKEUPS, 1)
 SCHED_FEAT(AFFINE_WAKEUPS, 1)
 
 /*
- * Weaken SYNC hint based on overlap
- */
-SCHED_FEAT(SYNC_LESS, 1)
-
-/*
- * Add SYNC hint based on overlap
- */
-SCHED_FEAT(SYNC_MORE, 0)
-
-/*
  * Prefer to schedule the task we woke last (assuming it failed
  * wakeup-preemption), since its likely going to consume data we
  * touched, increases cache locality.
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index a8a6d8a50947..9fa0f402c87c 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -6,7 +6,8 @@
  */
 
 #ifdef CONFIG_SMP
-static int select_task_rq_idle(struct task_struct *p, int sd_flag, int flags)
+static int
+select_task_rq_idle(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
 {
         return task_cpu(p); /* IDLE tasks as never migrated */
 }
@@ -22,8 +23,7 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
 static struct task_struct *pick_next_task_idle(struct rq *rq)
 {
         schedstat_inc(rq, sched_goidle);
-        /* adjust the active tasks as we might go into a long sleep */
-        calc_load_account_active(rq);
+        calc_load_account_idle(rq);
         return rq->idle;
 }
 
@@ -32,7 +32,7 @@ static struct task_struct *pick_next_task_idle(struct rq *rq)
  * message if some code attempts to do it:
  */
 static void
-dequeue_task_idle(struct rq *rq, struct task_struct *p, int sleep)
+dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
 {
         raw_spin_unlock_irq(&rq->lock);
         printk(KERN_ERR "bad: scheduling from the idle thread!\n");
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index b5b920ae2ea7..8afb953e31c6 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -613,7 +613,7 @@ static void update_curr_rt(struct rq *rq)
         if (unlikely((s64)delta_exec < 0))
                 delta_exec = 0;
 
-        schedstat_set(curr->se.exec_max, max(curr->se.exec_max, delta_exec));
+        schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec));
 
         curr->se.sum_exec_runtime += delta_exec;
         account_group_exec_runtime(curr, delta_exec);
@@ -888,20 +888,20 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
  * Adding/removing a task to/from a priority array:
  */
 static void
-enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup, bool head)
+enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 {
         struct sched_rt_entity *rt_se = &p->rt;
 
-        if (wakeup)
+        if (flags & ENQUEUE_WAKEUP)
                 rt_se->timeout = 0;
 
-        enqueue_rt_entity(rt_se, head);
+        enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD);
 
         if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
                 enqueue_pushable_task(rq, p);
 }
 
-static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
+static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 {
         struct sched_rt_entity *rt_se = &p->rt;
 
@@ -948,10 +948,9 @@ static void yield_task_rt(struct rq *rq)
 #ifdef CONFIG_SMP
 static int find_lowest_rq(struct task_struct *task);
 
-static int select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
+static int
+select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
 {
-        struct rq *rq = task_rq(p);
-
         if (sd_flag != SD_BALANCE_WAKE)
                 return smp_processor_id();
 
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 9bb9fb1bd79c..ef51d1fcf5e6 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -1,17 +1,381 @@
-/* Copyright 2008, 2005 Rusty Russell rusty@rustcorp.com.au IBM Corporation.
- * GPL v2 and any later version.
+/*
+ * kernel/stop_machine.c
+ *
+ * Copyright (C) 2008, 2005     IBM Corporation.
+ * Copyright (C) 2008, 2005     Rusty Russell rusty@rustcorp.com.au
+ * Copyright (C) 2010           SUSE Linux Products GmbH
+ * Copyright (C) 2010           Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2 and any later version.
  */
+#include <linux/completion.h>
 #include <linux/cpu.h>
-#include <linux/err.h>
+#include <linux/init.h>
 #include <linux/kthread.h>
 #include <linux/module.h>
+#include <linux/percpu.h>
 #include <linux/sched.h>
 #include <linux/stop_machine.h>
-#include <linux/syscalls.h>
 #include <linux/interrupt.h>
+#include <linux/kallsyms.h>
 
 #include <asm/atomic.h>
-#include <asm/uaccess.h>
+
+/*
+ * Structure to determine completion condition and record errors.  May
+ * be shared by works on different cpus.
+ */
+struct cpu_stop_done {
+        atomic_t                nr_todo;        /* nr left to execute */
+        bool                    executed;       /* actually executed? */
+        int                     ret;            /* collected return value */
+        struct completion       completion;     /* fired if nr_todo reaches 0 */
+};
+
+/* the actual stopper, one per every possible cpu, enabled on online cpus */
+struct cpu_stopper {
+        spinlock_t              lock;
+        struct list_head        works;          /* list of pending works */
+        struct task_struct      *thread;        /* stopper thread */
+        bool                    enabled;        /* is this stopper enabled? */
+};
+
+static DEFINE_PER_CPU(struct cpu_stopper, cpu_stopper);
+
+static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo)
+{
+        memset(done, 0, sizeof(*done));
+        atomic_set(&done->nr_todo, nr_todo);
+        init_completion(&done->completion);
+}
+
+/* signal completion unless @done is NULL */
+static void cpu_stop_signal_done(struct cpu_stop_done *done, bool executed)
+{
+        if (done) {
+                if (executed)
+                        done->executed = true;
+                if (atomic_dec_and_test(&done->nr_todo))
+                        complete(&done->completion);
+        }
+}
+
+/* queue @work to @stopper.  if offline, @work is completed immediately */
+static void cpu_stop_queue_work(struct cpu_stopper *stopper,
+                                struct cpu_stop_work *work)
+{
+        unsigned long flags;
+
+        spin_lock_irqsave(&stopper->lock, flags);
+
+        if (stopper->enabled) {
+                list_add_tail(&work->list, &stopper->works);
+                wake_up_process(stopper->thread);
+        } else
+                cpu_stop_signal_done(work->done, false);
+
+        spin_unlock_irqrestore(&stopper->lock, flags);
+}
+
+/**
+ * stop_one_cpu - stop a cpu
+ * @cpu: cpu to stop
+ * @fn: function to execute
+ * @arg: argument to @fn
+ *
+ * Execute @fn(@arg) on @cpu.  @fn is run in a process context with
+ * the highest priority preempting any task on the cpu and
+ * monopolizing it.  This function returns after the execution is
+ * complete.
+ *
+ * This function doesn't guarantee @cpu stays online till @fn
+ * completes.  If @cpu goes down in the middle, execution may happen
+ * partially or fully on different cpus.  @fn should either be ready
+ * for that or the caller should ensure that @cpu stays online until
+ * this function completes.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * -ENOENT if @fn(@arg) was not executed because @cpu was offline;
+ * otherwise, the return value of @fn.
+ */
+int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
+{
+        struct cpu_stop_done done;
+        struct cpu_stop_work work = { .fn = fn, .arg = arg, .done = &done };
+
+        cpu_stop_init_done(&done, 1);
+        cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu), &work);
+        wait_for_completion(&done.completion);
+        return done.executed ? done.ret : -ENOENT;
+}
+
+/**
+ * stop_one_cpu_nowait - stop a cpu but don't wait for completion
+ * @cpu: cpu to stop
+ * @fn: function to execute
+ * @arg: argument to @fn
+ *
+ * Similar to stop_one_cpu() but doesn't wait for completion.  The
+ * caller is responsible for ensuring @work_buf is currently unused
+ * and will remain untouched until stopper starts executing @fn.
+ *
+ * CONTEXT:
+ * Don't care.
+ */
+void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
+                        struct cpu_stop_work *work_buf)
+{
+        *work_buf = (struct cpu_stop_work){ .fn = fn, .arg = arg, };
+        cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu), work_buf);
+}
+
+/* static data for stop_cpus */
+static DEFINE_MUTEX(stop_cpus_mutex);
+static DEFINE_PER_CPU(struct cpu_stop_work, stop_cpus_work);
+
+int __stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)
+{
+        struct cpu_stop_work *work;
+        struct cpu_stop_done done;
+        unsigned int cpu;
+
+        /* initialize works and done */
+        for_each_cpu(cpu, cpumask) {
+                work = &per_cpu(stop_cpus_work, cpu);
+                work->fn = fn;
+                work->arg = arg;
+                work->done = &done;
+        }
+        cpu_stop_init_done(&done, cpumask_weight(cpumask));
+
+        /*
+         * Disable preemption while queueing to avoid getting
+         * preempted by a stopper which might wait for other stoppers
+         * to enter @fn which can lead to deadlock.
+         */
+        preempt_disable();
+        for_each_cpu(cpu, cpumask)
+                cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu),
+                                    &per_cpu(stop_cpus_work, cpu));
+        preempt_enable();
+
+        wait_for_completion(&done.completion);
+        return done.executed ? done.ret : -ENOENT;
+}
+
+/**
+ * stop_cpus - stop multiple cpus
+ * @cpumask: cpus to stop
+ * @fn: function to execute
+ * @arg: argument to @fn
+ *
+ * Execute @fn(@arg) on online cpus in @cpumask.  On each target cpu,
+ * @fn is run in a process context with the highest priority
+ * preempting any task on the cpu and monopolizing it.  This function
+ * returns after all executions are complete.
+ *
+ * This function doesn't guarantee the cpus in @cpumask stay online
+ * till @fn completes.  If some cpus go down in the middle, execution
+ * on the cpu may happen partially or fully on different cpus.  @fn
+ * should either be ready for that or the caller should ensure that
+ * the cpus stay online until this function completes.
+ *
+ * All stop_cpus() calls are serialized making it safe for @fn to wait
+ * for all cpus to start executing it.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * -ENOENT if @fn(@arg) was not executed at all because all cpus in
+ * @cpumask were offline; otherwise, 0 if all executions of @fn
+ * returned 0, any non zero return value if any returned non zero.
+ */
+int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)
+{
+        int ret;
+
+        /* static works are used, process one request at a time */
+        mutex_lock(&stop_cpus_mutex);
+        ret = __stop_cpus(cpumask, fn, arg);
+        mutex_unlock(&stop_cpus_mutex);
+        return ret;
+}
+
+/**
+ * try_stop_cpus - try to stop multiple cpus
+ * @cpumask: cpus to stop
+ * @fn: function to execute
+ * @arg: argument to @fn
+ *
+ * Identical to stop_cpus() except that it fails with -EAGAIN if
+ * someone else is already using the facility.
+ *
+ * CONTEXT:
+ * Might sleep.
+ *
+ * RETURNS:
+ * -EAGAIN if someone else is already stopping cpus, -ENOENT if
+ * @fn(@arg) was not executed at all because all cpus in @cpumask were
+ * offline; otherwise, 0 if all executions of @fn returned 0, any non
+ * zero return value if any returned non zero.
+ */
+int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)
+{
+        int ret;
+
+        /* static works are used, process one request at a time */
+        if (!mutex_trylock(&stop_cpus_mutex))
+                return -EAGAIN;
+        ret = __stop_cpus(cpumask, fn, arg);
+        mutex_unlock(&stop_cpus_mutex);
+        return ret;
+}
+
+static int cpu_stopper_thread(void *data)
+{
+        struct cpu_stopper *stopper = data;
+        struct cpu_stop_work *work;
+        int ret;
+
+repeat:
+        set_current_state(TASK_INTERRUPTIBLE);  /* mb paired w/ kthread_stop */
+
+        if (kthread_should_stop()) {
+                __set_current_state(TASK_RUNNING);
+                return 0;
+        }
+
+        work = NULL;
+        spin_lock_irq(&stopper->lock);
+        if (!list_empty(&stopper->works)) {
+                work = list_first_entry(&stopper->works,
+                                        struct cpu_stop_work, list);
+                list_del_init(&work->list);
+        }
+        spin_unlock_irq(&stopper->lock);
+
+        if (work) {
+                cpu_stop_fn_t fn = work->fn;
+                void *arg = work->arg;
+                struct cpu_stop_done *done = work->done;
+                char ksym_buf[KSYM_NAME_LEN];
+
+                __set_current_state(TASK_RUNNING);
+
+                /* cpu stop callbacks are not allowed to sleep */
+                preempt_disable();
+
+                ret = fn(arg);
+                if (ret)
+                        done->ret = ret;
+
+                /* restore preemption and check it's still balanced */
+                preempt_enable();
+                WARN_ONCE(preempt_count(),
+                          "cpu_stop: %s(%p) leaked preempt count\n",
+                          kallsyms_lookup((unsigned long)fn, NULL, NULL, NULL,
+                                          ksym_buf), arg);
+
+                cpu_stop_signal_done(done, true);
+        } else
+                schedule();
+
+        goto repeat;
+}
+
+/* manage stopper for a cpu, mostly lifted from sched migration thread mgmt */
+static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb,
+                                           unsigned long action, void *hcpu)
+{
+        struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
+        unsigned int cpu = (unsigned long)hcpu;
+        struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
+        struct cpu_stop_work *work;
+        struct task_struct *p;
+
+        switch (action & ~CPU_TASKS_FROZEN) {
+        case CPU_UP_PREPARE:
+                BUG_ON(stopper->thread || stopper->enabled ||
+                       !list_empty(&stopper->works));
+                p = kthread_create(cpu_stopper_thread, stopper, "migration/%d",
+                                   cpu);
+                if (IS_ERR(p))
+                        return NOTIFY_BAD;
+                sched_setscheduler_nocheck(p, SCHED_FIFO, &param);
+                get_task_struct(p);
+                stopper->thread = p;
+                break;
+
+        case CPU_ONLINE:
+                kthread_bind(stopper->thread, cpu);
+                /* strictly unnecessary, as first user will wake it */
+                wake_up_process(stopper->thread);
+                /* mark enabled */
+                spin_lock_irq(&stopper->lock);
+                stopper->enabled = true;
+                spin_unlock_irq(&stopper->lock);
+                break;
+
+#ifdef CONFIG_HOTPLUG_CPU
+        case CPU_UP_CANCELED:
+        case CPU_DEAD:
+                /* kill the stopper */
+                kthread_stop(stopper->thread);
+                /* drain remaining works */
+                spin_lock_irq(&stopper->lock);
+                list_for_each_entry(work, &stopper->works, list)
+                        cpu_stop_signal_done(work->done, false);
+                stopper->enabled = false;
+                spin_unlock_irq(&stopper->lock);
+                /* release the stopper */
+                put_task_struct(stopper->thread);
+                stopper->thread = NULL;
+                break;
+#endif
+        }
+
+        return NOTIFY_OK;
+}
+
+/*
+ * Give it a higher priority so that cpu stopper is available to other
+ * cpu notifiers.  It currently shares the same priority as sched
+ * migration_notifier.
+ */
+static struct notifier_block __cpuinitdata cpu_stop_cpu_notifier = {
+        .notifier_call  = cpu_stop_cpu_callback,
+        .priority       = 10,
+};
+
+static int __init cpu_stop_init(void)
+{
+        void *bcpu = (void *)(long)smp_processor_id();
+        unsigned int cpu;
+        int err;
+
+        for_each_possible_cpu(cpu) {
+                struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
+
+                spin_lock_init(&stopper->lock);
+                INIT_LIST_HEAD(&stopper->works);
+        }
+
+        /* start one for the boot cpu */
+        err = cpu_stop_cpu_callback(&cpu_stop_cpu_notifier, CPU_UP_PREPARE,
+                                    bcpu);
+        BUG_ON(err == NOTIFY_BAD);
+        cpu_stop_cpu_callback(&cpu_stop_cpu_notifier, CPU_ONLINE, bcpu);
+        register_cpu_notifier(&cpu_stop_cpu_notifier);
+
+        return 0;
+}
+early_initcall(cpu_stop_init);
+
+#ifdef CONFIG_STOP_MACHINE
 
 /* This controls the threads on each CPU. */
 enum stopmachine_state {
@@ -26,174 +390,94 @@ enum stopmachine_state {
         /* Exit */
         STOPMACHINE_EXIT,
 };
-static enum stopmachine_state state;
 
 struct stop_machine_data {
-        int (*fn)(void *);
-        void *data;
-        int fnret;
+        int                     (*fn)(void *);
+        void                    *data;
+        /* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
+        unsigned int            num_threads;
+        const struct cpumask    *active_cpus;
+
+        enum stopmachine_state  state;
+        atomic_t                thread_ack;
 };
 
-/* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
-static unsigned int num_threads;
-static atomic_t thread_ack;
-static DEFINE_MUTEX(lock);
-/* setup_lock protects refcount, stop_machine_wq and stop_machine_work. */
-static DEFINE_MUTEX(setup_lock);
-/* Users of stop_machine. */
-static int refcount;
-static struct workqueue_struct *stop_machine_wq;
-static struct stop_machine_data active, idle;
-static const struct cpumask *active_cpus;
-static void __percpu *stop_machine_work;
-
-static void set_state(enum stopmachine_state newstate)
+static void set_state(struct stop_machine_data *smdata,
+                      enum stopmachine_state newstate)
 {
         /* Reset ack counter. */
-        atomic_set(&thread_ack, num_threads);
+        atomic_set(&smdata->thread_ack, smdata->num_threads);
         smp_wmb();
-        state = newstate;
+        smdata->state = newstate;
 }
 
 /* Last one to ack a state moves to the next state. */
-static void ack_state(void)
+static void ack_state(struct stop_machine_data *smdata)
 {
-        if (atomic_dec_and_test(&thread_ack))
-                set_state(state + 1);
+        if (atomic_dec_and_test(&smdata->thread_ack))
+                set_state(smdata, smdata->state + 1);
 }
 
-/* This is the actual function which stops the CPU. It runs
- * in the context of a dedicated stopmachine workqueue. */
-static void stop_cpu(struct work_struct *unused)
+/* This is the cpu_stop function which stops the CPU. */
+static int stop_machine_cpu_stop(void *data)
 {
+        struct stop_machine_data *smdata = data;
         enum stopmachine_state curstate = STOPMACHINE_NONE;
-        struct stop_machine_data *smdata = &idle;
-        int cpu = smp_processor_id();
-        int err;
+        int cpu = smp_processor_id(), err = 0;
+        bool is_active;
+
+        if (!smdata->active_cpus)
+                is_active = cpu == cpumask_first(cpu_online_mask);
+        else
+                is_active = cpumask_test_cpu(cpu, smdata->active_cpus);
 
-        if (!active_cpus) {
-                if (cpu == cpumask_first(cpu_online_mask))
-                        smdata = &active;
-        } else {
-                if (cpumask_test_cpu(cpu, active_cpus))
-                        smdata = &active;
-        }
         /* Simple state machine */
         do {
                 /* Chill out and ensure we re-read stopmachine_state. */
                 cpu_relax();
-                if (state != curstate) {
-                        curstate = state;
+                if (smdata->state != curstate) {
+                        curstate = smdata->state;
                         switch (curstate) {
                         case STOPMACHINE_DISABLE_IRQ:
                                 local_irq_disable();
                                 hard_irq_disable();
                                 break;
                         case STOPMACHINE_RUN:
-                                /* On multiple CPUs only a single error code
-                                 * is needed to tell that something failed. */
-                                err = smdata->fn(smdata->data);
-                                if (err)
-                                        smdata->fnret = err;
+                                if (is_active)
+                                        err = smdata->fn(smdata->data);
                                 break;
                         default:
                                 break;
                         }
-                        ack_state();
+                        ack_state(smdata);
                 }
         } while (curstate != STOPMACHINE_EXIT);
 
         local_irq_enable();
+        return err;
 }
 
-/* Callback for CPUs which aren't supposed to do anything. */
-static int chill(void *unused)
-{
-        return 0;
-}
-
-int stop_machine_create(void)
-{
-        mutex_lock(&setup_lock);
-        if (refcount)
-                goto done;
-        stop_machine_wq = create_rt_workqueue("kstop");
-        if (!stop_machine_wq)
-                goto err_out;
-        stop_machine_work = alloc_percpu(struct work_struct);
-        if (!stop_machine_work)
-                goto err_out;
-done:
-        refcount++;
-        mutex_unlock(&setup_lock);
-        return 0;
-
-err_out:
-        if (stop_machine_wq)
-                destroy_workqueue(stop_machine_wq);
-        mutex_unlock(&setup_lock);
-        return -ENOMEM;
-}
-EXPORT_SYMBOL_GPL(stop_machine_create);
-
-void stop_machine_destroy(void)
-{
-        mutex_lock(&setup_lock);
-        refcount--;
-        if (refcount)
-                goto done;
-        destroy_workqueue(stop_machine_wq);
-        free_percpu(stop_machine_work);
-done:
-        mutex_unlock(&setup_lock);
-}
-EXPORT_SYMBOL_GPL(stop_machine_destroy);
-
 int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 {
-        struct work_struct *sm_work;
-        int i, ret;
-
-        /* Set up initial state. */
-        mutex_lock(&lock);
-        num_threads = num_online_cpus();
-        active_cpus = cpus;
-        active.fn = fn;
-        active.data = data;
-        active.fnret = 0;
-        idle.fn = chill;
-        idle.data = NULL;
-
-        set_state(STOPMACHINE_PREPARE);
-
-        /* Schedule the stop_cpu work on all cpus: hold this CPU so one
-         * doesn't hit this CPU until we're ready. */
-        get_cpu();
-        for_each_online_cpu(i) {
-                sm_work = per_cpu_ptr(stop_machine_work, i);
-                INIT_WORK(sm_work, stop_cpu);
-                queue_work_on(i, stop_machine_wq, sm_work);
-        }
-        /* This will release the thread on our CPU. */
-        put_cpu();
-        flush_workqueue(stop_machine_wq);
-        ret = active.fnret;
-        mutex_unlock(&lock);
-        return ret;
+        struct stop_machine_data smdata = { .fn = fn, .data = data,
+                                            .num_threads = num_online_cpus(),
+                                            .active_cpus = cpus };
+
+        /* Set the initial state and stop all online cpus. */
+        set_state(&smdata, STOPMACHINE_PREPARE);
+        return stop_cpus(cpu_online_mask, stop_machine_cpu_stop, &smdata);
 }
 
 int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 {
         int ret;
 
-        ret = stop_machine_create();
-        if (ret)
-                return ret;
         /* No CPUs can come up or down during this. */
         get_online_cpus();
         ret = __stop_machine(fn, data, cpus);
         put_online_cpus();
-        stop_machine_destroy();
         return ret;
 }
 EXPORT_SYMBOL_GPL(stop_machine);
+
+#endif  /* CONFIG_STOP_MACHINE */
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index f992762d7f51..1d7b9bc1c034 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -150,14 +150,32 @@ static void tick_nohz_update_jiffies(ktime_t now)
         touch_softlockup_watchdog();
 }
 
+/*
+ * Updates the per cpu time idle statistics counters
+ */
+static void
+update_ts_time_stats(struct tick_sched *ts, ktime_t now, u64 *last_update_time)
+{
+        ktime_t delta;
+
+        if (ts->idle_active) {
+                delta = ktime_sub(now, ts->idle_entrytime);
+                ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+                if (nr_iowait_cpu() > 0)
+                        ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta);
+                ts->idle_entrytime = now;
+        }
+
+        if (last_update_time)
+                *last_update_time = ktime_to_us(now);
+
+}
+
 static void tick_nohz_stop_idle(int cpu, ktime_t now)
 {
         struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
-        ktime_t delta;
 
-        delta = ktime_sub(now, ts->idle_entrytime);
-        ts->idle_lastupdate = now;
-        ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+        update_ts_time_stats(ts, now, NULL);
         ts->idle_active = 0;
 
         sched_clock_idle_wakeup_event(0);
@@ -165,20 +183,32 @@ static void tick_nohz_stop_idle(int cpu, ktime_t now)
 
 static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
 {
-        ktime_t now, delta;
+        ktime_t now;
 
         now = ktime_get();
-        if (ts->idle_active) {
-                delta = ktime_sub(now, ts->idle_entrytime);
-                ts->idle_lastupdate = now;
-                ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
-        }
+
+        update_ts_time_stats(ts, now, NULL);
+
         ts->idle_entrytime = now;
         ts->idle_active = 1;
         sched_clock_idle_sleep_event();
         return now;
 }
 
+/**
+ * get_cpu_idle_time_us - get the total idle time of a cpu
+ * @cpu: CPU number to query
+ * @last_update_time: variable to store update time in
+ *
+ * Return the cummulative idle time (since boot) for a given
+ * CPU, in microseconds. The idle time returned includes
+ * the iowait time (unlike what "top" and co report).
+ *
+ * This time is measured via accounting rather than sampling,
+ * and is as accurate as ktime_get() is.
+ *
+ * This function returns -1 if NOHZ is not enabled.
+ */
 u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
 {
         struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
@@ -186,15 +216,38 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
         if (!tick_nohz_enabled)
                 return -1;
 
-        if (ts->idle_active)
-                *last_update_time = ktime_to_us(ts->idle_lastupdate);
-        else
-                *last_update_time = ktime_to_us(ktime_get());
+        update_ts_time_stats(ts, ktime_get(), last_update_time);
 
         return ktime_to_us(ts->idle_sleeptime);
 }
 EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
 
+/*
+ * get_cpu_iowait_time_us - get the total iowait time of a cpu
+ * @cpu: CPU number to query
+ * @last_update_time: variable to store update time in
+ *
+ * Return the cummulative iowait time (since boot) for a given
+ * CPU, in microseconds.
+ *
+ * This time is measured via accounting rather than sampling,
+ * and is as accurate as ktime_get() is.
+ *
+ * This function returns -1 if NOHZ is not enabled.
+ */
+u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
+{
+        struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+
+        if (!tick_nohz_enabled)
+                return -1;
+
+        update_ts_time_stats(ts, ktime_get(), last_update_time);
+
+        return ktime_to_us(ts->iowait_sleeptime);
+}
+EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
+
 /**
  * tick_nohz_stop_sched_tick - stop the idle tick from the idle task
  *
@@ -262,6 +315,9 @@ void tick_nohz_stop_sched_tick(int inidle)
                 goto end;
         }
 
+        if (nohz_ratelimit(cpu))
+                goto end;
+
         ts->idle_calls++;
         /* Read jiffies and the time when jiffies were updated last */
         do {
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 1a4a7dd78777..ab8f5e33fa92 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -176,6 +176,7 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
                 P_ns(idle_waketime);
                 P_ns(idle_exittime);
                 P_ns(idle_sleeptime);
+                P_ns(iowait_sleeptime);
                 P(last_jiffies);
                 P(next_jiffies);
                 P_ns(idle_expires);
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index b3bc91a3f510..36ea2b65dcdc 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -675,28 +675,33 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
         }
 }
 
-static void blk_add_trace_rq_abort(struct request_queue *q, struct request *rq)
+static void blk_add_trace_rq_abort(void *ignore,
+                                   struct request_queue *q, struct request *rq)
 {
         blk_add_trace_rq(q, rq, BLK_TA_ABORT);
 }
 
-static void blk_add_trace_rq_insert(struct request_queue *q, struct request *rq)
+static void blk_add_trace_rq_insert(void *ignore,
+                                    struct request_queue *q, struct request *rq)
 {
         blk_add_trace_rq(q, rq, BLK_TA_INSERT);
 }
 
-static void blk_add_trace_rq_issue(struct request_queue *q, struct request *rq)
+static void blk_add_trace_rq_issue(void *ignore,
+                                   struct request_queue *q, struct request *rq)
 {
         blk_add_trace_rq(q, rq, BLK_TA_ISSUE);
 }
 
-static void blk_add_trace_rq_requeue(struct request_queue *q,
+static void blk_add_trace_rq_requeue(void *ignore,
+                                     struct request_queue *q,
                                      struct request *rq)
 {
         blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
 }
 
-static void blk_add_trace_rq_complete(struct request_queue *q,
+static void blk_add_trace_rq_complete(void *ignore,
+                                      struct request_queue *q,
                                       struct request *rq)
 {
         blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
@@ -724,34 +729,40 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
                         !bio_flagged(bio, BIO_UPTODATE), 0, NULL);
 }
 
-static void blk_add_trace_bio_bounce(struct request_queue *q, struct bio *bio)
+static void blk_add_trace_bio_bounce(void *ignore,
+                                     struct request_queue *q, struct bio *bio)
 {
         blk_add_trace_bio(q, bio, BLK_TA_BOUNCE);
 }
 
-static void blk_add_trace_bio_complete(struct request_queue *q, struct bio *bio)
+static void blk_add_trace_bio_complete(void *ignore,
+                                       struct request_queue *q, struct bio *bio)
 {
         blk_add_trace_bio(q, bio, BLK_TA_COMPLETE);
 }
 
-static void blk_add_trace_bio_backmerge(struct request_queue *q,
+static void blk_add_trace_bio_backmerge(void *ignore,
+                                        struct request_queue *q,
                                         struct bio *bio)
 {
         blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE);
 }
 
-static void blk_add_trace_bio_frontmerge(struct request_queue *q,
+static void blk_add_trace_bio_frontmerge(void *ignore,
+                                         struct request_queue *q,
                                          struct bio *bio)
 {
         blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE);
 }
 
-static void blk_add_trace_bio_queue(struct request_queue *q, struct bio *bio)
+static void blk_add_trace_bio_queue(void *ignore,
+                                    struct request_queue *q, struct bio *bio)
 {
         blk_add_trace_bio(q, bio, BLK_TA_QUEUE);
 }
 
-static void blk_add_trace_getrq(struct request_queue *q,
+static void blk_add_trace_getrq(void *ignore,
+                                struct request_queue *q,
                                 struct bio *bio, int rw)
 {
         if (bio)
@@ -765,7 +776,8 @@ static void blk_add_trace_getrq(struct request_queue *q,
 }
 
 
-static void blk_add_trace_sleeprq(struct request_queue *q,
+static void blk_add_trace_sleeprq(void *ignore,
+                                  struct request_queue *q,
                                   struct bio *bio, int rw)
 {
         if (bio)
@@ -779,7 +791,7 @@ static void blk_add_trace_sleeprq(struct request_queue *q,
         }
 }
 
-static void blk_add_trace_plug(struct request_queue *q)
+static void blk_add_trace_plug(void *ignore, struct request_queue *q)
 {
         struct blk_trace *bt = q->blk_trace;
 
@@ -787,7 +799,7 @@ static void blk_add_trace_plug(struct request_queue *q)
                 __blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL);
 }
 
-static void blk_add_trace_unplug_io(struct request_queue *q)
+static void blk_add_trace_unplug_io(void *ignore, struct request_queue *q)
 {
         struct blk_trace *bt = q->blk_trace;
 
@@ -800,7 +812,7 @@ static void blk_add_trace_unplug_io(struct request_queue *q)
         }
 }
 
-static void blk_add_trace_unplug_timer(struct request_queue *q)
+static void blk_add_trace_unplug_timer(void *ignore, struct request_queue *q)
 {
         struct blk_trace *bt = q->blk_trace;
 
@@ -813,7 +825,8 @@ static void blk_add_trace_unplug_timer(struct request_queue *q)
         }
 }
 
-static void blk_add_trace_split(struct request_queue *q, struct bio *bio,
+static void blk_add_trace_split(void *ignore,
+                                struct request_queue *q, struct bio *bio,
                                 unsigned int pdu)
 {
         struct blk_trace *bt = q->blk_trace;
@@ -839,8 +852,9 @@ static void blk_add_trace_split(struct request_queue *q, struct bio *bio,
  *     it spans a stripe (or similar). Add a trace for that action.
  *
  **/
-static void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
-                                       dev_t dev, sector_t from)
+static void blk_add_trace_remap(void *ignore,
+                                struct request_queue *q, struct bio *bio,
+                                dev_t dev, sector_t from)
 {
         struct blk_trace *bt = q->blk_trace;
         struct blk_io_trace_remap r;
@@ -869,7 +883,8 @@ static void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
  *     Add a trace for that action.
  *
  **/
-static void blk_add_trace_rq_remap(struct request_queue *q,
+static void blk_add_trace_rq_remap(void *ignore,
+                                   struct request_queue *q,
                                    struct request *rq, dev_t dev,
                                    sector_t from)
 {
@@ -921,64 +936,64 @@ static void blk_register_tracepoints(void)
 {
         int ret;
 
-        ret = register_trace_block_rq_abort(blk_add_trace_rq_abort);
+        ret = register_trace_block_rq_abort(blk_add_trace_rq_abort, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_rq_insert(blk_add_trace_rq_insert);
+        ret = register_trace_block_rq_insert(blk_add_trace_rq_insert, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_rq_issue(blk_add_trace_rq_issue);
+        ret = register_trace_block_rq_issue(blk_add_trace_rq_issue, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue);
+        ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_rq_complete(blk_add_trace_rq_complete);
+        ret = register_trace_block_rq_complete(blk_add_trace_rq_complete, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_bio_bounce(blk_add_trace_bio_bounce);
+        ret = register_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_bio_complete(blk_add_trace_bio_complete);
+        ret = register_trace_block_bio_complete(blk_add_trace_bio_complete, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_bio_backmerge(blk_add_trace_bio_backmerge);
+        ret = register_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge);
+        ret = register_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_bio_queue(blk_add_trace_bio_queue);
+        ret = register_trace_block_bio_queue(blk_add_trace_bio_queue, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_getrq(blk_add_trace_getrq);
+        ret = register_trace_block_getrq(blk_add_trace_getrq, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_sleeprq(blk_add_trace_sleeprq);
+        ret = register_trace_block_sleeprq(blk_add_trace_sleeprq, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_plug(blk_add_trace_plug);
+        ret = register_trace_block_plug(blk_add_trace_plug, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_unplug_timer(blk_add_trace_unplug_timer);
+        ret = register_trace_block_unplug_timer(blk_add_trace_unplug_timer, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_unplug_io(blk_add_trace_unplug_io);
+        ret = register_trace_block_unplug_io(blk_add_trace_unplug_io, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_split(blk_add_trace_split);
+        ret = register_trace_block_split(blk_add_trace_split, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_remap(blk_add_trace_remap);
+        ret = register_trace_block_remap(blk_add_trace_remap, NULL);
         WARN_ON(ret);
-        ret = register_trace_block_rq_remap(blk_add_trace_rq_remap);
+        ret = register_trace_block_rq_remap(blk_add_trace_rq_remap, NULL);
         WARN_ON(ret);
 }
 
 static void blk_unregister_tracepoints(void)
 {
-        unregister_trace_block_rq_remap(blk_add_trace_rq_remap);
-        unregister_trace_block_remap(blk_add_trace_remap);
-        unregister_trace_block_split(blk_add_trace_split);
-        unregister_trace_block_unplug_io(blk_add_trace_unplug_io);
-        unregister_trace_block_unplug_timer(blk_add_trace_unplug_timer);
-        unregister_trace_block_plug(blk_add_trace_plug);
-        unregister_trace_block_sleeprq(blk_add_trace_sleeprq);
-        unregister_trace_block_getrq(blk_add_trace_getrq);
-        unregister_trace_block_bio_queue(blk_add_trace_bio_queue);
-        unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge);
-        unregister_trace_block_bio_backmerge(blk_add_trace_bio_backmerge);
-        unregister_trace_block_bio_complete(blk_add_trace_bio_complete);
-        unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce);
-        unregister_trace_block_rq_complete(blk_add_trace_rq_complete);
-        unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue);
-        unregister_trace_block_rq_issue(blk_add_trace_rq_issue);
-        unregister_trace_block_rq_insert(blk_add_trace_rq_insert);
-        unregister_trace_block_rq_abort(blk_add_trace_rq_abort);
+        unregister_trace_block_rq_remap(blk_add_trace_rq_remap, NULL);
+        unregister_trace_block_remap(blk_add_trace_remap, NULL);
+        unregister_trace_block_split(blk_add_trace_split, NULL);
+        unregister_trace_block_unplug_io(blk_add_trace_unplug_io, NULL);
+        unregister_trace_block_unplug_timer(blk_add_trace_unplug_timer, NULL);
+        unregister_trace_block_plug(blk_add_trace_plug, NULL);
+        unregister_trace_block_sleeprq(blk_add_trace_sleeprq, NULL);
+        unregister_trace_block_getrq(blk_add_trace_getrq, NULL);
+        unregister_trace_block_bio_queue(blk_add_trace_bio_queue, NULL);
+        unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL);
+        unregister_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL);
+        unregister_trace_block_bio_complete(blk_add_trace_bio_complete, NULL);
+        unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL);
+        unregister_trace_block_rq_complete(blk_add_trace_rq_complete, NULL);
+        unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL);
+        unregister_trace_block_rq_issue(blk_add_trace_rq_issue, NULL);
+        unregister_trace_block_rq_insert(blk_add_trace_rq_insert, NULL);
+        unregister_trace_block_rq_abort(blk_add_trace_rq_abort, NULL);
 
         tracepoint_synchronize_unregister();
 }
@@ -1321,7 +1336,7 @@ out:
 }
 
 static enum print_line_t blk_trace_event_print(struct trace_iterator *iter,
-                                               int flags)
+                                               int flags, struct trace_event *event)
 {
         return print_one_line(iter, false);
 }
@@ -1343,7 +1358,8 @@ static int blk_trace_synthesize_old_trace(struct trace_iterator *iter)
 }
 
 static enum print_line_t
-blk_trace_event_print_binary(struct trace_iterator *iter, int flags)
+blk_trace_event_print_binary(struct trace_iterator *iter, int flags,
+                             struct trace_event *event)
 {
         return blk_trace_synthesize_old_trace(iter) ?
                         TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
@@ -1381,12 +1397,16 @@ static struct tracer blk_tracer __read_mostly = {
         .set_flag       = blk_tracer_set_flag,
 };
 
-static struct trace_event trace_blk_event = {
-        .type           = TRACE_BLK,
+static struct trace_event_functions trace_blk_event_funcs = {
         .trace          = blk_trace_event_print,
         .binary         = blk_trace_event_print_binary,
 };
 
+static struct trace_event trace_blk_event = {
+        .type           = TRACE_BLK,
+        .funcs          = &trace_blk_event_funcs,
+};
+
 static int __init init_blk_tracer(void)
 {
         if (!register_ftrace_event(&trace_blk_event)) {
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 2404b59b3097..6d2cb14f9449 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -264,6 +264,7 @@ struct ftrace_profile {
         unsigned long                   counter;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
         unsigned long long              time;
+        unsigned long long              time_squared;
 #endif
 };
 
@@ -366,9 +367,9 @@ static int function_stat_headers(struct seq_file *m)
 {
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
         seq_printf(m, "  Function                               "
-                   "Hit    Time            Avg\n"
+                   "Hit    Time            Avg             s^2\n"
                       "  --------                               "
-                   "---    ----            ---\n");
+                   "---    ----            ---             ---\n");
 #else
         seq_printf(m, "  Function                               Hit\n"
                       "  --------                               ---\n");
@@ -384,6 +385,7 @@ static int function_stat_show(struct seq_file *m, void *v)
         static DEFINE_MUTEX(mutex);
         static struct trace_seq s;
         unsigned long long avg;
+        unsigned long long stddev;
 #endif
 
         kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
@@ -394,11 +396,25 @@ static int function_stat_show(struct seq_file *m, void *v)
         avg = rec->time;
         do_div(avg, rec->counter);
 
+        /* Sample standard deviation (s^2) */
+        if (rec->counter <= 1)
+                stddev = 0;
+        else {
+                stddev = rec->time_squared - rec->counter * avg * avg;
+                /*
+                 * Divide only 1000 for ns^2 -> us^2 conversion.
+                 * trace_print_graph_duration will divide 1000 again.
+                 */
+                do_div(stddev, (rec->counter - 1) * 1000);
+        }
+
         mutex_lock(&mutex);
         trace_seq_init(&s);
         trace_print_graph_duration(rec->time, &s);
         trace_seq_puts(&s, "    ");
         trace_print_graph_duration(avg, &s);
+        trace_seq_puts(&s, "    ");
+        trace_print_graph_duration(stddev, &s);
         trace_print_seq(m, &s);
         mutex_unlock(&mutex);
 #endif
@@ -650,6 +666,10 @@ static void profile_graph_return(struct ftrace_graph_ret *trace)
         if (!stat->hash || !ftrace_profile_enabled)
                 goto out;
 
+        /* If the calltime was zero'd ignore it */
+        if (!trace->calltime)
+                goto out;
+
         calltime = trace->rettime - trace->calltime;
 
         if (!(trace_flags & TRACE_ITER_GRAPH_TIME)) {
@@ -668,8 +688,10 @@ static void profile_graph_return(struct ftrace_graph_ret *trace)
         }
 
         rec = ftrace_find_profiled_func(stat, trace->func);
-        if (rec)
+        if (rec) {
                 rec->time += calltime;
+                rec->time_squared += calltime * calltime;
+        }
 
  out:
         local_irq_restore(flags);
@@ -3212,8 +3234,8 @@ free:
 }
 
 static void
-ftrace_graph_probe_sched_switch(struct rq *__rq, struct task_struct *prev,
-                                struct task_struct *next)
+ftrace_graph_probe_sched_switch(void *ignore,
+                        struct task_struct *prev, struct task_struct *next)
 {
         unsigned long long timestamp;
         int index;
@@ -3267,7 +3289,7 @@ static int start_graph_tracing(void)
         } while (ret == -EAGAIN);
 
         if (!ret) {
-                ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch);
+                ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
                 if (ret)
                         pr_info("ftrace_graph: Couldn't activate tracepoint"
                                 " probe to kernel_sched_switch\n");
@@ -3339,11 +3361,11 @@ void unregister_ftrace_graph(void)
                 goto out;
 
         ftrace_graph_active--;
-        unregister_trace_sched_switch(ftrace_graph_probe_sched_switch);
         ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
         ftrace_graph_entry = ftrace_graph_entry_stub;
         ftrace_shutdown(FTRACE_STOP_FUNC_RET);
         unregister_pm_notifier(&ftrace_suspend_notifier);
+        unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
 
  out:
         mutex_unlock(&ftrace_lock);
diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
index a91da69f153a..bbfc1bb1660b 100644
--- a/kernel/trace/kmemtrace.c
+++ b/kernel/trace/kmemtrace.c
@@ -95,7 +95,8 @@ static inline void kmemtrace_free(enum kmemtrace_type_id type_id,
         trace_wake_up();
 }
 
-static void kmemtrace_kmalloc(unsigned long call_site,
+static void kmemtrace_kmalloc(void *ignore,
+                              unsigned long call_site,
                               const void *ptr,
                               size_t bytes_req,
                               size_t bytes_alloc,
@@ -105,7 +106,8 @@ static void kmemtrace_kmalloc(unsigned long call_site,
                         bytes_req, bytes_alloc, gfp_flags, -1);
 }
 
-static void kmemtrace_kmem_cache_alloc(unsigned long call_site,
+static void kmemtrace_kmem_cache_alloc(void *ignore,
+                                       unsigned long call_site,
                                        const void *ptr,
                                        size_t bytes_req,
                                        size_t bytes_alloc,
@@ -115,7 +117,8 @@ static void kmemtrace_kmem_cache_alloc(unsigned long call_site,
                         bytes_req, bytes_alloc, gfp_flags, -1);
 }
 
-static void kmemtrace_kmalloc_node(unsigned long call_site,
+static void kmemtrace_kmalloc_node(void *ignore,
+                                   unsigned long call_site,
                                    const void *ptr,
                                    size_t bytes_req,
                                    size_t bytes_alloc,
@@ -126,7 +129,8 @@ static void kmemtrace_kmalloc_node(unsigned long call_site,
                         bytes_req, bytes_alloc, gfp_flags, node);
 }
 
-static void kmemtrace_kmem_cache_alloc_node(unsigned long call_site,
+static void kmemtrace_kmem_cache_alloc_node(void *ignore,
+                                            unsigned long call_site,
                                             const void *ptr,
                                             size_t bytes_req,
                                             size_t bytes_alloc,
@@ -137,12 +141,14 @@ static void kmemtrace_kmem_cache_alloc_node(unsigned long call_site,
                         bytes_req, bytes_alloc, gfp_flags, node);
 }
 
-static void kmemtrace_kfree(unsigned long call_site, const void *ptr)
+static void
+kmemtrace_kfree(void *ignore, unsigned long call_site, const void *ptr)
 {
         kmemtrace_free(KMEMTRACE_TYPE_KMALLOC, call_site, ptr);
 }
 
-static void kmemtrace_kmem_cache_free(unsigned long call_site, const void *ptr)
+static void kmemtrace_kmem_cache_free(void *ignore,
+                                      unsigned long call_site, const void *ptr)
 {
         kmemtrace_free(KMEMTRACE_TYPE_CACHE, call_site, ptr);
 }
@@ -151,34 +157,34 @@ static int kmemtrace_start_probes(void)
 {
         int err;
 
-        err = register_trace_kmalloc(kmemtrace_kmalloc);
+        err = register_trace_kmalloc(kmemtrace_kmalloc, NULL);
         if (err)
                 return err;
-        err = register_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc);
+        err = register_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc, NULL);
         if (err)
                 return err;
-        err = register_trace_kmalloc_node(kmemtrace_kmalloc_node);
+        err = register_trace_kmalloc_node(kmemtrace_kmalloc_node, NULL);
         if (err)
                 return err;
-        err = register_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node);
+        err = register_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node, NULL);
         if (err)
                 return err;
-        err = register_trace_kfree(kmemtrace_kfree);
+        err = register_trace_kfree(kmemtrace_kfree, NULL);
         if (err)
                 return err;
-        err = register_trace_kmem_cache_free(kmemtrace_kmem_cache_free);
+        err = register_trace_kmem_cache_free(kmemtrace_kmem_cache_free, NULL);
 
         return err;
 }
 
 static void kmemtrace_stop_probes(void)
 {
-        unregister_trace_kmalloc(kmemtrace_kmalloc);
-        unregister_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc);
-        unregister_trace_kmalloc_node(kmemtrace_kmalloc_node);
-        unregister_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node);
-        unregister_trace_kfree(kmemtrace_kfree);
-        unregister_trace_kmem_cache_free(kmemtrace_kmem_cache_free);
+        unregister_trace_kmalloc(kmemtrace_kmalloc, NULL);
+        unregister_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc, NULL);
+        unregister_trace_kmalloc_node(kmemtrace_kmalloc_node, NULL);
+        unregister_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node, NULL);
+        unregister_trace_kfree(kmemtrace_kfree, NULL);
+        unregister_trace_kmem_cache_free(kmemtrace_kmem_cache_free, NULL);
 }
 
 static int kmem_trace_init(struct trace_array *tr)
@@ -237,7 +243,8 @@ struct kmemtrace_user_event_alloc {
 };
 
 static enum print_line_t
-kmemtrace_print_alloc(struct trace_iterator *iter, int flags)
+kmemtrace_print_alloc(struct trace_iterator *iter, int flags,
+                      struct trace_event *event)
 {
         struct trace_seq *s = &iter->seq;
         struct kmemtrace_alloc_entry *entry;
@@ -257,7 +264,8 @@ kmemtrace_print_alloc(struct trace_iterator *iter, int flags)
 }
 
 static enum print_line_t
-kmemtrace_print_free(struct trace_iterator *iter, int flags)
+kmemtrace_print_free(struct trace_iterator *iter, int flags,
+                     struct trace_event *event)
 {
         struct trace_seq *s = &iter->seq;
         struct kmemtrace_free_entry *entry;
@@ -275,7 +283,8 @@ kmemtrace_print_free(struct trace_iterator *iter, int flags)
 }
 
 static enum print_line_t
-kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags)
+kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags,
+                           struct trace_event *event)
 {
         struct trace_seq *s = &iter->seq;
         struct kmemtrace_alloc_entry *entry;
@@ -309,7 +318,8 @@ kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags)
 }
 
 static enum print_line_t
-kmemtrace_print_free_user(struct trace_iterator *iter, int flags)
+kmemtrace_print_free_user(struct trace_iterator *iter, int flags,
+                          struct trace_event *event)
 {
         struct trace_seq *s = &iter->seq;
         struct kmemtrace_free_entry *entry;
@@ -463,18 +473,26 @@ static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter)
         }
 }
 
-static struct trace_event kmem_trace_alloc = {
-        .type                   = TRACE_KMEM_ALLOC,
+static struct trace_event_functions kmem_trace_alloc_funcs = {
         .trace                  = kmemtrace_print_alloc,
         .binary                 = kmemtrace_print_alloc_user,
 };
 
-static struct trace_event kmem_trace_free = {
-        .type                   = TRACE_KMEM_FREE,
+static struct trace_event kmem_trace_alloc = {
+        .type                   = TRACE_KMEM_ALLOC,
+        .funcs                  = &kmem_trace_alloc_funcs,
+};
+
+static struct trace_event_functions kmem_trace_free_funcs = {
         .trace                  = kmemtrace_print_free,
         .binary                 = kmemtrace_print_free_user,
 };
 
+static struct trace_event kmem_trace_free = {
+        .type                   = TRACE_KMEM_FREE,
+        .funcs                  = &kmem_trace_free_funcs,
+};
+
 static struct tracer kmem_tracer __read_mostly = {
         .name                   = "kmemtrace",
         .init                   = kmem_trace_init,
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 41ca394feb22..7f6059c5aa94 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -319,6 +319,11 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
 #define TS_MASK         ((1ULL << TS_SHIFT) - 1)
 #define TS_DELTA_TEST   (~TS_MASK)
 
+/* Flag when events were overwritten */
+#define RB_MISSED_EVENTS        (1 << 31)
+/* Missed count stored at end */
+#define RB_MISSED_STORED        (1 << 30)
+
 struct buffer_data_page {
         u64              time_stamp;    /* page time stamp */
         local_t          commit;        /* write committed index */
@@ -338,6 +343,7 @@ struct buffer_page {
         local_t          write;         /* index for next write */
         unsigned         read;          /* index for next read */
         local_t          entries;       /* entries on this page */
+        unsigned long    real_end;      /* real end of data */
         struct buffer_data_page *page;  /* Actual data page */
 };
 
@@ -417,6 +423,12 @@ int ring_buffer_print_page_header(struct trace_seq *s)
                                (unsigned int)sizeof(field.commit),
                                (unsigned int)is_signed_type(long));
 
+        ret = trace_seq_printf(s, "\tfield: int overwrite;\t"
+                               "offset:%u;\tsize:%u;\tsigned:%u;\n",
+                               (unsigned int)offsetof(typeof(field), commit),
+                               1,
+                               (unsigned int)is_signed_type(long));
+
         ret = trace_seq_printf(s, "\tfield: char data;\t"
                                "offset:%u;\tsize:%u;\tsigned:%u;\n",
                                (unsigned int)offsetof(typeof(field), data),
@@ -440,6 +452,8 @@ struct ring_buffer_per_cpu {
         struct buffer_page              *tail_page;     /* write to tail */
         struct buffer_page              *commit_page;   /* committed pages */
         struct buffer_page              *reader_page;
+        unsigned long                   lost_events;
+        unsigned long                   last_overrun;
         local_t                         commit_overrun;
         local_t                         overrun;
         local_t                         entries;
@@ -1762,6 +1776,13 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
         kmemcheck_annotate_bitfield(event, bitfield);
 
         /*
+         * Save the original length to the meta data.
+         * This will be used by the reader to add lost event
+         * counter.
+         */
+        tail_page->real_end = tail;
+
+        /*
          * If this event is bigger than the minimum size, then
          * we need to be careful that we don't subtract the
          * write counter enough to allow another writer to slip
@@ -1979,17 +2000,13 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
                   u64 *ts, u64 *delta)
 {
         struct ring_buffer_event *event;
-        static int once;
         int ret;
 
-        if (unlikely(*delta > (1ULL << 59) && !once++)) {
-                printk(KERN_WARNING "Delta way too big! %llu"
-                       " ts=%llu write stamp = %llu\n",
-                       (unsigned long long)*delta,
-                       (unsigned long long)*ts,
-                       (unsigned long long)cpu_buffer->write_stamp);
-                WARN_ON(1);
-        }
+        WARN_ONCE(*delta > (1ULL << 59),
+                  KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n",
+                  (unsigned long long)*delta,
+                  (unsigned long long)*ts,
+                  (unsigned long long)cpu_buffer->write_stamp);
 
         /*
          * The delta is too big, we to add a
@@ -2838,6 +2855,7 @@ static struct buffer_page *
 rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 {
         struct buffer_page *reader = NULL;
+        unsigned long overwrite;
         unsigned long flags;
         int nr_loops = 0;
         int ret;
@@ -2879,6 +2897,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
         local_set(&cpu_buffer->reader_page->write, 0);
         local_set(&cpu_buffer->reader_page->entries, 0);
         local_set(&cpu_buffer->reader_page->page->commit, 0);
+        cpu_buffer->reader_page->real_end = 0;
 
  spin:
         /*
@@ -2899,6 +2918,18 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
         rb_set_list_to_head(cpu_buffer, &cpu_buffer->reader_page->list);
 
         /*
+         * We want to make sure we read the overruns after we set up our
+         * pointers to the next object. The writer side does a
+         * cmpxchg to cross pages which acts as the mb on the writer
+         * side. Note, the reader will constantly fail the swap
+         * while the writer is updating the pointers, so this
+         * guarantees that the overwrite recorded here is the one we
+         * want to compare with the last_overrun.
+         */
+        smp_mb();
+        overwrite = local_read(&(cpu_buffer->overrun));
+
+        /*
          * Here's the tricky part.
          *
          * We need to move the pointer past the header page.
@@ -2929,6 +2960,11 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
         cpu_buffer->reader_page = reader;
         rb_reset_reader_page(cpu_buffer);
 
+        if (overwrite != cpu_buffer->last_overrun) {
+                cpu_buffer->lost_events = overwrite - cpu_buffer->last_overrun;
+                cpu_buffer->last_overrun = overwrite;
+        }
+
         goto again;
 
  out:
@@ -3005,8 +3041,14 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
                 rb_advance_iter(iter);
 }
 
+static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer)
+{
+        return cpu_buffer->lost_events;
+}
+
 static struct ring_buffer_event *
-rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts)
+rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts,
+               unsigned long *lost_events)
 {
         struct ring_buffer_event *event;
         struct buffer_page *reader;
@@ -3058,6 +3100,8 @@ rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts)
                         ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
                                                          cpu_buffer->cpu, ts);
                 }
+                if (lost_events)
+                        *lost_events = rb_lost_events(cpu_buffer);
                 return event;
 
         default:
@@ -3168,12 +3212,14 @@ static inline int rb_ok_to_lock(void)
  * @buffer: The ring buffer to read
  * @cpu: The cpu to peak at
  * @ts: The timestamp counter of this event.
+ * @lost_events: a variable to store if events were lost (may be NULL)
  *
  * This will return the event that will be read next, but does
  * not consume the data.
  */
 struct ring_buffer_event *
-ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
+ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts,
+                 unsigned long *lost_events)
 {
         struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
         struct ring_buffer_event *event;
@@ -3188,7 +3234,7 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
         local_irq_save(flags);
         if (dolock)
                 spin_lock(&cpu_buffer->reader_lock);
-        event = rb_buffer_peek(cpu_buffer, ts);
+        event = rb_buffer_peek(cpu_buffer, ts, lost_events);
         if (event && event->type_len == RINGBUF_TYPE_PADDING)
                 rb_advance_reader(cpu_buffer);
         if (dolock)
@@ -3230,13 +3276,17 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 /**
  * ring_buffer_consume - return an event and consume it
  * @buffer: The ring buffer to get the next event from
+ * @cpu: the cpu to read the buffer from
+ * @ts: a variable to store the timestamp (may be NULL)
+ * @lost_events: a variable to store if events were lost (may be NULL)
  *
  * Returns the next event in the ring buffer, and that event is consumed.
  * Meaning, that sequential reads will keep returning a different event,
  * and eventually empty the ring buffer if the producer is slower.
  */
 struct ring_buffer_event *
-ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
+ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts,
+                    unsigned long *lost_events)
 {
         struct ring_buffer_per_cpu *cpu_buffer;
         struct ring_buffer_event *event = NULL;
@@ -3257,9 +3307,11 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
         if (dolock)
                 spin_lock(&cpu_buffer->reader_lock);
 
-        event = rb_buffer_peek(cpu_buffer, ts);
-        if (event)
+        event = rb_buffer_peek(cpu_buffer, ts, lost_events);
+        if (event) {
+                cpu_buffer->lost_events = 0;
                 rb_advance_reader(cpu_buffer);
+        }
 
         if (dolock)
                 spin_unlock(&cpu_buffer->reader_lock);
@@ -3276,23 +3328,30 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
 EXPORT_SYMBOL_GPL(ring_buffer_consume);
 
 /**
- * ring_buffer_read_start - start a non consuming read of the buffer
+ * ring_buffer_read_prepare - Prepare for a non consuming read of the buffer
  * @buffer: The ring buffer to read from
  * @cpu: The cpu buffer to iterate over
  *
- * This starts up an iteration through the buffer. It also disables
- * the recording to the buffer until the reading is finished.
- * This prevents the reading from being corrupted. This is not
- * a consuming read, so a producer is not expected.
+ * This performs the initial preparations necessary to iterate
+ * through the buffer.  Memory is allocated, buffer recording
+ * is disabled, and the iterator pointer is returned to the caller.
  *
- * Must be paired with ring_buffer_finish.
+ * Disabling buffer recordng prevents the reading from being
+ * corrupted. This is not a consuming read, so a producer is not
+ * expected.
+ *
+ * After a sequence of ring_buffer_read_prepare calls, the user is
+ * expected to make at least one call to ring_buffer_prepare_sync.
+ * Afterwards, ring_buffer_read_start is invoked to get things going
+ * for real.
+ *
+ * This overall must be paired with ring_buffer_finish.
  */
 struct ring_buffer_iter *
-ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
+ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu)
 {
         struct ring_buffer_per_cpu *cpu_buffer;
         struct ring_buffer_iter *iter;
-        unsigned long flags;
 
         if (!cpumask_test_cpu(cpu, buffer->cpumask))
                 return NULL;
@@ -3306,15 +3365,52 @@ ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
         iter->cpu_buffer = cpu_buffer;
 
         atomic_inc(&cpu_buffer->record_disabled);
+
+        return iter;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_read_prepare);
+
+/**
+ * ring_buffer_read_prepare_sync - Synchronize a set of prepare calls
+ *
+ * All previously invoked ring_buffer_read_prepare calls to prepare
+ * iterators will be synchronized.  Afterwards, read_buffer_read_start
+ * calls on those iterators are allowed.
+ */
+void
+ring_buffer_read_prepare_sync(void)
+{
         synchronize_sched();
+}
+EXPORT_SYMBOL_GPL(ring_buffer_read_prepare_sync);
+
+/**
+ * ring_buffer_read_start - start a non consuming read of the buffer
+ * @iter: The iterator returned by ring_buffer_read_prepare
+ *
+ * This finalizes the startup of an iteration through the buffer.
+ * The iterator comes from a call to ring_buffer_read_prepare and
+ * an intervening ring_buffer_read_prepare_sync must have been
+ * performed.
+ *
+ * Must be paired with ring_buffer_finish.
+ */
+void
+ring_buffer_read_start(struct ring_buffer_iter *iter)
+{
+        struct ring_buffer_per_cpu *cpu_buffer;
+        unsigned long flags;
+
+        if (!iter)
+                return;
+
+        cpu_buffer = iter->cpu_buffer;
 
         spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
         arch_spin_lock(&cpu_buffer->lock);
         rb_iter_reset(iter);
         arch_spin_unlock(&cpu_buffer->lock);
         spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
-
-        return iter;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_start);
 
@@ -3408,6 +3504,9 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
         cpu_buffer->write_stamp = 0;
         cpu_buffer->read_stamp = 0;
 
+        cpu_buffer->lost_events = 0;
+        cpu_buffer->last_overrun = 0;
+
         rb_head_page_activate(cpu_buffer);
 }
 
@@ -3683,6 +3782,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
         struct ring_buffer_event *event;
         struct buffer_data_page *bpage;
         struct buffer_page *reader;
+        unsigned long missed_events;
         unsigned long flags;
         unsigned int commit;
         unsigned int read;
@@ -3719,6 +3819,9 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
         read = reader->read;
         commit = rb_page_commit(reader);
 
+        /* Check if any events were dropped */
+        missed_events = cpu_buffer->lost_events;
+
         /*
          * If this page has been partially read or
          * if len is not big enough to read the rest of the page or
@@ -3779,9 +3882,35 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
                 local_set(&reader->entries, 0);
                 reader->read = 0;
                 *data_page = bpage;
+
+                /*
+                 * Use the real_end for the data size,
+                 * This gives us a chance to store the lost events
+                 * on the page.
+                 */
+                if (reader->real_end)
+                        local_set(&bpage->commit, reader->real_end);
         }
         ret = read;
 
+        cpu_buffer->lost_events = 0;
+        /*
+         * Set a flag in the commit field if we lost events
+         */
+        if (missed_events) {
+                commit = local_read(&bpage->commit);
+
+                /* If there is room at the end of the page to save the
+                 * missed events, then record it there.
+                 */
+                if (BUF_PAGE_SIZE - commit >= sizeof(missed_events)) {
+                        memcpy(&bpage->data[commit], &missed_events,
+                               sizeof(missed_events));
+                        local_add(RB_MISSED_STORED, &bpage->commit);
+                }
+                local_add(RB_MISSED_EVENTS, &bpage->commit);
+        }
+
  out_unlock:
         spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index df74c7982255..302f8a614635 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -81,7 +81,7 @@ static enum event_status read_event(int cpu)
         int *entry;
         u64 ts;
 
-        event = ring_buffer_consume(buffer, cpu, &ts);
+        event = ring_buffer_consume(buffer, cpu, &ts, NULL);
         if (!event)
                 return EVENT_DROPPED;
 
@@ -113,7 +113,8 @@ static enum event_status read_page(int cpu)
         ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1);
         if (ret >= 0) {
                 rpage = bpage;
-                commit = local_read(&rpage->commit);
+                /* The commit may have missed event flags set, clear them */
+                commit = local_read(&rpage->commit) & 0xfffff;
                 for (i = 0; i < commit && !kill_test; i += inc) {
 
                         if (i >= (PAGE_SIZE - offsetof(struct rb_page, data))) {
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 44f916a04065..ba0ec81158b2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -117,9 +117,12 @@ static cpumask_var_t __read_mostly	tracing_buffer_mask;
  *
  * It is default off, but you can enable it with either specifying
  * "ftrace_dump_on_oops" in the kernel command line, or setting
- * /proc/sys/kernel/ftrace_dump_on_oops to true.
+ * /proc/sys/kernel/ftrace_dump_on_oops
+ * Set 1 if you want to dump buffers of all CPUs
+ * Set 2 if you want to dump the buffer of the CPU that triggered oops
  */
-int ftrace_dump_on_oops;
+
+enum ftrace_dump_mode ftrace_dump_on_oops;
 
 static int tracing_set_tracer(const char *buf);
 
@@ -139,8 +142,17 @@ __setup("ftrace=", set_cmdline_ftrace);
 
 static int __init set_ftrace_dump_on_oops(char *str)
 {
-        ftrace_dump_on_oops = 1;
-        return 1;
+        if (*str++ != '=' || !*str) {
+                ftrace_dump_on_oops = DUMP_ALL;
+                return 1;
+        }
+
+        if (!strcmp("orig_cpu", str)) {
+                ftrace_dump_on_oops = DUMP_ORIG;
+                return 1;
+        }
+
+        return 0;
 }
 __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops);
 
@@ -1545,7 +1557,8 @@ static void trace_iterator_increment(struct trace_iterator *iter)
 }
 
 static struct trace_entry *
-peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
+peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
+                unsigned long *lost_events)
 {
         struct ring_buffer_event *event;
         struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu];
@@ -1556,7 +1569,8 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
         if (buf_iter)
                 event = ring_buffer_iter_peek(buf_iter, ts);
         else
-                event = ring_buffer_peek(iter->tr->buffer, cpu, ts);
+                event = ring_buffer_peek(iter->tr->buffer, cpu, ts,
+                                         lost_events);
 
         ftrace_enable_cpu();
 
@@ -1564,10 +1578,12 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
 }
 
 static struct trace_entry *
-__find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
+__find_next_entry(struct trace_iterator *iter, int *ent_cpu,
+                  unsigned long *missing_events, u64 *ent_ts)
 {
         struct ring_buffer *buffer = iter->tr->buffer;
         struct trace_entry *ent, *next = NULL;
+        unsigned long lost_events = 0, next_lost = 0;
         int cpu_file = iter->cpu_file;
         u64 next_ts = 0, ts;
         int next_cpu = -1;
@@ -1580,7 +1596,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
         if (cpu_file > TRACE_PIPE_ALL_CPU) {
                 if (ring_buffer_empty_cpu(buffer, cpu_file))
                         return NULL;
-                ent = peek_next_entry(iter, cpu_file, ent_ts);
+                ent = peek_next_entry(iter, cpu_file, ent_ts, missing_events);
                 if (ent_cpu)
                         *ent_cpu = cpu_file;
 
@@ -1592,7 +1608,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
                 if (ring_buffer_empty_cpu(buffer, cpu))
                         continue;
 
-                ent = peek_next_entry(iter, cpu, &ts);
+                ent = peek_next_entry(iter, cpu, &ts, &lost_events);
 
                 /*
                  * Pick the entry with the smallest timestamp:
@@ -1601,6 +1617,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
                         next = ent;
                         next_cpu = cpu;
                         next_ts = ts;
+                        next_lost = lost_events;
                 }
         }
 
@@ -1610,6 +1627,9 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
         if (ent_ts)
                 *ent_ts = next_ts;
 
+        if (missing_events)
+                *missing_events = next_lost;
+
         return next;
 }
 
@@ -1617,13 +1637,14 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
                                           int *ent_cpu, u64 *ent_ts)
 {
-        return __find_next_entry(iter, ent_cpu, ent_ts);
+        return __find_next_entry(iter, ent_cpu, NULL, ent_ts);
 }
 
 /* Find the next real entry, and increment the iterator to the next entry */
 static void *find_next_entry_inc(struct trace_iterator *iter)
 {
-        iter->ent = __find_next_entry(iter, &iter->cpu, &iter->ts);
+        iter->ent = __find_next_entry(iter, &iter->cpu,
+                                      &iter->lost_events, &iter->ts);
 
         if (iter->ent)
                 trace_iterator_increment(iter);
@@ -1635,7 +1656,8 @@ static void trace_consume(struct trace_iterator *iter)
 {
         /* Don't allow ftrace to trace into the ring buffers */
         ftrace_disable_cpu();
-        ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts);
+        ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts,
+                            &iter->lost_events);
         ftrace_enable_cpu();
 }
 
@@ -1786,7 +1808,7 @@ static void print_func_help_header(struct seq_file *m)
 }
 
 
-static void
+void
 print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 {
         unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
@@ -1914,7 +1936,7 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
         }
 
         if (event)
-                return event->trace(iter, sym_flags);
+                return event->funcs->trace(iter, sym_flags, event);
 
         if (!trace_seq_printf(s, "Unknown type %d\n", entry->type))
                 goto partial;
@@ -1940,7 +1962,7 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
 
         event = ftrace_find_event(entry->type);
         if (event)
-                return event->raw(iter, 0);
+                return event->funcs->raw(iter, 0, event);
 
         if (!trace_seq_printf(s, "%d ?\n", entry->type))
                 goto partial;
@@ -1967,7 +1989,7 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
 
         event = ftrace_find_event(entry->type);
         if (event) {
-                enum print_line_t ret = event->hex(iter, 0);
+                enum print_line_t ret = event->funcs->hex(iter, 0, event);
                 if (ret != TRACE_TYPE_HANDLED)
                         return ret;
         }
@@ -1992,10 +2014,11 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
         }
 
         event = ftrace_find_event(entry->type);
-        return event ? event->binary(iter, 0) : TRACE_TYPE_HANDLED;
+        return event ? event->funcs->binary(iter, 0, event) :
+                TRACE_TYPE_HANDLED;
 }
 
-static int trace_empty(struct trace_iterator *iter)
+int trace_empty(struct trace_iterator *iter)
 {
         int cpu;
 
@@ -2030,6 +2053,10 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
 {
         enum print_line_t ret;
 
+        if (iter->lost_events)
+                trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n",
+                                 iter->cpu, iter->lost_events);
+
         if (iter->trace && iter->trace->print_line) {
                 ret = iter->trace->print_line(iter);
                 if (ret != TRACE_TYPE_UNHANDLED)
@@ -2058,6 +2085,23 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
         return print_trace_fmt(iter);
 }
 
+void trace_default_header(struct seq_file *m)
+{
+        struct trace_iterator *iter = m->private;
+
+        if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
+                /* print nothing if the buffers are empty */
+                if (trace_empty(iter))
+                        return;
+                print_trace_header(m, iter);
+                if (!(trace_flags & TRACE_ITER_VERBOSE))
+                        print_lat_help_header(m);
+        } else {
+                if (!(trace_flags & TRACE_ITER_VERBOSE))
+                        print_func_help_header(m);
+        }
+}
+
 static int s_show(struct seq_file *m, void *v)
 {
         struct trace_iterator *iter = v;
@@ -2070,17 +2114,9 @@ static int s_show(struct seq_file *m, void *v)
                 }
                 if (iter->trace && iter->trace->print_header)
                         iter->trace->print_header(m);
-                else if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
-                        /* print nothing if the buffers are empty */
-                        if (trace_empty(iter))
-                                return 0;
-                        print_trace_header(m, iter);
-                        if (!(trace_flags & TRACE_ITER_VERBOSE))
-                                print_lat_help_header(m);
-                } else {
-                        if (!(trace_flags & TRACE_ITER_VERBOSE))
-                                print_func_help_header(m);
-                }
+                else
+                        trace_default_header(m);
+
         } else if (iter->leftover) {
                 /*
                  * If we filled the seq_file buffer earlier, we
@@ -2166,15 +2202,20 @@ __tracing_open(struct inode *inode, struct file *file)
 
         if (iter->cpu_file == TRACE_PIPE_ALL_CPU) {
                 for_each_tracing_cpu(cpu) {
-
                         iter->buffer_iter[cpu] =
-                                ring_buffer_read_start(iter->tr->buffer, cpu);
+                                ring_buffer_read_prepare(iter->tr->buffer, cpu);
+                }
+                ring_buffer_read_prepare_sync();
+                for_each_tracing_cpu(cpu) {
+                        ring_buffer_read_start(iter->buffer_iter[cpu]);
                         tracing_iter_reset(iter, cpu);
                 }
         } else {
                 cpu = iter->cpu_file;
                 iter->buffer_iter[cpu] =
-                                ring_buffer_read_start(iter->tr->buffer, cpu);
+                        ring_buffer_read_prepare(iter->tr->buffer, cpu);
+                ring_buffer_read_prepare_sync();
+                ring_buffer_read_start(iter->buffer_iter[cpu]);
                 tracing_iter_reset(iter, cpu);
         }
 
@@ -4324,7 +4365,7 @@ static int trace_panic_handler(struct notifier_block *this,
                                unsigned long event, void *unused)
 {
         if (ftrace_dump_on_oops)
-                ftrace_dump();
+                ftrace_dump(ftrace_dump_on_oops);
         return NOTIFY_OK;
 }
 
@@ -4341,7 +4382,7 @@ static int trace_die_handler(struct notifier_block *self,
         switch (val) {
         case DIE_OOPS:
                 if (ftrace_dump_on_oops)
-                        ftrace_dump();
+                        ftrace_dump(ftrace_dump_on_oops);
                 break;
         default:
                 break;
@@ -4382,7 +4423,8 @@ trace_printk_seq(struct trace_seq *s)
         trace_seq_init(s);
 }
 
-static void __ftrace_dump(bool disable_tracing)
+static void
+__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
 {
         static arch_spinlock_t ftrace_dump_lock =
                 (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
@@ -4415,12 +4457,25 @@ static void __ftrace_dump(bool disable_tracing)
         /* don't look at user memory in panic mode */
         trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
 
-        printk(KERN_TRACE "Dumping ftrace buffer:\n");
-
         /* Simulate the iterator */
         iter.tr = &global_trace;
         iter.trace = current_trace;
-        iter.cpu_file = TRACE_PIPE_ALL_CPU;
+
+        switch (oops_dump_mode) {
+        case DUMP_ALL:
+                iter.cpu_file = TRACE_PIPE_ALL_CPU;
+                break;
+        case DUMP_ORIG:
+                iter.cpu_file = raw_smp_processor_id();
+                break;
+        case DUMP_NONE:
+                goto out_enable;
+        default:
+                printk(KERN_TRACE "Bad dumping mode, switching to all CPUs dump\n");
+                iter.cpu_file = TRACE_PIPE_ALL_CPU;
+        }
+
+        printk(KERN_TRACE "Dumping ftrace buffer:\n");
 
         /*
          * We need to stop all tracing on all CPUS to read the
@@ -4459,6 +4514,7 @@ static void __ftrace_dump(bool disable_tracing)
         else
                 printk(KERN_TRACE "---------------------------------\n");
 
+ out_enable:
         /* Re-enable tracing if requested */
         if (!disable_tracing) {
                 trace_flags |= old_userobj;
@@ -4475,9 +4531,9 @@ static void __ftrace_dump(bool disable_tracing)
 }
 
 /* By default: disable tracing after the dump */
-void ftrace_dump(void)
+void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 {
-        __ftrace_dump(true);
+        __ftrace_dump(true, oops_dump_mode);
 }
 
 __init static int tracer_alloc_buffers(void)
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 3ebdb6bd2362..2cd96399463f 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -364,6 +364,9 @@ void trace_function(struct trace_array *tr,
                     unsigned long ip,
                     unsigned long parent_ip,
                     unsigned long flags, int pc);
+void trace_default_header(struct seq_file *m);
+void print_trace_header(struct seq_file *m, struct trace_iterator *iter);
+int trace_empty(struct trace_iterator *iter);
 
 void trace_graph_return(struct ftrace_graph_ret *trace);
 int trace_graph_entry(struct ftrace_graph_ent *trace);
@@ -402,12 +405,12 @@ void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags,
 void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
                    int pc);
 #else
-static inline void ftrace_trace_stack(struct trace_array *tr,
+static inline void ftrace_trace_stack(struct ring_buffer *buffer,
                                       unsigned long flags, int skip, int pc)
 {
 }
 
-static inline void ftrace_trace_userstack(struct trace_array *tr,
+static inline void ftrace_trace_userstack(struct ring_buffer *buffer,
                                           unsigned long flags, int pc)
 {
 }
@@ -475,9 +478,29 @@ extern int trace_clock_id;
 
 /* Standard output formatting function used for function return traces */
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-extern enum print_line_t print_graph_function(struct trace_iterator *iter);
+
+/* Flag options */
+#define TRACE_GRAPH_PRINT_OVERRUN       0x1
+#define TRACE_GRAPH_PRINT_CPU           0x2
+#define TRACE_GRAPH_PRINT_OVERHEAD      0x4
+#define TRACE_GRAPH_PRINT_PROC          0x8
+#define TRACE_GRAPH_PRINT_DURATION      0x10
+#define TRACE_GRAPH_PRINT_ABS_TIME      0x20
+
+extern enum print_line_t
+print_graph_function_flags(struct trace_iterator *iter, u32 flags);
+extern void print_graph_headers_flags(struct seq_file *s, u32 flags);
 extern enum print_line_t
 trace_print_graph_duration(unsigned long long duration, struct trace_seq *s);
+extern void graph_trace_open(struct trace_iterator *iter);
+extern void graph_trace_close(struct trace_iterator *iter);
+extern int __trace_graph_entry(struct trace_array *tr,
+                               struct ftrace_graph_ent *trace,
+                               unsigned long flags, int pc);
+extern void __trace_graph_return(struct trace_array *tr,
+                                 struct ftrace_graph_ret *trace,
+                                 unsigned long flags, int pc);
+
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 /* TODO: make this variable */
@@ -508,7 +531,7 @@ static inline int ftrace_graph_addr(unsigned long addr)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 #else /* CONFIG_FUNCTION_GRAPH_TRACER */
 static inline enum print_line_t
-print_graph_function(struct trace_iterator *iter)
+print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 {
         return TRACE_TYPE_UNHANDLED;
 }
@@ -755,12 +778,15 @@ extern void print_subsystem_event_filter(struct event_subsystem *system,
                                          struct trace_seq *s);
 extern int filter_assign_type(const char *type);
 
+struct list_head *
+trace_get_fields(struct ftrace_event_call *event_call);
+
 static inline int
 filter_check_discard(struct ftrace_event_call *call, void *rec,
                      struct ring_buffer *buffer,
                      struct ring_buffer_event *event)
 {
-        if (unlikely(call->filter_active) &&
+        if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) &&
             !filter_match_preds(call->filter, rec)) {
                 ring_buffer_discard_commit(buffer, event);
                 return 1;
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index b9bc4d470177..8d3538b4ea5f 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -143,7 +143,7 @@ static void branch_trace_reset(struct trace_array *tr)
 }
 
 static enum print_line_t trace_branch_print(struct trace_iterator *iter,
-                                            int flags)
+                                            int flags, struct trace_event *event)
 {
         struct trace_branch *field;
 
@@ -167,9 +167,13 @@ static void branch_print_header(struct seq_file *s)
                 "    |\n");
 }
 
+static struct trace_event_functions trace_branch_funcs = {
+        .trace          = trace_branch_print,
+};
+
 static struct trace_event trace_branch_event = {
         .type           = TRACE_BRANCH,
-        .trace          = trace_branch_print,
+        .funcs          = &trace_branch_funcs,
 };
 
 static struct tracer branch_trace __read_mostly =
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 0565bb42566f..0a47e8d6b491 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -49,7 +49,12 @@ static int perf_trace_event_enable(struct ftrace_event_call *event)
                 rcu_assign_pointer(perf_trace_buf_nmi, buf);
         }
 
-        ret = event->perf_event_enable(event);
+        if (event->class->reg)
+                ret = event->class->reg(event, TRACE_REG_PERF_REGISTER);
+        else
+                ret = tracepoint_probe_register(event->name,
+                                                event->class->perf_probe,
+                                                event);
         if (!ret) {
                 total_ref_count++;
                 return 0;
@@ -75,7 +80,8 @@ int perf_trace_enable(int event_id)
 
         mutex_lock(&event_mutex);
         list_for_each_entry(event, &ftrace_events, list) {
-                if (event->id == event_id && event->perf_event_enable &&
+                if (event->event.type == event_id &&
+                    event->class && event->class->perf_probe &&
                     try_module_get(event->mod)) {
                         ret = perf_trace_event_enable(event);
                         break;
@@ -93,7 +99,10 @@ static void perf_trace_event_disable(struct ftrace_event_call *event)
         if (--event->perf_refcount > 0)
                 return;
 
-        event->perf_event_disable(event);
+        if (event->class->reg)
+                event->class->reg(event, TRACE_REG_PERF_UNREGISTER);
+        else
+                tracepoint_probe_unregister(event->name, event->class->perf_probe, event);
 
         if (!--total_ref_count) {
                 buf = perf_trace_buf;
@@ -119,7 +128,7 @@ void perf_trace_disable(int event_id)
 
         mutex_lock(&event_mutex);
         list_for_each_entry(event, &ftrace_events, list) {
-                if (event->id == event_id) {
+                if (event->event.type == event_id) {
                         perf_trace_event_disable(event);
                         module_put(event->mod);
                         break;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index c697c7043349..53cffc0b0801 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -29,11 +29,23 @@ DEFINE_MUTEX(event_mutex);
 
 LIST_HEAD(ftrace_events);
 
+struct list_head *
+trace_get_fields(struct ftrace_event_call *event_call)
+{
+        if (!event_call->class->get_fields)
+                return &event_call->class->fields;
+        return event_call->class->get_fields(event_call);
+}
+
 int trace_define_field(struct ftrace_event_call *call, const char *type,
                        const char *name, int offset, int size, int is_signed,
                        int filter_type)
 {
         struct ftrace_event_field *field;
+        struct list_head *head;
+
+        if (WARN_ON(!call->class))
+                return 0;
 
         field = kzalloc(sizeof(*field), GFP_KERNEL);
         if (!field)
@@ -56,7 +68,8 @@ int trace_define_field(struct ftrace_event_call *call, const char *type,
         field->size = size;
         field->is_signed = is_signed;
 
-        list_add(&field->link, &call->fields);
+        head = trace_get_fields(call);
+        list_add(&field->link, head);
 
         return 0;
 
@@ -94,8 +107,10 @@ static int trace_define_common_fields(struct ftrace_event_call *call)
 void trace_destroy_fields(struct ftrace_event_call *call)
 {
         struct ftrace_event_field *field, *next;
+        struct list_head *head;
 
-        list_for_each_entry_safe(field, next, &call->fields, link) {
+        head = trace_get_fields(call);
+        list_for_each_entry_safe(field, next, head, link) {
                 list_del(&field->link);
                 kfree(field->type);
                 kfree(field->name);
@@ -107,11 +122,9 @@ int trace_event_raw_init(struct ftrace_event_call *call)
 {
         int id;
 
-        id = register_ftrace_event(call->event);
+        id = register_ftrace_event(&call->event);
         if (!id)
                 return -ENODEV;
-        call->id = id;
-        INIT_LIST_HEAD(&call->fields);
 
         return 0;
 }
@@ -124,23 +137,33 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call,
 
         switch (enable) {
         case 0:
-                if (call->enabled) {
-                        call->enabled = 0;
+                if (call->flags & TRACE_EVENT_FL_ENABLED) {
+                        call->flags &= ~TRACE_EVENT_FL_ENABLED;
                         tracing_stop_cmdline_record();
-                        call->unregfunc(call);
+                        if (call->class->reg)
+                                call->class->reg(call, TRACE_REG_UNREGISTER);
+                        else
+                                tracepoint_probe_unregister(call->name,
+                                                            call->class->probe,
+                                                            call);
                 }
                 break;
         case 1:
-                if (!call->enabled) {
+                if (!(call->flags & TRACE_EVENT_FL_ENABLED)) {
                         tracing_start_cmdline_record();
-                        ret = call->regfunc(call);
+                        if (call->class->reg)
+                                ret = call->class->reg(call, TRACE_REG_REGISTER);
+                        else
+                                ret = tracepoint_probe_register(call->name,
+                                                                call->class->probe,
+                                                                call);
                         if (ret) {
                                 tracing_stop_cmdline_record();
                                 pr_info("event trace: Could not enable event "
                                         "%s\n", call->name);
                                 break;
                         }
-                        call->enabled = 1;
+                        call->flags |= TRACE_EVENT_FL_ENABLED;
                 }
                 break;
         }
@@ -171,15 +194,16 @@ static int __ftrace_set_clr_event(const char *match, const char *sub,
         mutex_lock(&event_mutex);
         list_for_each_entry(call, &ftrace_events, list) {
 
-                if (!call->name || !call->regfunc)
+                if (!call->name || !call->class ||
+                    (!call->class->probe && !call->class->reg))
                         continue;
 
                 if (match &&
                     strcmp(match, call->name) != 0 &&
-                    strcmp(match, call->system) != 0)
+                    strcmp(match, call->class->system) != 0)
                         continue;
 
-                if (sub && strcmp(sub, call->system) != 0)
+                if (sub && strcmp(sub, call->class->system) != 0)
                         continue;
 
                 if (event && strcmp(event, call->name) != 0)
@@ -297,7 +321,7 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
                  * The ftrace subsystem is for showing formats only.
                  * They can not be enabled or disabled via the event files.
                  */
-                if (call->regfunc)
+                if (call->class && (call->class->probe || call->class->reg))
                         return call;
         }
 
@@ -328,7 +352,7 @@ s_next(struct seq_file *m, void *v, loff_t *pos)
         (*pos)++;
 
         list_for_each_entry_continue(call, &ftrace_events, list) {
-                if (call->enabled)
+                if (call->flags & TRACE_EVENT_FL_ENABLED)
                         return call;
         }
 
@@ -355,8 +379,8 @@ static int t_show(struct seq_file *m, void *v)
 {
         struct ftrace_event_call *call = v;
 
-        if (strcmp(call->system, TRACE_SYSTEM) != 0)
-                seq_printf(m, "%s:", call->system);
+        if (strcmp(call->class->system, TRACE_SYSTEM) != 0)
+                seq_printf(m, "%s:", call->class->system);
         seq_printf(m, "%s\n", call->name);
 
         return 0;
@@ -387,7 +411,7 @@ event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
         struct ftrace_event_call *call = filp->private_data;
         char *buf;
 
-        if (call->enabled)
+        if (call->flags & TRACE_EVENT_FL_ENABLED)
                 buf = "1\n";
         else
                 buf = "0\n";
@@ -450,10 +474,11 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
 
         mutex_lock(&event_mutex);
         list_for_each_entry(call, &ftrace_events, list) {
-                if (!call->name || !call->regfunc)
+                if (!call->name || !call->class ||
+                    (!call->class->probe && !call->class->reg))
                         continue;
 
-                if (system && strcmp(call->system, system) != 0)
+                if (system && strcmp(call->class->system, system) != 0)
                         continue;
 
                 /*
@@ -461,7 +486,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
                  * or if all events or cleared, or if we have
                  * a mixture.
                  */
-                set |= (1 << !!call->enabled);
+                set |= (1 << !!(call->flags & TRACE_EVENT_FL_ENABLED));
 
                 /*
                  * If we have a mixture, no need to look further.
@@ -525,6 +550,7 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
 {
         struct ftrace_event_call *call = filp->private_data;
         struct ftrace_event_field *field;
+        struct list_head *head;
         struct trace_seq *s;
         int common_field_count = 5;
         char *buf;
@@ -540,10 +566,11 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
         trace_seq_init(s);
 
         trace_seq_printf(s, "name: %s\n", call->name);
-        trace_seq_printf(s, "ID: %d\n", call->id);
+        trace_seq_printf(s, "ID: %d\n", call->event.type);
         trace_seq_printf(s, "format:\n");
 
-        list_for_each_entry_reverse(field, &call->fields, link) {
+        head = trace_get_fields(call);
+        list_for_each_entry_reverse(field, head, link) {
                 /*
                  * Smartly shows the array type(except dynamic array).
                  * Normal:
@@ -613,7 +640,7 @@ event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
                 return -ENOMEM;
 
         trace_seq_init(s);
-        trace_seq_printf(s, "%d\n", call->id);
+        trace_seq_printf(s, "%d\n", call->event.type);
 
         r = simple_read_from_buffer(ubuf, cnt, ppos,
                                     s->buffer, s->len);
@@ -919,14 +946,15 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
                  const struct file_operations *filter,
                  const struct file_operations *format)
 {
+        struct list_head *head;
         int ret;
 
         /*
          * If the trace point header did not define TRACE_SYSTEM
          * then the system would be called "TRACE_SYSTEM".
          */
-        if (strcmp(call->system, TRACE_SYSTEM) != 0)
-                d_events = event_subsystem_dir(call->system, d_events);
+        if (strcmp(call->class->system, TRACE_SYSTEM) != 0)
+                d_events = event_subsystem_dir(call->class->system, d_events);
 
         call->dir = debugfs_create_dir(call->name, d_events);
         if (!call->dir) {
@@ -935,22 +963,31 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
                 return -1;
         }
 
-        if (call->regfunc)
+        if (call->class->probe || call->class->reg)
                 trace_create_file("enable", 0644, call->dir, call,
                                   enable);
 
-        if (call->id && call->perf_event_enable)
+#ifdef CONFIG_PERF_EVENTS
+        if (call->event.type && (call->class->perf_probe || call->class->reg))
                 trace_create_file("id", 0444, call->dir, call,
                                   id);
+#endif
 
-        if (call->define_fields) {
-                ret = trace_define_common_fields(call);
-                if (!ret)
-                        ret = call->define_fields(call);
-                if (ret < 0) {
-                        pr_warning("Could not initialize trace point"
-                                   " events/%s\n", call->name);
-                        return ret;
+        if (call->class->define_fields) {
+                /*
+                 * Other events may have the same class. Only update
+                 * the fields if they are not already defined.
+                 */
+                head = trace_get_fields(call);
+                if (list_empty(head)) {
+                        ret = trace_define_common_fields(call);
+                        if (!ret)
+                                ret = call->class->define_fields(call);
+                        if (ret < 0) {
+                                pr_warning("Could not initialize trace point"
+                                           " events/%s\n", call->name);
+                                return ret;
+                        }
                 }
                 trace_create_file("filter", 0644, call->dir, call,
                                   filter);
@@ -970,8 +1007,8 @@ static int __trace_add_event_call(struct ftrace_event_call *call)
         if (!call->name)
                 return -EINVAL;
 
-        if (call->raw_init) {
-                ret = call->raw_init(call);
+        if (call->class->raw_init) {
+                ret = call->class->raw_init(call);
                 if (ret < 0) {
                         if (ret != -ENOSYS)
                                 pr_warning("Could not initialize trace "
@@ -1035,13 +1072,13 @@ static void remove_subsystem_dir(const char *name)
 static void __trace_remove_event_call(struct ftrace_event_call *call)
 {
         ftrace_event_enable_disable(call, 0);
-        if (call->event)
-                __unregister_ftrace_event(call->event);
+        if (call->event.funcs)
+                __unregister_ftrace_event(&call->event);
         debugfs_remove_recursive(call->dir);
         list_del(&call->list);
         trace_destroy_fields(call);
         destroy_preds(call);
-        remove_subsystem_dir(call->system);
+        remove_subsystem_dir(call->class->system);
 }
 
 /* Remove an event_call */
@@ -1132,8 +1169,8 @@ static void trace_module_add_events(struct module *mod)
                 /* The linker may leave blanks */
                 if (!call->name)
                         continue;
-                if (call->raw_init) {
-                        ret = call->raw_init(call);
+                if (call->class->raw_init) {
+                        ret = call->class->raw_init(call);
                         if (ret < 0) {
                                 if (ret != -ENOSYS)
                                         pr_warning("Could not initialize trace "
@@ -1286,8 +1323,8 @@ static __init int event_trace_init(void)
                 /* The linker may leave blanks */
                 if (!call->name)
                         continue;
-                if (call->raw_init) {
-                        ret = call->raw_init(call);
+                if (call->class->raw_init) {
+                        ret = call->class->raw_init(call);
                         if (ret < 0) {
                                 if (ret != -ENOSYS)
                                         pr_warning("Could not initialize trace "
@@ -1388,8 +1425,8 @@ static __init void event_trace_self_tests(void)
 
         list_for_each_entry(call, &ftrace_events, list) {
 
-                /* Only test those that have a regfunc */
-                if (!call->regfunc)
+                /* Only test those that have a probe */
+                if (!call->class || !call->class->probe)
                         continue;
 
 /*
@@ -1399,8 +1436,8 @@ static __init void event_trace_self_tests(void)
  * syscalls as we test.
  */
 #ifndef CONFIG_EVENT_TRACE_TEST_SYSCALLS
-                if (call->system &&
-                    strcmp(call->system, "syscalls") == 0)
+                if (call->class->system &&
+                    strcmp(call->class->system, "syscalls") == 0)
                         continue;
 #endif
 
@@ -1410,7 +1447,7 @@ static __init void event_trace_self_tests(void)
                  * If an event is already enabled, someone is using
                  * it and the self test should not be on.
                  */
-                if (call->enabled) {
+                if (call->flags & TRACE_EVENT_FL_ENABLED) {
                         pr_warning("Enabled event during self test!\n");
                         WARN_ON_ONCE(1);
                         continue;
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 58092d844a1f..57bb1bb32999 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -500,8 +500,10 @@ static struct ftrace_event_field *
 find_event_field(struct ftrace_event_call *call, char *name)
 {
         struct ftrace_event_field *field;
+        struct list_head *head;
 
-        list_for_each_entry(field, &call->fields, link) {
+        head = trace_get_fields(call);
+        list_for_each_entry(field, head, link) {
                 if (!strcmp(field->name, name))
                         return field;
         }
@@ -545,7 +547,7 @@ static void filter_disable_preds(struct ftrace_event_call *call)
         struct event_filter *filter = call->filter;
         int i;
 
-        call->filter_active = 0;
+        call->flags &= ~TRACE_EVENT_FL_FILTERED;
         filter->n_preds = 0;
 
         for (i = 0; i < MAX_FILTER_PRED; i++)
@@ -572,7 +574,7 @@ void destroy_preds(struct ftrace_event_call *call)
 {
         __free_preds(call->filter);
         call->filter = NULL;
-        call->filter_active = 0;
+        call->flags &= ~TRACE_EVENT_FL_FILTERED;
 }
 
 static struct event_filter *__alloc_preds(void)
@@ -611,7 +613,7 @@ static int init_preds(struct ftrace_event_call *call)
         if (call->filter)
                 return 0;
 
-        call->filter_active = 0;
+        call->flags &= ~TRACE_EVENT_FL_FILTERED;
         call->filter = __alloc_preds();
         if (IS_ERR(call->filter))
                 return PTR_ERR(call->filter);
@@ -625,10 +627,10 @@ static int init_subsystem_preds(struct event_subsystem *system)
         int err;
 
         list_for_each_entry(call, &ftrace_events, list) {
-                if (!call->define_fields)
+                if (!call->class || !call->class->define_fields)
                         continue;
 
-                if (strcmp(call->system, system->name) != 0)
+                if (strcmp(call->class->system, system->name) != 0)
                         continue;
 
                 err = init_preds(call);
@@ -644,10 +646,10 @@ static void filter_free_subsystem_preds(struct event_subsystem *system)
         struct ftrace_event_call *call;
 
         list_for_each_entry(call, &ftrace_events, list) {
-                if (!call->define_fields)
+                if (!call->class || !call->class->define_fields)
                         continue;
 
-                if (strcmp(call->system, system->name) != 0)
+                if (strcmp(call->class->system, system->name) != 0)
                         continue;
 
                 filter_disable_preds(call);
@@ -1249,10 +1251,10 @@ static int replace_system_preds(struct event_subsystem *system,
         list_for_each_entry(call, &ftrace_events, list) {
                 struct event_filter *filter = call->filter;
 
-                if (!call->define_fields)
+                if (!call->class || !call->class->define_fields)
                         continue;
 
-                if (strcmp(call->system, system->name) != 0)
+                if (strcmp(call->class->system, system->name) != 0)
                         continue;
 
                 /* try to see if the filter can be applied */
@@ -1266,7 +1268,7 @@ static int replace_system_preds(struct event_subsystem *system,
                 if (err)
                         filter_disable_preds(call);
                 else {
-                        call->filter_active = 1;
+                        call->flags |= TRACE_EVENT_FL_FILTERED;
                         replace_filter_string(filter, filter_string);
                 }
                 fail = false;
@@ -1315,7 +1317,7 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
         if (err)
                 append_filter_err(ps, call->filter);
         else
-                call->filter_active = 1;
+                call->flags |= TRACE_EVENT_FL_FILTERED;
 out:
         filter_opstack_clear(ps);
         postfix_clear(ps);
@@ -1393,7 +1395,7 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id,
         mutex_lock(&event_mutex);
 
         list_for_each_entry(call, &ftrace_events, list) {
-                if (call->id == event_id)
+                if (call->event.type == event_id)
                         break;
         }
 
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index e091f64ba6ce..8536e2a65969 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -127,7 +127,7 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call)	\
 
 static int ftrace_raw_init_event(struct ftrace_event_call *call)
 {
-        INIT_LIST_HEAD(&call->fields);
+        INIT_LIST_HEAD(&call->class->fields);
         return 0;
 }
 
@@ -153,17 +153,21 @@ static int ftrace_raw_init_event(struct ftrace_event_call *call)
 #define F_printk(fmt, args...) #fmt ", "  __stringify(args)
 
 #undef FTRACE_ENTRY
-#define FTRACE_ENTRY(call, struct_name, type, tstruct, print)           \
+#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print)          \
+                                                                        \
+struct ftrace_event_class event_class_ftrace_##call = {                 \
+        .system                 = __stringify(TRACE_SYSTEM),            \
+        .define_fields          = ftrace_define_fields_##call,          \
+        .raw_init               = ftrace_raw_init_event,                \
+};                                                                      \
                                                                         \
 struct ftrace_event_call __used                                         \
 __attribute__((__aligned__(4)))                                         \
 __attribute__((section("_ftrace_events"))) event_##call = {             \
         .name                   = #call,                                \
-        .id                     = type,                                 \
-        .system                 = __stringify(TRACE_SYSTEM),            \
-        .raw_init               = ftrace_raw_init_event,                \
+        .event.type             = etype,                                \
+        .class                  = &event_class_ftrace_##call,           \
         .print_fmt              = print,                                \
-        .define_fields          = ftrace_define_fields_##call,          \
 };                                                                      \
 
 #include "trace_entries.h"
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 9aed1a5cf553..79f4bac99a94 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -40,7 +40,7 @@ struct fgraph_data {
 #define TRACE_GRAPH_PRINT_OVERHEAD      0x4
 #define TRACE_GRAPH_PRINT_PROC          0x8
 #define TRACE_GRAPH_PRINT_DURATION      0x10
-#define TRACE_GRAPH_PRINT_ABS_TIME      0X20
+#define TRACE_GRAPH_PRINT_ABS_TIME      0x20
 
 static struct tracer_opt trace_opts[] = {
         /* Display overruns? (for self-debug purpose) */
@@ -179,7 +179,7 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
         return ret;
 }
 
-static int __trace_graph_entry(struct trace_array *tr,
+int __trace_graph_entry(struct trace_array *tr,
                                 struct ftrace_graph_ent *trace,
                                 unsigned long flags,
                                 int pc)
@@ -246,7 +246,7 @@ int trace_graph_thresh_entry(struct ftrace_graph_ent *trace)
                 return trace_graph_entry(trace);
 }
 
-static void __trace_graph_return(struct trace_array *tr,
+void __trace_graph_return(struct trace_array *tr,
                                 struct ftrace_graph_ret *trace,
                                 unsigned long flags,
                                 int pc)
@@ -490,9 +490,10 @@ get_return_for_leaf(struct trace_iterator *iter,
                          * We need to consume the current entry to see
                          * the next one.
                          */
-                        ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL);
+                        ring_buffer_consume(iter->tr->buffer, iter->cpu,
+                                            NULL, NULL);
                         event = ring_buffer_peek(iter->tr->buffer, iter->cpu,
-                                                 NULL);
+                                                 NULL, NULL);
                 }
 
                 if (!event)
@@ -526,17 +527,18 @@ get_return_for_leaf(struct trace_iterator *iter,
 
 /* Signal a overhead of time execution to the output */
 static int
-print_graph_overhead(unsigned long long duration, struct trace_seq *s)
+print_graph_overhead(unsigned long long duration, struct trace_seq *s,
+                     u32 flags)
 {
         /* If duration disappear, we don't need anything */
-        if (!(tracer_flags.val & TRACE_GRAPH_PRINT_DURATION))
+        if (!(flags & TRACE_GRAPH_PRINT_DURATION))
                 return 1;
 
         /* Non nested entry or return */
         if (duration == -1)
                 return trace_seq_printf(s, "  ");
 
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) {
+        if (flags & TRACE_GRAPH_PRINT_OVERHEAD) {
                 /* Duration exceeded 100 msecs */
                 if (duration > 100000ULL)
                         return trace_seq_printf(s, "! ");
@@ -562,7 +564,7 @@ static int print_graph_abs_time(u64 t, struct trace_seq *s)
 
 static enum print_line_t
 print_graph_irq(struct trace_iterator *iter, unsigned long addr,
-                enum trace_type type, int cpu, pid_t pid)
+                enum trace_type type, int cpu, pid_t pid, u32 flags)
 {
         int ret;
         struct trace_seq *s = &iter->seq;
@@ -572,21 +574,21 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
                 return TRACE_TYPE_UNHANDLED;
 
         /* Absolute time */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) {
+        if (flags & TRACE_GRAPH_PRINT_ABS_TIME) {
                 ret = print_graph_abs_time(iter->ts, s);
                 if (!ret)
                         return TRACE_TYPE_PARTIAL_LINE;
         }
 
         /* Cpu */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) {
+        if (flags & TRACE_GRAPH_PRINT_CPU) {
                 ret = print_graph_cpu(s, cpu);
                 if (ret == TRACE_TYPE_PARTIAL_LINE)
                         return TRACE_TYPE_PARTIAL_LINE;
         }
 
         /* Proc */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) {
+        if (flags & TRACE_GRAPH_PRINT_PROC) {
                 ret = print_graph_proc(s, pid);
                 if (ret == TRACE_TYPE_PARTIAL_LINE)
                         return TRACE_TYPE_PARTIAL_LINE;
@@ -596,7 +598,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
         }
 
         /* No overhead */
-        ret = print_graph_overhead(-1, s);
+        ret = print_graph_overhead(-1, s, flags);
         if (!ret)
                 return TRACE_TYPE_PARTIAL_LINE;
 
@@ -609,7 +611,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
                 return TRACE_TYPE_PARTIAL_LINE;
 
         /* Don't close the duration column if haven't one */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION)
+        if (flags & TRACE_GRAPH_PRINT_DURATION)
                 trace_seq_printf(s, " |");
         ret = trace_seq_printf(s, "\n");
 
@@ -679,7 +681,8 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s)
 static enum print_line_t
 print_graph_entry_leaf(struct trace_iterator *iter,
                 struct ftrace_graph_ent_entry *entry,
-                struct ftrace_graph_ret_entry *ret_entry, struct trace_seq *s)
+                struct ftrace_graph_ret_entry *ret_entry,
+                struct trace_seq *s, u32 flags)
 {
         struct fgraph_data *data = iter->private;
         struct ftrace_graph_ret *graph_ret;
@@ -711,12 +714,12 @@ print_graph_entry_leaf(struct trace_iterator *iter,
         }
 
         /* Overhead */
-        ret = print_graph_overhead(duration, s);
+        ret = print_graph_overhead(duration, s, flags);
         if (!ret)
                 return TRACE_TYPE_PARTIAL_LINE;
 
         /* Duration */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
+        if (flags & TRACE_GRAPH_PRINT_DURATION) {
                 ret = print_graph_duration(duration, s);
                 if (ret == TRACE_TYPE_PARTIAL_LINE)
                         return TRACE_TYPE_PARTIAL_LINE;
@@ -739,7 +742,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 static enum print_line_t
 print_graph_entry_nested(struct trace_iterator *iter,
                          struct ftrace_graph_ent_entry *entry,
-                         struct trace_seq *s, int cpu)
+                         struct trace_seq *s, int cpu, u32 flags)
 {
         struct ftrace_graph_ent *call = &entry->graph_ent;
         struct fgraph_data *data = iter->private;
@@ -759,12 +762,12 @@ print_graph_entry_nested(struct trace_iterator *iter,
         }
 
         /* No overhead */
-        ret = print_graph_overhead(-1, s);
+        ret = print_graph_overhead(-1, s, flags);
         if (!ret)
                 return TRACE_TYPE_PARTIAL_LINE;
 
         /* No time */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
+        if (flags & TRACE_GRAPH_PRINT_DURATION) {
                 ret = trace_seq_printf(s, "            |  ");
                 if (!ret)
                         return TRACE_TYPE_PARTIAL_LINE;
@@ -790,7 +793,7 @@ print_graph_entry_nested(struct trace_iterator *iter,
 
 static enum print_line_t
 print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
-                     int type, unsigned long addr)
+                     int type, unsigned long addr, u32 flags)
 {
         struct fgraph_data *data = iter->private;
         struct trace_entry *ent = iter->ent;
@@ -803,27 +806,27 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
 
         if (type) {
                 /* Interrupt */
-                ret = print_graph_irq(iter, addr, type, cpu, ent->pid);
+                ret = print_graph_irq(iter, addr, type, cpu, ent->pid, flags);
                 if (ret == TRACE_TYPE_PARTIAL_LINE)
                         return TRACE_TYPE_PARTIAL_LINE;
         }
 
         /* Absolute time */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME) {
+        if (flags & TRACE_GRAPH_PRINT_ABS_TIME) {
                 ret = print_graph_abs_time(iter->ts, s);
                 if (!ret)
                         return TRACE_TYPE_PARTIAL_LINE;
         }
 
         /* Cpu */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) {
+        if (flags & TRACE_GRAPH_PRINT_CPU) {
                 ret = print_graph_cpu(s, cpu);
                 if (ret == TRACE_TYPE_PARTIAL_LINE)
                         return TRACE_TYPE_PARTIAL_LINE;
         }
 
         /* Proc */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) {
+        if (flags & TRACE_GRAPH_PRINT_PROC) {
                 ret = print_graph_proc(s, ent->pid);
                 if (ret == TRACE_TYPE_PARTIAL_LINE)
                         return TRACE_TYPE_PARTIAL_LINE;
@@ -845,7 +848,7 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
 
 static enum print_line_t
 print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
-                        struct trace_iterator *iter)
+                        struct trace_iterator *iter, u32 flags)
 {
         struct fgraph_data *data = iter->private;
         struct ftrace_graph_ent *call = &field->graph_ent;
@@ -853,14 +856,14 @@ print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
         static enum print_line_t ret;
         int cpu = iter->cpu;
 
-        if (print_graph_prologue(iter, s, TRACE_GRAPH_ENT, call->func))
+        if (print_graph_prologue(iter, s, TRACE_GRAPH_ENT, call->func, flags))
                 return TRACE_TYPE_PARTIAL_LINE;
 
         leaf_ret = get_return_for_leaf(iter, field);
         if (leaf_ret)
-                ret = print_graph_entry_leaf(iter, field, leaf_ret, s);
+                ret = print_graph_entry_leaf(iter, field, leaf_ret, s, flags);
         else
-                ret = print_graph_entry_nested(iter, field, s, cpu);
+                ret = print_graph_entry_nested(iter, field, s, cpu, flags);
 
         if (data) {
                 /*
@@ -879,7 +882,8 @@ print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
 
 static enum print_line_t
 print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
-                   struct trace_entry *ent, struct trace_iterator *iter)
+                   struct trace_entry *ent, struct trace_iterator *iter,
+                   u32 flags)
 {
         unsigned long long duration = trace->rettime - trace->calltime;
         struct fgraph_data *data = iter->private;
@@ -909,16 +913,16 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
                 }
         }
 
-        if (print_graph_prologue(iter, s, 0, 0))
+        if (print_graph_prologue(iter, s, 0, 0, flags))
                 return TRACE_TYPE_PARTIAL_LINE;
 
         /* Overhead */
-        ret = print_graph_overhead(duration, s);
+        ret = print_graph_overhead(duration, s, flags);
         if (!ret)
                 return TRACE_TYPE_PARTIAL_LINE;
 
         /* Duration */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
+        if (flags & TRACE_GRAPH_PRINT_DURATION) {
                 ret = print_graph_duration(duration, s);
                 if (ret == TRACE_TYPE_PARTIAL_LINE)
                         return TRACE_TYPE_PARTIAL_LINE;
@@ -948,14 +952,15 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
         }
 
         /* Overrun */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERRUN) {
+        if (flags & TRACE_GRAPH_PRINT_OVERRUN) {
                 ret = trace_seq_printf(s, " (Overruns: %lu)\n",
                                         trace->overrun);
                 if (!ret)
                         return TRACE_TYPE_PARTIAL_LINE;
         }
 
-        ret = print_graph_irq(iter, trace->func, TRACE_GRAPH_RET, cpu, pid);
+        ret = print_graph_irq(iter, trace->func, TRACE_GRAPH_RET,
+                              cpu, pid, flags);
         if (ret == TRACE_TYPE_PARTIAL_LINE)
                 return TRACE_TYPE_PARTIAL_LINE;
 
@@ -963,8 +968,8 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 }
 
 static enum print_line_t
-print_graph_comment(struct trace_seq *s,  struct trace_entry *ent,
-                    struct trace_iterator *iter)
+print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
+                    struct trace_iterator *iter, u32 flags)
 {
         unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
         struct fgraph_data *data = iter->private;
@@ -976,16 +981,16 @@ print_graph_comment(struct trace_seq *s,  struct trace_entry *ent,
         if (data)
                 depth = per_cpu_ptr(data->cpu_data, iter->cpu)->depth;
 
-        if (print_graph_prologue(iter, s, 0, 0))
+        if (print_graph_prologue(iter, s, 0, 0, flags))
                 return TRACE_TYPE_PARTIAL_LINE;
 
         /* No overhead */
-        ret = print_graph_overhead(-1, s);
+        ret = print_graph_overhead(-1, s, flags);
         if (!ret)
                 return TRACE_TYPE_PARTIAL_LINE;
 
         /* No time */
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION) {
+        if (flags & TRACE_GRAPH_PRINT_DURATION) {
                 ret = trace_seq_printf(s, "            |  ");
                 if (!ret)
                         return TRACE_TYPE_PARTIAL_LINE;
@@ -1020,7 +1025,7 @@ print_graph_comment(struct trace_seq *s,  struct trace_entry *ent,
                 if (!event)
                         return TRACE_TYPE_UNHANDLED;
 
-                ret = event->trace(iter, sym_flags);
+                ret = event->funcs->trace(iter, sym_flags, event);
                 if (ret != TRACE_TYPE_HANDLED)
                         return ret;
         }
@@ -1040,7 +1045,7 @@ print_graph_comment(struct trace_seq *s,  struct trace_entry *ent,
 
 
 enum print_line_t
-print_graph_function(struct trace_iterator *iter)
+print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 {
         struct ftrace_graph_ent_entry *field;
         struct fgraph_data *data = iter->private;
@@ -1061,7 +1066,7 @@ print_graph_function(struct trace_iterator *iter)
         if (data && data->failed) {
                 field = &data->ent;
                 iter->cpu = data->cpu;
-                ret = print_graph_entry(field, s, iter);
+                ret = print_graph_entry(field, s, iter, flags);
                 if (ret == TRACE_TYPE_HANDLED && iter->cpu != cpu) {
                         per_cpu_ptr(data->cpu_data, iter->cpu)->ignore = 1;
                         ret = TRACE_TYPE_NO_CONSUME;
@@ -1081,32 +1086,50 @@ print_graph_function(struct trace_iterator *iter)
                 struct ftrace_graph_ent_entry saved;
                 trace_assign_type(field, entry);
                 saved = *field;
-                return print_graph_entry(&saved, s, iter);
+                return print_graph_entry(&saved, s, iter, flags);
         }
         case TRACE_GRAPH_RET: {
                 struct ftrace_graph_ret_entry *field;
                 trace_assign_type(field, entry);
-                return print_graph_return(&field->ret, s, entry, iter);
+                return print_graph_return(&field->ret, s, entry, iter, flags);
         }
+        case TRACE_STACK:
+        case TRACE_FN:
+                /* dont trace stack and functions as comments */
+                return TRACE_TYPE_UNHANDLED;
+
         default:
-                return print_graph_comment(s, entry, iter);
+                return print_graph_comment(s, entry, iter, flags);
         }
 
         return TRACE_TYPE_HANDLED;
 }
 
-static void print_lat_header(struct seq_file *s)
+static enum print_line_t
+print_graph_function(struct trace_iterator *iter)
+{
+        return print_graph_function_flags(iter, tracer_flags.val);
+}
+
+static enum print_line_t
+print_graph_function_event(struct trace_iterator *iter, int flags,
+                           struct trace_event *event)
+{
+        return print_graph_function(iter);
+}
+
+static void print_lat_header(struct seq_file *s, u32 flags)
 {
         static const char spaces[] = "                " /* 16 spaces */
                 "    "                                  /* 4 spaces */
                 "                 ";                    /* 17 spaces */
         int size = 0;
 
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME)
+        if (flags & TRACE_GRAPH_PRINT_ABS_TIME)
                 size += 16;
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
+        if (flags & TRACE_GRAPH_PRINT_CPU)
                 size += 4;
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
+        if (flags & TRACE_GRAPH_PRINT_PROC)
                 size += 17;
 
         seq_printf(s, "#%.*s  _-----=> irqs-off        \n", size, spaces);
@@ -1117,43 +1140,48 @@ static void print_lat_header(struct seq_file *s)
         seq_printf(s, "#%.*s|||| /                     \n", size, spaces);
 }
 
-static void print_graph_headers(struct seq_file *s)
+void print_graph_headers_flags(struct seq_file *s, u32 flags)
 {
         int lat = trace_flags & TRACE_ITER_LATENCY_FMT;
 
         if (lat)
-                print_lat_header(s);
+                print_lat_header(s, flags);
 
         /* 1st line */
         seq_printf(s, "#");
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME)
+        if (flags & TRACE_GRAPH_PRINT_ABS_TIME)
                 seq_printf(s, "     TIME       ");
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
+        if (flags & TRACE_GRAPH_PRINT_CPU)
                 seq_printf(s, " CPU");
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
+        if (flags & TRACE_GRAPH_PRINT_PROC)
                 seq_printf(s, "  TASK/PID       ");
         if (lat)
                 seq_printf(s, "|||||");
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION)
+        if (flags & TRACE_GRAPH_PRINT_DURATION)
                 seq_printf(s, "  DURATION   ");
         seq_printf(s, "               FUNCTION CALLS\n");
 
         /* 2nd line */
         seq_printf(s, "#");
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_ABS_TIME)
+        if (flags & TRACE_GRAPH_PRINT_ABS_TIME)
                 seq_printf(s, "      |         ");
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
+        if (flags & TRACE_GRAPH_PRINT_CPU)
                 seq_printf(s, " |  ");
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
+        if (flags & TRACE_GRAPH_PRINT_PROC)
                 seq_printf(s, "   |    |        ");
         if (lat)
                 seq_printf(s, "|||||");
-        if (tracer_flags.val & TRACE_GRAPH_PRINT_DURATION)
+        if (flags & TRACE_GRAPH_PRINT_DURATION)
                 seq_printf(s, "   |   |      ");
         seq_printf(s, "               |   |   |   |\n");
 }
 
-static void graph_trace_open(struct trace_iterator *iter)
+void print_graph_headers(struct seq_file *s)
+{
+        print_graph_headers_flags(s, tracer_flags.val);
+}
+
+void graph_trace_open(struct trace_iterator *iter)
 {
         /* pid and depth on the last trace processed */
         struct fgraph_data *data;
@@ -1188,7 +1216,7 @@ static void graph_trace_open(struct trace_iterator *iter)
         pr_warning("function graph tracer: not enough memory\n");
 }
 
-static void graph_trace_close(struct trace_iterator *iter)
+void graph_trace_close(struct trace_iterator *iter)
 {
         struct fgraph_data *data = iter->private;
 
@@ -1198,6 +1226,20 @@ static void graph_trace_close(struct trace_iterator *iter)
         }
 }
 
+static struct trace_event_functions graph_functions = {
+        .trace          = print_graph_function_event,
+};
+
+static struct trace_event graph_trace_entry_event = {
+        .type           = TRACE_GRAPH_ENT,
+        .funcs          = &graph_functions,
+};
+
+static struct trace_event graph_trace_ret_event = {
+        .type           = TRACE_GRAPH_RET,
+        .funcs          = &graph_functions
+};
+
 static struct tracer graph_trace __read_mostly = {
         .name           = "function_graph",
         .open           = graph_trace_open,
@@ -1219,6 +1261,16 @@ static __init int init_graph_trace(void)
 {
         max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1);
 
+        if (!register_ftrace_event(&graph_trace_entry_event)) {
+                pr_warning("Warning: could not register graph trace events\n");
+                return 1;
+        }
+
+        if (!register_ftrace_event(&graph_trace_ret_event)) {
+                pr_warning("Warning: could not register graph trace events\n");
+                return 1;
+        }
+
         return register_tracer(&graph_trace);
 }
 
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 2974bc7538c7..6fd486e0cef4 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -34,6 +34,9 @@ static int trace_type __read_mostly;
 
 static int save_lat_flag;
 
+static void stop_irqsoff_tracer(struct trace_array *tr, int graph);
+static int start_irqsoff_tracer(struct trace_array *tr, int graph);
+
 #ifdef CONFIG_PREEMPT_TRACER
 static inline int
 preempt_trace(void)
@@ -55,6 +58,23 @@ irq_trace(void)
 # define irq_trace() (0)
 #endif
 
+#define TRACE_DISPLAY_GRAPH     1
+
+static struct tracer_opt trace_opts[] = {
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+        /* display latency trace as call graph */
+        { TRACER_OPT(display-graph, TRACE_DISPLAY_GRAPH) },
+#endif
+        { } /* Empty entry */
+};
+
+static struct tracer_flags tracer_flags = {
+        .val  = 0,
+        .opts = trace_opts,
+};
+
+#define is_graph() (tracer_flags.val & TRACE_DISPLAY_GRAPH)
+
 /*
  * Sequence count - we record it when starting a measurement and
  * skip the latency if the sequence has changed - some other section
@@ -108,6 +128,202 @@ static struct ftrace_ops trace_ops __read_mostly =
 };
 #endif /* CONFIG_FUNCTION_TRACER */
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int irqsoff_set_flag(u32 old_flags, u32 bit, int set)
+{
+        int cpu;
+
+        if (!(bit & TRACE_DISPLAY_GRAPH))
+                return -EINVAL;
+
+        if (!(is_graph() ^ set))
+                return 0;
+
+        stop_irqsoff_tracer(irqsoff_trace, !set);
+
+        for_each_possible_cpu(cpu)
+                per_cpu(tracing_cpu, cpu) = 0;
+
+        tracing_max_latency = 0;
+        tracing_reset_online_cpus(irqsoff_trace);
+
+        return start_irqsoff_tracer(irqsoff_trace, set);
+}
+
+static int irqsoff_graph_entry(struct ftrace_graph_ent *trace)
+{
+        struct trace_array *tr = irqsoff_trace;
+        struct trace_array_cpu *data;
+        unsigned long flags;
+        long disabled;
+        int ret;
+        int cpu;
+        int pc;
+
+        cpu = raw_smp_processor_id();
+        if (likely(!per_cpu(tracing_cpu, cpu)))
+                return 0;
+
+        local_save_flags(flags);
+        /* slight chance to get a false positive on tracing_cpu */
+        if (!irqs_disabled_flags(flags))
+                return 0;
+
+        data = tr->data[cpu];
+        disabled = atomic_inc_return(&data->disabled);
+
+        if (likely(disabled == 1)) {
+                pc = preempt_count();
+                ret = __trace_graph_entry(tr, trace, flags, pc);
+        } else
+                ret = 0;
+
+        atomic_dec(&data->disabled);
+        return ret;
+}
+
+static void irqsoff_graph_return(struct ftrace_graph_ret *trace)
+{
+        struct trace_array *tr = irqsoff_trace;
+        struct trace_array_cpu *data;
+        unsigned long flags;
+        long disabled;
+        int cpu;
+        int pc;
+
+        cpu = raw_smp_processor_id();
+        if (likely(!per_cpu(tracing_cpu, cpu)))
+                return;
+
+        local_save_flags(flags);
+        /* slight chance to get a false positive on tracing_cpu */
+        if (!irqs_disabled_flags(flags))
+                return;
+
+        data = tr->data[cpu];
+        disabled = atomic_inc_return(&data->disabled);
+
+        if (likely(disabled == 1)) {
+                pc = preempt_count();
+                __trace_graph_return(tr, trace, flags, pc);
+        }
+
+        atomic_dec(&data->disabled);
+}
+
+static void irqsoff_trace_open(struct trace_iterator *iter)
+{
+        if (is_graph())
+                graph_trace_open(iter);
+
+}
+
+static void irqsoff_trace_close(struct trace_iterator *iter)
+{
+        if (iter->private)
+                graph_trace_close(iter);
+}
+
+#define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_CPU | \
+                            TRACE_GRAPH_PRINT_PROC)
+
+static enum print_line_t irqsoff_print_line(struct trace_iterator *iter)
+{
+        u32 flags = GRAPH_TRACER_FLAGS;
+
+        if (trace_flags & TRACE_ITER_LATENCY_FMT)
+                flags |= TRACE_GRAPH_PRINT_DURATION;
+        else
+                flags |= TRACE_GRAPH_PRINT_ABS_TIME;
+
+        /*
+         * In graph mode call the graph tracer output function,
+         * otherwise go with the TRACE_FN event handler
+         */
+        if (is_graph())
+                return print_graph_function_flags(iter, flags);
+
+        return TRACE_TYPE_UNHANDLED;
+}
+
+static void irqsoff_print_header(struct seq_file *s)
+{
+        if (is_graph()) {
+                struct trace_iterator *iter = s->private;
+                u32 flags = GRAPH_TRACER_FLAGS;
+
+                if (trace_flags & TRACE_ITER_LATENCY_FMT) {
+                        /* print nothing if the buffers are empty */
+                        if (trace_empty(iter))
+                                return;
+
+                        print_trace_header(s, iter);
+                        flags |= TRACE_GRAPH_PRINT_DURATION;
+                } else
+                        flags |= TRACE_GRAPH_PRINT_ABS_TIME;
+
+                print_graph_headers_flags(s, flags);
+        } else
+                trace_default_header(s);
+}
+
+static void
+trace_graph_function(struct trace_array *tr,
+                 unsigned long ip, unsigned long flags, int pc)
+{
+        u64 time = trace_clock_local();
+        struct ftrace_graph_ent ent = {
+                .func  = ip,
+                .depth = 0,
+        };
+        struct ftrace_graph_ret ret = {
+                .func     = ip,
+                .depth    = 0,
+                .calltime = time,
+                .rettime  = time,
+        };
+
+        __trace_graph_entry(tr, &ent, flags, pc);
+        __trace_graph_return(tr, &ret, flags, pc);
+}
+
+static void
+__trace_function(struct trace_array *tr,
+                 unsigned long ip, unsigned long parent_ip,
+                 unsigned long flags, int pc)
+{
+        if (!is_graph())
+                trace_function(tr, ip, parent_ip, flags, pc);
+        else {
+                trace_graph_function(tr, parent_ip, flags, pc);
+                trace_graph_function(tr, ip, flags, pc);
+        }
+}
+
+#else
+#define __trace_function trace_function
+
+static int irqsoff_set_flag(u32 old_flags, u32 bit, int set)
+{
+        return -EINVAL;
+}
+
+static int irqsoff_graph_entry(struct ftrace_graph_ent *trace)
+{
+        return -1;
+}
+
+static enum print_line_t irqsoff_print_line(struct trace_iterator *iter)
+{
+        return TRACE_TYPE_UNHANDLED;
+}
+
+static void irqsoff_graph_return(struct ftrace_graph_ret *trace) { }
+static void irqsoff_print_header(struct seq_file *s) { }
+static void irqsoff_trace_open(struct trace_iterator *iter) { }
+static void irqsoff_trace_close(struct trace_iterator *iter) { }
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
 /*
  * Should this new latency be reported/recorded?
  */
@@ -150,7 +366,7 @@ check_critical_timing(struct trace_array *tr,
         if (!report_latency(delta))
                 goto out_unlock;
 
-        trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
+        __trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
         /* Skip 5 functions to get to the irq/preempt enable function */
         __trace_stack(tr, flags, 5, pc);
 
@@ -172,7 +388,7 @@ out_unlock:
 out:
         data->critical_sequence = max_sequence;
         data->preempt_timestamp = ftrace_now(cpu);
-        trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
+        __trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
 }
 
 static inline void
@@ -204,7 +420,7 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip)
 
         local_save_flags(flags);
 
-        trace_function(tr, ip, parent_ip, flags, preempt_count());
+        __trace_function(tr, ip, parent_ip, flags, preempt_count());
 
         per_cpu(tracing_cpu, cpu) = 1;
 
@@ -238,7 +454,7 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip)
         atomic_inc(&data->disabled);
 
         local_save_flags(flags);
-        trace_function(tr, ip, parent_ip, flags, preempt_count());
+        __trace_function(tr, ip, parent_ip, flags, preempt_count());
         check_critical_timing(tr, data, parent_ip ? : ip, cpu);
         data->critical_start = 0;
         atomic_dec(&data->disabled);
@@ -347,19 +563,32 @@ void trace_preempt_off(unsigned long a0, unsigned long a1)
 }
 #endif /* CONFIG_PREEMPT_TRACER */
 
-static void start_irqsoff_tracer(struct trace_array *tr)
+static int start_irqsoff_tracer(struct trace_array *tr, int graph)
 {
-        register_ftrace_function(&trace_ops);
-        if (tracing_is_enabled())
+        int ret = 0;
+
+        if (!graph)
+                ret = register_ftrace_function(&trace_ops);
+        else
+                ret = register_ftrace_graph(&irqsoff_graph_return,
+                                            &irqsoff_graph_entry);
+
+        if (!ret && tracing_is_enabled())
                 tracer_enabled = 1;
         else
                 tracer_enabled = 0;
+
+        return ret;
 }
 
-static void stop_irqsoff_tracer(struct trace_array *tr)
+static void stop_irqsoff_tracer(struct trace_array *tr, int graph)
 {
         tracer_enabled = 0;
-        unregister_ftrace_function(&trace_ops);
+
+        if (!graph)
+                unregister_ftrace_function(&trace_ops);
+        else
+                unregister_ftrace_graph();
 }
 
 static void __irqsoff_tracer_init(struct trace_array *tr)
@@ -372,12 +601,14 @@ static void __irqsoff_tracer_init(struct trace_array *tr)
         /* make sure that the tracer is visible */
         smp_wmb();
         tracing_reset_online_cpus(tr);
-        start_irqsoff_tracer(tr);
+
+        if (start_irqsoff_tracer(tr, is_graph()))
+                printk(KERN_ERR "failed to start irqsoff tracer\n");
 }
 
 static void irqsoff_tracer_reset(struct trace_array *tr)
 {
-        stop_irqsoff_tracer(tr);
+        stop_irqsoff_tracer(tr, is_graph());
 
         if (!save_lat_flag)
                 trace_flags &= ~TRACE_ITER_LATENCY_FMT;
@@ -409,9 +640,15 @@ static struct tracer irqsoff_tracer __read_mostly =
         .start          = irqsoff_tracer_start,
         .stop           = irqsoff_tracer_stop,
         .print_max      = 1,
+        .print_header   = irqsoff_print_header,
+        .print_line     = irqsoff_print_line,
+        .flags          = &tracer_flags,
+        .set_flag       = irqsoff_set_flag,
 #ifdef CONFIG_FTRACE_SELFTEST
         .selftest    = trace_selftest_startup_irqsoff,
 #endif
+        .open           = irqsoff_trace_open,
+        .close          = irqsoff_trace_close,
 };
 # define register_irqsoff(trace) register_tracer(&trace)
 #else
@@ -435,9 +672,15 @@ static struct tracer preemptoff_tracer __read_mostly =
         .start          = irqsoff_tracer_start,
         .stop           = irqsoff_tracer_stop,
         .print_max      = 1,
+        .print_header   = irqsoff_print_header,
+        .print_line     = irqsoff_print_line,
+        .flags          = &tracer_flags,
+        .set_flag       = irqsoff_set_flag,
 #ifdef CONFIG_FTRACE_SELFTEST
         .selftest    = trace_selftest_startup_preemptoff,
 #endif
+        .open           = irqsoff_trace_open,
+        .close          = irqsoff_trace_close,
 };
 # define register_preemptoff(trace) register_tracer(&trace)
 #else
@@ -463,9 +706,15 @@ static struct tracer preemptirqsoff_tracer __read_mostly =
         .start          = irqsoff_tracer_start,
         .stop           = irqsoff_tracer_stop,
         .print_max      = 1,
+        .print_header   = irqsoff_print_header,
+        .print_line     = irqsoff_print_line,
+        .flags          = &tracer_flags,
+        .set_flag       = irqsoff_set_flag,
 #ifdef CONFIG_FTRACE_SELFTEST
         .selftest    = trace_selftest_startup_preemptirqsoff,
 #endif
+        .open           = irqsoff_trace_open,
+        .close          = irqsoff_trace_close,
 };
 
 # define register_preemptirqsoff(trace) register_tracer(&trace)
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index a7514326052b..9a082bba9537 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -324,8 +324,8 @@ struct trace_probe {
         unsigned long           nhit;
         unsigned int            flags;  /* For TP_FLAG_* */
         const char              *symbol;        /* symbol name */
+        struct ftrace_event_class       class;
         struct ftrace_event_call        call;
-        struct trace_event              event;
         ssize_t                 size;           /* trace entry size */
         unsigned int            nr_args;
         struct probe_arg        args[];
@@ -404,6 +404,7 @@ static struct trace_probe *alloc_trace_probe(const char *group,
                 goto error;
         }
 
+        tp->call.class = &tp->class;
         tp->call.name = kstrdup(event, GFP_KERNEL);
         if (!tp->call.name)
                 goto error;
@@ -413,8 +414,8 @@ static struct trace_probe *alloc_trace_probe(const char *group,
                 goto error;
         }
 
-        tp->call.system = kstrdup(group, GFP_KERNEL);
-        if (!tp->call.system)
+        tp->class.system = kstrdup(group, GFP_KERNEL);
+        if (!tp->class.system)
                 goto error;
 
         INIT_LIST_HEAD(&tp->list);
@@ -443,7 +444,7 @@ static void free_trace_probe(struct trace_probe *tp)
         for (i = 0; i < tp->nr_args; i++)
                 free_probe_arg(&tp->args[i]);
 
-        kfree(tp->call.system);
+        kfree(tp->call.class->system);
         kfree(tp->call.name);
         kfree(tp->symbol);
         kfree(tp);
@@ -456,7 +457,7 @@ static struct trace_probe *find_probe_event(const char *event,
 
         list_for_each_entry(tp, &probe_list, list)
                 if (strcmp(tp->call.name, event) == 0 &&
-                    strcmp(tp->call.system, group) == 0)
+                    strcmp(tp->call.class->system, group) == 0)
                         return tp;
         return NULL;
 }
@@ -481,7 +482,7 @@ static int register_trace_probe(struct trace_probe *tp)
         mutex_lock(&probe_lock);
 
         /* register as an event */
-        old_tp = find_probe_event(tp->call.name, tp->call.system);
+        old_tp = find_probe_event(tp->call.name, tp->call.class->system);
         if (old_tp) {
                 /* delete old event */
                 unregister_trace_probe(old_tp);
@@ -904,7 +905,7 @@ static int probes_seq_show(struct seq_file *m, void *v)
         int i;
 
         seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p');
-        seq_printf(m, ":%s/%s", tp->call.system, tp->call.name);
+        seq_printf(m, ":%s/%s", tp->call.class->system, tp->call.name);
 
         if (!tp->symbol)
                 seq_printf(m, " 0x%p", tp->rp.kp.addr);
@@ -1061,8 +1062,8 @@ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
 
         size = sizeof(*entry) + tp->size;
 
-        event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
-                                                  irq_flags, pc);
+        event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
+                                                  size, irq_flags, pc);
         if (!event)
                 return;
 
@@ -1094,8 +1095,8 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri,
 
         size = sizeof(*entry) + tp->size;
 
-        event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
-                                                  irq_flags, pc);
+        event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
+                                                  size, irq_flags, pc);
         if (!event)
                 return;
 
@@ -1112,18 +1113,17 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri,
 
 /* Event entry printers */
 enum print_line_t
-print_kprobe_event(struct trace_iterator *iter, int flags)
+print_kprobe_event(struct trace_iterator *iter, int flags,
+                   struct trace_event *event)
 {
         struct kprobe_trace_entry_head *field;
         struct trace_seq *s = &iter->seq;
-        struct trace_event *event;
         struct trace_probe *tp;
         u8 *data;
         int i;
 
         field = (struct kprobe_trace_entry_head *)iter->ent;
-        event = ftrace_find_event(field->ent.type);
-        tp = container_of(event, struct trace_probe, event);
+        tp = container_of(event, struct trace_probe, call.event);
 
         if (!trace_seq_printf(s, "%s: (", tp->call.name))
                 goto partial;
@@ -1149,18 +1149,17 @@ partial:
 }
 
 enum print_line_t
-print_kretprobe_event(struct trace_iterator *iter, int flags)
+print_kretprobe_event(struct trace_iterator *iter, int flags,
+                      struct trace_event *event)
 {
         struct kretprobe_trace_entry_head *field;
         struct trace_seq *s = &iter->seq;
-        struct trace_event *event;
         struct trace_probe *tp;
         u8 *data;
         int i;
 
         field = (struct kretprobe_trace_entry_head *)iter->ent;
-        event = ftrace_find_event(field->ent.type);
-        tp = container_of(event, struct trace_probe, event);
+        tp = container_of(event, struct trace_probe, call.event);
 
         if (!trace_seq_printf(s, "%s: (", tp->call.name))
                 goto partial;
@@ -1217,8 +1216,6 @@ static void probe_event_disable(struct ftrace_event_call *call)
 
 static int probe_event_raw_init(struct ftrace_event_call *event_call)
 {
-        INIT_LIST_HEAD(&event_call->fields);
-
         return 0;
 }
 
@@ -1353,7 +1350,8 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp,
                      "profile buffer not large enough"))
                 return;
 
-        entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags);
+        entry = perf_trace_buf_prepare(size, call->event.type,
+                                       &rctx, &irq_flags);
         if (!entry)
                 return;
 
@@ -1384,7 +1382,8 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
                      "profile buffer not large enough"))
                 return;
 
-        entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags);
+        entry = perf_trace_buf_prepare(size, call->event.type,
+                                       &rctx, &irq_flags);
         if (!entry)
                 return;
 
@@ -1425,6 +1424,26 @@ static void probe_perf_disable(struct ftrace_event_call *call)
 }
 #endif  /* CONFIG_PERF_EVENTS */
 
+static __kprobes
+int kprobe_register(struct ftrace_event_call *event, enum trace_reg type)
+{
+        switch (type) {
+        case TRACE_REG_REGISTER:
+                return probe_event_enable(event);
+        case TRACE_REG_UNREGISTER:
+                probe_event_disable(event);
+                return 0;
+
+#ifdef CONFIG_PERF_EVENTS
+        case TRACE_REG_PERF_REGISTER:
+                return probe_perf_enable(event);
+        case TRACE_REG_PERF_UNREGISTER:
+                probe_perf_disable(event);
+                return 0;
+#endif
+        }
+        return 0;
+}
 
 static __kprobes
 int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
@@ -1454,6 +1473,14 @@ int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
         return 0;       /* We don't tweek kernel, so just return 0 */
 }
 
+static struct trace_event_functions kretprobe_funcs = {
+        .trace          = print_kretprobe_event
+};
+
+static struct trace_event_functions kprobe_funcs = {
+        .trace          = print_kprobe_event
+};
+
 static int register_probe_event(struct trace_probe *tp)
 {
         struct ftrace_event_call *call = &tp->call;
@@ -1461,36 +1488,31 @@ static int register_probe_event(struct trace_probe *tp)
 
         /* Initialize ftrace_event_call */
         if (probe_is_return(tp)) {
-                tp->event.trace = print_kretprobe_event;
-                call->raw_init = probe_event_raw_init;
-                call->define_fields = kretprobe_event_define_fields;
+                INIT_LIST_HEAD(&call->class->fields);
+                call->event.funcs = &kretprobe_funcs;
+                call->class->raw_init = probe_event_raw_init;
+                call->class->define_fields = kretprobe_event_define_fields;
         } else {
-                tp->event.trace = print_kprobe_event;
-                call->raw_init = probe_event_raw_init;
-                call->define_fields = kprobe_event_define_fields;
+                INIT_LIST_HEAD(&call->class->fields);
+                call->event.funcs = &kprobe_funcs;
+                call->class->raw_init = probe_event_raw_init;
+                call->class->define_fields = kprobe_event_define_fields;
         }
         if (set_print_fmt(tp) < 0)
                 return -ENOMEM;
-        call->event = &tp->event;
-        call->id = register_ftrace_event(&tp->event);
-        if (!call->id) {
+        ret = register_ftrace_event(&call->event);
+        if (!ret) {
                 kfree(call->print_fmt);
                 return -ENODEV;
         }
-        call->enabled = 0;
-        call->regfunc = probe_event_enable;
-        call->unregfunc = probe_event_disable;
-
-#ifdef CONFIG_PERF_EVENTS
-        call->perf_event_enable = probe_perf_enable;
-        call->perf_event_disable = probe_perf_disable;
-#endif
+        call->flags = 0;
+        call->class->reg = kprobe_register;
         call->data = tp;
         ret = trace_add_event_call(call);
         if (ret) {
                 pr_info("Failed to register kprobe event: %s\n", call->name);
                 kfree(call->print_fmt);
-                unregister_ftrace_event(&tp->event);
+                unregister_ftrace_event(&call->event);
         }
         return ret;
 }
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 8e46b3323cdc..fc9d4dbb089e 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -253,7 +253,7 @@ void *trace_seq_reserve(struct trace_seq *s, size_t len)
         void *ret;
 
         if (s->full)
-                return 0;
+                return NULL;
 
         if (len > ((PAGE_SIZE - 1) - s->len)) {
                 s->full = 1;
@@ -726,6 +726,9 @@ int register_ftrace_event(struct trace_event *event)
         if (WARN_ON(!event))
                 goto out;
 
+        if (WARN_ON(!event->funcs))
+                goto out;
+
         INIT_LIST_HEAD(&event->list);
 
         if (!event->type) {
@@ -758,14 +761,14 @@ int register_ftrace_event(struct trace_event *event)
                         goto out;
         }
 
-        if (event->trace == NULL)
-                event->trace = trace_nop_print;
-        if (event->raw == NULL)
-                event->raw = trace_nop_print;
-        if (event->hex == NULL)
-                event->hex = trace_nop_print;
-        if (event->binary == NULL)
-                event->binary = trace_nop_print;
+        if (event->funcs->trace == NULL)
+                event->funcs->trace = trace_nop_print;
+        if (event->funcs->raw == NULL)
+                event->funcs->raw = trace_nop_print;
+        if (event->funcs->hex == NULL)
+                event->funcs->hex = trace_nop_print;
+        if (event->funcs->binary == NULL)
+                event->funcs->binary = trace_nop_print;
 
         key = event->type & (EVENT_HASHSIZE - 1);
 
@@ -807,13 +810,15 @@ EXPORT_SYMBOL_GPL(unregister_ftrace_event);
  * Standard events
  */
 
-enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags)
+enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags,
+                                  struct trace_event *event)
 {
         return TRACE_TYPE_HANDLED;
 }
 
 /* TRACE_FN */
-static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags,
+                                        struct trace_event *event)
 {
         struct ftrace_entry *field;
         struct trace_seq *s = &iter->seq;
@@ -840,7 +845,8 @@ static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags)
         return TRACE_TYPE_PARTIAL_LINE;
 }
 
-static enum print_line_t trace_fn_raw(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_fn_raw(struct trace_iterator *iter, int flags,
+                                      struct trace_event *event)
 {
         struct ftrace_entry *field;
 
@@ -854,7 +860,8 @@ static enum print_line_t trace_fn_raw(struct trace_iterator *iter, int flags)
         return TRACE_TYPE_HANDLED;
 }
 
-static enum print_line_t trace_fn_hex(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_fn_hex(struct trace_iterator *iter, int flags,
+                                      struct trace_event *event)
 {
         struct ftrace_entry *field;
         struct trace_seq *s = &iter->seq;
@@ -867,7 +874,8 @@ static enum print_line_t trace_fn_hex(struct trace_iterator *iter, int flags)
         return TRACE_TYPE_HANDLED;
 }
 
-static enum print_line_t trace_fn_bin(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_fn_bin(struct trace_iterator *iter, int flags,
+                                      struct trace_event *event)
 {
         struct ftrace_entry *field;
         struct trace_seq *s = &iter->seq;
@@ -880,14 +888,18 @@ static enum print_line_t trace_fn_bin(struct trace_iterator *iter, int flags)
         return TRACE_TYPE_HANDLED;
 }
 
-static struct trace_event trace_fn_event = {
-        .type           = TRACE_FN,
+static struct trace_event_functions trace_fn_funcs = {
         .trace          = trace_fn_trace,
         .raw            = trace_fn_raw,
         .hex            = trace_fn_hex,
         .binary         = trace_fn_bin,
 };
 
+static struct trace_event trace_fn_event = {
+        .type           = TRACE_FN,
+        .funcs          = &trace_fn_funcs,
+};
+
 /* TRACE_CTX an TRACE_WAKE */
 static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter,
                                              char *delim)
@@ -916,13 +928,14 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter,
         return TRACE_TYPE_HANDLED;
 }
 
-static enum print_line_t trace_ctx_print(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_ctx_print(struct trace_iterator *iter, int flags,
+                                         struct trace_event *event)
 {
         return trace_ctxwake_print(iter, "==>");
 }
 
 static enum print_line_t trace_wake_print(struct trace_iterator *iter,
-                                          int flags)
+                                          int flags, struct trace_event *event)
 {
         return trace_ctxwake_print(iter, "  +");
 }
@@ -950,12 +963,14 @@ static int trace_ctxwake_raw(struct trace_iterator *iter, char S)
         return TRACE_TYPE_HANDLED;
 }
 
-static enum print_line_t trace_ctx_raw(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_ctx_raw(struct trace_iterator *iter, int flags,
+                                       struct trace_event *event)
 {
         return trace_ctxwake_raw(iter, 0);
 }
 
-static enum print_line_t trace_wake_raw(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_wake_raw(struct trace_iterator *iter, int flags,
+                                        struct trace_event *event)
 {
         return trace_ctxwake_raw(iter, '+');
 }
@@ -984,18 +999,20 @@ static int trace_ctxwake_hex(struct trace_iterator *iter, char S)
         return TRACE_TYPE_HANDLED;
 }
 
-static enum print_line_t trace_ctx_hex(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_ctx_hex(struct trace_iterator *iter, int flags,
+                                       struct trace_event *event)
 {
         return trace_ctxwake_hex(iter, 0);
 }
 
-static enum print_line_t trace_wake_hex(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_wake_hex(struct trace_iterator *iter, int flags,
+                                        struct trace_event *event)
 {
         return trace_ctxwake_hex(iter, '+');
 }
 
 static enum print_line_t trace_ctxwake_bin(struct trace_iterator *iter,
-                                           int flags)
+                                           int flags, struct trace_event *event)
 {
         struct ctx_switch_entry *field;
         struct trace_seq *s = &iter->seq;
@@ -1012,25 +1029,33 @@ static enum print_line_t trace_ctxwake_bin(struct trace_iterator *iter,
         return TRACE_TYPE_HANDLED;
 }
 
-static struct trace_event trace_ctx_event = {
-        .type           = TRACE_CTX,
+static struct trace_event_functions trace_ctx_funcs = {
         .trace          = trace_ctx_print,
         .raw            = trace_ctx_raw,
         .hex            = trace_ctx_hex,
         .binary         = trace_ctxwake_bin,
 };
 
-static struct trace_event trace_wake_event = {
-        .type           = TRACE_WAKE,
+static struct trace_event trace_ctx_event = {
+        .type           = TRACE_CTX,
+        .funcs          = &trace_ctx_funcs,
+};
+
+static struct trace_event_functions trace_wake_funcs = {
         .trace          = trace_wake_print,
         .raw            = trace_wake_raw,
         .hex            = trace_wake_hex,
         .binary         = trace_ctxwake_bin,
 };
 
+static struct trace_event trace_wake_event = {
+        .type           = TRACE_WAKE,
+        .funcs          = &trace_wake_funcs,
+};
+
 /* TRACE_SPECIAL */
 static enum print_line_t trace_special_print(struct trace_iterator *iter,
-                                             int flags)
+                                             int flags, struct trace_event *event)
 {
         struct special_entry *field;
 
@@ -1046,7 +1071,7 @@ static enum print_line_t trace_special_print(struct trace_iterator *iter,
 }
 
 static enum print_line_t trace_special_hex(struct trace_iterator *iter,
-                                           int flags)
+                                           int flags, struct trace_event *event)
 {
         struct special_entry *field;
         struct trace_seq *s = &iter->seq;
@@ -1061,7 +1086,7 @@ static enum print_line_t trace_special_hex(struct trace_iterator *iter,
 }
 
 static enum print_line_t trace_special_bin(struct trace_iterator *iter,
-                                           int flags)
+                                           int flags, struct trace_event *event)
 {
         struct special_entry *field;
         struct trace_seq *s = &iter->seq;
@@ -1075,18 +1100,22 @@ static enum print_line_t trace_special_bin(struct trace_iterator *iter,
         return TRACE_TYPE_HANDLED;
 }
 
-static struct trace_event trace_special_event = {
-        .type           = TRACE_SPECIAL,
+static struct trace_event_functions trace_special_funcs = {
         .trace          = trace_special_print,
         .raw            = trace_special_print,
         .hex            = trace_special_hex,
         .binary         = trace_special_bin,
 };
 
+static struct trace_event trace_special_event = {
+        .type           = TRACE_SPECIAL,
+        .funcs          = &trace_special_funcs,
+};
+
 /* TRACE_STACK */
 
 static enum print_line_t trace_stack_print(struct trace_iterator *iter,
-                                           int flags)
+                                           int flags, struct trace_event *event)
 {
         struct stack_entry *field;
         struct trace_seq *s = &iter->seq;
@@ -1114,17 +1143,21 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter,
         return TRACE_TYPE_PARTIAL_LINE;
 }
 
-static struct trace_event trace_stack_event = {
-        .type           = TRACE_STACK,
+static struct trace_event_functions trace_stack_funcs = {
         .trace          = trace_stack_print,
         .raw            = trace_special_print,
         .hex            = trace_special_hex,
         .binary         = trace_special_bin,
 };
 
+static struct trace_event trace_stack_event = {
+        .type           = TRACE_STACK,
+        .funcs          = &trace_stack_funcs,
+};
+
 /* TRACE_USER_STACK */
 static enum print_line_t trace_user_stack_print(struct trace_iterator *iter,
-                                                int flags)
+                                                int flags, struct trace_event *event)
 {
         struct userstack_entry *field;
         struct trace_seq *s = &iter->seq;
@@ -1143,17 +1176,22 @@ static enum print_line_t trace_user_stack_print(struct trace_iterator *iter,
         return TRACE_TYPE_PARTIAL_LINE;
 }
 
-static struct trace_event trace_user_stack_event = {
-        .type           = TRACE_USER_STACK,
+static struct trace_event_functions trace_user_stack_funcs = {
         .trace          = trace_user_stack_print,
         .raw            = trace_special_print,
         .hex            = trace_special_hex,
         .binary         = trace_special_bin,
 };
 
+static struct trace_event trace_user_stack_event = {
+        .type           = TRACE_USER_STACK,
+        .funcs          = &trace_user_stack_funcs,
+};
+
 /* TRACE_BPRINT */
 static enum print_line_t
-trace_bprint_print(struct trace_iterator *iter, int flags)
+trace_bprint_print(struct trace_iterator *iter, int flags,
+                   struct trace_event *event)
 {
         struct trace_entry *entry = iter->ent;
         struct trace_seq *s = &iter->seq;
@@ -1178,7 +1216,8 @@ trace_bprint_print(struct trace_iterator *iter, int flags)
 
 
 static enum print_line_t
-trace_bprint_raw(struct trace_iterator *iter, int flags)
+trace_bprint_raw(struct trace_iterator *iter, int flags,
+                 struct trace_event *event)
 {
         struct bprint_entry *field;
         struct trace_seq *s = &iter->seq;
@@ -1197,16 +1236,19 @@ trace_bprint_raw(struct trace_iterator *iter, int flags)
         return TRACE_TYPE_PARTIAL_LINE;
 }
 
+static struct trace_event_functions trace_bprint_funcs = {
+        .trace          = trace_bprint_print,
+        .raw            = trace_bprint_raw,
+};
 
 static struct trace_event trace_bprint_event = {
         .type           = TRACE_BPRINT,
-        .trace          = trace_bprint_print,
-        .raw            = trace_bprint_raw,
+        .funcs          = &trace_bprint_funcs,
 };
 
 /* TRACE_PRINT */
 static enum print_line_t trace_print_print(struct trace_iterator *iter,
-                                           int flags)
+                                           int flags, struct trace_event *event)
 {
         struct print_entry *field;
         struct trace_seq *s = &iter->seq;
@@ -1225,7 +1267,8 @@ static enum print_line_t trace_print_print(struct trace_iterator *iter,
         return TRACE_TYPE_PARTIAL_LINE;
 }
 
-static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags,
+                                         struct trace_event *event)
 {
         struct print_entry *field;
 
@@ -1240,12 +1283,16 @@ static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags)
         return TRACE_TYPE_PARTIAL_LINE;
 }
 
-static struct trace_event trace_print_event = {
-        .type           = TRACE_PRINT,
+static struct trace_event_functions trace_print_funcs = {
         .trace          = trace_print_print,
         .raw            = trace_print_raw,
 };
 
+static struct trace_event trace_print_event = {
+        .type           = TRACE_PRINT,
+        .funcs          = &trace_print_funcs,
+};
+
 
 static struct trace_event *events[] __initdata = {
         &trace_fn_event,
diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h
index 9d91c72ba38b..c038eba0492b 100644
--- a/kernel/trace/trace_output.h
+++ b/kernel/trace/trace_output.h
@@ -25,7 +25,7 @@ extern void trace_event_read_unlock(void);
 extern struct trace_event *ftrace_find_event(int type);
 
 extern enum print_line_t trace_nop_print(struct trace_iterator *iter,
-                                         int flags);
+                                         int flags, struct trace_event *event);
 extern int
 trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry);
 
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 5fca0f51fde4..8f758d070c43 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -50,8 +50,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
 }
 
 static void
-probe_sched_switch(struct rq *__rq, struct task_struct *prev,
-                        struct task_struct *next)
+probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *next)
 {
         struct trace_array_cpu *data;
         unsigned long flags;
@@ -109,7 +108,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 }
 
 static void
-probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee, int success)
+probe_sched_wakeup(void *ignore, struct task_struct *wakee, int success)
 {
         struct trace_array_cpu *data;
         unsigned long flags;
@@ -139,21 +138,21 @@ static int tracing_sched_register(void)
 {
         int ret;
 
-        ret = register_trace_sched_wakeup(probe_sched_wakeup);
+        ret = register_trace_sched_wakeup(probe_sched_wakeup, NULL);
         if (ret) {
                 pr_info("wakeup trace: Couldn't activate tracepoint"
                         " probe to kernel_sched_wakeup\n");
                 return ret;
         }
 
-        ret = register_trace_sched_wakeup_new(probe_sched_wakeup);
+        ret = register_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
         if (ret) {
                 pr_info("wakeup trace: Couldn't activate tracepoint"
                         " probe to kernel_sched_wakeup_new\n");
                 goto fail_deprobe;
         }
 
-        ret = register_trace_sched_switch(probe_sched_switch);
+        ret = register_trace_sched_switch(probe_sched_switch, NULL);
         if (ret) {
                 pr_info("sched trace: Couldn't activate tracepoint"
                         " probe to kernel_sched_switch\n");
@@ -162,17 +161,17 @@ static int tracing_sched_register(void)
 
         return ret;
 fail_deprobe_wake_new:
-        unregister_trace_sched_wakeup_new(probe_sched_wakeup);
+        unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
 fail_deprobe:
-        unregister_trace_sched_wakeup(probe_sched_wakeup);
+        unregister_trace_sched_wakeup(probe_sched_wakeup, NULL);
         return ret;
 }
 
 static void tracing_sched_unregister(void)
 {
-        unregister_trace_sched_switch(probe_sched_switch);
-        unregister_trace_sched_wakeup_new(probe_sched_wakeup);
-        unregister_trace_sched_wakeup(probe_sched_wakeup);
+        unregister_trace_sched_switch(probe_sched_switch, NULL);
+        unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
+        unregister_trace_sched_wakeup(probe_sched_wakeup, NULL);
 }
 
 static void tracing_start_sched_switch(void)
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 0271742abb8d..0e73bc2ef8c5 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -98,7 +98,8 @@ static int report_latency(cycle_t delta)
         return 1;
 }
 
-static void probe_wakeup_migrate_task(struct task_struct *task, int cpu)
+static void
+probe_wakeup_migrate_task(void *ignore, struct task_struct *task, int cpu)
 {
         if (task != wakeup_task)
                 return;
@@ -107,8 +108,8 @@ static void probe_wakeup_migrate_task(struct task_struct *task, int cpu)
 }
 
 static void notrace
-probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
-        struct task_struct *next)
+probe_wakeup_sched_switch(void *ignore,
+                          struct task_struct *prev, struct task_struct *next)
 {
         struct trace_array_cpu *data;
         cycle_t T0, T1, delta;
@@ -200,7 +201,7 @@ static void wakeup_reset(struct trace_array *tr)
 }
 
 static void
-probe_wakeup(struct rq *rq, struct task_struct *p, int success)
+probe_wakeup(void *ignore, struct task_struct *p, int success)
 {
         struct trace_array_cpu *data;
         int cpu = smp_processor_id();
@@ -264,28 +265,28 @@ static void start_wakeup_tracer(struct trace_array *tr)
 {
         int ret;
 
-        ret = register_trace_sched_wakeup(probe_wakeup);
+        ret = register_trace_sched_wakeup(probe_wakeup, NULL);
         if (ret) {
                 pr_info("wakeup trace: Couldn't activate tracepoint"
                         " probe to kernel_sched_wakeup\n");
                 return;
         }
 
-        ret = register_trace_sched_wakeup_new(probe_wakeup);
+        ret = register_trace_sched_wakeup_new(probe_wakeup, NULL);
         if (ret) {
                 pr_info("wakeup trace: Couldn't activate tracepoint"
                         " probe to kernel_sched_wakeup_new\n");
                 goto fail_deprobe;
         }
 
-        ret = register_trace_sched_switch(probe_wakeup_sched_switch);
+        ret = register_trace_sched_switch(probe_wakeup_sched_switch, NULL);
         if (ret) {
                 pr_info("sched trace: Couldn't activate tracepoint"
                         " probe to kernel_sched_switch\n");
                 goto fail_deprobe_wake_new;
         }
 
-        ret = register_trace_sched_migrate_task(probe_wakeup_migrate_task);
+        ret = register_trace_sched_migrate_task(probe_wakeup_migrate_task, NULL);
         if (ret) {
                 pr_info("wakeup trace: Couldn't activate tracepoint"
                         " probe to kernel_sched_migrate_task\n");
@@ -312,19 +313,19 @@ static void start_wakeup_tracer(struct trace_array *tr)
 
         return;
 fail_deprobe_wake_new:
-        unregister_trace_sched_wakeup_new(probe_wakeup);
+        unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
 fail_deprobe:
-        unregister_trace_sched_wakeup(probe_wakeup);
+        unregister_trace_sched_wakeup(probe_wakeup, NULL);
 }
 
 static void stop_wakeup_tracer(struct trace_array *tr)
 {
         tracer_enabled = 0;
         unregister_ftrace_function(&trace_ops);
-        unregister_trace_sched_switch(probe_wakeup_sched_switch);
-        unregister_trace_sched_wakeup_new(probe_wakeup);
-        unregister_trace_sched_wakeup(probe_wakeup);
-        unregister_trace_sched_migrate_task(probe_wakeup_migrate_task);
+        unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL);
+        unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
+        unregister_trace_sched_wakeup(probe_wakeup, NULL);
+        unregister_trace_sched_migrate_task(probe_wakeup_migrate_task, NULL);
 }
 
 static int __wakeup_tracer_init(struct trace_array *tr)
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 1cc9858258b3..250e7f9bd2f0 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -29,7 +29,7 @@ static int trace_test_buffer_cpu(struct trace_array *tr, int cpu)
         struct trace_entry *entry;
         unsigned int loops = 0;
 
-        while ((event = ring_buffer_consume(tr->buffer, cpu, NULL))) {
+        while ((event = ring_buffer_consume(tr->buffer, cpu, NULL, NULL))) {
                 entry = ring_buffer_event_data(event);
 
                 /*
@@ -255,7 +255,8 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
 /* Maximum number of functions to trace before diagnosing a hang */
 #define GRAPH_MAX_FUNC_TEST     100000000
 
-static void __ftrace_dump(bool disable_tracing);
+static void
+__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode);
 static unsigned int graph_hang_thresh;
 
 /* Wrap the real function entry probe to avoid possible hanging */
@@ -266,7 +267,7 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace)
                 ftrace_graph_stop();
                 printk(KERN_WARNING "BUG: Function graph tracer hang!\n");
                 if (ftrace_dump_on_oops)
-                        __ftrace_dump(false);
+                        __ftrace_dump(false, DUMP_ALL);
                 return 0;
         }
 
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 4d6d711717f2..9d358301ae3e 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -15,6 +15,54 @@ static int sys_refcount_exit;
 static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
 static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
 
+static int syscall_enter_register(struct ftrace_event_call *event,
+                                 enum trace_reg type);
+static int syscall_exit_register(struct ftrace_event_call *event,
+                                 enum trace_reg type);
+
+static int syscall_enter_define_fields(struct ftrace_event_call *call);
+static int syscall_exit_define_fields(struct ftrace_event_call *call);
+
+static struct list_head *
+syscall_get_enter_fields(struct ftrace_event_call *call)
+{
+        struct syscall_metadata *entry = call->data;
+
+        return &entry->enter_fields;
+}
+
+static struct list_head *
+syscall_get_exit_fields(struct ftrace_event_call *call)
+{
+        struct syscall_metadata *entry = call->data;
+
+        return &entry->exit_fields;
+}
+
+struct trace_event_functions enter_syscall_print_funcs = {
+        .trace                  = print_syscall_enter,
+};
+
+struct trace_event_functions exit_syscall_print_funcs = {
+        .trace                  = print_syscall_exit,
+};
+
+struct ftrace_event_class event_class_syscall_enter = {
+        .system                 = "syscalls",
+        .reg                    = syscall_enter_register,
+        .define_fields          = syscall_enter_define_fields,
+        .get_fields             = syscall_get_enter_fields,
+        .raw_init               = init_syscall_trace,
+};
+
+struct ftrace_event_class event_class_syscall_exit = {
+        .system                 = "syscalls",
+        .reg                    = syscall_exit_register,
+        .define_fields          = syscall_exit_define_fields,
+        .get_fields             = syscall_get_exit_fields,
+        .raw_init               = init_syscall_trace,
+};
+
 extern unsigned long __start_syscalls_metadata[];
 extern unsigned long __stop_syscalls_metadata[];
 
@@ -53,7 +101,8 @@ static struct syscall_metadata *syscall_nr_to_meta(int nr)
 }
 
 enum print_line_t
-print_syscall_enter(struct trace_iterator *iter, int flags)
+print_syscall_enter(struct trace_iterator *iter, int flags,
+                    struct trace_event *event)
 {
         struct trace_seq *s = &iter->seq;
         struct trace_entry *ent = iter->ent;
@@ -68,7 +117,7 @@ print_syscall_enter(struct trace_iterator *iter, int flags)
         if (!entry)
                 goto end;
 
-        if (entry->enter_event->id != ent->type) {
+        if (entry->enter_event->event.type != ent->type) {
                 WARN_ON_ONCE(1);
                 goto end;
         }
@@ -105,7 +154,8 @@ end:
 }
 
 enum print_line_t
-print_syscall_exit(struct trace_iterator *iter, int flags)
+print_syscall_exit(struct trace_iterator *iter, int flags,
+                   struct trace_event *event)
 {
         struct trace_seq *s = &iter->seq;
         struct trace_entry *ent = iter->ent;
@@ -123,7 +173,7 @@ print_syscall_exit(struct trace_iterator *iter, int flags)
                 return TRACE_TYPE_HANDLED;
         }
 
-        if (entry->exit_event->id != ent->type) {
+        if (entry->exit_event->event.type != ent->type) {
                 WARN_ON_ONCE(1);
                 return TRACE_TYPE_UNHANDLED;
         }
@@ -205,7 +255,7 @@ static void free_syscall_print_fmt(struct ftrace_event_call *call)
                 kfree(call->print_fmt);
 }
 
-int syscall_enter_define_fields(struct ftrace_event_call *call)
+static int syscall_enter_define_fields(struct ftrace_event_call *call)
 {
         struct syscall_trace_enter trace;
         struct syscall_metadata *meta = call->data;
@@ -228,7 +278,7 @@ int syscall_enter_define_fields(struct ftrace_event_call *call)
         return ret;
 }
 
-int syscall_exit_define_fields(struct ftrace_event_call *call)
+static int syscall_exit_define_fields(struct ftrace_event_call *call)
 {
         struct syscall_trace_exit trace;
         int ret;
@@ -243,7 +293,7 @@ int syscall_exit_define_fields(struct ftrace_event_call *call)
         return ret;
 }
 
-void ftrace_syscall_enter(struct pt_regs *regs, long id)
+void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 {
         struct syscall_trace_enter *entry;
         struct syscall_metadata *sys_data;
@@ -265,7 +315,7 @@ void ftrace_syscall_enter(struct pt_regs *regs, long id)
         size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
 
         event = trace_current_buffer_lock_reserve(&buffer,
-                        sys_data->enter_event->id, size, 0, 0);
+                        sys_data->enter_event->event.type, size, 0, 0);
         if (!event)
                 return;
 
@@ -278,7 +328,7 @@ void ftrace_syscall_enter(struct pt_regs *regs, long id)
                 trace_current_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
-void ftrace_syscall_exit(struct pt_regs *regs, long ret)
+void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 {
         struct syscall_trace_exit *entry;
         struct syscall_metadata *sys_data;
@@ -297,7 +347,7 @@ void ftrace_syscall_exit(struct pt_regs *regs, long ret)
                 return;
 
         event = trace_current_buffer_lock_reserve(&buffer,
-                        sys_data->exit_event->id, sizeof(*entry), 0, 0);
+                        sys_data->exit_event->event.type, sizeof(*entry), 0, 0);
         if (!event)
                 return;
 
@@ -320,7 +370,7 @@ int reg_event_syscall_enter(struct ftrace_event_call *call)
                 return -ENOSYS;
         mutex_lock(&syscall_trace_lock);
         if (!sys_refcount_enter)
-                ret = register_trace_sys_enter(ftrace_syscall_enter);
+                ret = register_trace_sys_enter(ftrace_syscall_enter, NULL);
         if (!ret) {
                 set_bit(num, enabled_enter_syscalls);
                 sys_refcount_enter++;
@@ -340,7 +390,7 @@ void unreg_event_syscall_enter(struct ftrace_event_call *call)
         sys_refcount_enter--;
         clear_bit(num, enabled_enter_syscalls);
         if (!sys_refcount_enter)
-                unregister_trace_sys_enter(ftrace_syscall_enter);
+                unregister_trace_sys_enter(ftrace_syscall_enter, NULL);
         mutex_unlock(&syscall_trace_lock);
 }
 
@@ -354,7 +404,7 @@ int reg_event_syscall_exit(struct ftrace_event_call *call)
                 return -ENOSYS;
         mutex_lock(&syscall_trace_lock);
         if (!sys_refcount_exit)
-                ret = register_trace_sys_exit(ftrace_syscall_exit);
+                ret = register_trace_sys_exit(ftrace_syscall_exit, NULL);
         if (!ret) {
                 set_bit(num, enabled_exit_syscalls);
                 sys_refcount_exit++;
@@ -374,7 +424,7 @@ void unreg_event_syscall_exit(struct ftrace_event_call *call)
         sys_refcount_exit--;
         clear_bit(num, enabled_exit_syscalls);
         if (!sys_refcount_exit)
-                unregister_trace_sys_exit(ftrace_syscall_exit);
+                unregister_trace_sys_exit(ftrace_syscall_exit, NULL);
         mutex_unlock(&syscall_trace_lock);
 }
 
@@ -434,7 +484,7 @@ static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls);
 static int sys_perf_refcount_enter;
 static int sys_perf_refcount_exit;
 
-static void perf_syscall_enter(struct pt_regs *regs, long id)
+static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 {
         struct syscall_metadata *sys_data;
         struct syscall_trace_enter *rec;
@@ -461,7 +511,8 @@ static void perf_syscall_enter(struct pt_regs *regs, long id)
                 return;
 
         rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size,
-                                sys_data->enter_event->id, &rctx, &flags);
+                                sys_data->enter_event->event.type,
+                                &rctx, &flags);
         if (!rec)
                 return;
 
@@ -480,7 +531,7 @@ int perf_sysenter_enable(struct ftrace_event_call *call)
 
         mutex_lock(&syscall_trace_lock);
         if (!sys_perf_refcount_enter)
-                ret = register_trace_sys_enter(perf_syscall_enter);
+                ret = register_trace_sys_enter(perf_syscall_enter, NULL);
         if (ret) {
                 pr_info("event trace: Could not activate"
                                 "syscall entry trace point");
@@ -502,11 +553,11 @@ void perf_sysenter_disable(struct ftrace_event_call *call)
         sys_perf_refcount_enter--;
         clear_bit(num, enabled_perf_enter_syscalls);
         if (!sys_perf_refcount_enter)
-                unregister_trace_sys_enter(perf_syscall_enter);
+                unregister_trace_sys_enter(perf_syscall_enter, NULL);
         mutex_unlock(&syscall_trace_lock);
 }
 
-static void perf_syscall_exit(struct pt_regs *regs, long ret)
+static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 {
         struct syscall_metadata *sys_data;
         struct syscall_trace_exit *rec;
@@ -536,7 +587,8 @@ static void perf_syscall_exit(struct pt_regs *regs, long ret)
                 return;
 
         rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
-                                sys_data->exit_event->id, &rctx, &flags);
+                                sys_data->exit_event->event.type,
+                                &rctx, &flags);
         if (!rec)
                 return;
 
@@ -555,7 +607,7 @@ int perf_sysexit_enable(struct ftrace_event_call *call)
 
         mutex_lock(&syscall_trace_lock);
         if (!sys_perf_refcount_exit)
-                ret = register_trace_sys_exit(perf_syscall_exit);
+                ret = register_trace_sys_exit(perf_syscall_exit, NULL);
         if (ret) {
                 pr_info("event trace: Could not activate"
                                 "syscall exit trace point");
@@ -577,9 +629,50 @@ void perf_sysexit_disable(struct ftrace_event_call *call)
         sys_perf_refcount_exit--;
         clear_bit(num, enabled_perf_exit_syscalls);
         if (!sys_perf_refcount_exit)
-                unregister_trace_sys_exit(perf_syscall_exit);
+                unregister_trace_sys_exit(perf_syscall_exit, NULL);
         mutex_unlock(&syscall_trace_lock);
 }
 
 #endif /* CONFIG_PERF_EVENTS */
 
+static int syscall_enter_register(struct ftrace_event_call *event,
+                                 enum trace_reg type)
+{
+        switch (type) {
+        case TRACE_REG_REGISTER:
+                return reg_event_syscall_enter(event);
+        case TRACE_REG_UNREGISTER:
+                unreg_event_syscall_enter(event);
+                return 0;
+
+#ifdef CONFIG_PERF_EVENTS
+        case TRACE_REG_PERF_REGISTER:
+                return perf_sysenter_enable(event);
+        case TRACE_REG_PERF_UNREGISTER:
+                perf_sysenter_disable(event);
+                return 0;
+#endif
+        }
+        return 0;
+}
+
+static int syscall_exit_register(struct ftrace_event_call *event,
+                                 enum trace_reg type)
+{
+        switch (type) {
+        case TRACE_REG_REGISTER:
+                return reg_event_syscall_exit(event);
+        case TRACE_REG_UNREGISTER:
+                unreg_event_syscall_exit(event);
+                return 0;
+
+#ifdef CONFIG_PERF_EVENTS
+        case TRACE_REG_PERF_REGISTER:
+                return perf_sysexit_enable(event);
+        case TRACE_REG_PERF_UNREGISTER:
+                perf_sysexit_disable(event);
+                return 0;
+#endif
+        }
+        return 0;
+}
diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c
index cc2d2faa7d9e..a7cc3793baf6 100644
--- a/kernel/trace/trace_workqueue.c
+++ b/kernel/trace/trace_workqueue.c
@@ -49,7 +49,8 @@ static void cpu_workqueue_stat_free(struct kref *kref)
 
 /* Insertion of a work */
 static void
-probe_workqueue_insertion(struct task_struct *wq_thread,
+probe_workqueue_insertion(void *ignore,
+                          struct task_struct *wq_thread,
                           struct work_struct *work)
 {
         int cpu = cpumask_first(&wq_thread->cpus_allowed);
@@ -70,7 +71,8 @@ found:
 
 /* Execution of a work */
 static void
-probe_workqueue_execution(struct task_struct *wq_thread,
+probe_workqueue_execution(void *ignore,
+                          struct task_struct *wq_thread,
                           struct work_struct *work)
 {
         int cpu = cpumask_first(&wq_thread->cpus_allowed);
@@ -90,7 +92,8 @@ found:
 }
 
 /* Creation of a cpu workqueue thread */
-static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu)
+static void probe_workqueue_creation(void *ignore,
+                                     struct task_struct *wq_thread, int cpu)
 {
         struct cpu_workqueue_stats *cws;
         unsigned long flags;
@@ -114,7 +117,8 @@ static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu)
 }
 
 /* Destruction of a cpu workqueue thread */
-static void probe_workqueue_destruction(struct task_struct *wq_thread)
+static void
+probe_workqueue_destruction(void *ignore, struct task_struct *wq_thread)
 {
         /* Workqueue only execute on one cpu */
         int cpu = cpumask_first(&wq_thread->cpus_allowed);
@@ -259,19 +263,19 @@ int __init trace_workqueue_early_init(void)
 {
         int ret, cpu;
 
-        ret = register_trace_workqueue_insertion(probe_workqueue_insertion);
+        ret = register_trace_workqueue_insertion(probe_workqueue_insertion, NULL);
         if (ret)
                 goto out;
 
-        ret = register_trace_workqueue_execution(probe_workqueue_execution);
+        ret = register_trace_workqueue_execution(probe_workqueue_execution, NULL);
         if (ret)
                 goto no_insertion;
 
-        ret = register_trace_workqueue_creation(probe_workqueue_creation);
+        ret = register_trace_workqueue_creation(probe_workqueue_creation, NULL);
         if (ret)
                 goto no_execution;
 
-        ret = register_trace_workqueue_destruction(probe_workqueue_destruction);
+        ret = register_trace_workqueue_destruction(probe_workqueue_destruction, NULL);
         if (ret)
                 goto no_creation;
 
@@ -283,11 +287,11 @@ int __init trace_workqueue_early_init(void)
         return 0;
 
 no_creation:
-        unregister_trace_workqueue_creation(probe_workqueue_creation);
+        unregister_trace_workqueue_creation(probe_workqueue_creation, NULL);
 no_execution:
-        unregister_trace_workqueue_execution(probe_workqueue_execution);
+        unregister_trace_workqueue_execution(probe_workqueue_execution, NULL);
 no_insertion:
-        unregister_trace_workqueue_insertion(probe_workqueue_insertion);
+        unregister_trace_workqueue_insertion(probe_workqueue_insertion, NULL);
 out:
         pr_warning("trace_workqueue: unable to trace workqueues\n");
 
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index cc89be5bc0f8..c77f3eceea25 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -54,7 +54,7 @@ static struct hlist_head tracepoint_table[TRACEPOINT_TABLE_SIZE];
  */
 struct tracepoint_entry {
         struct hlist_node hlist;
-        void **funcs;
+        struct tracepoint_func *funcs;
         int refcount;   /* Number of times armed. 0 if disarmed. */
         char name[0];
 };
@@ -64,12 +64,12 @@ struct tp_probes {
                 struct rcu_head rcu;
                 struct list_head list;
         } u;
-        void *probes[0];
+        struct tracepoint_func probes[0];
 };
 
 static inline void *allocate_probes(int count)
 {
-        struct tp_probes *p  = kmalloc(count * sizeof(void *)
+        struct tp_probes *p  = kmalloc(count * sizeof(struct tracepoint_func)
                         + sizeof(struct tp_probes), GFP_KERNEL);
         return p == NULL ? NULL : p->probes;
 }
@@ -79,7 +79,7 @@ static void rcu_free_old_probes(struct rcu_head *head)
         kfree(container_of(head, struct tp_probes, u.rcu));
 }
 
-static inline void release_probes(void *old)
+static inline void release_probes(struct tracepoint_func *old)
 {
         if (old) {
                 struct tp_probes *tp_probes = container_of(old,
@@ -95,15 +95,16 @@ static void debug_print_probes(struct tracepoint_entry *entry)
         if (!tracepoint_debug || !entry->funcs)
                 return;
 
-        for (i = 0; entry->funcs[i]; i++)
-                printk(KERN_DEBUG "Probe %d : %p\n", i, entry->funcs[i]);
+        for (i = 0; entry->funcs[i].func; i++)
+                printk(KERN_DEBUG "Probe %d : %p\n", i, entry->funcs[i].func);
 }
 
-static void *
-tracepoint_entry_add_probe(struct tracepoint_entry *entry, void *probe)
+static struct tracepoint_func *
+tracepoint_entry_add_probe(struct tracepoint_entry *entry,
+                           void *probe, void *data)
 {
         int nr_probes = 0;
-        void **old, **new;
+        struct tracepoint_func *old, *new;
 
         WARN_ON(!probe);
 
@@ -111,8 +112,9 @@ tracepoint_entry_add_probe(struct tracepoint_entry *entry, void *probe)
         old = entry->funcs;
         if (old) {
                 /* (N -> N+1), (N != 0, 1) probes */
-                for (nr_probes = 0; old[nr_probes]; nr_probes++)
-                        if (old[nr_probes] == probe)
+                for (nr_probes = 0; old[nr_probes].func; nr_probes++)
+                        if (old[nr_probes].func == probe &&
+                            old[nr_probes].data == data)
                                 return ERR_PTR(-EEXIST);
         }
         /* + 2 : one for new probe, one for NULL func */
@@ -120,9 +122,10 @@ tracepoint_entry_add_probe(struct tracepoint_entry *entry, void *probe)
         if (new == NULL)
                 return ERR_PTR(-ENOMEM);
         if (old)
-                memcpy(new, old, nr_probes * sizeof(void *));
-        new[nr_probes] = probe;
-        new[nr_probes + 1] = NULL;
+                memcpy(new, old, nr_probes * sizeof(struct tracepoint_func));
+        new[nr_probes].func = probe;
+        new[nr_probes].data = data;
+        new[nr_probes + 1].func = NULL;
         entry->refcount = nr_probes + 1;
         entry->funcs = new;
         debug_print_probes(entry);
@@ -130,10 +133,11 @@ tracepoint_entry_add_probe(struct tracepoint_entry *entry, void *probe)
 }
 
 static void *
-tracepoint_entry_remove_probe(struct tracepoint_entry *entry, void *probe)
+tracepoint_entry_remove_probe(struct tracepoint_entry *entry,
+                              void *probe, void *data)
 {
         int nr_probes = 0, nr_del = 0, i;
-        void **old, **new;
+        struct tracepoint_func *old, *new;
 
         old = entry->funcs;
 
@@ -142,8 +146,10 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry, void *probe)
 
         debug_print_probes(entry);
         /* (N -> M), (N > 1, M >= 0) probes */
-        for (nr_probes = 0; old[nr_probes]; nr_probes++) {
-                if ((!probe || old[nr_probes] == probe))
+        for (nr_probes = 0; old[nr_probes].func; nr_probes++) {
+                if (!probe ||
+                    (old[nr_probes].func == probe &&
+                     old[nr_probes].data == data))
                         nr_del++;
         }
 
@@ -160,10 +166,11 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry, void *probe)
                 new = allocate_probes(nr_probes - nr_del + 1);
                 if (new == NULL)
                         return ERR_PTR(-ENOMEM);
-                for (i = 0; old[i]; i++)
-                        if ((probe && old[i] != probe))
+                for (i = 0; old[i].func; i++)
+                        if (probe &&
+                            (old[i].func != probe || old[i].data != data))
                                 new[j++] = old[i];
-                new[nr_probes - nr_del] = NULL;
+                new[nr_probes - nr_del].func = NULL;
                 entry->refcount = nr_probes - nr_del;
                 entry->funcs = new;
         }
@@ -315,18 +322,19 @@ static void tracepoint_update_probes(void)
         module_update_tracepoints();
 }
 
-static void *tracepoint_add_probe(const char *name, void *probe)
+static struct tracepoint_func *
+tracepoint_add_probe(const char *name, void *probe, void *data)
 {
         struct tracepoint_entry *entry;
-        void *old;
+        struct tracepoint_func *old;
 
         entry = get_tracepoint(name);
         if (!entry) {
                 entry = add_tracepoint(name);
                 if (IS_ERR(entry))
-                        return entry;
+                        return (struct tracepoint_func *)entry;
         }
-        old = tracepoint_entry_add_probe(entry, probe);
+        old = tracepoint_entry_add_probe(entry, probe, data);
         if (IS_ERR(old) && !entry->refcount)
                 remove_tracepoint(entry);
         return old;
@@ -340,12 +348,12 @@ static void *tracepoint_add_probe(const char *name, void *probe)
  * Returns 0 if ok, error value on error.
  * The probe address must at least be aligned on the architecture pointer size.
  */
-int tracepoint_probe_register(const char *name, void *probe)
+int tracepoint_probe_register(const char *name, void *probe, void *data)
 {
-        void *old;
+        struct tracepoint_func *old;
 
         mutex_lock(&tracepoints_mutex);
-        old = tracepoint_add_probe(name, probe);
+        old = tracepoint_add_probe(name, probe, data);
         mutex_unlock(&tracepoints_mutex);
         if (IS_ERR(old))
                 return PTR_ERR(old);
@@ -356,15 +364,16 @@ int tracepoint_probe_register(const char *name, void *probe)
 }
 EXPORT_SYMBOL_GPL(tracepoint_probe_register);
 
-static void *tracepoint_remove_probe(const char *name, void *probe)
+static struct tracepoint_func *
+tracepoint_remove_probe(const char *name, void *probe, void *data)
 {
         struct tracepoint_entry *entry;
-        void *old;
+        struct tracepoint_func *old;
 
         entry = get_tracepoint(name);
         if (!entry)
                 return ERR_PTR(-ENOENT);
-        old = tracepoint_entry_remove_probe(entry, probe);
+        old = tracepoint_entry_remove_probe(entry, probe, data);
         if (IS_ERR(old))
                 return old;
         if (!entry->refcount)
@@ -382,12 +391,12 @@ static void *tracepoint_remove_probe(const char *name, void *probe)
  * itself uses stop_machine(), which insures that every preempt disabled section
  * have finished.
  */
-int tracepoint_probe_unregister(const char *name, void *probe)
+int tracepoint_probe_unregister(const char *name, void *probe, void *data)
 {
-        void *old;
+        struct tracepoint_func *old;
 
         mutex_lock(&tracepoints_mutex);
-        old = tracepoint_remove_probe(name, probe);
+        old = tracepoint_remove_probe(name, probe, data);
         mutex_unlock(&tracepoints_mutex);
         if (IS_ERR(old))
                 return PTR_ERR(old);
@@ -418,12 +427,13 @@ static void tracepoint_add_old_probes(void *old)
  *
  * caller must call tracepoint_probe_update_all()
  */
-int tracepoint_probe_register_noupdate(const char *name, void *probe)
+int tracepoint_probe_register_noupdate(const char *name, void *probe,
+                                       void *data)
 {
-        void *old;
+        struct tracepoint_func *old;
 
         mutex_lock(&tracepoints_mutex);
-        old = tracepoint_add_probe(name, probe);
+        old = tracepoint_add_probe(name, probe, data);
         if (IS_ERR(old)) {
                 mutex_unlock(&tracepoints_mutex);
                 return PTR_ERR(old);
@@ -441,12 +451,13 @@ EXPORT_SYMBOL_GPL(tracepoint_probe_register_noupdate);
  *
  * caller must call tracepoint_probe_update_all()
  */
-int tracepoint_probe_unregister_noupdate(const char *name, void *probe)
+int tracepoint_probe_unregister_noupdate(const char *name, void *probe,
+                                         void *data)
 {
-        void *old;
+        struct tracepoint_func *old;
 
         mutex_lock(&tracepoints_mutex);
-        old = tracepoint_remove_probe(name, probe);
+        old = tracepoint_remove_probe(name, probe, data);
         if (IS_ERR(old)) {
                 mutex_unlock(&tracepoints_mutex);
                 return PTR_ERR(old);
diff --git a/kernel/user.c b/kernel/user.c
index 766467b3bcb7..7e72614b736d 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -16,7 +16,6 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/user_namespace.h>
-#include "cred-internals.h"
 
 struct user_namespace init_user_ns = {
         .kref = {
@@ -137,9 +136,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
         struct hlist_head *hashent = uidhashentry(ns, uid);
         struct user_struct *up, *new;
 
-        /* Make uid_hash_find() + uids_user_create() + uid_hash_insert()
-         * atomic.
-         */
         spin_lock_irq(&uidhash_lock);
         up = uid_hash_find(uid, hashent);
         spin_unlock_irq(&uidhash_lock);
@@ -161,11 +157,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
                 spin_lock_irq(&uidhash_lock);
                 up = uid_hash_find(uid, hashent);
                 if (up) {
-                        /* This case is not possible when CONFIG_USER_SCHED
-                         * is defined, since we serialize alloc_uid() using
-                         * uids_mutex. Hence no need to call
-                         * sched_destroy_user() or remove_user_sysfs_dir().
-                         */
                         key_put(new->uid_keyring);
                         key_put(new->session_keyring);
                         kmem_cache_free(uid_cachep, new);
@@ -178,8 +169,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
 
         return up;
 
-        put_user_ns(new->user_ns);
-        kmem_cache_free(uid_cachep, new);
 out_unlock:
         return NULL;
 }