20 files changed, 387 insertions, 108 deletions

diff --git a/kernel/async.c b/kernel/async.c
index 608b32b42812..f565891f2c9b 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -54,6 +54,7 @@ asynchronous and synchronous parts of the kernel.
 #include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/kthread.h>
+#include <linux/delay.h>
 #include <asm/atomic.h>
 
 static async_cookie_t next_cookie = 1;
@@ -132,21 +133,23 @@ static void run_one_entry(void)
         entry = list_first_entry(&async_pending, struct async_entry, list);
 
         /* 2) move it to the running queue */
-        list_del(&entry->list);
-        list_add_tail(&entry->list, &async_running);
+        list_move_tail(&entry->list, entry->running);
         spin_unlock_irqrestore(&async_lock, flags);
 
         /* 3) run it (and print duration)*/
         if (initcall_debug && system_state == SYSTEM_BOOTING) {
-                printk("calling  %lli_%pF @ %i\n", entry->cookie, entry->func, task_pid_nr(current));
+                printk("calling  %lli_%pF @ %i\n", (long long)entry->cookie,
+                        entry->func, task_pid_nr(current));
                 calltime = ktime_get();
         }
         entry->func(entry->data, entry->cookie);
         if (initcall_debug && system_state == SYSTEM_BOOTING) {
                 rettime = ktime_get();
                 delta = ktime_sub(rettime, calltime);
-                printk("initcall %lli_%pF returned 0 after %lld usecs\n", entry->cookie,
-                        entry->func, ktime_to_ns(delta) >> 10);
+                printk("initcall %lli_%pF returned 0 after %lld usecs\n",
+                        (long long)entry->cookie,
+                        entry->func,
+                        (long long)ktime_to_ns(delta) >> 10);
         }
 
         /* 4) remove it from the running queue */
@@ -205,18 +208,44 @@ static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct l
         return newcookie;
 }
 
+/**
+ * async_schedule - schedule a function for asynchronous execution
+ * @ptr: function to execute asynchronously
+ * @data: data pointer to pass to the function
+ *
+ * Returns an async_cookie_t that may be used for checkpointing later.
+ * Note: This function may be called from atomic or non-atomic contexts.
+ */
 async_cookie_t async_schedule(async_func_ptr *ptr, void *data)
 {
-        return __async_schedule(ptr, data, &async_pending);
+        return __async_schedule(ptr, data, &async_running);
 }
 EXPORT_SYMBOL_GPL(async_schedule);
 
-async_cookie_t async_schedule_special(async_func_ptr *ptr, void *data, struct list_head *running)
+/**
+ * async_schedule_domain - schedule a function for asynchronous execution within a certain domain
+ * @ptr: function to execute asynchronously
+ * @data: data pointer to pass to the function
+ * @running: running list for the domain
+ *
+ * Returns an async_cookie_t that may be used for checkpointing later.
+ * @running may be used in the async_synchronize_*_domain() functions
+ * to wait within a certain synchronization domain rather than globally.
+ * A synchronization domain is specified via the running queue @running to use.
+ * Note: This function may be called from atomic or non-atomic contexts.
+ */
+async_cookie_t async_schedule_domain(async_func_ptr *ptr, void *data,
+                                     struct list_head *running)
 {
         return __async_schedule(ptr, data, running);
 }
-EXPORT_SYMBOL_GPL(async_schedule_special);
+EXPORT_SYMBOL_GPL(async_schedule_domain);
 
+/**
+ * async_synchronize_full - synchronize all asynchronous function calls
+ *
+ * This function waits until all asynchronous function calls have been done.
+ */
 void async_synchronize_full(void)
 {
         do {
@@ -225,13 +254,30 @@ void async_synchronize_full(void)
 }
 EXPORT_SYMBOL_GPL(async_synchronize_full);
 
-void async_synchronize_full_special(struct list_head *list)
+/**
+ * async_synchronize_full_domain - synchronize all asynchronous function within a certain domain
+ * @list: running list to synchronize on
+ *
+ * This function waits until all asynchronous function calls for the
+ * synchronization domain specified by the running list @list have been done.
+ */
+void async_synchronize_full_domain(struct list_head *list)
 {
-        async_synchronize_cookie_special(next_cookie, list);
+        async_synchronize_cookie_domain(next_cookie, list);
 }
-EXPORT_SYMBOL_GPL(async_synchronize_full_special);
+EXPORT_SYMBOL_GPL(async_synchronize_full_domain);
 
-void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *running)
+/**
+ * async_synchronize_cookie_domain - synchronize asynchronous function calls within a certain domain with cookie checkpointing
+ * @cookie: async_cookie_t to use as checkpoint
+ * @running: running list to synchronize on
+ *
+ * This function waits until all asynchronous function calls for the
+ * synchronization domain specified by the running list @list submitted
+ * prior to @cookie have been done.
+ */
+void async_synchronize_cookie_domain(async_cookie_t cookie,
+                                     struct list_head *running)
 {
         ktime_t starttime, delta, endtime;
 
@@ -247,14 +293,22 @@ void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *r
                 delta = ktime_sub(endtime, starttime);
 
                 printk("async_continuing @ %i after %lli usec\n",
-                        task_pid_nr(current), ktime_to_ns(delta) >> 10);
+                        task_pid_nr(current),
+                        (long long)ktime_to_ns(delta) >> 10);
         }
 }
-EXPORT_SYMBOL_GPL(async_synchronize_cookie_special);
+EXPORT_SYMBOL_GPL(async_synchronize_cookie_domain);
 
+/**
+ * async_synchronize_cookie - synchronize asynchronous function calls with cookie checkpointing
+ * @cookie: async_cookie_t to use as checkpoint
+ *
+ * This function waits until all asynchronous function calls prior to @cookie
+ * have been done.
+ */
 void async_synchronize_cookie(async_cookie_t cookie)
 {
-        async_synchronize_cookie_special(cookie, &async_running);
+        async_synchronize_cookie_domain(cookie, &async_running);
 }
 EXPORT_SYMBOL_GPL(async_synchronize_cookie);
 
@@ -315,7 +369,11 @@ static int async_manager_thread(void *unused)
                 ec = atomic_read(&entry_count);
 
                 while (tc < ec && tc < MAX_THREADS) {
-                        kthread_run(async_thread, NULL, "async/%i", tc);
+                        if (IS_ERR(kthread_run(async_thread, NULL, "async/%i",
+                                               tc))) {
+                                msleep(100);
+                                continue;
+                        }
                         atomic_inc(&thread_count);
                         tc++;
                 }
@@ -330,7 +388,9 @@ static int async_manager_thread(void *unused)
 static int __init async_init(void)
 {
         if (async_enabled)
-                kthread_run(async_manager_thread, NULL, "async/mgr");
+                if (IS_ERR(kthread_run(async_manager_thread, NULL,
+                                       "async/mgr")))
+                        async_enabled = 0;
         return 0;
 }
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 5a54ff42874e..e14db9c089b9 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2351,7 +2351,7 @@ static void cgroup_lock_hierarchy(struct cgroupfs_root *root)
         for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
                 struct cgroup_subsys *ss = subsys[i];
                 if (ss->root == root)
-                        mutex_lock_nested(&ss->hierarchy_mutex, i);
+                        mutex_lock(&ss->hierarchy_mutex);
         }
 }
 
@@ -2637,6 +2637,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
         BUG_ON(!list_empty(&init_task.tasks));
 
         mutex_init(&ss->hierarchy_mutex);
+        lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key);
         ss->active = 1;
 }
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index a85678865c5e..f76db9dcaa05 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -61,6 +61,14 @@
 #include <linux/cgroup.h>
 
 /*
+ * Workqueue for cpuset related tasks.
+ *
+ * Using kevent workqueue may cause deadlock when memory_migrate
+ * is set. So we create a separate workqueue thread for cpuset.
+ */
+static struct workqueue_struct *cpuset_wq;
+
+/*
  * Tracks how many cpusets are currently defined in system.
  * When there is only one cpuset (the root cpuset) we can
  * short circuit some hooks.
@@ -831,7 +839,7 @@ static DECLARE_WORK(rebuild_sched_domains_work, do_rebuild_sched_domains);
  */
 static void async_rebuild_sched_domains(void)
 {
-        schedule_work(&rebuild_sched_domains_work);
+        queue_work(cpuset_wq, &rebuild_sched_domains_work);
 }
 
 /*
@@ -2111,6 +2119,9 @@ void __init cpuset_init_smp(void)
 
         hotcpu_notifier(cpuset_track_online_cpus, 0);
         hotplug_memory_notifier(cpuset_track_online_nodes, 10);
+
+        cpuset_wq = create_singlethread_workqueue("cpuset");
+        BUG_ON(!cpuset_wq);
 }
 
 /**
diff --git a/kernel/exit.c b/kernel/exit.c
index f80dec3f1875..efd30ccf3858 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -118,6 +118,8 @@ static void __exit_signal(struct task_struct *tsk)
                  * We won't ever get here for the group leader, since it
                  * will have been the last reference on the signal_struct.
                  */
+                sig->utime = cputime_add(sig->utime, task_utime(tsk));
+                sig->stime = cputime_add(sig->stime, task_stime(tsk));
                 sig->gtime = cputime_add(sig->gtime, task_gtime(tsk));
                 sig->min_flt += tsk->min_flt;
                 sig->maj_flt += tsk->maj_flt;
@@ -126,6 +128,7 @@ static void __exit_signal(struct task_struct *tsk)
                 sig->inblock += task_io_get_inblock(tsk);
                 sig->oublock += task_io_get_oublock(tsk);
                 task_io_accounting_add(&sig->ioac, &tsk->ioac);
+                sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
                 sig = NULL; /* Marker for below. */
         }
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 242a706e7721..a66fbde20715 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -851,13 +851,14 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
         sig->tty_old_pgrp = NULL;
         sig->tty = NULL;
 
-        sig->cutime = sig->cstime = cputime_zero;
+        sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero;
         sig->gtime = cputime_zero;
         sig->cgtime = cputime_zero;
         sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
         sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
         sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
         task_io_accounting_init(&sig->ioac);
+        sig->sum_sched_runtime = 0;
         taskstats_tgid_init(sig);
 
         task_lock(current->group_leader);
@@ -1005,6 +1006,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
          * triggers too late. This doesn't hurt, the check is only there
          * to stop root fork bombs.
          */
+        retval = -EAGAIN;
         if (nr_threads >= max_threads)
                 goto bad_fork_cleanup_count;
 
@@ -1093,7 +1095,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #ifdef CONFIG_DEBUG_MUTEXES
         p->blocked_on = NULL; /* not blocked yet */
 #endif
-        if (unlikely(ptrace_reparented(current)))
+        if (unlikely(current->ptrace))
                 ptrace_fork(p, clone_flags);
 
         /* Perform scheduler related setup. Assign this task to a CPU. */
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index ecf765c6a77a..acd88356ac76 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -71,7 +71,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
         desc = irq_desc_ptrs[irq];
 
         if (desc && old_desc != desc)
-                        goto out_unlock;
+                goto out_unlock;
 
         node = cpu_to_node(cpu);
         desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
@@ -84,10 +84,15 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
         init_copy_one_irq_desc(irq, old_desc, desc, cpu);
 
         irq_desc_ptrs[irq] = desc;
+        spin_unlock_irqrestore(&sparse_irq_lock, flags);
 
         /* free the old one */
         free_one_irq_desc(old_desc, desc);
+        spin_unlock(&old_desc->lock);
         kfree(old_desc);
+        spin_lock(&desc->lock);
+
+        return desc;
 
 out_unlock:
         spin_unlock_irqrestore(&sparse_irq_lock, flags);
diff --git a/kernel/itimer.c b/kernel/itimer.c
index 6a5fe93dd8bd..58762f7077ec 100644
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -62,7 +62,7 @@ int do_getitimer(int which, struct itimerval *value)
                         struct task_cputime cputime;
                         cputime_t utime;
 
-                        thread_group_cputime(tsk, &cputime);
+                        thread_group_cputimer(tsk, &cputime);
                         utime = cputime.utime;
                         if (cputime_le(cval, utime)) { /* about to fire */
                                 cval = jiffies_to_cputime(1);
@@ -82,7 +82,7 @@ int do_getitimer(int which, struct itimerval *value)
                         struct task_cputime times;
                         cputime_t ptime;
 
-                        thread_group_cputime(tsk, &times);
+                        thread_group_cputimer(tsk, &times);
                         ptime = cputime_add(times.utime, times.stime);
                         if (cputime_le(cval, ptime)) { /* about to fire */
                                 cval = jiffies_to_cputime(1);
diff --git a/kernel/module.c b/kernel/module.c
index e8b51d41dd72..ba22484a987e 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -573,13 +573,13 @@ static char last_unloaded_module[MODULE_NAME_LEN+1];
 /* Init the unload section of the module. */
 static void module_unload_init(struct module *mod)
 {
-        unsigned int i;
+        int cpu;
 
         INIT_LIST_HEAD(&mod->modules_which_use_me);
-        for (i = 0; i < NR_CPUS; i++)
-                local_set(&mod->ref[i].count, 0);
+        for_each_possible_cpu(cpu)
+                local_set(__module_ref_addr(mod, cpu), 0);
         /* Hold reference count during initialization. */
-        local_set(&mod->ref[raw_smp_processor_id()].count, 1);
+        local_set(__module_ref_addr(mod, raw_smp_processor_id()), 1);
         /* Backwards compatibility macros put refcount during init. */
         mod->waiter = current;
 }
@@ -717,10 +717,11 @@ static int try_stop_module(struct module *mod, int flags, int *forced)
 
 unsigned int module_refcount(struct module *mod)
 {
-        unsigned int i, total = 0;
+        unsigned int total = 0;
+        int cpu;
 
-        for (i = 0; i < NR_CPUS; i++)
-                total += local_read(&mod->ref[i].count);
+        for_each_possible_cpu(cpu)
+                total += local_read(__module_ref_addr(mod, cpu));
         return total;
 }
 EXPORT_SYMBOL(module_refcount);
@@ -894,7 +895,7 @@ void module_put(struct module *module)
 {
         if (module) {
                 unsigned int cpu = get_cpu();
-                local_dec(&module->ref[cpu].count);
+                local_dec(__module_ref_addr(module, cpu));
                 /* Maybe they're waiting for us to drop reference? */
                 if (unlikely(!module_is_live(module)))
                         wake_up_process(module->waiter);
@@ -1464,7 +1465,10 @@ static void free_module(struct module *mod)
         kfree(mod->args);
         if (mod->percpu)
                 percpu_modfree(mod->percpu);
-
+#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+        if (mod->refptr)
+                percpu_modfree(mod->refptr);
+#endif
         /* Free lock-classes: */
         lockdep_free_key_range(mod->module_core, mod->core_size);
 
@@ -2011,6 +2015,14 @@ static noinline struct module *load_module(void __user *umod,
         if (err < 0)
                 goto free_mod;
 
+#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+        mod->refptr = percpu_modalloc(sizeof(local_t), __alignof__(local_t),
+                                      mod->name);
+        if (!mod->refptr) {
+                err = -ENOMEM;
+                goto free_mod;
+        }
+#endif
         if (pcpuindex) {
                 /* We have a special allocation for this section. */
                 percpu = percpu_modalloc(sechdrs[pcpuindex].sh_size,
@@ -2018,7 +2030,7 @@ static noinline struct module *load_module(void __user *umod,
                                          mod->name);
                 if (!percpu) {
                         err = -ENOMEM;
-                        goto free_mod;
+                        goto free_percpu;
                 }
                 sechdrs[pcpuindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
                 mod->percpu = percpu;
@@ -2282,6 +2294,9 @@ static noinline struct module *load_module(void __user *umod,
  free_percpu:
         if (percpu)
                 percpu_modfree(percpu);
+#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+        percpu_modfree(mod->refptr);
+#endif
  free_mod:
         kfree(args);
  free_hdr:
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index fa07da94d7be..2313a4cc14ea 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -230,6 +230,71 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
         return 0;
 }
 
+void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
+{
+        struct sighand_struct *sighand;
+        struct signal_struct *sig;
+        struct task_struct *t;
+
+        *times = INIT_CPUTIME;
+
+        rcu_read_lock();
+        sighand = rcu_dereference(tsk->sighand);
+        if (!sighand)
+                goto out;
+
+        sig = tsk->signal;
+
+        t = tsk;
+        do {
+                times->utime = cputime_add(times->utime, t->utime);
+                times->stime = cputime_add(times->stime, t->stime);
+                times->sum_exec_runtime += t->se.sum_exec_runtime;
+
+                t = next_thread(t);
+        } while (t != tsk);
+
+        times->utime = cputime_add(times->utime, sig->utime);
+        times->stime = cputime_add(times->stime, sig->stime);
+        times->sum_exec_runtime += sig->sum_sched_runtime;
+out:
+        rcu_read_unlock();
+}
+
+static void update_gt_cputime(struct task_cputime *a, struct task_cputime *b)
+{
+        if (cputime_gt(b->utime, a->utime))
+                a->utime = b->utime;
+
+        if (cputime_gt(b->stime, a->stime))
+                a->stime = b->stime;
+
+        if (b->sum_exec_runtime > a->sum_exec_runtime)
+                a->sum_exec_runtime = b->sum_exec_runtime;
+}
+
+void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
+{
+        struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+        struct task_cputime sum;
+        unsigned long flags;
+
+        spin_lock_irqsave(&cputimer->lock, flags);
+        if (!cputimer->running) {
+                cputimer->running = 1;
+                /*
+                 * The POSIX timer interface allows for absolute time expiry
+                 * values through the TIMER_ABSTIME flag, therefore we have
+                 * to synchronize the timer to the clock every time we start
+                 * it.
+                 */
+                thread_group_cputime(tsk, &sum);
+                update_gt_cputime(&cputimer->cputime, &sum);
+        }
+        *times = cputimer->cputime;
+        spin_unlock_irqrestore(&cputimer->lock, flags);
+}
+
 /*
  * Sample a process (thread group) clock for the given group_leader task.
  * Must be called with tasklist_lock held for reading.
@@ -457,7 +522,7 @@ void posix_cpu_timers_exit_group(struct task_struct *tsk)
 {
         struct task_cputime cputime;
 
-        thread_group_cputime(tsk, &cputime);
+        thread_group_cputimer(tsk, &cputime);
         cleanup_timers(tsk->signal->cpu_timers,
                        cputime.utime, cputime.stime, cputime.sum_exec_runtime);
 }
@@ -964,6 +1029,19 @@ static void check_thread_timers(struct task_struct *tsk,
         }
 }
 
+static void stop_process_timers(struct task_struct *tsk)
+{
+        struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+        unsigned long flags;
+
+        if (!cputimer->running)
+                return;
+
+        spin_lock_irqsave(&cputimer->lock, flags);
+        cputimer->running = 0;
+        spin_unlock_irqrestore(&cputimer->lock, flags);
+}
+
 /*
  * Check for any per-thread CPU timers that have fired and move them
  * off the tsk->*_timers list onto the firing list.  Per-thread timers
@@ -987,13 +1065,15 @@ static void check_process_timers(struct task_struct *tsk,
             sig->rlim[RLIMIT_CPU].rlim_cur == RLIM_INFINITY &&
             list_empty(&timers[CPUCLOCK_VIRT]) &&
             cputime_eq(sig->it_virt_expires, cputime_zero) &&
-            list_empty(&timers[CPUCLOCK_SCHED]))
+            list_empty(&timers[CPUCLOCK_SCHED])) {
+                stop_process_timers(tsk);
                 return;
+        }
 
         /*
          * Collect the current process totals.
          */
-        thread_group_cputime(tsk, &cputime);
+        thread_group_cputimer(tsk, &cputime);
         utime = cputime.utime;
         ptime = cputime_add(utime, cputime.stime);
         sum_sched_runtime = cputime.sum_exec_runtime;
@@ -1259,7 +1339,7 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
         if (!task_cputime_zero(&sig->cputime_expires)) {
                 struct task_cputime group_sample;
 
-                thread_group_cputime(tsk, &group_sample);
+                thread_group_cputimer(tsk, &group_sample);
                 if (task_cputime_expired(&group_sample, &sig->cputime_expires))
                         return 1;
         }
@@ -1329,6 +1409,33 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 }
 
 /*
+ * Sample a process (thread group) timer for the given group_leader task.
+ * Must be called with tasklist_lock held for reading.
+ */
+static int cpu_timer_sample_group(const clockid_t which_clock,
+                                  struct task_struct *p,
+                                  union cpu_time_count *cpu)
+{
+        struct task_cputime cputime;
+
+        thread_group_cputimer(p, &cputime);
+        switch (CPUCLOCK_WHICH(which_clock)) {
+        default:
+                return -EINVAL;
+        case CPUCLOCK_PROF:
+                cpu->cpu = cputime_add(cputime.utime, cputime.stime);
+                break;
+        case CPUCLOCK_VIRT:
+                cpu->cpu = cputime.utime;
+                break;
+        case CPUCLOCK_SCHED:
+                cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p);
+                break;
+        }
+        return 0;
+}
+
+/*
  * Set one of the process-wide special case CPU timers.
  * The tsk->sighand->siglock must be held by the caller.
  * The *newval argument is relative and we update it to be absolute, *oldval
@@ -1341,7 +1448,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
         struct list_head *head;
 
         BUG_ON(clock_idx == CPUCLOCK_SCHED);
-        cpu_clock_sample_group(clock_idx, tsk, &now);
+        cpu_timer_sample_group(clock_idx, tsk, &now);
 
         if (oldval) {
                 if (!cputime_eq(*oldval, cputime_zero)) {
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 239988873971..b4d219016b6c 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -57,16 +57,6 @@ int pm_notifier_call_chain(unsigned long val)
 #ifdef CONFIG_PM_DEBUG
 int pm_test_level = TEST_NONE;
 
-static int suspend_test(int level)
-{
-        if (pm_test_level == level) {
-                printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n");
-                mdelay(5000);
-                return 1;
-        }
-        return 0;
-}
-
 static const char * const pm_tests[__TEST_AFTER_LAST] = {
         [TEST_NONE] = "none",
         [TEST_CORE] = "core",
@@ -125,14 +115,24 @@ static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr,
 }
 
 power_attr(pm_test);
-#else /* !CONFIG_PM_DEBUG */
-static inline int suspend_test(int level) { return 0; }
-#endif /* !CONFIG_PM_DEBUG */
+#endif /* CONFIG_PM_DEBUG */
 
 #endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_SUSPEND
 
+static int suspend_test(int level)
+{
+#ifdef CONFIG_PM_DEBUG
+        if (pm_test_level == level) {
+                printk(KERN_INFO "suspend debug: Waiting for 5 seconds.\n");
+                mdelay(5000);
+                return 1;
+        }
+#endif /* !CONFIG_PM_DEBUG */
+        return 0;
+}
+
 #ifdef CONFIG_PM_TEST_SUSPEND
 
 /*
diff --git a/kernel/profile.c b/kernel/profile.c
index 784933acf5b8..7724e0409bae 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -114,12 +114,15 @@ int __ref profile_init(void)
         if (!slab_is_available()) {
                 prof_buffer = alloc_bootmem(buffer_bytes);
                 alloc_bootmem_cpumask_var(&prof_cpu_mask);
+                cpumask_copy(prof_cpu_mask, cpu_possible_mask);
                 return 0;
         }
 
         if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL))
                 return -ENOMEM;
 
+        cpumask_copy(prof_cpu_mask, cpu_possible_mask);
+
         prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL);
         if (prof_buffer)
                 return 0;
diff --git a/kernel/sched.c b/kernel/sched.c
index 52bbf1c842a8..c1d0ed360088 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3880,19 +3880,24 @@ int select_nohz_load_balancer(int stop_tick)
         int cpu = smp_processor_id();
 
         if (stop_tick) {
-                cpumask_set_cpu(cpu, nohz.cpu_mask);
                 cpu_rq(cpu)->in_nohz_recently = 1;
 
-                /*
-                 * If we are going offline and still the leader, give up!
-                 */
-                if (!cpu_active(cpu) &&
-                    atomic_read(&nohz.load_balancer) == cpu) {
+                if (!cpu_active(cpu)) {
+                        if (atomic_read(&nohz.load_balancer) != cpu)
+                                return 0;
+
+                        /*
+                         * If we are going offline and still the leader,
+                         * give up!
+                         */
                         if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
                                 BUG();
+
                         return 0;
                 }
 
+                cpumask_set_cpu(cpu, nohz.cpu_mask);
+
                 /* time for ilb owner also to sleep */
                 if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
                         if (atomic_read(&nohz.load_balancer) == cpu)
@@ -4687,8 +4692,8 @@ EXPORT_SYMBOL(default_wake_function);
  * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
  * zero in this (rare) case, and we handle it by continuing to scan the queue.
  */
-static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
-                             int nr_exclusive, int sync, void *key)
+void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+                        int nr_exclusive, int sync, void *key)
 {
         wait_queue_t *curr, *next;
 
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 5cc1c162044f..0566f2a03c42 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -719,7 +719,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
                 __enqueue_entity(cfs_rq, se);
 }
 
-static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
         if (cfs_rq->last == se)
                 cfs_rq->last = NULL;
@@ -728,6 +728,12 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
                 cfs_rq->next = NULL;
 }
 
+static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+        for_each_sched_entity(se)
+                __clear_buddies(cfs_rq_of(se), se);
+}
+
 static void
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 {
@@ -768,8 +774,14 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 
         ideal_runtime = sched_slice(cfs_rq, curr);
         delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
-        if (delta_exec > ideal_runtime)
+        if (delta_exec > ideal_runtime) {
                 resched_task(rq_of(cfs_rq)->curr);
+                /*
+                 * The current task ran long enough, ensure it doesn't get
+                 * re-elected due to buddy favours.
+                 */
+                clear_buddies(cfs_rq, curr);
+        }
 }
 
 static void
@@ -1452,6 +1464,11 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
 
         do {
                 se = pick_next_entity(cfs_rq);
+                /*
+                 * If se was a buddy, clear it so that it will have to earn
+                 * the favour again.
+                 */
+                __clear_buddies(cfs_rq, se);
                 set_next_entity(cfs_rq, se);
                 cfs_rq = group_cfs_rq(se);
         } while (cfs_rq);
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 954e1a81b796..bac1061cea2f 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -968,8 +968,8 @@ static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask)
         if ((this_cpu != -1) && cpu_isset(this_cpu, *mask))
                 return this_cpu;
 
-        first = first_cpu(*mask);
-        if (first != NR_CPUS)
+        first = cpumask_first(mask);
+        if (first < nr_cpu_ids)
                 return first;
 
         return -1;
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index 8ab0cef8ecab..a8f93dd374e1 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -296,19 +296,21 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next)
 static inline void account_group_user_time(struct task_struct *tsk,
                                            cputime_t cputime)
 {
-        struct task_cputime *times;
-        struct signal_struct *sig;
+        struct thread_group_cputimer *cputimer;
 
         /* tsk == current, ensure it is safe to use ->signal */
         if (unlikely(tsk->exit_state))
                 return;
 
-        sig = tsk->signal;
-        times = &sig->cputime.totals;
+        cputimer = &tsk->signal->cputimer;
 
-        spin_lock(&times->lock);
-        times->utime = cputime_add(times->utime, cputime);
-        spin_unlock(&times->lock);
+        if (!cputimer->running)
+                return;
+
+        spin_lock(&cputimer->lock);
+        cputimer->cputime.utime =
+                cputime_add(cputimer->cputime.utime, cputime);
+        spin_unlock(&cputimer->lock);
 }
 
 /**
@@ -324,19 +326,21 @@ static inline void account_group_user_time(struct task_struct *tsk,
 static inline void account_group_system_time(struct task_struct *tsk,
                                              cputime_t cputime)
 {
-        struct task_cputime *times;
-        struct signal_struct *sig;
+        struct thread_group_cputimer *cputimer;
 
         /* tsk == current, ensure it is safe to use ->signal */
         if (unlikely(tsk->exit_state))
                 return;
 
-        sig = tsk->signal;
-        times = &sig->cputime.totals;
+        cputimer = &tsk->signal->cputimer;
+
+        if (!cputimer->running)
+                return;
 
-        spin_lock(&times->lock);
-        times->stime = cputime_add(times->stime, cputime);
-        spin_unlock(&times->lock);
+        spin_lock(&cputimer->lock);
+        cputimer->cputime.stime =
+                cputime_add(cputimer->cputime.stime, cputime);
+        spin_unlock(&cputimer->lock);
 }
 
 /**
@@ -352,7 +356,7 @@ static inline void account_group_system_time(struct task_struct *tsk,
 static inline void account_group_exec_runtime(struct task_struct *tsk,
                                               unsigned long long ns)
 {
-        struct task_cputime *times;
+        struct thread_group_cputimer *cputimer;
         struct signal_struct *sig;
 
         sig = tsk->signal;
@@ -361,9 +365,12 @@ static inline void account_group_exec_runtime(struct task_struct *tsk,
         if (unlikely(!sig))
                 return;
 
-        times = &sig->cputime.totals;
+        cputimer = &sig->cputimer;
+
+        if (!cputimer->running)
+                return;
 
-        spin_lock(&times->lock);
-        times->sum_exec_runtime += ns;
-        spin_unlock(&times->lock);
+        spin_lock(&cputimer->lock);
+        cputimer->cputime.sum_exec_runtime += ns;
+        spin_unlock(&cputimer->lock);
 }
diff --git a/kernel/signal.c b/kernel/signal.c
index b6b36768b758..2a74fe87c0dd 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1367,7 +1367,6 @@ int do_notify_parent(struct task_struct *tsk, int sig)
         struct siginfo info;
         unsigned long flags;
         struct sighand_struct *psig;
-        struct task_cputime cputime;
         int ret = sig;
 
         BUG_ON(sig == -1);
@@ -1397,9 +1396,10 @@ int do_notify_parent(struct task_struct *tsk, int sig)
         info.si_uid = __task_cred(tsk)->uid;
         rcu_read_unlock();
 
-        thread_group_cputime(tsk, &cputime);
-        info.si_utime = cputime_to_jiffies(cputime.utime);
-        info.si_stime = cputime_to_jiffies(cputime.stime);
+        info.si_utime = cputime_to_clock_t(cputime_add(tsk->utime,
+                                tsk->signal->utime));
+        info.si_stime = cputime_to_clock_t(cputime_add(tsk->stime,
+                                tsk->signal->stime));
 
         info.si_status = tsk->exit_code & 0x7f;
         if (tsk->exit_code & 0x80)
diff --git a/kernel/sys.c b/kernel/sys.c
index e7dc0e10a485..f145c415bc16 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1525,22 +1525,14 @@ SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim)
                 return -EINVAL;
         if (copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
                 return -EFAULT;
+        if (new_rlim.rlim_cur > new_rlim.rlim_max)
+                return -EINVAL;
         old_rlim = current->signal->rlim + resource;
         if ((new_rlim.rlim_max > old_rlim->rlim_max) &&
             !capable(CAP_SYS_RESOURCE))
                 return -EPERM;
-
-        if (resource == RLIMIT_NOFILE) {
-                if (new_rlim.rlim_max == RLIM_INFINITY)
-                        new_rlim.rlim_max = sysctl_nr_open;
-                if (new_rlim.rlim_cur == RLIM_INFINITY)
-                        new_rlim.rlim_cur = sysctl_nr_open;
-                if (new_rlim.rlim_max > sysctl_nr_open)
-                        return -EPERM;
-        }
-
-        if (new_rlim.rlim_cur > new_rlim.rlim_max)
-                return -EINVAL;
+        if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > sysctl_nr_open)
+                return -EPERM;
 
         retval = security_task_setrlimit(resource, &new_rlim);
         if (retval)
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 790f9d785663..c5ef44ff850f 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -101,6 +101,7 @@ static int two = 2;
 
 static int zero;
 static int one = 1;
+static unsigned long one_ul = 1;
 static int one_hundred = 100;
 
 /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
@@ -974,7 +975,7 @@ static struct ctl_table vm_table[] = {
                 .mode           = 0644,
                 .proc_handler   = &dirty_background_bytes_handler,
                 .strategy       = &sysctl_intvec,
-                .extra1         = &one,
+                .extra1         = &one_ul,
         },
         {
                 .ctl_name       = VM_DIRTY_RATIO,
@@ -995,7 +996,7 @@ static struct ctl_table vm_table[] = {
                 .mode           = 0644,
                 .proc_handler   = &dirty_bytes_handler,
                 .strategy       = &sysctl_intvec,
-                .extra1         = &one,
+                .extra1         = &one_ul,
         },
         {
                 .procname       = "dirty_writeback_centisecs",
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 7dcf6e9f2b04..9a236ffe2aa4 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1737,9 +1737,12 @@ static void clear_ftrace_pid(struct pid *pid)
 {
         struct task_struct *p;
 
+        rcu_read_lock();
         do_each_pid_task(pid, PIDTYPE_PID, p) {
                 clear_tsk_trace_trace(p);
         } while_each_pid_task(pid, PIDTYPE_PID, p);
+        rcu_read_unlock();
+
         put_pid(pid);
 }
 
@@ -1747,9 +1750,11 @@ static void set_ftrace_pid(struct pid *pid)
 {
         struct task_struct *p;
 
+        rcu_read_lock();
         do_each_pid_task(pid, PIDTYPE_PID, p) {
                 set_tsk_trace_trace(p);
         } while_each_pid_task(pid, PIDTYPE_PID, p);
+        rcu_read_unlock();
 }
 
 static void clear_ftrace_pid_task(struct pid **pid)
diff --git a/kernel/wait.c b/kernel/wait.c
index cd87131f2fc2..42a2dbc181c8 100644
--- a/kernel/wait.c
+++ b/kernel/wait.c
@@ -91,6 +91,15 @@ prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state)
 }
 EXPORT_SYMBOL(prepare_to_wait_exclusive);
 
+/*
+ * finish_wait - clean up after waiting in a queue
+ * @q: waitqueue waited on
+ * @wait: wait descriptor
+ *
+ * Sets current thread back to running state and removes
+ * the wait descriptor from the given waitqueue if still
+ * queued.
+ */
 void finish_wait(wait_queue_head_t *q, wait_queue_t *wait)
 {
         unsigned long flags;
@@ -117,6 +126,39 @@ void finish_wait(wait_queue_head_t *q, wait_queue_t *wait)
 }
 EXPORT_SYMBOL(finish_wait);
 
+/*
+ * abort_exclusive_wait - abort exclusive waiting in a queue
+ * @q: waitqueue waited on
+ * @wait: wait descriptor
+ * @state: runstate of the waiter to be woken
+ * @key: key to identify a wait bit queue or %NULL
+ *
+ * Sets current thread back to running state and removes
+ * the wait descriptor from the given waitqueue if still
+ * queued.
+ *
+ * Wakes up the next waiter if the caller is concurrently
+ * woken up through the queue.
+ *
+ * This prevents waiter starvation where an exclusive waiter
+ * aborts and is woken up concurrently and noone wakes up
+ * the next waiter.
+ */
+void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
+                        unsigned int mode, void *key)
+{
+        unsigned long flags;
+
+        __set_current_state(TASK_RUNNING);
+        spin_lock_irqsave(&q->lock, flags);
+        if (!list_empty(&wait->task_list))
+                list_del_init(&wait->task_list);
+        else if (waitqueue_active(q))
+                __wake_up_common(q, mode, 1, 0, key);
+        spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(abort_exclusive_wait);
+
 int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
 {
         int ret = default_wake_function(wait, mode, sync, key);
@@ -177,17 +219,20 @@ int __sched
 __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q,
                         int (*action)(void *), unsigned mode)
 {
-        int ret = 0;
-
         do {
+                int ret;
+
                 prepare_to_wait_exclusive(wq, &q->wait, mode);
-                if (test_bit(q->key.bit_nr, q->key.flags)) {
-                        if ((ret = (*action)(q->key.flags)))
-                                break;
-                }
+                if (!test_bit(q->key.bit_nr, q->key.flags))
+                        continue;
+                ret = action(q->key.flags);
+                if (!ret)
+                        continue;
+                abort_exclusive_wait(wq, &q->wait, mode, &q->key);
+                return ret;
         } while (test_and_set_bit(q->key.bit_nr, q->key.flags));
         finish_wait(wq, &q->wait);
-        return ret;
+        return 0;
 }
 EXPORT_SYMBOL(__wait_on_bit_lock);