10 files changed, 121 insertions, 81 deletions

diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 114e704760fe..bd7273e6282e 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -121,7 +121,9 @@ static void poll_all_shared_irqs(void)
                 if (!(status & IRQ_SPURIOUS_DISABLED))
                         continue;
 
+                local_irq_disable();
                 try_one_irq(i, desc);
+                local_irq_enable();
         }
 }
 
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 5fe709982caa..ab7ae57773e1 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -150,29 +150,6 @@ struct task_struct *kthread_create(int (*threadfn)(void *data),
 EXPORT_SYMBOL(kthread_create);
 
 /**
- * kthread_bind - bind a just-created kthread to a cpu.
- * @k: thread created by kthread_create().
- * @cpu: cpu (might not be online, must be possible) for @k to run on.
- *
- * Description: This function is equivalent to set_cpus_allowed(),
- * except that @cpu doesn't need to be online, and the thread must be
- * stopped (i.e., just returned from kthread_create()).
- */
-void kthread_bind(struct task_struct *k, unsigned int cpu)
-{
-        /* Must have done schedule() in kthread() before we set_task_cpu */
-        if (!wait_task_inactive(k, TASK_UNINTERRUPTIBLE)) {
-                WARN_ON(1);
-                return;
-        }
-        set_task_cpu(k, cpu);
-        k->cpus_allowed = cpumask_of_cpu(cpu);
-        k->rt.nr_cpus_allowed = 1;
-        k->flags |= PF_THREAD_BOUND;
-}
-EXPORT_SYMBOL(kthread_bind);
-
-/**
  * kthread_stop - stop a thread created by kthread_create().
  * @k: thread created by kthread_create().
  *
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 0536125b0497..f3077c0ab181 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -59,7 +59,7 @@
                 NUM_RCU_LVL_2, \
                 NUM_RCU_LVL_3, /* == MAX_RCU_LVLS */ \
         }, \
-        .signaled = RCU_SIGNAL_INIT, \
+        .signaled = RCU_GP_IDLE, \
         .gpnum = -300, \
         .completed = -300, \
         .onofflock = __SPIN_LOCK_UNLOCKED(&name.onofflock), \
@@ -657,14 +657,17 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
          * irqs disabled.
          */
         rcu_for_each_node_breadth_first(rsp, rnp) {
-                spin_lock(&rnp->lock);  /* irqs already disabled. */
+                spin_lock(&rnp->lock);          /* irqs already disabled. */
                 rcu_preempt_check_blocked_tasks(rnp);
                 rnp->qsmask = rnp->qsmaskinit;
                 rnp->gpnum = rsp->gpnum;
-                spin_unlock(&rnp->lock);        /* irqs already disabled. */
+                spin_unlock(&rnp->lock);        /* irqs remain disabled. */
         }
 
+        rnp = rcu_get_root(rsp);
+        spin_lock(&rnp->lock);                  /* irqs already disabled. */
         rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state now OK. */
+        spin_unlock(&rnp->lock);                /* irqs remain disabled. */
         spin_unlock_irqrestore(&rsp->onofflock, flags);
 }
 
@@ -706,6 +709,7 @@ static void cpu_quiet_msk_finish(struct rcu_state *rsp, unsigned long flags)
 {
         WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
         rsp->completed = rsp->gpnum;
+        rsp->signaled = RCU_GP_IDLE;
         rcu_process_gp_end(rsp, rsp->rda[smp_processor_id()]);
         rcu_start_gp(rsp, flags);  /* releases root node's rnp->lock. */
 }
@@ -1162,9 +1166,10 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
         }
         spin_unlock(&rnp->lock);
         switch (signaled) {
+        case RCU_GP_IDLE:
         case RCU_GP_INIT:
 
-                break; /* grace period still initializing, ignore. */
+                break; /* grace period idle or initializing, ignore. */
 
         case RCU_SAVE_DYNTICK:
 
@@ -1178,7 +1183,8 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
 
                 /* Update state, record completion counter. */
                 spin_lock(&rnp->lock);
-                if (lastcomp == rsp->completed) {
+                if (lastcomp == rsp->completed &&
+                    rsp->signaled == RCU_SAVE_DYNTICK) {
                         rsp->signaled = RCU_FORCE_QS;
                         dyntick_record_completed(rsp, lastcomp);
                 }
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 1823c6e20609..1899023b0962 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -201,9 +201,10 @@ struct rcu_data {
 };
 
 /* Values for signaled field in struct rcu_state. */
-#define RCU_GP_INIT             0       /* Grace period being initialized. */
-#define RCU_SAVE_DYNTICK        1       /* Need to scan dyntick state. */
-#define RCU_FORCE_QS            2       /* Need to force quiescent state. */
+#define RCU_GP_IDLE             0       /* No grace period in progress. */
+#define RCU_GP_INIT             1       /* Grace period being initialized. */
+#define RCU_SAVE_DYNTICK        2       /* Need to scan dyntick state. */
+#define RCU_FORCE_QS            3       /* Need to force quiescent state. */
 #ifdef CONFIG_NO_HZ
 #define RCU_SIGNAL_INIT         RCU_SAVE_DYNTICK
 #else /* #ifdef CONFIG_NO_HZ */
diff --git a/kernel/sched.c b/kernel/sched.c
index a455dca884a6..3c11ae0a948d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -309,6 +309,8 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq);
  */
 static DEFINE_SPINLOCK(task_group_lock);
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+
 #ifdef CONFIG_SMP
 static int root_task_group_empty(void)
 {
@@ -316,7 +318,6 @@ static int root_task_group_empty(void)
 }
 #endif
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
 #ifdef CONFIG_USER_SCHED
 # define INIT_TASK_GROUP_LOAD   (2*NICE_0_LOAD)
 #else /* !CONFIG_USER_SCHED */
@@ -1992,6 +1993,38 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
                 p->sched_class->prio_changed(rq, p, oldprio, running);
 }
 
+/**
+ * kthread_bind - bind a just-created kthread to a cpu.
+ * @p: thread created by kthread_create().
+ * @cpu: cpu (might not be online, must be possible) for @k to run on.
+ *
+ * Description: This function is equivalent to set_cpus_allowed(),
+ * except that @cpu doesn't need to be online, and the thread must be
+ * stopped (i.e., just returned from kthread_create()).
+ *
+ * Function lives here instead of kthread.c because it messes with
+ * scheduler internals which require locking.
+ */
+void kthread_bind(struct task_struct *p, unsigned int cpu)
+{
+        struct rq *rq = cpu_rq(cpu);
+        unsigned long flags;
+
+        /* Must have done schedule() in kthread() before we set_task_cpu */
+        if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) {
+                WARN_ON(1);
+                return;
+        }
+
+        spin_lock_irqsave(&rq->lock, flags);
+        set_task_cpu(p, cpu);
+        p->cpus_allowed = cpumask_of_cpu(cpu);
+        p->rt.nr_cpus_allowed = 1;
+        p->flags |= PF_THREAD_BOUND;
+        spin_unlock_irqrestore(&rq->lock, flags);
+}
+EXPORT_SYMBOL(kthread_bind);
+
 #ifdef CONFIG_SMP
 /*
  * Is this task likely cache-hot:
@@ -2004,7 +2037,7 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
         /*
          * Buddy candidates are cache hot:
          */
-        if (sched_feat(CACHE_HOT_BUDDY) &&
+        if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running &&
                         (&p->se == cfs_rq_of(&p->se)->next ||
                          &p->se == cfs_rq_of(&p->se)->last))
                 return 1;
@@ -9532,13 +9565,13 @@ void __init sched_init(void)
         current->sched_class = &fair_sched_class;
 
         /* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
-        alloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
+        zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
 #ifdef CONFIG_SMP
 #ifdef CONFIG_NO_HZ
-        alloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
+        zalloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
         alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT);
 #endif
-        alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
+        zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
 #endif /* SMP */
 
         perf_event_init();
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index c32c3e643daa..37087a7fac22 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -822,6 +822,26 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
                  * re-elected due to buddy favours.
                  */
                 clear_buddies(cfs_rq, curr);
+                return;
+        }
+
+        /*
+         * Ensure that a task that missed wakeup preemption by a
+         * narrow margin doesn't have to wait for a full slice.
+         * This also mitigates buddy induced latencies under load.
+         */
+        if (!sched_feat(WAKEUP_PREEMPT))
+                return;
+
+        if (delta_exec < sysctl_sched_min_granularity)
+                return;
+
+        if (cfs_rq->nr_running > 1) {
+                struct sched_entity *se = __pick_next_entity(cfs_rq);
+                s64 delta = curr->vruntime - se->vruntime;
+
+                if (delta > ideal_runtime)
+                        resched_task(rq_of(cfs_rq)->curr);
         }
 }
 
@@ -861,21 +881,18 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
 static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 {
         struct sched_entity *se = __pick_next_entity(cfs_rq);
-        struct sched_entity *buddy;
+        struct sched_entity *left = se;
 
-        if (cfs_rq->next) {
-                buddy = cfs_rq->next;
-                cfs_rq->next = NULL;
-                if (wakeup_preempt_entity(buddy, se) < 1)
-                        return buddy;
-        }
+        if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
+                se = cfs_rq->next;
 
-        if (cfs_rq->last) {
-                buddy = cfs_rq->last;
-                cfs_rq->last = NULL;
-                if (wakeup_preempt_entity(buddy, se) < 1)
-                        return buddy;
-        }
+        /*
+         * Prefer last buddy, try to return the CPU to a preempted task.
+         */
+        if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
+                se = cfs_rq->last;
+
+        clear_buddies(cfs_rq, se);
 
         return se;
 }
@@ -1577,6 +1594,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
         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;
 
         update_curr(cfs_rq);
 
@@ -1591,18 +1609,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
         if (unlikely(se == pse))
                 return;
 
-        /*
-         * Only set the backward buddy when the current task is still on the
-         * rq. This can happen when a wakeup gets interleaved with schedule on
-         * the ->pre_schedule() or idle_balance() point, either of which can
-         * drop the rq lock.
-         *
-         * Also, during early boot the idle thread is in the fair class, for
-         * obvious reasons its a bad idea to schedule back to the idle thread.
-         */
-        if (sched_feat(LAST_BUDDY) && likely(se->on_rq && curr != rq->idle))
-                set_last_buddy(se);
-        if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK))
+        if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK))
                 set_next_buddy(pse);
 
         /*
@@ -1648,8 +1655,22 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 
         BUG_ON(!pse);
 
-        if (wakeup_preempt_entity(se, pse) == 1)
+        if (wakeup_preempt_entity(se, pse) == 1) {
                 resched_task(curr);
+                /*
+                 * Only set the backward buddy when the current task is still
+                 * on the rq. This can happen when a wakeup gets interleaved
+                 * with schedule on the ->pre_schedule() or idle_balance()
+                 * point, either of which can * drop the rq lock.
+                 *
+                 * Also, during early boot the idle thread is in the fair class,
+                 * for obvious reasons its a bad idea to schedule back to it.
+                 */
+                if (unlikely(!se->on_rq || curr == rq->idle))
+                        return;
+                if (sched_feat(LAST_BUDDY) && scale && entity_is_task(se))
+                        set_last_buddy(se);
+        }
 }
 
 static struct task_struct *pick_next_task_fair(struct rq *rq)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 9c451a1930b6..6dc4e5ef7a01 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2222,15 +2222,15 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
                 ret = ftrace_process_regex(parser->buffer,
                                            parser->idx, enable);
                 if (ret)
-                        goto out;
+                        goto out_unlock;
 
                 trace_parser_clear(parser);
         }
 
         ret = read;
-
+out_unlock:
         mutex_unlock(&ftrace_regex_lock);
-out:
+
         return ret;
 }
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 3ffa502fb243..5dd017fea6f5 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1193,6 +1193,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
         atomic_inc(&cpu_buffer->record_disabled);
         synchronize_sched();
 
+        spin_lock_irq(&cpu_buffer->reader_lock);
         rb_head_page_deactivate(cpu_buffer);
 
         for (i = 0; i < nr_pages; i++) {
@@ -1207,6 +1208,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
                 return;
 
         rb_reset_cpu(cpu_buffer);
+        spin_unlock_irq(&cpu_buffer->reader_lock);
 
         rb_check_pages(cpu_buffer);
 
diff --git a/kernel/user.c b/kernel/user.c
index 2c000e7132ac..46d0165ca70c 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -330,9 +330,9 @@ done:
  */
 static void free_user(struct user_struct *up, unsigned long flags)
 {
-        spin_unlock_irqrestore(&uidhash_lock, flags);
         INIT_DELAYED_WORK(&up->work, cleanup_user_struct);
         schedule_delayed_work(&up->work, msecs_to_jiffies(1000));
+        spin_unlock_irqrestore(&uidhash_lock, flags);
 }
 
 #else   /* CONFIG_USER_SCHED && CONFIG_SYSFS */
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 12328147132c..67e526b6ae81 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -692,31 +692,29 @@ int schedule_on_each_cpu(work_func_t func)
         if (!works)
                 return -ENOMEM;
 
+        get_online_cpus();
+
         /*
-         * when running in keventd don't schedule a work item on itself.
-         * Can just call directly because the work queue is already bound.
-         * This also is faster.
-         * Make this a generic parameter for other workqueues?
+         * When running in keventd don't schedule a work item on
+         * itself.  Can just call directly because the work queue is
+         * already bound.  This also is faster.
          */
-        if (current_is_keventd()) {
+        if (current_is_keventd())
                 orig = raw_smp_processor_id();
-                INIT_WORK(per_cpu_ptr(works, orig), func);
-                func(per_cpu_ptr(works, orig));
-        }
 
-        get_online_cpus();
         for_each_online_cpu(cpu) {
                 struct work_struct *work = per_cpu_ptr(works, cpu);
 
-                if (cpu == orig)
-                        continue;
                 INIT_WORK(work, func);
-                schedule_work_on(cpu, work);
-        }
-        for_each_online_cpu(cpu) {
                 if (cpu != orig)
-                        flush_work(per_cpu_ptr(works, cpu));
+                        schedule_work_on(cpu, work);
         }
+        if (orig >= 0)
+                func(per_cpu_ptr(works, orig));
+
+        for_each_online_cpu(cpu)
+                flush_work(per_cpu_ptr(works, cpu));
+
         put_online_cpus();
         free_percpu(works);
         return 0;