10 files changed, 96 insertions, 62 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index d863b3c057bb..9efe7108ccaf 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7402,26 +7402,12 @@ static int __perf_cgroup_move(void *info)
         return 0;
 }
 
-static void perf_cgroup_move(struct task_struct *task)
+static void
+perf_cgroup_attach_task(struct cgroup *cgrp, struct task_struct *task)
 {
         task_function_call(task, __perf_cgroup_move, task);
 }
 
-static void perf_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
-                struct cgroup *old_cgrp, struct task_struct *task,
-                bool threadgroup)
-{
-        perf_cgroup_move(task);
-        if (threadgroup) {
-                struct task_struct *c;
-                rcu_read_lock();
-                list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
-                        perf_cgroup_move(c);
-                }
-                rcu_read_unlock();
-        }
-}
-
 static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
                 struct cgroup *old_cgrp, struct task_struct *task)
 {
@@ -7433,7 +7419,7 @@ static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
         if (!(task->flags & PF_EXITING))
                 return;
 
-        perf_cgroup_move(task);
+        perf_cgroup_attach_task(cgrp, task);
 }
 
 struct cgroup_subsys perf_subsys = {
@@ -7442,6 +7428,6 @@ struct cgroup_subsys perf_subsys = {
         .create         = perf_cgroup_create,
         .destroy        = perf_cgroup_destroy,
         .exit           = perf_cgroup_exit,
-        .attach         = perf_cgroup_attach,
+        .attach_task    = perf_cgroup_attach_task,
 };
 #endif /* CONFIG_CGROUP_PERF */
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 90cb55f6d7eb..470d08c82bbe 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -133,12 +133,6 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
                 switch (res) {
                 case IRQ_WAKE_THREAD:
                         /*
-                         * Set result to handled so the spurious check
-                         * does not trigger.
-                         */
-                        res = IRQ_HANDLED;
-
-                        /*
                          * Catch drivers which return WAKE_THREAD but
                          * did not set up a thread function
                          */
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 886e80347b32..4c60a50e66b2 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -257,13 +257,11 @@ int __init early_irq_init(void)
         count = ARRAY_SIZE(irq_desc);
 
         for (i = 0; i < count; i++) {
-                desc[i].irq_data.irq = i;
-                desc[i].irq_data.chip = &no_irq_chip;
                 desc[i].kstat_irqs = alloc_percpu(unsigned int);
-                irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS);
-                alloc_masks(desc + i, GFP_KERNEL, node);
-                desc_smp_init(desc + i, node);
+                alloc_masks(&desc[i], GFP_KERNEL, node);
+                raw_spin_lock_init(&desc[i].lock);
                 lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
+                desc_set_defaults(i, &desc[i], node);
         }
         return arch_early_irq_init();
 }
@@ -346,6 +344,12 @@ irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node)
         if (!cnt)
                 return -EINVAL;
 
+        if (irq >= 0) {
+                if (from > irq)
+                        return -EINVAL;
+                from = irq;
+        }
+
         mutex_lock(&sparse_irq_lock);
 
         start = bitmap_find_next_zero_area(allocated_irqs, IRQ_BITMAP_BITS,
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index f7ce0021e1c4..d64bafb1afd0 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -723,13 +723,16 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
  * context. So we need to disable bh here to avoid deadlocks and other
  * side effects.
  */
-static void
+static irqreturn_t
 irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
 {
+        irqreturn_t ret;
+
         local_bh_disable();
-        action->thread_fn(action->irq, action->dev_id);
+        ret = action->thread_fn(action->irq, action->dev_id);
         irq_finalize_oneshot(desc, action, false);
         local_bh_enable();
+        return ret;
 }
 
 /*
@@ -737,10 +740,14 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
  * preemtible - many of them need to sleep and wait for slow busses to
  * complete.
  */
-static void irq_thread_fn(struct irq_desc *desc, struct irqaction *action)
+static irqreturn_t irq_thread_fn(struct irq_desc *desc,
+                struct irqaction *action)
 {
-        action->thread_fn(action->irq, action->dev_id);
+        irqreturn_t ret;
+
+        ret = action->thread_fn(action->irq, action->dev_id);
         irq_finalize_oneshot(desc, action, false);
+        return ret;
 }
 
 /*
@@ -753,7 +760,8 @@ static int irq_thread(void *data)
         };
         struct irqaction *action = data;
         struct irq_desc *desc = irq_to_desc(action->irq);
-        void (*handler_fn)(struct irq_desc *desc, struct irqaction *action);
+        irqreturn_t (*handler_fn)(struct irq_desc *desc,
+                        struct irqaction *action);
         int wake;
 
         if (force_irqthreads & test_bit(IRQTF_FORCED_THREAD,
@@ -783,8 +791,12 @@ static int irq_thread(void *data)
                         desc->istate |= IRQS_PENDING;
                         raw_spin_unlock_irq(&desc->lock);
                 } else {
+                        irqreturn_t action_ret;
+
                         raw_spin_unlock_irq(&desc->lock);
-                        handler_fn(desc, action);
+                        action_ret = handler_fn(desc, action);
+                        if (!noirqdebug)
+                                note_interrupt(action->irq, desc, action_ret);
                 }
 
                 wake = atomic_dec_and_test(&desc->threads_active);
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index dfbd550401b2..aa57d5da18c1 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -167,6 +167,13 @@ out:
                   jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
 }
 
+static inline int bad_action_ret(irqreturn_t action_ret)
+{
+        if (likely(action_ret <= (IRQ_HANDLED | IRQ_WAKE_THREAD)))
+                return 0;
+        return 1;
+}
+
 /*
  * If 99,900 of the previous 100,000 interrupts have not been handled
  * then assume that the IRQ is stuck in some manner. Drop a diagnostic
@@ -182,7 +189,7 @@ __report_bad_irq(unsigned int irq, struct irq_desc *desc,
         struct irqaction *action;
         unsigned long flags;
 
-        if (action_ret != IRQ_HANDLED && action_ret != IRQ_NONE) {
+        if (bad_action_ret(action_ret)) {
                 printk(KERN_ERR "irq event %d: bogus return value %x\n",
                                 irq, action_ret);
         } else {
@@ -201,10 +208,11 @@ __report_bad_irq(unsigned int irq, struct irq_desc *desc,
         raw_spin_lock_irqsave(&desc->lock, flags);
         action = desc->action;
         while (action) {
-                printk(KERN_ERR "[<%p>]", action->handler);
-                print_symbol(" (%s)",
-                        (unsigned long)action->handler);
-                printk("\n");
+                printk(KERN_ERR "[<%p>] %pf", action->handler, action->handler);
+                if (action->thread_fn)
+                        printk(KERN_CONT " threaded [<%p>] %pf",
+                                        action->thread_fn, action->thread_fn);
+                printk(KERN_CONT "\n");
                 action = action->next;
         }
         raw_spin_unlock_irqrestore(&desc->lock, flags);
@@ -262,7 +270,16 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc,
         if (desc->istate & IRQS_POLL_INPROGRESS)
                 return;
 
-        if (unlikely(action_ret != IRQ_HANDLED)) {
+        /* we get here again via the threaded handler */
+        if (action_ret == IRQ_WAKE_THREAD)
+                return;
+
+        if (bad_action_ret(action_ret)) {
+                report_bad_irq(irq, desc, action_ret);
+                return;
+        }
+
+        if (unlikely(action_ret == IRQ_NONE)) {
                 /*
                  * If we are seeing only the odd spurious IRQ caused by
                  * bus asynchronicity then don't eventually trigger an error,
@@ -274,8 +291,6 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc,
                 else
                         desc->irqs_unhandled++;
                 desc->last_unhandled = jiffies;
-                if (unlikely(action_ret != IRQ_NONE))
-                        report_bad_irq(irq, desc, action_ret);
         }
 
         if (unlikely(try_misrouted_irq(irq, desc, action_ret))) {
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 63437d065ac8..298c9276dfdb 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -3426,7 +3426,7 @@ int lock_is_held(struct lockdep_map *lock)
         int ret = 0;
 
         if (unlikely(current->lockdep_recursion))
-                return ret;
+                return 1; /* avoid false negative lockdep_assert_held() */
 
         raw_local_irq_save(flags);
         check_flags(flags);
diff --git a/kernel/sched.c b/kernel/sched.c
index cbb3a0eee58e..3f2e502d609b 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -605,10 +605,10 @@ static inline int cpu_of(struct rq *rq)
 /*
  * Return the group to which this tasks belongs.
  *
- * We use task_subsys_state_check() and extend the RCU verification
- * with lockdep_is_held(&p->pi_lock) because cpu_cgroup_attach()
- * holds that lock for each task it moves into the cgroup. Therefore
- * by holding that lock, we pin the task to the current cgroup.
+ * We use task_subsys_state_check() and extend the RCU verification with
+ * pi->lock and rq->lock because cpu_cgroup_attach() holds those locks for each
+ * task it moves into the cgroup. Therefore by holding either of those locks,
+ * we pin the task to the current cgroup.
  */
 static inline struct task_group *task_group(struct task_struct *p)
 {
@@ -616,7 +616,8 @@ static inline struct task_group *task_group(struct task_struct *p)
         struct cgroup_subsys_state *css;
 
         css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
-                        lockdep_is_held(&p->pi_lock));
+                        lockdep_is_held(&p->pi_lock) ||
+                        lockdep_is_held(&task_rq(p)->lock));
         tg = container_of(css, struct task_group, css);
 
         return autogroup_task_group(p, tg);
@@ -2200,6 +2201,16 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
                         !(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE));
 
 #ifdef CONFIG_LOCKDEP
+        /*
+         * The caller should hold either p->pi_lock or rq->lock, when changing
+         * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks.
+         *
+         * sched_move_task() holds both and thus holding either pins the cgroup,
+         * see set_task_rq().
+         *
+         * Furthermore, all task_rq users should acquire both locks, see
+         * task_rq_lock().
+         */
         WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) ||
                                       lockdep_is_held(&task_rq(p)->lock)));
 #endif
@@ -2447,6 +2458,10 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
                 }
                 rcu_read_unlock();
         }
+
+        if (wake_flags & WF_MIGRATED)
+                schedstat_inc(p, se.statistics.nr_wakeups_migrate);
+
 #endif /* CONFIG_SMP */
 
         schedstat_inc(rq, ttwu_count);
@@ -2455,9 +2470,6 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
         if (wake_flags & WF_SYNC)
                 schedstat_inc(p, se.statistics.nr_wakeups_sync);
 
-        if (cpu != task_cpu(p))
-                schedstat_inc(p, se.statistics.nr_wakeups_migrate);
-
 #endif /* CONFIG_SCHEDSTATS */
 }
 
@@ -2600,6 +2612,7 @@ static void ttwu_queue(struct task_struct *p, int cpu)
 
 #if defined(CONFIG_SMP)
         if (sched_feat(TTWU_QUEUE) && cpu != smp_processor_id()) {
+                sched_clock_cpu(cpu); /* sync clocks x-cpu */
                 ttwu_queue_remote(p, cpu);
                 return;
         }
@@ -2674,8 +2687,10 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
                 p->sched_class->task_waking(p);
 
         cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
-        if (task_cpu(p) != cpu)
+        if (task_cpu(p) != cpu) {
+                wake_flags |= WF_MIGRATED;
                 set_task_cpu(p, cpu);
+        }
 #endif /* CONFIG_SMP */
 
         ttwu_queue(p, cpu);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4fc92445a29c..f175d98bd355 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -938,6 +938,12 @@ static struct ctl_table kern_table[] = {
         },
 #endif
 #ifdef CONFIG_PERF_EVENTS
+        /*
+         * User-space scripts rely on the existence of this file
+         * as a feature check for perf_events being enabled.
+         *
+         * So it's an ABI, do not remove!
+         */
         {
                 .procname       = "perf_event_paranoid",
                 .data           = &sysctl_perf_event_paranoid,
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index c027d4f602f1..e4c699dfa4e8 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -182,7 +182,10 @@ void clockevents_register_device(struct clock_event_device *dev)
         unsigned long flags;
 
         BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
-        BUG_ON(!dev->cpumask);
+        if (!dev->cpumask) {
+                WARN_ON(num_possible_cpus() > 1);
+                dev->cpumask = cpumask_of(smp_processor_id());
+        }
 
         raw_spin_lock_irqsave(&clockevents_lock, flags);
 
diff --git a/kernel/timer.c b/kernel/timer.c
index fd6198692b57..8cff36119e4d 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -749,16 +749,15 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires)
         unsigned long expires_limit, mask;
         int bit;
 
-        expires_limit = expires;
-
         if (timer->slack >= 0) {
                 expires_limit = expires + timer->slack;
         } else {
-                unsigned long now = jiffies;
+                long delta = expires - jiffies;
+
+                if (delta < 256)
+                        return expires;
 
-                /* No slack, if already expired else auto slack 0.4% */
-                if (time_after(expires, now))
-                        expires_limit = expires + (expires - now)/256;
+                expires_limit = expires + delta / 256;
         }
         mask = expires ^ expires_limit;
         if (mask == 0)
@@ -795,6 +794,8 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires)
  */
 int mod_timer(struct timer_list *timer, unsigned long expires)
 {
+        expires = apply_slack(timer, expires);
+
         /*
          * This is a common optimization triggered by the
          * networking code - if the timer is re-modified
@@ -803,8 +804,6 @@ int mod_timer(struct timer_list *timer, unsigned long expires)
         if (timer_pending(timer) && timer->expires == expires)
                 return 1;
 
-        expires = apply_slack(timer, expires);
-
         return __mod_timer(timer, expires, false, TIMER_NOT_PINNED);
 }
 EXPORT_SYMBOL(mod_timer);