Merge branch 'x86/urgent' into x86/xen

Conflicts:
	arch/frv/include/asm/pgtable.h
	arch/x86/include/asm/required-features.h
	arch/x86/xen/mmu.c

Merge reason: x86/xen was on a .29 base still, move it to a fresher
              branch and pick up Xen fixes as well, plus resolve
              conflicts

Signed-off-by: Ingo Molnar <mingo@elte.hu>

kernel/Makefile

@@ -74,6 +74,7 @@ obj-$(CONFIG_AUDIT_TREE) += audit_tree.o
 obj-$(CONFIG_KPROBES) += kprobes.o
 obj-$(CONFIG_KGDB) += kgdb.o
 obj-$(CONFIG_DETECT_SOFTLOCKUP) += softlockup.o
+obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
 obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
 obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o

kernel/audit_tree.c

@@ -734,9 +734,6 @@ int audit_tag_tree(char *old, char *new)
 	dentry = dget(path.dentry);
 	path_put(&path);
 
-	if (dentry == tagged->mnt_root && dentry == mnt->mnt_root)
-		follow_up(&mnt, &dentry);
-
 	list_add_tail(&list, &tagged->mnt_list);
 
 	mutex_lock(&audit_filter_mutex);

kernel/exit.c

@@ -923,6 +923,8 @@ NORET_TYPE void do_exit(long code)
 		schedule();
 	}
 
+	exit_irq_thread();
+
 	exit_signals(tsk);  /* sets PF_EXITING */
 	/*
 	 * tsk->flags are checked in the futex code to protect against

kernel/fork.c

@@ -645,6 +645,9 @@ static int copy_mm(unsigned long clone_flags, struct task_struct * tsk)
 
 	tsk->min_flt = tsk->maj_flt = 0;
 	tsk->nvcsw = tsk->nivcsw = 0;
+#ifdef CONFIG_DETECT_HUNG_TASK
+	tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw;
+#endif
 
 	tsk->mm = NULL;
 	tsk->active_mm = NULL;
@@ -797,6 +800,12 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig)
 	sig->cputime_expires.virt_exp = cputime_zero;
 	sig->cputime_expires.sched_exp = 0;
 
+	if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
+		sig->cputime_expires.prof_exp =
+			secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur);
+		sig->cputimer.running = 1;
+	}
+
 	/* The timer lists. */
 	INIT_LIST_HEAD(&sig->cpu_timers[0]);
 	INIT_LIST_HEAD(&sig->cpu_timers[1]);
@@ -812,11 +821,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 		atomic_inc(&current->signal->live);
 		return 0;
 	}
+
 	sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL);
-
-	if (sig)
-		posix_cpu_timers_init_group(sig);
-
 	tsk->signal = sig;
 	if (!sig)
 		return -ENOMEM;
@@ -856,6 +862,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim);
 	task_unlock(current->group_leader);
 
+	posix_cpu_timers_init_group(sig);
+
 	acct_init_pacct(&sig->pacct);
 
 	tty_audit_fork(sig);
@@ -1032,11 +1040,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	p->default_timer_slack_ns = current->timer_slack_ns;
 
-#ifdef CONFIG_DETECT_SOFTLOCKUP
-	p->last_switch_count = 0;
-	p->last_switch_timestamp = 0;
-#endif
-
 	task_io_accounting_init(&p->ioac);
 	acct_clear_integrals(p);
 

kernel/futex.c

@@ -883,7 +883,12 @@ retry_private:
 out_unlock:
 	double_unlock_hb(hb1, hb2);
 
-	/* drop_futex_key_refs() must be called outside the spinlocks. */
+	/*
+	 * drop_futex_key_refs() must be called outside the spinlocks. During
+	 * the requeue we moved futex_q's from the hash bucket at key1 to the
+	 * one at key2 and updated their key pointer.  We no longer need to
+	 * hold the references to key1.
+	 */
 	while (--drop_count >= 0)
 		drop_futex_key_refs(&key1);
 

kernel/hung_task.c

@@ -0,0 +1,217 @@
+/*
+ * Detect Hung Task
+ *
+ * kernel/hung_task.c - kernel thread for detecting tasks stuck in D state
+ *
+ */
+
+#include <linux/mm.h>
+#include <linux/cpu.h>
+#include <linux/nmi.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/freezer.h>
+#include <linux/kthread.h>
+#include <linux/lockdep.h>
+#include <linux/module.h>
+#include <linux/sysctl.h>
+
+/*
+ * The number of tasks checked:
+ */
+unsigned long __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT;
+
+/*
+ * Limit number of tasks checked in a batch.
+ *
+ * This value controls the preemptibility of khungtaskd since preemption
+ * is disabled during the critical section. It also controls the size of
+ * the RCU grace period. So it needs to be upper-bound.
+ */
+#define HUNG_TASK_BATCHING 1024
+
+/*
+ * Zero means infinite timeout - no checking done:
+ */
+unsigned long __read_mostly sysctl_hung_task_timeout_secs = 120;
+
+unsigned long __read_mostly sysctl_hung_task_warnings = 10;
+
+static int __read_mostly did_panic;
+
+static struct task_struct *watchdog_task;
+
+/*
+ * Should we panic (and reboot, if panic_timeout= is set) when a
+ * hung task is detected:
+ */
+unsigned int __read_mostly sysctl_hung_task_panic =
+				CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE;
+
+static int __init hung_task_panic_setup(char *str)
+{
+	sysctl_hung_task_panic = simple_strtoul(str, NULL, 0);
+
+	return 1;
+}
+__setup("hung_task_panic=", hung_task_panic_setup);
+
+static int
+hung_task_panic(struct notifier_block *this, unsigned long event, void *ptr)
+{
+	did_panic = 1;
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block panic_block = {
+	.notifier_call = hung_task_panic,
+};
+
+static void check_hung_task(struct task_struct *t, unsigned long timeout)
+{
+	unsigned long switch_count = t->nvcsw + t->nivcsw;
+
+	/*
+	 * Ensure the task is not frozen.
+	 * Also, when a freshly created task is scheduled once, changes
+	 * its state to TASK_UNINTERRUPTIBLE without having ever been
+	 * switched out once, it musn't be checked.
+	 */
+	if (unlikely(t->flags & PF_FROZEN || !switch_count))
+		return;
+
+	if (switch_count != t->last_switch_count) {
+		t->last_switch_count = switch_count;
+		return;
+	}
+	if (!sysctl_hung_task_warnings)
+		return;
+	sysctl_hung_task_warnings--;
+
+	/*
+	 * Ok, the task did not get scheduled for more than 2 minutes,
+	 * complain:
+	 */
+	printk(KERN_ERR "INFO: task %s:%d blocked for more than "
+			"%ld seconds.\n", t->comm, t->pid, timeout);
+	printk(KERN_ERR "\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\""
+			" disables this message.\n");
+	sched_show_task(t);
+	__debug_show_held_locks(t);
+
+	touch_nmi_watchdog();
+
+	if (sysctl_hung_task_panic)
+		panic("hung_task: blocked tasks");
+}
+
+/*
+ * To avoid extending the RCU grace period for an unbounded amount of time,
+ * periodically exit the critical section and enter a new one.
+ *
+ * For preemptible RCU it is sufficient to call rcu_read_unlock in order
+ * exit the grace period. For classic RCU, a reschedule is required.
+ */
+static void rcu_lock_break(struct task_struct *g, struct task_struct *t)
+{
+	get_task_struct(g);
+	get_task_struct(t);
+	rcu_read_unlock();
+	cond_resched();
+	rcu_read_lock();
+	put_task_struct(t);
+	put_task_struct(g);
+}
+
+/*
+ * Check whether a TASK_UNINTERRUPTIBLE does not get woken up for
+ * a really long time (120 seconds). If that happens, print out
+ * a warning.
+ */
+static void check_hung_uninterruptible_tasks(unsigned long timeout)
+{
+	int max_count = sysctl_hung_task_check_count;
+	int batch_count = HUNG_TASK_BATCHING;
+	struct task_struct *g, *t;
+
+	/*
+	 * If the system crashed already then all bets are off,
+	 * do not report extra hung tasks:
+	 */
+	if (test_taint(TAINT_DIE) || did_panic)
+		return;
+
+	rcu_read_lock();
+	do_each_thread(g, t) {
+		if (!--max_count)
+			goto unlock;
+		if (!--batch_count) {
+			batch_count = HUNG_TASK_BATCHING;
+			rcu_lock_break(g, t);
+			/* Exit if t or g was unhashed during refresh. */
+			if (t->state == TASK_DEAD || g->state == TASK_DEAD)
+				goto unlock;
+		}
+		/* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */
+		if (t->state == TASK_UNINTERRUPTIBLE)
+			check_hung_task(t, timeout);
+	} while_each_thread(g, t);
+ unlock:
+	rcu_read_unlock();
+}
+
+static unsigned long timeout_jiffies(unsigned long timeout)
+{
+	/* timeout of 0 will disable the watchdog */
+	return timeout ? timeout * HZ : MAX_SCHEDULE_TIMEOUT;
+}
+
+/*
+ * Process updating of timeout sysctl
+ */
+int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
+				  struct file *filp, void __user *buffer,
+				  size_t *lenp, loff_t *ppos)
+{
+	int ret;
+
+	ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos);
+
+	if (ret || !write)
+		goto out;
+
+	wake_up_process(watchdog_task);
+
+ out:
+	return ret;
+}
+
+/*
+ * kthread which checks for tasks stuck in D state
+ */
+static int watchdog(void *dummy)
+{
+	set_user_nice(current, 0);
+
+	for ( ; ; ) {
+		unsigned long timeout = sysctl_hung_task_timeout_secs;
+
+		while (schedule_timeout_interruptible(timeout_jiffies(timeout)))
+			timeout = sysctl_hung_task_timeout_secs;
+
+		check_hung_uninterruptible_tasks(timeout);
+	}
+
+	return 0;
+}
+
+static int __init hung_task_init(void)
+{
+	atomic_notifier_chain_register(&panic_notifier_list, &panic_block);
+	watchdog_task = kthread_run(watchdog, NULL, "khungtaskd");
+
+	return 0;
+}
+
+module_init(hung_task_init);

kernel/irq/devres.c

@@ -26,10 +26,12 @@ static int devm_irq_match(struct device *dev, void *res, void *data)
 }
 
 /**
- *	devm_request_irq - allocate an interrupt line for a managed device
+ *	devm_request_threaded_irq - allocate an interrupt line for a managed device
  *	@dev: device to request interrupt for
  *	@irq: Interrupt line to allocate
  *	@handler: Function to be called when the IRQ occurs
+ *	@thread_fn: function to be called in a threaded interrupt context. NULL
+ *		    for devices which handle everything in @handler
  *	@irqflags: Interrupt type flags
  *	@devname: An ascii name for the claiming device
  *	@dev_id: A cookie passed back to the handler function
@@ -42,9 +44,10 @@ static int devm_irq_match(struct device *dev, void *res, void *data)
  *	If an IRQ allocated with this function needs to be freed
  *	separately, dev_free_irq() must be used.
  */
-int devm_request_irq(struct device *dev, unsigned int irq,
-		     irq_handler_t handler, unsigned long irqflags,
-		     const char *devname, void *dev_id)
+int devm_request_threaded_irq(struct device *dev, unsigned int irq,
+			      irq_handler_t handler, irq_handler_t thread_fn,
+			      unsigned long irqflags, const char *devname,
+			      void *dev_id)
 {
 	struct irq_devres *dr;
 	int rc;
@@ -54,7 +57,8 @@ int devm_request_irq(struct device *dev, unsigned int irq,
 	if (!dr)
 		return -ENOMEM;
 
-	rc = request_irq(irq, handler, irqflags, devname, dev_id);
+	rc = request_threaded_irq(irq, handler, thread_fn, irqflags, devname,
+				  dev_id);
 	if (rc) {
 		devres_free(dr);
 		return rc;
@@ -66,7 +70,7 @@ int devm_request_irq(struct device *dev, unsigned int irq,
 
 	return 0;
 }
-EXPORT_SYMBOL(devm_request_irq);
+EXPORT_SYMBOL(devm_request_threaded_irq);
 
 /**
  *	devm_free_irq - free an interrupt

kernel/irq/handle.c

@@ -339,6 +339,15 @@ irqreturn_t no_action(int cpl, void *dev_id)
 	return IRQ_NONE;
 }
 
+static void warn_no_thread(unsigned int irq, struct irqaction *action)
+{
+	if (test_and_set_bit(IRQTF_WARNED, &action->thread_flags))
+		return;
+
+	printk(KERN_WARNING "IRQ %d device %s returned IRQ_WAKE_THREAD "
+	       "but no thread function available.", irq, action->name);
+}
+
 DEFINE_TRACE(irq_handler_entry);
 DEFINE_TRACE(irq_handler_exit);
 
@@ -354,8 +363,6 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
 	irqreturn_t ret, retval = IRQ_NONE;
 	unsigned int status = 0;
 
-	WARN_ONCE(!in_irq(), "BUG: IRQ handler called from non-hardirq context!");
-
 	if (!(action->flags & IRQF_DISABLED))
 		local_irq_enable_in_hardirq();
 
@@ -363,8 +370,47 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
 		trace_irq_handler_entry(irq, action);
 		ret = action->handler(irq, action->dev_id);
 		trace_irq_handler_exit(irq, action, ret);
-		if (ret == IRQ_HANDLED)
+
+		switch (ret) {
+		case IRQ_WAKE_THREAD:
+			/*
+			 * Set result to handled so the spurious check
+			 * does not trigger.
+			 */
+			ret = IRQ_HANDLED;
+
+			/*
+			 * Catch drivers which return WAKE_THREAD but
+			 * did not set up a thread function
+			 */
+			if (unlikely(!action->thread_fn)) {
+				warn_no_thread(irq, action);
+				break;
+			}
+
+			/*
+			 * Wake up the handler thread for this
+			 * action. In case the thread crashed and was
+			 * killed we just pretend that we handled the
+			 * interrupt. The hardirq handler above has
+			 * disabled the device interrupt, so no irq
+			 * storm is lurking.
+			 */
+			if (likely(!test_bit(IRQTF_DIED,
+					     &action->thread_flags))) {
+				set_bit(IRQTF_RUNTHREAD, &action->thread_flags);
+				wake_up_process(action->thread);
+			}
+
+			/* Fall through to add to randomness */
+		case IRQ_HANDLED:
 			status |= action->flags;
+			break;
+
+		default:
+			break;
+		}
+
 		retval |= ret;
 		action = action->next;
 	} while (action);

kernel/irq/manage.c

@@ -8,16 +8,15 @@
  */
 
 #include <linux/irq.h>
+#include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/interrupt.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
 
 #include "internals.h"
 
-#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
-cpumask_var_t irq_default_affinity;
-
 /**
  *	synchronize_irq - wait for pending IRQ handlers (on other CPUs)
  *	@irq: interrupt number to wait for
@@ -53,9 +52,18 @@ void synchronize_irq(unsigned int irq)
 
 		/* Oops, that failed? */
 	} while (status & IRQ_INPROGRESS);
+
+	/*
+	 * We made sure that no hardirq handler is running. Now verify
+	 * that no threaded handlers are active.
+	 */
+	wait_event(desc->wait_for_threads, !atomic_read(&desc->threads_active));
 }
 EXPORT_SYMBOL(synchronize_irq);
 
+#ifdef CONFIG_SMP
+cpumask_var_t irq_default_affinity;
+
 /**
  *	irq_can_set_affinity - Check if the affinity of a given irq can be set
  *	@irq:		Interrupt to check
@@ -72,6 +80,18 @@ int irq_can_set_affinity(unsigned int irq)
 	return 1;
 }
 
+static void
+irq_set_thread_affinity(struct irq_desc *desc, const struct cpumask *cpumask)
+{
+	struct irqaction *action = desc->action;
+
+	while (action) {
+		if (action->thread)
+			set_cpus_allowed_ptr(action->thread, cpumask);
+		action = action->next;
+	}
+}
+
 /**
  *	irq_set_affinity - Set the irq affinity of a given irq
  *	@irq:		Interrupt to set affinity
@@ -89,10 +109,9 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 	spin_lock_irqsave(&desc->lock, flags);
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
-	if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) {
-		cpumask_copy(desc->affinity, cpumask);
+	if (desc->status & IRQ_MOVE_PCNTXT)
 		desc->chip->set_affinity(irq, cpumask);
-	} else {
+	else {
 		desc->status |= IRQ_MOVE_PENDING;
 		cpumask_copy(desc->pending_mask, cpumask);
 	}
@@ -100,6 +119,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 	cpumask_copy(desc->affinity, cpumask);
 	desc->chip->set_affinity(irq, cpumask);
 #endif
+	irq_set_thread_affinity(desc, cpumask);
 	desc->status |= IRQ_AFFINITY_SET;
 	spin_unlock_irqrestore(&desc->lock, flags);
 	return 0;
@@ -150,6 +170,8 @@ int irq_select_affinity_usr(unsigned int irq)
 
 	spin_lock_irqsave(&desc->lock, flags);
 	ret = setup_affinity(irq, desc);
+	if (!ret)
+		irq_set_thread_affinity(desc, desc->affinity);
 	spin_unlock_irqrestore(&desc->lock, flags);
 
 	return ret;
@@ -401,6 +423,90 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 	return ret;
 }
 
+static int irq_wait_for_interrupt(struct irqaction *action)
+{
+	while (!kthread_should_stop()) {
+		set_current_state(TASK_INTERRUPTIBLE);
+
+		if (test_and_clear_bit(IRQTF_RUNTHREAD,
+				       &action->thread_flags)) {
+			__set_current_state(TASK_RUNNING);
+			return 0;
+		}
+		schedule();
+	}
+	return -1;
+}
+
+/*
+ * Interrupt handler thread
+ */
+static int irq_thread(void *data)
+{
+	struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO/2, };
+	struct irqaction *action = data;
+	struct irq_desc *desc = irq_to_desc(action->irq);
+	int wake;
+
+	sched_setscheduler(current, SCHED_FIFO, &param);
+	current->irqaction = action;
+
+	while (!irq_wait_for_interrupt(action)) {
+
+		atomic_inc(&desc->threads_active);
+
+		spin_lock_irq(&desc->lock);
+		if (unlikely(desc->status & IRQ_DISABLED)) {
+			/*
+			 * CHECKME: We might need a dedicated
+			 * IRQ_THREAD_PENDING flag here, which
+			 * retriggers the thread in check_irq_resend()
+			 * but AFAICT IRQ_PENDING should be fine as it
+			 * retriggers the interrupt itself --- tglx
+			 */
+			desc->status |= IRQ_PENDING;
+			spin_unlock_irq(&desc->lock);
+		} else {
+			spin_unlock_irq(&desc->lock);
+
+			action->thread_fn(action->irq, action->dev_id);
+		}
+
+		wake = atomic_dec_and_test(&desc->threads_active);
+
+		if (wake && waitqueue_active(&desc->wait_for_threads))
+			wake_up(&desc->wait_for_threads);
+	}
+
+	/*
+	 * Clear irqaction. Otherwise exit_irq_thread() would make
+	 * fuzz about an active irq thread going into nirvana.
+	 */
+	current->irqaction = NULL;
+	return 0;
+}
+
+/*
+ * Called from do_exit()
+ */
+void exit_irq_thread(void)
+{
+	struct task_struct *tsk = current;
+
+	if (!tsk->irqaction)
+		return;
+
+	printk(KERN_ERR
+	       "exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n",
+	       tsk->comm ? tsk->comm : "", tsk->pid, tsk->irqaction->irq);
+
+	/*
+	 * Set the THREAD DIED flag to prevent further wakeups of the
+	 * soon to be gone threaded handler.
+	 */
+	set_bit(IRQTF_DIED, &tsk->irqaction->flags);
+}
+
 /*
  * Internal function to register an irqaction - typically used to
  * allocate special interrupts that are part of the architecture.
@@ -436,6 +542,26 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		rand_initialize_irq(irq);
 	}
 
+	/*
+	 * Threaded handler ?
+	 */
+	if (new->thread_fn) {
+		struct task_struct *t;
+
+		t = kthread_create(irq_thread, new, "irq/%d-%s", irq,
+				   new->name);
+		if (IS_ERR(t))
+			return PTR_ERR(t);
+		/*
+		 * We keep the reference to the task struct even if
+		 * the thread dies to avoid that the interrupt code
+		 * references an already freed task_struct.
+		 */
+		get_task_struct(t);
+		new->thread = t;
+		wake_up_process(t);
+	}
+
 	/*
 	 * The following block of code has to be executed atomically
 	 */
@@ -473,15 +599,15 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	if (!shared) {
 		irq_chip_set_defaults(desc->chip);
 
+		init_waitqueue_head(&desc->wait_for_threads);
+
 		/* Setup the type (level, edge polarity) if configured: */
 		if (new->flags & IRQF_TRIGGER_MASK) {
 			ret = __irq_set_trigger(desc, irq,
 					new->flags & IRQF_TRIGGER_MASK);
 
-			if (ret) {
-				spin_unlock_irqrestore(&desc->lock, flags);
-				return ret;
-			}
+			if (ret)
+				goto out_thread;
 		} else
 			compat_irq_chip_set_default_handler(desc);
 #if defined(CONFIG_IRQ_PER_CPU)
@@ -549,8 +675,19 @@ mismatch:
 		dump_stack();
 	}
 #endif
+	ret = -EBUSY;
+
+out_thread:
 	spin_unlock_irqrestore(&desc->lock, flags);
-	return -EBUSY;
+	if (new->thread) {
+		struct task_struct *t = new->thread;
+
+		new->thread = NULL;
+		if (likely(!test_bit(IRQTF_DIED, &new->thread_flags)))
+			kthread_stop(t);
+		put_task_struct(t);
+	}
+	return ret;
 }
 
 /**
@@ -576,6 +713,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irqaction *action, **action_ptr;
+	struct task_struct *irqthread;
 	unsigned long flags;
 
 	WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
@@ -622,6 +760,10 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 		else
 			desc->chip->disable(irq);
 	}
+
+	irqthread = action->thread;
+	action->thread = NULL;
+
 	spin_unlock_irqrestore(&desc->lock, flags);
 
 	unregister_handler_proc(irq, action);
@@ -629,6 +771,12 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 	/* Make sure it's not being used on another CPU: */
 	synchronize_irq(irq);
 
+	if (irqthread) {
+		if (!test_bit(IRQTF_DIED, &action->thread_flags))
+			kthread_stop(irqthread);
+		put_task_struct(irqthread);
+	}
+
 #ifdef CONFIG_DEBUG_SHIRQ
 	/*
 	 * It's a shared IRQ -- the driver ought to be prepared for an IRQ
@@ -681,9 +829,12 @@ void free_irq(unsigned int irq, void *dev_id)
 EXPORT_SYMBOL(free_irq);
 
 /**
- *	request_irq - allocate an interrupt line
+ *	request_threaded_irq - allocate an interrupt line
  *	@irq: Interrupt line to allocate
- *	@handler: Function to be called when the IRQ occurs
+ *	@handler: Function to be called when the IRQ occurs.
+ *		  Primary handler for threaded interrupts
+ *	@thread_fn: Function called from the irq handler thread
+ *		    If NULL, no irq thread is created
  *	@irqflags: Interrupt type flags
  *	@devname: An ascii name for the claiming device
  *	@dev_id: A cookie passed back to the handler function
@@ -695,6 +846,15 @@ EXPORT_SYMBOL(free_irq);
  *	raises, you must take care both to initialise your hardware
  *	and to set up the interrupt handler in the right order.
  *
+ *	If you want to set up a threaded irq handler for your device
+ *	then you need to supply @handler and @thread_fn. @handler ist
+ *	still called in hard interrupt context and has to check
+ *	whether the interrupt originates from the device. If yes it
+ *	needs to disable the interrupt on the device and return
+ *	IRQ_THREAD_WAKE which will wake up the handler thread and run
+ *	@thread_fn. This split handler design is necessary to support
+ *	shared interrupts.
+ *
  *	Dev_id must be globally unique. Normally the address of the
  *	device data structure is used as the cookie. Since the handler
  *	receives this value it makes sense to use it.
@@ -710,8 +870,9 @@ EXPORT_SYMBOL(free_irq);
  *	IRQF_TRIGGER_*		Specify active edge(s) or level
  *
  */
-int request_irq(unsigned int irq, irq_handler_t handler,
-		unsigned long irqflags, const char *devname, void *dev_id)
+int request_threaded_irq(unsigned int irq, irq_handler_t handler,
+			 irq_handler_t thread_fn, unsigned long irqflags,
+			 const char *devname, void *dev_id)
 {
 	struct irqaction *action;
 	struct irq_desc *desc;
@@ -759,6 +920,7 @@ int request_irq(unsigned int irq, irq_handler_t handler,
 		return -ENOMEM;
 
 	action->handler = handler;
+	action->thread_fn = thread_fn;
 	action->flags = irqflags;
 	action->name = devname;
 	action->dev_id = dev_id;
@@ -788,4 +950,4 @@ int request_irq(unsigned int irq, irq_handler_t handler,
 #endif
 	return retval;
 }
-EXPORT_SYMBOL(request_irq);
+EXPORT_SYMBOL(request_threaded_irq);

kernel/irq/numa_migrate.c

@@ -54,6 +54,7 @@ static bool init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
 static void free_one_irq_desc(struct irq_desc *old_desc, struct irq_desc *desc)
 {
 	free_kstat_irqs(old_desc, desc);
+	free_desc_masks(old_desc, desc);
 	arch_free_chip_data(old_desc, desc);
 }
 

kernel/kthread.c

@@ -76,6 +76,7 @@ static int kthread(void *_create)
 
 	/* OK, tell user we're spawned, wait for stop or wakeup */
 	__set_current_state(TASK_UNINTERRUPTIBLE);
+	create->result = current;
 	complete(&create->started);
 	schedule();
 
@@ -96,22 +97,10 @@ static void create_kthread(struct kthread_create_info *create)
 
 	/* We want our own signal handler (we take no signals by default). */
 	pid = kernel_thread(kthread, create, CLONE_FS | CLONE_FILES | SIGCHLD);
-	if (pid < 0) {
+	if (pid < 0)
 		create->result = ERR_PTR(pid);
-	} else {
-		struct sched_param param = { .sched_priority = 0 };
+	else
 		wait_for_completion(&create->started);
-		read_lock(&tasklist_lock);
-		create->result = find_task_by_pid_ns(pid, &init_pid_ns);
-		read_unlock(&tasklist_lock);
-		/*
-		 * root may have changed our (kthreadd's) priority or CPU mask.
-		 * The kernel thread should not inherit these properties.
-		 */
-		sched_setscheduler(create->result, SCHED_NORMAL, &param);
-		set_user_nice(create->result, KTHREAD_NICE_LEVEL);
-		set_cpus_allowed_ptr(create->result, cpu_all_mask);
-	}
 	complete(&create->done);
 }
 
@@ -154,11 +143,20 @@ struct task_struct *kthread_create(int (*threadfn)(void *data),
 	wait_for_completion(&create.done);
 
 	if (!IS_ERR(create.result)) {
+		struct sched_param param = { .sched_priority = 0 };
 		va_list args;
+
 		va_start(args, namefmt);
 		vsnprintf(create.result->comm, sizeof(create.result->comm),
 			  namefmt, args);
 		va_end(args);
+		/*
+		 * root may have changed our (kthreadd's) priority or CPU mask.
+		 * The kernel thread should not inherit these properties.
+		 */
+		sched_setscheduler_nocheck(create.result, SCHED_NORMAL, &param);
+		set_user_nice(create.result, KTHREAD_NICE_LEVEL);
+		set_cpus_allowed_ptr(create.result, cpu_all_mask);
 	}
 	return create.result;
 }

kernel/lockdep.c

@@ -2490,13 +2490,20 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 void lockdep_init_map(struct lockdep_map *lock, const char *name,
 		      struct lock_class_key *key, int subclass)
 {
-	if (unlikely(!debug_locks))
+	lock->class_cache = NULL;
+#ifdef CONFIG_LOCK_STAT
+	lock->cpu = raw_smp_processor_id();
+#endif
+
+	if (DEBUG_LOCKS_WARN_ON(!name)) {
+		lock->name = "NULL";
 		return;
+	}
+
+	lock->name = name;
 
 	if (DEBUG_LOCKS_WARN_ON(!key))
 		return;
-	if (DEBUG_LOCKS_WARN_ON(!name))
-		return;
 	/*
 	 * Sanity check, the lock-class key must be persistent:
 	 */
@@ -2505,12 +2512,11 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name,
 		DEBUG_LOCKS_WARN_ON(1);
 		return;
 	}
-	lock->name = name;
 	lock->key = key;
-	lock->class_cache = NULL;
-#ifdef CONFIG_LOCK_STAT
-	lock->cpu = raw_smp_processor_id();
-#endif
+
+	if (unlikely(!debug_locks))
+		return;
+
 	if (subclass)
 		register_lock_class(lock, subclass, 1);
 }

kernel/module.c

@@ -2388,6 +2388,9 @@ SYSCALL_DEFINE3(init_module, void __user *, umod,
 	blocking_notifier_call_chain(&module_notify_list,
 				     MODULE_STATE_LIVE, mod);
 
+	/* We need to finish all async code before the module init sequence is done */
+	async_synchronize_full();
+
 	mutex_lock(&module_mutex);
 	/* Drop initial reference. */
 	module_put(mod);

kernel/mutex.c

@@ -148,7 +148,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 
 	preempt_disable();
 	mutex_acquire(&lock->dep_map, subclass, 0, ip);
-#if defined(CONFIG_SMP) && !defined(CONFIG_DEBUG_MUTEXES)
+#if defined(CONFIG_SMP) && !defined(CONFIG_DEBUG_MUTEXES) && \
+    !defined(CONFIG_HAVE_DEFAULT_NO_SPIN_MUTEXES)
 	/*
 	 * Optimistic spinning.
 	 *

kernel/panic.c

@@ -213,8 +213,16 @@ unsigned long get_taint(void)
 
 void add_taint(unsigned flag)
 {
-	/* can't trust the integrity of the kernel anymore: */
-	debug_locks = 0;
+	/*
+	 * Can't trust the integrity of the kernel anymore.
+	 * We don't call directly debug_locks_off() because the issue
+	 * is not necessarily serious enough to set oops_in_progress to 1
+	 * Also we want to keep up lockdep for staging development and
+	 * post-warning case.
+	 */
+	if (flag != TAINT_CRAP && flag != TAINT_WARN && __debug_locks_off())
+		printk(KERN_WARNING "Disabling lock debugging due to kernel taint\n");
+
 	set_bit(flag, &tainted_mask);
 }
 EXPORT_SYMBOL(add_taint);

kernel/posix-cpu-timers.c

@@ -18,7 +18,7 @@ void update_rlimit_cpu(unsigned long rlim_new)
 
 	cputime = secs_to_cputime(rlim_new);
 	if (cputime_eq(current->signal->it_prof_expires, cputime_zero) ||
-	    cputime_lt(current->signal->it_prof_expires, cputime)) {
+	    cputime_gt(current->signal->it_prof_expires, cputime)) {
 		spin_lock_irq(&current->sighand->siglock);
 		set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
 		spin_unlock_irq(&current->sighand->siglock);
@@ -224,7 +224,7 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
 		cpu->cpu = virt_ticks(p);
 		break;
 	case CPUCLOCK_SCHED:
-		cpu->sched = p->se.sum_exec_runtime + task_delta_exec(p);
+		cpu->sched = task_sched_runtime(p);
 		break;
 	}
 	return 0;
@@ -305,18 +305,19 @@ static int cpu_clock_sample_group(const clockid_t which_clock,
 {
 	struct task_cputime cputime;
 
-	thread_group_cputime(p, &cputime);
 	switch (CPUCLOCK_WHICH(which_clock)) {
 	default:
 		return -EINVAL;
 	case CPUCLOCK_PROF:
+		thread_group_cputime(p, &cputime);
 		cpu->cpu = cputime_add(cputime.utime, cputime.stime);
 		break;
 	case CPUCLOCK_VIRT:
+		thread_group_cputime(p, &cputime);
 		cpu->cpu = cputime.utime;
 		break;
 	case CPUCLOCK_SCHED:
-		cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p);
+		cpu->sched = thread_group_sched_runtime(p);
 		break;
 	}
 	return 0;
@@ -1419,19 +1420,19 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 	 * timer call will interfere.
 	 */
 	list_for_each_entry_safe(timer, next, &firing, it.cpu.entry) {
-		int firing;
+		int cpu_firing;
+
 		spin_lock(&timer->it_lock);
 		list_del_init(&timer->it.cpu.entry);
-		firing = timer->it.cpu.firing;
+		cpu_firing = timer->it.cpu.firing;
 		timer->it.cpu.firing = 0;
 		/*
 		 * The firing flag is -1 if we collided with a reset
 		 * of the timer, which already reported this
 		 * almost-firing as an overrun.  So don't generate an event.
 		 */
-		if (likely(firing >= 0)) {
+		if (likely(cpu_firing >= 0))
 			cpu_timer_fire(timer);
-		}
 		spin_unlock(&timer->it_lock);
 	}
 }

kernel/power/disk.c

@@ -22,6 +22,7 @@
 #include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/freezer.h>
+#include <scsi/scsi_scan.h>
 #include <asm/suspend.h>
 
 #include "power.h"
@@ -655,32 +656,42 @@ static int software_resume(void)
 	 * here to avoid lockdep complaining.
 	 */
 	mutex_lock_nested(&pm_mutex, SINGLE_DEPTH_NESTING);
+
+	if (swsusp_resume_device)
+		goto Check_image;
+
+	if (!strlen(resume_file)) {
+		error = -ENOENT;
+		goto Unlock;
+	}
+
+	pr_debug("PM: Checking image partition %s\n", resume_file);
+
+	/* Check if the device is there */
+	swsusp_resume_device = name_to_dev_t(resume_file);
 	if (!swsusp_resume_device) {
-		if (!strlen(resume_file)) {
-			mutex_unlock(&pm_mutex);
-			return -ENOENT;
-		}
 		/*
 		 * Some device discovery might still be in progress; we need
 		 * to wait for this to finish.
 		 */
 		wait_for_device_probe();
+		/*
+		 * We can't depend on SCSI devices being available after loading
+		 * one of their modules until scsi_complete_async_scans() is
+		 * called and the resume device usually is a SCSI one.
+		 */
+		scsi_complete_async_scans();
+
 		swsusp_resume_device = name_to_dev_t(resume_file);
-		pr_debug("PM: Resume from partition %s\n", resume_file);
-	} else {
-		pr_debug("PM: Resume from partition %d:%d\n",
-				MAJOR(swsusp_resume_device),
-				MINOR(swsusp_resume_device));
+		if (!swsusp_resume_device) {
+			error = -ENODEV;
+			goto Unlock;
+		}
 	}
 
-	if (noresume) {
-		/**
-		 * FIXME: If noresume is specified, we need to find the
-		 * partition and reset it back to normal swap space.
-		 */
-		mutex_unlock(&pm_mutex);
-		return 0;
-	}
+ Check_image:
+	pr_debug("PM: Resume from partition %d:%d\n",
+		MAJOR(swsusp_resume_device), MINOR(swsusp_resume_device));
 
 	pr_debug("PM: Checking hibernation image.\n");
 	error = swsusp_check();

kernel/power/main.c

@@ -291,20 +291,26 @@ static int suspend_enter(suspend_state_t state)
 
 	device_pm_lock();
 
+	if (suspend_ops->prepare) {
+		error = suspend_ops->prepare();
+		if (error)
+			goto Done;
+	}
+
 	error = device_power_down(PMSG_SUSPEND);
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down\n");
-		goto Done;
+		goto Platfrom_finish;
 	}
 
-	if (suspend_ops->prepare) {
-		error = suspend_ops->prepare();
+	if (suspend_ops->prepare_late) {
+		error = suspend_ops->prepare_late();
 		if (error)
 			goto Power_up_devices;
 	}
 
 	if (suspend_test(TEST_PLATFORM))
-		goto Platfrom_finish;
+		goto Platform_wake;
 
 	error = disable_nonboot_cpus();
 	if (error || suspend_test(TEST_CPUS))
@@ -326,13 +332,17 @@ static int suspend_enter(suspend_state_t state)
  Enable_cpus:
 	enable_nonboot_cpus();
 
- Platfrom_finish:
-	if (suspend_ops->finish)
-		suspend_ops->finish();
+ Platform_wake:
+	if (suspend_ops->wake)
+		suspend_ops->wake();
 
  Power_up_devices:
 	device_power_up(PMSG_RESUME);
 
+ Platfrom_finish:
+	if (suspend_ops->finish)
+		suspend_ops->finish();
+
  Done:
 	device_pm_unlock();
 

kernel/power/swap.c

@@ -64,8 +64,6 @@ static int submit(int rw, pgoff_t page_off, struct page *page,
 	struct bio *bio;
 
 	bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1);
-	if (!bio)
-		return -ENOMEM;
 	bio->bi_sector = page_off * (PAGE_SIZE >> 9);
 	bio->bi_bdev = resume_bdev;
 	bio->bi_end_io = end_swap_bio_read;

kernel/power/user.c

@@ -24,6 +24,7 @@
 #include <linux/cpu.h>
 #include <linux/freezer.h>
 #include <linux/smp_lock.h>
+#include <scsi/scsi_scan.h>
 
 #include <asm/uaccess.h>
 
@@ -92,6 +93,7 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 	filp->private_data = data;
 	memset(&data->handle, 0, sizeof(struct snapshot_handle));
 	if ((filp->f_flags & O_ACCMODE) == O_RDONLY) {
+		/* Hibernating.  The image device should be accessible. */
 		data->swap = swsusp_resume_device ?
 			swap_type_of(swsusp_resume_device, 0, NULL) : -1;
 		data->mode = O_RDONLY;
@@ -99,6 +101,13 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 		if (error)
 			pm_notifier_call_chain(PM_POST_HIBERNATION);
 	} else {
+		/*
+		 * Resuming.  We may need to wait for the image device to
+		 * appear.
+		 */
+		wait_for_device_probe();
+		scsi_complete_async_scans();
+
 		data->swap = -1;
 		data->mode = O_WRONLY;
 		error = pm_notifier_call_chain(PM_RESTORE_PREPARE);

kernel/ptrace.c

@@ -21,9 +21,7 @@
 #include <linux/audit.h>
 #include <linux/pid_namespace.h>
 #include <linux/syscalls.h>
-
-#include <asm/pgtable.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 
 /*
@@ -48,7 +46,7 @@ void __ptrace_link(struct task_struct *child, struct task_struct *new_parent)
 	list_add(&child->ptrace_entry, &new_parent->ptraced);
 	child->parent = new_parent;
 }
- 
+
 /*
  * Turn a tracing stop into a normal stop now, since with no tracer there
  * would be no way to wake it up with SIGCONT or SIGKILL.  If there was a
@@ -173,7 +171,7 @@ bool ptrace_may_access(struct task_struct *task, unsigned int mode)
 	task_lock(task);
 	err = __ptrace_may_access(task, mode);
 	task_unlock(task);
-	return (!err ? true : false);
+	return !err;
 }
 
 int ptrace_attach(struct task_struct *task)
@@ -190,7 +188,7 @@ int ptrace_attach(struct task_struct *task)
 	/* Protect exec's credential calculations against our interference;
 	 * SUID, SGID and LSM creds get determined differently under ptrace.
 	 */
-	retval = mutex_lock_interruptible(&current->cred_exec_mutex);
+	retval = mutex_lock_interruptible(&task->cred_exec_mutex);
 	if (retval  < 0)
 		goto out;
 
@@ -234,7 +232,7 @@ repeat:
 bad:
 	write_unlock_irqrestore(&tasklist_lock, flags);
 	task_unlock(task);
-	mutex_unlock(&current->cred_exec_mutex);
+	mutex_unlock(&task->cred_exec_mutex);
 out:
 	return retval;
 }
@@ -358,7 +356,7 @@ int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst
 		copied += retval;
 		src += retval;
 		dst += retval;
-		len -= retval;			
+		len -= retval;
 	}
 	return copied;
 }
@@ -383,7 +381,7 @@ int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long ds
 		copied += retval;
 		src += retval;
 		dst += retval;
-		len -= retval;			
+		len -= retval;
 	}
 	return copied;
 }
@@ -496,9 +494,9 @@ static int ptrace_resume(struct task_struct *child, long request, long data)
 		if (unlikely(!arch_has_single_step()))
 			return -EIO;
 		user_enable_single_step(child);
-	}
-	else
+	} else {
 		user_disable_single_step(child);
+	}
 
 	child->exit_code = data;
 	wake_up_process(child);
@@ -606,10 +604,11 @@ repeat:
 		ret = security_ptrace_traceme(current->parent);
 
 		/*
-		 * Set the ptrace bit in the process ptrace flags.
-		 * Then link us on our parent's ptraced list.
+		 * Check PF_EXITING to ensure ->real_parent has not passed
+		 * exit_ptrace(). Otherwise we don't report the error but
+		 * pretend ->real_parent untraces us right after return.
 		 */
-		if (!ret) {
+		if (!ret && !(current->real_parent->flags & PF_EXITING)) {
 			current->ptrace |= PT_PTRACED;
 			__ptrace_link(current, current->real_parent);
 		}

kernel/rcupdate.c

@@ -58,6 +58,10 @@ static DEFINE_MUTEX(rcu_barrier_mutex);
 static struct completion rcu_barrier_completion;
 int rcu_scheduler_active __read_mostly;
 
+static atomic_t rcu_migrate_type_count = ATOMIC_INIT(0);
+static struct rcu_head rcu_migrate_head[3];
+static DECLARE_WAIT_QUEUE_HEAD(rcu_migrate_wq);
+
 /*
  * Awaken the corresponding synchronize_rcu() instance now that a
  * grace period has elapsed.
@@ -122,7 +126,10 @@ static void rcu_barrier_func(void *type)
 	}
 }
 
-static inline void wait_migrated_callbacks(void);
+static inline void wait_migrated_callbacks(void)
+{
+	wait_event(rcu_migrate_wq, !atomic_read(&rcu_migrate_type_count));
+}
 
 /*
  * Orchestrate the specified type of RCU barrier, waiting for all
@@ -179,21 +186,12 @@ void rcu_barrier_sched(void)
 }
 EXPORT_SYMBOL_GPL(rcu_barrier_sched);
 
-static atomic_t rcu_migrate_type_count = ATOMIC_INIT(0);
-static struct rcu_head rcu_migrate_head[3];
-static DECLARE_WAIT_QUEUE_HEAD(rcu_migrate_wq);
-
 static void rcu_migrate_callback(struct rcu_head *notused)
 {
 	if (atomic_dec_and_test(&rcu_migrate_type_count))
 		wake_up(&rcu_migrate_wq);
 }
 
-static inline void wait_migrated_callbacks(void)
-{
-	wait_event(rcu_migrate_wq, !atomic_read(&rcu_migrate_type_count));
-}
-
 static int __cpuinit rcu_barrier_cpu_hotplug(struct notifier_block *self,
 		unsigned long action, void *hcpu)
 {

kernel/rcutree.c

@@ -530,8 +530,6 @@ static void note_new_gpnum(struct rcu_state *rsp, struct rcu_data *rdp)
 	rdp->qs_pending = 1;
 	rdp->passed_quiesc = 0;
 	rdp->gpnum = rsp->gpnum;
-	rdp->n_rcu_pending_force_qs = rdp->n_rcu_pending +
-				      RCU_JIFFIES_TILL_FORCE_QS;
 }
 
 /*
@@ -578,8 +576,6 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 	rsp->gpnum++;
 	rsp->signaled = RCU_GP_INIT; /* Hold off force_quiescent_state. */
 	rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS;
-	rdp->n_rcu_pending_force_qs = rdp->n_rcu_pending +
-				      RCU_JIFFIES_TILL_FORCE_QS;
 	record_gp_stall_check_time(rsp);
 	dyntick_record_completed(rsp, rsp->completed - 1);
 	note_new_gpnum(rsp, rdp);
@@ -1055,7 +1051,6 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
 {
 	unsigned long flags;
 	long lastcomp;
-	struct rcu_data *rdp = rsp->rda[smp_processor_id()];
 	struct rcu_node *rnp = rcu_get_root(rsp);
 	u8 signaled;
 
@@ -1066,16 +1061,13 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
 		return;	/* Someone else is already on the job. */
 	}
 	if (relaxed &&
-	    (long)(rsp->jiffies_force_qs - jiffies) >= 0 &&
-	    (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) >= 0)
+	    (long)(rsp->jiffies_force_qs - jiffies) >= 0)
 		goto unlock_ret; /* no emergency and done recently. */
 	rsp->n_force_qs++;
 	spin_lock(&rnp->lock);
 	lastcomp = rsp->completed;
 	signaled = rsp->signaled;
 	rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS;
-	rdp->n_rcu_pending_force_qs = rdp->n_rcu_pending +
-				      RCU_JIFFIES_TILL_FORCE_QS;
 	if (lastcomp == rsp->gpnum) {
 		rsp->n_force_qs_ngp++;
 		spin_unlock(&rnp->lock);
@@ -1144,8 +1136,7 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
 	 * If an RCU GP has gone long enough, go check for dyntick
 	 * idle CPUs and, if needed, send resched IPIs.
 	 */
-	if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0 ||
-	    (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) < 0)
+	if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0)
 		force_quiescent_state(rsp, 1);
 
 	/*
@@ -1230,8 +1221,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 	if (unlikely(++rdp->qlen > qhimark)) {
 		rdp->blimit = LONG_MAX;
 		force_quiescent_state(rsp, 0);
-	} else if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0 ||
-		   (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) < 0)
+	} else if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0)
 		force_quiescent_state(rsp, 1);
 	local_irq_restore(flags);
 }
@@ -1290,8 +1280,7 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 
 	/* Has an RCU GP gone long enough to send resched IPIs &c? */
 	if (ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum) &&
-	    ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0 ||
-	     (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) < 0))
+	    ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0))
 		return 1;
 
 	/* nothing to do */

kernel/rcutree_trace.c

@@ -49,14 +49,12 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 {
 	if (!rdp->beenonline)
 		return;
-	seq_printf(m, "%3d%cc=%ld g=%ld pq=%d pqc=%ld qp=%d rpfq=%ld rp=%x",
+	seq_printf(m, "%3d%cc=%ld g=%ld pq=%d pqc=%ld qp=%d",
 		   rdp->cpu,
 		   cpu_is_offline(rdp->cpu) ? '!' : ' ',
 		   rdp->completed, rdp->gpnum,
 		   rdp->passed_quiesc, rdp->passed_quiesc_completed,
-		   rdp->qs_pending,
-		   rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending,
-		   (int)(rdp->n_rcu_pending & 0xffff));
+		   rdp->qs_pending);
 #ifdef CONFIG_NO_HZ
 	seq_printf(m, " dt=%d/%d dn=%d df=%lu",
 		   rdp->dynticks->dynticks,
@@ -102,14 +100,12 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp)
 {
 	if (!rdp->beenonline)
 		return;
-	seq_printf(m, "%d,%s,%ld,%ld,%d,%ld,%d,%ld,%ld",
+	seq_printf(m, "%d,%s,%ld,%ld,%d,%ld,%d",
 		   rdp->cpu,
 		   cpu_is_offline(rdp->cpu) ? "\"Y\"" : "\"N\"",
 		   rdp->completed, rdp->gpnum,
 		   rdp->passed_quiesc, rdp->passed_quiesc_completed,
-		   rdp->qs_pending,
-		   rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending,
-		   rdp->n_rcu_pending);
+		   rdp->qs_pending);
 #ifdef CONFIG_NO_HZ
 	seq_printf(m, ",%d,%d,%d,%lu",
 		   rdp->dynticks->dynticks,
@@ -123,7 +119,7 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp)
 
 static int show_rcudata_csv(struct seq_file *m, void *unused)
 {
-	seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pqc\",\"pq\",\"rpfq\",\"rp\",");
+	seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pqc\",\"pq\",");
 #ifdef CONFIG_NO_HZ
 	seq_puts(m, "\"dt\",\"dt nesting\",\"dn\",\"df\",");
 #endif /* #ifdef CONFIG_NO_HZ */

kernel/resource.c

@@ -533,43 +533,21 @@ static void __init __reserve_region_with_split(struct resource *root,
 	res->end = end;
 	res->flags = IORESOURCE_BUSY;
 
-	for (;;) {
-		conflict = __request_resource(parent, res);
-		if (!conflict)
-			break;
-		if (conflict != parent) {
-			parent = conflict;
-			if (!(conflict->flags & IORESOURCE_BUSY))
-				continue;
-		}
+	conflict = __request_resource(parent, res);
+	if (!conflict)
+		return;
 
-		/* Uhhuh, that didn't work out.. */
-		kfree(res);
-		res = NULL;
-		break;
-	}
+	/* failed, split and try again */
+	kfree(res);
 
-	if (!res) {
-		/* failed, split and try again */
-
-		/* conflict covered whole area */
-		if (conflict->start <= start && conflict->end >= end)
-			return;
-
-		if (conflict->start > start)
-			__reserve_region_with_split(root, start, conflict->start-1, name);
-		if (!(conflict->flags & IORESOURCE_BUSY)) {
-			resource_size_t common_start, common_end;
-
-			common_start = max(conflict->start, start);
-			common_end = min(conflict->end, end);
-			if (common_start < common_end)
-				__reserve_region_with_split(root, common_start, common_end, name);
-		}
-		if (conflict->end < end)
-			__reserve_region_with_split(root, conflict->end+1, end, name);
-	}
+	/* conflict covered whole area */
+	if (conflict->start <= start && conflict->end >= end)
+		return;
 
+	if (conflict->start > start)
+		__reserve_region_with_split(root, start, conflict->start-1, name);
+	if (conflict->end < end)
+		__reserve_region_with_split(root, conflict->end+1, end, name);
 }
 
 void __init reserve_region_with_split(struct resource *root,

kernel/sched.c

@@ -1418,10 +1418,22 @@ iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		   struct rq_iterator *iterator);
 #endif
 
+/* Time spent by the tasks of the cpu accounting group executing in ... */
+enum cpuacct_stat_index {
+	CPUACCT_STAT_USER,	/* ... user mode */
+	CPUACCT_STAT_SYSTEM,	/* ... kernel mode */
+
+	CPUACCT_STAT_NSTATS,
+};
+
 #ifdef CONFIG_CGROUP_CPUACCT
 static void cpuacct_charge(struct task_struct *tsk, u64 cputime);
+static void cpuacct_update_stats(struct task_struct *tsk,
+		enum cpuacct_stat_index idx, cputime_t val);
 #else
 static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
+static inline void cpuacct_update_stats(struct task_struct *tsk,
+		enum cpuacct_stat_index idx, cputime_t val) {}
 #endif
 
 static inline void inc_cpu_load(struct rq *rq, unsigned long load)
@@ -4511,9 +4523,25 @@ DEFINE_PER_CPU(struct kernel_stat, kstat);
 EXPORT_PER_CPU_SYMBOL(kstat);
 
 /*
- * Return any ns on the sched_clock that have not yet been banked in
+ * Return any ns on the sched_clock that have not yet been accounted in
  * @p in case that task is currently running.
+ *
+ * Called with task_rq_lock() held on @rq.
  */
+static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq)
+{
+	u64 ns = 0;
+
+	if (task_current(rq, p)) {
+		update_rq_clock(rq);
+		ns = rq->clock - p->se.exec_start;
+		if ((s64)ns < 0)
+			ns = 0;
+	}
+
+	return ns;
+}
+
 unsigned long long task_delta_exec(struct task_struct *p)
 {
 	unsigned long flags;
@@ -4521,16 +4549,49 @@ unsigned long long task_delta_exec(struct task_struct *p)
 	u64 ns = 0;
 
 	rq = task_rq_lock(p, &flags);
+	ns = do_task_delta_exec(p, rq);
+	task_rq_unlock(rq, &flags);
 
-	if (task_current(rq, p)) {
-		u64 delta_exec;
+	return ns;
+}
 
-		update_rq_clock(rq);
-		delta_exec = rq->clock - p->se.exec_start;
-		if ((s64)delta_exec > 0)
-			ns = delta_exec;
-	}
+/*
+ * Return accounted runtime for the task.
+ * In case the task is currently running, return the runtime plus current's
+ * pending runtime that have not been accounted yet.
+ */
+unsigned long long task_sched_runtime(struct task_struct *p)
+{
+	unsigned long flags;
+	struct rq *rq;
+	u64 ns = 0;
 
+	rq = task_rq_lock(p, &flags);
+	ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq);
+	task_rq_unlock(rq, &flags);
+
+	return ns;
+}
+
+/*
+ * Return sum_exec_runtime for the thread group.
+ * In case the task is currently running, return the sum plus current's
+ * pending runtime that have not been accounted yet.
+ *
+ * Note that the thread group might have other running tasks as well,
+ * so the return value not includes other pending runtime that other
+ * running tasks might have.
+ */
+unsigned long long thread_group_sched_runtime(struct task_struct *p)
+{
+	struct task_cputime totals;
+	unsigned long flags;
+	struct rq *rq;
+	u64 ns;
+
+	rq = task_rq_lock(p, &flags);
+	thread_group_cputime(p, &totals);
+	ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq);
 	task_rq_unlock(rq, &flags);
 
 	return ns;
@@ -4559,6 +4620,8 @@ void account_user_time(struct task_struct *p, cputime_t cputime,
 		cpustat->nice = cputime64_add(cpustat->nice, tmp);
 	else
 		cpustat->user = cputime64_add(cpustat->user, tmp);
+
+	cpuacct_update_stats(p, CPUACCT_STAT_USER, cputime);
 	/* Account for user time used */
 	acct_update_integrals(p);
 }
@@ -4620,6 +4683,8 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
 	else
 		cpustat->system = cputime64_add(cpustat->system, tmp);
 
+	cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime);
+
 	/* Account for system time used */
 	acct_update_integrals(p);
 }
@@ -4667,7 +4732,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
 
 	if (user_tick)
 		account_user_time(p, one_jiffy, one_jiffy_scaled);
-	else if (p != rq->idle)
+	else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
 		account_system_time(p, HARDIRQ_OFFSET, one_jiffy,
 				    one_jiffy_scaled);
 	else
@@ -4781,7 +4846,7 @@ void scheduler_tick(void)
 #endif
 }
 
-unsigned long get_parent_ip(unsigned long addr)
+notrace unsigned long get_parent_ip(unsigned long addr)
 {
 	if (in_lock_functions(addr)) {
 		addr = CALLER_ADDR2;
@@ -7302,7 +7367,12 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 		cpumask_or(groupmask, groupmask, sched_group_cpus(group));
 
 		cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
+
 		printk(KERN_CONT " %s", str);
+		if (group->__cpu_power != SCHED_LOAD_SCALE) {
+			printk(KERN_CONT " (__cpu_power = %d)",
+				group->__cpu_power);
+		}
 
 		group = group->next;
 	} while (group != sd->groups);
@@ -9925,6 +9995,7 @@ struct cpuacct {
 	struct cgroup_subsys_state css;
 	/* cpuusage holds pointer to a u64-type object on every cpu */
 	u64 *cpuusage;
+	struct percpu_counter cpustat[CPUACCT_STAT_NSTATS];
 	struct cpuacct *parent;
 };
 
@@ -9949,20 +10020,32 @@ static struct cgroup_subsys_state *cpuacct_create(
 	struct cgroup_subsys *ss, struct cgroup *cgrp)
 {
 	struct cpuacct *ca = kzalloc(sizeof(*ca), GFP_KERNEL);
+	int i;
 
 	if (!ca)
-		return ERR_PTR(-ENOMEM);
+		goto out;
 
 	ca->cpuusage = alloc_percpu(u64);
-	if (!ca->cpuusage) {
-		kfree(ca);
-		return ERR_PTR(-ENOMEM);
-	}
+	if (!ca->cpuusage)
+		goto out_free_ca;
+
+	for (i = 0; i < CPUACCT_STAT_NSTATS; i++)
+		if (percpu_counter_init(&ca->cpustat[i], 0))
+			goto out_free_counters;
 
 	if (cgrp->parent)
 		ca->parent = cgroup_ca(cgrp->parent);
 
 	return &ca->css;
+
+out_free_counters:
+	while (--i >= 0)
+		percpu_counter_destroy(&ca->cpustat[i]);
+	free_percpu(ca->cpuusage);
+out_free_ca:
+	kfree(ca);
+out:
+	return ERR_PTR(-ENOMEM);
 }
 
 /* destroy an existing cpu accounting group */
@@ -9970,7 +10053,10 @@ static void
 cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
 {
 	struct cpuacct *ca = cgroup_ca(cgrp);
+	int i;
 
+	for (i = 0; i < CPUACCT_STAT_NSTATS; i++)
+		percpu_counter_destroy(&ca->cpustat[i]);
 	free_percpu(ca->cpuusage);
 	kfree(ca);
 }
@@ -10057,6 +10143,25 @@ static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft,
 	return 0;
 }
 
+static const char *cpuacct_stat_desc[] = {
+	[CPUACCT_STAT_USER] = "user",
+	[CPUACCT_STAT_SYSTEM] = "system",
+};
+
+static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft,
+		struct cgroup_map_cb *cb)
+{
+	struct cpuacct *ca = cgroup_ca(cgrp);
+	int i;
+
+	for (i = 0; i < CPUACCT_STAT_NSTATS; i++) {
+		s64 val = percpu_counter_read(&ca->cpustat[i]);
+		val = cputime64_to_clock_t(val);
+		cb->fill(cb, cpuacct_stat_desc[i], val);
+	}
+	return 0;
+}
+
 static struct cftype files[] = {
 	{
 		.name = "usage",
@@ -10067,7 +10172,10 @@ static struct cftype files[] = {
 		.name = "usage_percpu",
 		.read_seq_string = cpuacct_percpu_seq_read,
 	},
-
+	{
+		.name = "stat",
+		.read_map = cpuacct_stats_show,
+	},
 };
 
 static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
@@ -10089,12 +10197,38 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 		return;
 
 	cpu = task_cpu(tsk);
+
+	rcu_read_lock();
+
 	ca = task_ca(tsk);
 
 	for (; ca; ca = ca->parent) {
 		u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
 		*cpuusage += cputime;
 	}
+
+	rcu_read_unlock();
+}
+
+/*
+ * Charge the system/user time to the task's accounting group.
+ */
+static void cpuacct_update_stats(struct task_struct *tsk,
+		enum cpuacct_stat_index idx, cputime_t val)
+{
+	struct cpuacct *ca;
+
+	if (unlikely(!cpuacct_subsys.active))
+		return;
+
+	rcu_read_lock();
+	ca = task_ca(tsk);
+
+	do {
+		percpu_counter_add(&ca->cpustat[idx], val);
+		ca = ca->parent;
+	} while (ca);
+	rcu_read_unlock();
 }
 
 struct cgroup_subsys cpuacct_subsys = {

kernel/sched_cpupri.c

@@ -55,7 +55,7 @@ static int convert_prio(int prio)
  * cpupri_find - find the best (lowest-pri) CPU in the system
  * @cp: The cpupri context
  * @p: The task
- * @lowest_mask: A mask to fill in with selected CPUs
+ * @lowest_mask: A mask to fill in with selected CPUs (or NULL)
  *
  * Note: This function returns the recommended CPUs as calculated during the
  * current invokation.  By the time the call returns, the CPUs may have in
@@ -81,7 +81,8 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p,
 		if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids)
 			continue;
 
-		cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask);
+		if (lowest_mask)
+			cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask);
 		return 1;
 	}
 

kernel/sched_rt.c

@@ -948,20 +948,15 @@ static int select_task_rq_rt(struct task_struct *p, int sync)
 
 static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
 {
-	cpumask_var_t mask;
-
 	if (rq->curr->rt.nr_cpus_allowed == 1)
 		return;
 
-	if (!alloc_cpumask_var(&mask, GFP_ATOMIC))
+	if (p->rt.nr_cpus_allowed != 1
+	    && cpupri_find(&rq->rd->cpupri, p, NULL))
 		return;
 
-	if (p->rt.nr_cpus_allowed != 1
-	    && cpupri_find(&rq->rd->cpupri, p, mask))
-		goto free;
-
-	if (!cpupri_find(&rq->rd->cpupri, rq->curr, mask))
-		goto free;
+	if (!cpupri_find(&rq->rd->cpupri, rq->curr, NULL))
+		return;
 
 	/*
 	 * There appears to be other cpus that can accept
@@ -970,8 +965,6 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
 	 */
 	requeue_task_rt(rq, p, 1);
 	resched_task(rq->curr);
-free:
-	free_cpumask_var(mask);
 }
 
 #endif /* CONFIG_SMP */

kernel/slow-work.c

@@ -609,14 +609,14 @@ void slow_work_unregister_user(void)
 	if (slow_work_user_count == 0) {
 		printk(KERN_NOTICE "Slow work thread pool: Shutting down\n");
 		slow_work_threads_should_exit = true;
+		del_timer_sync(&slow_work_cull_timer);
+		del_timer_sync(&slow_work_oom_timer);
 		wake_up_all(&slow_work_thread_wq);
 		wait_for_completion(&slow_work_last_thread_exited);
 		printk(KERN_NOTICE "Slow work thread pool:"
 		       " Shut down complete\n");
 	}
 
-	del_timer_sync(&slow_work_cull_timer);
-
 	mutex_unlock(&slow_work_user_lock);
 }
 EXPORT_SYMBOL(slow_work_unregister_user);

kernel/softirq.c

@@ -472,9 +472,9 @@ void tasklet_kill(struct tasklet_struct *t)
 		printk("Attempt to kill tasklet from interrupt\n");
 
 	while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
-		do
+		do {
 			yield();
-		while (test_bit(TASKLET_STATE_SCHED, &t->state));
+		} while (test_bit(TASKLET_STATE_SCHED, &t->state));
 	}
 	tasklet_unlock_wait(t);
 	clear_bit(TASKLET_STATE_SCHED, &t->state);

kernel/softlockup.c

@@ -165,98 +165,12 @@ void softlockup_tick(void)
 		panic("softlockup: hung tasks");
 }
 
-/*
- * Have a reasonable limit on the number of tasks checked:
- */
-unsigned long __read_mostly sysctl_hung_task_check_count = 1024;
-
-/*
- * Zero means infinite timeout - no checking done:
- */
-unsigned long __read_mostly sysctl_hung_task_timeout_secs = 480;
-
-unsigned long __read_mostly sysctl_hung_task_warnings = 10;
-
-/*
- * Only do the hung-tasks check on one CPU:
- */
-static int check_cpu __read_mostly = -1;
-
-static void check_hung_task(struct task_struct *t, unsigned long now)
-{
-	unsigned long switch_count = t->nvcsw + t->nivcsw;
-
-	if (t->flags & PF_FROZEN)
-		return;
-
-	if (switch_count != t->last_switch_count || !t->last_switch_timestamp) {
-		t->last_switch_count = switch_count;
-		t->last_switch_timestamp = now;
-		return;
-	}
-	if ((long)(now - t->last_switch_timestamp) <
-					sysctl_hung_task_timeout_secs)
-		return;
-	if (!sysctl_hung_task_warnings)
-		return;
-	sysctl_hung_task_warnings--;
-
-	/*
-	 * Ok, the task did not get scheduled for more than 2 minutes,
-	 * complain:
-	 */
-	printk(KERN_ERR "INFO: task %s:%d blocked for more than "
-			"%ld seconds.\n", t->comm, t->pid,
-			sysctl_hung_task_timeout_secs);
-	printk(KERN_ERR "\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\""
-			" disables this message.\n");
-	sched_show_task(t);
-	__debug_show_held_locks(t);
-
-	t->last_switch_timestamp = now;
-	touch_nmi_watchdog();
-
-	if (softlockup_panic)
-		panic("softlockup: blocked tasks");
-}
-
-/*
- * Check whether a TASK_UNINTERRUPTIBLE does not get woken up for
- * a really long time (120 seconds). If that happens, print out
- * a warning.
- */
-static void check_hung_uninterruptible_tasks(int this_cpu)
-{
-	int max_count = sysctl_hung_task_check_count;
-	unsigned long now = get_timestamp(this_cpu);
-	struct task_struct *g, *t;
-
-	/*
-	 * If the system crashed already then all bets are off,
-	 * do not report extra hung tasks:
-	 */
-	if (test_taint(TAINT_DIE) || did_panic)
-		return;
-
-	read_lock(&tasklist_lock);
-	do_each_thread(g, t) {
-		if (!--max_count)
-			goto unlock;
-		/* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */
-		if (t->state == TASK_UNINTERRUPTIBLE)
-			check_hung_task(t, now);
-	} while_each_thread(g, t);
- unlock:
-	read_unlock(&tasklist_lock);
-}
-
 /*
  * The watchdog thread - runs every second and touches the timestamp.
  */
 static int watchdog(void *__bind_cpu)
 {
 	struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
-	int this_cpu = (long)__bind_cpu;
 
 	sched_setscheduler(current, SCHED_FIFO, &param);
 
@@ -276,11 +190,6 @@ static int watchdog(void *__bind_cpu)
 		if (kthread_should_stop())
 			break;
 
-		if (this_cpu == check_cpu) {
-			if (sysctl_hung_task_timeout_secs)
-				check_hung_uninterruptible_tasks(this_cpu);
-		}
-
 		set_current_state(TASK_INTERRUPTIBLE);
 	}
 	__set_current_state(TASK_RUNNING);
@@ -312,18 +221,9 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		break;
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-		check_cpu = cpumask_any(cpu_online_mask);
 		wake_up_process(per_cpu(watchdog_task, hotcpu));
 		break;
 #ifdef CONFIG_HOTPLUG_CPU
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		if (hotcpu == check_cpu) {
-			/* Pick any other online cpu. */
-			check_cpu = cpumask_any_but(cpu_online_mask, hotcpu);
-		}
-		break;
-
 	case CPU_UP_CANCELED:
 	case CPU_UP_CANCELED_FROZEN:
 		if (!per_cpu(watchdog_task, hotcpu))

kernel/sys.c

@@ -360,6 +360,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
 		void __user *, arg)
 {
 	char buffer[256];
+	int ret = 0;
 
 	/* We only trust the superuser with rebooting the system. */
 	if (!capable(CAP_SYS_BOOT))
@@ -397,7 +398,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
 		kernel_halt();
 		unlock_kernel();
 		do_exit(0);
-		break;
+		panic("cannot halt");
 
 	case LINUX_REBOOT_CMD_POWER_OFF:
 		kernel_power_off();
@@ -417,29 +418,22 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
 
 #ifdef CONFIG_KEXEC
 	case LINUX_REBOOT_CMD_KEXEC:
-		{
-			int ret;
-			ret = kernel_kexec();
-			unlock_kernel();
-			return ret;
-		}
+		ret = kernel_kexec();
+		break;
 #endif
 
 #ifdef CONFIG_HIBERNATION
 	case LINUX_REBOOT_CMD_SW_SUSPEND:
-		{
-			int ret = hibernate();
-			unlock_kernel();
-			return ret;
-		}
+		ret = hibernate();
+		break;
 #endif
 
 	default:
-		unlock_kernel();
-		return -EINVAL;
+		ret = -EINVAL;
+		break;
 	}
 	unlock_kernel();
-	return 0;
+	return ret;
 }
 
 static void deferred_cad(struct work_struct *dummy)

kernel/sysctl.c

@@ -103,6 +103,9 @@ static unsigned long one_ul = 1;
 static int one_hundred = 100;
 static int one_thousand = 1000;
 
+/* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
+static unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
+
 /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
 static int maxolduid = 65535;
 static int minolduid;
@@ -814,6 +817,19 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &neg_one,
 		.extra2		= &sixty,
 	},
+#endif
+#ifdef CONFIG_DETECT_HUNG_TASK
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "hung_task_panic",
+		.data		= &sysctl_hung_task_panic,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 	{
 		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "hung_task_check_count",
@@ -829,7 +845,7 @@ static struct ctl_table kern_table[] = {
 		.data		= &sysctl_hung_task_timeout_secs,
 		.maxlen		= sizeof(unsigned long),
 		.mode		= 0644,
-		.proc_handler	= &proc_doulongvec_minmax,
+		.proc_handler	= &proc_dohung_task_timeout_secs,
 		.strategy	= &sysctl_intvec,
 	},
 	{
@@ -889,16 +905,6 @@ static struct ctl_table kern_table[] = {
 		.proc_handler   = &proc_dointvec,
 	},
 #endif
-#ifdef CONFIG_UNEVICTABLE_LRU
-	{
-		.ctl_name	= CTL_UNNUMBERED,
-		.procname	= "scan_unevictable_pages",
-		.data		= &scan_unevictable_pages,
-		.maxlen		= sizeof(scan_unevictable_pages),
-		.mode		= 0644,
-		.proc_handler	= &scan_unevictable_handler,
-	},
-#endif
 #ifdef CONFIG_SLOW_WORK
 	{
 		.ctl_name	= CTL_UNNUMBERED,
@@ -1003,7 +1009,7 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &dirty_bytes_handler,
 		.strategy	= &sysctl_intvec,
-		.extra1		= &one_ul,
+		.extra1		= &dirty_bytes_min,
 	},
 	{
 		.procname	= "dirty_writeback_centisecs",
@@ -1289,6 +1295,16 @@ static struct ctl_table vm_table[] = {
 		.extra2		= &one,
 	},
 #endif
+#ifdef CONFIG_UNEVICTABLE_LRU
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "scan_unevictable_pages",
+		.data		= &scan_unevictable_pages,
+		.maxlen		= sizeof(scan_unevictable_pages),
+		.mode		= 0644,
+		.proc_handler	= &scan_unevictable_handler,
+	},
+#endif
 /*
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt

kernel/time/clocksource.c

@@ -181,12 +181,12 @@ static void clocksource_watchdog(unsigned long data)
 
 	resumed = test_and_clear_bit(0, &watchdog_resumed);
 
-	wdnow = watchdog->read();
+	wdnow = watchdog->read(watchdog);
 	wd_nsec = cyc2ns(watchdog, (wdnow - watchdog_last) & watchdog->mask);
 	watchdog_last = wdnow;
 
 	list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) {
-		csnow = cs->read();
+		csnow = cs->read(cs);
 
 		if (unlikely(resumed)) {
 			cs->wd_last = csnow;
@@ -247,7 +247,7 @@ static void clocksource_check_watchdog(struct clocksource *cs)
 
 		list_add(&cs->wd_list, &watchdog_list);
 		if (!started && watchdog) {
-			watchdog_last = watchdog->read();
+			watchdog_last = watchdog->read(watchdog);
 			watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL;
 			add_timer_on(&watchdog_timer,
 				     cpumask_first(cpu_online_mask));
@@ -268,7 +268,7 @@ static void clocksource_check_watchdog(struct clocksource *cs)
 				cse->flags &= ~CLOCK_SOURCE_WATCHDOG;
 			/* Start if list is not empty */
 			if (!list_empty(&watchdog_list)) {
-				watchdog_last = watchdog->read();
+				watchdog_last = watchdog->read(watchdog);
 				watchdog_timer.expires =
 					jiffies + WATCHDOG_INTERVAL;
 				add_timer_on(&watchdog_timer,

kernel/time/jiffies.c

@@ -50,7 +50,7 @@
  */
 #define JIFFIES_SHIFT	8
 
-static cycle_t jiffies_read(void)
+static cycle_t jiffies_read(struct clocksource *cs)
 {
 	return (cycle_t) jiffies;
 }

kernel/time/tick-common.c

@@ -93,7 +93,17 @@ void tick_handle_periodic(struct clock_event_device *dev)
 	for (;;) {
 		if (!clockevents_program_event(dev, next, ktime_get()))
 			return;
-		tick_periodic(cpu);
+		/*
+		 * Have to be careful here. If we're in oneshot mode,
+		 * before we call tick_periodic() in a loop, we need
+		 * to be sure we're using a real hardware clocksource.
+		 * Otherwise we could get trapped in an infinite
+		 * loop, as the tick_periodic() increments jiffies,
+		 * when then will increment time, posibly causing
+		 * the loop to trigger again and again.
+		 */
+		if (timekeeping_valid_for_hres())
+			tick_periodic(cpu);
 		next = ktime_add(next, tick_period);
 	}
 }

kernel/time/timekeeping.c

@@ -182,7 +182,7 @@ EXPORT_SYMBOL(do_settimeofday);
  */
 static void change_clocksource(void)
 {
-	struct clocksource *new;
+	struct clocksource *new, *old;
 
 	new = clocksource_get_next();
 
@@ -191,11 +191,16 @@ static void change_clocksource(void)
 
 	clocksource_forward_now();
 
-	new->raw_time = clock->raw_time;
+	if (clocksource_enable(new))
+		return;
 
+	new->raw_time = clock->raw_time;
+	old = clock;
 	clock = new;
+	clocksource_disable(old);
+
 	clock->cycle_last = 0;
-	clock->cycle_last = clocksource_read(new);
+	clock->cycle_last = clocksource_read(clock);
 	clock->error = 0;
 	clock->xtime_nsec = 0;
 	clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH);
@@ -292,6 +297,7 @@ void __init timekeeping_init(void)
 	ntp_init();
 
 	clock = clocksource_get_next();
+	clocksource_enable(clock);
 	clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH);
 	clock->cycle_last = clocksource_read(clock);
 

kernel/timer.c

@@ -531,10 +531,13 @@ static void __init_timer(struct timer_list *timer,
 }
 
 /**
- * init_timer - initialize a timer.
+ * init_timer_key - initialize a timer
  * @timer: the timer to be initialized
+ * @name: name of the timer
+ * @key: lockdep class key of the fake lock used for tracking timer
+ *       sync lock dependencies
  *
- * init_timer() must be done to a timer prior calling *any* of the
+ * init_timer_key() must be done to a timer prior calling *any* of the
  * other timer functions.
  */
 void init_timer_key(struct timer_list *timer,

kernel/trace/Kconfig

@@ -312,7 +312,7 @@ config KMEMTRACE
 	  and profile kernel code.
 
 	  This requires an userspace application to use. See
-	  Documentation/vm/kmemtrace.txt for more information.
+	  Documentation/trace/kmemtrace.txt for more information.
 
 	  Saying Y will make the kernel somewhat larger and slower. However,
 	  if you disable kmemtrace at run-time or boot-time, the performance
@@ -403,7 +403,7 @@ config MMIOTRACE
 	  implementation and works via page faults. Tracing is disabled by
 	  default and can be enabled at run-time.
 
-	  See Documentation/tracers/mmiotrace.txt.
+	  See Documentation/trace/mmiotrace.txt.
 	  If you are not helping to develop drivers, say N.
 
 config MMIOTRACE_TEST

kernel/trace/blktrace.c

@@ -327,10 +327,10 @@ static ssize_t blk_msg_write(struct file *filp, const char __user *buffer,
 	char *msg;
 	struct blk_trace *bt;
 
-	if (count > BLK_TN_MAX_MSG)
+	if (count >= BLK_TN_MAX_MSG)
 		return -EINVAL;
 
-	msg = kmalloc(count, GFP_KERNEL);
+	msg = kmalloc(count + 1, GFP_KERNEL);
 	if (msg == NULL)
 		return -ENOMEM;
 
@@ -339,6 +339,7 @@ static ssize_t blk_msg_write(struct file *filp, const char __user *buffer,
 		return -EFAULT;
 	}
 
+	msg[count] = '\0';
 	bt = filp->private_data;
 	__trace_note_message(bt, "%s", msg);
 	kfree(msg);
@@ -642,7 +643,7 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
 	if (blk_pc_request(rq)) {
 		what |= BLK_TC_ACT(BLK_TC_PC);
 		__blk_add_trace(bt, 0, rq->data_len, rw, what, rq->errors,
-				sizeof(rq->cmd), rq->cmd);
+				rq->cmd_len, rq->cmd);
 	} else  {
 		what |= BLK_TC_ACT(BLK_TC_FS);
 		__blk_add_trace(bt, rq->hard_sector, rq->hard_nr_sectors << 9,
@@ -1376,12 +1377,12 @@ static int blk_trace_str2mask(const char *str)
 {
 	int i;
 	int mask = 0;
-	char *s, *token;
+	char *buf, *s, *token;
 
-	s = kstrdup(str, GFP_KERNEL);
-	if (s == NULL)
+	buf = kstrdup(str, GFP_KERNEL);
+	if (buf == NULL)
 		return -ENOMEM;
-	s = strstrip(s);
+	s = strstrip(buf);
 
 	while (1) {
 		token = strsep(&s, ",");
@@ -1402,7 +1403,7 @@ static int blk_trace_str2mask(const char *str)
 			break;
 		}
 	}
-	kfree(s);
+	kfree(buf);
 
 	return mask;
 }

kernel/trace/trace.c

@@ -30,6 +30,7 @@
 #include <linux/percpu.h>
 #include <linux/splice.h>
 #include <linux/kdebug.h>
+#include <linux/string.h>
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/poll.h>
@@ -147,8 +148,7 @@ static int __init set_ftrace_dump_on_oops(char *str)
 }
 __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops);
 
-long
-ns2usecs(cycle_t nsec)
+unsigned long long ns2usecs(cycle_t nsec)
 {
 	nsec += 500;
 	do_div(nsec, 1000);
@@ -1632,7 +1632,11 @@ static void test_cpu_buff_start(struct trace_iterator *iter)
 		return;
 
 	cpumask_set_cpu(iter->cpu, iter->started);
-	trace_seq_printf(s, "##### CPU %u buffer started ####\n", iter->cpu);
+
+	/* Don't print started cpu buffer for the first entry of the trace */
+	if (iter->idx > 1)
+		trace_seq_printf(s, "##### CPU %u buffer started ####\n",
+				iter->cpu);
 }
 
 static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
@@ -1867,6 +1871,11 @@ __tracing_open(struct inode *inode, struct file *file)
 	if (current_trace)
 		*iter->trace = *current_trace;
 
+	if (!alloc_cpumask_var(&iter->started, GFP_KERNEL))
+		goto fail;
+
+	cpumask_clear(iter->started);
+
 	if (current_trace && current_trace->print_max)
 		iter->tr = &max_tr;
 	else
@@ -1917,6 +1926,7 @@ __tracing_open(struct inode *inode, struct file *file)
 		if (iter->buffer_iter[cpu])
 			ring_buffer_read_finish(iter->buffer_iter[cpu]);
 	}
+	free_cpumask_var(iter->started);
  fail:
 	mutex_unlock(&trace_types_lock);
 	kfree(iter->trace);
@@ -1960,6 +1970,7 @@ static int tracing_release(struct inode *inode, struct file *file)
 
 	seq_release(inode, file);
 	mutex_destroy(&iter->mutex);
+	free_cpumask_var(iter->started);
 	kfree(iter->trace);
 	kfree(iter);
 	return 0;
@@ -2358,9 +2369,9 @@ static const char readme_msg[] =
 	"# mkdir /debug\n"
 	"# mount -t debugfs nodev /debug\n\n"
 	"# cat /debug/tracing/available_tracers\n"
-	"wakeup preemptirqsoff preemptoff irqsoff ftrace sched_switch none\n\n"
+	"wakeup preemptirqsoff preemptoff irqsoff function sched_switch nop\n\n"
 	"# cat /debug/tracing/current_tracer\n"
-	"none\n"
+	"nop\n"
 	"# echo sched_switch > /debug/tracing/current_tracer\n"
 	"# cat /debug/tracing/current_tracer\n"
 	"sched_switch\n"
@@ -3266,19 +3277,13 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp)
 
 	info->tr	= &global_trace;
 	info->cpu	= cpu;
-	info->spare	= ring_buffer_alloc_read_page(info->tr->buffer);
+	info->spare	= NULL;
 	/* Force reading ring buffer for first read */
 	info->read	= (unsigned int)-1;
-	if (!info->spare)
-		goto out;
 
 	filp->private_data = info;
 
-	return 0;
-
- out:
-	kfree(info);
-	return -ENOMEM;
+	return nonseekable_open(inode, filp);
 }
 
 static ssize_t
@@ -3293,6 +3298,11 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 	if (!count)
 		return 0;
 
+	if (!info->spare)
+		info->spare = ring_buffer_alloc_read_page(info->tr->buffer);
+	if (!info->spare)
+		return -ENOMEM;
+
 	/* Do we have previous read data to read? */
 	if (info->read < PAGE_SIZE)
 		goto read;
@@ -3331,7 +3341,8 @@ static int tracing_buffers_release(struct inode *inode, struct file *file)
 {
 	struct ftrace_buffer_info *info = file->private_data;
 
-	ring_buffer_free_read_page(info->tr->buffer, info->spare);
+	if (info->spare)
+		ring_buffer_free_read_page(info->tr->buffer, info->spare);
 	kfree(info);
 
 	return 0;
@@ -3417,14 +3428,19 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 	int size, i;
 	size_t ret;
 
-	/*
-	 * We can't seek on a buffer input
-	 */
-	if (unlikely(*ppos))
-		return -ESPIPE;
+	if (*ppos & (PAGE_SIZE - 1)) {
+		WARN_ONCE(1, "Ftrace: previous read must page-align\n");
+		return -EINVAL;
+	}
 
+	if (len & (PAGE_SIZE - 1)) {
+		WARN_ONCE(1, "Ftrace: splice_read should page-align\n");
+		if (len < PAGE_SIZE)
+			return -EINVAL;
+		len &= PAGE_MASK;
+	}
 
-	for (i = 0; i < PIPE_BUFFERS && len; i++, len -= size) {
+	for (i = 0; i < PIPE_BUFFERS && len; i++, len -= PAGE_SIZE) {
 		struct page *page;
 		int r;
 
@@ -3432,6 +3448,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		if (!ref)
 			break;
 
+		ref->ref = 1;
 		ref->buffer = info->tr->buffer;
 		ref->page = ring_buffer_alloc_read_page(ref->buffer);
 		if (!ref->page) {
@@ -3463,6 +3480,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		spd.partial[i].offset = 0;
 		spd.partial[i].private = (unsigned long)ref;
 		spd.nr_pages++;
+		*ppos += PAGE_SIZE;
 	}
 
 	spd.nr_pages = i;

kernel/trace/trace.h

@@ -602,7 +602,7 @@ extern int trace_selftest_startup_branch(struct tracer *trace,
 #endif /* CONFIG_FTRACE_STARTUP_TEST */
 
 extern void *head_page(struct trace_array_cpu *data);
-extern long ns2usecs(cycle_t nsec);
+extern unsigned long long ns2usecs(cycle_t nsec);
 extern int
 trace_vbprintk(unsigned long ip, const char *fmt, va_list args);
 extern int

kernel/trace/trace_branch.c

@@ -155,6 +155,13 @@ static enum print_line_t trace_branch_print(struct trace_iterator *iter,
 	return TRACE_TYPE_HANDLED;
 }
 
+static void branch_print_header(struct seq_file *s)
+{
+	seq_puts(s, "#           TASK-PID    CPU#    TIMESTAMP  CORRECT"
+		"  FUNC:FILE:LINE\n");
+	seq_puts(s, "#              | |       |          |         |   "
+		"    |\n");
+}
 
 static struct trace_event trace_branch_event = {
 	.type		= TRACE_BRANCH,
@@ -169,6 +176,7 @@ static struct tracer branch_trace __read_mostly =
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest	= trace_selftest_startup_branch,
 #endif /* CONFIG_FTRACE_SELFTEST */
+	.print_header	= branch_print_header,
 };
 
 __init static int init_branch_tracer(void)

kernel/trace/trace_events.c

@@ -503,6 +503,7 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 
 	if (copy_from_user(&buf, ubuf, cnt))
 		return -EFAULT;
+	buf[cnt] = '\0';
 
 	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
 	if (!pred)
@@ -520,9 +521,10 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 		return cnt;
 	}
 
-	if (filter_add_pred(call, pred)) {
+	err = filter_add_pred(call, pred);
+	if (err < 0) {
 		filter_free_pred(pred);
-		return -EINVAL;
+		return err;
 	}
 
 	*ppos += cnt;
@@ -569,6 +571,7 @@ subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 
 	if (copy_from_user(&buf, ubuf, cnt))
 		return -EFAULT;
+	buf[cnt] = '\0';
 
 	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
 	if (!pred)
@@ -586,10 +589,11 @@ subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 		return cnt;
 	}
 
-	if (filter_add_subsystem_pred(system, pred)) {
+	err = filter_add_subsystem_pred(system, pred);
+	if (err < 0) {
 		filter_free_subsystem_preds(system);
 		filter_free_pred(pred);
-		return -EINVAL;
+		return err;
 	}
 
 	*ppos += cnt;

kernel/trace/trace_events_filter.c

@@ -215,7 +215,7 @@ static int __filter_add_pred(struct ftrace_event_call *call,
 		}
 	}
 
-	return -ENOMEM;
+	return -ENOSPC;
 }
 
 static int is_string_field(const char *type)
@@ -319,7 +319,7 @@ int filter_add_subsystem_pred(struct event_subsystem *system,
 	}
 
 	if (i == MAX_FILTER_PRED)
-		return -EINVAL;
+		return -ENOSPC;
 
 	events_for_each(call) {
 		int err;
@@ -410,16 +410,22 @@ int filter_parse(char **pbuf, struct filter_pred *pred)
 		}
 	}
 
+	if (!val_str) {
+		pred->field_name = NULL;
+		return -EINVAL;
+	}
+
 	pred->field_name = kstrdup(pred->field_name, GFP_KERNEL);
 	if (!pred->field_name)
 		return -ENOMEM;
 
-	pred->val = simple_strtoull(val_str, &tmp, 10);
+	pred->val = simple_strtoull(val_str, &tmp, 0);
 	if (tmp == val_str) {
 		pred->str_val = kstrdup(val_str, GFP_KERNEL);
 		if (!pred->str_val)
 			return -ENOMEM;
-	}
+	} else if (*tmp != '\0')
+		return -EINVAL;
 
 	return 0;
 }

kernel/trace/trace_events_stage_2.h

@@ -105,10 +105,10 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
 		return 0;
 
 #undef __entry
-#define __entry "REC"
+#define __entry REC
 
 #undef TP_printk
-#define TP_printk(fmt, args...) "%s, %s\n", #fmt, #args
+#define TP_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args)
 
 #undef TP_fast_assign
 #define TP_fast_assign(args...) args

kernel/trace/trace_export.c

@@ -40,7 +40,7 @@
 
 #undef TRACE_FIELD_ZERO_CHAR
 #define TRACE_FIELD_ZERO_CHAR(item)					\
-	ret = trace_seq_printf(s, "\tfield: char " #item ";\t"		\
+	ret = trace_seq_printf(s, "\tfield:char " #item ";\t"		\
 			       "offset:%u;\tsize:0;\n",			\
 			       (unsigned int)offsetof(typeof(field), item)); \
 	if (!ret)							\

kernel/trace/trace_output.c

@@ -423,7 +423,7 @@ int trace_print_lat_context(struct trace_iterator *iter)
 
 		trace_find_cmdline(entry->pid, comm);
 
-		ret = trace_seq_printf(s, "%16s %5d %3d %d %08x %08lx [%08lx]"
+		ret = trace_seq_printf(s, "%16s %5d %3d %d %08x %08lx [%08llx]"
 				       " %ld.%03ldms (+%ld.%03ldms): ", comm,
 				       entry->pid, iter->cpu, entry->flags,
 				       entry->preempt_count, iter->idx,

kernel/trace/trace_power.c

@@ -186,6 +186,12 @@ static enum print_line_t power_print_line(struct trace_iterator *iter)
 	return TRACE_TYPE_UNHANDLED;
 }
 
+static void power_print_header(struct seq_file *s)
+{
+	seq_puts(s, "#   TIMESTAMP      STATE  EVENT\n");
+	seq_puts(s, "#       |            |      |\n");
+}
+
 static struct tracer power_tracer __read_mostly =
 {
 	.name		= "power",
@@ -194,6 +200,7 @@ static struct tracer power_tracer __read_mostly =
 	.stop		= stop_power_trace,
 	.reset		= power_trace_reset,
 	.print_line	= power_print_line,
+	.print_header	= power_print_header,
 };
 
 static int init_power_trace(void)

kernel/trace/trace_sched_switch.c

@@ -62,6 +62,9 @@ probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee, int success)
 	pc = preempt_count();
 	tracing_record_cmdline(current);
 
+	if (sched_stopped)
+		return;
+
 	local_irq_save(flags);
 	cpu = raw_smp_processor_id();
 	data = ctx_trace->data[cpu];

kernel/trace/trace_sched_wakeup.c

@@ -154,7 +154,7 @@ probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev,
 	if (unlikely(!tracer_enabled || next != wakeup_task))
 		goto out_unlock;
 
-	trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, flags, pc);
+	trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc);
 	tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc);
 
 	/*
@@ -257,6 +257,12 @@ probe_wakeup(struct rq *rq, struct task_struct *p, int success)
 	data = wakeup_trace->data[wakeup_cpu];
 	data->preempt_timestamp = ftrace_now(cpu);
 	tracing_sched_wakeup_trace(wakeup_trace, p, current, flags, pc);
+
+	/*
+	 * We must be careful in using CALLER_ADDR2. But since wake_up
+	 * is not called by an assembly function  (where as schedule is)
+	 * it should be safe to use it here.
+	 */
 	trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, flags, pc);
 
 out_locked:

kernel/trace/trace_syscalls.c

@@ -1,5 +1,5 @@
+#include <trace/syscall.h>
 #include <linux/kernel.h>
-#include <linux/ftrace.h>
 #include <asm/syscall.h>
 
 #include "trace_output.h"

kernel/workqueue.c

@@ -966,20 +966,20 @@ undo:
 }
 
 #ifdef CONFIG_SMP
-static struct workqueue_struct *work_on_cpu_wq __read_mostly;
 
 struct work_for_cpu {
-	struct work_struct work;
+	struct completion completion;
 	long (*fn)(void *);
 	void *arg;
 	long ret;
 };
 
-static void do_work_for_cpu(struct work_struct *w)
+static int do_work_for_cpu(void *_wfc)
 {
-	struct work_for_cpu *wfc = container_of(w, struct work_for_cpu, work);
-
+	struct work_for_cpu *wfc = _wfc;
 	wfc->ret = wfc->fn(wfc->arg);
+	complete(&wfc->completion);
+	return 0;
 }
 
 /**
@@ -990,17 +990,23 @@ static void do_work_for_cpu(struct work_struct *w)
  *
  * This will return the value @fn returns.
  * It is up to the caller to ensure that the cpu doesn't go offline.
+ * The caller must not hold any locks which would prevent @fn from completing.
  */
 long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
 {
-	struct work_for_cpu wfc;
-
-	INIT_WORK(&wfc.work, do_work_for_cpu);
-	wfc.fn = fn;
-	wfc.arg = arg;
-	queue_work_on(cpu, work_on_cpu_wq, &wfc.work);
-	flush_work(&wfc.work);
+	struct task_struct *sub_thread;
+	struct work_for_cpu wfc = {
+		.completion = COMPLETION_INITIALIZER_ONSTACK(wfc.completion),
+		.fn = fn,
+		.arg = arg,
+	};
 
+	sub_thread = kthread_create(do_work_for_cpu, &wfc, "work_for_cpu");
+	if (IS_ERR(sub_thread))
+		return PTR_ERR(sub_thread);
+	kthread_bind(sub_thread, cpu);
+	wake_up_process(sub_thread);
+	wait_for_completion(&wfc.completion);
 	return wfc.ret;
 }
 EXPORT_SYMBOL_GPL(work_on_cpu);
@@ -1016,8 +1022,4 @@ void __init init_workqueues(void)
 	hotcpu_notifier(workqueue_cpu_callback, 0);
 	keventd_wq = create_workqueue("events");
 	BUG_ON(!keventd_wq);
-#ifdef CONFIG_SMP
-	work_on_cpu_wq = create_workqueue("work_on_cpu");
-	BUG_ON(!work_on_cpu_wq);
-#endif
 }