Merge branch 'master'

14 files changed, 297 insertions, 187 deletions

diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 3e376202dd4..c4394abcd5e 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -841,7 +841,7 @@ static void audit_log_exit(struct audit_context *context, gfp_t gfp_mask)
 
 	for (aux = context->aux; aux; aux = aux->next) {
 
-		ab = audit_log_start(context, GFP_KERNEL, aux->type);
+		ab = audit_log_start(context, gfp_mask, aux->type);
 		if (!ab)
 			continue; /* audit_panic has been called */
 
@@ -878,14 +878,14 @@ static void audit_log_exit(struct audit_context *context, gfp_t gfp_mask)
 	}
 
 	if (context->pwd && context->pwdmnt) {
-		ab = audit_log_start(context, GFP_KERNEL, AUDIT_CWD);
+		ab = audit_log_start(context, gfp_mask, AUDIT_CWD);
 		if (ab) {
 			audit_log_d_path(ab, "cwd=", context->pwd, context->pwdmnt);
 			audit_log_end(ab);
 		}
 	}
 	for (i = 0; i < context->name_count; i++) {
-		ab = audit_log_start(context, GFP_KERNEL, AUDIT_PATH);
+		ab = audit_log_start(context, gfp_mask, AUDIT_PATH);
 		if (!ab)
 			continue; /* audit_panic has been called */
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index ba42b0a7696..12815d3f1a0 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1977,6 +1977,39 @@ void cpuset_fork(struct task_struct *child)
  * We don't need to task_lock() this reference to tsk->cpuset,
  * because tsk is already marked PF_EXITING, so attach_task() won't
  * mess with it, or task is a failed fork, never visible to attach_task.
+ *
+ * Hack:
+ *
+ *    Set the exiting tasks cpuset to the root cpuset (top_cpuset).
+ *
+ *    Don't leave a task unable to allocate memory, as that is an
+ *    accident waiting to happen should someone add a callout in
+ *    do_exit() after the cpuset_exit() call that might allocate.
+ *    If a task tries to allocate memory with an invalid cpuset,
+ *    it will oops in cpuset_update_task_memory_state().
+ *
+ *    We call cpuset_exit() while the task is still competent to
+ *    handle notify_on_release(), then leave the task attached to
+ *    the root cpuset (top_cpuset) for the remainder of its exit.
+ *
+ *    To do this properly, we would increment the reference count on
+ *    top_cpuset, and near the very end of the kernel/exit.c do_exit()
+ *    code we would add a second cpuset function call, to drop that
+ *    reference.  This would just create an unnecessary hot spot on
+ *    the top_cpuset reference count, to no avail.
+ *
+ *    Normally, holding a reference to a cpuset without bumping its
+ *    count is unsafe.   The cpuset could go away, or someone could
+ *    attach us to a different cpuset, decrementing the count on
+ *    the first cpuset that we never incremented.  But in this case,
+ *    top_cpuset isn't going away, and either task has PF_EXITING set,
+ *    which wards off any attach_task() attempts, or task is a failed
+ *    fork, never visible to attach_task.
+ *
+ *    Another way to do this would be to set the cpuset pointer
+ *    to NULL here, and check in cpuset_update_task_memory_state()
+ *    for a NULL pointer.  This hack avoids that NULL check, for no
+ *    cost (other than this way too long comment ;).
  **/
 
 void cpuset_exit(struct task_struct *tsk)
@@ -1984,7 +2017,7 @@ void cpuset_exit(struct task_struct *tsk)
 	struct cpuset *cs;
 
 	cs = tsk->cpuset;
-	tsk->cpuset = NULL;
+	tsk->cpuset = &top_cpuset;	/* Hack - see comment above */
 
 	if (notify_on_release(cs)) {
 		char *pathbuf = NULL;
diff --git a/kernel/exit.c b/kernel/exit.c
index 93cee367133..531aadca553 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -360,6 +360,9 @@ void daemonize(const char *name, ...)
 	fs = init_task.fs;
 	current->fs = fs;
 	atomic_inc(&fs->count);
+	exit_namespace(current);
+	current->namespace = init_task.namespace;
+	get_namespace(current->namespace);
  	exit_files(current);
 	current->files = init_task.files;
 	atomic_inc(&current->files->count);
diff --git a/kernel/fork.c b/kernel/fork.c
index 8e88b374cee..ccdfbb16c86 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -108,8 +108,10 @@ void free_task(struct task_struct *tsk)
 }
 EXPORT_SYMBOL(free_task);
 
-void __put_task_struct(struct task_struct *tsk)
+void __put_task_struct_cb(struct rcu_head *rhp)
 {
+	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
+
 	WARN_ON(!(tsk->exit_state & (EXIT_DEAD | EXIT_ZOMBIE)));
 	WARN_ON(atomic_read(&tsk->usage));
 	WARN_ON(tsk == current);
@@ -1060,6 +1062,12 @@ static task_t *copy_process(unsigned long clone_flags,
 	p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL;
 
 	/*
+	 * sigaltstack should be cleared when sharing the same VM
+	 */
+	if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM)
+		p->sas_ss_sp = p->sas_ss_size = 0;
+
+	/*
 	 * Syscall tracing should be turned off in the child regardless
 	 * of CLONE_PTRACE.
 	 */
@@ -1123,8 +1131,8 @@ static task_t *copy_process(unsigned long clone_flags,
 		p->real_parent = current;
 	p->parent = p->real_parent;
 
+	spin_lock(&current->sighand->siglock);
 	if (clone_flags & CLONE_THREAD) {
-		spin_lock(&current->sighand->siglock);
 		/*
 		 * Important: if an exit-all has been started then
 		 * do not create this new thread - the whole thread
@@ -1162,8 +1170,6 @@ static task_t *copy_process(unsigned long clone_flags,
 			 */
 			p->it_prof_expires = jiffies_to_cputime(1);
 		}
-
-		spin_unlock(&current->sighand->siglock);
 	}
 
 	/*
@@ -1175,8 +1181,6 @@ static task_t *copy_process(unsigned long clone_flags,
 	if (unlikely(p->ptrace & PT_PTRACED))
 		__ptrace_link(p, current->parent);
 
-	attach_pid(p, PIDTYPE_PID, p->pid);
-	attach_pid(p, PIDTYPE_TGID, p->tgid);
 	if (thread_group_leader(p)) {
 		p->signal->tty = current->signal->tty;
 		p->signal->pgrp = process_group(current);
@@ -1186,9 +1190,12 @@ static task_t *copy_process(unsigned long clone_flags,
 		if (p->pid)
 			__get_cpu_var(process_counts)++;
 	}
+	attach_pid(p, PIDTYPE_TGID, p->tgid);
+	attach_pid(p, PIDTYPE_PID, p->pid);
 
 	nr_threads++;
 	total_forks++;
+	spin_unlock(&current->sighand->siglock);
 	write_unlock_irq(&tasklist_lock);
 	proc_fork_connector(p);
 	return p;
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 2b6e1757aed..14bc9cfa639 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -418,8 +418,19 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
 	/* Switch the timer base, if necessary: */
 	new_base = switch_hrtimer_base(timer, base);
 
-	if (mode == HRTIMER_REL)
+	if (mode == HRTIMER_REL) {
 		tim = ktime_add(tim, new_base->get_time());
+		/*
+		 * CONFIG_TIME_LOW_RES is a temporary way for architectures
+		 * to signal that they simply return xtime in
+		 * do_gettimeoffset(). In this case we want to round up by
+		 * resolution when starting a relative timer, to avoid short
+		 * timeouts. This will go away with the GTOD framework.
+		 */
+#ifdef CONFIG_TIME_LOW_RES
+		tim = ktime_add(tim, base->resolution);
+#endif
+	}
 	timer->expires = tim;
 
 	enqueue_hrtimer(timer, new_base);
@@ -494,6 +505,41 @@ ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
 	return rem;
 }
 
+#ifdef CONFIG_NO_IDLE_HZ
+/**
+ * hrtimer_get_next_event - get the time until next expiry event
+ *
+ * Returns the delta to the next expiry event or KTIME_MAX if no timer
+ * is pending.
+ */
+ktime_t hrtimer_get_next_event(void)
+{
+	struct hrtimer_base *base = __get_cpu_var(hrtimer_bases);
+	ktime_t delta, mindelta = { .tv64 = KTIME_MAX };
+	unsigned long flags;
+	int i;
+
+	for (i = 0; i < MAX_HRTIMER_BASES; i++, base++) {
+		struct hrtimer *timer;
+
+		spin_lock_irqsave(&base->lock, flags);
+		if (!base->first) {
+			spin_unlock_irqrestore(&base->lock, flags);
+			continue;
+		}
+		timer = rb_entry(base->first, struct hrtimer, node);
+		delta.tv64 = timer->expires.tv64;
+		spin_unlock_irqrestore(&base->lock, flags);
+		delta = ktime_sub(delta, base->get_time());
+		if (delta.tv64 < mindelta.tv64)
+			mindelta.tv64 = delta.tv64;
+	}
+	if (mindelta.tv64 < 0)
+		mindelta.tv64 = 0;
+	return mindelta;
+}
+#endif
+
 /**
  * hrtimer_init - initialize a timer to the given clock
  *
diff --git a/kernel/panic.c b/kernel/panic.c
index c5c4ab25583..126dc43f1c7 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -130,6 +130,7 @@ NORET_TYPE void panic(const char * fmt, ...)
 #endif
 	local_irq_enable();
 	for (i = 0;;) {
+		touch_softlockup_watchdog();
 		i += panic_blink(i);
 		mdelay(1);
 		i++;
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 41f66365f0d..8d5a5986d62 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -91,10 +91,8 @@ static int save_highmem_zone(struct zone *zone)
 		 * corrected eventually when the cases giving rise to this
 		 * are better understood.
 		 */
-		if (PageReserved(page)) {
-			printk("highmem reserved page?!\n");
+		if (PageReserved(page))
 			continue;
-		}
 		BUG_ON(PageNosave(page));
 		if (PageNosaveFree(page))
 			continue;
diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
index 4e90905f0e8..2d9d08f72f7 100644
--- a/kernel/power/swsusp.c
+++ b/kernel/power/swsusp.c
@@ -153,13 +153,11 @@ static int swsusp_swap_check(void) /* This is called before saving image */
 {
 	int i;
 
-	if (!swsusp_resume_device)
-		return -ENODEV;
 	spin_lock(&swap_lock);
 	for (i = 0; i < MAX_SWAPFILES; i++) {
 		if (!(swap_info[i].flags & SWP_WRITEOK))
 			continue;
-		if (is_resume_device(swap_info + i)) {
+		if (!swsusp_resume_device || is_resume_device(swap_info + i)) {
 			spin_unlock(&swap_lock);
 			root_swap = i;
 			return 0;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 5f33cdb6fff..d95a72c9279 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -72,8 +72,8 @@ void ptrace_untrace(task_t *child)
  */
 void __ptrace_unlink(task_t *child)
 {
-	if (!child->ptrace)
-		BUG();
+	BUG_ON(!child->ptrace);
+
 	child->ptrace = 0;
 	if (!list_empty(&child->ptrace_list)) {
 		list_del_init(&child->ptrace_list);
@@ -184,22 +184,27 @@ bad:
 	return retval;
 }
 
+void __ptrace_detach(struct task_struct *child, unsigned int data)
+{
+	child->exit_code = data;
+	/* .. re-parent .. */
+	__ptrace_unlink(child);
+	/* .. and wake it up. */
+	if (child->exit_state != EXIT_ZOMBIE)
+		wake_up_process(child);
+}
+
 int ptrace_detach(struct task_struct *child, unsigned int data)
 {
 	if (!valid_signal(data))
-		return	-EIO;
+		return -EIO;
 
 	/* Architecture-specific hardware disable .. */
 	ptrace_disable(child);
 
-	/* .. re-parent .. */
-	child->exit_code = data;
-
 	write_lock_irq(&tasklist_lock);
-	__ptrace_unlink(child);
-	/* .. and wake it up. */
-	if (child->exit_state != EXIT_ZOMBIE)
-		wake_up_process(child);
+	if (child->ptrace)
+		__ptrace_detach(child, data);
 	write_unlock_irq(&tasklist_lock);
 
 	return 0;
@@ -242,8 +247,7 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in
 		if (write) {
 			copy_to_user_page(vma, page, addr,
 					  maddr + offset, buf, bytes);
-			if (!PageCompound(page))
-				set_page_dirty_lock(page);
+			set_page_dirty_lock(page);
 		} else {
 			copy_from_user_page(vma, page, addr,
 					    buf, maddr + offset, bytes);
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 0cf8146bd58..8cf15a569fc 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -67,7 +67,43 @@ DEFINE_PER_CPU(struct rcu_data, rcu_bh_data) = { 0L };
 
 /* Fake initialization required by compiler */
 static DEFINE_PER_CPU(struct tasklet_struct, rcu_tasklet) = {NULL};
-static int maxbatch = 10000;
+static int blimit = 10;
+static int qhimark = 10000;
+static int qlowmark = 100;
+#ifdef CONFIG_SMP
+static int rsinterval = 1000;
+#endif
+
+static atomic_t rcu_barrier_cpu_count;
+static struct semaphore rcu_barrier_sema;
+static struct completion rcu_barrier_completion;
+
+#ifdef CONFIG_SMP
+static void force_quiescent_state(struct rcu_data *rdp,
+			struct rcu_ctrlblk *rcp)
+{
+	int cpu;
+	cpumask_t cpumask;
+	set_need_resched();
+	if (unlikely(rdp->qlen - rdp->last_rs_qlen > rsinterval)) {
+		rdp->last_rs_qlen = rdp->qlen;
+		/*
+		 * Don't send IPI to itself. With irqs disabled,
+		 * rdp->cpu is the current cpu.
+		 */
+		cpumask = rcp->cpumask;
+		cpu_clear(rdp->cpu, cpumask);
+		for_each_cpu_mask(cpu, cpumask)
+			smp_send_reschedule(cpu);
+	}
+}
+#else
+static inline void force_quiescent_state(struct rcu_data *rdp,
+			struct rcu_ctrlblk *rcp)
+{
+	set_need_resched();
+}
+#endif
 
 /**
  * call_rcu - Queue an RCU callback for invocation after a grace period.
@@ -92,17 +128,13 @@ void fastcall call_rcu(struct rcu_head *head,
 	rdp = &__get_cpu_var(rcu_data);
 	*rdp->nxttail = head;
 	rdp->nxttail = &head->next;
-
-	if (unlikely(++rdp->count > 10000))
-		set_need_resched();
-
+	if (unlikely(++rdp->qlen > qhimark)) {
+		rdp->blimit = INT_MAX;
+		force_quiescent_state(rdp, &rcu_ctrlblk);
+	}
 	local_irq_restore(flags);
 }
 
-static atomic_t rcu_barrier_cpu_count;
-static struct semaphore rcu_barrier_sema;
-static struct completion rcu_barrier_completion;
-
 /**
  * call_rcu_bh - Queue an RCU for invocation after a quicker grace period.
  * @head: structure to be used for queueing the RCU updates.
@@ -131,12 +163,12 @@ void fastcall call_rcu_bh(struct rcu_head *head,
 	rdp = &__get_cpu_var(rcu_bh_data);
 	*rdp->nxttail = head;
 	rdp->nxttail = &head->next;
-	rdp->count++;
-/*
- *  Should we directly call rcu_do_batch() here ?
- *  if (unlikely(rdp->count > 10000))
- *      rcu_do_batch(rdp);
- */
+
+	if (unlikely(++rdp->qlen > qhimark)) {
+		rdp->blimit = INT_MAX;
+		force_quiescent_state(rdp, &rcu_bh_ctrlblk);
+	}
+
 	local_irq_restore(flags);
 }
 
@@ -199,10 +231,12 @@ static void rcu_do_batch(struct rcu_data *rdp)
 		next = rdp->donelist = list->next;
 		list->func(list);
 		list = next;
-		rdp->count--;
-		if (++count >= maxbatch)
+		rdp->qlen--;
+		if (++count >= rdp->blimit)
 			break;
 	}
+	if (rdp->blimit == INT_MAX && rdp->qlen <= qlowmark)
+		rdp->blimit = blimit;
 	if (!rdp->donelist)
 		rdp->donetail = &rdp->donelist;
 	else
@@ -473,6 +507,7 @@ static void rcu_init_percpu_data(int cpu, struct rcu_ctrlblk *rcp,
 	rdp->quiescbatch = rcp->completed;
 	rdp->qs_pending = 0;
 	rdp->cpu = cpu;
+	rdp->blimit = blimit;
 }
 
 static void __devinit rcu_online_cpu(int cpu)
@@ -567,7 +602,12 @@ void synchronize_kernel(void)
 	synchronize_rcu();
 }
 
-module_param(maxbatch, int, 0);
+module_param(blimit, int, 0);
+module_param(qhimark, int, 0);
+module_param(qlowmark, int, 0);
+#ifdef CONFIG_SMP
+module_param(rsinterval, int, 0);
+#endif
 EXPORT_SYMBOL_GPL(rcu_batches_completed);
 EXPORT_SYMBOL(call_rcu);  /* WARNING: GPL-only in April 2006. */
 EXPORT_SYMBOL(call_rcu_bh);  /* WARNING: GPL-only in April 2006. */
diff --git a/kernel/sched.c b/kernel/sched.c
index bc38804e40d..4d46e90f59c 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -178,13 +178,6 @@ static unsigned int task_timeslice(task_t *p)
 #define task_hot(p, now, sd) ((long long) ((now) - (p)->last_ran)	\
 				< (long long) (sd)->cache_hot_time)
 
-void __put_task_struct_cb(struct rcu_head *rhp)
-{
-	__put_task_struct(container_of(rhp, struct task_struct, rcu));
-}
-
-EXPORT_SYMBOL_GPL(__put_task_struct_cb);
-
 /*
  * These are the runqueue data structures:
  */
@@ -215,7 +208,6 @@ struct runqueue {
 	 */
 	unsigned long nr_running;
 #ifdef CONFIG_SMP
-	unsigned long prio_bias;
 	unsigned long cpu_load[3];
 #endif
 	unsigned long long nr_switches;
@@ -669,68 +661,13 @@ static int effective_prio(task_t *p)
 	return prio;
 }
 
-#ifdef CONFIG_SMP
-static inline void inc_prio_bias(runqueue_t *rq, int prio)
-{
-	rq->prio_bias += MAX_PRIO - prio;
-}
-
-static inline void dec_prio_bias(runqueue_t *rq, int prio)
-{
-	rq->prio_bias -= MAX_PRIO - prio;
-}
-
-static inline void inc_nr_running(task_t *p, runqueue_t *rq)
-{
-	rq->nr_running++;
-	if (rt_task(p)) {
-		if (p != rq->migration_thread)
-			/*
-			 * The migration thread does the actual balancing. Do
-			 * not bias by its priority as the ultra high priority
-			 * will skew balancing adversely.
-			 */
-			inc_prio_bias(rq, p->prio);
-	} else
-		inc_prio_bias(rq, p->static_prio);
-}
-
-static inline void dec_nr_running(task_t *p, runqueue_t *rq)
-{
-	rq->nr_running--;
-	if (rt_task(p)) {
-		if (p != rq->migration_thread)
-			dec_prio_bias(rq, p->prio);
-	} else
-		dec_prio_bias(rq, p->static_prio);
-}
-#else
-static inline void inc_prio_bias(runqueue_t *rq, int prio)
-{
-}
-
-static inline void dec_prio_bias(runqueue_t *rq, int prio)
-{
-}
-
-static inline void inc_nr_running(task_t *p, runqueue_t *rq)
-{
-	rq->nr_running++;
-}
-
-static inline void dec_nr_running(task_t *p, runqueue_t *rq)
-{
-	rq->nr_running--;
-}
-#endif
-
 /*
  * __activate_task - move a task to the runqueue.
  */
 static inline void __activate_task(task_t *p, runqueue_t *rq)
 {
 	enqueue_task(p, rq->active);
-	inc_nr_running(p, rq);
+	rq->nr_running++;
 }
 
 /*
@@ -739,7 +676,7 @@ static inline void __activate_task(task_t *p, runqueue_t *rq)
 static inline void __activate_idle_task(task_t *p, runqueue_t *rq)
 {
 	enqueue_task_head(p, rq->active);
-	inc_nr_running(p, rq);
+	rq->nr_running++;
 }
 
 static int recalc_task_prio(task_t *p, unsigned long long now)
@@ -863,7 +800,7 @@ static void activate_task(task_t *p, runqueue_t *rq, int local)
  */
 static void deactivate_task(struct task_struct *p, runqueue_t *rq)
 {
-	dec_nr_running(p, rq);
+	rq->nr_running--;
 	dequeue_task(p, p->array);
 	p->array = NULL;
 }
@@ -1007,61 +944,27 @@ void kick_process(task_t *p)
  * We want to under-estimate the load of migration sources, to
  * balance conservatively.
  */
-static unsigned long __source_load(int cpu, int type, enum idle_type idle)
+static inline unsigned long source_load(int cpu, int type)
 {
 	runqueue_t *rq = cpu_rq(cpu);
-	unsigned long running = rq->nr_running;
-	unsigned long source_load, cpu_load = rq->cpu_load[type-1],
-		load_now = running * SCHED_LOAD_SCALE;
-
+	unsigned long load_now = rq->nr_running * SCHED_LOAD_SCALE;
 	if (type == 0)
-		source_load = load_now;
-	else
-		source_load = min(cpu_load, load_now);
-
-	if (running > 1 || (idle == NOT_IDLE && running))
-		/*
-		 * If we are busy rebalancing the load is biased by
-		 * priority to create 'nice' support across cpus. When
-		 * idle rebalancing we should only bias the source_load if
-		 * there is more than one task running on that queue to
-		 * prevent idle rebalance from trying to pull tasks from a
-		 * queue with only one running task.
-		 */
-		source_load = source_load * rq->prio_bias / running;
+		return load_now;
 
-	return source_load;
-}
-
-static inline unsigned long source_load(int cpu, int type)
-{
-	return __source_load(cpu, type, NOT_IDLE);
+	return min(rq->cpu_load[type-1], load_now);
 }
 
 /*
  * Return a high guess at the load of a migration-target cpu
  */
-static inline unsigned long __target_load(int cpu, int type, enum idle_type idle)
+static inline unsigned long target_load(int cpu, int type)
 {
 	runqueue_t *rq = cpu_rq(cpu);
-	unsigned long running = rq->nr_running;
-	unsigned long target_load, cpu_load = rq->cpu_load[type-1],
-		load_now = running * SCHED_LOAD_SCALE;
-
+	unsigned long load_now = rq->nr_running * SCHED_LOAD_SCALE;
 	if (type == 0)
-		target_load = load_now;
-	else
-		target_load = max(cpu_load, load_now);
-
-	if (running > 1 || (idle == NOT_IDLE && running))
-		target_load = target_load * rq->prio_bias / running;
+		return load_now;
 
-	return target_load;
-}
-
-static inline unsigned long target_load(int cpu, int type)
-{
-	return __target_load(cpu, type, NOT_IDLE);
+	return max(rq->cpu_load[type-1], load_now);
 }
 
 /*
@@ -1294,9 +1197,6 @@ static int try_to_wake_up(task_t *p, unsigned int state, int sync)
 		}
 	}
 
-	if (p->last_waker_cpu != this_cpu)
-		goto out_set_cpu;
-
 	if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
 		goto out_set_cpu;
 
@@ -1367,8 +1267,6 @@ out_set_cpu:
 		cpu = task_cpu(p);
 	}
 
-	p->last_waker_cpu = this_cpu;
-
 out_activate:
 #endif /* CONFIG_SMP */
 	if (old_state == TASK_UNINTERRUPTIBLE) {
@@ -1450,12 +1348,9 @@ void fastcall sched_fork(task_t *p, int clone_flags)
 #ifdef CONFIG_SCHEDSTATS
 	memset(&p->sched_info, 0, sizeof(p->sched_info));
 #endif
-#if defined(CONFIG_SMP)
-	p->last_waker_cpu = cpu;
-#if defined(__ARCH_WANT_UNLOCKED_CTXSW)
+#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
 	p->oncpu = 0;
 #endif
-#endif
 #ifdef CONFIG_PREEMPT
 	/* Want to start with kernel preemption disabled. */
 	task_thread_info(p)->preempt_count = 1;
@@ -1530,7 +1425,7 @@ void fastcall wake_up_new_task(task_t *p, unsigned long clone_flags)
 				list_add_tail(&p->run_list, &current->run_list);
 				p->array = current->array;
 				p->array->nr_active++;
-				inc_nr_running(p, rq);
+				rq->nr_running++;
 			}
 			set_need_resched();
 		} else
@@ -1875,9 +1770,9 @@ void pull_task(runqueue_t *src_rq, prio_array_t *src_array, task_t *p,
 	       runqueue_t *this_rq, prio_array_t *this_array, int this_cpu)
 {
 	dequeue_task(p, src_array);
-	dec_nr_running(p, src_rq);
+	src_rq->nr_running--;
 	set_task_cpu(p, this_cpu);
-	inc_nr_running(p, this_rq);
+	this_rq->nr_running++;
 	enqueue_task(p, this_array);
 	p->timestamp = (p->timestamp - src_rq->timestamp_last_tick)
 				+ this_rq->timestamp_last_tick;
@@ -2056,9 +1951,9 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 
 			/* Bias balancing toward cpus of our domain */
 			if (local_group)
-				load = __target_load(i, load_idx, idle);
+				load = target_load(i, load_idx);
 			else
-				load = __source_load(i, load_idx, idle);
+				load = source_load(i, load_idx);
 
 			avg_load += load;
 		}
@@ -2171,7 +2066,7 @@ static runqueue_t *find_busiest_queue(struct sched_group *group,
 	int i;
 
 	for_each_cpu_mask(i, group->cpumask) {
-		load = __source_load(i, 0, idle);
+		load = source_load(i, 0);
 
 		if (load > max_load) {
 			max_load = load;
@@ -3571,10 +3466,8 @@ void set_user_nice(task_t *p, long nice)
 		goto out_unlock;
 	}
 	array = p->array;
-	if (array) {
+	if (array)
 		dequeue_task(p, array);
-		dec_prio_bias(rq, p->static_prio);
-	}
 
 	old_prio = p->prio;
 	new_prio = NICE_TO_PRIO(nice);
@@ -3584,7 +3477,6 @@ void set_user_nice(task_t *p, long nice)
 
 	if (array) {
 		enqueue_task(p, array);
-		inc_prio_bias(rq, p->static_prio);
 		/*
 		 * If the task increased its priority or is running and
 		 * lowered its priority, then reschedule its CPU:
@@ -4129,6 +4021,8 @@ static inline void __cond_resched(void)
 	 */
 	if (unlikely(preempt_count()))
 		return;
+	if (unlikely(system_state != SYSTEM_RUNNING))
+		return;
 	do {
 		add_preempt_count(PREEMPT_ACTIVE);
 		schedule();
@@ -4434,6 +4328,7 @@ void __devinit init_idle(task_t *idle, int cpu)
 	runqueue_t *rq = cpu_rq(cpu);
 	unsigned long flags;
 
+	idle->timestamp = sched_clock();
 	idle->sleep_avg = 0;
 	idle->array = NULL;
 	idle->prio = MAX_PRIO;
@@ -5159,7 +5054,18 @@ static void init_sched_build_groups(struct sched_group groups[], cpumask_t span,
 #define MAX_DOMAIN_DISTANCE 32
 
 static unsigned long long migration_cost[MAX_DOMAIN_DISTANCE] =
-		{ [ 0 ... MAX_DOMAIN_DISTANCE-1 ] = -1LL };
+		{ [ 0 ... MAX_DOMAIN_DISTANCE-1 ] =
+/*
+ * Architectures may override the migration cost and thus avoid
+ * boot-time calibration. Unit is nanoseconds. Mostly useful for
+ * virtualized hardware:
+ */
+#ifdef CONFIG_DEFAULT_MIGRATION_COST
+			CONFIG_DEFAULT_MIGRATION_COST
+#else
+			-1LL
+#endif
+};
 
 /*
  * Allow override of migration cost - in units of microseconds.
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 17313b99e53..1067090db6b 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -104,6 +104,8 @@ cond_syscall(sys_setreuid16);
 cond_syscall(sys_setuid16);
 cond_syscall(sys_vm86old);
 cond_syscall(sys_vm86);
+cond_syscall(compat_sys_ipc);
+cond_syscall(compat_sys_sysctl);
 
 /* arch-specific weak syscall entries */
 cond_syscall(sys_pciconfig_read);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 71dd6f62efe..32b48e8ee36 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -44,13 +44,14 @@
 #include <linux/limits.h>
 #include <linux/dcache.h>
 #include <linux/syscalls.h>
+#include <linux/nfs_fs.h>
+#include <linux/acpi.h>
 
 #include <asm/uaccess.h>
 #include <asm/processor.h>
 
-#ifdef CONFIG_ROOT_NFS
-#include <linux/nfs_fs.h>
-#endif
+extern int proc_nr_files(ctl_table *table, int write, struct file *filp,
+                     void __user *buffer, size_t *lenp, loff_t *ppos);
 
 #if defined(CONFIG_SYSCTL)
 
@@ -126,7 +127,9 @@ extern int sysctl_hz_timer;
 extern int acct_parm[];
 #endif
 
-int randomize_va_space = 1;
+#ifdef CONFIG_IA64
+extern int no_unaligned_warning;
+#endif
 
 static int parse_table(int __user *, int, void __user *, size_t __user *, void __user *, size_t,
 		       ctl_table *, void **);
@@ -640,6 +643,7 @@ static ctl_table kern_table[] = {
 		.proc_handler	= &proc_dointvec,
 	},
 #endif
+#if defined(CONFIG_MMU)
 	{
 		.ctl_name	= KERN_RANDOMIZE,
 		.procname	= "randomize_va_space",
@@ -648,6 +652,7 @@ static ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
+#endif
 #if defined(CONFIG_S390) && defined(CONFIG_SMP)
 	{
 		.ctl_name	= KERN_SPIN_RETRY,
@@ -658,6 +663,26 @@ static ctl_table kern_table[] = {
 		.proc_handler	= &proc_dointvec,
 	},
 #endif
+#ifdef CONFIG_ACPI_SLEEP
+	{
+		.ctl_name	= KERN_ACPI_VIDEO_FLAGS,
+		.procname	= "acpi_video_flags",
+		.data		= &acpi_video_flags,
+		.maxlen		= sizeof (unsigned long),
+		.mode		= 0644,
+		.proc_handler	= &proc_doulongvec_minmax,
+	},
+#endif
+#ifdef CONFIG_IA64
+	{
+		.ctl_name	= KERN_IA64_UNALIGNED,
+		.procname	= "ignore-unaligned-usertrap",
+		.data		= &no_unaligned_warning,
+		.maxlen		= sizeof (int),
+	 	.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
 	{ .ctl_name = 0 }
 };
 
@@ -921,7 +946,7 @@ static ctl_table fs_table[] = {
 		.data		= &files_stat,
 		.maxlen		= 3*sizeof(int),
 		.mode		= 0444,
-		.proc_handler	= &proc_dointvec,
+		.proc_handler	= &proc_nr_files,
 	},
 	{
 		.ctl_name	= FS_MAXFILE,
diff --git a/kernel/timer.c b/kernel/timer.c
index b9dad399467..bf7c4193b93 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -489,9 +489,21 @@ unsigned long next_timer_interrupt(void)
 	struct list_head *list;
 	struct timer_list *nte;
 	unsigned long expires;
+	unsigned long hr_expires = MAX_JIFFY_OFFSET;
+	ktime_t hr_delta;
 	tvec_t *varray[4];
 	int i, j;
 
+	hr_delta = hrtimer_get_next_event();
+	if (hr_delta.tv64 != KTIME_MAX) {
+		struct timespec tsdelta;
+		tsdelta = ktime_to_timespec(hr_delta);
+		hr_expires = timespec_to_jiffies(&tsdelta);
+		if (hr_expires < 3)
+			return hr_expires + jiffies;
+	}
+	hr_expires += jiffies;
+
 	base = &__get_cpu_var(tvec_bases);
 	spin_lock(&base->t_base.lock);
 	expires = base->timer_jiffies + (LONG_MAX >> 1);
@@ -542,6 +554,10 @@ found:
 		}
 	}
 	spin_unlock(&base->t_base.lock);
+
+	if (time_before(hr_expires, expires))
+		return hr_expires;
+
 	return expires;
 }
 #endif
@@ -717,12 +733,16 @@ static void second_overflow(void)
 #endif
 }
 
-/* in the NTP reference this is called "hardclock()" */
-static void update_wall_time_one_tick(void)
+/*
+ * Returns how many microseconds we need to add to xtime this tick
+ * in doing an adjustment requested with adjtime.
+ */
+static long adjtime_adjustment(void)
 {
-	long time_adjust_step, delta_nsec;
+	long time_adjust_step;
 
-	if ((time_adjust_step = time_adjust) != 0 ) {
+	time_adjust_step = time_adjust;
+	if (time_adjust_step) {
 		/*
 		 * We are doing an adjtime thing.  Prepare time_adjust_step to
 		 * be within bounds.  Note that a positive time_adjust means we
@@ -733,10 +753,19 @@ static void update_wall_time_one_tick(void)
 		 */
 		time_adjust_step = min(time_adjust_step, (long)tickadj);
 		time_adjust_step = max(time_adjust_step, (long)-tickadj);
+	}
+	return time_adjust_step;
+}
 
+/* in the NTP reference this is called "hardclock()" */
+static void update_wall_time_one_tick(void)
+{
+	long time_adjust_step, delta_nsec;
+
+	time_adjust_step = adjtime_adjustment();
+	if (time_adjust_step)
 		/* Reduce by this step the amount of time left  */
 		time_adjust -= time_adjust_step;
-	}
 	delta_nsec = tick_nsec + time_adjust_step * 1000;
 	/*
 	 * Advance the phase, once it gets to one microsecond, then
@@ -759,6 +788,22 @@ static void update_wall_time_one_tick(void)
 }
 
 /*
+ * Return how long ticks are at the moment, that is, how much time
+ * update_wall_time_one_tick will add to xtime next time we call it
+ * (assuming no calls to do_adjtimex in the meantime).
+ * The return value is in fixed-point nanoseconds with SHIFT_SCALE-10
+ * bits to the right of the binary point.
+ * This function has no side-effects.
+ */
+u64 current_tick_length(void)
+{
+	long delta_nsec;
+
+	delta_nsec = tick_nsec + adjtime_adjustment() * 1000;
+	return ((u64) delta_nsec << (SHIFT_SCALE - 10)) + time_adj;
+}
+
+/*
  * Using a loop looks inefficient, but "ticks" is
  * usually just one (we shouldn't be losing ticks,
  * we're doing this this way mainly for interrupt
@@ -896,6 +941,8 @@ static inline void update_times(void)
 void do_timer(struct pt_regs *regs)
 {
 	jiffies_64++;
+	/* prevent loading jiffies before storing new jiffies_64 value. */
+	barrier();
 	update_times();
 	softlockup_tick(regs);
 }
@@ -1322,10 +1369,10 @@ static inline u64 time_interpolator_get_cycles(unsigned int src)
 			return x();
 
 		case TIME_SOURCE_MMIO64	:
-			return readq((void __iomem *) time_interpolator->addr);
+			return readq_relaxed((void __iomem *)time_interpolator->addr);
 
 		case TIME_SOURCE_MMIO32	:
-			return readl((void __iomem *) time_interpolator->addr);
+			return readl_relaxed((void __iomem *)time_interpolator->addr);
 
 		default: return get_cycles();
 	}