---
 init/Kconfig       |    2 
 kernel/sched/bfs.c |  134 +++++++++++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 125 insertions(+), 11 deletions(-)

Index: linux-3.7-bfs/init/Kconfig
===================================================================
--- linux-3.7-bfs.orig/init/Kconfig	2012-12-12 20:57:48.000000000 +1100
+++ linux-3.7-bfs/init/Kconfig	2012-12-12 21:19:34.585159323 +1100
@@ -366,11 +366,11 @@ config VIRT_CPU_ACCOUNTING
 	  small performance impact.  In the case of s390 or IBM POWER > 5,
 	  this also enables accounting of stolen time on logically-partitioned
 	  systems.
+endchoice
 
 config IRQ_TIME_ACCOUNTING
 	def_bool y
 
-endchoice
 
 config BSD_PROCESS_ACCT
 	bool "BSD Process Accounting"
Index: linux-3.7-bfs/kernel/sched/bfs.c
===================================================================
--- linux-3.7-bfs.orig/kernel/sched/bfs.c	2012-12-12 20:54:47.000000000 +1100
+++ linux-3.7-bfs/kernel/sched/bfs.c	2012-12-12 21:31:24.281203137 +1100
@@ -1188,7 +1188,7 @@ static inline void return_task(struct ta
 #ifdef CONFIG_SMP
 
 #ifndef tsk_is_polling
-#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
+#define tsk_is_polling(t) 0
 #endif
 
 static void resched_task(struct task_struct *p)
@@ -1927,14 +1927,9 @@ static inline void finish_task_switch(st
 	 *		Manfred Spraul <manfred@colorfullife.com>
 	 */
 	prev_state = prev->state;
+	vtime_task_switch(prev);
 	finish_arch_switch(prev);
-#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
-	local_irq_disable();
-#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
 	perf_event_task_sched_in(prev, current);
-#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
-	local_irq_enable();
-#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
 	finish_lock_switch(rq, prev);
 	finish_arch_post_lock_switch();
 
@@ -2012,6 +2007,7 @@ context_switch(struct rq *rq, struct tas
 #endif
 
 	/* Here we just switch the register state and the stack. */
+	rcu_switch(prev, next);
 	switch_to(prev, next, prev);
 
 	barrier();
@@ -2216,7 +2212,7 @@ static inline u64 irq_time_read(int cpu)
  * Called before incrementing preempt_count on {soft,}irq_enter
  * and before decrementing preempt_count on {soft,}irq_exit.
  */
-void account_system_vtime(struct task_struct *curr)
+void vtime_account(struct task_struct *curr)
 {
 	unsigned long flags;
 	s64 delta;
@@ -2246,7 +2242,7 @@ void account_system_vtime(struct task_st
 	irq_time_write_end();
 	local_irq_restore(flags);
 }
-EXPORT_SYMBOL_GPL(account_system_vtime);
+EXPORT_SYMBOL_GPL(vtime_account);
 
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
@@ -3194,6 +3190,40 @@ static void reset_rq_task(struct rq *rq,
 
 /*
  * schedule() is the main scheduler function.
+ *
+ * The main means of driving the scheduler and thus entering this function are:
+ *
+ *   1. Explicit blocking: mutex, semaphore, waitqueue, etc.
+ *
+ *   2. TIF_NEED_RESCHED flag is checked on interrupt and userspace return
+ *      paths. For example, see arch/x86/entry_64.S.
+ *
+ *      To drive preemption between tasks, the scheduler sets the flag in timer
+ *      interrupt handler scheduler_tick().
+ *
+ *   3. Wakeups don't really cause entry into schedule(). They add a
+ *      task to the run-queue and that's it.
+ *
+ *      Now, if the new task added to the run-queue preempts the current
+ *      task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets
+ *      called on the nearest possible occasion:
+ *
+ *       - If the kernel is preemptible (CONFIG_PREEMPT=y):
+ *
+ *         - in syscall or exception context, at the next outmost
+ *           preempt_enable(). (this might be as soon as the wake_up()'s
+ *           spin_unlock()!)
+ *
+ *         - in IRQ context, return from interrupt-handler to
+ *           preemptible context
+ *
+ *       - If the kernel is not preemptible (CONFIG_PREEMPT is not set)
+ *         then at the next:
+ *
+ *          - cond_resched() call
+ *          - explicit schedule() call
+ *          - return from syscall or exception to user-space
+ *          - return from interrupt-handler to user-space
  */
 asmlinkage void __sched schedule(void)
 {
@@ -3341,6 +3371,21 @@ rerun_prev_unlocked:
 }
 EXPORT_SYMBOL(schedule);
 
+#ifdef CONFIG_RCU_USER_QS
+asmlinkage void __sched schedule_user(void)
+{
+	/*
+	 * If we come here after a random call to set_need_resched(),
+	 * or we have been woken up remotely but the IPI has not yet arrived,
+	 * we haven't yet exited the RCU idle mode. Do it here manually until
+	 * we find a better solution.
+	 */
+	rcu_user_exit();
+	schedule();
+	rcu_user_enter();
+}
+#endif
+
 /**
  * schedule_preempt_disabled - called with preemption disabled
  *
@@ -3439,6 +3484,7 @@ asmlinkage void __sched preempt_schedule
 	/* Catch callers which need to be fixed */
 	BUG_ON(ti->preempt_count || !irqs_disabled());
 
+	rcu_user_exit();
 	do {
 		add_preempt_count(PREEMPT_ACTIVE);
 		local_irq_enable();
@@ -6396,7 +6442,6 @@ sd_numa_init(struct sched_domain_topolog
 					| 0*SD_BALANCE_FORK
 					| 0*SD_BALANCE_WAKE
 					| 0*SD_WAKE_AFFINE
-					| 0*SD_PREFER_LOCAL
 					| 0*SD_SHARE_CPUPOWER
 					| 0*SD_SHARE_PKG_RESOURCES
 					| 1*SD_SERIALIZE
@@ -6519,6 +6564,17 @@ static void sched_init_numa(void)
 	 * numbers.
 	 */
 
+	/*
+	 * Here, we should temporarily reset sched_domains_numa_levels to 0.
+	 * If it fails to allocate memory for array sched_domains_numa_masks[][],
+	 * the array will contain less then 'level' members. This could be
+	 * dangerous when we use it to iterate array sched_domains_numa_masks[][]
+	 * in other functions.
+	 *
+	 * We reset it to 'level' at the end of this function.
+	 */
+	sched_domains_numa_levels = 0;
+
 	sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL);
 	if (!sched_domains_numa_masks)
 		return;
@@ -6573,11 +6629,68 @@ static void sched_init_numa(void)
 	}
 
 	sched_domain_topology = tl;
+
+	sched_domains_numa_levels = level;
+}
+
+static void sched_domains_numa_masks_set(int cpu)
+{
+	int i, j;
+	int node = cpu_to_node(cpu);
+
+	for (i = 0; i < sched_domains_numa_levels; i++) {
+		for (j = 0; j < nr_node_ids; j++) {
+			if (node_distance(j, node) <= sched_domains_numa_distance[i])
+				cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]);
+		}
+	}
+}
+
+static void sched_domains_numa_masks_clear(int cpu)
+{
+	int i, j;
+	for (i = 0; i < sched_domains_numa_levels; i++) {
+		for (j = 0; j < nr_node_ids; j++)
+			cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]);
+	}
+}
+
+/*
+ * Update sched_domains_numa_masks[level][node] array when new cpus
+ * are onlined.
+ */
+static int sched_domains_numa_masks_update(struct notifier_block *nfb,
+					   unsigned long action,
+					   void *hcpu)
+{
+	int cpu = (long)hcpu;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_ONLINE:
+		sched_domains_numa_masks_set(cpu);
+		break;
+
+	case CPU_DEAD:
+		sched_domains_numa_masks_clear(cpu);
+		break;
+
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
 }
 #else
 static inline void sched_init_numa(void)
 {
 }
+
+static int sched_domains_numa_masks_update(struct notifier_block *nfb,
+					   unsigned long action,
+					   void *hcpu)
+{
+	return 0;
+}
 #endif /* CONFIG_NUMA */
 
 static int __sdt_alloc(const struct cpumask *cpu_map)
@@ -7034,6 +7147,7 @@ void __init sched_init_smp(void)
 	mutex_unlock(&sched_domains_mutex);
 	put_online_cpus();
 
+	hotcpu_notifier(sched_domains_numa_masks_update, CPU_PRI_SCHED_ACTIVE);
 	hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE);
 	hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE);