Merge branch 'x86/platform' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into stable/for-linus-3.7

* 'x86/platform' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (9690 commits)
  x86: Document x86_init.paging.pagetable_init()
  x86: xen: Cleanup and remove x86_init.paging.pagetable_setup_done()
  x86: Move paging_init() call to x86_init.paging.pagetable_init()
  x86: Rename pagetable_setup_start() to pagetable_init()
  x86: Remove base argument from x86_init.paging.pagetable_setup_start
  Linux 3.6-rc5
  HID: tpkbd: work even if the new Lenovo Keyboard driver is not configured
  Remove user-triggerable BUG from mpol_to_str
  xen/pciback: Fix proper FLR steps.
  uml: fix compile error in deliver_alarm()
  dj: memory scribble in logi_dj
  Fix order of arguments to compat_put_time[spec|val]
  xen: Use correct masking in xen_swiotlb_alloc_coherent.
  xen: fix logical error in tlb flushing
  xen/p2m: Fix one-off error in checking the P2M tree directory.
  powerpc: Don't use __put_user() in patch_instruction
  powerpc: Make sure IPI handlers see data written by IPI senders
  powerpc: Restore correct DSCR in context switch
  powerpc: Fix DSCR inheritance in copy_thread()
  powerpc: Keep thread.dscr and thread.dscr_inherit in sync
  ...

1 files changed, 109 insertions, 44 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c099cc6eebe3..c219bf8d704c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2637,8 +2637,6 @@ static int select_idle_sibling(struct task_struct *p, int target)
 	int cpu = smp_processor_id();
 	int prev_cpu = task_cpu(p);
 	struct sched_domain *sd;
-	struct sched_group *sg;
-	int i;
 
 	/*
 	 * If the task is going to be woken-up on this cpu and if it is
@@ -2655,29 +2653,17 @@ static int select_idle_sibling(struct task_struct *p, int target)
 		return prev_cpu;
 
 	/*
-	 * Otherwise, iterate the domains and find an elegible idle cpu.
+	 * Otherwise, check assigned siblings to find an elegible idle cpu.
 	 */
 	sd = rcu_dereference(per_cpu(sd_llc, target));
-	for_each_lower_domain(sd) {
-		sg = sd->groups;
-		do {
-			if (!cpumask_intersects(sched_group_cpus(sg),
-						tsk_cpus_allowed(p)))
-				goto next;
-
-			for_each_cpu(i, sched_group_cpus(sg)) {
-				if (!idle_cpu(i))
-					goto next;
-			}
 
-			target = cpumask_first_and(sched_group_cpus(sg),
-					tsk_cpus_allowed(p));
-			goto done;
-next:
-			sg = sg->next;
-		} while (sg != sd->groups);
+	for_each_lower_domain(sd) {
+		if (!cpumask_test_cpu(sd->idle_buddy, tsk_cpus_allowed(p)))
+			continue;
+		if (idle_cpu(sd->idle_buddy))
+			return sd->idle_buddy;
 	}
-done:
+
 	return target;
 }
 
@@ -3068,18 +3054,24 @@ static unsigned long __read_mostly max_load_balance_interval = HZ/10;
 
 #define LBF_ALL_PINNED	0x01
 #define LBF_NEED_BREAK	0x02
+#define LBF_SOME_PINNED 0x04
 
 struct lb_env {
 	struct sched_domain	*sd;
 
-	int			src_cpu;
 	struct rq		*src_rq;
+	int			src_cpu;
 
 	int			dst_cpu;
 	struct rq		*dst_rq;
 
+	struct cpumask		*dst_grpmask;
+	int			new_dst_cpu;
 	enum cpu_idle_type	idle;
 	long			imbalance;
+	/* The set of CPUs under consideration for load-balancing */
+	struct cpumask		*cpus;
+
 	unsigned int		flags;
 
 	unsigned int		loop;
@@ -3145,9 +3137,31 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	 * 3) are cache-hot on their current CPU.
 	 */
 	if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) {
+		int new_dst_cpu;
+
 		schedstat_inc(p, se.statistics.nr_failed_migrations_affine);
+
+		/*
+		 * Remember if this task can be migrated to any other cpu in
+		 * our sched_group. We may want to revisit it if we couldn't
+		 * meet load balance goals by pulling other tasks on src_cpu.
+		 *
+		 * Also avoid computing new_dst_cpu if we have already computed
+		 * one in current iteration.
+		 */
+		if (!env->dst_grpmask || (env->flags & LBF_SOME_PINNED))
+			return 0;
+
+		new_dst_cpu = cpumask_first_and(env->dst_grpmask,
+						tsk_cpus_allowed(p));
+		if (new_dst_cpu < nr_cpu_ids) {
+			env->flags |= LBF_SOME_PINNED;
+			env->new_dst_cpu = new_dst_cpu;
+		}
 		return 0;
 	}
+
+	/* Record that we found atleast one task that could run on dst_cpu */
 	env->flags &= ~LBF_ALL_PINNED;
 
 	if (task_running(env->src_rq, p)) {
@@ -3373,6 +3387,14 @@ static int tg_load_down(struct task_group *tg, void *data)
 
 static void update_h_load(long cpu)
 {
+	struct rq *rq = cpu_rq(cpu);
+	unsigned long now = jiffies;
+
+	if (rq->h_load_throttle == now)
+		return;
+
+	rq->h_load_throttle = now;
+
 	rcu_read_lock();
 	walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
 	rcu_read_unlock();
@@ -3642,8 +3664,7 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
  */
 static inline void update_sg_lb_stats(struct lb_env *env,
 			struct sched_group *group, int load_idx,
-			int local_group, const struct cpumask *cpus,
-			int *balance, struct sg_lb_stats *sgs)
+			int local_group, int *balance, struct sg_lb_stats *sgs)
 {
 	unsigned long nr_running, max_nr_running, min_nr_running;
 	unsigned long load, max_cpu_load, min_cpu_load;
@@ -3660,7 +3681,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 	max_nr_running = 0;
 	min_nr_running = ~0UL;
 
-	for_each_cpu_and(i, sched_group_cpus(group), cpus) {
+	for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
 		struct rq *rq = cpu_rq(i);
 
 		nr_running = rq->nr_running;
@@ -3789,8 +3810,7 @@ static bool update_sd_pick_busiest(struct lb_env *env,
  * @sds: variable to hold the statistics for this sched_domain.
  */
 static inline void update_sd_lb_stats(struct lb_env *env,
-				      const struct cpumask *cpus,
-				      int *balance, struct sd_lb_stats *sds)
+					int *balance, struct sd_lb_stats *sds)
 {
 	struct sched_domain *child = env->sd->child;
 	struct sched_group *sg = env->sd->groups;
@@ -3807,8 +3827,7 @@ static inline void update_sd_lb_stats(struct lb_env *env,
 
 		local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg));
 		memset(&sgs, 0, sizeof(sgs));
-		update_sg_lb_stats(env, sg, load_idx, local_group,
-				   cpus, balance, &sgs);
+		update_sg_lb_stats(env, sg, load_idx, local_group, balance, &sgs);
 
 		if (local_group && !(*balance))
 			return;
@@ -4044,7 +4063,6 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
  * to restore balance.
  *
  * @env: The load balancing environment.
- * @cpus: The set of CPUs under consideration for load-balancing.
  * @balance: Pointer to a variable indicating if this_cpu
  *	is the appropriate cpu to perform load balancing at this_level.
  *
@@ -4054,7 +4072,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
  *		   put to idle by rebalancing its tasks onto our group.
  */
 static struct sched_group *
-find_busiest_group(struct lb_env *env, const struct cpumask *cpus, int *balance)
+find_busiest_group(struct lb_env *env, int *balance)
 {
 	struct sd_lb_stats sds;
 
@@ -4064,7 +4082,7 @@ find_busiest_group(struct lb_env *env, const struct cpumask *cpus, int *balance)
 	 * Compute the various statistics relavent for load balancing at
 	 * this level.
 	 */
-	update_sd_lb_stats(env, cpus, balance, &sds);
+	update_sd_lb_stats(env, balance, &sds);
 
 	/*
 	 * this_cpu is not the appropriate cpu to perform load balancing at
@@ -4144,8 +4162,7 @@ ret:
  * find_busiest_queue - find the busiest runqueue among the cpus in group.
  */
 static struct rq *find_busiest_queue(struct lb_env *env,
-				     struct sched_group *group,
-				     const struct cpumask *cpus)
+				     struct sched_group *group)
 {
 	struct rq *busiest = NULL, *rq;
 	unsigned long max_load = 0;
@@ -4160,7 +4177,7 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 		if (!capacity)
 			capacity = fix_small_capacity(env->sd, group);
 
-		if (!cpumask_test_cpu(i, cpus))
+		if (!cpumask_test_cpu(i, env->cpus))
 			continue;
 
 		rq = cpu_rq(i);
@@ -4227,7 +4244,8 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 			struct sched_domain *sd, enum cpu_idle_type idle,
 			int *balance)
 {
-	int ld_moved, active_balance = 0;
+	int ld_moved, cur_ld_moved, active_balance = 0;
+	int lb_iterations, max_lb_iterations;
 	struct sched_group *group;
 	struct rq *busiest;
 	unsigned long flags;
@@ -4237,16 +4255,19 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 		.sd		= sd,
 		.dst_cpu	= this_cpu,
 		.dst_rq		= this_rq,
+		.dst_grpmask    = sched_group_cpus(sd->groups),
 		.idle		= idle,
 		.loop_break	= sched_nr_migrate_break,
+		.cpus		= cpus,
 	};
 
 	cpumask_copy(cpus, cpu_active_mask);
+	max_lb_iterations = cpumask_weight(env.dst_grpmask);
 
 	schedstat_inc(sd, lb_count[idle]);
 
 redo:
-	group = find_busiest_group(&env, cpus, balance);
+	group = find_busiest_group(&env, balance);
 
 	if (*balance == 0)
 		goto out_balanced;
@@ -4256,7 +4277,7 @@ redo:
 		goto out_balanced;
 	}
 
-	busiest = find_busiest_queue(&env, group, cpus);
+	busiest = find_busiest_queue(&env, group);
 	if (!busiest) {
 		schedstat_inc(sd, lb_nobusyq[idle]);
 		goto out_balanced;
@@ -4267,6 +4288,7 @@ redo:
 	schedstat_add(sd, lb_imbalance[idle], env.imbalance);
 
 	ld_moved = 0;
+	lb_iterations = 1;
 	if (busiest->nr_running > 1) {
 		/*
 		 * Attempt to move tasks. If find_busiest_group has found
@@ -4279,12 +4301,17 @@ redo:
 		env.src_rq    = busiest;
 		env.loop_max  = min(sysctl_sched_nr_migrate, busiest->nr_running);
 
+		update_h_load(env.src_cpu);
 more_balance:
 		local_irq_save(flags);
 		double_rq_lock(this_rq, busiest);
-		if (!env.loop)
-			update_h_load(env.src_cpu);
-		ld_moved += move_tasks(&env);
+
+		/*
+		 * cur_ld_moved - load moved in current iteration
+		 * ld_moved     - cumulative load moved across iterations
+		 */
+		cur_ld_moved = move_tasks(&env);
+		ld_moved += cur_ld_moved;
 		double_rq_unlock(this_rq, busiest);
 		local_irq_restore(flags);
 
@@ -4296,14 +4323,52 @@ more_balance:
 		/*
 		 * some other cpu did the load balance for us.
 		 */
-		if (ld_moved && this_cpu != smp_processor_id())
-			resched_cpu(this_cpu);
+		if (cur_ld_moved && env.dst_cpu != smp_processor_id())
+			resched_cpu(env.dst_cpu);
+
+		/*
+		 * Revisit (affine) tasks on src_cpu that couldn't be moved to
+		 * us and move them to an alternate dst_cpu in our sched_group
+		 * where they can run. The upper limit on how many times we
+		 * iterate on same src_cpu is dependent on number of cpus in our
+		 * sched_group.
+		 *
+		 * This changes load balance semantics a bit on who can move
+		 * load to a given_cpu. In addition to the given_cpu itself
+		 * (or a ilb_cpu acting on its behalf where given_cpu is
+		 * nohz-idle), we now have balance_cpu in a position to move
+		 * load to given_cpu. In rare situations, this may cause
+		 * conflicts (balance_cpu and given_cpu/ilb_cpu deciding
+		 * _independently_ and at _same_ time to move some load to
+		 * given_cpu) causing exceess load to be moved to given_cpu.
+		 * This however should not happen so much in practice and
+		 * moreover subsequent load balance cycles should correct the
+		 * excess load moved.
+		 */
+		if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0 &&
+				lb_iterations++ < max_lb_iterations) {
+
+			this_rq		 = cpu_rq(env.new_dst_cpu);
+			env.dst_rq	 = this_rq;
+			env.dst_cpu	 = env.new_dst_cpu;
+			env.flags	&= ~LBF_SOME_PINNED;
+			env.loop	 = 0;
+			env.loop_break	 = sched_nr_migrate_break;
+			/*
+			 * Go back to "more_balance" rather than "redo" since we
+			 * need to continue with same src_cpu.
+			 */
+			goto more_balance;
+		}
 
 		/* All tasks on this runqueue were pinned by CPU affinity */
 		if (unlikely(env.flags & LBF_ALL_PINNED)) {
 			cpumask_clear_cpu(cpu_of(busiest), cpus);
-			if (!cpumask_empty(cpus))
+			if (!cpumask_empty(cpus)) {
+				env.loop = 0;
+				env.loop_break = sched_nr_migrate_break;
 				goto redo;
+			}
 			goto out_balanced;
 		}
 	}