Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/l…

…inux/kernel/git/tip/tip

Pull scheduler changes from Ingo Molnar:
 "Various optimizations, cleanups and smaller fixes - no major changes
  in scheduler behavior"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/fair: Fix the sd_parent_degenerate() code
  sched/fair: Rework and comment the group_imb code
  sched/fair: Optimize find_busiest_queue()
  sched/fair: Make group power more consistent
  sched/fair: Remove duplicate load_per_task computations
  sched/fair: Shrink sg_lb_stats and play memset games
  sched: Clean-up struct sd_lb_stat
  sched: Factor out code to should_we_balance()
  sched: Remove one division operation in find_busiest_queue()
  sched/cputime: Use this_cpu_add() in task_group_account_field()
  cpumask: Fix cpumask leak in partition_sched_domains()
  sched/x86: Optimize switch_mm() for multi-threaded workloads
  generic-ipi: Kill unnecessary variable - csd_flags
  numa: Mark __node_set() as __always_inline
  sched/fair: Cleanup: remove duplicate variable declaration
  sched/__wake_up_sync_key(): Fix nr_exclusive tasks which lead to WF_SYNC clearing

arch/x86/include/asm/mmu_context.h

@@ -45,22 +45,28 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		/* Re-load page tables */
 		load_cr3(next->pgd);
 
-		/* stop flush ipis for the previous mm */
+		/* Stop flush ipis for the previous mm */
 		cpumask_clear_cpu(cpu, mm_cpumask(prev));
 
-		/*
-		 * load the LDT, if the LDT is different:
-		 */
+		/* Load the LDT, if the LDT is different: */
 		if (unlikely(prev->context.ldt != next->context.ldt))
 			load_LDT_nolock(&next->context);
 	}
 #ifdef CONFIG_SMP
-	else {
+	  else {
 		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
 		BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
 
-		if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next))) {
-			/* We were in lazy tlb mode and leave_mm disabled
+		if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
+			/*
+			 * On established mms, the mm_cpumask is only changed
+			 * from irq context, from ptep_clear_flush() while in
+			 * lazy tlb mode, and here. Irqs are blocked during
+			 * schedule, protecting us from simultaneous changes.
+			 */
+			cpumask_set_cpu(cpu, mm_cpumask(next));
+			/*
+			 * We were in lazy tlb mode and leave_mm disabled
 			 * tlb flush IPI delivery. We must reload CR3
 			 * to make sure to use no freed page tables.
 			 */

include/linux/nodemask.h

@@ -98,8 +98,17 @@
 typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t;
 extern nodemask_t _unused_nodemask_arg_;
 
+/*
+ * The inline keyword gives the compiler room to decide to inline, or
+ * not inline a function as it sees best.  However, as these functions
+ * are called in both __init and non-__init functions, if they are not
+ * inlined we will end up with a section mis-match error (of the type of
+ * freeable items not being freed).  So we must use __always_inline here
+ * to fix the problem.  If other functions in the future also end up in
+ * this situation they will also need to be annotated as __always_inline
+ */
 #define node_set(node, dst) __node_set((node), &(dst))
-static inline void __node_set(int node, volatile nodemask_t *dstp)
+static __always_inline void __node_set(int node, volatile nodemask_t *dstp)
 {
 	set_bit(node, dstp->bits);
 }

kernel/sched/core.c

@@ -2677,7 +2677,7 @@ void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
 	if (unlikely(!q))
 		return;
 
-	if (unlikely(!nr_exclusive))
+	if (unlikely(nr_exclusive != 1))
 		wake_flags = 0;
 
 	spin_lock_irqsave(&q->lock, flags);
@@ -4964,7 +4964,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 				SD_BALANCE_FORK |
 				SD_BALANCE_EXEC |
 				SD_SHARE_CPUPOWER |
-				SD_SHARE_PKG_RESOURCES);
+				SD_SHARE_PKG_RESOURCES |
+				SD_PREFER_SIBLING);
 		if (nr_node_ids == 1)
 			pflags &= ~SD_SERIALIZE;
 	}
@@ -5173,6 +5174,13 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 			tmp->parent = parent->parent;
 			if (parent->parent)
 				parent->parent->child = tmp;
+			/*
+			 * Transfer SD_PREFER_SIBLING down in case of a
+			 * degenerate parent; the spans match for this
+			 * so the property transfers.
+			 */
+			if (parent->flags & SD_PREFER_SIBLING)
+				tmp->flags |= SD_PREFER_SIBLING;
 			destroy_sched_domain(parent, cpu);
 		} else
 			tmp = tmp->parent;
@@ -6239,16 +6247,17 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 		;
 	}
 
+	n = ndoms_cur;
 	if (doms_new == NULL) {
-		ndoms_cur = 0;
+		n = 0;
 		doms_new = &fallback_doms;
 		cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map);
 		WARN_ON_ONCE(dattr_new);
 	}
 
 	/* Build new domains */
 	for (i = 0; i < ndoms_new; i++) {
-		for (j = 0; j < ndoms_cur && !new_topology; j++) {
+		for (j = 0; j < n && !new_topology; j++) {
 			if (cpumask_equal(doms_new[i], doms_cur[j])
 			    && dattrs_equal(dattr_new, i, dattr_cur, j))
 				goto match2;

kernel/sched/cputime.c

@@ -121,7 +121,7 @@ static inline void task_group_account_field(struct task_struct *p, int index,
 	 * is the only cgroup, then nothing else should be necessary.
 	 *
 	 */
-	__get_cpu_var(kernel_cpustat).cpustat[index] += tmp;
+	__this_cpu_add(kernel_cpustat.cpustat[index], tmp);
 
 	cpuacct_account_field(p, index, tmp);
 }