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

1 files changed, 13 insertions, 7 deletions

diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index cdbf36776106..be12c534fd59 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/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.
                          */