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

Pull scheduler changes from Ingo Molnar:
 "The main changes in this cycle are:

   - (much) improved CONFIG_NUMA_BALANCING support from Mel Gorman, Rik
     van Riel, Peter Zijlstra et al.  Yay!

   - optimize preemption counter handling: merge the NEED_RESCHED flag
     into the preempt_count variable, by Peter Zijlstra.

   - wait.h fixes and code reorganization from Peter Zijlstra

   - cfs_bandwidth fixes from Ben Segall

   - SMP load-balancer cleanups from Peter Zijstra

   - idle balancer improvements from Jason Low

   - other fixes and cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (129 commits)
  ftrace, sched: Add TRACE_FLAG_PREEMPT_RESCHED
  stop_machine: Fix race between stop_two_cpus() and stop_cpus()
  sched: Remove unnecessary iteration over sched domains to update nr_busy_cpus
  sched: Fix asymmetric scheduling for POWER7
  sched: Move completion code from core.c to completion.c
  sched: Move wait code from core.c to wait.c
  sched: Move wait.c into kernel/sched/
  sched/wait: Fix __wait_event_interruptible_lock_irq_timeout()
  sched: Avoid throttle_cfs_rq() racing with period_timer stopping
  sched: Guarantee new group-entities always have weight
  sched: Fix hrtimer_cancel()/rq->lock deadlock
  sched: Fix cfs_bandwidth misuse of hrtimer_expires_remaining
  sched: Fix race on toggling cfs_bandwidth_used
  sched: Remove extra put_online_cpus() inside sched_setaffinity()
  sched/rt: Fix task_tick_rt() comment
  sched/wait: Fix build breakage
  sched/wait: Introduce prepare_to_wait_event()
  sched/wait: Add ___wait_cond_timeout() to wait_event*_timeout() too
  sched: Remove get_online_cpus() usage
  sched: Fix race in migrate_swap_stop()
  ...

1 files changed, 19 insertions, 46 deletions

diff --git a/mm/mprotect.c b/mm/mprotect.c
index 412ba2b7326a..a597f2ffcd6f 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -37,14 +37,12 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 
 static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
                 unsigned long addr, unsigned long end, pgprot_t newprot,
-                int dirty_accountable, int prot_numa, bool *ret_all_same_node)
+                int dirty_accountable, int prot_numa)
 {
         struct mm_struct *mm = vma->vm_mm;
         pte_t *pte, oldpte;
         spinlock_t *ptl;
         unsigned long pages = 0;
-        bool all_same_node = true;
-        int last_nid = -1;
 
         pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
         arch_enter_lazy_mmu_mode();
@@ -63,15 +61,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 
                                 page = vm_normal_page(vma, addr, oldpte);
                                 if (page) {
-                                        int this_nid = page_to_nid(page);
-                                        if (last_nid == -1)
-                                                last_nid = this_nid;
-                                        if (last_nid != this_nid)
-                                                all_same_node = false;
-
-                                        /* only check non-shared pages */
-                                        if (!pte_numa(oldpte) &&
-                                            page_mapcount(page) == 1) {
+                                        if (!pte_numa(oldpte)) {
                                                 ptent = pte_mknuma(ptent);
                                                 updated = true;
                                         }
@@ -104,33 +94,17 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
                                 if (pte_swp_soft_dirty(oldpte))
                                         newpte = pte_swp_mksoft_dirty(newpte);
                                 set_pte_at(mm, addr, pte, newpte);
+
+                                pages++;
                         }
-                        pages++;
                 }
         } while (pte++, addr += PAGE_SIZE, addr != end);
         arch_leave_lazy_mmu_mode();
         pte_unmap_unlock(pte - 1, ptl);
 
-        *ret_all_same_node = all_same_node;
         return pages;
 }
 
-#ifdef CONFIG_NUMA_BALANCING
-static inline void change_pmd_protnuma(struct mm_struct *mm, unsigned long addr,
-                                       pmd_t *pmd)
-{
-        spin_lock(&mm->page_table_lock);
-        set_pmd_at(mm, addr & PMD_MASK, pmd, pmd_mknuma(*pmd));
-        spin_unlock(&mm->page_table_lock);
-}
-#else
-static inline void change_pmd_protnuma(struct mm_struct *mm, unsigned long addr,
-                                       pmd_t *pmd)
-{
-        BUG();
-}
-#endif /* CONFIG_NUMA_BALANCING */
-
 static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
                 pud_t *pud, unsigned long addr, unsigned long end,
                 pgprot_t newprot, int dirty_accountable, int prot_numa)
@@ -138,34 +112,33 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
         pmd_t *pmd;
         unsigned long next;
         unsigned long pages = 0;
-        bool all_same_node;
 
         pmd = pmd_offset(pud, addr);
         do {
+                unsigned long this_pages;
+
                 next = pmd_addr_end(addr, end);
                 if (pmd_trans_huge(*pmd)) {
                         if (next - addr != HPAGE_PMD_SIZE)
                                 split_huge_page_pmd(vma, addr, pmd);
-                        else if (change_huge_pmd(vma, pmd, addr, newprot,
-                                                 prot_numa)) {
-                                pages++;
-                                continue;
+                        else {
+                                int nr_ptes = change_huge_pmd(vma, pmd, addr,
+                                                newprot, prot_numa);
+
+                                if (nr_ptes) {
+                                        if (nr_ptes == HPAGE_PMD_NR)
+                                                pages++;
+
+                                        continue;
+                                }
                         }
                         /* fall through */
                 }
                 if (pmd_none_or_clear_bad(pmd))
                         continue;
-                pages += change_pte_range(vma, pmd, addr, next, newprot,
-                                 dirty_accountable, prot_numa, &all_same_node);
-
-                /*
-                 * If we are changing protections for NUMA hinting faults then
-                 * set pmd_numa if the examined pages were all on the same
-                 * node. This allows a regular PMD to be handled as one fault
-                 * and effectively batches the taking of the PTL
-                 */
-                if (prot_numa && all_same_node)
-                        change_pmd_protnuma(vma->vm_mm, addr, pmd);
+                this_pages = change_pte_range(vma, pmd, addr, next, newprot,
+                                 dirty_accountable, prot_numa);
+                pages += this_pages;
         } while (pmd++, addr = next, addr != end);
 
         return pages;