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, 17 insertions, 13 deletions

diff --git a/mm/migrate.c b/mm/migrate.c
index c04692774e88..dfc8300ecbb2 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -445,6 +445,8 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
  */
 void migrate_page_copy(struct page *newpage, struct page *page)
 {
+	int cpupid;
+
 	if (PageHuge(page) || PageTransHuge(page))
 		copy_huge_page(newpage, page);
 	else
@@ -481,6 +483,13 @@ void migrate_page_copy(struct page *newpage, struct page *page)
 			__set_page_dirty_nobuffers(newpage);
  	}
 
+	/*
+	 * Copy NUMA information to the new page, to prevent over-eager
+	 * future migrations of this same page.
+	 */
+	cpupid = page_cpupid_xchg_last(page, -1);
+	page_cpupid_xchg_last(newpage, cpupid);
+
 	mlock_migrate_page(newpage, page);
 	ksm_migrate_page(newpage, page);
 	/*
@@ -1500,7 +1509,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
 					  __GFP_NOWARN) &
 					 ~GFP_IOFS, 0);
 	if (newpage)
-		page_nid_xchg_last(newpage, page_nid_last(page));
+		page_cpupid_xchg_last(newpage, page_cpupid_last(page));
 
 	return newpage;
 }
@@ -1601,7 +1610,8 @@ int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
  * node. Caller is expected to have an elevated reference count on
  * the page that will be dropped by this function before returning.
  */
-int migrate_misplaced_page(struct page *page, int node)
+int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
+			   int node)
 {
 	pg_data_t *pgdat = NODE_DATA(node);
 	int isolated;
@@ -1609,10 +1619,11 @@ int migrate_misplaced_page(struct page *page, int node)
 	LIST_HEAD(migratepages);
 
 	/*
-	 * Don't migrate pages that are mapped in multiple processes.
-	 * TODO: Handle false sharing detection instead of this hammer
+	 * Don't migrate file pages that are mapped in multiple processes
+	 * with execute permissions as they are probably shared libraries.
 	 */
-	if (page_mapcount(page) != 1)
+	if (page_mapcount(page) != 1 && page_is_file_cache(page) &&
+	    (vma->vm_flags & VM_EXEC))
 		goto out;
 
 	/*
@@ -1663,13 +1674,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	int page_lru = page_is_file_cache(page);
 
 	/*
-	 * Don't migrate pages that are mapped in multiple processes.
-	 * TODO: Handle false sharing detection instead of this hammer
-	 */
-	if (page_mapcount(page) != 1)
-		goto out_dropref;
-
-	/*
 	 * Rate-limit the amount of data that is being migrated to a node.
 	 * Optimal placement is no good if the memory bus is saturated and
 	 * all the time is being spent migrating!
@@ -1682,7 +1686,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	if (!new_page)
 		goto out_fail;
 
-	page_nid_xchg_last(new_page, page_nid_last(page));
+	page_cpupid_xchg_last(new_page, page_cpupid_last(page));
 
 	isolated = numamigrate_isolate_page(pgdat, page);
 	if (!isolated) {