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

Pull scheduler changes from Ingo Molnar:
 "Bigger changes:

   - sched/idle restructuring: they are WIP preparation for deeper
     integration between the scheduler and idle state selection, by
     Nicolas Pitre.

   - add NUMA scheduling pseudo-interleaving, by Rik van Riel.

   - optimize cgroup context switches, by Peter Zijlstra.

   - RT scheduling enhancements, by Thomas Gleixner.

  The rest is smaller changes, non-urgnt fixes and cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (68 commits)
  sched: Clean up the task_hot() function
  sched: Remove double calculation in fix_small_imbalance()
  sched: Fix broken setscheduler()
  sparc64, sched: Remove unused sparc64_multi_core
  sched: Remove unused mc_capable() and smt_capable()
  sched/numa: Move task_numa_free() to __put_task_struct()
  sched/fair: Fix endless loop in idle_balance()
  sched/core: Fix endless loop in pick_next_task()
  sched/fair: Push down check for high priority class task into idle_balance()
  sched/rt: Fix picking RT and DL tasks from empty queue
  trace: Replace hardcoding of 19 with MAX_NICE
  sched: Guarantee task priority in pick_next_task()
  sched/idle: Remove stale old file
  sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED
  cpuidle/arm64: Remove redundant cpuidle_idle_call()
  cpuidle/powernv: Remove redundant cpuidle_idle_call()
  sched, nohz: Exclude isolated cores from load balancing
  sched: Fix select_task_rq_fair() description comments
  workqueue: Replace hardcoding of -20 and 19 with MIN_NICE and MAX_NICE
  sys: Replace hardcoding of -20 and 19 with MIN_NICE and MAX_NICE
  ...

1 files changed, 1 insertions, 73 deletions

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index ae3c8f3595d4..f520b9da9c1f 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2301,35 +2301,6 @@ static void sp_free(struct sp_node *n)
         kmem_cache_free(sn_cache, n);
 }
 
-#ifdef CONFIG_NUMA_BALANCING
-static bool numa_migrate_deferred(struct task_struct *p, int last_cpupid)
-{
-        /* Never defer a private fault */
-        if (cpupid_match_pid(p, last_cpupid))
-                return false;
-
-        if (p->numa_migrate_deferred) {
-                p->numa_migrate_deferred--;
-                return true;
-        }
-        return false;
-}
-
-static inline void defer_numa_migrate(struct task_struct *p)
-{
-        p->numa_migrate_deferred = sysctl_numa_balancing_migrate_deferred;
-}
-#else
-static inline bool numa_migrate_deferred(struct task_struct *p, int last_cpupid)
-{
-        return false;
-}
-
-static inline void defer_numa_migrate(struct task_struct *p)
-{
-}
-#endif /* CONFIG_NUMA_BALANCING */
-
 /**
  * mpol_misplaced - check whether current page node is valid in policy
  *
@@ -2403,52 +2374,9 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
 
         /* Migrate the page towards the node whose CPU is referencing it */
         if (pol->flags & MPOL_F_MORON) {
-                int last_cpupid;
-                int this_cpupid;
-
                 polnid = thisnid;
-                this_cpupid = cpu_pid_to_cpupid(thiscpu, current->pid);
-
-                /*
-                 * Multi-stage node selection is used in conjunction
-                 * with a periodic migration fault to build a temporal
-                 * task<->page relation. By using a two-stage filter we
-                 * remove short/unlikely relations.
-                 *
-                 * Using P(p) ~ n_p / n_t as per frequentist
-                 * probability, we can equate a task's usage of a
-                 * particular page (n_p) per total usage of this
-                 * page (n_t) (in a given time-span) to a probability.
-                 *
-                 * Our periodic faults will sample this probability and
-                 * getting the same result twice in a row, given these
-                 * samples are fully independent, is then given by
-                 * P(n)^2, provided our sample period is sufficiently
-                 * short compared to the usage pattern.
-                 *
-                 * This quadric squishes small probabilities, making
-                 * it less likely we act on an unlikely task<->page
-                 * relation.
-                 */
-                last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
-                if (!cpupid_pid_unset(last_cpupid) && cpupid_to_nid(last_cpupid) != thisnid) {
 
-                        /* See sysctl_numa_balancing_migrate_deferred comment */
-                        if (!cpupid_match_pid(current, last_cpupid))
-                                defer_numa_migrate(current);
-
-                        goto out;
-                }
-
-                /*
-                 * The quadratic filter above reduces extraneous migration
-                 * of shared pages somewhat. This code reduces it even more,
-                 * reducing the overhead of page migrations of shared pages.
-                 * This makes workloads with shared pages rely more on
-                 * "move task near its memory", and less on "move memory
-                 * towards its task", which is exactly what we want.
-                 */
-                if (numa_migrate_deferred(current, last_cpupid))
+                if (!should_numa_migrate_memory(current, page, curnid, thiscpu))
                         goto out;
         }