1 files changed, 30 insertions, 5 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0b069bf3e708..ef2b104b254c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -726,6 +726,11 @@ static void update_curr(struct cfs_rq *cfs_rq)
         account_cfs_rq_runtime(cfs_rq, delta_exec);
 }
 
+static void update_curr_fair(struct rq *rq)
+{
+        update_curr(cfs_rq_of(&rq->curr->se));
+}
+
 static inline void
 update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
@@ -828,11 +833,12 @@ static unsigned int task_nr_scan_windows(struct task_struct *p)
 
 static unsigned int task_scan_min(struct task_struct *p)
 {
+        unsigned int scan_size = ACCESS_ONCE(sysctl_numa_balancing_scan_size);
         unsigned int scan, floor;
         unsigned int windows = 1;
 
-        if (sysctl_numa_balancing_scan_size < MAX_SCAN_WINDOW)
-                windows = MAX_SCAN_WINDOW / sysctl_numa_balancing_scan_size;
+        if (scan_size < MAX_SCAN_WINDOW)
+                windows = MAX_SCAN_WINDOW / scan_size;
         floor = 1000 / windows;
 
         scan = sysctl_numa_balancing_scan_period_min / task_nr_scan_windows(p);
@@ -1164,9 +1170,26 @@ static void task_numa_compare(struct task_numa_env *env,
         long moveimp = imp;
 
         rcu_read_lock();
-        cur = ACCESS_ONCE(dst_rq->curr);
-        if (cur->pid == 0) /* idle */
+
+        raw_spin_lock_irq(&dst_rq->lock);
+        cur = dst_rq->curr;
+        /*
+         * No need to move the exiting task, and this ensures that ->curr
+         * wasn't reaped and thus get_task_struct() in task_numa_assign()
+         * is safe under RCU read lock.
+         * Note that rcu_read_lock() itself can't protect from the final
+         * put_task_struct() after the last schedule().
+         */
+        if ((cur->flags & PF_EXITING) || is_idle_task(cur))
                 cur = NULL;
+        raw_spin_unlock_irq(&dst_rq->lock);
+
+        /*
+         * Because we have preemption enabled we can get migrated around and
+         * end try selecting ourselves (current == env->p) as a swap candidate.
+         */
+        if (cur == env->p)
+                goto unlock;
 
         /*
          * "imp" is the fault differential for the source task between the
@@ -1520,7 +1543,7 @@ static void update_task_scan_period(struct task_struct *p,
                  * scanning faster if shared accesses dominate as it may
                  * simply bounce migrations uselessly
                  */
-                ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared));
+                ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared + 1));
                 diff = (diff * ratio) / NUMA_PERIOD_SLOTS;
         }
 
@@ -7938,6 +7961,8 @@ const struct sched_class fair_sched_class = {
 
         .get_rr_interval        = get_rr_interval_fair,
 
+        .update_curr            = update_curr_fair,
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
         .task_move_group        = task_move_group_fair,
 #endif