3 files changed, 19 insertions, 9 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index dfb924ffe65b..fe28dc282eae 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1886,7 +1886,7 @@ retry:
         restart->futex.val = val;
         restart->futex.time = abs_time->tv64;
         restart->futex.bitset = bitset;
-        restart->futex.flags = flags;
+        restart->futex.flags = flags | FLAGS_HAS_TIMEOUT;
 
         ret = -ERESTART_RESTARTBLOCK;
 
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 27960f114efd..8e81a9860a0d 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -364,6 +364,7 @@ void perf_cgroup_switch(struct task_struct *task, int mode)
                         }
 
                         if (mode & PERF_CGROUP_SWIN) {
+                                WARN_ON_ONCE(cpuctx->cgrp);
                                 /* set cgrp before ctxsw in to
                                  * allow event_filter_match() to not
                                  * have to pass task around
@@ -2423,6 +2424,14 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx)
         if (!ctx || !ctx->nr_events)
                 goto out;
 
+        /*
+         * We must ctxsw out cgroup events to avoid conflict
+         * when invoking perf_task_event_sched_in() later on
+         * in this function. Otherwise we end up trying to
+         * ctxswin cgroup events which are already scheduled
+         * in.
+         */
+        perf_cgroup_sched_out(current);
         task_ctx_sched_out(ctx, EVENT_ALL);
 
         raw_spin_lock(&ctx->lock);
@@ -2447,6 +2456,9 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx)
 
         raw_spin_unlock(&ctx->lock);
 
+        /*
+         * Also calls ctxswin for cgroup events, if any:
+         */
         perf_event_context_sched_in(ctx, ctx->task);
 out:
         local_irq_restore(flags);
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 7f00772e57c9..6fa833ab2cb8 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -2104,21 +2104,20 @@ balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
               enum cpu_idle_type idle, int *all_pinned,
               int *this_best_prio, struct cfs_rq *busiest_cfs_rq)
 {
-        int loops = 0, pulled = 0, pinned = 0;
+        int loops = 0, pulled = 0;
         long rem_load_move = max_load_move;
         struct task_struct *p, *n;
 
         if (max_load_move == 0)
                 goto out;
 
-        pinned = 1;
-
         list_for_each_entry_safe(p, n, &busiest_cfs_rq->tasks, se.group_node) {
                 if (loops++ > sysctl_sched_nr_migrate)
                         break;
 
                 if ((p->se.load.weight >> 1) > rem_load_move ||
-                    !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned))
+                    !can_migrate_task(p, busiest, this_cpu, sd, idle,
+                                      all_pinned))
                         continue;
 
                 pull_task(busiest, p, this_rq, this_cpu);
@@ -2153,9 +2152,6 @@ out:
          */
         schedstat_add(sd, lb_gained[idle], pulled);
 
-        if (all_pinned)
-                *all_pinned = pinned;
-
         return max_load_move - rem_load_move;
 }
 
@@ -3127,6 +3123,8 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
         if (!sds.busiest || sds.busiest_nr_running == 0)
                 goto out_balanced;
 
+        sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr;
+
         /*
          * If the busiest group is imbalanced the below checks don't
          * work because they assumes all things are equal, which typically
@@ -3151,7 +3149,6 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
          * Don't pull any tasks if this group is already above the domain
          * average load.
          */
-        sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr;
         if (sds.this_load >= sds.avg_load)
                 goto out_balanced;
 
@@ -3340,6 +3337,7 @@ redo:
                  * still unbalanced. ld_moved simply stays zero, so it is
                  * correctly treated as an imbalance.
                  */
+                all_pinned = 1;
                 local_irq_save(flags);
                 double_rq_lock(this_rq, busiest);
                 ld_moved = move_tasks(this_rq, this_cpu, busiest,