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

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

   - Optimized support for Intel "Cluster-on-Die" (CoD) topologies (Dave
     Hansen)

   - Various sched/idle refinements for better idle handling (Nicolas
     Pitre, Daniel Lezcano, Chuansheng Liu, Vincent Guittot)

   - sched/numa updates and optimizations (Rik van Riel)

   - sysbench speedup (Vincent Guittot)

   - capacity calculation cleanups/refactoring (Vincent Guittot)

   - Various cleanups to thread group iteration (Oleg Nesterov)

   - Double-rq-lock removal optimization and various refactorings
     (Kirill Tkhai)

   - various sched/deadline fixes

  ... and lots of other changes"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (72 commits)
  sched/dl: Use dl_bw_of() under rcu_read_lock_sched()
  sched/fair: Delete resched_cpu() from idle_balance()
  sched, time: Fix build error with 64 bit cputime_t on 32 bit systems
  sched: Improve sysbench performance by fixing spurious active migration
  sched/x86: Fix up typo in topology detection
  x86, sched: Add new topology for multi-NUMA-node CPUs
  sched/rt: Use resched_curr() in task_tick_rt()
  sched: Use rq->rd in sched_setaffinity() under RCU read lock
  sched: cleanup: Rename 'out_unlock' to 'out_free_new_mask'
  sched: Use dl_bw_of() under RCU read lock
  sched/fair: Remove duplicate code from can_migrate_task()
  sched, mips, ia64: Remove __ARCH_WANT_UNLOCKED_CTXSW
  sched: print_rq(): Don't use tasklist_lock
  sched: normalize_rt_tasks(): Don't use _irqsave for tasklist_lock, use task_rq_lock()
  sched: Fix the task-group check in tg_has_rt_tasks()
  sched/fair: Leverage the idle state info when choosing the "idlest" cpu
  sched: Let the scheduler see CPU idle states
  sched/deadline: Fix inter- exclusive cpusets migrations
  sched/deadline: Clear dl_entity params when setscheduling to different class
  sched/numa: Kill the wrong/dead TASK_DEAD check in task_numa_fault()
  ...

1 files changed, 25 insertions, 22 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index d13f2eec4bb8..5d30019ff953 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -115,32 +115,33 @@ static void __exit_signal(struct task_struct *tsk)
 
                 if (tsk == sig->curr_target)
                         sig->curr_target = next_thread(tsk);
-                /*
-                 * Accumulate here the counters for all threads but the
-                 * group leader as they die, so they can be added into
-                 * the process-wide totals when those are taken.
-                 * The group leader stays around as a zombie as long
-                 * as there are other threads.  When it gets reaped,
-                 * the exit.c code will add its counts into these totals.
-                 * We won't ever get here for the group leader, since it
-                 * will have been the last reference on the signal_struct.
-                 */
-                task_cputime(tsk, &utime, &stime);
-                sig->utime += utime;
-                sig->stime += stime;
-                sig->gtime += task_gtime(tsk);
-                sig->min_flt += tsk->min_flt;
-                sig->maj_flt += tsk->maj_flt;
-                sig->nvcsw += tsk->nvcsw;
-                sig->nivcsw += tsk->nivcsw;
-                sig->inblock += task_io_get_inblock(tsk);
-                sig->oublock += task_io_get_oublock(tsk);
-                task_io_accounting_add(&sig->ioac, &tsk->ioac);
-                sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
         }
 
+        /*
+         * Accumulate here the counters for all threads but the group leader
+         * as they die, so they can be added into the process-wide totals
+         * when those are taken.  The group leader stays around as a zombie as
+         * long as there are other threads.  When it gets reaped, the exit.c
+         * code will add its counts into these totals.  We won't ever get here
+         * for the group leader, since it will have been the last reference on
+         * the signal_struct.
+         */
+        task_cputime(tsk, &utime, &stime);
+        write_seqlock(&sig->stats_lock);
+        sig->utime += utime;
+        sig->stime += stime;
+        sig->gtime += task_gtime(tsk);
+        sig->min_flt += tsk->min_flt;
+        sig->maj_flt += tsk->maj_flt;
+        sig->nvcsw += tsk->nvcsw;
+        sig->nivcsw += tsk->nivcsw;
+        sig->inblock += task_io_get_inblock(tsk);
+        sig->oublock += task_io_get_oublock(tsk);
+        task_io_accounting_add(&sig->ioac, &tsk->ioac);
+        sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
         sig->nr_threads--;
         __unhash_process(tsk, group_dead);
+        write_sequnlock(&sig->stats_lock);
 
         /*
          * Do this under ->siglock, we can race with another thread
@@ -1046,6 +1047,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
                 spin_lock_irq(&p->real_parent->sighand->siglock);
                 psig = p->real_parent->signal;
                 sig = p->signal;
+                write_seqlock(&psig->stats_lock);
                 psig->cutime += tgutime + sig->cutime;
                 psig->cstime += tgstime + sig->cstime;
                 psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime;
@@ -1068,6 +1070,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
                         psig->cmaxrss = maxrss;
                 task_io_accounting_add(&psig->ioac, &p->ioac);
                 task_io_accounting_add(&psig->ioac, &sig->ioac);
+                write_sequnlock(&psig->stats_lock);
                 spin_unlock_irq(&p->real_parent->sighand->siglock);
         }