do CPU_DEAD migrating under read_lock(tasklist) instead of write_lock_irq(tasklist)

Currently move_task_off_dead_cpu() is called under
write_lock_irq(tasklist).  This means it can't use task_lock() which is
needed to improve migrating to take task's ->cpuset into account.

Change the code to call move_task_off_dead_cpu() with irqs enabled, and
change migrate_live_tasks() to use read_lock(tasklist).

This all is a preparation for the futher changes proposed by Cliff Wickman, see
	http://marc.info/?t=117327786100003

Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Cliff Wickman <cpw@sgi.com>
Cc: Gautham R Shenoy <ego@in.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com>
Cc: Akinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 16 insertions, 6 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 0da2b2635c54..c747bc9f3c24 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -5060,6 +5060,17 @@ wait_to_die:
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
+
+static int __migrate_task_irq(struct task_struct *p, int src_cpu, int dest_cpu)
+{
+        int ret;
+
+        local_irq_disable();
+        ret = __migrate_task(p, src_cpu, dest_cpu);
+        local_irq_enable();
+        return ret;
+}
+
 /*
  * Figure out where task on dead CPU should go, use force if neccessary.
  * NOTE: interrupts should be disabled by the caller
@@ -5098,7 +5109,7 @@ static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
                                        "longer affine to cpu%d\n",
                                        p->pid, p->comm, dead_cpu);
                 }
-        } while (!__migrate_task(p, dead_cpu, dest_cpu));
+        } while (!__migrate_task_irq(p, dead_cpu, dest_cpu));
 }
 
 /*
@@ -5126,7 +5137,7 @@ static void migrate_live_tasks(int src_cpu)
 {
         struct task_struct *p, *t;
 
-        write_lock_irq(&tasklist_lock);
+        read_lock(&tasklist_lock);
 
         do_each_thread(t, p) {
                 if (p == current)
@@ -5136,7 +5147,7 @@ static void migrate_live_tasks(int src_cpu)
                         move_task_off_dead_cpu(src_cpu, p);
         } while_each_thread(t, p);
 
-        write_unlock_irq(&tasklist_lock);
+        read_unlock(&tasklist_lock);
 }
 
 /*
@@ -5214,11 +5225,10 @@ static void migrate_dead(unsigned int dead_cpu, struct task_struct *p)
          * Drop lock around migration; if someone else moves it,
          * that's OK.  No task can be added to this CPU, so iteration is
          * fine.
-         * NOTE: interrupts should be left disabled  --dev@
          */
-        spin_unlock(&rq->lock);
+        spin_unlock_irq(&rq->lock);
         move_task_off_dead_cpu(dead_cpu, p);
-        spin_lock(&rq->lock);
+        spin_lock_irq(&rq->lock);
 
         put_task_struct(p);
 }