stop_machine: Change cpu_stop_queue_two_works() to rely on stopper->enabled

Change cpu_stop_queue_two_works() to ensure that both CPU's have
stopper->enabled == T or fail otherwise.

This way stop_two_cpus() no longer needs to check cpu_active() to
avoid the deadlock. This patch doesn't remove these checks, we will
do this later.

Note: we need to take both stopper->lock's at the same time, but this
will also help to remove lglock from stop_machine.c, so I hope this
is fine.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: heiko.carstens@de.ibm.com
Link: http://lkml.kernel.org/r/20151008170141.GA25537@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 688d6b3..91fbb10 100644 (file)
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -219,12 +219,27 @@ static int multi_cpu_stop(void *data)
 static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
                                    int cpu2, struct cpu_stop_work *work2)
 {
+       struct cpu_stopper *stopper1 = per_cpu_ptr(&cpu_stopper, cpu1);
+       struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2);
+       int err;
+
        lg_double_lock(&stop_cpus_lock, cpu1, cpu2);
-       cpu_stop_queue_work(cpu1, work1);
-       cpu_stop_queue_work(cpu2, work2);
+       spin_lock_irq(&stopper1->lock);
+       spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING);
+
+       err = -ENOENT;
+       if (!stopper1->enabled || !stopper2->enabled)
+               goto unlock;
+
+       err = 0;
+       __cpu_stop_queue_work(stopper1, work1);
+       __cpu_stop_queue_work(stopper2, work2);
+unlock:
+       spin_unlock(&stopper2->lock);
+       spin_unlock_irq(&stopper1->lock);
        lg_double_unlock(&stop_cpus_lock, cpu1, cpu2);
 
-       return 0;
+       return err;
 }
 /**
  * stop_two_cpus - stops two cpus
@@ -261,12 +276,8 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
        set_state(&msdata, MULTI_STOP_PREPARE);
 
        /*
-        * If we observe both CPUs active we know _cpu_down() cannot yet have
-        * queued its stop_machine works and therefore ours will get executed
-        * first. Or its not either one of our CPUs that's getting unplugged,
-        * in which case we don't care.
-        *
-        * This relies on the stopper workqueues to be FIFO.
+        * We do not want to migrate to inactive CPU. FIXME: move this
+        * into migrate_swap_stop() callback.
         */
        if (!cpu_active(cpu1) || !cpu_active(cpu2)) {
                preempt_enable();