stop_machine, sched: Fix migrate_swap() vs. active_balance() deadlock

Matt reported the following deadlock:

CPU0					CPU1

schedule(.prev=migrate/0)		<fault>
  pick_next_task()			  ...
    idle_balance()			    migrate_swap()
      active_balance()			      stop_two_cpus()
						spin_lock(stopper0->lock)
						spin_lock(stopper1->lock)
						ttwu(migrate/0)
						  smp_cond_load_acquire() -- waits for schedule()
        stop_one_cpu(1)
	  spin_lock(stopper1->lock) -- waits for stopper lock

Fix this deadlock by taking the wakeups out from under stopper->lock.
This allows the active_balance() to queue the stop work and finish the
context switch, which in turn allows the wakeup from migrate_swap() to
observe the context and complete the wakeup.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reported-by: Matt Fleming <matt@codeblueprint.co.uk>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20180420095005.GH4064@hirez.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index b7591261652d3ea88811f9d2af2a3ce188fb3320..64c0291b579c9a1ce240e5eb941f2f6fcbff5f29 100644 (file)
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -21,6 +21,7 @@
 #include <linux/smpboot.h>
 #include <linux/atomic.h>
 #include <linux/nmi.h>
+#include <linux/sched/wake_q.h>
 
 /*
  * Structure to determine completion condition and record errors.  May
@@ -65,27 +66,31 @@ static void cpu_stop_signal_done(struct cpu_stop_done *done)
 }
 
 static void __cpu_stop_queue_work(struct cpu_stopper *stopper,
-                                       struct cpu_stop_work *work)
+                                       struct cpu_stop_work *work,
+                                       struct wake_q_head *wakeq)
 {
        list_add_tail(&work->list, &stopper->works);
-       wake_up_process(stopper->thread);
+       wake_q_add(wakeq, stopper->thread);
 }
 
 /* queue @work to @stopper.  if offline, @work is completed immediately */
 static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 {
        struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
+       DEFINE_WAKE_Q(wakeq);
        unsigned long flags;
        bool enabled;
 
        spin_lock_irqsave(&stopper->lock, flags);
        enabled = stopper->enabled;
        if (enabled)
-               __cpu_stop_queue_work(stopper, work);
+               __cpu_stop_queue_work(stopper, work, &wakeq);
        else if (work->done)
                cpu_stop_signal_done(work->done);
        spin_unlock_irqrestore(&stopper->lock, flags);
 
+       wake_up_q(&wakeq);
+
        return enabled;
 }
 
@@ -229,6 +234,7 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
 {
        struct cpu_stopper *stopper1 = per_cpu_ptr(&cpu_stopper, cpu1);
        struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2);
+       DEFINE_WAKE_Q(wakeq);
        int err;
 retry:
        spin_lock_irq(&stopper1->lock);
@@ -252,8 +258,8 @@ retry:
                        goto unlock;
 
        err = 0;
-       __cpu_stop_queue_work(stopper1, work1);
-       __cpu_stop_queue_work(stopper2, work2);
+       __cpu_stop_queue_work(stopper1, work1, &wakeq);
+       __cpu_stop_queue_work(stopper2, work2, &wakeq);
 unlock:
        spin_unlock(&stopper2->lock);
        spin_unlock_irq(&stopper1->lock);
@@ -263,6 +269,9 @@ unlock:
                        cpu_relax();
                goto retry;
        }
+
+       wake_up_q(&wakeq);
+
        return err;
 }
 /**