sched/stop_machine: Fix deadlock between multiple stop_two_cpus()

Jiri reported a machine stuck in multi_cpu_stop() with
migrate_swap_stop() as function and with the following src,dst cpu
pairs: {11,  4} {13, 11} { 4, 13}

                        4       11      13

cpuM: queue(4 ,13)
                        *Ma
cpuN: queue(13,11)
                                *N      Na
                        *M              Mb
cpuO: queue(11, 4)
                        *O      Oa
                                *Nb
                        *Ob

Where *X denotes the cpu running the queueing of cpu-X and X[ab] denotes
the first/second queued work.

You'll observe the top of the workqueue for each cpu: 4,11,13 to be work
from cpus: M, O, N resp. IOW. deadlock.

Do away with the queueing trickery and introduce lg_double_lock() to
lock both CPUs and fully serialize the stop_two_cpus() callers instead
of the partial (and buggy) serialization we have now.
Reported-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20150605153023.GH19282@twins.programming.kicks-ass.netSigned-off-by: Ingo Molnar <mingo@kernel.org>

include/linux/lglock.h

@@ -52,10 +52,15 @@ struct lglock {
 	static struct lglock name = { .lock = &name ## _lock }
 
 void lg_lock_init(struct lglock *lg, char *name);
+
 void lg_local_lock(struct lglock *lg);
 void lg_local_unlock(struct lglock *lg);
 void lg_local_lock_cpu(struct lglock *lg, int cpu);
 void lg_local_unlock_cpu(struct lglock *lg, int cpu);
+
+void lg_double_lock(struct lglock *lg, int cpu1, int cpu2);
+void lg_double_unlock(struct lglock *lg, int cpu1, int cpu2);
+
 void lg_global_lock(struct lglock *lg);
 void lg_global_unlock(struct lglock *lg);
 

kernel/locking/lglock.c

@@ -60,6 +60,28 @@ void lg_local_unlock_cpu(struct lglock *lg, int cpu)
 }
 EXPORT_SYMBOL(lg_local_unlock_cpu);
 
+void lg_double_lock(struct lglock *lg, int cpu1, int cpu2)
+{
+	BUG_ON(cpu1 == cpu2);
+
+	/* lock in cpu order, just like lg_global_lock */
+	if (cpu2 < cpu1)
+		swap(cpu1, cpu2);
+
+	preempt_disable();
+	lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_);
+	arch_spin_lock(per_cpu_ptr(lg->lock, cpu1));
+	arch_spin_lock(per_cpu_ptr(lg->lock, cpu2));
+}
+
+void lg_double_unlock(struct lglock *lg, int cpu1, int cpu2)
+{
+	lock_release(&lg->lock_dep_map, 1, _RET_IP_);
+	arch_spin_unlock(per_cpu_ptr(lg->lock, cpu1));
+	arch_spin_unlock(per_cpu_ptr(lg->lock, cpu2));
+	preempt_enable();
+}
+
 void lg_global_lock(struct lglock *lg)
 {
 	int i;

kernel/stop_machine.c

@@ -211,25 +211,6 @@ static int multi_cpu_stop(void *data)
 	return err;
 }
 
-struct irq_cpu_stop_queue_work_info {
-	int cpu1;
-	int cpu2;
-	struct cpu_stop_work *work1;
-	struct cpu_stop_work *work2;
-};
-
-/*
- * This function is always run with irqs and preemption disabled.
- * This guarantees that both work1 and work2 get queued, before
- * our local migrate thread gets the chance to preempt us.
- */
-static void irq_cpu_stop_queue_work(void *arg)
-{
-	struct irq_cpu_stop_queue_work_info *info = arg;
-	cpu_stop_queue_work(info->cpu1, info->work1);
-	cpu_stop_queue_work(info->cpu2, info->work2);
-}
-
 /**
  * stop_two_cpus - stops two cpus
  * @cpu1: the cpu to stop
@@ -245,7 +226,6 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
 {
 	struct cpu_stop_done done;
 	struct cpu_stop_work work1, work2;
-	struct irq_cpu_stop_queue_work_info call_args;
 	struct multi_stop_data msdata;
 
 	preempt_disable();
@@ -262,13 +242,6 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
 		.done = &done
 	};
 
-	call_args = (struct irq_cpu_stop_queue_work_info){
-		.cpu1 = cpu1,
-		.cpu2 = cpu2,
-		.work1 = &work1,
-		.work2 = &work2,
-	};
-
 	cpu_stop_init_done(&done, 2);
 	set_state(&msdata, MULTI_STOP_PREPARE);
 
@@ -285,16 +258,11 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
 		return -ENOENT;
 	}
 
-	lg_local_lock(&stop_cpus_lock);
-	/*
-	 * Queuing needs to be done by the lowest numbered CPU, to ensure
-	 * that works are always queued in the same order on every CPU.
-	 * This prevents deadlocks.
-	 */
-	smp_call_function_single(min(cpu1, cpu2),
-				 &irq_cpu_stop_queue_work,
-				 &call_args, 1);
-	lg_local_unlock(&stop_cpus_lock);
+	lg_double_lock(&stop_cpus_lock, cpu1, cpu2);
+	cpu_stop_queue_work(cpu1, &work1);
+	cpu_stop_queue_work(cpu2, &work2);
+	lg_double_unlock(&stop_cpus_lock, cpu1, cpu2);
+
 	preempt_enable();
 
 	wait_for_completion(&done.completion);