[PATCH 6/7] stop_machine: Remove stop_cpus_lock and lg_double_lock/unlock()

[Peter Zijlstra <peterz@infradead.org>]

[-- Attachment #1: oleg_nesterov-stop_machine-remove_stop_cpus_lock_and_lg_double_lock_unlock.patch --]
[-- Type: text/plain, Size: 5967 bytes --]

stop_two_cpus() and stop_cpus() use stop_cpus_lock to avoid the deadlock,
we need to ensure that the stopper functions can't be queued "backwards"
from one another. This doesn't look nice; if we use lglock then we do not
really need stopper->lock, cpu_stop_queue_work() could use lg_local_lock()
under local_irq_save().

OTOH it would be even better to avoid lglock in stop_machine.c and remove
lg_double_lock(). This patch adds "bool stop_cpus_in_progress" set/cleared
by queue_stop_cpus_work(), and changes cpu_stop_queue_two_works() to busy
wait until it is cleared.

queue_stop_cpus_work() sets stop_cpus_in_progress = T lockless, but after
it queues a work on CPU1 it must be visible to stop_two_cpus(CPU1, CPU2)
which checks it under the same lock. And since stop_two_cpus() holds the
2nd lock too, queue_stop_cpus_work() can not clear stop_cpus_in_progress
if it is also going to queue a work on CPU2, it needs to take that 2nd
lock to do this.

Cc: Ingo Molnar <mingo@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20151121181148.GA433@redhat.com
---
 include/linux/lglock.h  |    5 -----
 kernel/locking/lglock.c |   22 ----------------------
 kernel/stop_machine.c   |   42 ++++++++++++++++++++++++++----------------
 3 files changed, 26 insertions(+), 43 deletions(-)

--- a/include/linux/lglock.h
+++ b/include/linux/lglock.h
@@ -52,15 +52,10 @@ 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);
 
--- a/kernel/locking/lglock.c
+++ b/kernel/locking/lglock.c
@@ -60,28 +60,6 @@ void lg_local_unlock_cpu(struct lglock *
 }
 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;
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -20,7 +20,6 @@
 #include <linux/kallsyms.h>
 #include <linux/smpboot.h>
 #include <linux/atomic.h>
-#include <linux/lglock.h>
 #include <linux/nmi.h>
 
 /*
@@ -47,13 +46,9 @@ struct cpu_stopper {
 static DEFINE_PER_CPU(struct cpu_stopper, cpu_stopper);
 static bool stop_machine_initialized = false;
 
-/*
- * Avoids a race between stop_two_cpus and global stop_cpus, where
- * the stoppers could get queued up in reverse order, leading to
- * system deadlock. Using an lglock means stop_two_cpus remains
- * relatively cheap.
- */
-DEFINE_STATIC_LGLOCK(stop_cpus_lock);
+/* static data for stop_cpus */
+static DEFINE_MUTEX(stop_cpus_mutex);
+static bool stop_cpus_in_progress;
 
 static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo)
 {
@@ -230,14 +225,26 @@ static int cpu_stop_queue_two_works(int
 	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);
+retry:
 	spin_lock_irq(&stopper1->lock);
 	spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING);
 
 	err = -ENOENT;
 	if (!stopper1->enabled || !stopper2->enabled)
 		goto unlock;
+	/*
+	 * Ensure that if we race with __stop_cpus() the stoppers won't get
+	 * queued up in reverse order leading to system deadlock.
+	 *
+	 * We can't miss stop_cpus_in_progress if queue_stop_cpus_work() has
+	 * queued a work on cpu1 but not on cpu2, we hold both locks.
+	 *
+	 * It can be falsely true but it is safe to spin until it is cleared,
+	 * queue_stop_cpus_work() does everything under preempt_disable().
+	 */
+	err = -EDEADLK;
+	if (unlikely(stop_cpus_in_progress))
+			goto unlock;
 
 	err = 0;
 	__cpu_stop_queue_work(stopper1, work1);
@@ -245,8 +252,12 @@ static int cpu_stop_queue_two_works(int
 unlock:
 	spin_unlock(&stopper2->lock);
 	spin_unlock_irq(&stopper1->lock);
-	lg_double_unlock(&stop_cpus_lock, cpu1, cpu2);
 
+	if (unlikely(err == -EDEADLK)) {
+		while (stop_cpus_in_progress)
+			cpu_relax();
+		goto retry;
+	}
 	return err;
 }
 /**
@@ -316,9 +327,6 @@ bool stop_one_cpu_nowait(unsigned int cp
 	return cpu_stop_queue_work(cpu, work_buf);
 }
 
-/* static data for stop_cpus */
-static DEFINE_MUTEX(stop_cpus_mutex);
-
 static bool queue_stop_cpus_work(const struct cpumask *cpumask,
 				 cpu_stop_fn_t fn, void *arg,
 				 struct cpu_stop_done *done)
@@ -332,7 +340,8 @@ static bool queue_stop_cpus_work(const s
 	 * preempted by a stopper which might wait for other stoppers
 	 * to enter @fn which can lead to deadlock.
 	 */
-	lg_global_lock(&stop_cpus_lock);
+	preempt_disable();
+	stop_cpus_in_progress = true;
 	for_each_cpu(cpu, cpumask) {
 		work = &per_cpu(cpu_stopper.stop_work, cpu);
 		work->fn = fn;
@@ -341,7 +350,8 @@ static bool queue_stop_cpus_work(const s
 		if (cpu_stop_queue_work(cpu, work))
 			queued = true;
 	}
-	lg_global_unlock(&stop_cpus_lock);
+	stop_cpus_in_progress = false;
+	preempt_enable();
 
 	return queued;
 }