[PATCH RT 10/17] kernel/stop_machine: partly revert "stop_machine: Use raw spinlocks"

[Steven Rostedt]

3.14.61-rt64-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>

With completion using swait and so rawlocks we don't need this anymore.
Further, bisect thinks this patch is responsible for:

|BUG: unable to handle kernel NULL pointer dereference at           (null)
|IP: [<ffffffff81082123>] sched_cpu_active+0x53/0x70
|PGD 0
|Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
|Dumping ftrace buffer:
|   (ftrace buffer empty)
|Modules linked in:
|CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.4.1+ #330
|Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS Debian-1.8.2-1 04/01/2014
|task: ffff88013ae64b00 ti: ffff88013ae74000 task.ti: ffff88013ae74000
|RIP: 0010:[<ffffffff81082123>]  [<ffffffff81082123>] sched_cpu_active+0x53/0x70
|RSP: 0000:ffff88013ae77eb8  EFLAGS: 00010082
|RAX: 0000000000000001 RBX: ffffffff81c2cf20 RCX: 0000001050fb52fb
|RDX: 0000001050fb52fb RSI: 000000105117ca1e RDI: 00000000001c7723
|RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000001
|R10: 0000000000000000 R11: 0000000000000001 R12: 00000000ffffffff
|R13: ffffffff81c2cee0 R14: 0000000000000000 R15: 0000000000000001
|FS:  0000000000000000(0000) GS:ffff88013b200000(0000) knlGS:0000000000000000
|CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
|CR2: 0000000000000000 CR3: 0000000001c09000 CR4: 00000000000006e0
|Stack:
| ffffffff810c446d ffff88013ae77f00 ffffffff8107d8dd 000000000000000a
| 0000000000000001 0000000000000000 0000000000000000 0000000000000000
| 0000000000000000 ffff88013ae77f10 ffffffff8107d90e ffff88013ae77f20
|Call Trace:
| [<ffffffff810c446d>] ? debug_lockdep_rcu_enabled+0x1d/0x20
| [<ffffffff8107d8dd>] ? notifier_call_chain+0x5d/0x80
| [<ffffffff8107d90e>] ? __raw_notifier_call_chain+0xe/0x10
| [<ffffffff810598a3>] ? cpu_notify+0x23/0x40
| [<ffffffff8105a7b8>] ? notify_cpu_starting+0x28/0x30

during hotplug. The rawlocks need to remain however.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
Signed-off-by: Steven Rostedt <rostedt@xxxxxxxxxxx>
---
 kernel/stop_machine.c | 40 ++++++++--------------------------------
 1 file changed, 8 insertions(+), 32 deletions(-)

diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index bcbae9c962a9..f2731ce8308e 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -30,7 +30,7 @@ struct cpu_stop_done {
 	atomic_t		nr_todo;	/* nr left to execute */
 	bool			executed;	/* actually executed? */
 	int			ret;		/* collected return value */
-	struct task_struct	*waiter;	/* woken when nr_todo reaches 0 */
+	struct completion	completion;	/* fired if nr_todo reaches 0 */
 };
 
 /* the actual stopper, one per every possible cpu, enabled on online cpus */
@@ -56,7 +56,7 @@ static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo)
 {
 	memset(done, 0, sizeof(*done));
 	atomic_set(&done->nr_todo, nr_todo);
-	done->waiter = current;
+	init_completion(&done->completion);
 }
 
 /* signal completion unless @done is NULL */
@@ -65,10 +65,8 @@ static void cpu_stop_signal_done(struct cpu_stop_done *done, bool executed)
 	if (done) {
 		if (executed)
 			done->executed = true;
-		if (atomic_dec_and_test(&done->nr_todo)) {
-			wake_up_process(done->waiter);
-			done->waiter = NULL;
-		}
+		if (atomic_dec_and_test(&done->nr_todo))
+			complete(&done->completion);
 	}
 }
 
@@ -91,22 +89,6 @@ static void cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 	raw_spin_unlock_irqrestore(&stopper->lock, flags);
 }
 
-static void wait_for_stop_done(struct cpu_stop_done *done)
-{
-	set_current_state(TASK_UNINTERRUPTIBLE);
-	while (atomic_read(&done->nr_todo)) {
-		schedule();
-		set_current_state(TASK_UNINTERRUPTIBLE);
-	}
-	/*
-	 * We need to wait until cpu_stop_signal_done() has cleared
-	 * done->waiter.
-	 */
-	while (done->waiter)
-		cpu_relax();
-	set_current_state(TASK_RUNNING);
-}
-
 /**
  * stop_one_cpu - stop a cpu
  * @cpu: cpu to stop
@@ -138,7 +120,7 @@ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
 
 	cpu_stop_init_done(&done, 1);
 	cpu_stop_queue_work(cpu, &work);
-	wait_for_stop_done(&done);
+	wait_for_completion(&done.completion);
 	return done.executed ? done.ret : -ENOENT;
 }
 
@@ -315,7 +297,7 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
 	lg_local_unlock(&stop_cpus_lock);
 	preempt_enable_nort();
 
-	wait_for_stop_done(&done);
+	wait_for_completion(&done.completion);
 
 	return done.executed ? done.ret : -ENOENT;
 }
@@ -379,7 +361,7 @@ static int __stop_cpus(const struct cpumask *cpumask,
 
 	cpu_stop_init_done(&done, cpumask_weight(cpumask));
 	queue_stop_cpus_work(cpumask, fn, arg, &done, false);
-	wait_for_stop_done(&done);
+	wait_for_completion(&done.completion);
 	return done.executed ? done.ret : -ENOENT;
 }
 
@@ -510,13 +492,7 @@ repeat:
 			  kallsyms_lookup((unsigned long)fn, NULL, NULL, NULL,
 					  ksym_buf), arg);
 
-		/*
-		 * Make sure that the wakeup and setting done->waiter
-		 * to NULL is atomic.
-		 */
-		local_irq_disable();
 		cpu_stop_signal_done(done, true);
-		local_irq_enable();
 		goto repeat;
 	}
 }
@@ -675,7 +651,7 @@ int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data,
 	ret = multi_cpu_stop(&msdata);
 
 	/* Busy wait for completion. */
-	while (atomic_read(&done.nr_todo))
+	while (!completion_done(&done.completion))
 		cpu_relax();
 
 	mutex_unlock(&stop_cpus_mutex);
-- 
2.7.0