tracing: Remove ftrace_preempt_disable/enable

The ftrace_preempt_disable/enable functions were to address a
recursive race caused by the function tracer. The function tracer
traces all functions which makes it easily susceptible to recursion.
One area was preempt_enable(). This would call the scheduler and
the schedulre would call the function tracer and loop.
(So was it thought).

The ftrace_preempt_disable/enable was made to protect against recursion
inside the scheduler by storing the NEED_RESCHED flag. If it was
set before the ftrace_preempt_disable() it would not call schedule
on ftrace_preempt_enable(), thinking that if it was set before then
it would have already scheduled unless it was already in the scheduler.

This worked fine except in the case of SMP, where another task would set
the NEED_RESCHED flag for a task on another CPU, and then kick off an
IPI to trigger it. This could cause the NEED_RESCHED to be saved at
ftrace_preempt_disable() but the IPI to arrive in the the preempt
disabled section. The ftrace_preempt_enable() would not call the scheduler
because the flag was already set before entring the section.

This bug would cause a missed preemption check and cause lower latencies.

Investigating further, I found that the recusion caused by the function
tracer was not due to schedule(), but due to preempt_schedule(). Now
that preempt_schedule is completely annotated with notrace, the recusion
no longer is an issue.

Reported-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

1 files changed, 8 insertions, 30 deletions

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 7f6059c5aa94..c3d3cd9c2a53 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2234,8 +2234,6 @@ static void trace_recursive_unlock(void)
 
 #endif
 
-static DEFINE_PER_CPU(int, rb_need_resched);
-
 /**
  * ring_buffer_lock_reserve - reserve a part of the buffer
  * @buffer: the ring buffer to reserve from
@@ -2256,13 +2254,13 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct ring_buffer_event *event;
-	int cpu, resched;
+	int cpu;
 
 	if (ring_buffer_flags != RB_BUFFERS_ON)
 		return NULL;
 
 	/* If we are tracing schedule, we don't want to recurse */
-	resched = ftrace_preempt_disable();
+	preempt_disable_notrace();
 
 	if (atomic_read(&buffer->record_disabled))
 		goto out_nocheck;
@@ -2287,21 +2285,13 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
 	if (!event)
 		goto out;
 
-	/*
-	 * Need to store resched state on this cpu.
-	 * Only the first needs to.
-	 */
-
-	if (preempt_count() == 1)
-		per_cpu(rb_need_resched, cpu) = resched;
-
 	return event;
 
  out:
 	trace_recursive_unlock();
 
  out_nocheck:
-	ftrace_preempt_enable(resched);
+	preempt_enable_notrace();
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_lock_reserve);
@@ -2347,13 +2337,7 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
 
 	trace_recursive_unlock();
 
-	/*
-	 * Only the last preempt count needs to restore preemption.
-	 */
-	if (preempt_count() == 1)
-		ftrace_preempt_enable(per_cpu(rb_need_resched, cpu));
-	else
-		preempt_enable_no_resched_notrace();
+	preempt_enable_notrace();
 
 	return 0;
 }
@@ -2461,13 +2445,7 @@ void ring_buffer_discard_commit(struct ring_buffer *buffer,
 
 	trace_recursive_unlock();
 
-	/*
-	 * Only the last preempt count needs to restore preemption.
-	 */
-	if (preempt_count() == 1)
-		ftrace_preempt_enable(per_cpu(rb_need_resched, cpu));
-	else
-		preempt_enable_no_resched_notrace();
+	preempt_enable_notrace();
 
 }
 EXPORT_SYMBOL_GPL(ring_buffer_discard_commit);
@@ -2493,12 +2471,12 @@ int ring_buffer_write(struct ring_buffer *buffer,
 	struct ring_buffer_event *event;
 	void *body;
 	int ret = -EBUSY;
-	int cpu, resched;
+	int cpu;
 
 	if (ring_buffer_flags != RB_BUFFERS_ON)
 		return -EBUSY;
 
-	resched = ftrace_preempt_disable();
+	preempt_disable_notrace();
 
 	if (atomic_read(&buffer->record_disabled))
 		goto out;
@@ -2528,7 +2506,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
 
 	ret = 0;
  out:
-	ftrace_preempt_enable(resched);
+	preempt_enable_notrace();
 
 	return ret;
 }