ring-buffer: Move recursive check to per_cpu descriptor

Instead of using a global per_cpu variable to perform the recursive
checks into the ring buffer, use the already existing per_cpu descriptor
that is part of the ring buffer itself.

Not only does this simplify the code, it also allows for one ring buffer
to be used within the guts of the use of another ring buffer. For example
trace_printk() can now be used within the ring buffer to record changes
done by an instance into the main ring buffer. The recursion checks
will prevent the trace_printk() itself from causing recursive issues
with the main ring buffer (it is just ignored), but the recursive
checks wont prevent the trace_printk() from recording other ring buffers.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

kernel/trace/ring_buffer.c

@@ -462,6 +462,7 @@ struct ring_buffer_per_cpu {
 	arch_spinlock_t			lock;
 	struct lock_class_key		lock_key;
 	unsigned int			nr_pages;
+	unsigned int			current_context;
 	struct list_head		*pages;
 	struct buffer_page		*head_page;	/* read from head */
 	struct buffer_page		*tail_page;	/* write to tail */
@@ -2675,11 +2676,11 @@ rb_reserve_next_event(struct ring_buffer *buffer,
  * just so happens that it is the same bit corresponding to
  * the current context.
  */
-static DEFINE_PER_CPU(unsigned int, current_context);
 
-static __always_inline int trace_recursive_lock(void)
+static __always_inline int
+trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
 {
-	unsigned int val = __this_cpu_read(current_context);
+	unsigned int val = cpu_buffer->current_context;
 	int bit;
 
 	if (in_interrupt()) {
@@ -2696,20 +2697,21 @@ static __always_inline int trace_recursive_lock(void)
 		return 1;
 
 	val |= (1 << bit);
-	__this_cpu_write(current_context, val);
+	cpu_buffer->current_context = val;
 
 	return 0;
 }
 
-static __always_inline void trace_recursive_unlock(void)
+static __always_inline void
+trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer)
 {
-	__this_cpu_and(current_context, __this_cpu_read(current_context) - 1);
+	cpu_buffer->current_context &= cpu_buffer->current_context - 1;
 }
 
 #else
 
-#define trace_recursive_lock()		(0)
-#define trace_recursive_unlock()	do { } while (0)
+#define trace_recursive_lock(cpu_buffer)	(0)
+#define trace_recursive_unlock(cpu_buffer)	do { } while (0)
 
 #endif
 
@@ -2742,10 +2744,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
 	preempt_disable_notrace();
 
 	if (unlikely(atomic_read(&buffer->record_disabled)))
-		goto out_nocheck;
-
-	if (unlikely(trace_recursive_lock()))
-		goto out_nocheck;
+		goto out;
 
 	cpu = raw_smp_processor_id();
 
@@ -2760,16 +2759,18 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
 	if (unlikely(length > BUF_MAX_DATA_SIZE))
 		goto out;
 
+	if (unlikely(trace_recursive_lock(cpu_buffer)))
+		goto out;
+
 	event = rb_reserve_next_event(buffer, cpu_buffer, length);
 	if (!event)
-		goto out;
+		goto out_unlock;
 
 	return event;
 
+ out_unlock:
+	trace_recursive_unlock(cpu_buffer);
  out:
-	trace_recursive_unlock();
-
- out_nocheck:
 	preempt_enable_notrace();
 	return NULL;
 }
@@ -2859,7 +2860,7 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
 
 	rb_wakeups(buffer, cpu_buffer);
 
-	trace_recursive_unlock();
+	trace_recursive_unlock(cpu_buffer);
 
 	preempt_enable_notrace();
 
@@ -2970,7 +2971,7 @@ void ring_buffer_discard_commit(struct ring_buffer *buffer,
  out:
 	rb_end_commit(cpu_buffer);
 
-	trace_recursive_unlock();
+	trace_recursive_unlock(cpu_buffer);
 
 	preempt_enable_notrace();