tracepoint: Give priority to probes of tracepoints

In order to guarantee that a probe will be called before other probes that
are attached to a tracepoint, there needs to be a mechanism to provide
priority of one probe over the others.

Adding a prio field to the struct tracepoint_func, which lets the probes be
sorted by the priority set in the structure. If no priority is specified,
then a priority of 10 is given (this is a macro, and perhaps may be changed
in the future).

Now probes may be added to affect other probes that are attached to a
tracepoint with a guaranteed order.

One use case would be to allow tracing of tracepoints be able to filter by
pid. A special (higher priority probe) may be added to the sched_switch
tracepoint and set the necessary flags of the other tracepoints to notify
them if they should be traced or not. In case a tracepoint is enabled at the
sched_switch tracepoint too, the order of the two are not random.

Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

include/linux/tracepoint.h

@@ -26,6 +26,7 @@ struct notifier_block;
 struct tracepoint_func {
 	void *func;
 	void *data;
+	int prio;
 };
 
 struct tracepoint {
@@ -42,9 +43,14 @@ struct trace_enum_map {
 	unsigned long		enum_value;
 };
 
+#define TRACEPOINT_DEFAULT_PRIO	10
+
 extern int
 tracepoint_probe_register(struct tracepoint *tp, void *probe, void *data);
 extern int
+tracepoint_probe_register_prio(struct tracepoint *tp, void *probe, void *data,
+			       int prio);
+extern int
 tracepoint_probe_unregister(struct tracepoint *tp, void *probe, void *data);
 extern void
 for_each_kernel_tracepoint(void (*fct)(struct tracepoint *tp, void *priv),
@@ -207,6 +213,13 @@ extern void syscall_unregfunc(void);
 						(void *)probe, data);	\
 	}								\
 	static inline int						\
+	register_trace_prio_##name(void (*probe)(data_proto), void *data,\
+				   int prio)				\
+	{								\
+		return tracepoint_probe_register_prio(&__tracepoint_##name, \
+					      (void *)probe, data, prio); \
+	}								\
+	static inline int						\
 	unregister_trace_##name(void (*probe)(data_proto), void *data)	\
 	{								\
 		return tracepoint_probe_unregister(&__tracepoint_##name,\

kernel/tracepoint.c

@@ -91,11 +91,13 @@ static void debug_print_probes(struct tracepoint_func *funcs)
 		printk(KERN_DEBUG "Probe %d : %p\n", i, funcs[i].func);
 }
 
-static struct tracepoint_func *func_add(struct tracepoint_func **funcs,
-		struct tracepoint_func *tp_func)
+static struct tracepoint_func *
+func_add(struct tracepoint_func **funcs, struct tracepoint_func *tp_func,
+	 int prio)
 {
-	int nr_probes = 0;
 	struct tracepoint_func *old, *new;
+	int nr_probes = 0;
+	int pos = -1;
 
 	if (WARN_ON(!tp_func->func))
 		return ERR_PTR(-EINVAL);
@@ -104,18 +106,33 @@ static struct tracepoint_func *func_add(struct tracepoint_func **funcs,
 	old = *funcs;
 	if (old) {
 		/* (N -> N+1), (N != 0, 1) probes */
-		for (nr_probes = 0; old[nr_probes].func; nr_probes++)
+		for (nr_probes = 0; old[nr_probes].func; nr_probes++) {
+			/* Insert before probes of lower priority */
+			if (pos < 0 && old[nr_probes].prio < prio)
+				pos = nr_probes;
 			if (old[nr_probes].func == tp_func->func &&
 			    old[nr_probes].data == tp_func->data)
 				return ERR_PTR(-EEXIST);
 		}
+	}
 	/* + 2 : one for new probe, one for NULL func */
 	new = allocate_probes(nr_probes + 2);
 	if (new == NULL)
 		return ERR_PTR(-ENOMEM);
-	if (old)
+	if (old) {
+		if (pos < 0) {
+			pos = nr_probes;
 			memcpy(new, old, nr_probes * sizeof(struct tracepoint_func));
-	new[nr_probes] = *tp_func;
+		} else {
+			/* Copy higher priority probes ahead of the new probe */
+			memcpy(new, old, pos * sizeof(struct tracepoint_func));
+			/* Copy the rest after it. */
+			memcpy(new + pos + 1, old + pos,
+			       (nr_probes - pos) * sizeof(struct tracepoint_func));
+		}
+	} else
+		pos = 0;
+	new[pos] = *tp_func;
 	new[nr_probes + 1].func = NULL;
 	*funcs = new;
 	debug_print_probes(*funcs);
@@ -174,7 +191,7 @@ static void *func_remove(struct tracepoint_func **funcs,
  * Add the probe function to a tracepoint.
  */
 static int tracepoint_add_func(struct tracepoint *tp,
-		struct tracepoint_func *func)
+			       struct tracepoint_func *func, int prio)
 {
 	struct tracepoint_func *old, *tp_funcs;
 
@@ -183,7 +200,7 @@ static int tracepoint_add_func(struct tracepoint *tp,
 
 	tp_funcs = rcu_dereference_protected(tp->funcs,
 			lockdep_is_held(&tracepoints_mutex));
-	old = func_add(&tp_funcs, func);
+	old = func_add(&tp_funcs, func, prio);
 	if (IS_ERR(old)) {
 		WARN_ON_ONCE(1);
 		return PTR_ERR(old);
@@ -240,6 +257,7 @@ static int tracepoint_remove_func(struct tracepoint *tp,
  * @tp: tracepoint
  * @probe: probe handler
  * @data: tracepoint data
+ * @prio: priority of this function over other registered functions
  *
  * Returns 0 if ok, error value on error.
  * Note: if @tp is within a module, the caller is responsible for
@@ -247,7 +265,8 @@ static int tracepoint_remove_func(struct tracepoint *tp,
  * performed either with a tracepoint module going notifier, or from
  * within module exit functions.
  */
-int tracepoint_probe_register(struct tracepoint *tp, void *probe, void *data)
+int tracepoint_probe_register_prio(struct tracepoint *tp, void *probe,
+				   void *data, int prio)
 {
 	struct tracepoint_func tp_func;
 	int ret;
@@ -255,10 +274,30 @@ int tracepoint_probe_register(struct tracepoint *tp, void *probe, void *data)
 	mutex_lock(&tracepoints_mutex);
 	tp_func.func = probe;
 	tp_func.data = data;
-	ret = tracepoint_add_func(tp, &tp_func);
+	tp_func.prio = prio;
+	ret = tracepoint_add_func(tp, &tp_func, prio);
 	mutex_unlock(&tracepoints_mutex);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(tracepoint_probe_register_prio);
+
+/**
+ * tracepoint_probe_register -  Connect a probe to a tracepoint
+ * @tp: tracepoint
+ * @probe: probe handler
+ * @data: tracepoint data
+ * @prio: priority of this function over other registered functions
+ *
+ * Returns 0 if ok, error value on error.
+ * Note: if @tp is within a module, the caller is responsible for
+ * unregistering the probe before the module is gone. This can be
+ * performed either with a tracepoint module going notifier, or from
+ * within module exit functions.
+ */
+int tracepoint_probe_register(struct tracepoint *tp, void *probe, void *data)
+{
+	return tracepoint_probe_register_prio(tp, probe, data, TRACEPOINT_DEFAULT_PRIO);
+}
 EXPORT_SYMBOL_GPL(tracepoint_probe_register);
 
 /**