Linux Kernel Markers: support multiple probes

RCU style multiple probes support for the Linux Kernel Markers.  Common case
(one probe) is still fast and does not require dynamic allocation or a
supplementary pointer dereference on the fast path.

- Move preempt disable from the marker site to the callback.

Since we now have an internal callback, move the preempt disable/enable to the
callback instead of the marker site.

Since the callback change is done asynchronously (passing from a handler that
supports arguments to a handler that does not setup the arguments is no
arguments are passed), we can safely update it even if it is outside the
preempt disable section.

- Move probe arm to probe connection. Now, a connected probe is automatically
  armed.

Remove MARK_MAX_FORMAT_LEN, unused.

This patch modifies the Linux Kernel Markers API : it removes the probe
"arm/disarm" and changes the probe function prototype : it now expects a
va_list * instead of a "...".

If we want to have more than one probe connected to a marker at a given
time (LTTng, or blktrace, ssytemtap) then we need this patch. Without it,
connecting a second probe handler to a marker will fail.

It allow us, for instance, to do interesting combinations :

Do standard tracing with LTTng and, eventually, to compute statistics
with SystemTAP, or to have a special trigger on an event that would call
a systemtap script which would stop flight recorder tracing.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Mike Mason <mmlnx@us.ibm.com>
Cc: Dipankar Sarma <dipankar@in.ibm.com>
Cc: David Smith <dsmith@redhat.com>
Cc: "Paul E. McKenney" <paulmck@us.ibm.com>
Cc: "Frank Ch. Eigler" <fche@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/powerpc/platforms/cell/spufs/sputrace.c

@@ -146,34 +146,28 @@ static void sputrace_log_item(const char *name, struct spu_context *ctx,
 	wake_up(&sputrace_wait);
 }
 
-static void spu_context_event(const struct marker *mdata,
-		void *private, const char *format, ...)
+static void spu_context_event(void *probe_private, void *call_data,
+		const char *format, va_list *args)
 {
-	struct spu_probe *p = mdata->private;
-	va_list ap;
+	struct spu_probe *p = probe_private;
 	struct spu_context *ctx;
 	struct spu *spu;
 
-	va_start(ap, format);
-	ctx = va_arg(ap, struct spu_context *);
-	spu = va_arg(ap, struct spu *);
+	ctx = va_arg(*args, struct spu_context *);
+	spu = va_arg(*args, struct spu *);
 
 	sputrace_log_item(p->name, ctx, spu);
-	va_end(ap);
 }
 
-static void spu_context_nospu_event(const struct marker *mdata,
-		void *private, const char *format, ...)
+static void spu_context_nospu_event(void *probe_private, void *call_data,
+		const char *format, va_list *args)
 {
-	struct spu_probe *p = mdata->private;
-	va_list ap;
+	struct spu_probe *p = probe_private;
 	struct spu_context *ctx;
 
-	va_start(ap, format);
-	ctx = va_arg(ap, struct spu_context *);
+	ctx = va_arg(*args, struct spu_context *);
 
 	sputrace_log_item(p->name, ctx, NULL);
-	va_end(ap);
 }
 
 struct spu_probe spu_probes[] = {
@@ -219,10 +213,6 @@ static int __init sputrace_init(void)
 		if (error)
 			printk(KERN_INFO "Unable to register probe %s\n",
 					p->name);
-
-		error = marker_arm(p->name);
-		if (error)
-			printk(KERN_INFO "Unable to arm probe %s\n", p->name);
 	}
 
 	return 0;
@@ -238,7 +228,8 @@ static void __exit sputrace_exit(void)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(spu_probes); i++)
-		marker_probe_unregister(spu_probes[i].name);
+		marker_probe_unregister(spu_probes[i].name,
+			spu_probes[i].probe_func, &spu_probes[i]);
 
 	remove_proc_entry("sputrace", NULL);
 	kfree(sputrace_log);

include/linux/marker.h

@@ -19,16 +19,23 @@ struct marker;
 
 /**
  * marker_probe_func - Type of a marker probe function
- * @mdata: pointer of type struct marker
- * @private_data: caller site private data
+ * @probe_private: probe private data
+ * @call_private: call site private data
  * @fmt: format string
- * @...: variable argument list
+ * @args: variable argument list pointer. Use a pointer to overcome C's
+ *        inability to pass this around as a pointer in a portable manner in
+ *        the callee otherwise.
  *
  * Type of marker probe functions. They receive the mdata and need to parse the
  * format string to recover the variable argument list.
  */
-typedef void marker_probe_func(const struct marker *mdata,
-	void *private_data, const char *fmt, ...);
+typedef void marker_probe_func(void *probe_private, void *call_private,
+		const char *fmt, va_list *args);
+
+struct marker_probe_closure {
+	marker_probe_func *func;	/* Callback */
+	void *probe_private;		/* Private probe data */
+};
 
 struct marker {
 	const char *name;	/* Marker name */
@@ -36,8 +43,11 @@ struct marker {
 				 * variable argument list.
 				 */
 	char state;		/* Marker state. */
-	marker_probe_func *call;/* Probe handler function pointer */
-	void *private;		/* Private probe data */
+	char ptype;		/* probe type : 0 : single, 1 : multi */
+	void (*call)(const struct marker *mdata,	/* Probe wrapper */
+		void *call_private, const char *fmt, ...);
+	struct marker_probe_closure single;
+	struct marker_probe_closure *multi;
 } __attribute__((aligned(8)));
 
 #ifdef CONFIG_MARKERS
@@ -49,7 +59,7 @@ struct marker {
  * not add unwanted padding between the beginning of the section and the
  * structure. Force alignment to the same alignment as the section start.
  */
-#define __trace_mark(name, call_data, format, args...)			\
+#define __trace_mark(name, call_private, format, args...)		\
 	do {								\
 		static const char __mstrtab_name_##name[]		\
 		__attribute__((section("__markers_strings")))		\
@@ -60,24 +70,23 @@ struct marker {
 		static struct marker __mark_##name			\
 		__attribute__((section("__markers"), aligned(8))) =	\
 		{ __mstrtab_name_##name, __mstrtab_format_##name,	\
-		0, __mark_empty_function, NULL };			\
+		0, 0, marker_probe_cb,					\
+		{ __mark_empty_function, NULL}, NULL };			\
 		__mark_check_format(format, ## args);			\
 		if (unlikely(__mark_##name.state)) {			\
-			preempt_disable();				\
 			(*__mark_##name.call)				\
-				(&__mark_##name, call_data,		\
+				(&__mark_##name, call_private,		\
 				format, ## args);			\
-			preempt_enable();				\
 		}							\
 	} while (0)
 
 extern void marker_update_probe_range(struct marker *begin,
-	struct marker *end, struct module *probe_module, int *refcount);
+	struct marker *end);
 #else /* !CONFIG_MARKERS */
-#define __trace_mark(name, call_data, format, args...) \
+#define __trace_mark(name, call_private, format, args...) \
 		__mark_check_format(format, ## args)
 static inline void marker_update_probe_range(struct marker *begin,
-	struct marker *end, struct module *probe_module, int *refcount)
+	struct marker *end)
 { }
 #endif /* CONFIG_MARKERS */
 
@@ -92,8 +101,6 @@ static inline void marker_update_probe_range(struct marker *begin,
 #define trace_mark(name, format, args...) \
 	__trace_mark(name, NULL, format, ## args)
 
-#define MARK_MAX_FORMAT_LEN	1024
-
 /**
  * MARK_NOARGS - Format string for a marker with no argument.
  */
@@ -106,24 +113,30 @@ static inline void __printf(1, 2) __mark_check_format(const char *fmt, ...)
 
 extern marker_probe_func __mark_empty_function;
 
+extern void marker_probe_cb(const struct marker *mdata,
+	void *call_private, const char *fmt, ...);
+extern void marker_probe_cb_noarg(const struct marker *mdata,
+	void *call_private, const char *fmt, ...);
+
 /*
  * Connect a probe to a marker.
  * private data pointer must be a valid allocated memory address, or NULL.
  */
 extern int marker_probe_register(const char *name, const char *format,
-				marker_probe_func *probe, void *private);
+				marker_probe_func *probe, void *probe_private);
 
 /*
  * Returns the private data given to marker_probe_register.
  */
-extern void *marker_probe_unregister(const char *name);
+extern int marker_probe_unregister(const char *name,
+	marker_probe_func *probe, void *probe_private);
 /*
  * Unregister a marker by providing the registered private data.
  */
-extern void *marker_probe_unregister_private_data(void *private);
+extern int marker_probe_unregister_private_data(marker_probe_func *probe,
+	void *probe_private);
 
-extern int marker_arm(const char *name);
-extern int marker_disarm(const char *name);
-extern void *marker_get_private_data(const char *name);
+extern void *marker_get_private_data(const char *name, marker_probe_func *probe,
+	int num);
 
 #endif

include/linux/module.h

@@ -465,7 +465,7 @@ int unregister_module_notifier(struct notifier_block * nb);
 
 extern void print_modules(void);
 
-extern void module_update_markers(struct module *probe_module, int *refcount);
+extern void module_update_markers(void);
 
 #else /* !CONFIG_MODULES... */
 #define EXPORT_SYMBOL(sym)

kernel/module.c

@@ -2038,7 +2038,7 @@ static struct module *load_module(void __user *umod,
 #ifdef CONFIG_MARKERS
 	if (!mod->taints)
 		marker_update_probe_range(mod->markers,
-			mod->markers + mod->num_markers, NULL, NULL);
+			mod->markers + mod->num_markers);
 #endif
 	err = module_finalize(hdr, sechdrs, mod);
 	if (err < 0)
@@ -2564,7 +2564,7 @@ EXPORT_SYMBOL(struct_module);
 #endif
 
 #ifdef CONFIG_MARKERS
-void module_update_markers(struct module *probe_module, int *refcount)
+void module_update_markers(void)
 {
 	struct module *mod;
 
@@ -2572,8 +2572,7 @@ void module_update_markers(struct module *probe_module, int *refcount)
 	list_for_each_entry(mod, &modules, list)
 		if (!mod->taints)
 			marker_update_probe_range(mod->markers,
-				mod->markers + mod->num_markers,
-				probe_module, refcount);
+				mod->markers + mod->num_markers);
 	mutex_unlock(&module_mutex);
 }
 #endif

samples/markers/probe-example.c

@@ -20,31 +20,27 @@ struct probe_data {
 	marker_probe_func *probe_func;
 };
 
-void probe_subsystem_event(const struct marker *mdata, void *private,
-	const char *format, ...)
+void probe_subsystem_event(void *probe_data, void *call_data,
+	const char *format, va_list *args)
 {
-	va_list ap;
 	/* Declare args */
 	unsigned int value;
 	const char *mystr;
 
 	/* Assign args */
-	va_start(ap, format);
-	value = va_arg(ap, typeof(value));
-	mystr = va_arg(ap, typeof(mystr));
+	value = va_arg(*args, typeof(value));
+	mystr = va_arg(*args, typeof(mystr));
 
 	/* Call printk */
-	printk(KERN_DEBUG "Value %u, string %s\n", value, mystr);
+	printk(KERN_INFO "Value %u, string %s\n", value, mystr);
 
 	/* or count, check rights, serialize data in a buffer */
-
-	va_end(ap);
 }
 
 atomic_t eventb_count = ATOMIC_INIT(0);
 
-void probe_subsystem_eventb(const struct marker *mdata, void *private,
-	const char *format, ...)
+void probe_subsystem_eventb(void *probe_data, void *call_data,
+	const char *format, va_list *args)
 {
 	/* Increment counter */
 	atomic_inc(&eventb_count);
@@ -72,10 +68,6 @@ static int __init probe_init(void)
 		if (result)
 			printk(KERN_INFO "Unable to register probe %s\n",
 				probe_array[i].name);
-		result = marker_arm(probe_array[i].name);
-		if (result)
-			printk(KERN_INFO "Unable to arm probe %s\n",
-				probe_array[i].name);
 	}
 	return 0;
 }
@@ -85,7 +77,8 @@ static void __exit probe_fini(void)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(probe_array); i++)
-		marker_probe_unregister(probe_array[i].name);
+		marker_probe_unregister(probe_array[i].name,
+			probe_array[i].probe_func, &probe_array[i]);
 	printk(KERN_INFO "Number of event b : %u\n",
 			atomic_read(&eventb_count));
 }