[PATCH 5/7] ftrace, perf: Add support to use function tracepoint in perf

[Jiri Olsa <jolsa@redhat.com>]

Adding perf registration support for the ftrace function event,
so it is now possible to register it via perf interface.

The perf_event struct statically contains ftrace_ops as a handle
for function tracer. The function tracer is registered/unregistered
in open/close actions.

To be efficient, we enable/disable ftrace_ops each time the traced
process is scheduled in/out (via TRACE_REG_PERF_(ADD|DELL) handlers).
This way tracing is enabled only when the process is running.
Intentionally using this way instead of the event's hw state
PERF_HES_STOPPED, which would not disable the ftrace_ops.

It is now possible to use function trace within perf commands
like:

  perf record -e ftrace:function ls
  perf stat -e ftrace:function ls

Allowed only for root.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
 include/linux/perf_event.h      |    3 +
 kernel/trace/trace.h            |    2 +
 kernel/trace/trace_event_perf.c |   90 +++++++++++++++++++++++++++++++++++++++
 kernel/trace/trace_export.c     |   28 ++++++++++++
 4 files changed, 123 insertions(+), 0 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 412b790..92a056f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -859,6 +859,9 @@ struct perf_event {
 #ifdef CONFIG_EVENT_TRACING
 	struct ftrace_event_call	*tp_event;
 	struct event_filter		*filter;
+#ifdef CONFIG_FUNCTION_TRACER
+	struct ftrace_ops               ftrace_ops;
+#endif
 #endif
 
 #ifdef CONFIG_CGROUP_PERF
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 0eaf077..8ff7324 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -591,6 +591,8 @@ static inline int ftrace_trace_task(struct task_struct *task)
 static inline int ftrace_is_dead(void) { return 0; }
 #endif
 
+int ftrace_event_is_function(struct ftrace_event_call *call);
+
 /*
  * struct trace_parser - servers for reading the user input separated by spaces
  * @cont: set if the input is not complete - no final space char was found
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index d72af0b..8ee0461 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -24,6 +24,11 @@ static int	total_ref_count;
 static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
 				 struct perf_event *p_event)
 {
+	/* The ftrace function trace is allowed only for root. */
+	if (ftrace_event_is_function(tp_event) &&
+	    perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	/* No tracing, just counting, so no obvious leak */
 	if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW))
 		return 0;
@@ -250,3 +255,88 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
 	return raw_data;
 }
 EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
+
+
+static void
+perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip)
+{
+	struct ftrace_entry *entry;
+	struct hlist_head *head;
+	struct pt_regs regs;
+	int rctx;
+
+#define ENTRY_SIZE (ALIGN(sizeof(struct ftrace_entry) + sizeof(u32), \
+		    sizeof(u64)) - sizeof(u32))
+
+	BUILD_BUG_ON(ENTRY_SIZE > PERF_MAX_TRACE_SIZE);
+
+	perf_fetch_caller_regs(&regs);
+
+	entry = perf_trace_buf_prepare(ENTRY_SIZE, TRACE_FN, NULL, &rctx);
+	if (!entry)
+		return;
+
+	entry->ip = ip;
+	entry->parent_ip = parent_ip;
+
+	head = this_cpu_ptr(event_function.perf_events);
+	perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, 0,
+			      1, &regs, head);
+
+#undef ENTRY_SIZE
+}
+
+static int perf_ftrace_function_register(struct perf_event *event)
+{
+	struct ftrace_ops *ops = &event->ftrace_ops;
+
+	ops->flags |= FTRACE_OPS_FL_CONTROL;
+	ops->func = perf_ftrace_function_call;
+	return register_ftrace_function(ops);
+}
+
+static int perf_ftrace_function_unregister(struct perf_event *event)
+{
+	struct ftrace_ops *ops = &event->ftrace_ops;
+	return unregister_ftrace_function(ops);
+}
+
+static void perf_ftrace_function_enable(struct perf_event *event)
+{
+	ftrace_function_local_enable(&event->ftrace_ops);
+}
+
+static void perf_ftrace_function_disable(struct perf_event *event)
+{
+	ftrace_function_local_disable(&event->ftrace_ops);
+}
+
+int perf_ftrace_event_register(struct ftrace_event_call *call,
+			       enum trace_reg type, void *data)
+{
+	int etype = call->event.type;
+
+	if (etype != TRACE_FN)
+		return -EINVAL;
+
+	switch (type) {
+	case TRACE_REG_REGISTER:
+	case TRACE_REG_UNREGISTER:
+		break;
+	case TRACE_REG_PERF_REGISTER:
+	case TRACE_REG_PERF_UNREGISTER:
+		return 0;
+	case TRACE_REG_PERF_OPEN:
+		return perf_ftrace_function_register(data);
+	case TRACE_REG_PERF_CLOSE:
+		return perf_ftrace_function_unregister(data);
+	case TRACE_REG_PERF_ADD:
+		perf_ftrace_function_enable(data);
+		return 0;
+	case TRACE_REG_PERF_DEL:
+		perf_ftrace_function_disable(data);
+		return 0;
+	}
+
+	return -EINVAL;
+}
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index bbeec31..867653c 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -131,6 +131,28 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call)	\
 
 #include "trace_entries.h"
 
+static int ftrace_event_class_register(struct ftrace_event_call *call,
+				       enum trace_reg type, void *data)
+{
+	switch (type) {
+	case TRACE_REG_PERF_REGISTER:
+	case TRACE_REG_PERF_UNREGISTER:
+		return 0;
+	case TRACE_REG_PERF_OPEN:
+	case TRACE_REG_PERF_CLOSE:
+	case TRACE_REG_PERF_ADD:
+	case TRACE_REG_PERF_DEL:
+#ifdef CONFIG_PERF_EVENTS
+		return perf_ftrace_event_register(call, type, data);
+#endif
+	case TRACE_REG_REGISTER:
+	case TRACE_REG_UNREGISTER:
+		break;
+	}
+
+	return -EINVAL;
+}
+
 #undef __entry
 #define __entry REC
 
@@ -159,6 +181,7 @@ struct ftrace_event_class event_class_ftrace_##call = {			\
 	.system			= __stringify(TRACE_SYSTEM),		\
 	.define_fields		= ftrace_define_fields_##call,		\
 	.fields			= LIST_HEAD_INIT(event_class_ftrace_##call.fields),\
+	.reg			= ftrace_event_class_register,		\
 };									\
 									\
 struct ftrace_event_call __used event_##call = {			\
@@ -170,4 +193,9 @@ struct ftrace_event_call __used event_##call = {			\
 struct ftrace_event_call __used						\
 __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;
 
+int ftrace_event_is_function(struct ftrace_event_call *call)
+{
+	return call == &event_function;
+}
+
 #include "trace_entries.h"
-- 
1.7.1