ftrace, perf: Add open/close tracepoint perf registration actions

Adding TRACE_REG_PERF_OPEN and TRACE_REG_PERF_CLOSE to differentiate
register/unregister from open/close actions.

The register/unregister actions are invoked for the first/last
tracepoint user when opening/closing the event.

The open/close actions are invoked for each tracepoint user when
opening/closing the event.

Link: http://lkml.kernel.org/r/1329317514-8131-3-git-send-email-jolsa@redhat.com
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index c3da42d..195e360 100644 (file)
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -146,6 +146,8 @@ enum trace_reg {
        TRACE_REG_UNREGISTER,
        TRACE_REG_PERF_REGISTER,
        TRACE_REG_PERF_UNREGISTER,
+       TRACE_REG_PERF_OPEN,
+       TRACE_REG_PERF_CLOSE,
 };
 
 struct ftrace_event_call;
@@ -157,7 +159,7 @@ struct ftrace_event_class {
        void                    *perf_probe;
 #endif
        int                     (*reg)(struct ftrace_event_call *event,
-                                      enum trace_reg type);
+                                      enum trace_reg type, void *data);
        int                     (*define_fields)(struct ftrace_event_call *);
        struct list_head        *(*get_fields)(struct ftrace_event_call *);
        struct list_head        fields;
@@ -165,7 +167,7 @@ struct ftrace_event_class {
 };
 
 extern int ftrace_event_reg(struct ftrace_event_call *event,
-                           enum trace_reg type);
+                           enum trace_reg type, void *data);
 
 enum {
        TRACE_EVENT_FL_ENABLED_BIT,

diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 19a359d..0cfcc37 100644 (file)
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -44,23 +44,17 @@ static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
        return 0;
 }
 
-static int perf_trace_event_init(struct ftrace_event_call *tp_event,
-                                struct perf_event *p_event)
+static int perf_trace_event_reg(struct ftrace_event_call *tp_event,
+                               struct perf_event *p_event)
 {
        struct hlist_head __percpu *list;
-       int ret;
+       int ret = -ENOMEM;
        int cpu;
 
-       ret = perf_trace_event_perm(tp_event, p_event);
-       if (ret)
-               return ret;
-
        p_event->tp_event = tp_event;
        if (tp_event->perf_refcount++ > 0)
                return 0;
 
-       ret = -ENOMEM;
-
        list = alloc_percpu(struct hlist_head);
        if (!list)
                goto fail;
@@ -83,7 +77,7 @@ static int perf_trace_event_init(struct ftrace_event_call *tp_event,
                }
        }
 
-       ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER);
+       ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER, NULL);
        if (ret)
                goto fail;
 
@@ -108,6 +102,69 @@ fail:
        return ret;
 }
 
+static void perf_trace_event_unreg(struct perf_event *p_event)
+{
+       struct ftrace_event_call *tp_event = p_event->tp_event;
+       int i;
+
+       if (--tp_event->perf_refcount > 0)
+               goto out;
+
+       tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER, NULL);
+
+       /*
+        * Ensure our callback won't be called anymore. The buffers
+        * will be freed after that.
+        */
+       tracepoint_synchronize_unregister();
+
+       free_percpu(tp_event->perf_events);
+       tp_event->perf_events = NULL;
+
+       if (!--total_ref_count) {
+               for (i = 0; i < PERF_NR_CONTEXTS; i++) {
+                       free_percpu(perf_trace_buf[i]);
+                       perf_trace_buf[i] = NULL;
+               }
+       }
+out:
+       module_put(tp_event->mod);
+}
+
+static int perf_trace_event_open(struct perf_event *p_event)
+{
+       struct ftrace_event_call *tp_event = p_event->tp_event;
+       return tp_event->class->reg(tp_event, TRACE_REG_PERF_OPEN, p_event);
+}
+
+static void perf_trace_event_close(struct perf_event *p_event)
+{
+       struct ftrace_event_call *tp_event = p_event->tp_event;
+       tp_event->class->reg(tp_event, TRACE_REG_PERF_CLOSE, p_event);
+}
+
+static int perf_trace_event_init(struct ftrace_event_call *tp_event,
+                                struct perf_event *p_event)
+{
+       int ret;
+
+       ret = perf_trace_event_perm(tp_event, p_event);
+       if (ret)
+               return ret;
+
+       ret = perf_trace_event_reg(tp_event, p_event);
+       if (ret)
+               return ret;
+
+       ret = perf_trace_event_open(p_event);
+       if (ret) {
+               perf_trace_event_unreg(p_event);
+               return ret;
+       }
+
+       return 0;
+}
+
 int perf_trace_init(struct perf_event *p_event)
 {
        struct ftrace_event_call *tp_event;
@@ -130,6 +187,14 @@ int perf_trace_init(struct perf_event *p_event)
        return ret;
 }
 
+void perf_trace_destroy(struct perf_event *p_event)
+{
+       mutex_lock(&event_mutex);
+       perf_trace_event_close(p_event);
+       perf_trace_event_unreg(p_event);
+       mutex_unlock(&event_mutex);
+}
+
 int perf_trace_add(struct perf_event *p_event, int flags)
 {
        struct ftrace_event_call *tp_event = p_event->tp_event;
@@ -154,37 +219,6 @@ void perf_trace_del(struct perf_event *p_event, int flags)
        hlist_del_rcu(&p_event->hlist_entry);
 }
 
-void perf_trace_destroy(struct perf_event *p_event)
-{
-       struct ftrace_event_call *tp_event = p_event->tp_event;
-       int i;
-
-       mutex_lock(&event_mutex);
-       if (--tp_event->perf_refcount > 0)
-               goto out;
-
-       tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER);
-
-       /*
-        * Ensure our callback won't be called anymore. The buffers
-        * will be freed after that.
-        */
-       tracepoint_synchronize_unregister();
-
-       free_percpu(tp_event->perf_events);
-       tp_event->perf_events = NULL;
-
-       if (!--total_ref_count) {
-               for (i = 0; i < PERF_NR_CONTEXTS; i++) {
-                       free_percpu(perf_trace_buf[i]);
-                       perf_trace_buf[i] = NULL;
-               }
-       }
-out:
-       module_put(tp_event->mod);
-       mutex_unlock(&event_mutex);
-}
-
 __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
                                       struct pt_regs *regs, int *rctxp)
 {

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index c212a7f..5138fea 100644 (file)
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -147,7 +147,8 @@ int trace_event_raw_init(struct ftrace_event_call *call)
 }
 EXPORT_SYMBOL_GPL(trace_event_raw_init);
 
-int ftrace_event_reg(struct ftrace_event_call *call, enum trace_reg type)
+int ftrace_event_reg(struct ftrace_event_call *call,
+                    enum trace_reg type, void *data)
 {
        switch (type) {
        case TRACE_REG_REGISTER:
@@ -170,6 +171,9 @@ int ftrace_event_reg(struct ftrace_event_call *call, enum trace_reg type)
                                            call->class->perf_probe,
                                            call);
                return 0;
+       case TRACE_REG_PERF_OPEN:
+       case TRACE_REG_PERF_CLOSE:
+               return 0;
 #endif
        }
        return 0;
@@ -209,7 +213,7 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call,
                                tracing_stop_cmdline_record();
                                call->flags &= ~TRACE_EVENT_FL_RECORDED_CMD;
                        }
-                       call->class->reg(call, TRACE_REG_UNREGISTER);
+                       call->class->reg(call, TRACE_REG_UNREGISTER, NULL);
                }
                break;
        case 1:
@@ -218,7 +222,7 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call,
                                tracing_start_cmdline_record();
                                call->flags |= TRACE_EVENT_FL_RECORDED_CMD;
                        }
-                       ret = call->class->reg(call, TRACE_REG_REGISTER);
+                       ret = call->class->reg(call, TRACE_REG_REGISTER, NULL);
                        if (ret) {
                                tracing_stop_cmdline_record();
                                pr_info("event trace: Could not enable event "

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 00d527c..5667f89 100644 (file)
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1892,7 +1892,8 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
 #endif /* CONFIG_PERF_EVENTS */
 
 static __kprobes
-int kprobe_register(struct ftrace_event_call *event, enum trace_reg type)
+int kprobe_register(struct ftrace_event_call *event,
+                   enum trace_reg type, void *data)
 {
        struct trace_probe *tp = (struct trace_probe *)event->data;
 
@@ -1909,6 +1910,9 @@ int kprobe_register(struct ftrace_event_call *event, enum trace_reg type)
        case TRACE_REG_PERF_UNREGISTER:
                disable_trace_probe(tp, TP_FLAG_PROFILE);
                return 0;
+       case TRACE_REG_PERF_OPEN:
+       case TRACE_REG_PERF_CLOSE:
+               return 0;
 #endif
        }
        return 0;

diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 4350015..e23515f 100644 (file)
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -17,9 +17,9 @@ static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
 static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
 
 static int syscall_enter_register(struct ftrace_event_call *event,
-                                enum trace_reg type);
+                                enum trace_reg type, void *data);
 static int syscall_exit_register(struct ftrace_event_call *event,
-                                enum trace_reg type);
+                                enum trace_reg type, void *data);
 
 static int syscall_enter_define_fields(struct ftrace_event_call *call);
 static int syscall_exit_define_fields(struct ftrace_event_call *call);
@@ -649,7 +649,7 @@ void perf_sysexit_disable(struct ftrace_event_call *call)
 #endif /* CONFIG_PERF_EVENTS */
 
 static int syscall_enter_register(struct ftrace_event_call *event,
-                                enum trace_reg type)
+                                enum trace_reg type, void *data)
 {
        switch (type) {
        case TRACE_REG_REGISTER:
@@ -664,13 +664,16 @@ static int syscall_enter_register(struct ftrace_event_call *event,
        case TRACE_REG_PERF_UNREGISTER:
                perf_sysenter_disable(event);
                return 0;
+       case TRACE_REG_PERF_OPEN:
+       case TRACE_REG_PERF_CLOSE:
+               return 0;
 #endif
        }
        return 0;
 }
 
 static int syscall_exit_register(struct ftrace_event_call *event,
-                                enum trace_reg type)
+                                enum trace_reg type, void *data)
 {
        switch (type) {
        case TRACE_REG_REGISTER:
@@ -685,6 +688,9 @@ static int syscall_exit_register(struct ftrace_event_call *event,
        case TRACE_REG_PERF_UNREGISTER:
                perf_sysexit_disable(event);
                return 0;
+       case TRACE_REG_PERF_OPEN:
+       case TRACE_REG_PERF_CLOSE:
+               return 0;
 #endif
        }
        return 0;