From e248491ac283b516958ca9ab62c8e74b6718bca8 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Wed, 15 Feb 2012 15:51:48 +0100
Subject: ftrace: Add enable/disable ftrace_ops control interface

Adding a way to temporarily enable/disable ftrace_ops. The change
follows the same way as 'global' ftrace_ops are done.

Introducing 2 global ftrace_ops - control_ops and ftrace_control_list
which take over all ftrace_ops registered with FTRACE_OPS_FL_CONTROL
flag. In addition new per cpu flag called 'disabled' is also added to
ftrace_ops to provide the control information for each cpu.

When ftrace_ops with FTRACE_OPS_FL_CONTROL is registered, it is
set as disabled for all cpus.

The ftrace_control_list contains all the registered 'control' ftrace_ops.
The control_ops provides function which iterates ftrace_control_list
and does the check for 'disabled' flag on current cpu.

Adding 3 inline functions:
  ftrace_function_local_disable/ftrace_function_local_enable
  - enable/disable the ftrace_ops on current cpu
  ftrace_function_local_disabled
  - get disabled ftrace_ops::disabled value for current cpu

Link: http://lkml.kernel.org/r/1329317514-8131-2-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>
---
 include/linux/ftrace.h | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 66 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index f33fb3b041c6..64a309d2fbd6 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -31,16 +31,33 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 
 typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip);
 
+/*
+ * FTRACE_OPS_FL_* bits denote the state of ftrace_ops struct and are
+ * set in the flags member.
+ *
+ * ENABLED - set/unset when ftrace_ops is registered/unregistered
+ * GLOBAL  - set manualy by ftrace_ops user to denote the ftrace_ops
+ *           is part of the global tracers sharing the same filter
+ *           via set_ftrace_* debugfs files.
+ * DYNAMIC - set when ftrace_ops is registered to denote dynamically
+ *           allocated ftrace_ops which need special care
+ * CONTROL - set manualy by ftrace_ops user to denote the ftrace_ops
+ *           could be controled by following calls:
+ *             ftrace_function_local_enable
+ *             ftrace_function_local_disable
+ */
 enum {
 	FTRACE_OPS_FL_ENABLED		= 1 << 0,
 	FTRACE_OPS_FL_GLOBAL		= 1 << 1,
 	FTRACE_OPS_FL_DYNAMIC		= 1 << 2,
+	FTRACE_OPS_FL_CONTROL		= 1 << 3,
 };
 
 struct ftrace_ops {
 	ftrace_func_t			func;
 	struct ftrace_ops		*next;
 	unsigned long			flags;
+	int __percpu			*disabled;
 #ifdef CONFIG_DYNAMIC_FTRACE
 	struct ftrace_hash		*notrace_hash;
 	struct ftrace_hash		*filter_hash;
@@ -97,6 +114,55 @@ int register_ftrace_function(struct ftrace_ops *ops);
 int unregister_ftrace_function(struct ftrace_ops *ops);
 void clear_ftrace_function(void);
 
+/**
+ * ftrace_function_local_enable - enable controlled ftrace_ops on current cpu
+ *
+ * This function enables tracing on current cpu by decreasing
+ * the per cpu control variable.
+ * It must be called with preemption disabled and only on ftrace_ops
+ * registered with FTRACE_OPS_FL_CONTROL. If called without preemption
+ * disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled.
+ */
+static inline void ftrace_function_local_enable(struct ftrace_ops *ops)
+{
+	if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL)))
+		return;
+
+	(*this_cpu_ptr(ops->disabled))--;
+}
+
+/**
+ * ftrace_function_local_disable - enable controlled ftrace_ops on current cpu
+ *
+ * This function enables tracing on current cpu by decreasing
+ * the per cpu control variable.
+ * It must be called with preemption disabled and only on ftrace_ops
+ * registered with FTRACE_OPS_FL_CONTROL. If called without preemption
+ * disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled.
+ */
+static inline void ftrace_function_local_disable(struct ftrace_ops *ops)
+{
+	if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL)))
+		return;
+
+	(*this_cpu_ptr(ops->disabled))++;
+}
+
+/**
+ * ftrace_function_local_disabled - returns ftrace_ops disabled value
+ *                                  on current cpu
+ *
+ * This function returns value of ftrace_ops::disabled on current cpu.
+ * It must be called with preemption disabled and only on ftrace_ops
+ * registered with FTRACE_OPS_FL_CONTROL. If called without preemption
+ * disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled.
+ */
+static inline int ftrace_function_local_disabled(struct ftrace_ops *ops)
+{
+	WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL));
+	return *this_cpu_ptr(ops->disabled);
+}
+
 extern void ftrace_stub(unsigned long a0, unsigned long a1);
 
 #else /* !CONFIG_FUNCTION_TRACER */
-- 
cgit v1.2.3-71-gd317


From ceec0b6fc7cd43b38a40c2d40223f9cd0616f0cd Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Wed, 15 Feb 2012 15:51:49 +0100
Subject: 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>
---
 include/linux/ftrace_event.h    |   6 ++-
 kernel/trace/trace_event_perf.c | 116 ++++++++++++++++++++++++++--------------
 kernel/trace/trace_events.c     |  10 ++--
 kernel/trace/trace_kprobe.c     |   6 ++-
 kernel/trace/trace_syscalls.c   |  14 +++--
 5 files changed, 101 insertions(+), 51 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index c3da42dd22ba..195e3606ddd7 100644
--- 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 19a359d5e6d5..0cfcc37f63de 100644
--- 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 c212a7f934ec..5138fea37908 100644
--- 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 00d527c945a4..5667f8958cc9 100644
--- 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 43500153dd1e..e23515f51ed4 100644
--- 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;
-- 
cgit v1.2.3-71-gd317


From 489c75c3b333dfda4c8d2b7ad1b00e5da024bfa7 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Wed, 15 Feb 2012 15:51:50 +0100
Subject: ftrace, perf: Add add/del tracepoint perf registration actions

Adding TRACE_REG_PERF_ADD and TRACE_REG_PERF_DEL to handle
perf event schedule in/out actions.

The add action is invoked for when the perf event is scheduled in,
while the del action is invoked when the event is scheduled out.

Link: http://lkml.kernel.org/r/1329317514-8131-4-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>
---
 include/linux/ftrace_event.h    | 2 ++
 kernel/trace/trace_event_perf.c | 4 +++-
 kernel/trace/trace_events.c     | 2 ++
 kernel/trace/trace_kprobe.c     | 2 ++
 kernel/trace/trace_syscalls.c   | 4 ++++
 5 files changed, 13 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 195e3606ddd7..2bf677cb2d6f 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -148,6 +148,8 @@ enum trace_reg {
 	TRACE_REG_PERF_UNREGISTER,
 	TRACE_REG_PERF_OPEN,
 	TRACE_REG_PERF_CLOSE,
+	TRACE_REG_PERF_ADD,
+	TRACE_REG_PERF_DEL,
 };
 
 struct ftrace_event_call;
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 0cfcc37f63de..d72af0b03822 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -211,12 +211,14 @@ int perf_trace_add(struct perf_event *p_event, int flags)
 	list = this_cpu_ptr(pcpu_list);
 	hlist_add_head_rcu(&p_event->hlist_entry, list);
 
-	return 0;
+	return tp_event->class->reg(tp_event, TRACE_REG_PERF_ADD, p_event);
 }
 
 void perf_trace_del(struct perf_event *p_event, int flags)
 {
+	struct ftrace_event_call *tp_event = p_event->tp_event;
 	hlist_del_rcu(&p_event->hlist_entry);
+	tp_event->class->reg(tp_event, TRACE_REG_PERF_DEL, p_event);
 }
 
 __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 5138fea37908..079a93ae8a9d 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -173,6 +173,8 @@ int ftrace_event_reg(struct ftrace_event_call *call,
 		return 0;
 	case TRACE_REG_PERF_OPEN:
 	case TRACE_REG_PERF_CLOSE:
+	case TRACE_REG_PERF_ADD:
+	case TRACE_REG_PERF_DEL:
 		return 0;
 #endif
 	}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 5667f8958cc9..580a05ec926b 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1912,6 +1912,8 @@ int kprobe_register(struct ftrace_event_call *event,
 		return 0;
 	case TRACE_REG_PERF_OPEN:
 	case TRACE_REG_PERF_CLOSE:
+	case TRACE_REG_PERF_ADD:
+	case TRACE_REG_PERF_DEL:
 		return 0;
 #endif
 	}
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index e23515f51ed4..96fc73369099 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -666,6 +666,8 @@ static int syscall_enter_register(struct ftrace_event_call *event,
 		return 0;
 	case TRACE_REG_PERF_OPEN:
 	case TRACE_REG_PERF_CLOSE:
+	case TRACE_REG_PERF_ADD:
+	case TRACE_REG_PERF_DEL:
 		return 0;
 #endif
 	}
@@ -690,6 +692,8 @@ static int syscall_exit_register(struct ftrace_event_call *event,
 		return 0;
 	case TRACE_REG_PERF_OPEN:
 	case TRACE_REG_PERF_CLOSE:
+	case TRACE_REG_PERF_ADD:
+	case TRACE_REG_PERF_DEL:
 		return 0;
 #endif
 	}
-- 
cgit v1.2.3-71-gd317


From ced39002f5ea736b716ae233fb68b26d59783912 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Wed, 15 Feb 2012 15:51:52 +0100
Subject: ftrace, perf: Add support to use function tracepoint in perf

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.

Link: http://lkml.kernel.org/r/1329317514-8131-6-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>
---
 include/linux/perf_event.h      |  3 ++
 kernel/trace/trace.h            | 11 ++++++
 kernel/trace/trace_entries.h    |  6 ++-
 kernel/trace/trace_event_perf.c | 86 +++++++++++++++++++++++++++++++++++++++++
 kernel/trace/trace_export.c     |  5 +++
 5 files changed, 109 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 412b790f5da6..92a056f6d18d 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 638476af8d7b..76a1c5094bbf 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -595,6 +595,8 @@ 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
@@ -832,4 +834,13 @@ extern const char *__stop___trace_bprintk_fmt[];
 	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
 #include "trace_entries.h"
 
+#ifdef CONFIG_PERF_EVENTS
+#ifdef CONFIG_FUNCTION_TRACER
+int perf_ftrace_event_register(struct ftrace_event_call *call,
+			       enum trace_reg type, void *data);
+#else
+#define perf_ftrace_event_register NULL
+#endif /* CONFIG_FUNCTION_TRACER */
+#endif /* CONFIG_PERF_EVENTS */
+
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index 93365907f219..47db7eda0531 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -55,7 +55,7 @@
 /*
  * Function trace entry - function address and parent function address:
  */
-FTRACE_ENTRY(function, ftrace_entry,
+FTRACE_ENTRY_REG(function, ftrace_entry,
 
 	TRACE_FN,
 
@@ -64,7 +64,9 @@ FTRACE_ENTRY(function, ftrace_entry,
 		__field(	unsigned long,	parent_ip	)
 	),
 
-	F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip)
+	F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip),
+
+	perf_ftrace_event_register
 );
 
 /* Function call entry */
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index d72af0b03822..fdeeb5c49627 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 +255,84 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
 	return raw_data;
 }
 EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
+
+#ifdef CONFIG_FUNCTION_TRACER
+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)
+{
+	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;
+}
+#endif /* CONFIG_FUNCTION_TRACER */
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index f74de861cde9..a3dbee6d04cd 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -184,4 +184,9 @@ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;
 	FTRACE_ENTRY_REG(call, struct_name, etype,			\
 			 PARAMS(tstruct), PARAMS(print), NULL)
 
+int ftrace_event_is_function(struct ftrace_event_call *call)
+{
+	return call == &event_function;
+}
+
 #include "trace_entries.h"
-- 
cgit v1.2.3-71-gd317


From 02aa3162edaa166a01d193f80ccde890be8b55da Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Wed, 15 Feb 2012 15:51:53 +0100
Subject: ftrace: Allow to specify filter field type for ftrace events

Adding FILTER_TRACE_FN event field type for function tracepoint
event, so it can be properly recognized within filtering code.

Currently all fields of ftrace subsystem events share the common
field type FILTER_OTHER. Since the function trace fields need
special care within the filtering code we need to recognize it
properly, hence adding the FILTER_TRACE_FN event type.

Adding filter parameter to the FTRACE_ENTRY macro, to specify the
filter field type for the event.

Link: http://lkml.kernel.org/r/1329317514-8131-7-git-send-email-jolsa@redhat.com

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace_event.h       |  1 +
 kernel/trace/trace.h               | 23 +++++++++--------
 kernel/trace/trace_entries.h       | 48 +++++++++++++++++++++++++----------
 kernel/trace/trace_events_filter.c |  7 +++++-
 kernel/trace/trace_export.c        | 51 +++++++++++++++++++++-----------------
 5 files changed, 83 insertions(+), 47 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 2bf677cb2d6f..dd478fc8f9f5 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -245,6 +245,7 @@ enum {
 	FILTER_STATIC_STRING,
 	FILTER_DYN_STRING,
 	FILTER_PTR_STRING,
+	FILTER_TRACE_FN,
 };
 
 #define EVENT_STORAGE_SIZE 128
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 76a1c5094bbf..29f93cd434a5 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -56,21 +56,23 @@ enum trace_type {
 #define F_STRUCT(args...)		args
 
 #undef FTRACE_ENTRY
-#define FTRACE_ENTRY(name, struct_name, id, tstruct, print)	\
-	struct struct_name {					\
-		struct trace_entry	ent;			\
-		tstruct						\
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter)	\
+	struct struct_name {						\
+		struct trace_entry	ent;				\
+		tstruct							\
 	}
 
 #undef TP_ARGS
 #define TP_ARGS(args...)	args
 
 #undef FTRACE_ENTRY_DUP
-#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk)
+#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk, filter)
 
 #undef FTRACE_ENTRY_REG
-#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, regfn) \
-	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print))
+#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print,	\
+			 filter, regfn) \
+	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
+		     filter)
 
 #include "trace_entries.h"
 
@@ -826,12 +828,13 @@ extern const char *__start___trace_bprintk_fmt[];
 extern const char *__stop___trace_bprintk_fmt[];
 
 #undef FTRACE_ENTRY
-#define FTRACE_ENTRY(call, struct_name, id, tstruct, print)		\
+#define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter)	\
 	extern struct ftrace_event_call					\
 	__attribute__((__aligned__(4))) event_##call;
 #undef FTRACE_ENTRY_DUP
-#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print)		\
-	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
+#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter)	\
+	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \
+		     filter)
 #include "trace_entries.h"
 
 #ifdef CONFIG_PERF_EVENTS
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index 47db7eda0531..d91eb0541b3a 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -66,6 +66,8 @@ FTRACE_ENTRY_REG(function, ftrace_entry,
 
 	F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip),
 
+	FILTER_TRACE_FN,
+
 	perf_ftrace_event_register
 );
 
@@ -80,7 +82,9 @@ FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry,
 		__field_desc(	int,		graph_ent,	depth		)
 	),
 
-	F_printk("--> %lx (%d)", __entry->func, __entry->depth)
+	F_printk("--> %lx (%d)", __entry->func, __entry->depth),
+
+	FILTER_OTHER
 );
 
 /* Function return entry */
@@ -100,7 +104,9 @@ FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry,
 	F_printk("<-- %lx (%d) (start: %llx  end: %llx) over: %d",
 		 __entry->func, __entry->depth,
 		 __entry->calltime, __entry->rettime,
-		 __entry->depth)
+		 __entry->depth),
+
+	FILTER_OTHER
 );
 
 /*
@@ -129,8 +135,9 @@ FTRACE_ENTRY(context_switch, ctx_switch_entry,
 	F_printk("%u:%u:%u  ==> %u:%u:%u [%03u]",
 		 __entry->prev_pid, __entry->prev_prio, __entry->prev_state,
 		 __entry->next_pid, __entry->next_prio, __entry->next_state,
-		 __entry->next_cpu
-		)
+		 __entry->next_cpu),
+
+	FILTER_OTHER
 );
 
 /*
@@ -148,8 +155,9 @@ FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry,
 	F_printk("%u:%u:%u  ==+ %u:%u:%u [%03u]",
 		 __entry->prev_pid, __entry->prev_prio, __entry->prev_state,
 		 __entry->next_pid, __entry->next_prio, __entry->next_state,
-		 __entry->next_cpu
-		)
+		 __entry->next_cpu),
+
+	FILTER_OTHER
 );
 
 /*
@@ -171,7 +179,9 @@ FTRACE_ENTRY(kernel_stack, stack_entry,
 		 "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n",
 		 __entry->caller[0], __entry->caller[1], __entry->caller[2],
 		 __entry->caller[3], __entry->caller[4], __entry->caller[5],
-		 __entry->caller[6], __entry->caller[7])
+		 __entry->caller[6], __entry->caller[7]),
+
+	FILTER_OTHER
 );
 
 FTRACE_ENTRY(user_stack, userstack_entry,
@@ -187,7 +197,9 @@ FTRACE_ENTRY(user_stack, userstack_entry,
 		 "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n",
 		 __entry->caller[0], __entry->caller[1], __entry->caller[2],
 		 __entry->caller[3], __entry->caller[4], __entry->caller[5],
-		 __entry->caller[6], __entry->caller[7])
+		 __entry->caller[6], __entry->caller[7]),
+
+	FILTER_OTHER
 );
 
 /*
@@ -204,7 +216,9 @@ FTRACE_ENTRY(bprint, bprint_entry,
 	),
 
 	F_printk("%08lx fmt:%p",
-		 __entry->ip, __entry->fmt)
+		 __entry->ip, __entry->fmt),
+
+	FILTER_OTHER
 );
 
 FTRACE_ENTRY(print, print_entry,
@@ -217,7 +231,9 @@ FTRACE_ENTRY(print, print_entry,
 	),
 
 	F_printk("%08lx %s",
-		 __entry->ip, __entry->buf)
+		 __entry->ip, __entry->buf),
+
+	FILTER_OTHER
 );
 
 FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw,
@@ -236,7 +252,9 @@ FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw,
 
 	F_printk("%lx %lx %lx %d %x %x",
 		 (unsigned long)__entry->phys, __entry->value, __entry->pc,
-		 __entry->map_id, __entry->opcode, __entry->width)
+		 __entry->map_id, __entry->opcode, __entry->width),
+
+	FILTER_OTHER
 );
 
 FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map,
@@ -254,7 +272,9 @@ FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map,
 
 	F_printk("%lx %lx %lx %d %x",
 		 (unsigned long)__entry->phys, __entry->virt, __entry->len,
-		 __entry->map_id, __entry->opcode)
+		 __entry->map_id, __entry->opcode),
+
+	FILTER_OTHER
 );
 
 
@@ -274,6 +294,8 @@ FTRACE_ENTRY(branch, trace_branch,
 
 	F_printk("%u:%s:%s (%u)",
 		 __entry->line,
-		 __entry->func, __entry->file, __entry->correct)
+		 __entry->func, __entry->file, __entry->correct),
+
+	FILTER_OTHER
 );
 
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 76afaee99dbc..3da3d0ec3584 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -899,6 +899,11 @@ int filter_assign_type(const char *type)
 	return FILTER_OTHER;
 }
 
+static bool is_function_field(struct ftrace_event_field *field)
+{
+	return field->filter_type == FILTER_TRACE_FN;
+}
+
 static bool is_string_field(struct ftrace_event_field *field)
 {
 	return field->filter_type == FILTER_DYN_STRING ||
@@ -986,7 +991,7 @@ static int init_pred(struct filter_parse_state *ps,
 			fn = filter_pred_strloc;
 		else
 			fn = filter_pred_pchar;
-	} else {
+	} else if (!is_function_field(field)) {
 		if (field->is_signed)
 			ret = strict_strtoll(pred->regex.pattern, 0, &val);
 		else
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index a3dbee6d04cd..7b46c9bd22ae 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -23,8 +23,10 @@
  * function and thus become accesible via perf.
  */
 #undef FTRACE_ENTRY_REG
-#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, regfn) \
-	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print))
+#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \
+			 filter, regfn) \
+	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
+		     filter)
 
 /* not needed for this file */
 #undef __field_struct
@@ -52,21 +54,22 @@
 #define F_printk(fmt, args...) fmt, args
 
 #undef FTRACE_ENTRY
-#define FTRACE_ENTRY(name, struct_name, id, tstruct, print)	\
-struct ____ftrace_##name {					\
-	tstruct							\
-};								\
-static void __always_unused ____ftrace_check_##name(void)	\
-{								\
-	struct ____ftrace_##name *__entry = NULL;		\
-								\
-	/* force compile-time check on F_printk() */		\
-	printk(print);						\
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter)	\
+struct ____ftrace_##name {						\
+	tstruct								\
+};									\
+static void __always_unused ____ftrace_check_##name(void)		\
+{									\
+	struct ____ftrace_##name *__entry = NULL;			\
+									\
+	/* force compile-time check on F_printk() */			\
+	printk(print);							\
 }
 
 #undef FTRACE_ENTRY_DUP
-#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print)	\
-	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print))
+#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print, filter)	\
+	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
+		     filter)
 
 #include "trace_entries.h"
 
@@ -75,7 +78,7 @@ static void __always_unused ____ftrace_check_##name(void)	\
 	ret = trace_define_field(event_call, #type, #item,		\
 				 offsetof(typeof(field), item),		\
 				 sizeof(field.item),			\
-				 is_signed_type(type), FILTER_OTHER);	\
+				 is_signed_type(type), filter_type);	\
 	if (ret)							\
 		return ret;
 
@@ -85,7 +88,7 @@ static void __always_unused ____ftrace_check_##name(void)	\
 				 offsetof(typeof(field),		\
 					  container.item),		\
 				 sizeof(field.container.item),		\
-				 is_signed_type(type), FILTER_OTHER);	\
+				 is_signed_type(type), filter_type);	\
 	if (ret)							\
 		return ret;
 
@@ -99,7 +102,7 @@ static void __always_unused ____ftrace_check_##name(void)	\
 		ret = trace_define_field(event_call, event_storage, #item, \
 				 offsetof(typeof(field), item),		\
 				 sizeof(field.item),			\
-				 is_signed_type(type), FILTER_OTHER);	\
+				 is_signed_type(type), filter_type);	\
 		mutex_unlock(&event_storage_mutex);			\
 		if (ret)						\
 			return ret;					\
@@ -112,7 +115,7 @@ static void __always_unused ____ftrace_check_##name(void)	\
 				 offsetof(typeof(field),		\
 					  container.item),		\
 				 sizeof(field.container.item),		\
-				 is_signed_type(type), FILTER_OTHER);	\
+				 is_signed_type(type), filter_type);	\
 	if (ret)							\
 		return ret;
 
@@ -120,17 +123,18 @@ static void __always_unused ____ftrace_check_##name(void)	\
 #define __dynamic_array(type, item)					\
 	ret = trace_define_field(event_call, #type, #item,		\
 				 offsetof(typeof(field), item),		\
-				 0, is_signed_type(type), FILTER_OTHER);\
+				 0, is_signed_type(type), filter_type);\
 	if (ret)							\
 		return ret;
 
 #undef FTRACE_ENTRY
-#define FTRACE_ENTRY(name, struct_name, id, tstruct, print)		\
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter)	\
 int									\
 ftrace_define_fields_##name(struct ftrace_event_call *event_call)	\
 {									\
 	struct struct_name field;					\
 	int ret;							\
+	int filter_type = filter;					\
 									\
 	tstruct;							\
 									\
@@ -161,7 +165,8 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call)	\
 #define F_printk(fmt, args...) #fmt ", "  __stringify(args)
 
 #undef FTRACE_ENTRY_REG
-#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, regfn)\
+#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, filter,\
+			 regfn)						\
 									\
 struct ftrace_event_class event_class_ftrace_##call = {			\
 	.system			= __stringify(TRACE_SYSTEM),		\
@@ -180,9 +185,9 @@ struct ftrace_event_call __used						\
 __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;
 
 #undef FTRACE_ENTRY
-#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print)		\
+#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print, filter)	\
 	FTRACE_ENTRY_REG(call, struct_name, etype,			\
-			 PARAMS(tstruct), PARAMS(print), NULL)
+			 PARAMS(tstruct), PARAMS(print), filter, NULL)
 
 int ftrace_event_is_function(struct ftrace_event_call *call)
 {
-- 
cgit v1.2.3-71-gd317


From 5500fa51199aee770ce53718853732600543619e Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Wed, 15 Feb 2012 15:51:54 +0100
Subject: ftrace, perf: Add filter support for function trace event

Adding support to filter function trace event via perf
interface. It is now possible to use filter interface
in the perf tool like:

  perf record -e ftrace:function --filter="(ip == mm_*)" ls

The filter syntax is restricted to the the 'ip' field only,
and following operators are accepted '==' '!=' '||', ending
up with the filter strings like:

  ip == f1[, ]f2 ... || ip != f3[, ]f4 ...

with comma ',' or space ' ' as a function separator. If the
space ' ' is used as a separator, the right side of the
assignment needs to be enclosed in double quotes '"', e.g.:

  perf record -e ftrace:function --filter '(ip == do_execve,sys_*,ext*)' ls
  perf record -e ftrace:function --filter '(ip == "do_execve,sys_*,ext*")' ls
  perf record -e ftrace:function --filter '(ip == "do_execve sys_* ext*")' ls

The '==' operator adds trace filter with same effect as would
be added via set_ftrace_filter file.

The '!=' operator adds trace filter with same effect as would
be added via set_ftrace_notrace file.

The right side of the '!=', '==' operators is list of functions
or regexp. to be added to filter separated by space.

The '||' operator is used for connecting multiple filter definitions
together. It is possible to have more than one '==' and '!='
operators within one filter string.

Link: http://lkml.kernel.org/r/1329317514-8131-8-git-send-email-jolsa@redhat.com

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace.h             |   7 +-
 kernel/trace/ftrace.c              |   6 ++
 kernel/trace/trace.h               |   2 -
 kernel/trace/trace_event_perf.c    |   4 +-
 kernel/trace/trace_events_filter.c | 165 +++++++++++++++++++++++++++++++++++--
 5 files changed, 172 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 64a309d2fbd6..72a6cabb4d5b 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -250,6 +250,7 @@ int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
 			int len, int reset);
 void ftrace_set_global_filter(unsigned char *buf, int len, int reset);
 void ftrace_set_global_notrace(unsigned char *buf, int len, int reset);
+void ftrace_free_filter(struct ftrace_ops *ops);
 
 int register_ftrace_command(struct ftrace_func_command *cmd);
 int unregister_ftrace_command(struct ftrace_func_command *cmd);
@@ -380,9 +381,6 @@ extern void ftrace_enable_daemon(void);
 #else
 static inline int skip_trace(unsigned long ip) { return 0; }
 static inline int ftrace_force_update(void) { return 0; }
-static inline void ftrace_set_filter(unsigned char *buf, int len, int reset)
-{
-}
 static inline void ftrace_disable_daemon(void) { }
 static inline void ftrace_enable_daemon(void) { }
 static inline void ftrace_release_mod(struct module *mod) {}
@@ -406,6 +404,9 @@ static inline int ftrace_text_reserved(void *start, void *end)
  */
 #define ftrace_regex_open(ops, flag, inod, file) ({ -ENODEV; })
 #define ftrace_set_early_filter(ops, buf, enable) do { } while (0)
+#define ftrace_set_filter(ops, buf, len, reset) ({ -ENODEV; })
+#define ftrace_set_notrace(ops, buf, len, reset) ({ -ENODEV; })
+#define ftrace_free_filter(ops) do { } while (0)
 
 static inline ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf,
 			    size_t cnt, loff_t *ppos) { return -ENODEV; }
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f615f974d90e..867bd1dd2dd0 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1186,6 +1186,12 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash)
 	call_rcu_sched(&hash->rcu, __free_ftrace_hash_rcu);
 }
 
+void ftrace_free_filter(struct ftrace_ops *ops)
+{
+	free_ftrace_hash(ops->filter_hash);
+	free_ftrace_hash(ops->notrace_hash);
+}
+
 static struct ftrace_hash *alloc_ftrace_hash(int size_bits)
 {
 	struct ftrace_hash *hash;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 29f93cd434a5..54faec790bc1 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -776,9 +776,7 @@ struct filter_pred {
 	u64 			val;
 	struct regex		regex;
 	unsigned short		*ops;
-#ifdef CONFIG_FTRACE_STARTUP_TEST
 	struct ftrace_event_field *field;
-#endif
 	int 			offset;
 	int 			not;
 	int 			op;
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index fdeeb5c49627..fee3752ae8f6 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -298,7 +298,9 @@ static int perf_ftrace_function_register(struct perf_event *event)
 static int perf_ftrace_function_unregister(struct perf_event *event)
 {
 	struct ftrace_ops *ops = &event->ftrace_ops;
-	return unregister_ftrace_function(ops);
+	int ret = unregister_ftrace_function(ops);
+	ftrace_free_filter(ops);
+	return ret;
 }
 
 static void perf_ftrace_function_enable(struct perf_event *event)
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 3da3d0ec3584..431dba8b7542 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -81,6 +81,7 @@ enum {
 	FILT_ERR_TOO_MANY_PREDS,
 	FILT_ERR_MISSING_FIELD,
 	FILT_ERR_INVALID_FILTER,
+	FILT_ERR_IP_FIELD_ONLY,
 };
 
 static char *err_text[] = {
@@ -96,6 +97,7 @@ static char *err_text[] = {
 	"Too many terms in predicate expression",
 	"Missing field name and/or value",
 	"Meaningless filter expression",
+	"Only 'ip' field is supported for function trace",
 };
 
 struct opstack_op {
@@ -991,7 +993,12 @@ static int init_pred(struct filter_parse_state *ps,
 			fn = filter_pred_strloc;
 		else
 			fn = filter_pred_pchar;
-	} else if (!is_function_field(field)) {
+	} else if (is_function_field(field)) {
+		if (strcmp(field->name, "ip")) {
+			parse_error(ps, FILT_ERR_IP_FIELD_ONLY, 0);
+			return -EINVAL;
+		}
+	} else {
 		if (field->is_signed)
 			ret = strict_strtoll(pred->regex.pattern, 0, &val);
 		else
@@ -1338,10 +1345,7 @@ static struct filter_pred *create_pred(struct filter_parse_state *ps,
 
 	strcpy(pred.regex.pattern, operand2);
 	pred.regex.len = strlen(pred.regex.pattern);
-
-#ifdef CONFIG_FTRACE_STARTUP_TEST
 	pred.field = field;
-#endif
 	return init_pred(ps, field, &pred) ? NULL : &pred;
 }
 
@@ -1954,6 +1958,148 @@ void ftrace_profile_free_filter(struct perf_event *event)
 	__free_filter(filter);
 }
 
+struct function_filter_data {
+	struct ftrace_ops *ops;
+	int first_filter;
+	int first_notrace;
+};
+
+#ifdef CONFIG_FUNCTION_TRACER
+static char **
+ftrace_function_filter_re(char *buf, int len, int *count)
+{
+	char *str, *sep, **re;
+
+	str = kstrndup(buf, len, GFP_KERNEL);
+	if (!str)
+		return NULL;
+
+	/*
+	 * The argv_split function takes white space
+	 * as a separator, so convert ',' into spaces.
+	 */
+	while ((sep = strchr(str, ',')))
+		*sep = ' ';
+
+	re = argv_split(GFP_KERNEL, str, count);
+	kfree(str);
+	return re;
+}
+
+static int ftrace_function_set_regexp(struct ftrace_ops *ops, int filter,
+				      int reset, char *re, int len)
+{
+	int ret;
+
+	if (filter)
+		ret = ftrace_set_filter(ops, re, len, reset);
+	else
+		ret = ftrace_set_notrace(ops, re, len, reset);
+
+	return ret;
+}
+
+static int __ftrace_function_set_filter(int filter, char *buf, int len,
+					struct function_filter_data *data)
+{
+	int i, re_cnt, ret;
+	int *reset;
+	char **re;
+
+	reset = filter ? &data->first_filter : &data->first_notrace;
+
+	/*
+	 * The 'ip' field could have multiple filters set, separated
+	 * either by space or comma. We first cut the filter and apply
+	 * all pieces separatelly.
+	 */
+	re = ftrace_function_filter_re(buf, len, &re_cnt);
+	if (!re)
+		return -EINVAL;
+
+	for (i = 0; i < re_cnt; i++) {
+		ret = ftrace_function_set_regexp(data->ops, filter, *reset,
+						 re[i], strlen(re[i]));
+		if (ret)
+			break;
+
+		if (*reset)
+			*reset = 0;
+	}
+
+	argv_free(re);
+	return ret;
+}
+
+static int ftrace_function_check_pred(struct filter_pred *pred, int leaf)
+{
+	struct ftrace_event_field *field = pred->field;
+
+	if (leaf) {
+		/*
+		 * Check the leaf predicate for function trace, verify:
+		 *  - only '==' and '!=' is used
+		 *  - the 'ip' field is used
+		 */
+		if ((pred->op != OP_EQ) && (pred->op != OP_NE))
+			return -EINVAL;
+
+		if (strcmp(field->name, "ip"))
+			return -EINVAL;
+	} else {
+		/*
+		 * Check the non leaf predicate for function trace, verify:
+		 *  - only '||' is used
+		*/
+		if (pred->op != OP_OR)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int ftrace_function_set_filter_cb(enum move_type move,
+					 struct filter_pred *pred,
+					 int *err, void *data)
+{
+	/* Checking the node is valid for function trace. */
+	if ((move != MOVE_DOWN) ||
+	    (pred->left != FILTER_PRED_INVALID)) {
+		*err = ftrace_function_check_pred(pred, 0);
+	} else {
+		*err = ftrace_function_check_pred(pred, 1);
+		if (*err)
+			return WALK_PRED_ABORT;
+
+		*err = __ftrace_function_set_filter(pred->op == OP_EQ,
+						    pred->regex.pattern,
+						    pred->regex.len,
+						    data);
+	}
+
+	return (*err) ? WALK_PRED_ABORT : WALK_PRED_DEFAULT;
+}
+
+static int ftrace_function_set_filter(struct perf_event *event,
+				      struct event_filter *filter)
+{
+	struct function_filter_data data = {
+		.first_filter  = 1,
+		.first_notrace = 1,
+		.ops           = &event->ftrace_ops,
+	};
+
+	return walk_pred_tree(filter->preds, filter->root,
+			      ftrace_function_set_filter_cb, &data);
+}
+#else
+static int ftrace_function_set_filter(struct perf_event *event,
+				      struct event_filter *filter)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_FUNCTION_TRACER */
+
 int ftrace_profile_set_filter(struct perf_event *event, int event_id,
 			      char *filter_str)
 {
@@ -1974,9 +2120,16 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id,
 		goto out_unlock;
 
 	err = create_filter(call, filter_str, false, &filter);
-	if (!err)
-		event->filter = filter;
+	if (err)
+		goto free_filter;
+
+	if (ftrace_event_is_function(call))
+		err = ftrace_function_set_filter(event, filter);
 	else
+		event->filter = filter;
+
+free_filter:
+	if (err || ftrace_event_is_function(call))
 		__free_filter(filter);
 
 out_unlock:
-- 
cgit v1.2.3-71-gd317