[PATCH 4/6] perf: implement uprobe support to PERF_TYPE_PROBE

[Song Liu]

This patch adds uprobe support to perf_probe with similar pattern
as previous patch (for kprobe).

Two functions, create_local_trace_uprobe() and
destroy_local_trace_uprobe(), are created so a uprobe can be created
and attached to the file descriptor created by perf_event_open().

Signed-off-by: Song Liu <songliubraving@xxxxxx>
Reviewed-by: Yonghong Song <yhs@xxxxxx>
Reviewed-by: Josef Bacik <jbacik@xxxxxx>
---
 kernel/trace/trace_event_perf.c | 48 +++++++++++++++++++++-
 kernel/trace/trace_probe.h      |  4 ++
 kernel/trace/trace_uprobe.c     | 90 ++++++++++++++++++++++++++++++++++++-----
 3 files changed, 131 insertions(+), 11 deletions(-)

diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index bf9b99b..4e4de84 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -256,6 +256,39 @@ static int perf_probe_create_kprobe(struct perf_event *p_event,
 }
 #endif /* CONFIG_KPROBE_EVENTS */
 
+#ifdef CONFIG_UPROBE_EVENTS
+static int perf_probe_create_uprobe(struct perf_event *p_event,
+				    struct probe_desc *pd, char *name)
+{
+	struct trace_event_call *tp_event;
+	int ret;
+
+	if (!name)
+		return -EINVAL;
+	tp_event = create_local_trace_uprobe(
+		name, pd->offset, p_event->attr.is_return);
+	if (IS_ERR(tp_event))
+		return PTR_ERR(tp_event);
+	/*
+	 * local trace_uprobe need to hold event_mutex to call
+	 * uprobe_buffer_enable() and uprobe_buffer_disable().
+	 * event_mutex is not required for local trace_kprobes.
+	 */
+	mutex_lock(&event_mutex);
+	ret = perf_trace_event_init(tp_event, p_event);
+	if (ret)
+		destroy_local_trace_uprobe(tp_event);
+	mutex_unlock(&event_mutex);
+	return ret;
+}
+#else
+static int perf_probe_create_uprobe(struct perf_event *p_event,
+				    struct probe_desc *pd, char *name)
+{
+	return -EOPNOTSUPP;
+}
+#endif /* CONFIG_KPROBE_EVENTS */
+
 int perf_probe_init(struct perf_event *p_event)
 {
 	struct probe_desc pd;
@@ -292,7 +325,7 @@ int perf_probe_init(struct perf_event *p_event)
 	if (!p_event->attr.is_uprobe)
 		ret = perf_probe_create_kprobe(p_event, &pd, name);
 	else
-		ret = -EOPNOTSUPP;
+		ret = perf_probe_create_uprobe(p_event, &pd, name);
 out:
 	kfree(name);
 	return ret;
@@ -308,13 +341,26 @@ void perf_trace_destroy(struct perf_event *p_event)
 
 void perf_probe_destroy(struct perf_event *p_event)
 {
+	/*
+	 * local trace_uprobe need to hold event_mutex to call
+	 * uprobe_buffer_enable() and uprobe_buffer_disable().
+	 * event_mutex is not required for local trace_kprobes.
+	 */
+	if (p_event->attr.is_uprobe)
+		mutex_lock(&event_mutex);
 	perf_trace_event_close(p_event);
 	perf_trace_event_unreg(p_event);
+	if (p_event->attr.is_uprobe)
+		mutex_unlock(&event_mutex);
 
 	if (!p_event->attr.is_uprobe) {
 #ifdef CONFIG_KPROBE_EVENTS
 		destroy_local_trace_kprobe(p_event->tp_event);
 #endif
+	} else {
+#ifdef CONFIG_UPROBE_EVENTS
+		destroy_local_trace_uprobe(p_event->tp_event);
+#endif
 	}
 }
 
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 910ae1b..86b5925 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -417,4 +417,8 @@ extern struct trace_event_call *
 create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
 			  bool is_return);
 extern void destroy_local_trace_kprobe(struct trace_event_call *event_call);
+
+extern struct trace_event_call *
+create_local_trace_uprobe(char *name, unsigned long offs, bool is_return);
+extern void destroy_local_trace_uprobe(struct trace_event_call *event_call);
 #endif
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 4525e02..4d805d2 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -31,8 +31,8 @@
 #define UPROBE_EVENT_SYSTEM	"uprobes"
 
 struct uprobe_trace_entry_head {
-	struct trace_entry	ent;
-	unsigned long		vaddr[];
+	struct trace_entry      ent;
+	unsigned long           vaddr[];
 };
 
 #define SIZEOF_TRACE_ENTRY(is_return)			\
@@ -1293,16 +1293,25 @@ static struct trace_event_functions uprobe_funcs = {
 	.trace		= print_uprobe_event
 };
 
-static int register_uprobe_event(struct trace_uprobe *tu)
+static inline void init_trace_event_call(struct trace_uprobe *tu,
+					 struct trace_event_call *call)
 {
-	struct trace_event_call *call = &tu->tp.call;
-	int ret;
-
-	/* Initialize trace_event_call */
 	INIT_LIST_HEAD(&call->class->fields);
 	call->event.funcs = &uprobe_funcs;
 	call->class->define_fields = uprobe_event_define_fields;
 
+	call->flags = TRACE_EVENT_FL_UPROBE;
+	call->class->reg = trace_uprobe_register;
+	call->data = tu;
+}
+
+static int register_uprobe_event(struct trace_uprobe *tu)
+{
+	struct trace_event_call *call = &tu->tp.call;
+	int ret = 0;
+
+	init_trace_event_call(tu, call);
+
 	if (set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0)
 		return -ENOMEM;
 
@@ -1312,9 +1321,6 @@ static int register_uprobe_event(struct trace_uprobe *tu)
 		return -ENODEV;
 	}
 
-	call->flags = TRACE_EVENT_FL_UPROBE;
-	call->class->reg = trace_uprobe_register;
-	call->data = tu;
 	ret = trace_add_event_call(call);
 
 	if (ret) {
@@ -1340,6 +1346,70 @@ static int unregister_uprobe_event(struct trace_uprobe *tu)
 	return 0;
 }
 
+#ifdef CONFIG_PERF_EVENTS
+struct trace_event_call *
+create_local_trace_uprobe(char *name, unsigned long offs, bool is_return)
+{
+	struct trace_uprobe *tu;
+	struct inode *inode;
+	struct path path;
+	int ret;
+
+	ret = kern_path(name, LOOKUP_FOLLOW, &path);
+	if (ret)
+		return ERR_PTR(ret);
+
+	inode = igrab(d_inode(path.dentry));
+	path_put(&path);
+
+	if (!inode || !S_ISREG(inode->i_mode)) {
+		iput(inode);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/*
+	 * local trace_kprobes are not added to probe_list, so they are never
+	 * searched in find_trace_kprobe(). Therefore, there is no concern of
+	 * duplicated name "DUMMY_EVENT" here.
+	 */
+	tu = alloc_trace_uprobe(UPROBE_EVENT_SYSTEM, "DUMMY_EVENT", 0,
+				is_return);
+
+	if (IS_ERR(tu)) {
+		pr_info("Failed to allocate trace_uprobe.(%d)\n",
+			(int)PTR_ERR(tu));
+		return ERR_CAST(tu);
+	}
+
+	tu->offset = offs;
+	tu->inode = inode;
+	tu->filename = kstrdup(name, GFP_KERNEL);
+	init_trace_event_call(tu, &tu->tp.call);
+
+	if (set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	return &tu->tp.call;
+error:
+	free_trace_uprobe(tu);
+	return ERR_PTR(ret);
+}
+
+void destroy_local_trace_uprobe(struct trace_event_call *event_call)
+{
+	struct trace_uprobe *tu;
+
+	tu = container_of(event_call, struct trace_uprobe, tp.call);
+
+	kfree(tu->tp.call.print_fmt);
+	tu->tp.call.print_fmt = NULL;
+
+	free_trace_uprobe(tu);
+}
+#endif /* CONFIG_PERF_EVENTS */
+
 /* Make a trace interface for controling probe points */
 static __init int init_uprobe_trace(void)
 {
-- 
2.9.5