[PATCH v2 4/6] perf: implement support of PERF_TYPE_UPROBE

[Song Liu]

This patch adds perf_uprobe support 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>
---
 include/linux/trace_events.h    |  2 +
 kernel/events/core.c            | 39 +++++++++++++++++-
 kernel/trace/trace_event_perf.c | 58 ++++++++++++++++++++++++++
 kernel/trace/trace_probe.h      |  4 ++
 kernel/trace/trace_uprobe.c     | 90 ++++++++++++++++++++++++++++++++++++-----
 5 files changed, 181 insertions(+), 12 deletions(-)

diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 51f748c9..9272fa6 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -496,6 +496,8 @@ extern int  perf_trace_add(struct perf_event *event, int flags);
 extern void perf_trace_del(struct perf_event *event, int flags);
 extern int  perf_kprobe_init(struct perf_event *event);
 extern void perf_kprobe_destroy(struct perf_event *event);
+extern int  perf_uprobe_init(struct perf_event *event);
+extern void perf_uprobe_destroy(struct perf_event *event);
 extern int  ftrace_profile_set_filter(struct perf_event *event, int event_id,
 				     char *filter_str);
 extern void ftrace_profile_free_filter(struct perf_event *event);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index daa6e0a..b566a53 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7992,6 +7992,28 @@ static int perf_kprobe_event_init(struct perf_event *event)
 	return 0;
 }
 
+static int perf_uprobe_event_init(struct perf_event *event)
+{
+	int err;
+
+	if (event->attr.type != PERF_TYPE_UPROBE)
+		return -ENOENT;
+
+	/*
+	 * no branch sampling for probe events
+	 */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
+	err = perf_uprobe_init(event);
+	if (err)
+		return err;
+
+	event->destroy = perf_uprobe_destroy;
+
+	return 0;
+}
+
 static struct pmu perf_tracepoint = {
 	.task_ctx_nr	= perf_sw_context,
 
@@ -8013,10 +8035,21 @@ static struct pmu perf_kprobe = {
 	.read		= perf_swevent_read,
 };
 
+static struct pmu perf_uprobe = {
+	.task_ctx_nr	= perf_sw_context,
+	.event_init	= perf_uprobe_event_init,
+	.add		= perf_trace_add,
+	.del		= perf_trace_del,
+	.start		= perf_swevent_start,
+	.stop		= perf_swevent_stop,
+	.read		= perf_swevent_read,
+};
+
 static inline void perf_tp_register(void)
 {
 	perf_pmu_register(&perf_tracepoint, "tracepoint", PERF_TYPE_TRACEPOINT);
 	perf_pmu_register(&perf_kprobe, "kprobe", PERF_TYPE_KPROBE);
+	perf_pmu_register(&perf_uprobe, "uprobe", PERF_TYPE_UPROBE);
 }
 
 static void perf_event_free_filter(struct perf_event *event)
@@ -8099,7 +8132,8 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd)
 	struct bpf_prog *prog;
 
 	if (event->attr.type != PERF_TYPE_TRACEPOINT &&
-	    event->attr.type != PERF_TYPE_KPROBE)
+	    event->attr.type != PERF_TYPE_KPROBE &&
+	    event->attr.type != PERF_TYPE_UPROBE)
 		return perf_event_set_bpf_handler(event, prog_fd);
 
 	if (event->tp_event->prog)
@@ -8572,7 +8606,8 @@ static int perf_event_set_filter(struct perf_event *event, void __user *arg)
 	int ret = -EINVAL;
 
 	if (((event->attr.type != PERF_TYPE_TRACEPOINT &&
-	      event->attr.type != PERF_TYPE_KPROBE) ||
+	      event->attr.type != PERF_TYPE_KPROBE &&
+	      event->attr.type != PERF_TYPE_UPROBE) ||
 	     !IS_ENABLED(CONFIG_EVENT_TRACING)) &&
 	    !has_addr_filter(event))
 		return -EINVAL;
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 7cf0d99..1b97ea2 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -272,6 +272,52 @@ int perf_kprobe_init(struct perf_event *p_event)
 #endif /* CONFIG_KPROBE_EVENTS */
 }
 
+int perf_uprobe_init(struct perf_event *p_event)
+{
+	int ret;
+	char *path = NULL;
+	struct trace_event_call *tp_event;
+
+#ifdef CONFIG_UPROBE_EVENTS
+	if (!p_event->attr.uprobe_path)
+		return -EINVAL;
+	path = kzalloc(PATH_MAX, GFP_KERNEL);
+	if (!path)
+		return -ENOMEM;
+	ret = strncpy_from_user(
+		path, u64_to_user_ptr(p_event->attr.uprobe_path), PATH_MAX);
+	if (ret < 0)
+		goto out;
+	if (path[0] == '\0') {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	tp_event = create_local_trace_uprobe(
+		path, p_event->attr.probe_offset, p_event->attr.config != 0);
+	if (IS_ERR(tp_event)) {
+		ret = PTR_ERR(tp_event);
+		goto out;
+	}
+
+	/*
+	 * 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);
+out:
+	kfree(path);
+	return ret;
+#else
+	return -EOPNOTSUPP;
+#endif /* CONFIG_UPROBE_EVENTS */
+}
+
 void perf_trace_destroy(struct perf_event *p_event)
 {
 	mutex_lock(&event_mutex);
@@ -290,6 +336,18 @@ void perf_kprobe_destroy(struct perf_event *p_event)
 #endif
 }
 
+void perf_uprobe_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);
+
+#ifdef CONFIG_UPROBE_EVENTS
+	destroy_local_trace_uprobe(p_event->tp_event);
+#endif
+}
+
 int perf_trace_add(struct perf_event *p_event, int flags)
 {
 	struct trace_event_call *tp_event = p_event->tp_event;
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