1 files changed, 166 insertions, 42 deletions

diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 19a359d5e6d5..fee3752ae8f6 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;
@@ -44,23 +49,17 @@ 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 +82,7 @@ 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 +107,69 @@ 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 +192,14 @@ 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;
@@ -146,43 +216,14 @@ 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)
 {
-        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);
+        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,
@@ -214,3 +255,86 @@ __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;
+        int ret = unregister_ftrace_function(ops);
+        ftrace_free_filter(ops);
+        return ret;
+}
+
+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 */