ftrace/x86: Add dynamic allocated trampoline for ftrace_ops

The current method of handling multiple function callbacks is to register
a list function callback that calls all the other callbacks based on
their hash tables and compare it to the function that the callback was
called on. But this is very inefficient.

For example, if you are tracing all functions in the kernel and then
add a kprobe to a function such that the kprobe uses ftrace, the
mcount trampoline will switch from calling the function trace callback
to calling the list callback that will iterate over all registered
ftrace_ops (in this case, the function tracer and the kprobes callback).
That means for every function being traced it checks the hash of the
ftrace_ops for function tracing and kprobes, even though the kprobes
is only set at a single function. The kprobes ftrace_ops is checked
for every function being traced!

Instead of calling the list function for functions that are only being
traced by a single callback, we can call a dynamically allocated
trampoline that calls the callback directly. The function graph tracer
already uses a direct call trampoline when it is being traced by itself
but it is not dynamically allocated. It's trampoline is static in the
kernel core. The infrastructure that called the function graph trampoline
can also be used to call a dynamically allocated one.

For now, only ftrace_ops that are not dynamically allocated can have
a trampoline. That is, users such as function tracer or stack tracer.
kprobes and perf allocate their ftrace_ops, and until there's a safe
way to free the trampoline, it can not be used. The dynamically allocated
ftrace_ops may, although, use the trampoline if the kernel is not
compiled with CONFIG_PREEMPT. But that will come later.

Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Tested-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

1 files changed, 36 insertions, 4 deletions

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 31c90fec4158..15f85eac7e95 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -387,6 +387,8 @@ static int remove_ftrace_list_ops(struct ftrace_ops **list,
 	return ret;
 }
 
+static void ftrace_update_trampoline(struct ftrace_ops *ops);
+
 static int __register_ftrace_function(struct ftrace_ops *ops)
 {
 	if (ops->flags & FTRACE_OPS_FL_DELETED)
@@ -419,6 +421,8 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
 	} else
 		add_ftrace_ops(&ftrace_ops_list, ops);
 
+	ftrace_update_trampoline(ops);
+
 	if (ftrace_enabled)
 		update_ftrace_function();
 
@@ -3020,9 +3024,6 @@ ftrace_enabled_open(struct inode *inode, struct file *file)
 {
 	struct ftrace_iterator *iter;
 
-	if (unlikely(ftrace_disabled))
-		return -ENODEV;
-
 	iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter));
 	if (iter) {
 		iter->pg = ftrace_pages_start;
@@ -3975,6 +3976,9 @@ static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata;
 static char ftrace_graph_notrace_buf[FTRACE_FILTER_SIZE] __initdata;
 static int ftrace_set_func(unsigned long *array, int *idx, int size, char *buffer);
 
+static unsigned long save_global_trampoline;
+static unsigned long save_global_flags;
+
 static int __init set_graph_function(char *str)
 {
 	strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE);
@@ -4696,6 +4700,20 @@ void __init ftrace_init(void)
 	ftrace_disabled = 1;
 }
 
+/* Do nothing if arch does not support this */
+void __weak arch_ftrace_update_trampoline(struct ftrace_ops *ops)
+{
+}
+
+static void ftrace_update_trampoline(struct ftrace_ops *ops)
+{
+	/* Currently, only non dynamic ops can have a trampoline */
+	if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
+		return;
+
+	arch_ftrace_update_trampoline(ops);
+}
+
 #else
 
 static struct ftrace_ops global_ops = {
@@ -4738,6 +4756,10 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
 	return 1;
 }
 
+static void ftrace_update_trampoline(struct ftrace_ops *ops)
+{
+}
+
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 __init void ftrace_init_global_array_ops(struct trace_array *tr)
@@ -5522,7 +5544,6 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 	update_function_graph_func();
 
 	ret = ftrace_startup(&graph_ops, FTRACE_START_FUNC_RET);
-
 out:
 	mutex_unlock(&ftrace_lock);
 	return ret;
@@ -5543,6 +5564,17 @@ void unregister_ftrace_graph(void)
 	unregister_pm_notifier(&ftrace_suspend_notifier);
 	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+	/*
+	 * Function graph does not allocate the trampoline, but
+	 * other global_ops do. We need to reset the ALLOC_TRAMP flag
+	 * if one was used.
+	 */
+	global_ops.trampoline = save_global_trampoline;
+	if (save_global_flags & FTRACE_OPS_FL_ALLOC_TRAMP)
+		global_ops.flags |= FTRACE_OPS_FL_ALLOC_TRAMP;
+#endif
+
  out:
 	mutex_unlock(&ftrace_lock);
 }