function_graph: Add an array structure that will allow multiple callb…

…acks

Add an array structure that will eventually allow the function graph tracer
to have up to 16 simultaneous callbacks attached. It's an array of 16
fgraph_ops pointers, that is assigned when one is registered. On entry of a
function the entry of the first item in the array is called, and if it
returns zero, then the callback returns non zero if it wants the return
callback to be called on exit of the function.

The array will simplify the process of having more than one callback
attached to the same function, as its index into the array can be stored on
the shadow stack. We need to only save the index, because this will allow
the fgraph_ops to be freed before the function returns (which may happen if
the function call schedule for a long time).

Co-developed with Masami Hiramatsu:
Link: https://lore.kernel.org/linux-trace-kernel/171509095075.162236.8272148192748284581.stgit@devnote2
Link: https://lore.kernel.org/linux-trace-kernel/[email protected]

Cc: Mark Rutland <[email protected]>
Cc: Mathieu Desnoyers <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Alexei Starovoitov <[email protected]>
Cc: Florent Revest <[email protected]>
Cc: Martin KaFai Lau <[email protected]>
Cc: bpf <[email protected]>
Cc: Sven Schnelle <[email protected]>
Cc: Alexei Starovoitov <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Daniel Borkmann <[email protected]>
Cc: Alan Maguire <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Guo Ren <[email protected]>
Reviewed-by: Masami Hiramatsu (Google) <[email protected]>
Signed-off-by: Steven Rostedt (VMware) <[email protected]>
Signed-off-by: Masami Hiramatsu (Google) <[email protected]>
Signed-off-by: Steven Rostedt (Google) <[email protected]>

kernel/trace/fgraph.c

@@ -52,6 +52,11 @@
 DEFINE_STATIC_KEY_FALSE(kill_ftrace_graph);
 int ftrace_graph_active;
 
+static int fgraph_array_cnt;
+#define FGRAPH_ARRAY_SIZE	16
+
+static struct fgraph_ops *fgraph_array[FGRAPH_ARRAY_SIZE];
+
 /* Both enabled by default (can be cleared by function_graph tracer flags */
 static bool fgraph_sleep_time = true;
 
@@ -75,6 +80,20 @@ int __weak ftrace_disable_ftrace_graph_caller(void)
 }
 #endif
 
+int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
+{
+	return 0;
+}
+
+static void ftrace_graph_ret_stub(struct ftrace_graph_ret *trace)
+{
+}
+
+static struct fgraph_ops fgraph_stub = {
+	.entryfunc = ftrace_graph_entry_stub,
+	.retfunc = ftrace_graph_ret_stub,
+};
+
 /**
  * ftrace_graph_stop - set to permanently disable function graph tracing
  *
@@ -161,7 +180,7 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 		goto out;
 
 	/* Only trace if the calling function expects to */
-	if (!ftrace_graph_entry(&trace))
+	if (!fgraph_array[0]->entryfunc(&trace))
 		goto out_ret;
 
 	return 0;
@@ -276,7 +295,7 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs
 	trace.retval = fgraph_ret_regs_return_value(ret_regs);
 #endif
 	trace.rettime = trace_clock_local();
-	ftrace_graph_return(&trace);
+	fgraph_array[0]->retfunc(&trace);
 	/*
 	 * The ftrace_graph_return() may still access the current
 	 * ret_stack structure, we need to make sure the update of
@@ -412,11 +431,6 @@ void ftrace_graph_sleep_time_control(bool enable)
 	fgraph_sleep_time = enable;
 }
 
-int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
-{
-	return 0;
-}
-
 /*
  * Simply points to ftrace_stub, but with the proper protocol.
  * Defined by the linker script in linux/vmlinux.lds.h
@@ -654,57 +668,91 @@ static int start_graph_tracing(void)
 int register_ftrace_graph(struct fgraph_ops *gops)
 {
 	int ret = 0;
+	int i;
 
 	mutex_lock(&ftrace_lock);
 
-	/* we currently allow only one tracer registered at a time */
-	if (ftrace_graph_active) {
+	if (!fgraph_array[0]) {
+		/* The array must always have real data on it */
+		for (i = 0; i < FGRAPH_ARRAY_SIZE; i++)
+			fgraph_array[i] = &fgraph_stub;
+	}
+
+	/* Look for an available spot */
+	for (i = 0; i < FGRAPH_ARRAY_SIZE; i++) {
+		if (fgraph_array[i] == &fgraph_stub)
+			break;
+	}
+	if (i >= FGRAPH_ARRAY_SIZE) {
 		ret = -EBUSY;
 		goto out;
 	}
 
-	register_pm_notifier(&ftrace_suspend_notifier);
+	fgraph_array[i] = gops;
+	if (i + 1 > fgraph_array_cnt)
+		fgraph_array_cnt = i + 1;
 
 	ftrace_graph_active++;
-	ret = start_graph_tracing();
-	if (ret) {
-		ftrace_graph_active--;
-		goto out;
-	}
 
-	ftrace_graph_return = gops->retfunc;
+	if (ftrace_graph_active == 1) {
+		register_pm_notifier(&ftrace_suspend_notifier);
+		ret = start_graph_tracing();
+		if (ret) {
+			ftrace_graph_active--;
+			goto out;
+		}
+
+		ftrace_graph_return = gops->retfunc;
 
-	/*
-	 * Update the indirect function to the entryfunc, and the
-	 * function that gets called to the entry_test first. Then
-	 * call the update fgraph entry function to determine if
-	 * the entryfunc should be called directly or not.
-	 */
-	__ftrace_graph_entry = gops->entryfunc;
-	ftrace_graph_entry = ftrace_graph_entry_test;
-	update_function_graph_func();
+		/*
+		 * Update the indirect function to the entryfunc, and the
+		 * function that gets called to the entry_test first. Then
+		 * call the update fgraph entry function to determine if
+		 * the entryfunc should be called directly or not.
+		 */
+		__ftrace_graph_entry = gops->entryfunc;
+		ftrace_graph_entry = ftrace_graph_entry_test;
+		update_function_graph_func();
 
-	ret = ftrace_startup(&graph_ops, FTRACE_START_FUNC_RET);
+		ret = ftrace_startup(&graph_ops, FTRACE_START_FUNC_RET);
+	}
 out:
 	mutex_unlock(&ftrace_lock);
 	return ret;
 }
 
 void unregister_ftrace_graph(struct fgraph_ops *gops)
 {
+	int i;
+
 	mutex_lock(&ftrace_lock);
 
 	if (unlikely(!ftrace_graph_active))
 		goto out;
 
-	ftrace_graph_active--;
-	ftrace_graph_return = ftrace_stub_graph;
-	ftrace_graph_entry = ftrace_graph_entry_stub;
-	__ftrace_graph_entry = ftrace_graph_entry_stub;
-	ftrace_shutdown(&graph_ops, FTRACE_STOP_FUNC_RET);
-	unregister_pm_notifier(&ftrace_suspend_notifier);
-	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
+	for (i = 0; i < fgraph_array_cnt; i++)
+		if (gops == fgraph_array[i])
+			break;
+	if (i >= fgraph_array_cnt)
+		goto out;
 
+	fgraph_array[i] = &fgraph_stub;
+	if (i + 1 == fgraph_array_cnt) {
+		for (; i >= 0; i--)
+			if (fgraph_array[i] != &fgraph_stub)
+				break;
+		fgraph_array_cnt = i + 1;
+	}
+
+	ftrace_graph_active--;
+	if (!ftrace_graph_active) {
+		ftrace_graph_return = ftrace_stub_graph;
+		ftrace_graph_entry = ftrace_graph_entry_stub;
+		__ftrace_graph_entry = ftrace_graph_entry_stub;
+		ftrace_shutdown(&graph_ops, FTRACE_STOP_FUNC_RET);
+		unregister_pm_notifier(&ftrace_suspend_notifier);
+		unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
+	}
  out:
 	mutex_unlock(&ftrace_lock);
 }