ftrace: Rework event_create_dir()

Rework event_create_dir() to use an array of static data instead of
function pointers where possible.

The problem is that it would call the function pointer on module load
before parse_args(), possibly even before jump_labels were initialized.
Luckily the generated functions don't use jump_labels but it still seems
fragile. It also gets in the way of changing when we make the module map
executable.

The generated function are basically calling trace_define_field() with a
bunch of static arguments. So instead of a function, capture these
arguments in a static array, avoiding the function call.

Now there are a number of cases where the fields are dynamic (syscall
arguments, kprobes and uprobes), in which case a static array does not
work, for these we preserve the function call. Luckily all these cases
are not related to modules and so we can retain the function call for
them.

Also fix up all broken tracepoint definitions that now generate a
compile error.

Tested-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20191111132458.342979914@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 20 insertions, 30 deletions

diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index fa8fbff736d6..53935259f701 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -198,11 +198,10 @@ print_syscall_exit(struct trace_iterator *iter, int flags,
 
 extern char *__bad_type_size(void);
 
-#define SYSCALL_FIELD(type, field, name)				\
-	sizeof(type) != sizeof(trace.field) ?				\
-		__bad_type_size() :					\
-		#type, #name, offsetof(typeof(trace), field),		\
-		sizeof(trace.field), is_signed_type(type)
+#define SYSCALL_FIELD(_type, _name) {					\
+	.type = #_type, .name = #_name,					\
+	.size = sizeof(_type), .align = __alignof__(_type),		\
+	.is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }
 
 static int __init
 __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
@@ -269,42 +268,22 @@ static int __init syscall_enter_define_fields(struct trace_event_call *call)
 {
 	struct syscall_trace_enter trace;
 	struct syscall_metadata *meta = call->data;
-	int ret;
-	int i;
 	int offset = offsetof(typeof(trace), args);
-
-	ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr),
-				 FILTER_OTHER);
-	if (ret)
-		return ret;
+	int ret, i;
 
 	for (i = 0; i < meta->nb_args; i++) {
 		ret = trace_define_field(call, meta->types[i],
 					 meta->args[i], offset,
 					 sizeof(unsigned long), 0,
 					 FILTER_OTHER);
+		if (ret)
+			break;
 		offset += sizeof(unsigned long);
 	}
 
 	return ret;
 }
 
-static int __init syscall_exit_define_fields(struct trace_event_call *call)
-{
-	struct syscall_trace_exit trace;
-	int ret;
-
-	ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr),
-				 FILTER_OTHER);
-	if (ret)
-		return ret;
-
-	ret = trace_define_field(call, SYSCALL_FIELD(long, ret, ret),
-				 FILTER_OTHER);
-
-	return ret;
-}
-
 static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 {
 	struct trace_array *tr = data;
@@ -502,6 +481,13 @@ static int __init init_syscall_trace(struct trace_event_call *call)
 	return id;
 }
 
+static struct trace_event_fields __refdata syscall_enter_fields_array[] = {
+	SYSCALL_FIELD(int, __syscall_nr),
+	{ .type = TRACE_FUNCTION_TYPE,
+	  .define_fields = syscall_enter_define_fields },
+	{}
+};
+
 struct trace_event_functions enter_syscall_print_funcs = {
 	.trace		= print_syscall_enter,
 };
@@ -513,7 +499,7 @@ struct trace_event_functions exit_syscall_print_funcs = {
 struct trace_event_class __refdata event_class_syscall_enter = {
 	.system		= "syscalls",
 	.reg		= syscall_enter_register,
-	.define_fields	= syscall_enter_define_fields,
+	.fields_array	= syscall_enter_fields_array,
 	.get_fields	= syscall_get_enter_fields,
 	.raw_init	= init_syscall_trace,
 };
@@ -521,7 +507,11 @@ struct trace_event_class __refdata event_class_syscall_enter = {
 struct trace_event_class __refdata event_class_syscall_exit = {
 	.system		= "syscalls",
 	.reg		= syscall_exit_register,
-	.define_fields	= syscall_exit_define_fields,
+	.fields_array	= (struct trace_event_fields[]){
+		SYSCALL_FIELD(int, __syscall_nr),
+		SYSCALL_FIELD(long, ret),
+		{}
+	},
 	.fields		= LIST_HEAD_INIT(event_class_syscall_exit.fields),
 	.raw_init	= init_syscall_trace,
 };