tracing: Add fields format definition for syscall events

Define the format of the syscall trace fields to parse the binary
values from a raw trace using the syscall events "format" file.

This is defined dynamically using the syscalls metadata.
It prepares the export of syscall event raw records to perf
counters.

Example:

$ cat /debug/tracing/events/syscalls/sys_enter_sched_getparam/format
name: sys_enter_sched_getparam
ID: 39
format:
	field:unsigned short common_type;	offset:0;	size:2;
	field:unsigned char common_flags;	offset:2;	size:1;
	field:unsigned char common_preempt_count;	offset:3;	size:1;
	field:int common_pid;	offset:4;	size:4;
	field:int common_tgid;	offset:8;	size:4;

	field:pid_t pid;	offset:12;	size:8;
	field:struct sched_param * param;	offset:20;	size:8;

print fmt: "pid: 0x%08lx, param: 0x%08lx", ((unsigned long)(REC->pid)), ((unsigned long)(REC->param))

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: Jiaying Zhang <jiayingz@google.com>
Cc: Martin Bligh <mbligh@google.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Jason Baron <jbaron@redhat.com>

3 files changed, 49 insertions, 0 deletions

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 5541e75..87d06c1 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -189,6 +189,7 @@ static void prof_sysexit_disable_##sname(struct ftrace_event_call *event_call) \
 		.system                 = "syscalls",			\
 		.event                  = &event_syscall_enter,		\
 		.raw_init		= init_enter_##sname,		\
+		.show_format		= ftrace_format_syscall,	\
 		.regfunc		= reg_event_syscall_enter,	\
 		.unregfunc		= unreg_event_syscall_enter,	\
 		.data			= "sys"#sname,			\
diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index 3ab6dd1..0cb0362 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -55,6 +55,8 @@ extern int reg_event_syscall_enter(void *ptr);
 extern void unreg_event_syscall_enter(void *ptr);
 extern int reg_event_syscall_exit(void *ptr);
 extern void unreg_event_syscall_exit(void *ptr);
+extern int
+ftrace_format_syscall(struct ftrace_event_call *call, struct trace_seq *s);
 enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags);
 enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags);
 #endif
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index f4eaec3..9ee6386 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -105,6 +105,52 @@ print_syscall_exit(struct trace_iterator *iter, int flags)
 	return TRACE_TYPE_HANDLED;
 }
 
+int ftrace_format_syscall(struct ftrace_event_call *call, struct trace_seq *s)
+{
+	int i;
+	int nr;
+	int ret = 0;
+	struct syscall_metadata *entry;
+	int offset = sizeof(struct trace_entry);
+
+	nr = syscall_name_to_nr((char *)call->data);
+	entry = syscall_nr_to_meta(nr);
+
+	if (!entry)
+		return ret;
+
+	for (i = 0; i < entry->nb_args; i++) {
+		ret = trace_seq_printf(s, "\tfield:%s %s;", entry->types[i],
+				        entry->args[i]);
+		if (!ret)
+			return 0;
+		ret = trace_seq_printf(s, "\toffset:%d;\tsize:%lu;\n", offset,
+				       sizeof(unsigned long));
+		if (!ret)
+			return 0;
+		offset += sizeof(unsigned long);
+	}
+
+	trace_seq_printf(s, "\nprint fmt: \"");
+	for (i = 0; i < entry->nb_args; i++) {
+		ret = trace_seq_printf(s, "%s: 0x%%0%lulx%s", entry->args[i],
+				        sizeof(unsigned long),
+					i == entry->nb_args - 1 ? "\", " : ", ");
+		if (!ret)
+			return 0;
+	}
+
+	for (i = 0; i < entry->nb_args; i++) {
+		ret = trace_seq_printf(s, "((unsigned long)(REC->%s))%s",
+				        entry->args[i],
+					i == entry->nb_args - 1 ? "\n" : ", ");
+		if (!ret)
+			return 0;
+	}
+
+	return ret;
+}
+
 void ftrace_syscall_enter(struct pt_regs *regs, long id)
 {
 	struct syscall_trace_enter *entry;