adjust tracepoint field type based on size

Fix issue #1807

tracepoint may have a format like this:
(from syscalls/sys_enter_socket)
	field:unsigned short common_type;	offset:0;	size:2;	signed:0;
	field:unsigned char common_flags;	offset:2;	size:1;	signed:0;
	field:unsigned char common_preempt_count;	offset:3;	size:1;	signed:0;
	field:int common_pid;	offset:4;	size:4;	signed:1;

	field:int __syscall_nr;	offset:8;	size:4;	signed:1;
	field:int family;	offset:16;	size:8;	signed:0;
	field:int type;	offset:24;	size:8;	signed:0;
	field:int protocol;	offset:32;	size:8;	signed:0;

Current rewriter generates:
    struct tracepoint__syscalls__sys_enter_socket {
	    u64 __do_not_use__;
	    int __syscall_nr;
	    int family;
	    int type;
	    int protocol;
    };

This is incorrect as in the above structure, offsets of
`family`/`type`/`procotol` becomingg 12/16/20.

This patch fixed the issue by adjusting field type based on its size.
The new structure:
    struct tracepoint__syscalls__sys_enter_socket {
	    u64 __do_not_use__;
	    int __syscall_nr;
	    s64 family;
	    s64 type;
	    s64 protocol;
    };
The offsets of all fields are correct now.

Signed-off-by: Yonghong Song <[email protected]>

src/cc/frontends/clang/tp_frontend_action.cc

@@ -62,16 +62,32 @@ static inline field_kind_t _get_field_kind(string const& line,
  if (field_pos == string::npos)
  return field_kind_t::invalid;
 
- auto semi_pos = line.find(';', field_pos);
+ auto field_semi_pos = line.find(';', field_pos);
+ if (field_semi_pos == string::npos)
+ return field_kind_t::invalid;
+
+ auto offset_pos = line.find("offset:", field_semi_pos);
+ if (offset_pos == string::npos)
+ return field_kind_t::invalid;
+
+ auto semi_pos = line.find(';', offset_pos);
  if (semi_pos == string::npos)
  return field_kind_t::invalid;
 
  auto size_pos = line.find("size:", semi_pos);
  if (size_pos == string::npos)
  return field_kind_t::invalid;
 
+ semi_pos = line.find(';', size_pos);
+ if (semi_pos == string::npos)
+ return field_kind_t::invalid;
+
+ auto size_str = line.substr(size_pos + 5,
+ semi_pos - size_pos - 5);
+ int size = std::stoi(size_str, nullptr);
+
  auto field = line.substr(field_pos + 6/*"field:"*/,
- semi_pos - field_pos - 6);
+ field_semi_pos - field_pos - 6);
  auto pos = field.find_last_of("\t ");
  if (pos == string::npos)
  return field_kind_t::invalid;
@@ -83,6 +99,32 @@ static inline field_kind_t _get_field_kind(string const& line,
  if (field_name.find("common_") == 0)
  return field_kind_t::common;
 
+ // adjust the field_type based on the size of field
+ // otherwise, incorrect value may be retrieved for big endian
+ // and the field may have incorrect structure offset.
+ if (size == 2) {
+ if (field_type == "char" || field_type == "int8_t")
+ field_type = "s16";
+ if (field_type == "unsigned char" || field_type == "uint8_t")
+ field_type = "u16";
+ } else if (size == 4) {
+ if (field_type == "char" || field_type == "short" ||
+ field_type == "int8_t" || field_type == "int16_t")
+ field_type = "s32";
+ if (field_type == "unsigned char" || field_type == "unsiggned short" ||
+ field_type == "uint8_t" || field_type == "uint16_t")
+ field_type = "u32";
+ } else if (size == 8) {
+ if (field_type == "char" || field_type == "short" || field_type == "int" ||
+ field_type == "int8_t" || field_type == "int16_t" ||
+ field_type == "int32_t")
+ field_type = "s64";
+ if (field_type == "unsigned char" || field_type == "unsiggned short" ||
+ field_type == "unsigned int" || field_type == "uint8_t" ||
+ field_type == "uint16_t" || field_type == "uint32_t")
+ field_type = "u64";
+ }
+
  return field_kind_t::regular;
 }