perf dwarf-aux: Handle type transfer for memory access

We want to track type states as instructions are executed.  Each
instruction can access compound types like struct or union and load/
store its members to a different location.

The die_deref_ptr_type() is to find a type of memory access with a
pointer variable.  If it points to a compound type like struct, the
target memory is a member in the struct.  The access will happen with an
offset indicating which member it refers.  Let's follow the DWARF info
to figure out the type of the pointer target.

For example, say we have the following code.

  struct foo {
    int a;
    int b;
  };

  struct foo *p = malloc(sizeof(*p));
  p->b = 0;

The last pointer access should produce x86 asm like below:

  mov  0x0, 4(%rbx)

And we know %rbx register has a pointer to struct foo.  Then offset 4
should return the debug info of member 'b'.

Also variables of compound types can be accessed directly without a
pointer.  The die_get_member_type() is to handle a such case.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20240319055115.4063940-4-namhyung@kernel.org
[ Check if die_get_real_type() returned NULL ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/dwarf-aux.c

@@ -1838,3 +1838,116 @@ int die_get_scopes(Dwarf_Die *cu_die, Dwarf_Addr pc, Dwarf_Die **scopes)
 	*scopes = data.scopes;
 	return data.nr;
 }
+
+static int __die_find_member_offset_cb(Dwarf_Die *die_mem, void *arg)
+{
+	Dwarf_Die type_die;
+	Dwarf_Word size, loc;
+	Dwarf_Word offset = (long)arg;
+	int tag = dwarf_tag(die_mem);
+
+	if (tag != DW_TAG_member)
+		return DIE_FIND_CB_SIBLING;
+
+	/* Unions might not have location */
+	if (die_get_data_member_location(die_mem, &loc) < 0)
+		loc = 0;
+
+	if (offset == loc)
+		return DIE_FIND_CB_END;
+
+	if (die_get_real_type(die_mem, &type_die) == NULL) {
+		// TODO: add a pr_debug_dtp() later for this unlikely failure
+		return DIE_FIND_CB_SIBLING;
+	}
+
+	if (dwarf_aggregate_size(&type_die, &size) < 0)
+		size = 0;
+
+	if (loc < offset && offset < (loc + size))
+		return DIE_FIND_CB_END;
+
+	return DIE_FIND_CB_SIBLING;
+}
+
+/**
+ * die_get_member_type - Return type info of struct member
+ * @type_die: a type DIE
+ * @offset: offset in the type
+ * @die_mem: a buffer to save the resulting DIE
+ *
+ * This function returns a type of a member in @type_die where it's located at
+ * @offset if it's a struct.  For now, it just returns the first matching
+ * member in a union.  For other types, it'd return the given type directly
+ * if it's within the size of the type or NULL otherwise.
+ */
+Dwarf_Die *die_get_member_type(Dwarf_Die *type_die, int offset,
+			       Dwarf_Die *die_mem)
+{
+	Dwarf_Die *member;
+	Dwarf_Die mb_type;
+	int tag;
+
+	tag = dwarf_tag(type_die);
+	/* If it's not a compound type, return the type directly */
+	if (tag != DW_TAG_structure_type && tag != DW_TAG_union_type) {
+		Dwarf_Word size;
+
+		if (dwarf_aggregate_size(type_die, &size) < 0)
+			size = 0;
+
+		if ((unsigned)offset >= size)
+			return NULL;
+
+		*die_mem = *type_die;
+		return die_mem;
+	}
+
+	mb_type = *type_die;
+	/* TODO: Handle union types better? */
+	while (tag == DW_TAG_structure_type || tag == DW_TAG_union_type) {
+		member = die_find_child(&mb_type, __die_find_member_offset_cb,
+					(void *)(long)offset, die_mem);
+		if (member == NULL)
+			return NULL;
+
+		if (die_get_real_type(member, &mb_type) == NULL)
+			return NULL;
+
+		tag = dwarf_tag(&mb_type);
+
+		if (tag == DW_TAG_structure_type || tag == DW_TAG_union_type) {
+			Dwarf_Word loc;
+
+			/* Update offset for the start of the member struct */
+			if (die_get_data_member_location(member, &loc) == 0)
+				offset -= loc;
+		}
+	}
+	*die_mem = mb_type;
+	return die_mem;
+}
+
+/**
+ * die_deref_ptr_type - Return type info for pointer access
+ * @ptr_die: a pointer type DIE
+ * @offset: access offset for the pointer
+ * @die_mem: a buffer to save the resulting DIE
+ *
+ * This function follows the pointer in @ptr_die with given @offset
+ * and saves the resulting type in @die_mem.  If the pointer points
+ * a struct type, actual member at the offset would be returned.
+ */
+Dwarf_Die *die_deref_ptr_type(Dwarf_Die *ptr_die, int offset,
+			      Dwarf_Die *die_mem)
+{
+	Dwarf_Die type_die;
+
+	if (dwarf_tag(ptr_die) != DW_TAG_pointer_type)
+		return NULL;
+
+	if (die_get_real_type(ptr_die, &type_die) == NULL)
+		return NULL;
+
+	return die_get_member_type(&type_die, offset, die_mem);
+}

tools/perf/util/dwarf-aux.h

@@ -144,6 +144,12 @@ struct die_var_type {
 	int offset;
 };
 
+/* Return type info of a member at offset */
+Dwarf_Die *die_get_member_type(Dwarf_Die *type_die, int offset, Dwarf_Die *die_mem);
+
+/* Return type info where the pointer and offset point to */
+Dwarf_Die *die_deref_ptr_type(Dwarf_Die *ptr_die, int offset, Dwarf_Die *die_mem);
+
 #ifdef HAVE_DWARF_GETLOCATIONS_SUPPORT
 
 /* Get byte offset range of given variable DIE */