perf annotate-data: Support global variables

Global variables are accessed using PC-relative address so it needs to
be handled separately.  The PC-rel addressing is detected by using
DWARF_REG_PC.  On x86, %rip register would be used.

The address can be calculated using the ip and offset in the
instruction.  But it should start from the next instruction so add
calculate_pcrel_addr() to do it properly.

But global variables defined in a different file would only have a
declaration which doesn't include a location list.  So it first tries
to get the type info using the address, and then looks up the variable
declarations using name.  The name of global variables should be get
from the symbol table.  The declaration would have the type info.

So extend find_var_type() to take both address and name for global
variables.

The stat is now looks like:

  Annotate data type stats:
  total 294, ok 153 (52.0%), bad 141 (48.0%)
  -----------------------------------------------------------
          30 : no_sym
          32 : no_mem_ops
          61 : no_var
          10 : no_typeinfo
           8 : bad_offset

Reviewed-by: Ian Rogers <[email protected]>
Cc: Stephane Eranian <[email protected]>
Cc: Masami Hiramatsu <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Namhyung Kim <[email protected]>

1 files changed, 29 insertions, 9 deletions

diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
index 58c0fac42e9d..e375dd288f67 100644
--- a/tools/perf/util/annotate-data.c
+++ b/tools/perf/util/annotate-data.c
@@ -240,7 +240,8 @@ static int check_variable(Dwarf_Die *var_die, Dwarf_Die *type_die, int offset,
 
 /* The result will be saved in @type_die */
 static int find_data_type_die(struct debuginfo *di, u64 pc, u64 addr,
-			      struct annotated_op_loc *loc, Dwarf_Die *type_die)
+			      const char *var_name, struct annotated_op_loc *loc,
+			      Dwarf_Die *type_die)
 {
 	Dwarf_Die cu_die, var_die;
 	Dwarf_Die *scopes = NULL;
@@ -258,11 +259,21 @@ static int find_data_type_die(struct debuginfo *di, u64 pc, u64 addr,
 	reg = loc->reg1;
 	offset = loc->offset;
 
-	if (reg == DWARF_REG_PC &&
-	    die_find_variable_by_addr(&cu_die, pc, addr, &var_die, &offset)) {
-		ret = check_variable(&var_die, type_die, offset,
-				     /*is_pointer=*/false);
-		goto out;
+	if (reg == DWARF_REG_PC) {
+		if (die_find_variable_by_addr(&cu_die, pc, addr, &var_die, &offset)) {
+			ret = check_variable(&var_die, type_die, offset,
+					     /*is_pointer=*/false);
+			loc->offset = offset;
+			goto out;
+		}
+
+		if (var_name && die_find_variable_at(&cu_die, var_name, pc,
+						     &var_die)) {
+			ret = check_variable(&var_die, type_die, 0,
+					     /*is_pointer=*/false);
+			/* loc->offset will be updated by the caller */
+			goto out;
+		}
 	}
 
 	/* Get a list of nested scopes - i.e. (inlined) functions and blocks. */
@@ -285,6 +296,7 @@ retry:
 		/* Found a variable, see if it's correct */
 		ret = check_variable(&var_die, type_die, offset,
 				     reg != DWARF_REG_PC);
+		loc->offset = offset;
 		goto out;
 	}
 
@@ -306,13 +318,21 @@ out:
  * @ms: map and symbol at the location
  * @ip: instruction address of the memory access
  * @loc: instruction operand location
+ * @addr: data address of the memory access
+ * @var_name: global variable name
  *
  * This functions searches the debug information of the binary to get the data
- * type it accesses.  The exact location is expressed by (ip, reg, offset).
+ * type it accesses.  The exact location is expressed by (@ip, reg, offset)
+ * for pointer variables or (@ip, @addr) for global variables.  Note that global
+ * variables might update the @loc->offset after finding the start of the variable.
+ * If it cannot find a global variable by address, it tried to fine a declaration
+ * of the variable using @var_name.  In that case, @loc->offset won't be updated.
+ *
  * It return %NULL if not found.
  */
 struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip,
-					   struct annotated_op_loc *loc)
+					   struct annotated_op_loc *loc, u64 addr,
+					   const char *var_name)
 {
 	struct annotated_data_type *result = NULL;
 	struct dso *dso = map__dso(ms->map);
@@ -332,7 +352,7 @@ struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip,
 	 * a file address for DWARF processing.
 	 */
 	pc = map__rip_2objdump(ms->map, ip);
-	if (find_data_type_die(di, pc, 0, loc, &type_die) < 0)
+	if (find_data_type_die(di, pc, addr, var_name, loc, &type_die) < 0)
 		goto out;
 
 	result = dso__findnew_data_type(dso, &type_die);