perf annotate-data: Support stack variables

Local variables are allocated in the stack and the location list
should look like base register(s) and an offset.  Extend the
die_find_variable_by_reg() to handle the following expressions

 * DW_OP_breg{0..31}
 * DW_OP_bregx
 * DW_OP_fbreg

Ususally DWARF subprogram entries have frame base information and
use it to locate stack variable like below:

 <2><43d1575>: Abbrev Number: 62 (DW_TAG_variable)
    <43d1576>   DW_AT_location    : 2 byte block: 91 7c         (DW_OP_fbreg: -4)  <--- here
    <43d1579>   DW_AT_name        : (indirect string, offset: 0x2c00c9): i
    <43d157d>   DW_AT_decl_file   : 1
    <43d157e>   DW_AT_decl_line   : 78
    <43d157f>   DW_AT_type        : <0x43d19d7>

I found some differences on saving the frame base between gcc and clang.
The gcc uses the CFA to get the base so it needs to check the current
frame's CFI info.  In this case, stack offset needs to be adjusted from
the start of the CFA.

 <1><1bb8d>: Abbrev Number: 102 (DW_TAG_subprogram)
    <1bb8e>   DW_AT_name        : (indirect string, offset: 0x74d41): kernel_init
    <1bb92>   DW_AT_decl_file   : 2
    <1bb92>   DW_AT_decl_line   : 1440
    <1bb94>   DW_AT_decl_column : 18
    <1bb95>   DW_AT_prototyped  : 1
    <1bb95>   DW_AT_type        : <0xcc>
    <1bb99>   DW_AT_low_pc      : 0xffffffff81bab9e0
    <1bba1>   DW_AT_high_pc     : 0x1b2
    <1bba9>   DW_AT_frame_base  : 1 byte block: 9c      (DW_OP_call_frame_cfa)  <------ here
    <1bbab>   DW_AT_call_all_calls: 1
    <1bbab>   DW_AT_sibling     : <0x1bf5a>

While clang sets it to a register directly and it can check the register
and offset in the instruction directly.

 <1><43d1542>: Abbrev Number: 60 (DW_TAG_subprogram)
    <43d1543>   DW_AT_low_pc      : 0xffffffff816a7c60
    <43d154b>   DW_AT_high_pc     : 0x98
    <43d154f>   DW_AT_frame_base  : 1 byte block: 56    (DW_OP_reg6 (rbp))  <---------- here
    <43d1551>   DW_AT_GNU_all_call_sites: 1
    <43d1551>   DW_AT_name        : (indirect string, offset: 0x3bce91): foo
    <43d1555>   DW_AT_decl_file   : 1
    <43d1556>   DW_AT_decl_line   : 75
    <43d1557>   DW_AT_prototyped  : 1
    <43d1557>   DW_AT_type        : <0x43c7332>
    <43d155b>   DW_AT_external    : 1

Also it needs to update the offset after finding the type like global
variables since the offset was from the frame base.  Factor out
match_var_offset() to check global and local variables in the same way.

The type stats are improved too:

  Annotate data type stats:
  total 294, ok 160 (54.4%), bad 134 (45.6%)
  -----------------------------------------------------------
          30 : no_sym
          32 : no_mem_ops
          51 : no_var
          14 : no_typeinfo
           7 : bad_offset

Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Link: https://lore.kernel.org/r/20240117062657.985479-9-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>

1 files changed, 32 insertions, 3 deletions

diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
index e375dd288f67..30c4d19fcf11 100644
--- a/tools/perf/util/annotate-data.c
+++ b/tools/perf/util/annotate-data.c
@@ -209,7 +209,7 @@ static int check_variable(Dwarf_Die *var_die, Dwarf_Die *type_die, int offset,
 	/*
 	 * Usually it expects a pointer type for a memory access.
 	 * Convert to a real type it points to.  But global variables
-	 * are accessed directly without a pointer.
+	 * and local variables are accessed directly without a pointer.
 	 */
 	if (is_pointer) {
 		if ((dwarf_tag(type_die) != DW_TAG_pointer_type &&
@@ -248,6 +248,9 @@ static int find_data_type_die(struct debuginfo *di, u64 pc, u64 addr,
 	int reg, offset;
 	int ret = -1;
 	int i, nr_scopes;
+	int fbreg = -1;
+	bool is_fbreg = false;
+	int fb_offset = 0;
 
 	/* Get a compile_unit for this address */
 	if (!find_cu_die(di, pc, &cu_die)) {
@@ -279,7 +282,33 @@ static int find_data_type_die(struct debuginfo *di, u64 pc, u64 addr,
 	/* Get a list of nested scopes - i.e. (inlined) functions and blocks. */
 	nr_scopes = die_get_scopes(&cu_die, pc, &scopes);
 
+	if (reg != DWARF_REG_PC && dwarf_hasattr(&scopes[0], DW_AT_frame_base)) {
+		Dwarf_Attribute attr;
+		Dwarf_Block block;
+
+		/* Check if the 'reg' is assigned as frame base register */
+		if (dwarf_attr(&scopes[0], DW_AT_frame_base, &attr) != NULL &&
+		    dwarf_formblock(&attr, &block) == 0 && block.length == 1) {
+			switch (*block.data) {
+			case DW_OP_reg0 ... DW_OP_reg31:
+				fbreg = *block.data - DW_OP_reg0;
+				break;
+			case DW_OP_call_frame_cfa:
+				if (die_get_cfa(di->dbg, pc, &fbreg,
+						&fb_offset) < 0)
+					fbreg = -1;
+				break;
+			default:
+				break;
+			}
+		}
+	}
+
 retry:
+	is_fbreg = (reg == fbreg);
+	if (is_fbreg)
+		offset = loc->offset - fb_offset;
+
 	/* Search from the inner-most scope to the outer */
 	for (i = nr_scopes - 1; i >= 0; i--) {
 		if (reg == DWARF_REG_PC) {
@@ -289,13 +318,13 @@ retry:
 		} else {
 			/* Look up variables/parameters in this scope */
 			if (!die_find_variable_by_reg(&scopes[i], pc, reg,
-						      &var_die))
+						      &offset, is_fbreg, &var_die))
 				continue;
 		}
 
 		/* Found a variable, see if it's correct */
 		ret = check_variable(&var_die, type_die, offset,
-				     reg != DWARF_REG_PC);
+				     reg != DWARF_REG_PC && !is_fbreg);
 		loc->offset = offset;
 		goto out;
 	}