[PATCH 1/2] perf annotate: Treat 'call' instruction as stack operation

[PATCH 1/2] perf annotate: Treat 'call' instruction as stack operation

[Namhyung Kim]

I found some portion of mem-store events sampled on CALL instruction
which has no memory access.  But it actually saves a return address
into stack.  It should be considered as a stack operation like RET
instruction.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/annotate.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 4990c70b1794d7a9..1a347a711dcf5c62 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -2474,6 +2474,7 @@ static bool is_stack_operation(struct arch *arch, struct disasm_line *dl)
 	if (arch__is(arch, "x86")) {
 		if (!strncmp(dl->ins.name, "push", 4) ||
 		    !strncmp(dl->ins.name, "pop", 3) ||
+		    !strncmp(dl->ins.name, "call", 4) ||
 		    !strncmp(dl->ins.name, "ret", 3))
 			return true;
 	}
-- 
2.46.0.598.g6f2099f65c-goog

[PATCH 2/2] perf annotate-data: Add pr_debug_scope()

[Namhyung Kim]

The pr_debug_scope() is to print more information about the scope DIE
during the instruction tracking so that it can help finding relevant
debug info and the source code like inlined functions more easily.

  $ perf --debug type-profile annotate --data-type
  ...
  -----------------------------------------------------------
  find data type for 0(reg0, reg12) at set_task_cpu+0xdd
  CU for kernel/sched/core.c (die:0x1268dae)
  frame base: cfa=1 fbreg=7
  scope: [3/3] (die:12b6d28) [inlined] set_task_rq       <<<--- (here)
  bb: [9f - dd]
  var [9f] reg3 type='struct task_struct*' size=0x8 (die:0x126aff0)
  var [9f] reg6 type='unsigned int' size=0x4 (die:0x1268e0d)

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/annotate-data.c | 25 +++++++++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
index a0ea4e07e57031ff..976abedca09ef547 100644
--- a/tools/perf/util/annotate-data.c
+++ b/tools/perf/util/annotate-data.c
@@ -131,6 +131,26 @@ static void pr_debug_location(Dwarf_Die *die, u64 pc, int reg)
 	}
 }
 
+static void pr_debug_scope(Dwarf_Die *scope_die)
+{
+	int tag;
+
+	if (!debug_type_profile && verbose < 3)
+		return;
+
+	pr_info("(die:%lx) ", (long)dwarf_dieoffset(scope_die));
+
+	tag = dwarf_tag(scope_die);
+	if (tag == DW_TAG_subprogram)
+		pr_info("[function] %s\n", dwarf_diename(scope_die));
+	else if (tag == DW_TAG_inlined_subroutine)
+		pr_info("[inlined] %s\n", dwarf_diename(scope_die));
+	else if (tag == DW_TAG_lexical_block)
+		pr_info("[block]\n");
+	else
+		pr_info("[unknown] tag=%x\n", tag);
+}
+
 bool has_reg_type(struct type_state *state, int reg)
 {
 	return (unsigned)reg < ARRAY_SIZE(state->regs);
@@ -1305,8 +1325,9 @@ static enum type_match_result find_data_type_block(struct data_loc_info *dloc,
 		if (dwarf_ranges(&scopes[i], 0, &base, &start, &end) < 0)
 			break;
 
-		pr_debug_dtp("scope: [%d/%d] (die:%lx)\n",
-			     i + 1, nr_scopes, (long)dwarf_dieoffset(&scopes[i]));
+		pr_debug_dtp("scope: [%d/%d] ", i + 1, nr_scopes);
+		pr_debug_scope(&scopes[i]);
+
 		src_ip = map__objdump_2rip(dloc->ms->map, start);
 
 again:
-- 
2.46.0.598.g6f2099f65c-goog

Re: [PATCH 1/2] perf annotate: Treat 'call' instruction as stack operation

[Arnaldo Carvalho de Melo]

On Mon, Sep 09, 2024 at 02:42:50PM -0700, Namhyung Kim wrote:
> I found some portion of mem-store events sampled on CALL instruction
> which has no memory access.  But it actually saves a return address
> into stack.  It should be considered as a stack operation like RET
> instruction.

Thanks, applied to perf-tools-next,

- Arnaldo
 
> Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> ---
>  tools/perf/util/annotate.c | 1 +
>  1 file changed, 1 insertion(+)
> 
> diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
> index 4990c70b1794d7a9..1a347a711dcf5c62 100644
> --- a/tools/perf/util/annotate.c
> +++ b/tools/perf/util/annotate.c
> @@ -2474,6 +2474,7 @@ static bool is_stack_operation(struct arch *arch, struct disasm_line *dl)
>  	if (arch__is(arch, "x86")) {
>  		if (!strncmp(dl->ins.name, "push", 4) ||
>  		    !strncmp(dl->ins.name, "pop", 3) ||
> +		    !strncmp(dl->ins.name, "call", 4) ||
>  		    !strncmp(dl->ins.name, "ret", 3))
>  			return true;
>  	}
> -- 
> 2.46.0.598.g6f2099f65c-goog