Received-SPF: pass (google.com: domain of linux-kernel+bounces-28562-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
From: Namhyung Kim <namhyung@kernel.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>,
	Jiri Olsa <jolsa@kernel.org>
Cc: Ian Rogers <irogers@google.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@kernel.org>,
	LKML <linux-kernel@vger.kernel.org>,
	linux-perf-users@vger.kernel.org,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Stephane Eranian <eranian@google.com>,
	Masami Hiramatsu <mhiramat@kernel.org>,
	linux-toolchains@vger.kernel.org,
	linux-trace-devel@vger.kernel.org
Subject: [PATCH 4/9] perf annotate-data: Add stack operation pseudo type
Date: Tue, 16 Jan 2024 22:26:52 -0800
Message-ID: <20240117062657.985479-5-namhyung@kernel.org>
In-Reply-To: <20240117062657.985479-1-namhyung@kernel.org>
References: <20240117062657.985479-1-namhyung@kernel.org>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

A typical function prologue and epilogue include multiple stack
operations to save and restore the current value of registers.
On x86, it looks like below:

  push  r15
  push  r14
  push  r13
  push  r12

  ...

  pop   r12
  pop   r13
  pop   r14
  pop   r15
  ret

As these all touches the stack memory region, chances are high that they
appear in a memory profile data.  But these are not used for any real
purpose yet so it'd return no types.

One of my profile type shows that non neglible portion of data came from
the stack operations.  It also seems GCC generates more stack operations
than clang.

Annotate Instruction stats
total 264, ok 169 (64.0%), bad 95 (36.0%)

    Name      :  Good   Bad
  -----------------------------------------------------------
    movq      :    49    27
    movl      :    24     9
    popq      :     0    19   <-- here
    cmpl      :    17     2
    addq      :    14     1
    cmpq      :    12     2
    cmpxchgl  :     3     7

Instead of dealing them as unknown, let's create a seperate pseudo type
to represent those stack operations separately.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/annotate-data.h |  1 +
 tools/perf/util/annotate.c      | 26 ++++++++++++++++++++++++++
 2 files changed, 27 insertions(+)

diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h
index 65ddd839850f..214c625e7bc9 100644
--- a/tools/perf/util/annotate-data.h
+++ b/tools/perf/util/annotate-data.h
@@ -70,6 +70,7 @@ struct annotated_data_type {
 };
 
 extern struct annotated_data_type unknown_type;
+extern struct annotated_data_type stackop_type;
 
 /**
  * struct annotated_data_stat - Debug statistics
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 3cdcdd449c86..655bd9443f5e 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -107,6 +107,14 @@ static struct ins_ops ret_ops;
 struct annotated_data_stat ann_data_stat;
 LIST_HEAD(ann_insn_stat);
 
+/* Pseudo data types */
+struct annotated_data_type stackop_type = {
+	.self = {
+		.type_name = (char *)"(stack operation)",
+		.children = LIST_HEAD_INIT(stackop_type.self.children),
+	},
+};
+
 static int arch__grow_instructions(struct arch *arch)
 {
 	struct ins *new_instructions;
@@ -3724,6 +3732,18 @@ static struct annotated_item_stat *annotate_data_stat(struct list_head *head,
 	return istat;
 }
 
+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, "ret", 3))
+			return true;
+	}
+
+	return false;
+}
+
 /**
  * hist_entry__get_data_type - find data type for given hist entry
  * @he: hist entry
@@ -3789,6 +3809,12 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 		return NULL;
 	}
 
+	if (is_stack_operation(arch, dl)) {
+		istat->good++;
+		he->mem_type_off = 0;
+		return &stackop_type;
+	}
+
 	for_each_insn_op_loc(&loc, i, op_loc) {
 		if (!op_loc->mem_ref)
 			continue;
-- 
2.43.0.381.gb435a96ce8-goog