linux-kernel - [PATCH v4 5/6] perf scripts python: implement internal get or create frame, stack and string function

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <4cbbbb2b748f29c1a5025d23f0260a395054003a.1689718662.git.anupnewsmail@gmail.com>
Date:   Wed, 19 Jul 2023 04:20:51 +0530
From:   Anup Sharma <anupnewsmail@...il.com>
To:     Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...hat.com>,
        Arnaldo Carvalho de Melo <acme@...nel.org>,
        Mark Rutland <mark.rutland@....com>,
        Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
        Jiri Olsa <jolsa@...nel.org>,
        Namhyung Kim <namhyung@...nel.org>,
        Ian Rogers <irogers@...gle.com>,
        Adrian Hunter <adrian.hunter@...el.com>,
        Anup Sharma <anupnewsmail@...il.com>,
        linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: [PATCH v4 5/6] perf scripts python: implement internal get or create
 frame, stack and string function

The intern_stack function is responsible for retrieving
or creating a stack_id based on the provided frame_id and prefix_id.
It first generates a key using the frame_id and prefix_id values.
If the stack corresponding to the key is found in the stackMap,
it is returned. Otherwise, a new stack is created by appending
the prefix_id and frame_id to the stackTable. The key
and the index of the newly created stack are added to the
stackMap for future reference.

The _intern_frame function is responsible for retrieving or
creating a frame_id based on the provided frame string. If the frame_id
corresponding to the frameString is found in the frameMap, it is
returned. Otherwise, a new frame is created by appending relevant
information to the frameTable and adding the frameString to the string_id
through _intern_string.

The _intern_string function will gets a matching string, or saves the new
string and returns a String ID.

Signed-off-by: Anup Sharma <anupnewsmail@...il.com>
---
 .../scripts/python/firefox-gecko-converter.py | 58 ++++++++++++++++++-
 1 file changed, 57 insertions(+), 1 deletion(-)

diff --git a/tools/perf/scripts/python/firefox-gecko-converter.py b/tools/perf/scripts/python/firefox-gecko-converter.py
index a0218e2245f2..ae69c0a4af13 100644
--- a/tools/perf/scripts/python/firefox-gecko-converter.py
+++ b/tools/perf/scripts/python/firefox-gecko-converter.py
@@ -13,6 +13,7 @@ import os
 import sys
 import json
 import argparse
+from functools import reduce
 from dataclasses import dataclass, field
 from typing import List, Dict, Optional, NamedTuple, Set, Tuple, Any
 
@@ -39,6 +40,13 @@ CATEGORIES = None
 # The product name is used by the profiler UI to show the Operating system and Processor.
 PRODUCT = os.popen('uname -op').read().strip()
 
+# Here key = tid, value = Thread
+tid_to_thread = dict()
+
+# The category index is used by the profiler UI to show the color of the flame graph.
+USER_CATEGORY_INDEX = 0
+KERNEL_CATEGORY_INDEX = 1
+
 # https://github.com/firefox-devtools/profiler/blob/53970305b51b9b472e26d7457fee1d66cd4e2737/src/types/gecko-profile.js#L156
 class Frame(NamedTuple):
 	string_id: StringID
@@ -99,6 +107,55 @@ class Thread:
 	stackMap: Dict[Tuple[Optional[int], int], int] = field(default_factory=dict)
 	frameMap: Dict[str, int] = field(default_factory=dict)
 
+	def _intern_stack(self, frame_id: int, prefix_id: Optional[int]) -> int:
+		"""Gets a matching stack, or saves the new stack. Returns a Stack ID."""
+		key = f"{frame_id}" if prefix_id is None else f"{frame_id},{prefix_id}"
+		# key = (prefix_id, frame_id)
+		stack_id = self.stackMap.get(key)
+		if stack_id is None:
+			# return stack_id
+			stack_id = len(self.stackTable)
+			self.stackTable.append(Stack(prefix_id=prefix_id, frame_id=frame_id))
+			self.stackMap[key] = stack_id
+		return stack_id
+
+	def _intern_string(self, string: str) -> int:
+		"""Gets a matching string, or saves the new string. Returns a String ID."""
+		string_id = self.stringMap.get(string)
+		if string_id is not None:
+			return string_id
+		string_id = len(self.stringTable)
+		self.stringTable.append(string)
+		self.stringMap[string] = string_id
+		return string_id
+
+	def _intern_frame(self, frame_str: str) -> int:
+		"""Gets a matching stack frame, or saves the new frame. Returns a Frame ID."""
+		frame_id = self.frameMap.get(frame_str)
+		if frame_id is not None:
+			return frame_id
+		frame_id = len(self.frameTable)
+		self.frameMap[frame_str] = frame_id
+		string_id = self._intern_string(frame_str)
+
+		symbol_name_to_category = KERNEL_CATEGORY_INDEX if frame_str.find('kallsyms') != -1 \
+		or frame_str.find('/vmlinux') != -1 \
+		or frame_str.endswith('.ko)') \
+		else USER_CATEGORY_INDEX
+
+		self.frameTable.append(Frame(
+			string_id=string_id,
+			relevantForJS=False,
+			innerWindowID=0,
+			implementation=None,
+			optimizations=None,
+			line=None,
+			column=None,
+			category=symbol_name_to_category,
+			subcategory=None,
+		))
+		return frame_id
+
 	def _to_json_dict(self) -> Dict:
 		"""Converts current Thread to GeckoThread JSON format."""
 		# Gecko profile format is row-oriented data as List[List],
@@ -163,7 +220,6 @@ class Thread:
 			"processType": "default",
 		}
 
-
 # Uses perf script python interface to parse each
 # event and store the data in the thread builder.
 def process_event(param_dict: Dict) -> None:
-- 
2.34.1