talk-2019-10-OOPSLA19/slides.tex

638 lines
20 KiB
TeX
Raw Normal View History

% vim: spell spelllang=en
\documentclass[11pt,xcolor={usenames,dvipsnames}]{beamer}
\usetheme{Warsaw}
\usepackage[utf8]{inputenc}
\usepackage[english]{babel}
\usepackage[T1]{fontenc}
\usepackage{amsmath}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{booktabs}
\usepackage{makecell}
\usepackage{ifthen}
\usepackage{colortbl}
\usepackage{tabularx}
2018-11-06 12:28:17 +01:00
\usepackage{pifont}
2019-10-11 11:45:35 +02:00
\usepackage{multirow}
\usepackage{texlib/my_listings}
\usepackage{texlib/specific}
\usepackage{texlib/common}
\usepackage{texlib/todo}
\usepackage{inconsolata}
\lstset{basicstyle=\footnotesize\ttfamily}
\renewcommand\theadalign{c}
\renewcommand\theadfont{\scriptsize\bfseries}
\setbeamertemplate{navigation symbols}{}
\setbeamertemplate{headline}{}
\newcommand{\thenalert}[1]{\only<1>{#1}\only<2>{\alert{#1}}}
\newcommand{\slidecountline}{
\ifthenelse{\theframenumber = 0}
{}
{\insertframenumber/\inserttotalframenumber}}
\newcommand{\sectionline}{
\ifthenelse{\thesection = 0}
{}
{\Roman{section}~-- \insertsection}}
2018-11-06 12:28:17 +01:00
\newcommand{\cmark}{\color{OliveGreen}\ding{52}}
\newcommand{\xmark}{\color{BrickRed}\ding{56}}
2018-11-08 19:37:04 +01:00
\AtBeginSection{
\begin{frame}
\vfill
\centering
\begin{beamercolorbox}[sep=8pt,center,shadow=true,rounded=true]{title}
\usebeamerfont{title}\insertsectionhead\par%
\end{beamercolorbox}
\vfill
\end{frame}
}
\lstdefinelanguage{gdb}{
morekeywords={gdb},
sensitive=false,
}
\newcolumntype{b}{X}
\newcolumntype{s}{>{\hsize=.43\hsize}X}
\newcommand{\lstinl}
{\lstinline[language=C, keepspaces=true, basicstyle=\ttfamily]}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
2019-10-08 12:00:43 +02:00
\title[\sectionline] {Reliable and Fast DWARF-based Stack Unwinding}
\author[\slidecountline]{\textbf{Théophile Bastian},\\
\textbf{Stephen Kell}, \\
\textbf{Francesco Zappa Nardelli}}
\date{}
%\subject{}
%\logo{}
2019-10-08 12:00:43 +02:00
\institute{ENS Paris, University of Kent, Inria}
\begin{document}
\begin{frame}
\addtocounter{framenumber}{-1}
\titlepage{}
\vspace{-2em}
\begin{center}
\begin{align*}
2019-10-08 12:00:43 +02:00
\text{Slides: } &\text{\todo{add URL for this PDF}} \\
\end{align*}
\end{center}
\end{frame}
\begin{frame}{~}
\addtocounter{framenumber}{-1}
\tableofcontents[hideallsubsections]
\end{frame}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\section{DWARF and stack unwinding data}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\subsection{Introduction}
\begin{frame}[fragile]{We often use stack unwinding!}
\begin{columns}[c]
\begin{column}{0.70\textwidth}
\begin{lstlisting}[language=gdb, numbers=none, escapechar=|]
Program received signal SIGSEGV.
0x54625 in fct_b at segfault.c:5
5 printf("%l\n", *b);
|\pause| (gdb) backtrace
#0 0x54625 in fct_b at segfault.c:5
#1 0x54663 in fct_a at segfault.c:10
#2 0x54674 in main at segfault.c:14
|\pause| (gdb) frame 1
#1 0x54663 in fct_a at segfault.c:10
10 fct_b((int*) a);
|\pause| (gdb) print a
$1 = 84
\end{lstlisting}
\vspace{-1em}
\pause{}
\begin{center}
\textbf{\Large How does it work?!}
\end{center}
\end{column}
\begin{column}{0.35\textwidth}
\pause{}
\includegraphics[width=0.95\linewidth]{img/call_stack}
\end{column}
\end{columns}
\end{frame}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\subsection{Stack frames and unwinding}
\begin{frame}{Call stack and registers}
\begin{columns}[c]
\begin{column}{0.55\textwidth}
\begin{center}
\large\bf
How do we get the grandparent RA\@?
\medskip
Isn't it as trivial as \texttt{pop()}?
\vspace{2em}
2018-11-08 20:35:15 +01:00
\onslide<2>{We only have \reg{rsp} and \reg{rip}.}
\end{center}
\end{column}
\begin{column}{0.45\textwidth}
\includegraphics[width=0.95\linewidth]{img/call_stack}
\end{column}
\end{columns}
\end{frame}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\subsection{DWARF tables}
\newcolumntype{a}{>{\columncolor{RedOrange}}l}
\begin{frame}{DWARF unwinding data}
\vspace{2em}
\tt \footnotesize
\begin{tabular}{
>{\columncolor{YellowGreen}}l
>{\columncolor{Thistle}}l
l l l l l l
>{\columncolor{Apricot}}l}
~LOC & CFA & rbx & rbp & r12 & r13 & r14 & r15 & ra \\
0084950 & rsp+8 & u & u & u & u & u & u & c-8 \\
0084952 & rsp+16 & u & u & u & u & u & c-16 & c-8 \\
0084954 & rsp+24 & u & u & u & u & c-24 & c-16 & c-8 \\
0084956 & rsp+32 & u & u & u & c-32 & c-24 & c-16 & c-8 \\
0084958 & rsp+40 & u & u & c-40 & c-32 & c-24 & c-16 & c-8 \\
0084959 & rsp+48 & u & c-48 & c-40 & c-32 & c-24 & c-16 & c-8 \\
\rowcolor{Aquamarine} 008495a & rsp+56 & c-56 & c-48 & c-40 & c-32 & c-24 & c-16 & c-8 \\
0084962 & rsp+64 & c-56 & c-48 & c-40 & c-32 & c-24 & c-16 & c-8 \\
0084a19 & rsp+56 & c-56 & c-48 & c-40 & c-32 & c-24 & c-16 & c-8 \\
0084a1d & rsp+48 & c-56 & c-48 & c-40 & c-32 & c-24 & c-16 & c-8 \\
0084a1e & rsp+40 & c-56 & c-48 & c-40 & c-32 & c-24 & c-16 & c-8 \\
0084a20 & rsp+32 & c-56 & c-48 & c-40 & c-32 & c-24 & c-16 & c-8 \\
0084a22 & rsp+24 & c-56 & c-48 & c-40 & c-32 & c-24 & c-16 & c-8 \\
0084a24 & rsp+16 & c-56 & c-48 & c-40 & c-32 & c-24 & c-16 & c-8 \\
0084a26 & rsp+8 & c-56 & c-48 & c-40 & c-32 & c-24 & c-16 & c-8 \\
0084a30 & rsp+64 & c-56 & c-48 & c-40 & c-32 & c-24 & c-16 & c-8 \\
\end{tabular}
\pause{}
\vspace{-3cm}
\hfill\includegraphics[height=3cm, angle=45, origin=c]{img/dwarf_logo}
\hspace{-1cm}
\end{frame}
\begin{frame}[t, fragile]{The real DWARF}
\begin{lstlisting}[numbers=none, language=]
00009b30 48 009b34 FDE cie=0000 pc=0084950..0084b37
DW_CFA_advance_loc: 2 to 0000000000084952
DW_CFA_def_cfa_offset: 16
DW_CFA_offset: r15 (r15) at cfa-16
DW_CFA_advance_loc: 2 to 0000000000084954
DW_CFA_def_cfa_offset: 24
DW_CFA_offset: r14 (r14) at cfa-24
DW_CFA_advance_loc: 2 to 0000000000084956
DW_CFA_def_cfa_offset: 32
DW_CFA_offset: r13 (r13) at cfa-32
DW_CFA_advance_loc: 2 to 0000000000084958
DW_CFA_def_cfa_offset: 40
DW_CFA_offset: r12 (r12) at cfa-40
DW_CFA_advance_loc: 1 to 0000000000084959
[...]
\end{lstlisting}
\begin{itemize}
\item[\textbf{$\longrightarrow$}] \textbf{\alert{constructed} on-demand
by a \alert{Turing-complete bytecode}!}
\end{itemize}
\pause{}
\vspace{-6.5cm}
\begin{center}
\bf \fontsize{8cm}{1cm}
\colorbox{white}{\alert{Complex}} \\
\colorbox{white}{\alert{\& slow!}}
\end{center}
\end{frame}
\begin{frame}{Why does slow matter?}
\begin{itemize}
\item{} After all, we're talking about \alert{debugging procedures} ran
by a \alert{human being} (slower than the machine).
\ldots{}or are we?
\end{itemize}
\pause{}
\begin{center}
\textbf{\Large{}No!}
\end{center}
\begin{itemize}
\pause{}\item{} Pretty much any \alert{program analysis tool}
\pause{}\item{} \alert{Profiling} with polling profilers
\pause{}\item{} \alert{Exception handling} in C++
\end{itemize}
\vspace{2em}
\begin{center}
\textbf{\Large{}Debug data is not only for debugging}
\end{center}
2019-10-08 12:13:01 +02:00
\vspace{1em}
$\leadsto$ we might want \alert{an alternative time/space trade-off}
\end{frame}
2018-11-08 19:37:04 +01:00
\newcommand{\LinusMailOne}{
``Sorry, but last time was too f\dots painful. The whole (and
only) point of unwinders is to make debugging easy
when a bug occurs. But \alert{the dwarf unwinder had bugs}
itself, or \alert{our dwarf information had bugs}, and in either
case it actually turned several trivial bugs into a \alert{total
undebuggable hell}.''
2018-11-08 19:37:04 +01:00
}
\newcommand{\LinusMailTwo}{
``If you can \alert{mathematically prove that the unwinder is
correct} — even in the presence of bogus and actively
incorrect unwinding information — and never ever
follows a bad pointer, \alert{Ill reconsider}.''
2018-11-08 19:37:04 +01:00
}
\newcommand{\LinusSource}{
\hfill ---~Linus Torvalds, Kernel mailing list, 2012
}
\begin{frame}{A debugging hell: Linux kernel}
\LinusMailOne{}
2019-10-08 12:00:43 +02:00
\only<1-2>{
\vspace{1em}
\LinusSource{}
}
\vspace{1em}
2019-10-08 12:00:43 +02:00
\only<2>{
\begin{center}
\Large\bf
\alert{This is where we still are!}
\end{center}
}
2019-10-08 12:00:43 +02:00
\only<3>{
\LinusMailTwo{}
\vspace{1em}
\LinusSource{}
}
\end{frame}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
2019-10-08 12:00:43 +02:00
\section{Unwinding data as an abstract state}
\newcommand{\tblrowval}[4]{#1 & #2 & \only<2->{#3} & \only<2->{#4} \\}
\newcommand{\blknote}[1]
{\begin{block}{}
\centering\large
#1
\end{block}}
\newcommand{\blklnote}[1]
{\begin{block}{}
\large
#1
\end{block}}
\newcommand{\tblhl}{\rowcolor{Tan}}
2019-10-08 12:00:43 +02:00
\begin{frame}{Working on an example}
\newcommand{\firsttblrows}{
\tblrowval{\hspace{-2ex}<{\bf foo}>:}{}{\textbf{CFA}}{\textbf{ra}}
\rowonly<3>{\tblhl{}} \tblrowval{push}{\%r15}{rsp+8}{c-8}
\rowonly<4>{\tblhl{}} \tblrowval{push}{\%r14}{rsp+16}{c-8}
\rowonly<5>{\tblhl{}} \tblrowval{mov}{\$0x3,\%eax}{rsp+24}{c-8}
\rowonly<6>{\tblhl{}} \tblrowval{push}{\%r13}{rsp+24}{c-8}
\tblrowval{push}{\%r12}{rsp+32}{c-8}
\tblrowval{push}{\%rbp}{rsp+40}{c-8}
\tblrowval{push}{\%rbx}{rsp+48}{c-8}
\tblrowval{sub}{\$0x68,\%rsp}{rsp+56}{c-8}
}
\only<-8>{
\begin{table}
\ttfamily\large
\begin{tabularx}{0.9\linewidth}{
l
b
>{\columncolor{SkyBlue}}s
>{\columncolor{SkyBlue}}s
}
\firsttblrows{}%
\tblrowval{add}{\$0x68,\%rsp}{rsp+160}{c-8}
\tblrowval{pop}{\%rbx}{rsp+56}{c-8}
\tblrowval{pop}{\%rbp}{rsp+48}{c-8}
\end{tabularx}
\end{table}
\blknote{
\centering
\begin{overlayarea}{0.9\textwidth}{4.8ex}
\only<3>{Upon function call, \alert{ra = *(\reg{rsp})} (ABI)}
\only<4>{\texttt{push} decreases \reg{rsp} by 8: %
\alert{ra = *(\reg{rsp} + 8)}}
\only<5>{and again: %
\alert{ra = *(\reg{rsp} + 16)}}
\only<6>{This \texttt{mov} leaves \reg{rsp} untouched: %
\alert{ra = *(\reg{rsp} + 16)}}
\only<7>{The unwinding table can actually be seen as\\
an \alert{abstract interpretation} of the code\ldots}
\only<8>{\ldots and thus, for a given run, be
2019-10-08 12:00:43 +02:00
\alert{re-computed from scratch}}
\end{overlayarea}
}
}
\end{frame}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
2018-11-14 10:13:19 +01:00
\section{Unwinding data synthesis from binaries}
\begin{frame}{Why would synthesis be useful?}
\pause{}
\begin{itemize}
\item As said earlier, \alert{DWARF is complex}
\pause{}
\item Some compilers \alert{do not generate it}: hard to \alert{debug}
\& \alert{profile}.
\pause{}
\item Think of \alert{JIT-compiled assembly} (eg. JVM)
\pause{}
\item \ldots{}or even \alert{hand-written inlined assembly}!
\pause{}
\begin{itemize}
\item Painful enough to write for not bothering with DWARF
\item May not even be known by the programmer, breaks gdb
\item May be wrong (remember Linus!)
\end{itemize}
\end{itemize}
\end{frame}
2018-11-07 08:50:04 +01:00
\begin{frame}{What have we got so far?}
We now want to \alert{synthesize unwinding data}. \pause{}That means
\alert{forgetting the blue part of the previous schemes}.
\begin{itemize}[<+->]
\item Upon entering a function, we know (ABI)
\[ \cfa = \reg{rsp} - 8
\qquad \ra = \cfa + 8 \]
\item For each instruction, we know \alert{how it changes \cfa}.
\item We assume \alert{\ra{} constant wrt. \cfa}.
\begin{itemize}
\item[$\leadsto$] only \cfa{} tracking matters (for unwinding)
\end{itemize}
2018-11-08 19:37:04 +01:00
\item We had a working strategy for a \alert{linear execution}
\item We still have to handle
\begin{itemize}
\item \alert{\cfa{} expression}
\item \alert{control flow graph}
\end{itemize}
\end{itemize}
\end{frame}
\begin{frame}{\cfa{} expression}
Two possibilities:
\begin{itemize}
2019-10-08 12:00:43 +02:00
\item Either we track \cfa{} wrt. \reg{rsp}
2018-11-08 19:37:04 +01:00
\begin{itemize}
2019-10-08 12:00:43 +02:00
\item and update it after each instruction if needed
\end{itemize} \pause{}
\item Or \reg{rbp} is used as base pointer: easy
2018-11-07 08:50:04 +01:00
\end{itemize}
\end{frame}
2018-11-08 19:37:04 +01:00
\begin{frame}{Control flow graph}
\begin{columns}[c]
\column{0.4\textwidth}
\lstinputlisting[language=C]{src/cfg/cfg.c}
\pause{}
\column{0.30\textwidth}
\begin{figure}
\centering
\includegraphics[width=\textwidth]{src/cfg/cfg.png}
\end{figure}
\end{columns}
\pause{}
\begin{itemize}
\item \alert{Upon split} (eg. \texttt{X})\alert{:} nothing special,
2019-10-08 12:00:43 +02:00
propagate end state of X to child nodes A and B
2018-11-08 20:35:15 +01:00
\item \alert{Upon join} (eg. \texttt{while\_end})\alert{:} check
2018-11-08 19:37:04 +01:00
consistency of both input states
\begin{itemize}
\item If tricky, \texttt{gcc} will have used \reg{rbp}, even
with \texttt{-fomit-frame-pointer}.
\end{itemize}
\end{itemize}
\end{frame}
2018-11-08 20:35:15 +01:00
\begin{frame}{}
\vfill
\centering
\begin{beamercolorbox}[sep=8pt,center,shadow=true,rounded=true]{title}
\Large\bf
Demo time!
\end{beamercolorbox}
\vfill
\end{frame}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\section{Unwinding data compilation}
\subsection{Compilation ahead-of-time}
\begin{frame}{Compilation overview}
\begin{itemize}
\item Compiled to \alert{C code}
\item C code then \alert{compiled to native binary} (gcc)
\begin{itemize}
\item[$\leadsto$] gcc optimisations for free
\end{itemize}
\item Compiled as \alert{separate \texttt{.so} files}, called \ehelfs{}
\bigskip{}
\item Morally a \alert{monolithic switch} on IPs
\item Each case contains assembly that computes a \alert{row of the
table}
\end{itemize}
\end{frame}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\begin{frame}[shrink]{Compilation example: generated C}
\lstinputlisting[language=C]{src/fib7/fib7.eh_elf_basic.c}
2019-10-08 12:13:01 +02:00
\pause{}
\vspace{1em}
\begin{center}
The real code is optimised, but boils down to this.
\end{center}
\end{frame}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
2019-10-08 12:00:43 +02:00
\begin{frame}{Mostly plug-and-play: libunwind interface}
\begin{itemize}
\item \alert{libunwind}: \textit{de facto} standard library for
unwinding
\item Relies on DWARF
\bigskip{}
\item \texttt{libunwind-eh\_elf}: alternative implementation using
\ehelfs{}
2019-10-08 12:13:01 +02:00
\item[$\leadsto$] almost \alert{``relink-and-play''} for existing projects!
\end{itemize}
\end{frame}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\subsection{Results}
\begin{frame}{Time performance}
2019-10-11 11:45:35 +02:00
\begin{columns}
\begin{column}{1.1\textwidth}
\begin{table}[h]
\centering
\begin{tabular}{l l r r r r r}
\toprule
& \thead{Unwinding method} & \thead{Frames \\ unwound}
& \thead{Tot. time \\ ($\mu s$)}
& \thead{Avg. \\ time / frame \\ ($ns$)}
& \thead{Time ratio} \\
\midrule
\midrule
\multirow{2}{*}{\rotatebox{90}{\textbf{\prog{Gzip}}~~}}
&\alert{\ehelfs{}}
& 331523 % Frames unwound
& 25930 % Total time
& 78 % Avg time
& 1
\\
& \prog{libunwind}, \alert{cached}
& 331523 % Frames unwound
& 403292 % Total time
& 1217 % Avg time
& \alert{15.6}
\\
&\prog{libunwind}, \alert{uncached}
& 331523 % Frames unwound
& 2197296 % Total time
& 6635 % Avg time
& \alert{84.7}
\\
\midrule
\multirow{2}{*}{\rotatebox{90}{\textbf{\prog{hackbench}}}}
& \alert{\ehelfs{}}
& 152297 % Frames unwound
& 12941 % Total time
& 84 % Avg time
& 1
\\
& \prog{libunwind}, \alert{cached}
& 152297 % Frames unwound
& 316907 % Total time
& 2076 % Avg time
& \alert{24.6}
\\
& \prog{libunwind}, \alert{uncached}
& 152297 % Frames unwound
& 982697 % Total time
& 6439 % Avg time
& \alert{76.3}\vspace{0.8em}
\\
\bottomrule
\end{tabular}
\end{table}
\end{column}
\end{columns}
\end{frame}
2019-10-11 11:45:35 +02:00
\begin{frame}{Space overhead}
\begin{table}[h]
\centering
\begin{tabular}{l r r r r}
\toprule
2019-10-11 11:45:35 +02:00
\thead{Shared object}
& \thead{Original \\ \lstinline{.eh\_frame}}
& \thead{Generated \\ \lstinline{eh_elf} \lstinline{.text}}
& \thead{\% of original \\ program size}
& \thead{Growth \\ factor} \\
\midrule
2019-10-11 11:45:35 +02:00
find & 21.3 KiB & 68.3 KiB & 46.63 & 3.21 \\
\hfill + libs & 196.6 KiB & 577.2 KiB & 19.75 & 2.94 \\
\hline
python3.7
& 160.0 B & 1.4 KiB & 355.98 & 8.33 \\
\hfill + libs
& 449.0 KiB & 1.1 MiB & 23.77 & 2.61 \\
\hline
gzip & 5.1 KiB & 10.9 KiB & 16.48 & 2.13 \\
\hfill + libs & 143.5 KiB & 413.1 KiB & 24.96 & 2.88 \\
\hline
hackbench
2019-10-11 11:45:35 +02:00
& 568.0 B & 3.2 KiB & 107.99 & 5.74 \\
\hfill + libs
& 150.4 KiB & 439.4 KiB & 26.60 & 2.92 \\
\hline
sqlite & 121.7 KiB & 382.8 KiB & 34.68 & 3.14 \\
\hfill + libs & 376.2 KiB & 1.1 MiB & 25.32 & 3.00 \\
\bottomrule
\end{tabular}
2019-10-11 11:45:35 +02:00
\end{table}
\end{frame}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
2018-11-08 19:37:04 +01:00
\section*{Conclusion}
\setcounter{section}{0}
2019-10-08 12:00:43 +02:00
\begin{frame}{A fragment of our article}
The original article \textbf{Reliable and Fast DWARF-based Stack Unwinding}
contains
2018-11-08 19:37:04 +01:00
\vspace{1em}
2019-10-08 12:00:43 +02:00
\begin{itemize}
\item{} DWARF unwinding tables validation;
\item{} DWARF unwinding tables synthesis;
\item{} DWARF-based unwinding speedup.
\end{itemize}
2019-10-08 12:00:43 +02:00
\vspace{1em}
\begin{center}
2019-10-08 12:00:43 +02:00
Come and chat if interested! \texttt{:)}
\end{center}
\end{frame}
\end{document}