527 lines
15 KiB
TeX
527 lines
15 KiB
TeX
% 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}
|
||
\usepackage{pifont}
|
||
\usepackage{multirow}
|
||
\usepackage[many]{tcolorbox}
|
||
|
||
\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{\cmark}{\color{OliveGreen}\ding{52}}
|
||
\newcommand{\xmark}{\color{BrickRed}\ding{56}}
|
||
|
||
\newcommand{\sectiontitleframe}{
|
||
\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,
|
||
}
|
||
|
||
\setbeamertemplate{footline}
|
||
{
|
||
\leavevmode%
|
||
\hbox{%
|
||
\hskip0.9\paperwidth
|
||
%\begin{beamercolorbox}[wd=.4\paperwidth,ht=2.25ex,dp=1ex,center]{author in head/foot}%
|
||
% \usebeamerfont{author in head/foot}\insertshortauthor
|
||
%\end{beamercolorbox}%
|
||
\begin{beamercolorbox}[center, wd=.1\paperwidth,ht=2.25ex,dp=1ex,center]{title in head/foot}%
|
||
\slidecountline{}
|
||
\end{beamercolorbox}}%
|
||
\vskip0pt%
|
||
}
|
||
|
||
|
||
\newcolumntype{b}{X}
|
||
\newcolumntype{s}{>{\hsize=.43\hsize}X}
|
||
|
||
\newcommand{\lstinl}
|
||
{\lstinline[language=C, keepspaces=true, basicstyle=\ttfamily]}
|
||
|
||
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
||
\title[] {Reliable and Fast DWARF-based Stack Unwinding}
|
||
\author[\slidecountline]{\textbf{Théophile Bastian}\\
|
||
\textbf{Stephen Kell} \\
|
||
\textbf{Francesco Zappa Nardelli}}
|
||
\date{}
|
||
%\subject{}
|
||
%\logo{}
|
||
\institute{ENS Paris, University of Kent, Inria}
|
||
|
||
\begin{document}
|
||
|
||
\begin{frame}
|
||
\addtocounter{framenumber}{-1}
|
||
\titlepage{}
|
||
|
||
\vspace{-2em}
|
||
|
||
\begin{columns}
|
||
\begin{column}{0.55\textwidth}
|
||
\begin{tcolorbox}[halign=center, colframe=blue]
|
||
\textbf{Webpage} (incl. slides)
|
||
|
||
\smallskip
|
||
\vspace{0.5em}
|
||
{\url{https://huit.re/frdwarf}}\\
|
||
\vspace{0.5em}
|
||
\end{tcolorbox}
|
||
\end{column}
|
||
|
||
\begin{column}{0.55\textwidth}
|
||
\begin{tcolorbox}[colframe=blue]
|
||
\begin{center}\textbf{Funding}\end{center}
|
||
\vspace{-1em}
|
||
|
||
\smallskip
|
||
ONR Vertica \\
|
||
Google Research Fellowship
|
||
\end{tcolorbox}
|
||
\end{column}
|
||
\end{columns}
|
||
\end{frame}
|
||
|
||
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
||
\section{DWARF and stack unwinding data}
|
||
|
||
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
||
\subsection{Introduction}
|
||
|
||
\begin{frame}[fragile]{}
|
||
\begin{columns}[c]
|
||
\begin{column}{0.70\textwidth}
|
||
\begin{lstlisting}[language=gdb, numbers=none, escapechar=|]
|
||
$ ./a.out
|
||
Segmentation fault.
|
||
|
||
|\pause|(gdb) backtrace
|
||
#0 0x54625 in fct_b
|
||
#1 0x54663 in fct_a
|
||
#2 0x54674 in main
|
||
\end{lstlisting}
|
||
\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}
|
||
\begin{columns}[c]
|
||
\begin{column}{0.55\textwidth}
|
||
\begin{center}
|
||
\large\bf
|
||
How do we get the RA\@?\\Easy, \reg{rbp}!
|
||
|
||
\vspace{2em}
|
||
|
||
\onslide<2>{What if we only have \reg{rsp}?}
|
||
|
||
\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 \\
|
||
\end{tabular}
|
||
\vspace{1em}
|
||
|
||
\only<1>{\vspace{19mm}}
|
||
\begin{columns}
|
||
\begin{column}{0.50\textwidth}
|
||
\only<2->{
|
||
\begin{tcolorbox}[enhanced, halign=center, frame hidden, colback=YellowGreen]
|
||
\textbf{For each instruction\ldots}\\
|
||
(identified by its program counter)
|
||
\end{tcolorbox}
|
||
}
|
||
\end{column}
|
||
\begin{column}{0.50\textwidth}
|
||
\only<3->{
|
||
\begin{tcolorbox}[enhanced, halign=center, frame hidden,
|
||
interior style={right color=Apricot, left color=Thistle}]
|
||
\textbf{\ldots{}an expression to compute its return address
|
||
location on the stack}
|
||
\end{tcolorbox}
|
||
}
|
||
\end{column}
|
||
\end{columns}
|
||
\end{frame}
|
||
|
||
\begin{frame}[t, fragile]{The real DWARF}
|
||
\begin{lstlisting}[numbers=none, language=]
|
||
30 24 34 FDE pc=004020..004040
|
||
DW_CFA_def_cfa_offset: 16
|
||
DW_CFA_advance_loc: 6 to 0000000000004026
|
||
DW_CFA_def_cfa_offset: 24
|
||
DW_CFA_advance_loc: 10 to 0000000000004030
|
||
DW_CFA_def_cfa_expression (DW_OP_breg7 (rsp): 8; DW_OP_breg16 (rip): 0; DW_OP_lit15; DW_OP_and; DW_OP_lit11; DW_OP_ge; DW_OP_lit3; DW_OP_shl; DW_OP_plus)
|
||
[...]
|
||
\end{lstlisting}
|
||
|
||
\begin{itemize}
|
||
\item[\textbf{$\longrightarrow$}] \textbf{\alert{constructed} on-demand
|
||
by a \alert{Turing-complete stack machine}!}
|
||
\end{itemize}
|
||
|
||
\pause{}
|
||
|
||
\vspace{-4cm}
|
||
\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}
|
||
|
||
\vspace{1em}
|
||
$\leadsto$ we might want \alert{an alternative time/space trade-off}
|
||
\end{frame}
|
||
|
||
\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}.''
|
||
}
|
||
\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{I’ll reconsider}.''
|
||
}
|
||
\newcommand{\LinusSource}{
|
||
\hfill ---~Linus Torvalds, 2012
|
||
}
|
||
\begin{frame}
|
||
\LinusMailOne{}
|
||
|
||
\only<1-2>{
|
||
\vspace{1em}
|
||
\LinusSource{}
|
||
}
|
||
|
||
\vspace{1em}
|
||
\only<2>{
|
||
\begin{center}
|
||
\Large\bf
|
||
\alert{This is where we still are!}
|
||
\end{center}
|
||
}
|
||
|
||
\only<3>{
|
||
\LinusMailTwo{}
|
||
|
||
\vspace{1em}
|
||
\LinusSource{}
|
||
}
|
||
\end{frame}
|
||
|
||
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
||
\section{Unwinding data as an abstract execution of the assembly}
|
||
\sectiontitleframe{}
|
||
|
||
\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}}
|
||
|
||
\begin{frame}
|
||
\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})}}
|
||
\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 captures an \alert{abstract execution}
|
||
of the code\ldots}
|
||
\only<8>{\ldots and thus can be \alert{synthesized from the binary}.}
|
||
\end{overlayarea}
|
||
}
|
||
}
|
||
\end{frame}
|
||
|
||
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
||
\section{Unwinding data synthesis from binaries}
|
||
|
||
%\begin{frame}{Why would synthesis be useful?}
|
||
% \begin{itemize}
|
||
% \item As said earlier, \alert{DWARF is complex}
|
||
% \item Some compilers \alert{do not generate it}: hard to \alert{debug}
|
||
% \& \alert{profile}.
|
||
% \item Think of \alert{JIT-compiled assembly} (eg. JVM)
|
||
% \item \ldots{}or even \alert{hand-written inlined assembly}!
|
||
% \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}
|
||
|
||
\begin{frame}{How do we actually synthesize?}
|
||
\begin{itemize}
|
||
\item Upon entering a function, we know (ABI)
|
||
\[ \cfa = \reg{rsp} - 8
|
||
\qquad \ra = \cfa + 8 \]
|
||
\item The semantics of each instruction specifies \alert{how it changes \cfa}.
|
||
\begin{itemize}
|
||
\item Heuristic to decide whether we index with \reg{rbp} or
|
||
\reg{rsp}
|
||
\end{itemize}
|
||
\item By performing a symbolic execution, we can \alert{synthesize the
|
||
unwinding table} line by line.
|
||
\item Control flow: forward data-flow analysis
|
||
\item The fixpoints are immediate, cf article
|
||
\end{itemize}
|
||
\end{frame}
|
||
|
||
\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}
|
||
|
||
\sectiontitleframe{}
|
||
|
||
\subsection{Compilation ahead-of-time}
|
||
|
||
\begin{frame}
|
||
\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]
|
||
\lstinputlisting[language=C]{src/fib7/fib7.eh_elf_basic.c}
|
||
|
||
\pause{}
|
||
\vspace{1em}
|
||
\begin{center}
|
||
The real code is optimised, but boils down to this.
|
||
\end{center}
|
||
\end{frame}
|
||
|
||
|
||
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
||
|
||
\begin{frame}
|
||
\begin{itemize}
|
||
\item \alert{libunwind}: \textit{de facto} standard library for
|
||
unwinding
|
||
|
||
\bigskip{}
|
||
|
||
\item \texttt{libunwind-eh\_elf}: alternative implementation using
|
||
\ehelfs{}
|
||
|
||
\item[$\leadsto$] almost \alert{``relink-and-play''} for existing projects!
|
||
\end{itemize}
|
||
\end{frame}
|
||
|
||
|
||
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
||
\subsection{Results}
|
||
|
||
\begin{frame}{Performances}
|
||
\begin{itemize}
|
||
\item \alert{Speedup}: x15 (\prog{gzip}) to x25 (\prog{hackbench}) vs.
|
||
libunwind
|
||
|
||
\begin{itemize}
|
||
\item libunwind: state of the art, aggressive caching.
|
||
\end{itemize}
|
||
|
||
\item \alert{Space overhead}: x2.6 to x3 vs. DWARF
|
||
|
||
\vspace{2em}
|
||
|
||
\item[$\leadsto$] Alternative time/space trade-off, favorable eg. for
|
||
profiling.
|
||
\end{itemize}
|
||
\end{frame}
|
||
|
||
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
||
\section*{Conclusion}
|
||
\setcounter{section}{0}
|
||
|
||
\begin{frame}
|
||
The original article \textbf{Reliable and Fast DWARF-based Stack Unwinding}
|
||
contains
|
||
|
||
\vspace{1em}
|
||
|
||
\begin{itemize}
|
||
\item{} DWARF unwinding tables validation;
|
||
\item{} DWARF unwinding tables synthesis;
|
||
\item{} DWARF-based unwinding speedup.
|
||
\end{itemize}
|
||
|
||
\vspace{1em}
|
||
|
||
\begin{center}
|
||
Come and chat if interested! \texttt{:)}
|
||
\end{center}
|
||
\end{frame}
|
||
|
||
\end{document}
|