llvm-project/clang/www/analyzer/open_projects.html

242 lines
10 KiB
HTML

<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
"http://www.w3.org/TR/html4/strict.dtd">
<html>
<head>
<title>Open Projects</title>
<link type="text/css" rel="stylesheet" href="menu.css">
<link type="text/css" rel="stylesheet" href="content.css">
<script type="text/javascript" src="scripts/menu.js"></script>
</head>
<body>
<div id="page">
<!--#include virtual="menu.html.incl"-->
<div id="content">
<h1>Open Projects</h1>
<p>This page lists several projects that would boost analyzer's usability and
power. Most of the projects listed here are infrastructure-related so this list
is an addition to the <a href="potential_checkers.html">potential checkers
list</a>. If you are interested in tackling one of these, please send an email
to the <a href=http://lists.llvm.org/mailman/listinfo/cfe-dev>cfe-dev
mailing list</a> to notify other members of the community.</p>
<ul>
<li>Release checkers from "alpha"
<p>New checkers which were contributed to the analyzer,
but have not passed a rigorous evaluation process,
are committed as "alpha checkers" (from "alpha version"),
and are not enabled by default.</p>
<p>Ideally, only the checkers which are actively being worked on should be in
"alpha",
but over the years the development of many of those has stalled.
Such checkers should either be improved
up to a point where they can be enabled by default,
or removed from the analyzer entirely.
<ul>
<li><code>alpha.security.ArrayBound</code> and
<code>alpha.security.ArrayBoundV2</code>
<p>Array bounds checking is a desired feature,
but having an acceptable rate of false positives might not be possible
without a proper
<a href="https://en.wikipedia.org/wiki/Widening_(computer_science)">loop widening</a> support.
Additionally, it might be more promising to perform index checking based on
<a href="https://en.wikipedia.org/wiki/Taint_checking">tainted</a> index values.
<p><i>(Difficulty: Medium)</i></p></p>
</li>
<li><code>alpha.cplusplus.MisusedMovedObject</code>
<p>The checker emits a warning on objects which were used after
<a href="https://en.cppreference.com/w/cpp/utility/move">move</a>.
Currently it has an overly high false positive rate due to classes
which have a well-defined semantics for use-after-move.
This property does not hold for STL objects, but is often the case
for custom containers.
<p><i>(Difficulty: Medium)</i></p></p>
</li>
<li><code>alpha.unix.StreamChecker</code>
<p>A SimpleStreamChecker has been presented in the Building a Checker in 24
Hours talk
(<a href="http://llvm.org/devmtg/2012-11/Zaks-Rose-Checker24Hours.pdf">slides</a>
<a href="https://youtu.be/kdxlsP5QVPw">video</a>).</p>
<p>This alpha checker is an attempt to write a production grade stream checker.
However, it was found to have an unacceptably high false positive rate.
One of the found problems was that eagerly splitting the state
based on whether the system call may fail leads to too many reports.
A <em>delayed</em> split where the implication is stored in the state
(similarly to nullability implications in <code>TrustNonnullChecker</code>)
may produce much better results.</p>
<p><i>(Difficulty: Medium)</i></p>
</li>
</ul>
</li>
<li>Improve C++ support
<ul>
<li>Handle aggregate construction.
<p><a href="https://en.cppreference.com/w/cpp/language/aggregate_initialization">Aggregates</a>
are objects that can be brace-initialized without calling a
constructor (that is, <code><a href="https://clang.llvm.org/doxygen/classclang_1_1CXXConstructExpr.html">
CXXConstructExpr</a></code> does not occur in the AST),
but potentially calling
constructors for their fields and base classes
These
constructors of sub-objects need to know what object they are constructing.
Moreover, if the aggregate contains
references, lifetime extension needs to be properly modeled.
One can start untangling this problem by trying to replace the
current ad-hoc <code><a href="https://clang.llvm.org/doxygen/classclang_1_1ParentMap.html">
ParentMap</a></code> lookup in <a href="https://clang.llvm.org/doxygen/ExprEngineCXX_8cpp_source.html#l00430">
<code>CXXConstructExpr::CK_NonVirtualBase</code></a> branch of
<code>ExprEngine::VisitCXXConstructExpr()</code>
with proper support for the feature.
<p><i>(Difficulty: Medium) </i></p></p>
</li>
<li>Handle constructors within <code>new[]</code>
<p>When an array of objects is allocated using the <code>operator new[]</code>,
constructors for all elements of the array are called.
We should model (potentially some of) such evaluations,
and the same applies for destructors called from
<code>operator delete[]</code>.
</p>
</li>
<li>Handle constructors that can be elided due to Named Return Value Optimization (NRVO)
<p>Local variables which are returned by values on all return statements
may be stored directly at the address for the return value,
eliding the copy or move constructor call.
Such variables can be identified using the AST call <code>VarDecl::isNRVOVariable</code>.
</p>
</li>
<li>Handle constructors of lambda captures
<p>Variables which are captured by value into a lambda require a call to
a copy constructor.
This call is not currently modeled.
</p>
</li>
<li>Handle constructors for default arguments
<p>Default arguments in C++ are recomputed at every call,
and are therefore local, and not static, variables.
</p>
</li>
<li>Enhance the modeling of the standard library.
<p>The analyzer needs a better understanding of STL in order to be more
useful on C++ codebases.
While full library modeling is not an easy task,
large gains can be achieved by supporting only a few cases:
e.g. calling <code>.length()</code> on an empty
<code>std::string</code> always yields zero.
<p><i>(Difficulty: Medium)</i></p><p>
</li>
<li>Enhance CFG to model exception-handling.
<p>Currently exceptions are treated as "black holes", and exception-handling
control structures are poorly modeled in order to be conservative.
This could be improved for both C++ and Objective-C exceptions.
<p><i>(Difficulty: Hard)</i></p></p>
</li>
</ul>
</li>
<li>Core Analyzer Infrastructure
<ul>
<li>Handle unions.
<p>Currently in the analyzer the value of a union is always regarded as
an unknown.
This problem was
previously <a href="http://lists.llvm.org/pipermail/cfe-dev/2017-March/052864.html">discussed</a>
on the mailing list, but no solution was implemented.
<p><i> (Difficulty: Medium) </i></p></p>
</li>
<li>Floating-point support.
<p>Currently, the analyzer treats all floating-point values as unknown.
This project would involve adding a new <code>SVal</code> kind
for constant floats, generalizing the constraint manager to handle floats,
and auditing existing code to make sure it doesn't
make incorrect assumptions (most notably, that <code>X == X</code>
is always true, since it does not hold for <code>NaN</code>).
<p><i> (Difficulty: Medium)</i></p></p>
</li>
<li>Improved loop execution modeling.
<p>The analyzer simply unrolls each loop <tt>N</tt> times before
dropping the path, for a fixed constant <tt>N</tt>.
However, that results in lost coverage in cases where the loop always
executes more than <tt>N</tt> times.
A Google Summer Of Code
<a href="https://summerofcode.withgoogle.com/archive/2017/projects/6071606019358720/">project</a>
was completed to make the loop bound parameterizable,
but the <a href="https://en.wikipedia.org/wiki/Widening_(computer_science)">widening</a>
problem still remains open.
<p><i> (Difficulty: Hard)</i></p></p>
</li>
<li>Basic function summarization support
<p>The analyzer performs inter-procedural analysis using
either inlining or "conservative evaluation" (invalidating all data
passed to the function).
Often, a very simple summary
(e.g. "this function is <a href="https://en.wikipedia.org/wiki/Pure_function">pure</a>") would be
enough to be a large improvement over conservative evaluation.
Such summaries could be obtained either syntactically,
or using a dataflow framework.
<p><i>(Difficulty: Hard)</i></p><p>
</li>
<li>Implement a dataflow flamework.
<p>The analyzer core
implements a <a href="https://en.wikipedia.org/wiki/Symbolic_execution">symbolic execution</a>
engine, which performs checks
(use-after-free, uninitialized value read, etc.)
over a <em>single</em> program path.
However, many useful properties
(dead code, check-after-use, etc.) require
reasoning over <em>all</em> possible in a program.
Such reasoning requires a
<a href="https://en.wikipedia.org/wiki/Data-flow_analysis">dataflow analysis</a> framework.
Clang already implements
a few dataflow analyses (most notably, liveness),
but they implemented in an ad-hoc fashion.
A proper framework would enable us writing many more useful checkers.
<p><i> (Difficulty: Hard) </i></p></p>
</li>
<li>Track type information through casts more precisely.
<p>The <code>DynamicTypePropagation</code>
checker is in charge of inferring a region's
dynamic type based on what operations the code is performing.
Casts are a rich source of type information that the analyzer currently ignores.
<p><i>(Difficulty: Medium)</i></p></p>
</li>
</ul>
</li>
<li>Fixing miscellaneous bugs
<p>Apart from the open projects listed above,
contributors are welcome to fix any of the outstanding
<a href="https://bugs.llvm.org/buglist.cgi?component=Static%20Analyzer&list_id=147756&product=clang&resolution=---">bugs</a>
in the Bugzilla.
<p><i>(Difficulty: Anything)</i></p></p>
</li>
</ul>
</div>
</div>
</body>
</html>