Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

171 lines
5.7 KiB
C++
Raw Normal View History

//== CheckerContext.cpp - Context info for path-sensitive checkers-----------=//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file defines CheckerContext that provides contextual info for
// path-sensitive checkers.
//
//===----------------------------------------------------------------------===//
#include "clang/StaticAnalyzer/Core/PathSensitive/CheckerContext.h"
#include "clang/Basic/Builtins.h"
#include "clang/Lex/Lexer.h"
#include "llvm/ADT/StringExtras.h"
using namespace clang;
using namespace ento;
const FunctionDecl *CheckerContext::getCalleeDecl(const CallExpr *CE) const {
const FunctionDecl *D = CE->getDirectCallee();
if (D)
return D;
const Expr *Callee = CE->getCallee();
SVal L = Pred->getSVal(Callee);
return L.getAsFunctionDecl();
}
StringRef CheckerContext::getCalleeName(const FunctionDecl *FunDecl) const {
if (!FunDecl)
return StringRef();
IdentifierInfo *funI = FunDecl->getIdentifier();
if (!funI)
return StringRef();
return funI->getName();
}
StringRef CheckerContext::getDeclDescription(const Decl *D) {
if (isa<ObjCMethodDecl, CXXMethodDecl>(D))
return "method";
if (isa<BlockDecl>(D))
return "anonymous block";
return "function";
}
bool CheckerContext::isCLibraryFunction(const FunctionDecl *FD,
StringRef Name) {
// To avoid false positives (Ex: finding user defined functions with
// similar names), only perform fuzzy name matching when it's a builtin.
// Using a string compare is slow, we might want to switch on BuiltinID here.
unsigned BId = FD->getBuiltinID();
if (BId != 0) {
if (Name.empty())
return true;
StringRef BName = FD->getASTContext().BuiltinInfo.getName(BId);
size_t start = BName.find(Name);
if (start != StringRef::npos) {
// Accept exact match.
if (BName.size() == Name.size())
return true;
// v-- match starts here
// ...xxxxx...
// _xxxxx_
// ^ ^ lookbehind and lookahead characters
const auto MatchPredecessor = [=]() -> bool {
return start <= 0 || !llvm::isAlpha(BName[start - 1]);
};
const auto MatchSuccessor = [=]() -> bool {
std::size_t LookbehindPlace = start + Name.size();
return LookbehindPlace >= BName.size() ||
!llvm::isAlpha(BName[LookbehindPlace]);
};
if (MatchPredecessor() && MatchSuccessor())
return true;
}
}
const IdentifierInfo *II = FD->getIdentifier();
// If this is a special C++ name without IdentifierInfo, it can't be a
// C library function.
if (!II)
return false;
// C library functions are either declared directly within a TU (the common
// case) or they are accessed through the namespace `std` (when they are used
// in C++ via headers like <cstdlib>).
const DeclContext *DC = FD->getDeclContext()->getRedeclContext();
if (!(DC->isTranslationUnit() || DC->isStdNamespace()))
return false;
// If this function is not externally visible, it is not a C library function.
// Note that we make an exception for inline functions, which may be
// declared in header files without external linkage.
if (!FD->isInlined() && !FD->isExternallyVisible())
return false;
if (Name.empty())
return true;
StringRef FName = II->getName();
if (FName == Name)
return true;
if (FName.starts_with("__inline") && FName.contains(Name))
return true;
return false;
}
[analyzer] Make recognition of hardened __FOO_chk functions explicit (#86536) In builds that use source hardening (-D_FORTIFY_SOURCE), many standard functions are implemented as macros that expand to calls of hardened functions that take one additional argument compared to the "usual" variant and perform additional input validation. For example, a `memcpy` call may expand to `__memcpy_chk()` or `__builtin___memcpy_chk()`. Before this commit, `CallDescription`s created with the matching mode `CDM::CLibrary` automatically matched these hardened variants (in a addition to the "usual" function) with a fairly lenient heuristic. Unfortunately this heuristic meant that the `CLibrary` matching mode was only usable by checkers that were prepared to handle matches with an unusual number of arguments. This commit limits the recognition of the hardened functions to a separate matching mode `CDM::CLibraryMaybeHardened` and applies this mode for functions that have hardened variants and were previously recognized with `CDM::CLibrary`. This way checkers that are prepared to handle the hardened variants will be able to detect them easily; while other checkers can simply use `CDM::CLibrary` for matching C library functions (and they won't encounter surprising argument counts). The initial motivation for refactoring this area was that previously `CDM::CLibrary` accepted calls with more arguments/parameters than the expected number, so I wasn't able to use it for `malloc` without accidentally matching calls to the 3-argument BSD kernel malloc. After this commit this "may have more args/params" logic will only activate when we're actually matching a hardened variant function (in `CDM::CLibraryMaybeHardened` mode). The recognition of "sprintf()" and "snprintf()" in CStringChecker was refactored, because previously it was abusing the behavior that extra arguments are accepted even if the matched function is not a hardened variant. This commit also fixes the oversight that the old code would've recognized e.g. `__wmemcpy_chk` as a hardened variant of `memcpy`. After this commit I'm planning to create several follow-up commits that ensure that checkers looking for C library functions use `CDM::CLibrary` as a "sane default" matching mode. This commit is not truly NFC (it eliminates some buggy corner cases), but it does not intentionally modify the behavior of CSA on real-world non-crazy code. As a minor unrelated change I'm eliminating the argument/variable "IsBuiltin" from the evalSprintf function family in CStringChecker, because it was completely unused. --------- Co-authored-by: Balazs Benics <benicsbalazs@gmail.com>
2024-04-05 11:20:27 +02:00
bool CheckerContext::isHardenedVariantOf(const FunctionDecl *FD,
StringRef Name) {
const IdentifierInfo *II = FD->getIdentifier();
if (!II)
return false;
auto CompletelyMatchesParts = [II](auto... Parts) -> bool {
StringRef FName = II->getName();
return (FName.consume_front(Parts) && ...) && FName.empty();
};
return CompletelyMatchesParts("__", Name, "_chk") ||
CompletelyMatchesParts("__builtin_", "__", Name, "_chk");
}
StringRef CheckerContext::getMacroNameOrSpelling(SourceLocation &Loc) {
if (Loc.isMacroID())
return Lexer::getImmediateMacroName(Loc, getSourceManager(),
getLangOpts());
SmallString<16> buf;
return Lexer::getSpelling(Loc, buf, getSourceManager(), getLangOpts());
}
/// Evaluate comparison and return true if it's known that condition is true
static bool evalComparison(SVal LHSVal, BinaryOperatorKind ComparisonOp,
SVal RHSVal, ProgramStateRef State) {
if (LHSVal.isUnknownOrUndef())
return false;
ProgramStateManager &Mgr = State->getStateManager();
if (!isa<NonLoc>(LHSVal)) {
LHSVal = Mgr.getStoreManager().getBinding(State->getStore(),
LHSVal.castAs<Loc>());
if (LHSVal.isUnknownOrUndef() || !isa<NonLoc>(LHSVal))
return false;
}
SValBuilder &Bldr = Mgr.getSValBuilder();
SVal Eval = Bldr.evalBinOp(State, ComparisonOp, LHSVal, RHSVal,
Bldr.getConditionType());
if (Eval.isUnknownOrUndef())
return false;
ProgramStateRef StTrue, StFalse;
std::tie(StTrue, StFalse) = State->assume(Eval.castAs<DefinedSVal>());
return StTrue && !StFalse;
}
bool CheckerContext::isGreaterOrEqual(const Expr *E, unsigned long long Val) {
DefinedSVal V = getSValBuilder().makeIntVal(Val, getASTContext().LongLongTy);
return evalComparison(getSVal(E), BO_GE, V, getState());
}
bool CheckerContext::isNegative(const Expr *E) {
DefinedSVal V = getSValBuilder().makeIntVal(0, false);
return evalComparison(getSVal(E), BO_LT, V, getState());
}