head	1.1;
branch	1.1.1;
access;
symbols
	netbsd-11-0-RC4:1.1.1.6
	netbsd-11-0-RC3:1.1.1.6
	netbsd-11-0-RC2:1.1.1.6
	netbsd-11-0-RC1:1.1.1.6
	perseant-exfatfs-base-20250801:1.1.1.6
	netbsd-11:1.1.1.6.0.10
	netbsd-11-base:1.1.1.6
	netbsd-10-1-RELEASE:1.1.1.6
	perseant-exfatfs-base-20240630:1.1.1.6
	perseant-exfatfs:1.1.1.6.0.8
	perseant-exfatfs-base:1.1.1.6
	netbsd-8-3-RELEASE:1.1.1.3
	netbsd-9-4-RELEASE:1.1.1.5
	netbsd-10-0-RELEASE:1.1.1.6
	netbsd-10-0-RC6:1.1.1.6
	netbsd-10-0-RC5:1.1.1.6
	netbsd-10-0-RC4:1.1.1.6
	netbsd-10-0-RC3:1.1.1.6
	netbsd-10-0-RC2:1.1.1.6
	netbsd-10-0-RC1:1.1.1.6
	netbsd-10:1.1.1.6.0.6
	netbsd-10-base:1.1.1.6
	netbsd-9-3-RELEASE:1.1.1.5
	cjep_sun2x:1.1.1.6.0.4
	cjep_sun2x-base:1.1.1.6
	cjep_staticlib_x-base1:1.1.1.6
	netbsd-9-2-RELEASE:1.1.1.5
	cjep_staticlib_x:1.1.1.6.0.2
	cjep_staticlib_x-base:1.1.1.6
	netbsd-9-1-RELEASE:1.1.1.5
	phil-wifi-20200421:1.1.1.6
	phil-wifi-20200411:1.1.1.6
	phil-wifi-20200406:1.1.1.6
	netbsd-8-2-RELEASE:1.1.1.3
	netbsd-9-0-RELEASE:1.1.1.5
	netbsd-9-0-RC2:1.1.1.5
	netbsd-9-0-RC1:1.1.1.5
	netbsd-9:1.1.1.5.0.2
	netbsd-9-base:1.1.1.5
	phil-wifi-20190609:1.1.1.5
	netbsd-8-1-RELEASE:1.1.1.3
	netbsd-8-1-RC1:1.1.1.3
	pgoyette-compat-merge-20190127:1.1.1.4.2.1
	pgoyette-compat-20190127:1.1.1.5
	pgoyette-compat-20190118:1.1.1.5
	pgoyette-compat-1226:1.1.1.5
	pgoyette-compat-1126:1.1.1.5
	pgoyette-compat-1020:1.1.1.5
	pgoyette-compat-0930:1.1.1.5
	pgoyette-compat-0906:1.1.1.5
	netbsd-7-2-RELEASE:1.1.1.2
	pgoyette-compat-0728:1.1.1.5
	clang-337282:1.1.1.5
	netbsd-8-0-RELEASE:1.1.1.3
	phil-wifi:1.1.1.4.0.4
	phil-wifi-base:1.1.1.4
	pgoyette-compat-0625:1.1.1.4
	netbsd-8-0-RC2:1.1.1.3
	pgoyette-compat-0521:1.1.1.4
	pgoyette-compat-0502:1.1.1.4
	pgoyette-compat-0422:1.1.1.4
	netbsd-8-0-RC1:1.1.1.3
	pgoyette-compat-0415:1.1.1.4
	pgoyette-compat-0407:1.1.1.4
	pgoyette-compat-0330:1.1.1.4
	pgoyette-compat-0322:1.1.1.4
	pgoyette-compat-0315:1.1.1.4
	netbsd-7-1-2-RELEASE:1.1.1.2
	pgoyette-compat:1.1.1.4.0.2
	pgoyette-compat-base:1.1.1.4
	netbsd-7-1-1-RELEASE:1.1.1.2
	clang-319952:1.1.1.4
	matt-nb8-mediatek:1.1.1.3.0.12
	matt-nb8-mediatek-base:1.1.1.3
	clang-309604:1.1.1.4
	perseant-stdc-iso10646:1.1.1.3.0.10
	perseant-stdc-iso10646-base:1.1.1.3
	netbsd-8:1.1.1.3.0.8
	netbsd-8-base:1.1.1.3
	prg-localcount2-base3:1.1.1.3
	prg-localcount2-base2:1.1.1.3
	prg-localcount2-base1:1.1.1.3
	prg-localcount2:1.1.1.3.0.6
	prg-localcount2-base:1.1.1.3
	pgoyette-localcount-20170426:1.1.1.3
	bouyer-socketcan-base1:1.1.1.3
	pgoyette-localcount-20170320:1.1.1.3
	netbsd-7-1:1.1.1.2.0.14
	netbsd-7-1-RELEASE:1.1.1.2
	netbsd-7-1-RC2:1.1.1.2
	clang-294123:1.1.1.3
	netbsd-7-nhusb-base-20170116:1.1.1.2
	bouyer-socketcan:1.1.1.3.0.4
	bouyer-socketcan-base:1.1.1.3
	clang-291444:1.1.1.3
	pgoyette-localcount-20170107:1.1.1.3
	netbsd-7-1-RC1:1.1.1.2
	pgoyette-localcount-20161104:1.1.1.3
	netbsd-7-0-2-RELEASE:1.1.1.2
	localcount-20160914:1.1.1.3
	netbsd-7-nhusb:1.1.1.2.0.12
	netbsd-7-nhusb-base:1.1.1.2
	clang-280599:1.1.1.3
	pgoyette-localcount-20160806:1.1.1.3
	pgoyette-localcount-20160726:1.1.1.3
	pgoyette-localcount:1.1.1.3.0.2
	pgoyette-localcount-base:1.1.1.3
	netbsd-7-0-1-RELEASE:1.1.1.2
	clang-261930:1.1.1.3
	netbsd-7-0:1.1.1.2.0.10
	netbsd-7-0-RELEASE:1.1.1.2
	netbsd-7-0-RC3:1.1.1.2
	netbsd-7-0-RC2:1.1.1.2
	netbsd-7-0-RC1:1.1.1.2
	clang-237755:1.1.1.2
	clang-232565:1.1.1.2
	clang-227398:1.1.1.2
	tls-maxphys-base:1.1.1.2
	tls-maxphys:1.1.1.2.0.8
	netbsd-7:1.1.1.2.0.6
	netbsd-7-base:1.1.1.2
	clang-215315:1.1.1.2
	clang-209886:1.1.1.2
	yamt-pagecache:1.1.1.2.0.4
	yamt-pagecache-base9:1.1.1.2
	tls-earlyentropy:1.1.1.2.0.2
	tls-earlyentropy-base:1.1.1.2
	riastradh-xf86-video-intel-2-7-1-pre-2-21-15:1.1.1.2
	riastradh-drm2-base3:1.1.1.2
	clang-202566:1.1.1.2
	clang-201163:1.1.1.1
	clang-199312:1.1.1.1
	clang-198450:1.1.1.1
	clang-196603:1.1.1.1
	clang-195771:1.1.1.1
	LLVM:1.1.1;
locks; strict;
comment	@// @;


1.1
date	2013.11.28.14.14.52;	author joerg;	state Exp;
branches
	1.1.1.1;
next	;
commitid	ow8OybrawrB1f3fx;

1.1.1.1
date	2013.11.28.14.14.52;	author joerg;	state Exp;
branches;
next	1.1.1.2;
commitid	ow8OybrawrB1f3fx;

1.1.1.2
date	2014.03.04.19.55.00;	author joerg;	state Exp;
branches
	1.1.1.2.4.1
	1.1.1.2.8.1;
next	1.1.1.3;
commitid	29z1hJonZISIXprx;

1.1.1.3
date	2016.02.27.22.12.06;	author joerg;	state Exp;
branches;
next	1.1.1.4;
commitid	tIimz3oDlh1NpBWy;

1.1.1.4
date	2017.08.01.19.35.16;	author joerg;	state Exp;
branches
	1.1.1.4.2.1
	1.1.1.4.4.1;
next	1.1.1.5;
commitid	pMuDy65V0VicSx1A;

1.1.1.5
date	2018.07.17.18.31.07;	author joerg;	state Exp;
branches;
next	1.1.1.6;
commitid	wDzL46ALjrCZgwKA;

1.1.1.6
date	2019.11.13.22.19.28;	author joerg;	state dead;
branches;
next	;
commitid	QD8YATxuNG34YJKB;

1.1.1.2.4.1
date	2014.03.04.19.55.00;	author yamt;	state dead;
branches;
next	1.1.1.2.4.2;
commitid	WSrDtL5nYAUyiyBx;

1.1.1.2.4.2
date	2014.05.22.16.18.30;	author yamt;	state Exp;
branches;
next	;
commitid	WSrDtL5nYAUyiyBx;

1.1.1.2.8.1
date	2014.03.04.19.55.00;	author tls;	state dead;
branches;
next	1.1.1.2.8.2;
commitid	jTnpym9Qu0o4R1Nx;

1.1.1.2.8.2
date	2014.08.19.23.47.31;	author tls;	state Exp;
branches;
next	;
commitid	jTnpym9Qu0o4R1Nx;

1.1.1.4.2.1
date	2018.07.28.04.33.23;	author pgoyette;	state Exp;
branches;
next	;
commitid	1UP1xAIUxv1ZgRLA;

1.1.1.4.4.1
date	2019.06.10.21.45.28;	author christos;	state Exp;
branches;
next	1.1.1.4.4.2;
commitid	jtc8rnCzWiEEHGqB;

1.1.1.4.4.2
date	2020.04.13.07.46.38;	author martin;	state dead;
branches;
next	;
commitid	X01YhRUPVUDaec4C;


desc
@@


1.1
log
@Initial revision
@
text
@//== CStringSyntaxChecker.cpp - CoreFoundation containers API *- C++ -*-==//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// An AST checker that looks for common pitfalls when using C string APIs.
//  - Identifies erroneous patterns in the last argument to strncat - the number
//    of bytes to copy.
//
//===----------------------------------------------------------------------===//
#include "ClangSACheckers.h"
#include "clang/AST/Expr.h"
#include "clang/AST/OperationKinds.h"
#include "clang/AST/StmtVisitor.h"
#include "clang/Analysis/AnalysisContext.h"
#include "clang/Basic/TargetInfo.h"
#include "clang/Basic/TypeTraits.h"
#include "clang/StaticAnalyzer/Core/BugReporter/BugReporter.h"
#include "clang/StaticAnalyzer/Core/Checker.h"
#include "clang/StaticAnalyzer/Core/PathSensitive/AnalysisManager.h"
#include "clang/StaticAnalyzer/Core/PathSensitive/CheckerContext.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/Support/raw_ostream.h"

using namespace clang;
using namespace ento;

namespace {
class WalkAST: public StmtVisitor<WalkAST> {
  BugReporter &BR;
  AnalysisDeclContext* AC;

  /// Check if two expressions refer to the same declaration.
  inline bool sameDecl(const Expr *A1, const Expr *A2) {
    if (const DeclRefExpr *D1 = dyn_cast<DeclRefExpr>(A1->IgnoreParenCasts()))
      if (const DeclRefExpr *D2 = dyn_cast<DeclRefExpr>(A2->IgnoreParenCasts()))
        return D1->getDecl() == D2->getDecl();
    return false;
  }

  /// Check if the expression E is a sizeof(WithArg).
  inline bool isSizeof(const Expr *E, const Expr *WithArg) {
    if (const UnaryExprOrTypeTraitExpr *UE =
    dyn_cast<UnaryExprOrTypeTraitExpr>(E))
      if (UE->getKind() == UETT_SizeOf)
        return sameDecl(UE->getArgumentExpr(), WithArg);
    return false;
  }

  /// Check if the expression E is a strlen(WithArg).
  inline bool isStrlen(const Expr *E, const Expr *WithArg) {
    if (const CallExpr *CE = dyn_cast<CallExpr>(E)) {
      const FunctionDecl *FD = CE->getDirectCallee();
      if (!FD)
        return false;
      return (CheckerContext::isCLibraryFunction(FD, "strlen") &&
              sameDecl(CE->getArg(0), WithArg));
    }
    return false;
  }

  /// Check if the expression is an integer literal with value 1.
  inline bool isOne(const Expr *E) {
    if (const IntegerLiteral *IL = dyn_cast<IntegerLiteral>(E))
      return (IL->getValue().isIntN(1));
    return false;
  }

  inline StringRef getPrintableName(const Expr *E) {
    if (const DeclRefExpr *D = dyn_cast<DeclRefExpr>(E->IgnoreParenCasts()))
      return D->getDecl()->getName();
    return StringRef();
  }

  /// Identify erroneous patterns in the last argument to strncat - the number
  /// of bytes to copy.
  bool containsBadStrncatPattern(const CallExpr *CE);

public:
  WalkAST(BugReporter &br, AnalysisDeclContext* ac) :
      BR(br), AC(ac) {
  }

  // Statement visitor methods.
  void VisitChildren(Stmt *S);
  void VisitStmt(Stmt *S) {
    VisitChildren(S);
  }
  void VisitCallExpr(CallExpr *CE);
};
} // end anonymous namespace

// The correct size argument should look like following:
//   strncat(dst, src, sizeof(dst) - strlen(dest) - 1);
// We look for the following anti-patterns:
//   - strncat(dst, src, sizeof(dst) - strlen(dst));
//   - strncat(dst, src, sizeof(dst) - 1);
//   - strncat(dst, src, sizeof(dst));
bool WalkAST::containsBadStrncatPattern(const CallExpr *CE) {
  if (CE->getNumArgs() != 3)
    return false;
  const Expr *DstArg = CE->getArg(0);
  const Expr *SrcArg = CE->getArg(1);
  const Expr *LenArg = CE->getArg(2);

  // Identify wrong size expressions, which are commonly used instead.
  if (const BinaryOperator *BE =
              dyn_cast<BinaryOperator>(LenArg->IgnoreParenCasts())) {
    // - sizeof(dst) - strlen(dst)
    if (BE->getOpcode() == BO_Sub) {
      const Expr *L = BE->getLHS();
      const Expr *R = BE->getRHS();
      if (isSizeof(L, DstArg) && isStrlen(R, DstArg))
        return true;

      // - sizeof(dst) - 1
      if (isSizeof(L, DstArg) && isOne(R->IgnoreParenCasts()))
        return true;
    }
  }
  // - sizeof(dst)
  if (isSizeof(LenArg, DstArg))
    return true;

  // - sizeof(src)
  if (isSizeof(LenArg, SrcArg))
    return true;
  return false;
}

void WalkAST::VisitCallExpr(CallExpr *CE) {
  const FunctionDecl *FD = CE->getDirectCallee();
  if (!FD)
    return;

  if (CheckerContext::isCLibraryFunction(FD, "strncat")) {
    if (containsBadStrncatPattern(CE)) {
      const Expr *DstArg = CE->getArg(0);
      const Expr *LenArg = CE->getArg(2);
      PathDiagnosticLocation Loc =
        PathDiagnosticLocation::createBegin(LenArg, BR.getSourceManager(), AC);

      StringRef DstName = getPrintableName(DstArg);

      SmallString<256> S;
      llvm::raw_svector_ostream os(S);
      os << "Potential buffer overflow. ";
      if (!DstName.empty()) {
        os << "Replace with 'sizeof(" << DstName << ") "
              "- strlen(" << DstName <<") - 1'";
        os << " or u";
      } else
        os << "U";
      os << "se a safer 'strlcat' API";

      BR.EmitBasicReport(FD, "Anti-pattern in the argument", "C String API",
                         os.str(), Loc, LenArg->getSourceRange());
    }
  }

  // Recurse and check children.
  VisitChildren(CE);
}

void WalkAST::VisitChildren(Stmt *S) {
  for (Stmt::child_iterator I = S->child_begin(), E = S->child_end(); I != E;
      ++I)
    if (Stmt *child = *I)
      Visit(child);
}

namespace {
class CStringSyntaxChecker: public Checker<check::ASTCodeBody> {
public:

  void checkASTCodeBody(const Decl *D, AnalysisManager& Mgr,
      BugReporter &BR) const {
    WalkAST walker(BR, Mgr.getAnalysisDeclContext(D));
    walker.Visit(D->getBody());
  }
};
}

void ento::registerCStringSyntaxChecker(CheckerManager &mgr) {
  mgr.registerChecker<CStringSyntaxChecker>();
}

@


1.1.1.1
log
@Import Clang 3.4rc1 r195771.
@
text
@@


1.1.1.2
log
@Import Clang 3.5svn r202566.
@
text
@a33 1
  const CheckerBase *Checker;
d84 3
a86 2
  WalkAST(const CheckerBase *checker, BugReporter &br, AnalysisDeclContext *ac)
      : Checker(checker), BR(br), AC(ac) {}
d160 2
a161 3
      BR.EmitBasicReport(FD, Checker, "Anti-pattern in the argument",
                         "C String API", os.str(), Loc,
                         LenArg->getSourceRange());
d182 1
a182 1
    WalkAST walker(this, BR, Mgr.getAnalysisDeclContext(D));
@


1.1.1.3
log
@Import Clang 3.8.0rc3 r261930.
@
text
@d171 4
a174 3
  for (Stmt *Child : S->children())
    if (Child)
      Visit(Child);
@


1.1.1.4
log
@Import clang r309604 from branches/release_50
@
text
@d39 3
a41 3
  bool sameDecl(const Expr *A1, const Expr *A2) {
    if (const auto *D1 = dyn_cast<DeclRefExpr>(A1->IgnoreParenCasts()))
      if (const auto *D2 = dyn_cast<DeclRefExpr>(A2->IgnoreParenCasts()))
d47 4
a50 3
  bool isSizeof(const Expr *E, const Expr *WithArg) {
    if (const auto *UE = dyn_cast<UnaryExprOrTypeTraitExpr>(E))
      if (UE->getKind() == UETT_SizeOf && !UE->isArgumentType())
d56 2
a57 2
  bool isStrlen(const Expr *E, const Expr *WithArg) {
    if (const auto *CE = dyn_cast<CallExpr>(E)) {
d68 2
a69 2
  bool isOne(const Expr *E) {
    if (const auto *IL = dyn_cast<IntegerLiteral>(E))
d74 2
a75 2
  StringRef getPrintableName(const Expr *E) {
    if (const auto *D = dyn_cast<DeclRefExpr>(E->IgnoreParenCasts()))
d85 2
a86 2
  WalkAST(const CheckerBase *Checker, BugReporter &BR, AnalysisDeclContext *AC)
      : Checker(Checker), BR(BR), AC(AC) {}
d111 2
a112 1
  if (const auto *BE = dyn_cast<BinaryOperator>(LenArg->IgnoreParenCasts())) {
@


1.1.1.4.4.1
log
@Sync with HEAD
@
text
@d19 1
a19 1
#include "clang/Analysis/AnalysisDeclContext.h"
@


1.1.1.4.4.2
log
@Mostly merge changes from HEAD upto 20200411
@
text
@@


1.1.1.4.2.1
log
@Sync with HEAD
@
text
@d19 1
a19 1
#include "clang/Analysis/AnalysisDeclContext.h"
@


1.1.1.5
log
@Import clang r337282 from trunk
@
text
@d19 1
a19 1
#include "clang/Analysis/AnalysisDeclContext.h"
@


1.1.1.6
log
@Mark old LLVM instance as dead.
@
text
@@


1.1.1.2.8.1
log
@file CStringSyntaxChecker.cpp was added on branch tls-maxphys on 2014-08-19 23:47:31 +0000
@
text
@d1 192
@


1.1.1.2.8.2
log
@Rebase to HEAD as of a few days ago.
@
text
@a0 192
//== CStringSyntaxChecker.cpp - CoreFoundation containers API *- C++ -*-==//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// An AST checker that looks for common pitfalls when using C string APIs.
//  - Identifies erroneous patterns in the last argument to strncat - the number
//    of bytes to copy.
//
//===----------------------------------------------------------------------===//
#include "ClangSACheckers.h"
#include "clang/AST/Expr.h"
#include "clang/AST/OperationKinds.h"
#include "clang/AST/StmtVisitor.h"
#include "clang/Analysis/AnalysisContext.h"
#include "clang/Basic/TargetInfo.h"
#include "clang/Basic/TypeTraits.h"
#include "clang/StaticAnalyzer/Core/BugReporter/BugReporter.h"
#include "clang/StaticAnalyzer/Core/Checker.h"
#include "clang/StaticAnalyzer/Core/PathSensitive/AnalysisManager.h"
#include "clang/StaticAnalyzer/Core/PathSensitive/CheckerContext.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/Support/raw_ostream.h"

using namespace clang;
using namespace ento;

namespace {
class WalkAST: public StmtVisitor<WalkAST> {
  const CheckerBase *Checker;
  BugReporter &BR;
  AnalysisDeclContext* AC;

  /// Check if two expressions refer to the same declaration.
  inline bool sameDecl(const Expr *A1, const Expr *A2) {
    if (const DeclRefExpr *D1 = dyn_cast<DeclRefExpr>(A1->IgnoreParenCasts()))
      if (const DeclRefExpr *D2 = dyn_cast<DeclRefExpr>(A2->IgnoreParenCasts()))
        return D1->getDecl() == D2->getDecl();
    return false;
  }

  /// Check if the expression E is a sizeof(WithArg).
  inline bool isSizeof(const Expr *E, const Expr *WithArg) {
    if (const UnaryExprOrTypeTraitExpr *UE =
    dyn_cast<UnaryExprOrTypeTraitExpr>(E))
      if (UE->getKind() == UETT_SizeOf)
        return sameDecl(UE->getArgumentExpr(), WithArg);
    return false;
  }

  /// Check if the expression E is a strlen(WithArg).
  inline bool isStrlen(const Expr *E, const Expr *WithArg) {
    if (const CallExpr *CE = dyn_cast<CallExpr>(E)) {
      const FunctionDecl *FD = CE->getDirectCallee();
      if (!FD)
        return false;
      return (CheckerContext::isCLibraryFunction(FD, "strlen") &&
              sameDecl(CE->getArg(0), WithArg));
    }
    return false;
  }

  /// Check if the expression is an integer literal with value 1.
  inline bool isOne(const Expr *E) {
    if (const IntegerLiteral *IL = dyn_cast<IntegerLiteral>(E))
      return (IL->getValue().isIntN(1));
    return false;
  }

  inline StringRef getPrintableName(const Expr *E) {
    if (const DeclRefExpr *D = dyn_cast<DeclRefExpr>(E->IgnoreParenCasts()))
      return D->getDecl()->getName();
    return StringRef();
  }

  /// Identify erroneous patterns in the last argument to strncat - the number
  /// of bytes to copy.
  bool containsBadStrncatPattern(const CallExpr *CE);

public:
  WalkAST(const CheckerBase *checker, BugReporter &br, AnalysisDeclContext *ac)
      : Checker(checker), BR(br), AC(ac) {}

  // Statement visitor methods.
  void VisitChildren(Stmt *S);
  void VisitStmt(Stmt *S) {
    VisitChildren(S);
  }
  void VisitCallExpr(CallExpr *CE);
};
} // end anonymous namespace

// The correct size argument should look like following:
//   strncat(dst, src, sizeof(dst) - strlen(dest) - 1);
// We look for the following anti-patterns:
//   - strncat(dst, src, sizeof(dst) - strlen(dst));
//   - strncat(dst, src, sizeof(dst) - 1);
//   - strncat(dst, src, sizeof(dst));
bool WalkAST::containsBadStrncatPattern(const CallExpr *CE) {
  if (CE->getNumArgs() != 3)
    return false;
  const Expr *DstArg = CE->getArg(0);
  const Expr *SrcArg = CE->getArg(1);
  const Expr *LenArg = CE->getArg(2);

  // Identify wrong size expressions, which are commonly used instead.
  if (const BinaryOperator *BE =
              dyn_cast<BinaryOperator>(LenArg->IgnoreParenCasts())) {
    // - sizeof(dst) - strlen(dst)
    if (BE->getOpcode() == BO_Sub) {
      const Expr *L = BE->getLHS();
      const Expr *R = BE->getRHS();
      if (isSizeof(L, DstArg) && isStrlen(R, DstArg))
        return true;

      // - sizeof(dst) - 1
      if (isSizeof(L, DstArg) && isOne(R->IgnoreParenCasts()))
        return true;
    }
  }
  // - sizeof(dst)
  if (isSizeof(LenArg, DstArg))
    return true;

  // - sizeof(src)
  if (isSizeof(LenArg, SrcArg))
    return true;
  return false;
}

void WalkAST::VisitCallExpr(CallExpr *CE) {
  const FunctionDecl *FD = CE->getDirectCallee();
  if (!FD)
    return;

  if (CheckerContext::isCLibraryFunction(FD, "strncat")) {
    if (containsBadStrncatPattern(CE)) {
      const Expr *DstArg = CE->getArg(0);
      const Expr *LenArg = CE->getArg(2);
      PathDiagnosticLocation Loc =
        PathDiagnosticLocation::createBegin(LenArg, BR.getSourceManager(), AC);

      StringRef DstName = getPrintableName(DstArg);

      SmallString<256> S;
      llvm::raw_svector_ostream os(S);
      os << "Potential buffer overflow. ";
      if (!DstName.empty()) {
        os << "Replace with 'sizeof(" << DstName << ") "
              "- strlen(" << DstName <<") - 1'";
        os << " or u";
      } else
        os << "U";
      os << "se a safer 'strlcat' API";

      BR.EmitBasicReport(FD, Checker, "Anti-pattern in the argument",
                         "C String API", os.str(), Loc,
                         LenArg->getSourceRange());
    }
  }

  // Recurse and check children.
  VisitChildren(CE);
}

void WalkAST::VisitChildren(Stmt *S) {
  for (Stmt::child_iterator I = S->child_begin(), E = S->child_end(); I != E;
      ++I)
    if (Stmt *child = *I)
      Visit(child);
}

namespace {
class CStringSyntaxChecker: public Checker<check::ASTCodeBody> {
public:

  void checkASTCodeBody(const Decl *D, AnalysisManager& Mgr,
      BugReporter &BR) const {
    WalkAST walker(this, BR, Mgr.getAnalysisDeclContext(D));
    walker.Visit(D->getBody());
  }
};
}

void ento::registerCStringSyntaxChecker(CheckerManager &mgr) {
  mgr.registerChecker<CStringSyntaxChecker>();
}

@


1.1.1.2.4.1
log
@file CStringSyntaxChecker.cpp was added on branch yamt-pagecache on 2014-05-22 16:18:30 +0000
@
text
@d1 192
@


1.1.1.2.4.2
log
@sync with head.

for a reference, the tree before this commit was tagged
as yamt-pagecache-tag8.

this commit was splitted into small chunks to avoid
a limitation of cvs.  ("Protocol error: too many arguments")
@
text
@a0 192
//== CStringSyntaxChecker.cpp - CoreFoundation containers API *- C++ -*-==//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// An AST checker that looks for common pitfalls when using C string APIs.
//  - Identifies erroneous patterns in the last argument to strncat - the number
//    of bytes to copy.
//
//===----------------------------------------------------------------------===//
#include "ClangSACheckers.h"
#include "clang/AST/Expr.h"
#include "clang/AST/OperationKinds.h"
#include "clang/AST/StmtVisitor.h"
#include "clang/Analysis/AnalysisContext.h"
#include "clang/Basic/TargetInfo.h"
#include "clang/Basic/TypeTraits.h"
#include "clang/StaticAnalyzer/Core/BugReporter/BugReporter.h"
#include "clang/StaticAnalyzer/Core/Checker.h"
#include "clang/StaticAnalyzer/Core/PathSensitive/AnalysisManager.h"
#include "clang/StaticAnalyzer/Core/PathSensitive/CheckerContext.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/Support/raw_ostream.h"

using namespace clang;
using namespace ento;

namespace {
class WalkAST: public StmtVisitor<WalkAST> {
  const CheckerBase *Checker;
  BugReporter &BR;
  AnalysisDeclContext* AC;

  /// Check if two expressions refer to the same declaration.
  inline bool sameDecl(const Expr *A1, const Expr *A2) {
    if (const DeclRefExpr *D1 = dyn_cast<DeclRefExpr>(A1->IgnoreParenCasts()))
      if (const DeclRefExpr *D2 = dyn_cast<DeclRefExpr>(A2->IgnoreParenCasts()))
        return D1->getDecl() == D2->getDecl();
    return false;
  }

  /// Check if the expression E is a sizeof(WithArg).
  inline bool isSizeof(const Expr *E, const Expr *WithArg) {
    if (const UnaryExprOrTypeTraitExpr *UE =
    dyn_cast<UnaryExprOrTypeTraitExpr>(E))
      if (UE->getKind() == UETT_SizeOf)
        return sameDecl(UE->getArgumentExpr(), WithArg);
    return false;
  }

  /// Check if the expression E is a strlen(WithArg).
  inline bool isStrlen(const Expr *E, const Expr *WithArg) {
    if (const CallExpr *CE = dyn_cast<CallExpr>(E)) {
      const FunctionDecl *FD = CE->getDirectCallee();
      if (!FD)
        return false;
      return (CheckerContext::isCLibraryFunction(FD, "strlen") &&
              sameDecl(CE->getArg(0), WithArg));
    }
    return false;
  }

  /// Check if the expression is an integer literal with value 1.
  inline bool isOne(const Expr *E) {
    if (const IntegerLiteral *IL = dyn_cast<IntegerLiteral>(E))
      return (IL->getValue().isIntN(1));
    return false;
  }

  inline StringRef getPrintableName(const Expr *E) {
    if (const DeclRefExpr *D = dyn_cast<DeclRefExpr>(E->IgnoreParenCasts()))
      return D->getDecl()->getName();
    return StringRef();
  }

  /// Identify erroneous patterns in the last argument to strncat - the number
  /// of bytes to copy.
  bool containsBadStrncatPattern(const CallExpr *CE);

public:
  WalkAST(const CheckerBase *checker, BugReporter &br, AnalysisDeclContext *ac)
      : Checker(checker), BR(br), AC(ac) {}

  // Statement visitor methods.
  void VisitChildren(Stmt *S);
  void VisitStmt(Stmt *S) {
    VisitChildren(S);
  }
  void VisitCallExpr(CallExpr *CE);
};
} // end anonymous namespace

// The correct size argument should look like following:
//   strncat(dst, src, sizeof(dst) - strlen(dest) - 1);
// We look for the following anti-patterns:
//   - strncat(dst, src, sizeof(dst) - strlen(dst));
//   - strncat(dst, src, sizeof(dst) - 1);
//   - strncat(dst, src, sizeof(dst));
bool WalkAST::containsBadStrncatPattern(const CallExpr *CE) {
  if (CE->getNumArgs() != 3)
    return false;
  const Expr *DstArg = CE->getArg(0);
  const Expr *SrcArg = CE->getArg(1);
  const Expr *LenArg = CE->getArg(2);

  // Identify wrong size expressions, which are commonly used instead.
  if (const BinaryOperator *BE =
              dyn_cast<BinaryOperator>(LenArg->IgnoreParenCasts())) {
    // - sizeof(dst) - strlen(dst)
    if (BE->getOpcode() == BO_Sub) {
      const Expr *L = BE->getLHS();
      const Expr *R = BE->getRHS();
      if (isSizeof(L, DstArg) && isStrlen(R, DstArg))
        return true;

      // - sizeof(dst) - 1
      if (isSizeof(L, DstArg) && isOne(R->IgnoreParenCasts()))
        return true;
    }
  }
  // - sizeof(dst)
  if (isSizeof(LenArg, DstArg))
    return true;

  // - sizeof(src)
  if (isSizeof(LenArg, SrcArg))
    return true;
  return false;
}

void WalkAST::VisitCallExpr(CallExpr *CE) {
  const FunctionDecl *FD = CE->getDirectCallee();
  if (!FD)
    return;

  if (CheckerContext::isCLibraryFunction(FD, "strncat")) {
    if (containsBadStrncatPattern(CE)) {
      const Expr *DstArg = CE->getArg(0);
      const Expr *LenArg = CE->getArg(2);
      PathDiagnosticLocation Loc =
        PathDiagnosticLocation::createBegin(LenArg, BR.getSourceManager(), AC);

      StringRef DstName = getPrintableName(DstArg);

      SmallString<256> S;
      llvm::raw_svector_ostream os(S);
      os << "Potential buffer overflow. ";
      if (!DstName.empty()) {
        os << "Replace with 'sizeof(" << DstName << ") "
              "- strlen(" << DstName <<") - 1'";
        os << " or u";
      } else
        os << "U";
      os << "se a safer 'strlcat' API";

      BR.EmitBasicReport(FD, Checker, "Anti-pattern in the argument",
                         "C String API", os.str(), Loc,
                         LenArg->getSourceRange());
    }
  }

  // Recurse and check children.
  VisitChildren(CE);
}

void WalkAST::VisitChildren(Stmt *S) {
  for (Stmt::child_iterator I = S->child_begin(), E = S->child_end(); I != E;
      ++I)
    if (Stmt *child = *I)
      Visit(child);
}

namespace {
class CStringSyntaxChecker: public Checker<check::ASTCodeBody> {
public:

  void checkASTCodeBody(const Decl *D, AnalysisManager& Mgr,
      BugReporter &BR) const {
    WalkAST walker(this, BR, Mgr.getAnalysisDeclContext(D));
    walker.Visit(D->getBody());
  }
};
}

void ento::registerCStringSyntaxChecker(CheckerManager &mgr) {
  mgr.registerChecker<CStringSyntaxChecker>();
}

@


