head	1.1;
branch	1.1.1;
access;
symbols
	netbsd-9-5-RELEASE:1.1.1.4
	netbsd-11-0-RELEASE:1.1.1.5
	netbsd-11-0-RC7:1.1.1.5
	netbsd-11-0-RC6:1.1.1.5
	netbsd-11-0-RC5:1.1.1.5
	netbsd-11-0-RC4:1.1.1.5
	netbsd-11-0-RC3:1.1.1.5
	netbsd-11-0-RC2:1.1.1.5
	netbsd-11-0-RC1:1.1.1.5
	perseant-exfatfs-base-20250801:1.1.1.5
	netbsd-11:1.1.1.5.0.10
	netbsd-11-base:1.1.1.5
	netbsd-10-1-RELEASE:1.1.1.5
	perseant-exfatfs-base-20240630:1.1.1.5
	perseant-exfatfs:1.1.1.5.0.8
	perseant-exfatfs-base:1.1.1.5
	netbsd-8-3-RELEASE:1.1.1.4
	netbsd-9-4-RELEASE:1.1.1.4
	netbsd-10-0-RELEASE:1.1.1.5
	netbsd-10-0-RC6:1.1.1.5
	netbsd-10-0-RC5:1.1.1.5
	netbsd-10-0-RC4:1.1.1.5
	netbsd-10-0-RC3:1.1.1.5
	netbsd-10-0-RC2:1.1.1.5
	netbsd-10-0-RC1:1.1.1.5
	netbsd-10:1.1.1.5.0.6
	netbsd-10-base:1.1.1.5
	netbsd-9-3-RELEASE:1.1.1.4
	cjep_sun2x:1.1.1.5.0.4
	cjep_sun2x-base:1.1.1.5
	cjep_staticlib_x-base1:1.1.1.5
	netbsd-9-2-RELEASE:1.1.1.4
	cjep_staticlib_x:1.1.1.5.0.2
	cjep_staticlib_x-base:1.1.1.5
	netbsd-9-1-RELEASE:1.1.1.4
	phil-wifi-20200421:1.1.1.5
	phil-wifi-20200411:1.1.1.5
	phil-wifi-20200406:1.1.1.5
	netbsd-8-2-RELEASE:1.1.1.4
	netbsd-9-0-RELEASE:1.1.1.4
	netbsd-9-0-RC2:1.1.1.4
	netbsd-9-0-RC1:1.1.1.4
	netbsd-9:1.1.1.4.0.18
	netbsd-9-base:1.1.1.4
	phil-wifi-20190609:1.1.1.4
	netbsd-8-1-RELEASE:1.1.1.4
	netbsd-8-1-RC1:1.1.1.4
	pgoyette-compat-merge-20190127:1.1.1.4
	pgoyette-compat-20190127:1.1.1.4
	pgoyette-compat-20190118:1.1.1.4
	pgoyette-compat-1226:1.1.1.4
	pgoyette-compat-1126:1.1.1.4
	pgoyette-compat-1020:1.1.1.4
	pgoyette-compat-0930:1.1.1.4
	pgoyette-compat-0906:1.1.1.4
	netbsd-7-2-RELEASE:1.1.1.3
	pgoyette-compat-0728:1.1.1.4
	clang-337282:1.1.1.4
	netbsd-8-0-RELEASE:1.1.1.4
	phil-wifi:1.1.1.4.0.16
	phil-wifi-base:1.1.1.4
	pgoyette-compat-0625:1.1.1.4
	netbsd-8-0-RC2:1.1.1.4
	pgoyette-compat-0521:1.1.1.4
	pgoyette-compat-0502:1.1.1.4
	pgoyette-compat-0422:1.1.1.4
	netbsd-8-0-RC1:1.1.1.4
	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:1.1.1.3
	pgoyette-compat:1.1.1.4.0.14
	pgoyette-compat-base:1.1.1.4
	netbsd-7-1-1-RELEASE:1.1.1.3
	clang-319952:1.1.1.4
	matt-nb8-mediatek:1.1.1.4.0.12
	matt-nb8-mediatek-base:1.1.1.4
	clang-309604:1.1.1.4
	perseant-stdc-iso10646:1.1.1.4.0.10
	perseant-stdc-iso10646-base:1.1.1.4
	netbsd-8:1.1.1.4.0.8
	netbsd-8-base:1.1.1.4
	prg-localcount2-base3:1.1.1.4
	prg-localcount2-base2:1.1.1.4
	prg-localcount2-base1:1.1.1.4
	prg-localcount2:1.1.1.4.0.6
	prg-localcount2-base:1.1.1.4
	pgoyette-localcount-20170426:1.1.1.4
	bouyer-socketcan-base1:1.1.1.4
	pgoyette-localcount-20170320:1.1.1.4
	netbsd-7-1:1.1.1.3.0.10
	netbsd-7-1-RELEASE:1.1.1.3
	netbsd-7-1-RC2:1.1.1.3
	clang-294123:1.1.1.4
	netbsd-7-nhusb-base-20170116:1.1.1.3
	bouyer-socketcan:1.1.1.4.0.4
	bouyer-socketcan-base:1.1.1.4
	clang-291444:1.1.1.4
	pgoyette-localcount-20170107:1.1.1.4
	netbsd-7-1-RC1:1.1.1.3
	pgoyette-localcount-20161104:1.1.1.4
	netbsd-7-0-2-RELEASE:1.1.1.3
	localcount-20160914:1.1.1.4
	netbsd-7-nhusb:1.1.1.3.0.8
	netbsd-7-nhusb-base:1.1.1.3
	clang-280599:1.1.1.4
	pgoyette-localcount-20160806:1.1.1.4
	pgoyette-localcount-20160726:1.1.1.4
	pgoyette-localcount:1.1.1.4.0.2
	pgoyette-localcount-base:1.1.1.4
	netbsd-7-0-1-RELEASE:1.1.1.3
	clang-261930:1.1.1.4
	netbsd-7-0:1.1.1.3.0.6
	netbsd-7-0-RELEASE:1.1.1.3
	netbsd-7-0-RC3:1.1.1.3
	netbsd-7-0-RC2:1.1.1.3
	netbsd-7-0-RC1:1.1.1.3
	clang-237755:1.1.1.3
	clang-232565:1.1.1.3
	clang-227398:1.1.1.3
	tls-maxphys-base:1.1.1.3
	tls-maxphys:1.1.1.3.0.4
	netbsd-7:1.1.1.3.0.2
	netbsd-7-base:1.1.1.3
	clang-215315:1.1.1.3
	clang-209886:1.1.1.3
	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:1.1.1.3
	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
	1.1.1.2.2.1
	1.1.1.2.4.1;
next	1.1.1.3;
commitid	29z1hJonZISIXprx;

1.1.1.3
date	2014.05.30.18.14.44;	author joerg;	state Exp;
branches
	1.1.1.3.4.1;
next	1.1.1.4;
commitid	8q0kdlBlCn09GACx;

1.1.1.4
date	2016.02.27.22.12.06;	author joerg;	state Exp;
branches
	1.1.1.4.16.1;
next	1.1.1.5;
commitid	tIimz3oDlh1NpBWy;

1.1.1.5
date	2019.11.13.22.19.28;	author joerg;	state dead;
branches;
next	;
commitid	QD8YATxuNG34YJKB;

1.1.1.2.2.1
date	2014.08.10.07.08.10;	author tls;	state Exp;
branches;
next	;
commitid	t01A1TLTYxkpGMLx;

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	2014.05.22.16.18.31;	author yamt;	state Exp;
branches;
next	;
commitid	WSrDtL5nYAUyiyBx;

1.1.1.3.4.1
date	2014.05.30.18.14.44;	author tls;	state dead;
branches;
next	1.1.1.3.4.2;
commitid	jTnpym9Qu0o4R1Nx;

1.1.1.3.4.2
date	2014.08.19.23.47.31;	author tls;	state Exp;
branches;
next	;
commitid	jTnpym9Qu0o4R1Nx;

1.1.1.4.16.1
date	2020.04.13.07.46.38;	author martin;	state dead;
branches;
next	;
commitid	X01YhRUPVUDaec4C;


desc
@@


1.1
log
@Initial revision
@
text
@//=== LLVMConventionsChecker.cpp - Check LLVM codebase conventions ---*- C++ -*-
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This defines LLVMConventionsChecker, a bunch of small little checks
// for checking specific coding conventions in the LLVM/Clang codebase.
//
//===----------------------------------------------------------------------===//

#include "ClangSACheckers.h"
#include "clang/AST/DeclTemplate.h"
#include "clang/AST/StmtVisitor.h"
#include "clang/StaticAnalyzer/Core/BugReporter/BugReporter.h"
#include "clang/StaticAnalyzer/Core/Checker.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/Support/raw_ostream.h"

using namespace clang;
using namespace ento;

//===----------------------------------------------------------------------===//
// Generic type checking routines.
//===----------------------------------------------------------------------===//

static bool IsLLVMStringRef(QualType T) {
  const RecordType *RT = T->getAs<RecordType>();
  if (!RT)
    return false;

  return StringRef(QualType(RT, 0).getAsString()) ==
          "class StringRef";
}

/// Check whether the declaration is semantically inside the top-level
/// namespace named by ns.
static bool InNamespace(const Decl *D, StringRef NS) {
  const NamespaceDecl *ND = dyn_cast<NamespaceDecl>(D->getDeclContext());
  if (!ND)
    return false;
  const IdentifierInfo *II = ND->getIdentifier();
  if (!II || !II->getName().equals(NS))
    return false;
  return isa<TranslationUnitDecl>(ND->getDeclContext());
}

static bool IsStdString(QualType T) {
  if (const ElaboratedType *QT = T->getAs<ElaboratedType>())
    T = QT->getNamedType();

  const TypedefType *TT = T->getAs<TypedefType>();
  if (!TT)
    return false;

  const TypedefNameDecl *TD = TT->getDecl();

  if (!InNamespace(TD, "std"))
    return false;

  return TD->getName() == "string";
}

static bool IsClangType(const RecordDecl *RD) {
  return RD->getName() == "Type" && InNamespace(RD, "clang");
}

static bool IsClangDecl(const RecordDecl *RD) {
  return RD->getName() == "Decl" && InNamespace(RD, "clang");
}

static bool IsClangStmt(const RecordDecl *RD) {
  return RD->getName() == "Stmt" && InNamespace(RD, "clang");
}

static bool IsClangAttr(const RecordDecl *RD) {
  return RD->getName() == "Attr" && InNamespace(RD, "clang");
}

static bool IsStdVector(QualType T) {
  const TemplateSpecializationType *TS = T->getAs<TemplateSpecializationType>();
  if (!TS)
    return false;

  TemplateName TM = TS->getTemplateName();
  TemplateDecl *TD = TM.getAsTemplateDecl();

  if (!TD || !InNamespace(TD, "std"))
    return false;

  return TD->getName() == "vector";
}

static bool IsSmallVector(QualType T) {
  const TemplateSpecializationType *TS = T->getAs<TemplateSpecializationType>();
  if (!TS)
    return false;

  TemplateName TM = TS->getTemplateName();
  TemplateDecl *TD = TM.getAsTemplateDecl();

  if (!TD || !InNamespace(TD, "llvm"))
    return false;

  return TD->getName() == "SmallVector";
}

//===----------------------------------------------------------------------===//
// CHECK: a StringRef should not be bound to a temporary std::string whose
// lifetime is shorter than the StringRef's.
//===----------------------------------------------------------------------===//

namespace {
class StringRefCheckerVisitor : public StmtVisitor<StringRefCheckerVisitor> {
  BugReporter &BR;
  const Decl *DeclWithIssue;
public:
  StringRefCheckerVisitor(const Decl *declWithIssue, BugReporter &br)
    : BR(br), DeclWithIssue(declWithIssue) {}
  void VisitChildren(Stmt *S) {
    for (Stmt::child_iterator I = S->child_begin(), E = S->child_end() ;
      I != E; ++I)
      if (Stmt *child = *I)
        Visit(child);
  }
  void VisitStmt(Stmt *S) { VisitChildren(S); }
  void VisitDeclStmt(DeclStmt *DS);
private:
  void VisitVarDecl(VarDecl *VD);
};
} // end anonymous namespace

static void CheckStringRefAssignedTemporary(const Decl *D, BugReporter &BR) {
  StringRefCheckerVisitor walker(D, BR);
  walker.Visit(D->getBody());
}

void StringRefCheckerVisitor::VisitDeclStmt(DeclStmt *S) {
  VisitChildren(S);

  for (DeclStmt::decl_iterator I = S->decl_begin(), E = S->decl_end();I!=E; ++I)
    if (VarDecl *VD = dyn_cast<VarDecl>(*I))
      VisitVarDecl(VD);
}

void StringRefCheckerVisitor::VisitVarDecl(VarDecl *VD) {
  Expr *Init = VD->getInit();
  if (!Init)
    return;

  // Pattern match for:
  // StringRef x = call() (where call returns std::string)
  if (!IsLLVMStringRef(VD->getType()))
    return;
  ExprWithCleanups *Ex1 = dyn_cast<ExprWithCleanups>(Init);
  if (!Ex1)
    return;
  CXXConstructExpr *Ex2 = dyn_cast<CXXConstructExpr>(Ex1->getSubExpr());
  if (!Ex2 || Ex2->getNumArgs() != 1)
    return;
  ImplicitCastExpr *Ex3 = dyn_cast<ImplicitCastExpr>(Ex2->getArg(0));
  if (!Ex3)
    return;
  CXXConstructExpr *Ex4 = dyn_cast<CXXConstructExpr>(Ex3->getSubExpr());
  if (!Ex4 || Ex4->getNumArgs() != 1)
    return;
  ImplicitCastExpr *Ex5 = dyn_cast<ImplicitCastExpr>(Ex4->getArg(0));
  if (!Ex5)
    return;
  CXXBindTemporaryExpr *Ex6 = dyn_cast<CXXBindTemporaryExpr>(Ex5->getSubExpr());
  if (!Ex6 || !IsStdString(Ex6->getType()))
    return;

  // Okay, badness!  Report an error.
  const char *desc = "StringRef should not be bound to temporary "
                     "std::string that it outlives";
  PathDiagnosticLocation VDLoc =
    PathDiagnosticLocation::createBegin(VD, BR.getSourceManager());
  BR.EmitBasicReport(DeclWithIssue, desc, "LLVM Conventions", desc,
                     VDLoc, Init->getSourceRange());
}

//===----------------------------------------------------------------------===//
// CHECK: Clang AST nodes should not have fields that can allocate
//   memory.
//===----------------------------------------------------------------------===//

static bool AllocatesMemory(QualType T) {
  return IsStdVector(T) || IsStdString(T) || IsSmallVector(T);
}

// This type checking could be sped up via dynamic programming.
static bool IsPartOfAST(const CXXRecordDecl *R) {
  if (IsClangStmt(R) || IsClangType(R) || IsClangDecl(R) || IsClangAttr(R))
    return true;

  for (CXXRecordDecl::base_class_const_iterator I = R->bases_begin(),
                                                E = R->bases_end(); I!=E; ++I) {
    CXXBaseSpecifier BS = *I;
    QualType T = BS.getType();
    if (const RecordType *baseT = T->getAs<RecordType>()) {
      CXXRecordDecl *baseD = cast<CXXRecordDecl>(baseT->getDecl());
      if (IsPartOfAST(baseD))
        return true;
    }
  }

  return false;
}

namespace {
class ASTFieldVisitor {
  SmallVector<FieldDecl*, 10> FieldChain;
  const CXXRecordDecl *Root;
  BugReporter &BR;
public:
  ASTFieldVisitor(const CXXRecordDecl *root, BugReporter &br)
    : Root(root), BR(br) {}

  void Visit(FieldDecl *D);
  void ReportError(QualType T);
};
} // end anonymous namespace

static void CheckASTMemory(const CXXRecordDecl *R, BugReporter &BR) {
  if (!IsPartOfAST(R))
    return;

  for (RecordDecl::field_iterator I = R->field_begin(), E = R->field_end();
       I != E; ++I) {
    ASTFieldVisitor walker(R, BR);
    walker.Visit(*I);
  }
}

void ASTFieldVisitor::Visit(FieldDecl *D) {
  FieldChain.push_back(D);

  QualType T = D->getType();

  if (AllocatesMemory(T))
    ReportError(T);

  if (const RecordType *RT = T->getAs<RecordType>()) {
    const RecordDecl *RD = RT->getDecl()->getDefinition();
    for (RecordDecl::field_iterator I = RD->field_begin(), E = RD->field_end();
         I != E; ++I)
      Visit(*I);
  }

  FieldChain.pop_back();
}

void ASTFieldVisitor::ReportError(QualType T) {
  SmallString<1024> buf;
  llvm::raw_svector_ostream os(buf);

  os << "AST class '" << Root->getName() << "' has a field '"
     << FieldChain.front()->getName() << "' that allocates heap memory";
  if (FieldChain.size() > 1) {
    os << " via the following chain: ";
    bool isFirst = true;
    for (SmallVectorImpl<FieldDecl*>::iterator I=FieldChain.begin(),
         E=FieldChain.end(); I!=E; ++I) {
      if (!isFirst)
        os << '.';
      else
        isFirst = false;
      os << (*I)->getName();
    }
  }
  os << " (type " << FieldChain.back()->getType().getAsString() << ")";
  os.flush();

  // Note that this will fire for every translation unit that uses this
  // class.  This is suboptimal, but at least scan-build will merge
  // duplicate HTML reports.  In the future we need a unified way of merging
  // duplicate reports across translation units.  For C++ classes we cannot
  // just report warnings when we see an out-of-line method definition for a
  // class, as that heuristic doesn't always work (the complete definition of
  // the class may be in the header file, for example).
  PathDiagnosticLocation L = PathDiagnosticLocation::createBegin(
                               FieldChain.front(), BR.getSourceManager());
  BR.EmitBasicReport(Root, "AST node allocates heap memory", "LLVM Conventions",
                     os.str(), L);
}

//===----------------------------------------------------------------------===//
// LLVMConventionsChecker
//===----------------------------------------------------------------------===//

namespace {
class LLVMConventionsChecker : public Checker<
                                                check::ASTDecl<CXXRecordDecl>,
                                                check::ASTCodeBody > {
public:
  void checkASTDecl(const CXXRecordDecl *R, AnalysisManager& mgr,
                    BugReporter &BR) const {
    if (R->isCompleteDefinition())
      CheckASTMemory(R, BR);
  }

  void checkASTCodeBody(const Decl *D, AnalysisManager& mgr,
                        BugReporter &BR) const {
    CheckStringRefAssignedTemporary(D, BR);
  }
};
}

void ento::registerLLVMConventionsChecker(CheckerManager &mgr) {
  mgr.registerChecker<LLVMConventionsChecker>();
}
@


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


1.1.1.2
log
@Import Clang 3.5svn r202566.
@
text
@d118 1
a119 3
  BugReporter &BR;
  const CheckerBase *Checker;

d121 2
a122 3
  StringRefCheckerVisitor(const Decl *declWithIssue, BugReporter &br,
                          const CheckerBase *checker)
      : DeclWithIssue(declWithIssue), BR(br), Checker(checker) {}
d136 2
a137 3
static void CheckStringRefAssignedTemporary(const Decl *D, BugReporter &BR,
                                            const CheckerBase *Checker) {
  StringRefCheckerVisitor walker(D, BR, Checker);
d182 1
a182 1
  BR.EmitBasicReport(DeclWithIssue, Checker, desc, "LLVM Conventions", desc,
a218 2
  const CheckerBase *Checker;

d220 2
a221 3
  ASTFieldVisitor(const CXXRecordDecl *root, BugReporter &br,
                  const CheckerBase *checker)
      : Root(root), BR(br), Checker(checker) {}
d228 1
a228 2
static void CheckASTMemory(const CXXRecordDecl *R, BugReporter &BR,
                           const CheckerBase *Checker) {
d234 1
a234 1
    ASTFieldVisitor walker(R, BR, Checker);
d287 2
a288 2
  BR.EmitBasicReport(Root, Checker, "AST node allocates heap memory",
                     "LLVM Conventions", os.str(), L);
d303 1
a303 1
      CheckASTMemory(R, BR, this);
d308 1
a308 1
    CheckStringRefAssignedTemporary(D, BR, this);
@


1.1.1.2.2.1
log
@Rebase.
@
text
@d61 1
a61 1
  if (!TD->isInStdNamespace())
d148 2
a149 2
  for (auto *I : S->decls())
    if (VarDecl *VD = dyn_cast<VarDecl>(I))
d204 3
a206 1
  for (const auto &BS : R->bases()) {
d240 2
a241 1
  for (auto *I : R->fields()) {
d243 1
a243 1
    walker.Visit(I);
d257 3
a259 2
    for (auto *I : RD->fields())
      Visit(I);
@


1.1.1.3
log
@Import Clang 3.5svn r209886.
@
text
@d61 1
a61 1
  if (!TD->isInStdNamespace())
d148 2
a149 2
  for (auto *I : S->decls())
    if (VarDecl *VD = dyn_cast<VarDecl>(I))
d204 3
a206 1
  for (const auto &BS : R->bases()) {
d240 2
a241 1
  for (auto *I : R->fields()) {
d243 1
a243 1
    walker.Visit(I);
d257 3
a259 2
    for (auto *I : RD->fields())
      Visit(I);
@


1.1.1.4
log
@Import Clang 3.8.0rc3 r261930.
@
text
@d127 4
a130 3
    for (Stmt *Child : S->children())
      if (Child)
        Visit(Child);
d280 1
@


1.1.1.4.16.1
log
@Mostly merge changes from HEAD upto 20200411
@
text
@@


1.1.1.5
log
@Mark old LLVM instance as dead.
@
text
@@


1.1.1.3.4.1
log
@file LLVMConventionsChecker.cpp was added on branch tls-maxphys on 2014-08-19 23:47:31 +0000
@
text
@d1 319
@


1.1.1.3.4.2
log
@Rebase to HEAD as of a few days ago.
@
text
@a0 319
//=== LLVMConventionsChecker.cpp - Check LLVM codebase conventions ---*- C++ -*-
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This defines LLVMConventionsChecker, a bunch of small little checks
// for checking specific coding conventions in the LLVM/Clang codebase.
//
//===----------------------------------------------------------------------===//

#include "ClangSACheckers.h"
#include "clang/AST/DeclTemplate.h"
#include "clang/AST/StmtVisitor.h"
#include "clang/StaticAnalyzer/Core/BugReporter/BugReporter.h"
#include "clang/StaticAnalyzer/Core/Checker.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/Support/raw_ostream.h"

using namespace clang;
using namespace ento;

//===----------------------------------------------------------------------===//
// Generic type checking routines.
//===----------------------------------------------------------------------===//

static bool IsLLVMStringRef(QualType T) {
  const RecordType *RT = T->getAs<RecordType>();
  if (!RT)
    return false;

  return StringRef(QualType(RT, 0).getAsString()) ==
          "class StringRef";
}

/// Check whether the declaration is semantically inside the top-level
/// namespace named by ns.
static bool InNamespace(const Decl *D, StringRef NS) {
  const NamespaceDecl *ND = dyn_cast<NamespaceDecl>(D->getDeclContext());
  if (!ND)
    return false;
  const IdentifierInfo *II = ND->getIdentifier();
  if (!II || !II->getName().equals(NS))
    return false;
  return isa<TranslationUnitDecl>(ND->getDeclContext());
}

static bool IsStdString(QualType T) {
  if (const ElaboratedType *QT = T->getAs<ElaboratedType>())
    T = QT->getNamedType();

  const TypedefType *TT = T->getAs<TypedefType>();
  if (!TT)
    return false;

  const TypedefNameDecl *TD = TT->getDecl();

  if (!TD->isInStdNamespace())
    return false;

  return TD->getName() == "string";
}

static bool IsClangType(const RecordDecl *RD) {
  return RD->getName() == "Type" && InNamespace(RD, "clang");
}

static bool IsClangDecl(const RecordDecl *RD) {
  return RD->getName() == "Decl" && InNamespace(RD, "clang");
}

static bool IsClangStmt(const RecordDecl *RD) {
  return RD->getName() == "Stmt" && InNamespace(RD, "clang");
}

static bool IsClangAttr(const RecordDecl *RD) {
  return RD->getName() == "Attr" && InNamespace(RD, "clang");
}

static bool IsStdVector(QualType T) {
  const TemplateSpecializationType *TS = T->getAs<TemplateSpecializationType>();
  if (!TS)
    return false;

  TemplateName TM = TS->getTemplateName();
  TemplateDecl *TD = TM.getAsTemplateDecl();

  if (!TD || !InNamespace(TD, "std"))
    return false;

  return TD->getName() == "vector";
}

static bool IsSmallVector(QualType T) {
  const TemplateSpecializationType *TS = T->getAs<TemplateSpecializationType>();
  if (!TS)
    return false;

  TemplateName TM = TS->getTemplateName();
  TemplateDecl *TD = TM.getAsTemplateDecl();

  if (!TD || !InNamespace(TD, "llvm"))
    return false;

  return TD->getName() == "SmallVector";
}

//===----------------------------------------------------------------------===//
// CHECK: a StringRef should not be bound to a temporary std::string whose
// lifetime is shorter than the StringRef's.
//===----------------------------------------------------------------------===//

namespace {
class StringRefCheckerVisitor : public StmtVisitor<StringRefCheckerVisitor> {
  const Decl *DeclWithIssue;
  BugReporter &BR;
  const CheckerBase *Checker;

public:
  StringRefCheckerVisitor(const Decl *declWithIssue, BugReporter &br,
                          const CheckerBase *checker)
      : DeclWithIssue(declWithIssue), BR(br), Checker(checker) {}
  void VisitChildren(Stmt *S) {
    for (Stmt::child_iterator I = S->child_begin(), E = S->child_end() ;
      I != E; ++I)
      if (Stmt *child = *I)
        Visit(child);
  }
  void VisitStmt(Stmt *S) { VisitChildren(S); }
  void VisitDeclStmt(DeclStmt *DS);
private:
  void VisitVarDecl(VarDecl *VD);
};
} // end anonymous namespace

static void CheckStringRefAssignedTemporary(const Decl *D, BugReporter &BR,
                                            const CheckerBase *Checker) {
  StringRefCheckerVisitor walker(D, BR, Checker);
  walker.Visit(D->getBody());
}

void StringRefCheckerVisitor::VisitDeclStmt(DeclStmt *S) {
  VisitChildren(S);

  for (auto *I : S->decls())
    if (VarDecl *VD = dyn_cast<VarDecl>(I))
      VisitVarDecl(VD);
}

void StringRefCheckerVisitor::VisitVarDecl(VarDecl *VD) {
  Expr *Init = VD->getInit();
  if (!Init)
    return;

  // Pattern match for:
  // StringRef x = call() (where call returns std::string)
  if (!IsLLVMStringRef(VD->getType()))
    return;
  ExprWithCleanups *Ex1 = dyn_cast<ExprWithCleanups>(Init);
  if (!Ex1)
    return;
  CXXConstructExpr *Ex2 = dyn_cast<CXXConstructExpr>(Ex1->getSubExpr());
  if (!Ex2 || Ex2->getNumArgs() != 1)
    return;
  ImplicitCastExpr *Ex3 = dyn_cast<ImplicitCastExpr>(Ex2->getArg(0));
  if (!Ex3)
    return;
  CXXConstructExpr *Ex4 = dyn_cast<CXXConstructExpr>(Ex3->getSubExpr());
  if (!Ex4 || Ex4->getNumArgs() != 1)
    return;
  ImplicitCastExpr *Ex5 = dyn_cast<ImplicitCastExpr>(Ex4->getArg(0));
  if (!Ex5)
    return;
  CXXBindTemporaryExpr *Ex6 = dyn_cast<CXXBindTemporaryExpr>(Ex5->getSubExpr());
  if (!Ex6 || !IsStdString(Ex6->getType()))
    return;

  // Okay, badness!  Report an error.
  const char *desc = "StringRef should not be bound to temporary "
                     "std::string that it outlives";
  PathDiagnosticLocation VDLoc =
    PathDiagnosticLocation::createBegin(VD, BR.getSourceManager());
  BR.EmitBasicReport(DeclWithIssue, Checker, desc, "LLVM Conventions", desc,
                     VDLoc, Init->getSourceRange());
}

//===----------------------------------------------------------------------===//
// CHECK: Clang AST nodes should not have fields that can allocate
//   memory.
//===----------------------------------------------------------------------===//

static bool AllocatesMemory(QualType T) {
  return IsStdVector(T) || IsStdString(T) || IsSmallVector(T);
}

// This type checking could be sped up via dynamic programming.
static bool IsPartOfAST(const CXXRecordDecl *R) {
  if (IsClangStmt(R) || IsClangType(R) || IsClangDecl(R) || IsClangAttr(R))
    return true;

  for (const auto &BS : R->bases()) {
    QualType T = BS.getType();
    if (const RecordType *baseT = T->getAs<RecordType>()) {
      CXXRecordDecl *baseD = cast<CXXRecordDecl>(baseT->getDecl());
      if (IsPartOfAST(baseD))
        return true;
    }
  }

  return false;
}

namespace {
class ASTFieldVisitor {
  SmallVector<FieldDecl*, 10> FieldChain;
  const CXXRecordDecl *Root;
  BugReporter &BR;
  const CheckerBase *Checker;

public:
  ASTFieldVisitor(const CXXRecordDecl *root, BugReporter &br,
                  const CheckerBase *checker)
      : Root(root), BR(br), Checker(checker) {}

  void Visit(FieldDecl *D);
  void ReportError(QualType T);
};
} // end anonymous namespace

static void CheckASTMemory(const CXXRecordDecl *R, BugReporter &BR,
                           const CheckerBase *Checker) {
  if (!IsPartOfAST(R))
    return;

  for (auto *I : R->fields()) {
    ASTFieldVisitor walker(R, BR, Checker);
    walker.Visit(I);
  }
}

void ASTFieldVisitor::Visit(FieldDecl *D) {
  FieldChain.push_back(D);

  QualType T = D->getType();

  if (AllocatesMemory(T))
    ReportError(T);

  if (const RecordType *RT = T->getAs<RecordType>()) {
    const RecordDecl *RD = RT->getDecl()->getDefinition();
    for (auto *I : RD->fields())
      Visit(I);
  }

  FieldChain.pop_back();
}

void ASTFieldVisitor::ReportError(QualType T) {
  SmallString<1024> buf;
  llvm::raw_svector_ostream os(buf);

  os << "AST class '" << Root->getName() << "' has a field '"
     << FieldChain.front()->getName() << "' that allocates heap memory";
  if (FieldChain.size() > 1) {
    os << " via the following chain: ";
    bool isFirst = true;
    for (SmallVectorImpl<FieldDecl*>::iterator I=FieldChain.begin(),
         E=FieldChain.end(); I!=E; ++I) {
      if (!isFirst)
        os << '.';
      else
        isFirst = false;
      os << (*I)->getName();
    }
  }
  os << " (type " << FieldChain.back()->getType().getAsString() << ")";
  os.flush();

  // Note that this will fire for every translation unit that uses this
  // class.  This is suboptimal, but at least scan-build will merge
  // duplicate HTML reports.  In the future we need a unified way of merging
  // duplicate reports across translation units.  For C++ classes we cannot
  // just report warnings when we see an out-of-line method definition for a
  // class, as that heuristic doesn't always work (the complete definition of
  // the class may be in the header file, for example).
  PathDiagnosticLocation L = PathDiagnosticLocation::createBegin(
                               FieldChain.front(), BR.getSourceManager());
  BR.EmitBasicReport(Root, Checker, "AST node allocates heap memory",
                     "LLVM Conventions", os.str(), L);
}

//===----------------------------------------------------------------------===//
// LLVMConventionsChecker
//===----------------------------------------------------------------------===//

namespace {
class LLVMConventionsChecker : public Checker<
                                                check::ASTDecl<CXXRecordDecl>,
                                                check::ASTCodeBody > {
public:
  void checkASTDecl(const CXXRecordDecl *R, AnalysisManager& mgr,
                    BugReporter &BR) const {
    if (R->isCompleteDefinition())
      CheckASTMemory(R, BR, this);
  }

  void checkASTCodeBody(const Decl *D, AnalysisManager& mgr,
                        BugReporter &BR) const {
    CheckStringRefAssignedTemporary(D, BR, this);
  }
};
}

void ento::registerLLVMConventionsChecker(CheckerManager &mgr) {
  mgr.registerChecker<LLVMConventionsChecker>();
}
@


1.1.1.2.4.1
log
@file LLVMConventionsChecker.cpp was added on branch yamt-pagecache on 2014-05-22 16:18:31 +0000
@
text
@d1 323
@


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 323
//=== LLVMConventionsChecker.cpp - Check LLVM codebase conventions ---*- C++ -*-
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This defines LLVMConventionsChecker, a bunch of small little checks
// for checking specific coding conventions in the LLVM/Clang codebase.
//
//===----------------------------------------------------------------------===//

#include "ClangSACheckers.h"
#include "clang/AST/DeclTemplate.h"
#include "clang/AST/StmtVisitor.h"
#include "clang/StaticAnalyzer/Core/BugReporter/BugReporter.h"
#include "clang/StaticAnalyzer/Core/Checker.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/Support/raw_ostream.h"

using namespace clang;
using namespace ento;

//===----------------------------------------------------------------------===//
// Generic type checking routines.
//===----------------------------------------------------------------------===//

static bool IsLLVMStringRef(QualType T) {
  const RecordType *RT = T->getAs<RecordType>();
  if (!RT)
    return false;

  return StringRef(QualType(RT, 0).getAsString()) ==
          "class StringRef";
}

/// Check whether the declaration is semantically inside the top-level
/// namespace named by ns.
static bool InNamespace(const Decl *D, StringRef NS) {
  const NamespaceDecl *ND = dyn_cast<NamespaceDecl>(D->getDeclContext());
  if (!ND)
    return false;
  const IdentifierInfo *II = ND->getIdentifier();
  if (!II || !II->getName().equals(NS))
    return false;
  return isa<TranslationUnitDecl>(ND->getDeclContext());
}

static bool IsStdString(QualType T) {
  if (const ElaboratedType *QT = T->getAs<ElaboratedType>())
    T = QT->getNamedType();

  const TypedefType *TT = T->getAs<TypedefType>();
  if (!TT)
    return false;

  const TypedefNameDecl *TD = TT->getDecl();

  if (!InNamespace(TD, "std"))
    return false;

  return TD->getName() == "string";
}

static bool IsClangType(const RecordDecl *RD) {
  return RD->getName() == "Type" && InNamespace(RD, "clang");
}

static bool IsClangDecl(const RecordDecl *RD) {
  return RD->getName() == "Decl" && InNamespace(RD, "clang");
}

static bool IsClangStmt(const RecordDecl *RD) {
  return RD->getName() == "Stmt" && InNamespace(RD, "clang");
}

static bool IsClangAttr(const RecordDecl *RD) {
  return RD->getName() == "Attr" && InNamespace(RD, "clang");
}

static bool IsStdVector(QualType T) {
  const TemplateSpecializationType *TS = T->getAs<TemplateSpecializationType>();
  if (!TS)
    return false;

  TemplateName TM = TS->getTemplateName();
  TemplateDecl *TD = TM.getAsTemplateDecl();

  if (!TD || !InNamespace(TD, "std"))
    return false;

  return TD->getName() == "vector";
}

static bool IsSmallVector(QualType T) {
  const TemplateSpecializationType *TS = T->getAs<TemplateSpecializationType>();
  if (!TS)
    return false;

  TemplateName TM = TS->getTemplateName();
  TemplateDecl *TD = TM.getAsTemplateDecl();

  if (!TD || !InNamespace(TD, "llvm"))
    return false;

  return TD->getName() == "SmallVector";
}

//===----------------------------------------------------------------------===//
// CHECK: a StringRef should not be bound to a temporary std::string whose
// lifetime is shorter than the StringRef's.
//===----------------------------------------------------------------------===//

namespace {
class StringRefCheckerVisitor : public StmtVisitor<StringRefCheckerVisitor> {
  const Decl *DeclWithIssue;
  BugReporter &BR;
  const CheckerBase *Checker;

public:
  StringRefCheckerVisitor(const Decl *declWithIssue, BugReporter &br,
                          const CheckerBase *checker)
      : DeclWithIssue(declWithIssue), BR(br), Checker(checker) {}
  void VisitChildren(Stmt *S) {
    for (Stmt::child_iterator I = S->child_begin(), E = S->child_end() ;
      I != E; ++I)
      if (Stmt *child = *I)
        Visit(child);
  }
  void VisitStmt(Stmt *S) { VisitChildren(S); }
  void VisitDeclStmt(DeclStmt *DS);
private:
  void VisitVarDecl(VarDecl *VD);
};
} // end anonymous namespace

static void CheckStringRefAssignedTemporary(const Decl *D, BugReporter &BR,
                                            const CheckerBase *Checker) {
  StringRefCheckerVisitor walker(D, BR, Checker);
  walker.Visit(D->getBody());
}

void StringRefCheckerVisitor::VisitDeclStmt(DeclStmt *S) {
  VisitChildren(S);

  for (DeclStmt::decl_iterator I = S->decl_begin(), E = S->decl_end();I!=E; ++I)
    if (VarDecl *VD = dyn_cast<VarDecl>(*I))
      VisitVarDecl(VD);
}

void StringRefCheckerVisitor::VisitVarDecl(VarDecl *VD) {
  Expr *Init = VD->getInit();
  if (!Init)
    return;

  // Pattern match for:
  // StringRef x = call() (where call returns std::string)
  if (!IsLLVMStringRef(VD->getType()))
    return;
  ExprWithCleanups *Ex1 = dyn_cast<ExprWithCleanups>(Init);
  if (!Ex1)
    return;
  CXXConstructExpr *Ex2 = dyn_cast<CXXConstructExpr>(Ex1->getSubExpr());
  if (!Ex2 || Ex2->getNumArgs() != 1)
    return;
  ImplicitCastExpr *Ex3 = dyn_cast<ImplicitCastExpr>(Ex2->getArg(0));
  if (!Ex3)
    return;
  CXXConstructExpr *Ex4 = dyn_cast<CXXConstructExpr>(Ex3->getSubExpr());
  if (!Ex4 || Ex4->getNumArgs() != 1)
    return;
  ImplicitCastExpr *Ex5 = dyn_cast<ImplicitCastExpr>(Ex4->getArg(0));
  if (!Ex5)
    return;
  CXXBindTemporaryExpr *Ex6 = dyn_cast<CXXBindTemporaryExpr>(Ex5->getSubExpr());
  if (!Ex6 || !IsStdString(Ex6->getType()))
    return;

  // Okay, badness!  Report an error.
  const char *desc = "StringRef should not be bound to temporary "
                     "std::string that it outlives";
  PathDiagnosticLocation VDLoc =
    PathDiagnosticLocation::createBegin(VD, BR.getSourceManager());
  BR.EmitBasicReport(DeclWithIssue, Checker, desc, "LLVM Conventions", desc,
                     VDLoc, Init->getSourceRange());
}

//===----------------------------------------------------------------------===//
// CHECK: Clang AST nodes should not have fields that can allocate
//   memory.
//===----------------------------------------------------------------------===//

static bool AllocatesMemory(QualType T) {
  return IsStdVector(T) || IsStdString(T) || IsSmallVector(T);
}

// This type checking could be sped up via dynamic programming.
static bool IsPartOfAST(const CXXRecordDecl *R) {
  if (IsClangStmt(R) || IsClangType(R) || IsClangDecl(R) || IsClangAttr(R))
    return true;

  for (CXXRecordDecl::base_class_const_iterator I = R->bases_begin(),
                                                E = R->bases_end(); I!=E; ++I) {
    CXXBaseSpecifier BS = *I;
    QualType T = BS.getType();
    if (const RecordType *baseT = T->getAs<RecordType>()) {
      CXXRecordDecl *baseD = cast<CXXRecordDecl>(baseT->getDecl());
      if (IsPartOfAST(baseD))
        return true;
    }
  }

  return false;
}

namespace {
class ASTFieldVisitor {
  SmallVector<FieldDecl*, 10> FieldChain;
  const CXXRecordDecl *Root;
  BugReporter &BR;
  const CheckerBase *Checker;

public:
  ASTFieldVisitor(const CXXRecordDecl *root, BugReporter &br,
                  const CheckerBase *checker)
      : Root(root), BR(br), Checker(checker) {}

  void Visit(FieldDecl *D);
  void ReportError(QualType T);
};
} // end anonymous namespace

static void CheckASTMemory(const CXXRecordDecl *R, BugReporter &BR,
                           const CheckerBase *Checker) {
  if (!IsPartOfAST(R))
    return;

  for (RecordDecl::field_iterator I = R->field_begin(), E = R->field_end();
       I != E; ++I) {
    ASTFieldVisitor walker(R, BR, Checker);
    walker.Visit(*I);
  }
}

void ASTFieldVisitor::Visit(FieldDecl *D) {
  FieldChain.push_back(D);

  QualType T = D->getType();

  if (AllocatesMemory(T))
    ReportError(T);

  if (const RecordType *RT = T->getAs<RecordType>()) {
    const RecordDecl *RD = RT->getDecl()->getDefinition();
    for (RecordDecl::field_iterator I = RD->field_begin(), E = RD->field_end();
         I != E; ++I)
      Visit(*I);
  }

  FieldChain.pop_back();
}

void ASTFieldVisitor::ReportError(QualType T) {
  SmallString<1024> buf;
  llvm::raw_svector_ostream os(buf);

  os << "AST class '" << Root->getName() << "' has a field '"
     << FieldChain.front()->getName() << "' that allocates heap memory";
  if (FieldChain.size() > 1) {
    os << " via the following chain: ";
    bool isFirst = true;
    for (SmallVectorImpl<FieldDecl*>::iterator I=FieldChain.begin(),
         E=FieldChain.end(); I!=E; ++I) {
      if (!isFirst)
        os << '.';
      else
        isFirst = false;
      os << (*I)->getName();
    }
  }
  os << " (type " << FieldChain.back()->getType().getAsString() << ")";
  os.flush();

  // Note that this will fire for every translation unit that uses this
  // class.  This is suboptimal, but at least scan-build will merge
  // duplicate HTML reports.  In the future we need a unified way of merging
  // duplicate reports across translation units.  For C++ classes we cannot
  // just report warnings when we see an out-of-line method definition for a
  // class, as that heuristic doesn't always work (the complete definition of
  // the class may be in the header file, for example).
  PathDiagnosticLocation L = PathDiagnosticLocation::createBegin(
                               FieldChain.front(), BR.getSourceManager());
  BR.EmitBasicReport(Root, Checker, "AST node allocates heap memory",
                     "LLVM Conventions", os.str(), L);
}

//===----------------------------------------------------------------------===//
// LLVMConventionsChecker
//===----------------------------------------------------------------------===//

namespace {
class LLVMConventionsChecker : public Checker<
                                                check::ASTDecl<CXXRecordDecl>,
                                                check::ASTCodeBody > {
public:
  void checkASTDecl(const CXXRecordDecl *R, AnalysisManager& mgr,
                    BugReporter &BR) const {
    if (R->isCompleteDefinition())
      CheckASTMemory(R, BR, this);
  }

  void checkASTCodeBody(const Decl *D, AnalysisManager& mgr,
                        BugReporter &BR) const {
    CheckStringRefAssignedTemporary(D, BR, this);
  }
};
}

void ento::registerLLVMConventionsChecker(CheckerManager &mgr) {
  mgr.registerChecker<LLVMConventionsChecker>();
}
@


