[Preprocessor]Correct Macro-Arg allocation of StringifiedArguments,

correct getNumArguments

StringifiedArguments is allocated (resized) based on the size the
getNumArguments function. However, this function ACTUALLY currently
returns the amount of total UnexpArgTokens which is minimum the same as
the new implementation of getNumMacroArguments, since empty/omitted arguments
result in 1 UnexpArgToken, and included ones at minimum include 2
(1 for the arg itself, 1 for eof).

This patch renames the otherwise unused getNumArguments to be more clear
that it is the number of arguments that the Macro expects, and thus the maximum
number that can be stringified. This patch also replaces the explicit memset
(which results in value instantiation of the new tokens, PLUS clearing the
memory) with brace initialization.

Differential Revision: https://reviews.llvm.org/D32046

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@305425 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/clang/Lex/MacroArgs.h b/include/clang/Lex/MacroArgs.h
index 7b2a48561ff63a37e7f36fc09af908048b1a6394..cfe46ceb0979768f3a364b1fffc1915cd1baee65 100644 (file)
--- a/include/clang/Lex/MacroArgs.h
+++ b/include/clang/Lex/MacroArgs.h
@@ -53,9 +53,12 @@ class MacroArgs {
   /// Preprocessor owns which we use to avoid thrashing malloc/free.
   MacroArgs *ArgCache;
 
-  MacroArgs(unsigned NumToks, bool varargsElided)
-    : NumUnexpArgTokens(NumToks), VarargsElided(varargsElided),
-      ArgCache(nullptr) {}
+  /// MacroArgs - The number of arguments the invoked macro expects.
+  unsigned NumMacroArgs;
+
+  MacroArgs(unsigned NumToks, bool varargsElided, unsigned MacroArgs)
+      : NumUnexpArgTokens(NumToks), VarargsElided(varargsElided),
+        ArgCache(nullptr), NumMacroArgs(MacroArgs) {}
   ~MacroArgs() = default;
 
 public:
@@ -94,10 +97,9 @@ public:
                                       SourceLocation ExpansionLocStart,
                                       SourceLocation ExpansionLocEnd);
 
-  /// getNumArguments - Return the number of arguments passed into this macro
-  /// invocation.
-  unsigned getNumArguments() const { return NumUnexpArgTokens; }
-
+  /// getNumMacroArguments - Return the number of arguments the invoked macro
+  /// expects.
+  unsigned getNumMacroArguments() const { return NumMacroArgs; }
 
   /// isVarargsElidedUse - Return true if this is a C99 style varargs macro
   /// invocation and there was no argument specified for the "..." argument.  If

diff --git a/lib/Lex/MacroArgs.cpp b/lib/Lex/MacroArgs.cpp
index 1c1979d8e83dfb23cc3698d6af4dc6ddf085fda5..a201d16590735f828ed8ef3959c4a6d3bddc8c33 100644 (file)
--- a/lib/Lex/MacroArgs.cpp
+++ b/lib/Lex/MacroArgs.cpp
@@ -44,20 +44,22 @@ MacroArgs *MacroArgs::create(const MacroInfo *MI,
       // Otherwise, use the best fit.
       ClosestMatch = (*Entry)->NumUnexpArgTokens;
     }
-  
+
   MacroArgs *Result;
   if (!ResultEnt) {
     // Allocate memory for a MacroArgs object with the lexer tokens at the end.
-    Result = (MacroArgs*)malloc(sizeof(MacroArgs) + 
-                                UnexpArgTokens.size() * sizeof(Token));
+    Result = (MacroArgs *)malloc(sizeof(MacroArgs) +
+                                 UnexpArgTokens.size() * sizeof(Token));
     // Construct the MacroArgs object.
-    new (Result) MacroArgs(UnexpArgTokens.size(), VarargsElided);
+    new (Result)
+        MacroArgs(UnexpArgTokens.size(), VarargsElided, MI->getNumArgs());
   } else {
     Result = *ResultEnt;
     // Unlink this node from the preprocessors singly linked list.
     *ResultEnt = Result->ArgCache;
     Result->NumUnexpArgTokens = UnexpArgTokens.size();
     Result->VarargsElided = VarargsElided;
+    Result->NumMacroArgs = MI->getNumArgs();
   }
 
   // Copy the actual unexpanded tokens to immediately after the result ptr.
@@ -298,12 +300,10 @@ const Token &MacroArgs::getStringifiedArgument(unsigned ArgNo,
                                                Preprocessor &PP,
                                                SourceLocation ExpansionLocStart,
                                                SourceLocation ExpansionLocEnd) {
-  assert(ArgNo < NumUnexpArgTokens && "Invalid argument number!");
-  if (StringifiedArgs.empty()) {
-    StringifiedArgs.resize(getNumArguments());
-    memset((void*)&StringifiedArgs[0], 0,
-           sizeof(StringifiedArgs[0])*getNumArguments());
-  }
+  assert(ArgNo < getNumMacroArguments() && "Invalid argument number!");
+  if (StringifiedArgs.empty())
+    StringifiedArgs.resize(getNumMacroArguments(), {});
+
   if (StringifiedArgs[ArgNo].isNot(tok::string_literal))
     StringifiedArgs[ArgNo] = StringifyArgument(getUnexpArgument(ArgNo), PP,
                                                /*Charify=*/false,

diff --git a/unittests/Lex/LexerTest.cpp b/unittests/Lex/LexerTest.cpp
index e2507d3580d37b07451e53a91bf06ded63c10dcf..a708de8a5a87899d4cd7605e4ed07e34f0175c5b 100644 (file)
--- a/unittests/Lex/LexerTest.cpp
+++ b/unittests/Lex/LexerTest.cpp
@@ -18,6 +18,8 @@
 #include "clang/Basic/TargetOptions.h"
 #include "clang/Lex/HeaderSearch.h"
 #include "clang/Lex/HeaderSearchOptions.h"
+#include "clang/Lex/MacroArgs.h"
+#include "clang/Lex/MacroInfo.h"
 #include "clang/Lex/ModuleLoader.h"
 #include "clang/Lex/Preprocessor.h"
 #include "clang/Lex/PreprocessorOptions.h"
@@ -41,26 +43,33 @@ protected:
     Target = TargetInfo::CreateTargetInfo(Diags, TargetOpts);
   }
 
-  std::vector<Token> Lex(StringRef Source) {
+  std::unique_ptr<Preprocessor> CreatePP(StringRef Source,
+                                         TrivialModuleLoader &ModLoader) {
     std::unique_ptr<llvm::MemoryBuffer> Buf =
         llvm::MemoryBuffer::getMemBuffer(Source);
     SourceMgr.setMainFileID(SourceMgr.createFileID(std::move(Buf)));
 
-    TrivialModuleLoader ModLoader;
     MemoryBufferCache PCMCache;
     HeaderSearch HeaderInfo(std::make_shared<HeaderSearchOptions>(), SourceMgr,
                             Diags, LangOpts, Target.get());
-    Preprocessor PP(std::make_shared<PreprocessorOptions>(), Diags, LangOpts,
-                    SourceMgr, PCMCache, HeaderInfo, ModLoader,
-                    /*IILookup =*/nullptr,
-                    /*OwnsHeaderSearch =*/false);
-    PP.Initialize(*Target);
-    PP.EnterMainSourceFile();
+    std::unique_ptr<Preprocessor> PP = llvm::make_unique<Preprocessor>(
+        std::make_shared<PreprocessorOptions>(), Diags, LangOpts, SourceMgr,
+        PCMCache, HeaderInfo, ModLoader,
+        /*IILookup =*/nullptr,
+        /*OwnsHeaderSearch =*/false);
+    PP->Initialize(*Target);
+    PP->EnterMainSourceFile();
+    return PP;
+  }
+
+  std::vector<Token> Lex(StringRef Source) {
+    TrivialModuleLoader ModLoader;
+    auto PP = CreatePP(Source, ModLoader);
 
     std::vector<Token> toks;
     while (1) {
       Token tok;
-      PP.Lex(tok);
+      PP->Lex(tok);
       if (tok.is(tok::eof))
         break;
       toks.push_back(tok);
@@ -365,4 +374,48 @@ TEST_F(LexerTest, DontMergeMacroArgsFromDifferentMacroFiles) {
   EXPECT_EQ(SourceMgr.getFileIDSize(SourceMgr.getFileID(helper1ArgLoc)), 8U);
 }
 
+TEST_F(LexerTest, DontOverallocateStringifyArgs) {
+  TrivialModuleLoader ModLoader;
+  auto PP = CreatePP("\"StrArg\", 5, 'C'", ModLoader);
+
+  llvm::BumpPtrAllocator Allocator;
+  std::array<IdentifierInfo *, 3> ArgList;
+  MacroInfo *MI = PP->AllocateMacroInfo({});
+  MI->setIsFunctionLike();
+  MI->setArgumentList(ArgList, Allocator);
+  EXPECT_EQ(3, MI->getNumArgs());
+  EXPECT_TRUE(MI->isFunctionLike());
+
+  Token Eof;
+  Eof.setKind(tok::eof);
+  std::vector<Token> ArgTokens;
+  while (1) {
+    Token tok;
+    PP->Lex(tok);
+    if (tok.is(tok::eof)) {
+      ArgTokens.push_back(Eof);
+      break;
+    }
+    if (tok.is(tok::comma))
+      ArgTokens.push_back(Eof);
+    else
+      ArgTokens.push_back(tok);
+  }
+
+  MacroArgs *MA = MacroArgs::create(MI, ArgTokens, false, *PP);
+  Token Result = MA->getStringifiedArgument(0, *PP, {}, {});
+  EXPECT_EQ(tok::string_literal, Result.getKind());
+  EXPECT_STREQ("\"\\\"StrArg\\\"\"", Result.getLiteralData());
+  Result = MA->getStringifiedArgument(1, *PP, {}, {});
+  EXPECT_EQ(tok::string_literal, Result.getKind());
+  EXPECT_STREQ("\"5\"", Result.getLiteralData());
+  Result = MA->getStringifiedArgument(2, *PP, {}, {});
+  EXPECT_EQ(tok::string_literal, Result.getKind());
+  EXPECT_STREQ("\"'C'\"", Result.getLiteralData());
+#if !defined(NDEBUG) && GTEST_HAS_DEATH_TEST
+  EXPECT_DEATH(MA->getStringifiedArgument(3, *PP, {}, {}),
+               "Invalid argument number!");
+#endif
+}
+
 } // anonymous namespace