PR25416: Improve performance of processing inline assembly consisting of many

implicitly-concatenated string literals. When looking for the start of a token
in the inline assembly, start from the end of the previous token, not the start
of the entire string.

Patch by Yunlian Jiang!

llvm-svn: 255198

clang/include/clang/AST/Expr.h

@@ -1631,13 +1631,15 @@ public:
   /// and can have escape sequences in them in addition to the usual trigraph
   /// and escaped newline business.  This routine handles this complexity.
   ///
-  SourceLocation getLocationOfByte(unsigned ByteNo, const SourceManager &SM,
-                                   const LangOptions &Features,
-                                   const TargetInfo &Target) const;
+  SourceLocation
+  getLocationOfByte(unsigned ByteNo, const SourceManager &SM,
+                    const LangOptions &Features, const TargetInfo &Target,
+                    unsigned *StartToken = nullptr,
+                    unsigned *StartTokenByteOffset = nullptr) const;
 
   typedef const SourceLocation *tokloc_iterator;
   tokloc_iterator tokloc_begin() const { return TokLocs; }
-  tokloc_iterator tokloc_end() const { return TokLocs+NumConcatenated; }
+  tokloc_iterator tokloc_end() const { return TokLocs + NumConcatenated; }
 
   SourceLocation getLocStart() const LLVM_READONLY { return TokLocs[0]; }
   SourceLocation getLocEnd() const LLVM_READONLY {

clang/lib/AST/Expr.cpp

@@ -1007,15 +1007,33 @@ void StringLiteral::setString(const ASTContext &C, StringRef Str,
 /// can have escape sequences in them in addition to the usual trigraph and
 /// escaped newline business.  This routine handles this complexity.
 ///
-SourceLocation StringLiteral::
-getLocationOfByte(unsigned ByteNo, const SourceManager &SM,
-                  const LangOptions &Features, const TargetInfo &Target) const {
+/// The *StartToken sets the first token to be searched in this function and
+/// the *StartTokenByteOffset is the byte offset of the first token. Before
+/// returning, it updates the *StartToken to the TokNo of the token being found
+/// and sets *StartTokenByteOffset to the byte offset of the token in the
+/// string.
+/// Using these two parameters can reduce the time complexity from O(n^2) to
+/// O(n) if one wants to get the location of byte for all the tokens in a
+/// string.
+///
+SourceLocation
+StringLiteral::getLocationOfByte(unsigned ByteNo, const SourceManager &SM,
+                                 const LangOptions &Features,
+                                 const TargetInfo &Target, unsigned *StartToken,
+                                 unsigned *StartTokenByteOffset) const {
   assert((Kind == StringLiteral::Ascii || Kind == StringLiteral::UTF8) &&
          "Only narrow string literals are currently supported");
 
   // Loop over all of the tokens in this string until we find the one that
   // contains the byte we're looking for.
   unsigned TokNo = 0;
+  unsigned StringOffset = 0;
+  if (StartToken)
+    TokNo = *StartToken;
+  if (StartTokenByteOffset) {
+    StringOffset = *StartTokenByteOffset;
+    ByteNo -= StringOffset;
+  }
   while (1) {
     assert(TokNo < getNumConcatenated() && "Invalid byte number!");
     SourceLocation StrTokLoc = getStrTokenLoc(TokNo);
@@ -1026,11 +1044,17 @@ getLocationOfByte(unsigned ByteNo, const SourceManager &SM,
     SourceLocation StrTokSpellingLoc = SM.getSpellingLoc(StrTokLoc);
 
     // Re-lex the token to get its length and original spelling.
-    std::pair<FileID, unsigned> LocInfo =SM.getDecomposedLoc(StrTokSpellingLoc);
+    std::pair<FileID, unsigned> LocInfo =
+        SM.getDecomposedLoc(StrTokSpellingLoc);
     bool Invalid = false;
     StringRef Buffer = SM.getBufferData(LocInfo.first, &Invalid);
-    if (Invalid)
+    if (Invalid) {
+      if (StartTokenByteOffset != nullptr)
+        *StartTokenByteOffset = StringOffset;
+      if (StartToken != nullptr)
+        *StartToken = TokNo;
       return StrTokSpellingLoc;
+    }
 
     const char *StrData = Buffer.data()+LocInfo.second;
     
@@ -1051,10 +1075,15 @@ getLocationOfByte(unsigned ByteNo, const SourceManager &SM,
 
       // Now that we know the offset of the token in the spelling, use the
       // preprocessor to get the offset in the original source.
+      if (StartTokenByteOffset != nullptr)
+        *StartTokenByteOffset = StringOffset;
+      if (StartToken != nullptr)
+        *StartToken = TokNo;
       return Lexer::AdvanceToTokenCharacter(StrTokLoc, Offset, SM, Features);
     }
 
     // Move to the next string token.
+    StringOffset += TokNumBytes;
     ++TokNo;
     ByteNo -= TokNumBytes;
   }

clang/lib/CodeGen/CGStmt.cpp

@@ -1714,13 +1714,15 @@ static llvm::MDNode *getAsmSrcLocInfo(const StringLiteral *Str,
   if (!StrVal.empty()) {
     const SourceManager &SM = CGF.CGM.getContext().getSourceManager();
     const LangOptions &LangOpts = CGF.CGM.getLangOpts();
+    unsigned StartToken = 0;
+    unsigned ByteOffset = 0;
 
     // Add the location of the start of each subsequent line of the asm to the
     // MDNode.
-    for (unsigned i = 0, e = StrVal.size()-1; i != e; ++i) {
+    for (unsigned i = 0, e = StrVal.size() - 1; i != e; ++i) {
       if (StrVal[i] != '\n') continue;
-      SourceLocation LineLoc = Str->getLocationOfByte(i+1, SM, LangOpts,
-                                                      CGF.getTarget());
+      SourceLocation LineLoc = Str->getLocationOfByte(
+          i + 1, SM, LangOpts, CGF.getTarget(), &StartToken, &ByteOffset);
       Locs.push_back(llvm::ConstantAsMetadata::get(
           llvm::ConstantInt::get(CGF.Int32Ty, LineLoc.getRawEncoding())));
     }