Recommit [ELF] - Versionscript: do not treat non-wildcarded names as wildcards.

Fixed code that was not checked before on windows for me, because of testcases that are
disabled on that platform atm.

Inital commit message:
"[ELF] - Versionscript: do not treat non-wildcarded names as wildcards."
Previously we incorrectly handled cases when symbol name in extern c++ tag
was enclosed in quotes. Next case was treated as wildcard:

GLIBCXX_3.4 {
    extern "C++" {
    "aaa*"
   }
But it should have not. Quotes around aaa here means that we should have do exact
name matching.
That is PR30268 which has name with pointer is interpreted as wildcard by lld:

extern "C++" {
    "operator delete[](void*)";

Patch fixes the issue.

Differential revision: https://reviews.llvm.org/D24229

llvm-svn: 281049

diff --git a/lld/ELF/Config.h b/lld/ELF/Config.h
index 4d7cf3e..98246c3 100644 (file)
--- a/lld/ELF/Config.h
+++ b/lld/ELF/Config.h
@@ -45,6 +45,7 @@ enum class UnresolvedPolicy { NoUndef, ReportError, Warn, Ignore };
 struct SymbolVersion {
   llvm::StringRef Name;
   bool IsExternCpp;
+  bool HasWildcards;
 };
 
 // This struct contains symbols version definition that

diff --git a/lld/ELF/LinkerScript.cpp b/lld/ELF/LinkerScript.cpp
index 9d6935f..ef8ccb9 100644 (file)
--- a/lld/ELF/LinkerScript.cpp
+++ b/lld/ELF/LinkerScript.cpp
@@ -785,7 +785,7 @@ void ScriptParser::readAsNeeded() {
   bool Orig = Config->AsNeeded;
   Config->AsNeeded = true;
   while (!Error && !skip(")"))
-    addFile(next());
+    addFile(unquote(next()));
   Config->AsNeeded = Orig;
 }
 
@@ -811,13 +811,13 @@ void ScriptParser::readGroup() {
     if (Tok == "AS_NEEDED")
       readAsNeeded();
     else
-      addFile(Tok);
+      addFile(unquote(Tok));
   }
 }
 
 void ScriptParser::readInclude() {
   StringRef Tok = next();
-  auto MBOrErr = MemoryBuffer::getFile(Tok);
+  auto MBOrErr = MemoryBuffer::getFile(unquote(Tok));
   if (!MBOrErr) {
     setError("cannot open " + Tok);
     return;
@@ -833,7 +833,7 @@ void ScriptParser::readOutput() {
   expect("(");
   StringRef Tok = next();
   if (Config->OutputFile.empty())
-    Config->OutputFile = Tok;
+    Config->OutputFile = unquote(Tok);
   expect(")");
 }
 
@@ -896,7 +896,7 @@ void ScriptParser::readSearchDir() {
   expect("(");
   StringRef Tok = next();
   if (!Config->Nostdlib)
-    Config->SearchPaths.push_back(Tok);
+    Config->SearchPaths.push_back(unquote(Tok));
   expect(")");
 }
 
@@ -1004,7 +1004,7 @@ Expr ScriptParser::readAssert() {
   expect("(");
   Expr E = readExpr();
   expect(",");
-  StringRef Msg = next();
+  StringRef Msg = unquote(next());
   expect(")");
   return [=](uint64_t Dot) {
     uint64_t V = E(Dot);
@@ -1421,13 +1421,14 @@ void ScriptParser::readLocal() {
 }
 
 void ScriptParser::readExtern(std::vector<SymbolVersion> *Globals) {
-  expect("C++");
+  expect("\"C++\"");
   expect("{");
 
   for (;;) {
     if (peek() == "}" || Error)
       break;
-    Globals->push_back({next(), true});
+    bool HasWildcard = !peek().startswith("\"") && hasWildcard(peek());
+    Globals->push_back({unquote(next()), true, HasWildcard});
     expect(";");
   }
 
@@ -1450,7 +1451,7 @@ void ScriptParser::readGlobal(StringRef VerStr) {
     if (Cur == "}" || Cur == "local:" || Error)
       return;
     next();
-    Globals->push_back({Cur, false});
+    Globals->push_back({unquote(Cur), false, hasWildcard(Cur)});
     expect(";");
   }
 }

diff --git a/lld/ELF/ScriptParser.cpp b/lld/ELF/ScriptParser.cpp
index 19e20b6..97d68d9 100644 (file)
--- a/lld/ELF/ScriptParser.cpp
+++ b/lld/ELF/ScriptParser.cpp
@@ -60,14 +60,17 @@ std::vector<StringRef> ScriptParserBase::tokenize(StringRef S) {
     if (S.empty())
       return Ret;
 
-    // Quoted token.
+    // Quoted token. Note that double-quote characters are parts of a token
+    // because, in a glob match context, only unquoted tokens are interpreted
+    // as glob patterns. Double-quoted tokens are literal patterns in that
+    // context.
     if (S.startswith("\"")) {
       size_t E = S.find("\"", 1);
       if (E == StringRef::npos) {
         error("unclosed quote");
         return {};
       }
-      Ret.push_back(S.substr(1, E - 1));
+      Ret.push_back(S.take_front(E + 1));
       S = S.substr(E + 1);
       continue;
     }

diff --git a/lld/ELF/Strings.cpp b/lld/ELF/Strings.cpp
index fec7bd4..cd19612 100644 (file)
--- a/lld/ELF/Strings.cpp
+++ b/lld/ELF/Strings.cpp
@@ -24,6 +24,12 @@ bool elf::hasWildcard(StringRef S) {
   return S.find_first_of("?*[") != StringRef::npos;
 }
 
+StringRef elf::unquote(StringRef S) {
+  if (!S.startswith("\""))
+    return S;
+  return S.substr(1, S.size() - 2);
+}
+
 // Converts a glob pattern to a regular expression.
 static std::string toRegex(StringRef S) {
   std::string T;

diff --git a/lld/ELF/Strings.h b/lld/ELF/Strings.h
index ad99eb9..e08423a 100644 (file)
--- a/lld/ELF/Strings.h
+++ b/lld/ELF/Strings.h
@@ -20,6 +20,7 @@ llvm::Regex compileGlobPatterns(ArrayRef<StringRef> V);
 bool hasWildcard(StringRef S);
 std::vector<uint8_t> parseHex(StringRef S);
 bool isValidCIdentifier(StringRef S);
+StringRef unquote(StringRef S);
 
 // Returns a demangled C++ symbol name. If Name is not a mangled
 // name or the system does not provide __cxa_demangle function,

diff --git a/lld/ELF/SymbolListFile.cpp b/lld/ELF/SymbolListFile.cpp
index cd977c5..3fe83d4 100644 (file)
--- a/lld/ELF/SymbolListFile.cpp
+++ b/lld/ELF/SymbolListFile.cpp
@@ -16,6 +16,7 @@
 #include "SymbolListFile.h"
 #include "Config.h"
 #include "ScriptParser.h"
+#include "Strings.h"
 #include "llvm/Support/MemoryBuffer.h"
 
 using namespace llvm;
@@ -43,7 +44,7 @@ void DynamicListParser::run() {
   while (!atEOF()) {
     expect("{");
     while (!Error) {
-      Config->DynamicList.push_back(next());
+      Config->DynamicList.push_back(unquote(next()));
       expect(";");
       if (skip("}"))
         break;

diff --git a/lld/ELF/SymbolTable.cpp b/lld/ELF/SymbolTable.cpp
index d80e512..f758247 100644 (file)
--- a/lld/ELF/SymbolTable.cpp
+++ b/lld/ELF/SymbolTable.cpp
@@ -18,7 +18,6 @@
 #include "Config.h"
 #include "Error.h"
 #include "LinkerScript.h"
-#include "Strings.h"
 #include "SymbolListFile.h"
 #include "Symbols.h"
 #include "llvm/Bitcode/ReaderWriter.h"
@@ -678,7 +677,7 @@ template <class ELFT> void SymbolTable<ELFT>::scanVersionScript() {
   // i.e. version definitions not containing any glob meta-characters.
   for (VersionDefinition &V : Config->VersionDefinitions) {
     for (SymbolVersion Sym : V.Globals) {
-      if (hasWildcard(Sym.Name))
+      if (Sym.HasWildcards)
         continue;
       StringRef N = Sym.Name;
       SymbolBody *B = Sym.IsExternCpp ? findDemangled(Demangled, N) : find(N);
@@ -693,7 +692,7 @@ template <class ELFT> void SymbolTable<ELFT>::scanVersionScript() {
   for (size_t I = Config->VersionDefinitions.size() - 1; I != (size_t)-1; --I) {
     VersionDefinition &V = Config->VersionDefinitions[I];
     for (SymbolVersion &Sym : V.Globals) {
-      if (!hasWildcard(Sym.Name))
+      if (!Sym.HasWildcards)
         continue;
       Regex Re = compileGlobPatterns({Sym.Name});
       std::vector<SymbolBody *> Syms =

diff --git a/lld/test/ELF/invalid-dynamic-list.test b/lld/test/ELF/invalid-dynamic-list.test
index 0e7c820..11b7900 100644 (file)
--- a/lld/test/ELF/invalid-dynamic-list.test
+++ b/lld/test/ELF/invalid-dynamic-list.test
@@ -34,4 +34,4 @@
 
 # RUN: echo "{ extern \"BOGUS\" { test }; };" > %t1
 # RUN: not ld.lld --dynamic-list %t1 2>&1 | FileCheck -check-prefix=ERR6 %s
-# ERR6: line 1: ; expected, but got BOGUS
+# ERR6: line 1: ; expected, but got "BOGUS"

diff --git a/lld/test/ELF/version-script-extern-exact.s b/lld/test/ELF/version-script-extern-exact.s
new file mode 100644 (file)
index 0000000..b33ea35
--- /dev/null
+++ b/lld/test/ELF/version-script-extern-exact.s
@@ -0,0 +1,22 @@
+# REQUIRES: x86
+
+# RUN: llvm-mc -filetype=obj -triple=x86_64-pc-linux %s -o %t.o
+# RUN: echo "FOO { global: extern \"C++\" { \"aaa*\"; }; };" > %t.script
+# RUN: ld.lld --version-script %t.script -shared %t.o -o %t.so
+# RUN: llvm-readobj -V -dyn-symbols %t.so | FileCheck %s
+
+# CHECK: Symbol {
+# CHECK:   Name: _Z3aaaPf@ (1)
+# CHECK: Symbol {
+# CHECK:   Name: _Z3aaaPi@ (10)
+
+.text
+.globl _Z3aaaPi
+.type _Z3aaaPi,@function
+_Z3aaaPi:
+retq
+
+.globl _Z3aaaPf
+.type _Z3aaaPf,@function
+_Z3aaaPf:
+retq