[COFF] Fix /export:foo=bar when bar is a weak alias

Summary:
When handling exports from the command line or from .def files, the
linker does a "fuzzy" string lookup to allow finding mangled symbols.
However, when the symbol is re-exported under a new name, the linker has
to transfer the decorations from the exported symbol over to the new
name. This is implemented by taking the mangled symbol that was found in
the object and replacing the original symbol name with the export name.

Before this patch, LLD implemented the fuzzy search by adding an
undefined symbol with the unmangled name, and then during symbol
resolution, checking if similar mangled symbols had been added after the
last round of symbol resolution. If so, LLD makes the original symbol a
weak alias of the mangled symbol. Later, to get the original symbol
name, LLD would look through the weak alias and forward it on to the
import library writer, which copies the symbol decorations. This
approach doesn't work when bar is itself a weak alias, as is the case in
asan. It's especially bad when the aliasee of bar contains the string
"bar", consider "bar_default". In this case, we would end up exporting
the symbol "foo_default" when we should've exported just "foo".

To fix this, don't look through weak aliases to find the mangled name.
Save the mangled name earlier during fuzzy symbol lookup.

Fixes PR42074

Reviewers: mstorsjo, ruiu

Subscribers: thakis, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D62984

llvm-svn: 362849

8 files changed, 136 insertions, 45 deletions

diff --git a/lld/COFF/Driver.cpp b/lld/COFF/Driver.cpp
index 7f7fde12980..ef25fe3b688 100644
--- a/lld/COFF/Driver.cpp
+++ b/lld/COFF/Driver.cpp
@@ -138,8 +138,8 @@ static StringRef mangle(StringRef Sym) {
 }
 
 static bool findUnderscoreMangle(StringRef Sym) {
-  StringRef Entry = Symtab->findMangle(mangle(Sym));
-  return !Entry.empty() && !isa<Undefined>(Symtab->find(Entry));
+  Symbol *S = Symtab->findMangle(mangle(Sym));
+  return S && !isa<Undefined>(S);
 }
 
 MemoryBufferRef LinkerDriver::takeBuffer(std::unique_ptr<MemoryBuffer> MB) {
@@ -486,6 +486,24 @@ Symbol *LinkerDriver::addUndefined(StringRef Name) {
   return B;
 }
 
+StringRef LinkerDriver::mangleMaybe(Symbol *S) {
+  // If the plain symbol name has already been resolved, do nothing.
+  Undefined *Unmangled = dyn_cast<Undefined>(S);
+  if (!Unmangled)
+    return "";
+
+  // Otherwise, see if a similar, mangled symbol exists in the symbol table.
+  Symbol *Mangled = Symtab->findMangle(Unmangled->getName());
+  if (!Mangled)
+    return "";
+
+  // If we find a similar mangled symbol, make this an alias to it and return
+  // its name.
+  log(Unmangled->getName() + " aliased to " + Mangled->getName());
+  Unmangled->WeakAlias = Symtab->addUndefined(Mangled->getName());
+  return Mangled->getName();
+}
+
 // Windows specific -- find default entry point name.
 //
 // There are four different entry point functions for Windows executables,
@@ -1644,7 +1662,7 @@ void LinkerDriver::link(ArrayRef<const char *> ArgsArr) {
     // Windows specific -- if entry point is not found,
     // search for its mangled names.
     if (Config->Entry)
-      Symtab->mangleMaybe(Config->Entry);
+      mangleMaybe(Config->Entry);
 
     // Windows specific -- Make sure we resolve all dllexported symbols.
     for (Export &E : Config->Exports) {
@@ -1652,7 +1670,7 @@ void LinkerDriver::link(ArrayRef<const char *> ArgsArr) {
         continue;
       E.Sym = addUndefined(E.Name);
       if (!E.Directives)
-        Symtab->mangleMaybe(E.Sym);
+        E.SymbolName = mangleMaybe(E.Sym);
     }
 
     // Add weak aliases. Weak aliases is a mechanism to give remaining
diff --git a/lld/COFF/Driver.h b/lld/COFF/Driver.h
index f0c2ee6a772..6b4266a85e1 100644
--- a/lld/COFF/Driver.h
+++ b/lld/COFF/Driver.h
@@ -108,6 +108,8 @@ private:
 
   Symbol *addUndefined(StringRef Sym);
 
+  StringRef mangleMaybe(Symbol *S);
+
   // Windows specific -- "main" is not the only main function in Windows.
   // You can choose one from these four -- {w,}{WinMain,main}.
   // There are four different entry point functions for them,
diff --git a/lld/COFF/DriverUtils.cpp b/lld/COFF/DriverUtils.cpp
index f689cd1d419..c59027e809e 100644
--- a/lld/COFF/DriverUtils.cpp
+++ b/lld/COFF/DriverUtils.cpp
@@ -655,18 +655,6 @@ void fixupExports() {
   }
 
   for (Export &E : Config->Exports) {
-    Symbol *Sym = E.Sym;
-    if (!E.ForwardTo.empty() || !Sym) {
-      E.SymbolName = E.Name;
-    } else {
-      if (auto *U = dyn_cast<Undefined>(Sym))
-        if (U->WeakAlias)
-          Sym = U->WeakAlias;
-      E.SymbolName = Sym->getName();
-    }
-  }
-
-  for (Export &E : Config->Exports) {
     if (!E.ForwardTo.empty()) {
       E.ExportName = undecorate(E.Name);
     } else {
diff --git a/lld/COFF/SymbolTable.cpp b/lld/COFF/SymbolTable.cpp
index 1c602c65ef3..5180559a86e 100644
--- a/lld/COFF/SymbolTable.cpp
+++ b/lld/COFF/SymbolTable.cpp
@@ -472,48 +472,56 @@ Symbol *SymbolTable::findUnderscore(StringRef Name) {
   return find(Name);
 }
 
-StringRef SymbolTable::findByPrefix(StringRef Prefix) {
+// Return all symbols that start with Prefix, possibly ignoring the first
+// character of Prefix or the first character symbol.
+std::vector<Symbol *> SymbolTable::getSymsWithPrefix(StringRef Prefix) {
+  std::vector<Symbol *> Syms;
   for (auto Pair : SymMap) {
     StringRef Name = Pair.first.val();
-    if (Name.startswith(Prefix))
-      return Name;
+    if (Name.startswith(Prefix) || Name.startswith(Prefix.drop_front()) ||
+        Name.drop_front().startswith(Prefix) ||
+        Name.drop_front().startswith(Prefix.drop_front())) {
+      Syms.push_back(Pair.second);
+    }
   }
-  return "";
+  return Syms;
 }
 
-StringRef SymbolTable::findMangle(StringRef Name) {
+Symbol *SymbolTable::findMangle(StringRef Name) {
   if (Symbol *Sym = find(Name))
     if (!isa<Undefined>(Sym))
-      return Name;
+      return Sym;
+
+  // Efficient fuzzy string lookup is impossible with a hash table, so iterate
+  // the symbol table once and collect all possibly matching symbols into this
+  // vector. Then compare each possibly matching symbol with each possible
+  // mangling.
+  std::vector<Symbol *> Syms = getSymsWithPrefix(Name);
+  auto FindByPrefix = [&Syms](const Twine &T) -> Symbol * {
+    std::string Prefix = T.str();
+    for (auto *S : Syms)
+      if (S->getName().startswith(Prefix))
+        return S;
+    return nullptr;
+  };
+
+  // For non-x86, just look for C++ functions.
   if (Config->Machine != I386)
-    return findByPrefix(("?" + Name + "@@Y").str());
+    return FindByPrefix("?" + Name + "@@Y");
+
   if (!Name.startswith("_"))
-    return "";
+    return nullptr;
   // Search for x86 stdcall function.
-  StringRef S = findByPrefix((Name + "@").str());
-  if (!S.empty())
+  if (Symbol *S = FindByPrefix(Name + "@"))
     return S;
   // Search for x86 fastcall function.
-  S = findByPrefix(("@" + Name.substr(1) + "@").str());
-  if (!S.empty())
+  if (Symbol *S = FindByPrefix("@" + Name.substr(1) + "@"))
     return S;
   // Search for x86 vectorcall function.
-  S = findByPrefix((Name.substr(1) + "@@").str());
-  if (!S.empty())
+  if (Symbol *S = FindByPrefix(Name.substr(1) + "@@"))
     return S;
   // Search for x86 C++ non-member function.
-  return findByPrefix(("?" + Name.substr(1) + "@@Y").str());
-}
-
-void SymbolTable::mangleMaybe(Symbol *B) {
-  auto *U = dyn_cast<Undefined>(B);
-  if (!U || U->WeakAlias)
-    return;
-  StringRef Alias = findMangle(U->getName());
-  if (!Alias.empty()) {
-    log(U->getName() + " aliased to " + Alias);
-    U->WeakAlias = addUndefined(Alias);
-  }
+  return FindByPrefix("?" + Name.substr(1) + "@@Y");
 }
 
 Symbol *SymbolTable::addUndefined(StringRef Name) {
diff --git a/lld/COFF/SymbolTable.h b/lld/COFF/SymbolTable.h
index 7f74863bfd3..d01bac1c252 100644
--- a/lld/COFF/SymbolTable.h
+++ b/lld/COFF/SymbolTable.h
@@ -68,8 +68,7 @@ public:
   // mangled symbol. This function tries to find a mangled name
   // for U from the symbol table, and if found, set the symbol as
   // a weak alias for U.
-  void mangleMaybe(Symbol *B);
-  StringRef findMangle(StringRef Name);
+  Symbol *findMangle(StringRef Name);
 
   // Build a set of COFF objects representing the combined contents of
   // BitcodeFiles and add them to the symbol table. Called after all files are
@@ -115,7 +114,8 @@ private:
   std::pair<Symbol *, bool> insert(StringRef Name);
   /// Same as insert(Name), but also sets IsUsedInRegularObj.
   std::pair<Symbol *, bool> insert(StringRef Name, InputFile *F);
-  StringRef findByPrefix(StringRef Prefix);
+
+  std::vector<Symbol *> getSymsWithPrefix(StringRef Prefix);
 
   llvm::DenseMap<llvm::CachedHashStringRef, Symbol *> SymMap;
   std::unique_ptr<BitcodeCompiler> LTO;
diff --git a/lld/test/COFF/export-stdcall.s b/lld/test/COFF/export-stdcall.s
new file mode 100644
index 00000000000..b1146412607
--- /dev/null
+++ b/lld/test/COFF/export-stdcall.s
@@ -0,0 +1,31 @@
+# RUN: llvm-mc -triple i686-windows-msvc %s -o %t.obj -filetype=obj
+# RUN: lld-link %t.obj -out:%t.dll -dll -nodefaultlib -noentry -export:foo_std=bar_std -export:foo_fast=bar_fast
+# RUN: llvm-nm %t.lib | FileCheck %s
+
+# MSVC fudges the lookup of 'bar' to allow it to find the stdcall function
+# _bar_std@8, and then exports _foo_std@8. Same for fastcall and other mangling
+# schemes.
+
+# CHECK: export-stdcall.s.tmp.dll:
+# CHECK: 00000000 T @foo_fast@8
+# CHECK: 00000000 T __imp_@foo_fast@8
+
+# CHECK: export-stdcall.s.tmp.dll:
+# CHECK: 00000000 T __imp__foo_std@8
+# CHECK: 00000000 T _foo_std@8
+
+	.text
+	.def	 _bar_std@8; .scl	2; .type	32; .endef
+	.globl	_bar_std@8
+_bar_std@8:
+	movl	8(%esp), %eax
+	movl	4(%esp), %ecx
+	leal	42(%ecx,%eax), %eax
+	retl	$8
+
+	.def	 @bar_fast@8; .scl	2; .type	32; .endef
+	.globl	@bar_fast@8
+@bar_fast@8:
+	leal	42(%ecx,%eax), %eax
+	retl
+
diff --git a/lld/test/COFF/export-weak-alias.s b/lld/test/COFF/export-weak-alias.s
new file mode 100644
index 00000000000..d1c2141bdf9
--- /dev/null
+++ b/lld/test/COFF/export-weak-alias.s
@@ -0,0 +1,32 @@
+# RUN: llvm-mc -triple x86_64-windows-msvc %s -o %t.obj -filetype=obj
+# RUN: lld-link %t.obj -out:%t.dll -dll -nodefaultlib -noentry
+# RUN: llvm-nm %t.lib | FileCheck %s
+
+# CHECK: export-weak-alias.s.tmp.dll:
+# CHECK: 00000000 T __imp_foo_dll{{$}}
+# CHECK: 00000000 T foo_dll{{$}}
+
+	.text
+	.def	 @feat.00;
+	.scl	3;
+	.type	0;
+	.endef
+	.globl	@feat.00
+.set @feat.00, 0
+	.file	"t.c"
+	.def	 foo_def;
+	.scl	2;
+	.type	32;
+	.endef
+	.globl	foo_def                 # -- Begin function foo_def
+	.p2align	4, 0x90
+foo_def:                                # @foo_def
+# %bb.0:                                # %entry
+	movl	$42, %eax
+	retq
+                                        # -- End function
+	.section	.drectve,"yn"
+	.ascii	" /alternatename:foo=foo_def"
+	.ascii	" /export:foo_dll=foo"
+
+	.addrsig
diff --git a/llvm/include/llvm/Object/COFFImportFile.h b/llvm/include/llvm/Object/COFFImportFile.h
index e07060cea2b..5aa83641111 100644
--- a/llvm/include/llvm/Object/COFFImportFile.h
+++ b/llvm/include/llvm/Object/COFFImportFile.h
@@ -69,9 +69,21 @@ private:
 };
 
 struct COFFShortExport {
+  /// The name of the export as specified in the .def file or on the command
+  /// line, i.e. "foo" in "/EXPORT:foo", and "bar" in "/EXPORT:foo=bar". This
+  /// may lack mangling, such as underscore prefixing and stdcall suffixing.
   std::string Name;
+
+  /// The external, exported name. Only non-empty when export renaming is in
+  /// effect, i.e. "foo" in "/EXPORT:foo=bar".
   std::string ExtName;
+
+  /// The real, mangled symbol name from the object file. Given
+  /// "/export:foo=bar", this could be "_bar@8" if bar is stdcall.
   std::string SymbolName;
+
+  /// Creates a weak alias. This is the name of the weak aliasee. In a .def
+  /// file, this is "baz" in "EXPORTS\nfoo = bar == baz".
   std::string AliasTarget;
 
   uint16_t Ordinal = 0;