release/21.x: [LLD][COFF] Avoid resolving symbols with -alternatename if the target is undefined (#149496)

lld/COFF/Driver.cpp

@@ -2554,28 +2554,7 @@ void LinkerDriver::linkerMain(ArrayRef<const char *> argsArr) {
             e.symbolName = symtab.mangleMaybe(e.sym);
         }
 
-        // Add weak aliases. Weak aliases is a mechanism to give remaining
-        // undefined symbols final chance to be resolved successfully.
-        for (auto pair : symtab.alternateNames) {
-          StringRef from = pair.first;
-          StringRef to = pair.second;
-          Symbol *sym = symtab.find(from);
-          if (!sym)
-            continue;
-          if (auto *u = dyn_cast<Undefined>(sym)) {
-            if (u->weakAlias) {
-              // On ARM64EC, anti-dependency aliases are treated as undefined
-              // symbols unless a demangled symbol aliases a defined one, which
-              // is part of the implementation.
-              if (!symtab.isEC() || !u->isAntiDep)
-                continue;
-              if (!isa<Undefined>(u->weakAlias) &&
-                  !isArm64ECMangledFunctionName(u->getName()))
-                continue;
-            }
-            u->setWeakAlias(symtab.addUndefined(to));
-          }
-        }
+        symtab.resolveAlternateNames();
       });
 
       ctx.forEachActiveSymtab([&](SymbolTable &symtab) {

lld/COFF/SymbolTable.cpp

@@ -1344,6 +1344,43 @@ void SymbolTable::parseAlternateName(StringRef s) {
   alternateNames.insert(it, std::make_pair(from, to));
 }
 
+void SymbolTable::resolveAlternateNames() {
+  // Add weak aliases. Weak aliases is a mechanism to give remaining
+  // undefined symbols final chance to be resolved successfully.
+  for (auto pair : alternateNames) {
+    StringRef from = pair.first;
+    StringRef to = pair.second;
+    Symbol *sym = find(from);
+    if (!sym)
+      continue;
+    if (auto *u = dyn_cast<Undefined>(sym)) {
+      if (u->weakAlias) {
+        // On ARM64EC, anti-dependency aliases are treated as undefined
+        // symbols unless a demangled symbol aliases a defined one, which
+        // is part of the implementation.
+        if (!isEC() || !u->isAntiDep)
+          continue;
+        if (!isa<Undefined>(u->weakAlias) &&
+            !isArm64ECMangledFunctionName(u->getName()))
+          continue;
+      }
+
+      // Check if the destination symbol is defined. If not, skip it.
+      // It may still be resolved later if more input files are added.
+      // Also skip anti-dependency targets, as they can't be chained anyway.
+      Symbol *toSym = find(to);
+      if (!toSym)
+        continue;
+      auto toUndef = dyn_cast<Undefined>(toSym);
+      if (toUndef && (!toUndef->weakAlias || toUndef->isAntiDep))
+        continue;
+      if (toSym->isLazy())
+        forceLazy(toSym);
+      u->setWeakAlias(toSym);
+    }
+  }
+}
+
 // Parses /aligncomm option argument.
 void SymbolTable::parseAligncomm(StringRef s) {
   auto [name, align] = s.split(',');

lld/COFF/SymbolTable.h

@@ -69,6 +69,9 @@ class SymbolTable {
   // symbols and warn about imported local symbols.
   void resolveRemainingUndefines();
 
+  // Try to resolve undefined symbols with alternate names.
+  void resolveAlternateNames();
+
   // Load lazy objects that are needed for MinGW automatic import and for
   // doing stdcall fixups.
   void loadMinGWSymbols();

lld/test/COFF/alternatename-alias.s

@@ -0,0 +1,15 @@
+// REQUIRES: x86
+
+// Check that a weak alias can be used as an alternate name target.
+// RUN: llvm-mc -filetype=obj -triple=x86_64-windows %s -o %t.obj
+// RUN: lld-link -dll -noentry %t.obj -alternatename:sym=altsym
+
+        .data
+        .rva sym
+
+        .weak altsym
+        .set altsym,a
+
+        .globl a
+a:
+        .word 1

lld/test/COFF/alternatename-antidep.s

@@ -0,0 +1,16 @@
+// REQUIRES: x86
+
+// Check that an anti-dependency alias can't be used as an alternate name target.
+// RUN: llvm-mc -filetype=obj -triple=x86_64-windows %s -o %t.obj
+// RUN: not lld-link -dll -noentry %t.obj -alternatename:sym=altsym 2>&1 | FileCheck %s
+// CHECK: error: undefined symbol: sym
+
+        .data
+        .rva sym
+
+        .weak_anti_dep altsym
+        .set altsym,a
+
+        .globl a
+a:
+        .word 1

lld/test/COFF/alternatename-lib.s

@@ -0,0 +1,43 @@
+// REQUIRES: x86
+// RUN: split-file %s %t.dir && cd %t.dir
+
+// RUN: llvm-mc -filetype=obj -triple=x86_64-windows refab.s -o refab.obj
+// RUN: llvm-mc -filetype=obj -triple=x86_64-windows aa.s -o aa.obj
+// RUN: llvm-mc -filetype=obj -triple=x86_64-windows b.s -o b.obj
+// RUN: llvm-mc -filetype=obj -triple=x86_64-windows antidep.s -o antidep.obj
+// RUN: llvm-lib -out:aa.lib aa.obj
+// RUN: llvm-lib -out:b.lib b.obj
+
+// Check that -alternatename with an undefined target does not prevent the symbol from being resolved to a library,
+// once another alternate name is resolved and pulls in the source symbol.
+// RUN: lld-link -out:out.dll -dll -noentry -machine:amd64 refab.obj aa.lib -alternatename:a=aa -alternatename:b=undef
+
+// Check that -alternatename with an anti-dependency target does not prevent the symbol from being resolved to a library,
+// after another alternate name is resolved and pulls in the source symbol.
+// RUN: lld-link -out:out2.dll -dll -noentry -machine:amd64 antidep.obj refab.obj aa.lib -alternatename:a=aa -alternatename:b=u
+
+#--- refab.s
+        .data
+        .rva a
+        .rva b
+
+#--- aa.s
+        .globl aa
+aa:
+        .word 1
+
+        .section .drectve, "yn"
+        .ascii "/defaultlib:b.lib"
+
+#--- b.s
+        .globl b
+b:
+        .word 2
+
+#--- antidep.s
+        .weak_anti_dep u
+        .set u,d
+
+        .globl d
+d:
+        .word 3

lld/test/COFF/arm64ec-altnames.s

@@ -2,6 +2,7 @@ REQUIRES: aarch64
 RUN: split-file %s %t.dir && cd %t.dir
 
 RUN: llvm-mc -filetype=obj -triple=arm64ec-windows ext.s -o ext.obj
+RUN: llvm-mc -filetype=obj -triple=arm64ec-windows ext-mangled.s -o ext-mangled.obj
 RUN: llvm-mc -filetype=obj -triple=arm64ec-windows impl.s -o impl.obj
 RUN: llvm-mc -filetype=obj -triple=arm64ec-windows impl-cpp.s -o impl-cpp.obj
 RUN: llvm-mc -filetype=obj -triple=arm64ec-windows %S/Inputs/loadconfig-arm64ec.s -o loadconfig.obj
@@ -49,6 +50,20 @@ RUN: lld-link -machine:arm64ec -dll -noentry -out:out4.dll impl-cpp.obj loadconf
 RUN: llvm-objdump -d out4.dll | FileCheck --check-prefix=DISASM %s
 RUN: llvm-readobj --hex-dump=.test out4.dll | FileCheck --check-prefix=TESTSEC %s
 
+# Check that when both mangled and demangled alternate names are used,
+# only the one whose target is defined is used (the mangled one in this case).
+
+RUN: lld-link -machine:arm64ec -dll -noentry -out:out5.dll ext-mangled.obj loadconfig.obj "-alternatename:#func=#altsym" -alternatename:func=altsym
+RUN: llvm-objdump -d out5.dll | FileCheck --check-prefix=DISASM %s
+RUN: llvm-readobj --hex-dump=.test out5.dll | FileCheck --check-prefix=TESTSEC %s
+
+# Check that when both mangled and demangled alternate names are used,
+# only the one whose target is defined is used (the demangled one in this case).
+
+RUN: lld-link -machine:arm64ec -dll -noentry -out:out6.dll ext.obj loadconfig.obj "-alternatename:#func=#altsym" -alternatename:func=altsym
+RUN: llvm-objdump -d out6.dll | FileCheck --check-prefix=DISASM2 %s
+RUN: llvm-readobj --hex-dump=.test out6.dll | FileCheck --check-prefix=TESTSEC2 %s
+
 #--- ext.s
         .weak_anti_dep func
 .set func, "#func"
@@ -70,6 +85,30 @@ altsym:
         mov w0, #1
         ret
 
+#--- ext-mangled.s
+        .weak_anti_dep func
+.set func, "#func"
+        .weak_anti_dep "#func"
+.set "#func", thunksym
+
+        .section .test, "r"
+        .rva func
+        .rva "#func"
+
+        .section .thnk,"xr",discard,thunksym
+thunksym:
+        mov w0, #2
+        ret
+
+        .section .text,"xr",discard,"#altsym"
+        .globl "#altsym"
+"#altsym":
+        mov w0, #1
+        ret
+
+        .weak_anti_dep altsym
+        .set altsym,"#altsym"
+
 #--- impl.s
         .weak_anti_dep func
 .set func, "#func"