[BOLT][AArch64] Compensate for missing code markers (llvm#151060)

Code written in assembly can have missing code markers. In BOLT, we can
compensate by recognizing that a function entry point should start a
code sequence.

Seen such code in lua jit library.

Author: maksfb

bolt/lib/Rewrite/RewriteInstance.cpp

@@ -896,6 +896,20 @@ void RewriteInstance::discoverFileObjects() {
         continue;
 
       MarkerSymType MarkerType = BC->getMarkerType(SymInfo.Symbol);
+
+      // Treat ST_Function as code.
+      Expected<object::SymbolRef::Type> TypeOrError = SymInfo.Symbol.getType();
+      consumeError(TypeOrError.takeError());
+      if (TypeOrError && *TypeOrError == SymbolRef::ST_Function) {
+        if (IsData) {
+          Expected<StringRef> NameOrError = SymInfo.Symbol.getName();
+          consumeError(NameOrError.takeError());
+          BC->errs() << "BOLT-WARNING: function symbol " << *NameOrError
+                     << " lacks code marker\n";
+        }
+        MarkerType = MarkerSymType::CODE;
+      }
+
       if (MarkerType != MarkerSymType::NONE) {
         SortedMarkerSymbols.push_back(MarkerSym{SymInfo.Address, MarkerType});
         LastAddr = SymInfo.Address;

bolt/test/AArch64/missing-code-marker.s

@@ -0,0 +1,26 @@
+## Check that llvm-bolt is able to recover a missing code marker.
+
+# RUN: %clang %cflags %s -o %t.exe -nostdlib -fuse-ld=lld -Wl,-q
+# RUN: llvm-bolt %t.exe -o %t.bolt 2>&1 | FileCheck %s
+
+# CHECK: BOLT-WARNING: function symbol foo lacks code marker
+
+.text
+.balign 4
+
+.word 0
+
+## Function foo starts immediately after a data object and does not have
+## a matching "$x" symbol to indicate the start of code.
+.global foo
+.type foo, %function
+foo:
+  .word 0xd65f03c0
+.size foo, .-foo
+
+.global _start
+.type _start, %function
+_start:
+  bl foo
+  ret
+.size _start, .-_start