[BOLT][AArch64] Detect veneers with missing data markers (#142069)

The linker may omit data markers for long absolute veneers causing BOLT
to treat data as code. Detect such veneers and introduce data markers
artificially before BOLT's disassembler kicks in.

Author: maksfb

bolt/lib/Rewrite/RewriteInstance.cpp

@@ -1341,6 +1341,19 @@ void RewriteInstance::discoverFileObjects() {
         }
       }
     }
+
+    // The linker may omit data markers for absolute long veneers. Introduce
+    // those markers artificially to assist the disassembler.
+    for (BinaryFunction &BF :
+         llvm::make_second_range(BC->getBinaryFunctions())) {
+      if (BF.getOneName().starts_with("__AArch64AbsLongThunk_") &&
+          BF.getSize() == 16 && !BF.getSizeOfDataInCodeAt(8)) {
+        BC->errs() << "BOLT-WARNING: missing data marker detected in veneer "
+                   << BF << '\n';
+        BF.markDataAtOffset(8);
+        BC->AddressToConstantIslandMap[BF.getAddress() + 8] = &BF;
+      }
+    }
   }
 
   if (!BC->IsLinuxKernel) {

bolt/test/AArch64/veneer-lld-abs.s

@@ -6,10 +6,21 @@
 # RUN:    -fuse-ld=lld -Wl,-q
 # RUN: llvm-objdump -d %t.exe | FileCheck --check-prefix=CHECK-INPUT %s
 # RUN: llvm-objcopy --remove-section .rela.mytext %t.exe
-# RUN: llvm-bolt %t.exe -o %t.bolt --elim-link-veneers=true --lite=0
+# RUN: llvm-bolt %t.exe -o %t.bolt
 # RUN: llvm-objdump -d -j .text  %t.bolt | \
 # RUN:   FileCheck --check-prefix=CHECK-OUTPUT %s
 
+## Occasionally, we see the linker not generating $d symbols for long veneers
+## causing BOLT to fail veneer elimination.
+# RUN: llvm-objcopy --remove-symbol-prefix=\$d %t.exe %t.no-marker.exe
+# RUN: llvm-bolt %t.no-marker.exe -o %t.no-marker.bolt \
+# RUN:   2>&1 | FileCheck %s --check-prefix=CHECK-BOLT
+# RUN: llvm-objdump -d -j .text  %t.no-marker.bolt | \
+# RUN:   FileCheck --check-prefix=CHECK-OUTPUT %s
+
+# CHECK-BOLT-NOT: BOLT-WARNING: unable to disassemble instruction
+# CHECK-BOLT: BOLT-WARNING: missing data marker detected in veneer __AArch64AbsLongThunk_far_function
+
 .text
 .balign 4
 .global far_function