[llvm-symbolizer][llvm-nm] Fix AArch64 and ARM mapping symbols handling.

Exclude AArch64 mapping symbols ($x and $d) for symtab symbolization as
it was done for ARM since D95916 tom bring bots back to green state.

This is implemented by setting SF_FormatSpecific such that
llvm-symbolizer will ignore them, and use this flag to re-implement
llvm-nm --special-syms option which make it work for both targets.

Differential Revision: https://reviews.llvm.org/D98803

include/llvm/Object/ELFObjectFile.h

@@ -716,7 +716,16 @@ Expected<uint32_t> ELFObjectFile<ELFT>::getSymbolFlags(DataRefImpl Sym) const {
     // TODO: Test this error.
     return SymbolsOrErr.takeError();
 
-  if (EF.getHeader().e_machine == ELF::EM_ARM) {
+  if (EF.getHeader().e_machine == ELF::EM_AARCH64) {
+    if (Expected<StringRef> NameOrErr = getSymbolName(Sym)) {
+      StringRef Name = *NameOrErr;
+      if (Name.startswith("$d") || Name.startswith("$x"))
+        Result |= SymbolRef::SF_FormatSpecific;
+    } else {
+      // TODO: Actually report errors helpfully.
+      consumeError(NameOrErr.takeError());
+    }
+  } else if (EF.getHeader().e_machine == ELF::EM_ARM) {
     if (Expected<StringRef> NameOrErr = getSymbolName(Sym)) {
       StringRef Name = *NameOrErr;
       if (Name.startswith("$d") || Name.startswith("$t") ||

test/DebugInfo/Symbolize/ELF/aarch64-mapping-symbol.s

@@ -0,0 +1,31 @@
+# REQUIRES: aarch64-registered-target
+## Ignore AArch64 mapping symbols (with a prefix of $d or $x).
+
+# RUN: llvm-mc -filetype=obj -triple=aarch64 %s -o %t
+
+## Verify that mapping symbols are actually present in the object at expected
+## addresses.
+# RUN: llvm-nm --special-syms %t | FileCheck %s -check-prefix MAPPING_SYM
+
+# MAPPING_SYM:      0000000000000000 t $d.0
+# MAPPING_SYM-NEXT: 000000000000000c t $d.2
+# MAPPING_SYM-NEXT: 0000000000000004 t $x.1
+# MAPPING_SYM-NEXT: 0000000000000000 T foo
+
+# RUN: llvm-symbolizer --obj=%t 0 4 0xc | FileCheck %s -check-prefix SYMBOL
+
+# SYMBOL:      foo
+# SYMBOL-NEXT: ??:0:0
+# SYMBOL-EMPTY:
+# SYMBOL:      foo
+# SYMBOL-NEXT: ??:0:0
+# SYMBOL-EMPTY:
+# SYMBOL:      foo
+# SYMBOL-NEXT: ??:0:0
+
+    .global foo
+foo:
+    .word 32
+    nop
+    nop
+    .word 42

test/DebugInfo/Symbolize/ELF/arm-mapping-symbol.s

@@ -2,15 +2,32 @@
 ## Ignore ARM mapping symbols (with a prefix of $a, $d or $t).
 
 # RUN: llvm-mc -filetype=obj -triple=armv7-none-linux %s -o %t
-# RUN: llvm-symbolizer --obj=%t 4 8 | FileCheck %s
-# RUN: llvm-mc -filetype=obj -triple=thumbv7-none-linux %s -o %tthumb
-# RUN: llvm-symbolizer --obj=%tthumb 4 8 | FileCheck %s
 
-# CHECK:       foo
-# CHECK-NEXT:  ??:0:0
-# CHECK-EMPTY:
-# CHECK-NEXT:  foo
-# CHECK-NEXT:  ??:0:0
+## Verify that mapping symbols are actually present in the object at expected
+## addresses.
+# RUN: llvm-nm --special-syms %t | FileCheck %s -check-prefix MAPPING_A
+
+# MAPPING_A:      00000004 t $a.1
+# MAPPING_A-NEXT: 00000000 t $d.0
+# MAPPING_A-NEXT: 00000008 t $d.2
+# MAPPING_A-NEXT: 00000000 T foo
+
+# RUN: llvm-mc -filetype=obj -triple=thumbv7-none-linux %s -o %tthumb
+# RUN: llvm-nm --special-syms %tthumb | FileCheck %s -check-prefix MAPPING_T
+
+# MAPPING_T:      00000000 t $d.0
+# MAPPING_T-NEXT: 00000006 t $d.2
+# MAPPING_T-NEXT: 00000004 t $t.1
+# MAPPING_T-NEXT: 00000000 T foo
+
+# RUN: llvm-symbolizer --obj=%t 4 8 | FileCheck %s -check-prefix SYMBOL
+# RUN: llvm-symbolizer --obj=%tthumb 4 8 | FileCheck %s -check-prefix SYMBOL
+
+# SYMBOL:       foo
+# SYMBOL-NEXT:  ??:0:0
+# SYMBOL-EMPTY:
+# SYMBOL-NEXT:  foo
+# SYMBOL-NEXT:  ??:0:0
 
 .globl foo
 foo:

test/tools/llvm-nm/ARM/special-syms.test

@@ -0,0 +1,30 @@
+## Test --special-syms flag for ARM mapping symbols used to mark transitions
+## between ARM code, THUMB code and data ($a, $t, $t).
+#
+# RUN: yaml2obj %s -o %t
+# RUN: llvm-nm %t | count 0
+# RUN: llvm-nm --special-syms %t | FileCheck %s
+
+!ELF
+FileHeader:
+  Class:           ELFCLASS32
+  Data:            ELFDATA2LSB
+  Type:            ET_REL
+  Machine:         EM_ARM
+  Flags:           [ EF_ARM_EABI_VER5 ]
+Sections:
+  - Name:            .text
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_ALLOC, SHF_EXECINSTR ]
+    AddressAlign:    0x4
+Symbols:
+  - Name:            '$d.0'
+    Section:         .text
+  - Name:            '$a.1'
+    Section:         .text
+  - Name:            '$t.1'
+    Section:         .text
+
+# CHECK: 00000000 t $a.1
+# CHECK: 00000000 t $d.0
+# CHECK: 00000000 t $t.1

test/tools/llvm-nm/debug-syms.test

@@ -1,6 +1,6 @@
 # RUN: yaml2obj %s -o %t.o
-# RUN: llvm-nm --special-syms --debug-syms %t.o | FileCheck %s --implicit-check-not {{.}} --check-prefix SYMBOL
-# RUN: llvm-nm --special-syms -a %t.o | FileCheck %s --implicit-check-not {{.}} --check-prefix SYMBOL
+# RUN: llvm-nm --debug-syms %t.o | FileCheck %s --implicit-check-not {{.}} --check-prefix SYMBOL
+# RUN: llvm-nm -a %t.o | FileCheck %s --implicit-check-not {{.}} --check-prefix SYMBOL
 
 # SYMBOL:      0000000000000000 n $a
 # SYMBOL-NEXT: 0000000000000000 n $d

tools/llvm-nm/llvm-nm.cpp

@@ -742,16 +742,6 @@ static void writeFileName(raw_ostream &S, StringRef ArchiveName,
   }
 }
 
-static bool isSpecialSym(SymbolicFile &Obj, StringRef Name) {
-  auto *ELFObj = dyn_cast<ELFObjectFileBase>(&Obj);
-  if (!ELFObj)
-    return false;
-  uint16_t EMachine = ELFObj->getEMachine();
-  if (EMachine != ELF::EM_ARM && EMachine != ELF::EM_AARCH64)
-    return false;
-  return !Name.empty() && Name[0] == '$';
-}
-
 static void sortAndPrintSymbolList(SymbolicFile &Obj, bool printName,
                                    StringRef ArchiveName,
                                    StringRef ArchitectureName) {
@@ -840,9 +830,10 @@ static void sortAndPrintSymbolList(SymbolicFile &Obj, bool printName,
     bool Undefined = SymFlags & SymbolRef::SF_Undefined;
     bool Global = SymFlags & SymbolRef::SF_Global;
     bool Weak = SymFlags & SymbolRef::SF_Weak;
+    bool FormatSpecific = SymFlags & SymbolRef::SF_FormatSpecific;
     if ((!Undefined && UndefinedOnly) || (Undefined && DefinedOnly) ||
         (!Global && ExternalOnly) || (Weak && NoWeakSymbols) ||
-        (!SpecialSyms && isSpecialSym(Obj, Name)))
+        (FormatSpecific && !(SpecialSyms || DebugSyms)))
       continue;
     if (PrintFileName)
       writeFileName(outs(), ArchiveName, ArchitectureName);
@@ -1812,7 +1803,14 @@ static void dumpSymbolNamesFromObject(SymbolicFile &Obj, bool printName,
         error(SymFlagsOrErr.takeError(), Obj.getFileName());
         return;
       }
-      if (!DebugSyms && (*SymFlagsOrErr & SymbolRef::SF_FormatSpecific))
+
+      // Don't drop format specifc symbols for ARM and AArch64 ELF targets, they
+      // are used to repesent mapping symbols and needed to honor the
+      // --special-syms option.
+      auto *ELFObj = dyn_cast<ELFObjectFileBase>(&Obj);
+      if ((!ELFObj || (ELFObj->getEMachine() != ELF::EM_ARM &&
+                       ELFObj->getEMachine() != ELF::EM_AARCH64)) &&
+          !DebugSyms && (*SymFlagsOrErr & SymbolRef::SF_FormatSpecific))
         continue;
       if (WithoutAliases && (*SymFlagsOrErr & SymbolRef::SF_Indirect))
         continue;