[X86][APX] Suppress EGPR/NDD instructions for relocations

clang/CMakeLists.txt

@@ -219,6 +219,9 @@ set(ENABLE_LINKER_BUILD_ID OFF CACHE BOOL "pass --build-id to ld")
 set(ENABLE_X86_RELAX_RELOCATIONS ON CACHE BOOL
     "enable x86 relax relocations by default")
 
+set(ENABLE_X86_APX_RELAX_RELOCATIONS OFF CACHE BOOL
+    "Enable x86 APX relax relocations by default")
+
 set(PPC_LINUX_DEFAULT_IEEELONGDOUBLE OFF CACHE BOOL
     "Enable IEEE binary128 as default long double format on PowerPC Linux.")
 

clang/cmake/caches/Fuchsia-stage2.cmake

@@ -49,6 +49,7 @@ set(CLANG_PLUGIN_SUPPORT OFF CACHE BOOL "")
 
 set(ENABLE_LINKER_BUILD_ID ON CACHE BOOL "")
 set(ENABLE_X86_RELAX_RELOCATIONS ON CACHE BOOL "")
+set(ENABLE_X86_APX_RELAX_RELOCATIONS OFF CACHE BOOL "")
 
 # TODO(#67176): relative-vtables doesn't play well with different default
 # visibilities. Making everything hidden visibility causes other complications

clang/cmake/caches/Fuchsia.cmake

@@ -89,6 +89,7 @@ set(CLANG_PLUGIN_SUPPORT OFF CACHE BOOL "")
 
 set(ENABLE_LINKER_BUILD_ID ON CACHE BOOL "")
 set(ENABLE_X86_RELAX_RELOCATIONS ON CACHE BOOL "")
+set(ENABLE_X86_APX_RELAX_RELOCATIONS OFF CACHE BOOL "")
 
 set(LLVM_ENABLE_ASSERTIONS ON CACHE BOOL "")
 set(LLVM_ENABLE_BACKTRACES ON CACHE BOOL "")

clang/include/clang/Basic/CodeGenOptions.def

@@ -201,6 +201,7 @@ CODEGENOPT(UniqueInternalLinkageNames, 1, 0) ///< Internal Linkage symbols get u
 CODEGENOPT(SplitMachineFunctions, 1, 0) ///< Split machine functions using profile information.
 CODEGENOPT(PPCUseFullRegisterNames, 1, 0) ///< Print full register names in assembly
 CODEGENOPT(X86RelaxRelocations, 1, 1) ///< -Wa,-mrelax-relocations={yes,no}
+CODEGENOPT(X86APXRelaxRelocations, 1, 0) ///< -Wa,-mrelax-relocations={yes,no}
 CODEGENOPT(X86Sse2Avx        , 1, 0)   ///< -Wa,-msse2avx
 
 /// When false, this attempts to generate code as if the result of an

clang/include/clang/Config/config.h.cmake

@@ -72,6 +72,9 @@
 /* enable x86 relax relocations by default */
 #cmakedefine01 ENABLE_X86_RELAX_RELOCATIONS
 
+/* enable x86 APX relax relocations by default */
+#cmakedefine01 ENABLE_X86_APX_RELAX_RELOCATIONS
+
 /* Enable IEEE binary128 as default long double format on PowerPC Linux. */
 #cmakedefine01 PPC_LINUX_DEFAULT_IEEELONGDOUBLE
 

clang/include/clang/Driver/Options.td

@@ -7442,6 +7442,9 @@ def mmapsyms_implicit : Flag<["-"], "mmapsyms=implicit">,
 def mrelax_relocations_no : Flag<["-"], "mrelax-relocations=no">,
     HelpText<"Disable x86 relax relocations">,
     MarshallingInfoNegativeFlag<CodeGenOpts<"X86RelaxRelocations">>;
+def mapx_relax_relocations_yes : Flag<["-"], "mapx-relax-relocations=yes">,
+    HelpText<"Enable x86 APX relax relocations">,
+    MarshallingInfoNegativeFlag<CodeGenOpts<"X86APXRelaxRelocations">>;
 def msave_temp_labels : Flag<["-"], "msave-temp-labels">,
   HelpText<"Save temporary labels in the symbol table. "
            "Note this may change .s semantics and shouldn't generally be used "

clang/include/clang/Driver/ToolChain.h

@@ -473,6 +473,9 @@ class ToolChain {
   /// Check whether to enable x86 relax relocations by default.
   virtual bool useRelaxRelocations() const;
 
+  /// Check whether to enable x86 APX relax relocations by default.
+  virtual bool useAPXRelaxRelocations() const;
+
   /// Check whether use IEEE binary128 as long double format by default.
   bool defaultToIEEELongDouble() const;
 

clang/lib/CodeGen/BackendUtil.cpp

@@ -513,6 +513,7 @@ static bool initTargetOptions(const CompilerInstance &CI,
   Options.MCOptions.Crel = CodeGenOpts.Crel;
   Options.MCOptions.ImplicitMapSyms = CodeGenOpts.ImplicitMapSyms;
   Options.MCOptions.X86RelaxRelocations = CodeGenOpts.X86RelaxRelocations;
+  Options.MCOptions.X86APXRelaxRelocations = CodeGenOpts.X86APXRelaxRelocations;
   Options.MCOptions.CompressDebugSections =
       CodeGenOpts.getCompressDebugSections();
   if (CodeGenOpts.OutputAsmVariant != 3) // 3 (default): not specified

clang/lib/Driver/ToolChain.cpp

@@ -192,6 +192,10 @@ bool ToolChain::useRelaxRelocations() const {
   return ENABLE_X86_RELAX_RELOCATIONS;
 }
 
+bool ToolChain::useAPXRelaxRelocations() const {
+  return ENABLE_X86_APX_RELAX_RELOCATIONS;
+}
+
 bool ToolChain::defaultToIEEELongDouble() const {
   return PPC_LINUX_DEFAULT_IEEELONGDOUBLE && getTriple().isOSLinux();
 }

clang/lib/Driver/ToolChains/Clang.cpp

@@ -2602,6 +2602,8 @@ static void CollectArgsForIntegratedAssembler(Compilation &C,
   bool Crel = false, ExperimentalCrel = false;
   bool ImplicitMapSyms = false;
   bool UseRelaxRelocations = C.getDefaultToolChain().useRelaxRelocations();
+  bool UseAPXRelaxRelocations =
+      C.getDefaultToolChain().useAPXRelaxRelocations();
   bool UseNoExecStack = false;
   bool Msa = false;
   const char *MipsTargetFeature = nullptr;
@@ -2663,6 +2665,12 @@ static void CollectArgsForIntegratedAssembler(Compilation &C,
           checkArg(IsELF, {"yes", "no"});
           continue;
         }
+        if (Equal.first == "-mapx-relax-relocations" ||
+            Equal.first == "--mapx-relax-relocations") {
+          UseAPXRelaxRelocations = Equal.second == "yes";
+          checkArg(IsELF, {"yes", "no"});
+          continue;
+        }
         if (Value == "-msse2avx") {
           CmdArgs.push_back("-msse2avx");
           continue;
@@ -2874,6 +2882,8 @@ static void CollectArgsForIntegratedAssembler(Compilation &C,
     CmdArgs.push_back("-mmsa");
   if (!UseRelaxRelocations)
     CmdArgs.push_back("-mrelax-relocations=no");
+  if (UseAPXRelaxRelocations)
+    CmdArgs.push_back("-mapx-relax-relocations=yes");
   if (UseNoExecStack)
     CmdArgs.push_back("-mnoexecstack");
   if (MipsTargetFeature != nullptr) {

clang/test/Driver/relax.s

@@ -4,11 +4,20 @@
 // CHECK: "-cc1as"
 // CHECK: "-mrelax-relocations=no"
 
+// RUN: %clang -### -c --target=x86_64-pc-linux -integrated-as -Wa,--mapx-relax-relocations=yes %s 2>&1 | FileCheck %s --check-prefix=APXREL_OPTION
+
+// APXREL_OPTION: "-cc1as"
+// APXREL_OPTION: "-mapx-relax-relocations=yes"
+
+// RUN: %clang -cc1as -triple x86_64-pc-linux %s -o %t -filetype obj -mapx-relax-relocations=yes
+// RUN: llvm-readobj -r %t | FileCheck --check-prefix=APXREL %s
 // RUN: %clang -cc1as -triple x86_64-pc-linux %s -o %t -filetype obj
-// RUN: llvm-readobj -r %t | FileCheck --check-prefix=REL %s
+// RUN: llvm-readobj -r %t | FileCheck --check-prefix=NOAPXREL %s
 
-// REL: R_X86_64_REX_GOTPCRELX foo
-// REL: R_X86_64_CODE_4_GOTPCRELX foo
+// APXREL: R_X86_64_REX_GOTPCRELX foo
+// APXREL: R_X86_64_CODE_4_GOTPCRELX foo
+// NOAPXREL: R_X86_64_REX_GOTPCRELX foo
+// NOAPXREL: R_X86_64_GOTPCREL foo
 
         movq	foo@GOTPCREL(%rip), %rax
         movq	foo@GOTPCREL(%rip), %r16

clang/tools/driver/cc1as_main.cpp

@@ -171,6 +171,8 @@ struct AssemblerInvocation {
   LLVM_PREFERRED_TYPE(bool)
   unsigned X86RelaxRelocations : 1;
   LLVM_PREFERRED_TYPE(bool)
+  unsigned X86APXRelaxRelocations : 1;
+  LLVM_PREFERRED_TYPE(bool)
   unsigned X86Sse2Avx : 1;
 
   /// The name of the relocation model to use.
@@ -216,6 +218,7 @@ struct AssemblerInvocation {
     Crel = false;
     ImplicitMapsyms = 0;
     X86RelaxRelocations = 0;
+    X86APXRelaxRelocations = 0;
     X86Sse2Avx = 0;
   }
 
@@ -388,6 +391,7 @@ bool AssemblerInvocation::CreateFromArgs(AssemblerInvocation &Opts,
   Opts.Crel = Args.hasArg(OPT_crel);
   Opts.ImplicitMapsyms = Args.hasArg(OPT_mmapsyms_implicit);
   Opts.X86RelaxRelocations = !Args.hasArg(OPT_mrelax_relocations_no);
+  Opts.X86APXRelaxRelocations = Args.hasArg(OPT_mapx_relax_relocations_yes);
   Opts.X86Sse2Avx = Args.hasArg(OPT_msse2avx);
 
   Opts.AsSecureLogFile = Args.getLastArgValue(OPT_as_secure_log_file);
@@ -449,6 +453,7 @@ static bool ExecuteAssemblerImpl(AssemblerInvocation &Opts,
   MCOptions.Crel = Opts.Crel;
   MCOptions.ImplicitMapSyms = Opts.ImplicitMapsyms;
   MCOptions.X86RelaxRelocations = Opts.X86RelaxRelocations;
+  MCOptions.X86APXRelaxRelocations = Opts.X86APXRelaxRelocations;
   MCOptions.X86Sse2Avx = Opts.X86Sse2Avx;
   MCOptions.CompressDebugSections = Opts.CompressDebugSections;
   MCOptions.AsSecureLogFile = Opts.AsSecureLogFile;

lld/ELF/Arch/X86_64.cpp

@@ -912,9 +912,9 @@ void X86_64::relocate(uint8_t *loc, const Relocation &rel, uint64_t val) const {
   case R_X86_64_CODE_4_GOTPC32_TLSDESC:
   case R_X86_64_TLSDESC_CALL:
   case R_X86_64_TLSGD:
-    if (rel.expr == R_RELAX_TLS_GD_TO_LE) {
+    if (rel.expr == R_RELAX_TLS_GD_TO_LE && ctx.arg.relax) {
       relaxTlsGdToLe(loc, rel, val);
-    } else if (rel.expr == R_RELAX_TLS_GD_TO_IE) {
+    } else if (rel.expr == R_RELAX_TLS_GD_TO_IE && ctx.arg.relax) {
       relaxTlsGdToIe(loc, rel, val);
     } else {
       checkInt(ctx, loc, val, 32, rel);
@@ -932,7 +932,7 @@ void X86_64::relocate(uint8_t *loc, const Relocation &rel, uint64_t val) const {
   case R_X86_64_GOTTPOFF:
   case R_X86_64_CODE_4_GOTTPOFF:
   case R_X86_64_CODE_6_GOTTPOFF:
-    if (rel.expr == R_RELAX_TLS_IE_TO_LE) {
+    if (rel.expr == R_RELAX_TLS_IE_TO_LE && ctx.arg.relax) {
       relaxTlsIeToLe(loc, rel, val);
     } else {
       checkInt(ctx, loc, val, 32, rel);

lld/test/ELF/tls-opt.s

@@ -1,44 +1,84 @@
 // REQUIRES: x86
-// RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %s -o %t.o
+// RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %s -o %t.o -x86-apx-relax-relocations=true
 // RUN: ld.lld %t.o -o %t1
 // RUN: llvm-readobj -r %t1 | FileCheck --check-prefix=NORELOC %s
-// RUN: llvm-objdump --no-print-imm-hex -d --no-show-raw-insn %t1 | FileCheck --check-prefix=DISASM %s
+// RUN: llvm-objdump --no-print-imm-hex -d --no-show-raw-insn %t1 | FileCheck --check-prefixes=DISASM,APXRELAX %s
+
+// RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %s -o %t.o
+// RUN: ld.lld %t.o -o %t1 --no-relax
+// RUN: llvm-readobj -r %t1 | FileCheck --check-prefix=NORELOC %s
+// RUN: llvm-objdump --no-print-imm-hex -d --no-show-raw-insn %t1 | FileCheck --check-prefixes=DISASM,NOAPXRELAX %s
 
 // NORELOC:      Relocations [
 // NORELOC-NEXT: ]
 
 // DISASM:      <_start>:
-// DISASM-NEXT:   movq $-8, %rax
-// DISASM-NEXT:   movq $-8, %r15
-// DISASM-NEXT:   leaq -8(%rax), %rax
-// DISASM-NEXT:   leaq -8(%r15), %r15
-// DISASM-NEXT:   addq $-8, %rsp
-// DISASM-NEXT:   addq $-8, %r12
-// DISASM-NEXT:   movq $-4, %rax
-// DISASM-NEXT:   movq $-4, %r15
-// DISASM-NEXT:   leaq -4(%rax), %rax
-// DISASM-NEXT:   leaq -4(%r15), %r15
-// DISASM-NEXT:   addq $-4, %rsp
-// DISASM-NEXT:   addq $-4, %r12
+// APXRELAX-NEXT:   movq $-8, %rax
+// APXRELAX-NEXT:   movq $-8, %r15
+// APXRELAX-NEXT:   leaq -8(%rax), %rax
+// APXRELAX-NEXT:   leaq -8(%r15), %r15
+// APXRELAX-NEXT:   addq $-8, %rsp
+// APXRELAX-NEXT:   addq $-8, %r12
+// APXRELAX-NEXT:   movq $-4, %rax
+// APXRELAX-NEXT:   movq $-4, %r15
+// APXRELAX-NEXT:   leaq -4(%rax), %rax
+// APXRELAX-NEXT:   leaq -4(%r15), %r15
+// APXRELAX-NEXT:   addq $-4, %rsp
+// APXRELAX-NEXT:   addq $-4, %r12
+
+// NOAPXRELAX-NEXT:   movq -12(%rip), %rax
+// NOAPXRELAX-NEXT:   movq -12(%rip), %r15
+// NOAPXRELAX-NEXT:   addq -12(%rip), %rax
+// NOAPXRELAX-NEXT:   addq -12(%rip), %r15
+// NOAPXRELAX-NEXT:   addq -12(%rip), %rsp
+// NOAPXRELAX-NEXT:   addq -12(%rip), %r12
+// NOAPXRELAX-NEXT:   movq -8(%rip), %rax
+// NOAPXRELAX-NEXT:   movq -8(%rip), %r15
+// NOAPXRELAX-NEXT:   addq -8(%rip), %rax
+// NOAPXRELAX-NEXT:   addq -8(%rip), %r15
+// NOAPXRELAX-NEXT:   addq -8(%rip), %rsp
+// NOAPXRELAX-NEXT:   addq -8(%rip), %r12
+
 # EGPR
-// DISASM-NEXT:   movq $-8, %r16
-// DISASM-NEXT:   movq $-8, %r20
-// DISASM-NEXT:   movq $-4, %r16
-// DISASM-NEXT:   addq $-8, %r16
-// DISASM-NEXT:   addq $-8, %r28
-// DISASM-NEXT:   addq $-4, %r16
+// APXRELAX-NEXT:   movq $-8, %r16
+// APXRELAX-NEXT:   movq $-8, %r20
+// APXRELAX-NEXT:   movq $-4, %r16
+// APXRELAX-NEXT:   addq $-8, %r16
+// APXRELAX-NEXT:   addq $-8, %r28
+// APXRELAX-NEXT:   addq $-4, %r16
+
+// NOAPXRELAX-NEXT: movq -12(%rip), %r16
+// NOAPXRELAX-NEXT: movq -12(%rip), %r20
+// NOAPXRELAX-NEXT: movq -8(%rip), %r16
+// NOAPXRELAX-NEXT: addq -12(%rip), %r16
+// NOAPXRELAX-NEXT: addq -12(%rip), %r28
+// NOAPXRELAX-NEXT: addq -8(%rip), %r16
+
 # NDD
-// DISASM-NEXT:   addq $-8, %r16, %r16
-// DISASM-NEXT:   addq $-8, %r16, %r20
-// DISASM-NEXT:   addq $-8, %r16, %rax
-// DISASM-NEXT:   addq $-8, %rax, %r16
-// DISASM-NEXT:   addq $-8, %r8, %r16
-// DISASM-NEXT:   addq $-8, %rax, %r12
+// APXRELAX-NEXT:   addq $-8, %r16, %r16
+// APXRELAX-NEXT:   addq $-8, %r16, %r20
+// APXRELAX-NEXT:   addq $-8, %r16, %rax
+// APXRELAX-NEXT:   addq $-8, %rax, %r16
+// APXRELAX-NEXT:   addq $-8, %r8, %r16
+// APXRELAX-NEXT:   addq $-8, %rax, %r12
+
+// NOAPXRELAX-NEXT:   addq -12(%rip), %r16, %r16
+// NOAPXRELAX-NEXT:   addq -12(%rip), %r16, %r20
+// NOAPXRELAX-NEXT:   addq -12(%rip), %r16, %rax
+// NOAPXRELAX-NEXT:   addq -12(%rip), %rax, %r16
+// NOAPXRELAX-NEXT:   addq %r8, -12(%rip), %r16
+// NOAPXRELAX-NEXT:   addq -12(%rip), %rax, %r12
+
 # NDD + NF
-// DISASM-NEXT:   {nf} addq $-8, %r8, %r16
-// DISASM-NEXT:   {nf} addq $-8, %rax, %r12
+// APXRELAX-NEXT:   {nf} addq $-8, %r8, %r16
+// APXRELAX-NEXT:   {nf} addq $-8, %rax, %r12
+
+// NOAPXRELAX-NEXT:   {nf} addq %r8, -12(%rip), %r16
+// NOAPXRELAX-NEXT:   {nf} addq -12(%rip), %rax, %r12
+
 # NF
-// DISASM-NEXT:   {nf} addq $-8, %r12
+// APXRELAX-NEXT:   {nf} addq $-8, %r12
+// NOAPXRELAX-NEXT:   {nf} addq -12(%rip), %r12
 
 // LD to LE:
 // DISASM-NEXT:   movq %fs:0, %rax
@@ -47,10 +87,15 @@
 // DISASM-NEXT:   leaq -4(%rax), %rcx
 
 // GD to LE:
-// DISASM-NEXT:   movq %fs:0, %rax
-// DISASM-NEXT:   leaq -8(%rax), %rax
-// DISASM-NEXT:   movq %fs:0, %rax
-// DISASM-NEXT:   leaq -4(%rax), %rax
+// APXRELAX-NEXT:   movq %fs:0, %rax
+// APXRELAX-NEXT:   leaq -8(%rax), %rax
+// APXRELAX-NEXT:   movq %fs:0, %rax
+// APXRELAX-NEXT:   leaq -4(%rax), %rax
+
+// NOAPXRELAX-NEXT:   leaq -12(%rip), %rdi
+// NOAPXRELAX-NEXT:   callq 0x20126c
+// NOAPXRELAX-NEXT:   leaq -8(%rip), %rdi
+// NOAPXRELAX-NEXT:   callq 0x20127c
 
 // LD to LE:
 // DISASM:     <_DTPOFF64_1>:

lld/test/ELF/x86-64-gotpc-no-relax-err.s

@@ -1,7 +1,10 @@
 # REQUIRES: x86
 # RUN: split-file %s %t
+# RUN: llvm-mc -filetype=obj -triple=x86_64 %t/a.s -o %t/a.o -x86-apx-relax-relocations=true
+# RUN: not ld.lld --no-relax -T %t/lds %t/a.o -o /dev/null 2>&1 | FileCheck %s --implicit-check-not=error: --check-prefixes=CHECK,APXRELAX
+
 # RUN: llvm-mc -filetype=obj -triple=x86_64 %t/a.s -o %t/a.o
-# RUN: not ld.lld --no-relax -T %t/lds %t/a.o -o /dev/null 2>&1 | FileCheck %s --implicit-check-not=error:
+# RUN: not ld.lld --no-relax -T %t/lds %t/a.o -o /dev/null 2>&1 | FileCheck %s --implicit-check-not=error: --check-prefixes=CHECK,NOAPXRELAX
 
 ## Test diagnostics for unrelaxed GOTPCRELX overflows. In addition, test that there is no
 ## `>>> defined in` for linker synthesized __stop_* symbols (there is no
@@ -13,9 +16,11 @@
 # CHECK-NEXT: error: {{.*}}:(.text+0x9): relocation R_X86_64_REX_GOTPCRELX out of range: 2147483659 is not in [-2147483648, 2147483647]; references '__stop_data'
 # CHECK-NEXT: >>> defined in <internal>
 # CHECK-EMPTY:
-# CHECK-NEXT: error: {{.*}}:(.text+0x11): relocation R_X86_64_CODE_4_GOTPCRELX out of range: 2147483651 is not in [-2147483648, 2147483647]; references '__stop_data'
+# APXRELAX-NEXT: error: {{.*}}:(.text+0x11): relocation R_X86_64_CODE_4_GOTPCRELX out of range: 2147483651 is not in [-2147483648, 2147483647]; references '__stop_data'
+# NOAPXRELAX-NEXT: error: {{.*}}:(.text+0x11): relocation R_X86_64_GOTPCREL out of range: 2147483651 is not in [-2147483648, 2147483647]; references '__stop_data'
 # CHECK-NEXT: >>> defined in <internal>
 
+
 #--- a.s
   movl __stop_data@GOTPCREL(%rip), %eax  # out of range
   movq __stop_data@GOTPCREL(%rip), %rax  # out of range