[X86] Zero out the 32-bit GPRs explicitly

[void]

Summary

This should ensure that only the 32-bit xors are emitted, and not the
64-bit xors.

llvm/lib/Target/X86/X86FrameLowering.cpp

for (unsigned i = 0; i != NumFPRegs; ++i)
       BuildMI(MBB, MBBI, DL, TII.get(X86::LD_F0));
 
     for (unsigned i = 0; i != NumFPRegs; ++i)
       BuildMI(MBB, MBBI, DL, TII.get(X86::ST_FPrr)).addReg(X86::ST0);
     break;
   }
 
   // For GPRs, we only care to clear out the 32-bit register.
+  BitVector GPRsToZero(TRI->getNumRegs());
   for (MCRegister Reg : RegsToZero.set_bits())
     if (TRI->isGeneralPurposeRegister(MF, Reg)) {
-      Reg = getX86SubSuperRegisterOrZero(Reg, 32);
-      for (const MCPhysReg &Reg : TRI->sub_and_superregs_inclusive(Reg))
-        RegsToZero.reset(Reg);
-      RegsToZero.set(Reg);
+      GPRsToZero.set(getX86SubSuperRegisterOrZero(Reg, 32));
     }
 
+  for (MCRegister Reg : GPRsToZero.set_bits())
+    BuildMI(MBB, MBBI, DL, TII.get(X86::XOR32rr), Reg)
+        .addReg(Reg, RegState::Undef)
+        .addReg(Reg, RegState::Undef);
+
   // Zero out registers.
   for (MCRegister Reg : RegsToZero.set_bits()) {
     if (ST.hasMMX() && X86::VR64RegClass.contains(Reg))
       // FIXME: Ignore MMX registers?
       continue;
 
     unsigned XorOp;
-    if (TRI->isGeneralPurposeRegister(MF, Reg)) {
-      XorOp = X86::XOR32rr;
-    } else if (X86::VR128RegClass.contains(Reg)) {
+    if (X86::VR128RegClass.contains(Reg)) {
       // XMM#
       if (!ST.hasSSE1())
         continue;
       XorOp = X86::PXORrr;
     } else if (X86::VR256RegClass.contains(Reg)) {
       // YMM#
       if (!ST.hasAVX())
         continue;

llvm/test/CodeGen/X86/zero-call-used-regs.ll

 ;
 ; X86-64-LABEL: all_arg:
 ; X86-64:       # %bb.0: # %entry
 ; X86-64-NEXT:    movl %edi, %eax
 ; X86-64-NEXT:    xorl %ecx, %ecx
 ; X86-64-NEXT:    xorl %edi, %edi
 ; X86-64-NEXT:    xorl %edx, %edx
 ; X86-64-NEXT:    xorl %esi, %esi
+; X86-64-NEXT:    xorl %r8d, %r8d
+; X86-64-NEXT:    xorl %r9d, %r9d
 ; X86-64-NEXT:    xorps %xmm0, %xmm0
 ; X86-64-NEXT:    xorps %xmm1, %xmm1
 ; X86-64-NEXT:    xorps %xmm2, %xmm2
 ; X86-64-NEXT:    xorps %xmm3, %xmm3
 ; X86-64-NEXT:    xorps %xmm4, %xmm4
 ; X86-64-NEXT:    xorps %xmm5, %xmm5
 ; X86-64-NEXT:    xorps %xmm6, %xmm6
 ; X86-64-NEXT:    xorps %xmm7, %xmm7
-; X86-64-NEXT:    xorl %r8d, %r8d
-; X86-64-NEXT:    xorl %r9d, %r9d
 ; X86-64-NEXT:    retq
 
 entry:
   ret i32 %x
 }
 
 define dso_local i32 @all(i32 returned %x) local_unnamed_addr #0 "zero-call-used-regs"="all" {
 ; I386-LABEL: all:

 ; X86-64-NEXT:    fstp %st(0)
 ; X86-64-NEXT:    fstp %st(0)
 ; X86-64-NEXT:    xorl %ebp, %ebp
 ; X86-64-NEXT:    xorl %ebx, %ebx
 ; X86-64-NEXT:    xorl %ecx, %ecx
 ; X86-64-NEXT:    xorl %edi, %edi
 ; X86-64-NEXT:    xorl %edx, %edx
 ; X86-64-NEXT:    xorl %esi, %esi
+; X86-64-NEXT:    xorl %r8d, %r8d
+; X86-64-NEXT:    xorl %r9d, %r9d
+; X86-64-NEXT:    xorl %r10d, %r10d
+; X86-64-NEXT:    xorl %r11d, %r11d
+; X86-64-NEXT:    xorl %r12d, %r12d
+; X86-64-NEXT:    xorl %r13d, %r13d
+; X86-64-NEXT:    xorl %r14d, %r14d
+; X86-64-NEXT:    xorl %r15d, %r15d
 ; X86-64-NEXT:    xorps %xmm0, %xmm0
 ; X86-64-NEXT:    xorps %xmm1, %xmm1
 ; X86-64-NEXT:    xorps %xmm2, %xmm2
 ; X86-64-NEXT:    xorps %xmm3, %xmm3
 ; X86-64-NEXT:    xorps %xmm4, %xmm4
 ; X86-64-NEXT:    xorps %xmm5, %xmm5
 ; X86-64-NEXT:    xorps %xmm6, %xmm6
 ; X86-64-NEXT:    xorps %xmm7, %xmm7
 ; X86-64-NEXT:    xorps %xmm8, %xmm8
 ; X86-64-NEXT:    xorps %xmm9, %xmm9
 ; X86-64-NEXT:    xorps %xmm10, %xmm10
 ; X86-64-NEXT:    xorps %xmm11, %xmm11
 ; X86-64-NEXT:    xorps %xmm12, %xmm12
 ; X86-64-NEXT:    xorps %xmm13, %xmm13
 ; X86-64-NEXT:    xorps %xmm14, %xmm14
 ; X86-64-NEXT:    xorps %xmm15, %xmm15
-; X86-64-NEXT:    xorl %r8d, %r8d
-; X86-64-NEXT:    xorl %r9d, %r9d
-; X86-64-NEXT:    xorl %r10d, %r10d
-; X86-64-NEXT:    xorl %r11d, %r11d
-; X86-64-NEXT:    xorl %r12d, %r12d
-; X86-64-NEXT:    xorl %r13d, %r13d
-; X86-64-NEXT:    xorl %r14d, %r14d
-; X86-64-NEXT:    xorl %r15d, %r15d
 ; X86-64-NEXT:    retq
 
 entry:
   ret i32 %x
 }
 
 ; Don't emit zeroing registers in "main" function.
 define dso_local i32 @main() local_unnamed_addr #1 {