[X86][APX] Fix the assertion of NF instruction with relocation

The assertion should be raised only for the NF instructions with GOTTPOFF
relocation.

Author: fzou1

llvm/lib/Target/X86/X86SuppressAPXForReloc.cpp

@@ -155,8 +155,14 @@ static bool handleNDDOrNFInstructions(MachineFunction &MF,
       switch (Opcode) {
       case X86::ADD64rm_NF:
       case X86::ADD64mr_NF_ND:
-      case X86::ADD64rm_NF_ND:
-        llvm_unreachable("Unexpected NF instruction!");
+      case X86::ADD64rm_NF_ND: {
+        int MemOpNo = X86II::getMemoryOperandNo(MI.getDesc().TSFlags) +
+                      X86II::getOperandBias(MI.getDesc());
+        const MachineOperand &MO = MI.getOperand(X86::AddrDisp + MemOpNo);
+        if (MO.getTargetFlags() == X86II::MO_GOTTPOFF)
+          llvm_unreachable("Unexpected NF instruction!");
+        break;
+      }
       case X86::ADD64rm_ND: {
         int MemOpNo = X86II::getMemoryOperandNo(MI.getDesc().TSFlags) +
                       X86II::getOperandBias(MI.getDesc());

llvm/test/CodeGen/X86/apx/check-nf-in-suppress-reloc-pass.ll

@@ -0,0 +1,96 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc < %s -mtriple=x86_64 -mattr=+nf -verify-machineinstrs | FileCheck %s
+
+; This is to check no assertion raised in X86 Suppress APX for Relocation pass
+; if there is a NF instruction
+
+define fastcc void @foo(i32 %0, i1 %or.cond) {
+; CHECK-LABEL: foo:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    pushq %rbp
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    pushq %r15
+; CHECK-NEXT:    .cfi_def_cfa_offset 24
+; CHECK-NEXT:    pushq %r14
+; CHECK-NEXT:    .cfi_def_cfa_offset 32
+; CHECK-NEXT:    pushq %r13
+; CHECK-NEXT:    .cfi_def_cfa_offset 40
+; CHECK-NEXT:    pushq %r12
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
+; CHECK-NEXT:    pushq %rbx
+; CHECK-NEXT:    .cfi_def_cfa_offset 56
+; CHECK-NEXT:    pushq %rax
+; CHECK-NEXT:    .cfi_def_cfa_offset 64
+; CHECK-NEXT:    .cfi_offset %rbx, -56
+; CHECK-NEXT:    .cfi_offset %r12, -48
+; CHECK-NEXT:    .cfi_offset %r13, -40
+; CHECK-NEXT:    .cfi_offset %r14, -32
+; CHECK-NEXT:    .cfi_offset %r15, -24
+; CHECK-NEXT:    .cfi_offset %rbp, -16
+; CHECK-NEXT:    movl %esi, %ebx
+; CHECK-NEXT:    movslq %edi, %r15
+; CHECK-NEXT:    leaq (,%r15,4), %rax
+; CHECK-NEXT:    leaq (%rax,%rax,4), %r14
+; CHECK-NEXT:    movl %r15d, %r12d
+; CHECK-NEXT:    xorl %r13d, %r13d
+; CHECK-NEXT:    xorl %ebp, %ebp
+; CHECK-NEXT:    jmp .LBB0_1
+; CHECK-NEXT:    .p2align 4
+; CHECK-NEXT:  .LBB0_3: # %if.end41
+; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
+; CHECK-NEXT:    leaq (%r12,%rbp), %rdi
+; CHECK-NEXT:    # kill: def $edi killed $edi killed $rdi
+; CHECK-NEXT:    xorl %esi, %esi
+; CHECK-NEXT:    movq %r14, %rdx
+; CHECK-NEXT:    callq *%r13
+; CHECK-NEXT:    incq %rbp
+; CHECK-NEXT:    addq $20, %r14
+; CHECK-NEXT:  .LBB0_1: # %for.body30
+; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    testb $1, %bl
+; CHECK-NEXT:    je .LBB0_3
+; CHECK-NEXT:  # %bb.2: # %if.then37
+; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
+; CHECK-NEXT:    movq %r15, %rax
+; CHECK-NEXT:    addq %rbp, %rax
+; CHECK-NEXT:    movq 0, %rax
+; CHECK-NEXT:    {nf} addq %r15, %rax
+; CHECK-NEXT:    movb $0, (%rbp,%rax)
+; CHECK-NEXT:    jmp .LBB0_3
+entry:
+  %1 = sext i32 %0 to i64
+  br label %for.body30
+
+for.body30:                                       ; preds = %if.end41, %entry
+  %indvars.iv = phi i64 [ %1, %entry ], [ %indvars.iv.next, %if.end41 ]
+  %.pre88 = trunc i64 %indvars.iv to i32
+  br label %if.end16.i
+
+if.then9.i:                                       ; No predecessors!
+  call fastcc void null(ptr null, i32 %.pre88)
+  br label %if.end16.i
+
+if.end16.i:                                       ; preds = %if.then9.i, %for.body30
+  br i1 %or.cond, label %if.then37, label %if.end41
+
+if.then37:                                        ; preds = %if.end16.i
+  %2 = load ptr, ptr null, align 8
+  %arrayidx.i = getelementptr i8, ptr %2, i64 %indvars.iv
+  store i8 0, ptr %arrayidx.i, align 1
+  %3 = icmp eq i64 %indvars.iv, 0
+  br i1 %3, label %if.end41, label %if.then.i65
+
+if.then.i65:                                      ; preds = %if.then37
+  %arraydecay.i = getelementptr [5 x float], ptr null, i64 %indvars.iv, i64 -5
+  %4 = call <5 x float> @llvm.masked.load.v5f32.p0(ptr %arraydecay.i, i32 1, <5 x i1> zeroinitializer, <5 x float> zeroinitializer)
+  br label %if.end41
+
+if.end41:                                         ; preds = %if.then.i65, %if.then37, %if.end16.i
+  %arraydecay44 = getelementptr [5 x float], ptr null, i64 %indvars.iv, i64 0
+  call fastcc void null(i32 %.pre88, i32 0, ptr %arraydecay44)
+  %indvars.iv.next = add i64 %indvars.iv, 1
+  %cmp29 = icmp slt i64 %indvars.iv, 0
+  br label %for.body30
+}
+
+declare <5 x float> @llvm.masked.load.v5f32.p0(ptr captures(none), i32 immarg, <5 x i1>, <5 x float>)