[AARCH64 folding] Do not fold any copy with NZCV

[skatkov]

Summary

There is no instruction to fold NZCV, so, just do not do it.

Without the fix the added test case crashes with an assert
"Mismatched register size in non subreg COPY"

[skatkov]

ping

[danilaml]

LGTM

llvm/lib/Target/AArch64/AArch64InstrInfo.cpp

4440

llvm/lib/Target/AArch64/AArch64InstrInfo.cpp

if (MI.isFullCopy()) {
     if (SrcReg == AArch64::SP && Register::isVirtualRegister(DstReg)) {
       MF.getRegInfo().constrainRegClass(DstReg, &AArch64::GPR64RegClass);
       return nullptr;
     }
     if (DstReg == AArch64::SP && Register::isVirtualRegister(SrcReg)) {
       MF.getRegInfo().constrainRegClass(SrcReg, &AArch64::GPR64RegClass);
       return nullptr;
     }
+    // Nothing can folded with copy from/to NZCV.
+    if (SrcReg == AArch64::NZCV || DstReg == AArch64::NZCV)
+      return nullptr;
   }
 
   // Handle the case where a copy is being spilled or filled but the source
   // and destination register class don't match.  For example:
   //
   //   %0 = COPY %xzr; GPR64common:%0
   //
   // In this case we can still safely fold away the COPY and generate the

llvm/test/CodeGen/AArch64/spill-fold.mir

 # RUN: llc -mtriple=aarch64-none-linux-gnu -run-pass greedy -verify-machineinstrs  -o - %s | FileCheck %s
 --- |
   define i64 @test_subreg_spill_fold() { ret i64 0 }
   define i64 @test_subreg_spill_fold2() { ret i64 0 }
   define i64 @test_subreg_spill_fold3() { ret i64 0 }
   define i64 @test_subreg_fill_fold() { ret i64 0 }
   define double @test_subreg_fill_fold2() { ret double 0.0 }
+  define i64 @test_nzcv_spill_fold() { ret i64 0 }
 ...
 ---
 # CHECK-LABEL: name: test_subreg_spill_fold
 # Ensure that the spilled subreg COPY is eliminated and folded into the spill store.
 name:            test_subreg_spill_fold
 registers:
   - { id: 0, class: gpr64 }
 body:             |
body:             |
   bb.0:
     %0 = COPY $wzr
     INLINEASM &nop, 1, 12, implicit-def dead $x0, 12, implicit-def dead $x1, 12, implicit-def dead $x2, 12, implicit-def dead $x3, 12, implicit-def dead $x4, 12, implicit-def dead $x5, 12, implicit-def dead $x6, 12, implicit-def dead $x7, 12, implicit-def dead $x8, 12, implicit-def dead $x9, 12, implicit-def dead $x10, 12, implicit-def dead $x11, 12, implicit-def dead $x12, 12, implicit-def dead $x13, 12, implicit-def dead $x14, 12, implicit-def dead $x15, 12, implicit-def dead $x16, 12, implicit-def dead $x17, 12, implicit-def dead $x18, 12, implicit-def dead $x19, 12, implicit-def dead $x20, 12, implicit-def dead $x21, 12, implicit-def dead $x22, 12, implicit-def dead $x23, 12, implicit-def dead $x24, 12, implicit-def dead $x25, 12, implicit-def dead $x26, 12, implicit-def dead $x27, 12, implicit-def dead $x28, 12, implicit-def dead $fp, 12, implicit-def dead $lr, 12, implicit-def $sp
     ; CHECK: undef %1.ssub:fpr64 = LDRSui %stack.0, 0 :: (load (s32) from %stack.0)
     undef %1.ssub = COPY %0
     $d0 = COPY %1
     RET_ReallyLR implicit $d0
 ...
+---
+# CHECK-LABEL: name: test_nzcv_spill_fold
+# Ensure that nzcv COPY cannot be folded.
+name:            test_nzcv_spill_fold
+registers:
+  - { id: 0, class: gpr64 }
+body:             |
+  bb.0:
+    ; CHECK: %1:gpr64 = COPY $nzcv
+    ; CHECK: STRXui %1, %stack.0, 0 :: (store (s64) into %stack.0)
+    %0 = COPY $nzcv
+    INLINEASM &nop, 1, 12, implicit-def dead $x0, 12, implicit-def dead $x1, 12, implicit-def dead $x2, 12, implicit-def dead $x3, 12, implicit-def dead $x4, 12, implicit-def dead $x5, 12, implicit-def dead $x6, 12, implicit-def dead $x7, 12, implicit-def dead $x8, 12, implicit-def dead $x9, 12, implicit-def dead $x10, 12, implicit-def dead $x11, 12, implicit-def dead $x12, 12, implicit-def dead $x13, 12, implicit-def dead $x14, 12, implicit-def dead $x15, 12, implicit-def dead $x16, 12, implicit-def dead $x17, 12, implicit-def dead $x18, 12, implicit-def dead $x19, 12, implicit-def dead $x20, 12, implicit-def dead $x21, 12, implicit-def dead $x22, 12, implicit-def dead $x23, 12, implicit-def dead $x24, 12, implicit-def dead $x25, 12, implicit-def dead $x26, 12, implicit-def dead $x27, 12, implicit-def dead $x28, 12, implicit-def dead $fp, 12, implicit-def dead $lr, 12, implicit-def $sp
+    $x0 = COPY %0
+    RET_ReallyLR implicit $x0
+...