[AARCH64 folding] Do not fold any copy with NZCV

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"

Reviewed By: danilaml
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D127294

diff --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp b/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
index 77135de..05fd190 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
@@ -4437,6 +4437,9 @@ MachineInstr *AArch64InstrInfo::foldMemoryOperandImpl(
       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

diff --git a/llvm/test/CodeGen/AArch64/spill-fold.mir b/llvm/test/CodeGen/AArch64/spill-fold.mir
index 624fcc4..02d409d 100644 (file)
--- a/llvm/test/CodeGen/AArch64/spill-fold.mir
+++ b/llvm/test/CodeGen/AArch64/spill-fold.mir
@@ -5,6 +5,7 @@
   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
@@ -80,3 +81,18 @@ body:             |
     $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
+...