[AMDGPU] Ensure non-reserved CSR spilled regs are live-in (llvm#146427) (llvm#3432)

Author: ronlieb

llvm/lib/Target/AMDGPU/SIFrameLowering.cpp

@@ -1160,6 +1160,7 @@ void SIFrameLowering::emitCSRSpillStores(MachineFunction &MF,
   const SIInstrInfo *TII = ST.getInstrInfo();
   const SIRegisterInfo &TRI = TII->getRegisterInfo();
   const MCRegisterInfo *MCRI = MF.getContext().getRegisterInfo();
+  MachineRegisterInfo &MRI = MF.getRegInfo();
 
   // Spill Whole-Wave Mode VGPRs. Save only the inactive lanes of the scratch
   // registers. However, save all lanes of callee-saved VGPRs. Due to this, we
@@ -1188,6 +1189,12 @@ void SIFrameLowering::emitCSRSpillStores(MachineFunction &MF,
         }
       };
 
+  for (const Register Reg : make_first_range(WWMScratchRegs)) {
+    if (!MRI.isReserved(Reg)) {
+      MRI.addLiveIn(Reg);
+      MBB.addLiveIn(Reg);
+    }
+  }
   StoreWWMRegisters(WWMScratchRegs);
   if (!WWMCalleeSavedRegs.empty()) {
     if (ScratchExecCopy) {

llvm/test/CodeGen/AMDGPU/bug-undef-spilled-agpr.mir

@@ -0,0 +1,103 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx908 -run-pass=si-lower-sgpr-spills,greedy,si-lower-wwm-copies,virtregrewriter,prologepilog -verify-machineinstrs -o - %s | FileCheck -check-prefix=GCN %s
+
+---
+name:            widget
+tracksRegLiveness: true
+frameInfo:
+  adjustsStack:    true
+stack:
+  - { id: 0, type: spill-slot, size: 4, alignment: 4, stack-id: sgpr-spill }
+  - { id: 1, type: spill-slot, size: 4, alignment: 4, stack-id: sgpr-spill }
+machineFunctionInfo:
+  hasSpilledSGPRs: true
+  scratchRSrcReg:  '$sgpr0_sgpr1_sgpr2_sgpr3'
+  stackPtrOffsetReg: '$sgpr32'
+body:             |
+  ; GCN-LABEL: name: widget
+  ; GCN: bb.0:
+  ; GCN-NEXT:   successors: %bb.1(0x80000000)
+  ; GCN-NEXT:   liveins: $sgpr12, $sgpr13, $sgpr14, $sgpr15, $agpr0
+  ; GCN-NEXT: {{  $}}
+  ; GCN-NEXT:   frame-setup CFI_INSTRUCTION llvm_def_aspace_cfa $sgpr32, 0, 6
+  ; GCN-NEXT:   frame-setup CFI_INSTRUCTION llvm_register_pair $pc_reg, $sgpr30, 32, $sgpr31, 32
+  ; GCN-NEXT:   frame-setup CFI_INSTRUCTION undefined $agpr0
+  ; GCN-NEXT:   frame-setup CFI_INSTRUCTION undefined $sgpr14
+  ; GCN-NEXT:   $sgpr4_sgpr5 = S_XOR_SAVEEXEC_B64 -1, implicit-def $exec, implicit-def dead $scc, implicit $exec
+  ; GCN-NEXT:   $vgpr63 = V_ACCVGPR_READ_B32_e64 $agpr0, implicit $exec
+  ; GCN-NEXT:   BUFFER_STORE_DWORD_OFFSET $vgpr63, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 0, 0, 0, implicit $exec :: (store (s32) into %stack.2, addrspace 5)
+  ; GCN-NEXT:   frame-setup CFI_INSTRUCTION offset $agpr0, 0
+  ; GCN-NEXT:   $exec = S_MOV_B64 -1
+  ; GCN-NEXT:   BUFFER_STORE_DWORD_OFFSET killed $vgpr62, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 4, 0, 0, implicit $exec :: (store (s32) into %stack.3, addrspace 5)
+  ; GCN-NEXT:   frame-setup CFI_INSTRUCTION offset $vgpr62, 256
+  ; GCN-NEXT:   $exec = S_MOV_B64 killed $sgpr4_sgpr5
+  ; GCN-NEXT:   renamable $vgpr62 = IMPLICIT_DEF
+  ; GCN-NEXT:   $vgpr62 = SI_SPILL_S32_TO_VGPR $sgpr15, 0, killed $vgpr62
+  ; GCN-NEXT:   $noreg = S_OR_SAVEEXEC_B64 -1, implicit-def $exec, implicit-def dead $scc, implicit $exec
+  ; GCN-NEXT:   renamable $agpr0 = COPY killed renamable $vgpr62
+  ; GCN-NEXT:   $exec = S_MOV_B64 killed $noreg
+  ; GCN-NEXT:   renamable $vgpr62 = IMPLICIT_DEF
+  ; GCN-NEXT:   dead renamable $vgpr62 = V_AND_B32_e32 1, killed $vgpr62, implicit $exec
+  ; GCN-NEXT: {{  $}}
+  ; GCN-NEXT: bb.1:
+  ; GCN-NEXT:   successors: %bb.3(0x40000000), %bb.2(0x40000000)
+  ; GCN-NEXT:   liveins: $agpr0
+  ; GCN-NEXT: {{  $}}
+  ; GCN-NEXT:   S_CBRANCH_EXECZ %bb.2, implicit $exec
+  ; GCN-NEXT:   S_BRANCH %bb.3
+  ; GCN-NEXT: {{  $}}
+  ; GCN-NEXT: bb.2:
+  ; GCN-NEXT:   successors: %bb.4(0x04000000), %bb.1(0x7c000000)
+  ; GCN-NEXT:   liveins: $agpr0, $sgpr86, $sgpr87, $sgpr66_sgpr67, $sgpr68_sgpr69, $sgpr70_sgpr71, $sgpr80_sgpr81, $sgpr82_sgpr83, $sgpr84_sgpr85, $sgpr96_sgpr97, $sgpr98_sgpr99
+  ; GCN-NEXT: {{  $}}
+  ; GCN-NEXT:   S_CBRANCH_EXECNZ %bb.1, implicit $exec
+  ; GCN-NEXT:   S_BRANCH %bb.4
+  ; GCN-NEXT: {{  $}}
+  ; GCN-NEXT: bb.3:
+  ; GCN-NEXT:   successors: %bb.2(0x80000000)
+  ; GCN-NEXT:   liveins: $agpr0
+  ; GCN-NEXT: {{  $}}
+  ; GCN-NEXT:   $noreg = S_OR_SAVEEXEC_B64 -1, implicit-def $exec, implicit-def dead $scc, implicit $exec
+  ; GCN-NEXT:   renamable $vgpr62 = COPY renamable $agpr0
+  ; GCN-NEXT:   $exec = S_MOV_B64 killed $noreg
+  ; GCN-NEXT:   $sgpr14 = SI_RESTORE_S32_FROM_VGPR killed $vgpr62, 1
+  ; GCN-NEXT:   S_BRANCH %bb.2
+  ; GCN-NEXT: {{  $}}
+  ; GCN-NEXT: bb.4:
+  ; GCN-NEXT:   $sgpr4_sgpr5 = S_XOR_SAVEEXEC_B64 -1, implicit-def $exec, implicit-def dead $scc, implicit $exec
+  ; GCN-NEXT:   $vgpr63 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 0, 0, 0, implicit $exec :: (load (s32) from %stack.2, addrspace 5)
+  ; GCN-NEXT:   $agpr0 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr63, implicit $exec
+  ; GCN-NEXT:   $exec = S_MOV_B64 -1
+  ; GCN-NEXT:   $vgpr62 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 4, 0, 0, implicit $exec :: (load (s32) from %stack.3, addrspace 5)
+  ; GCN-NEXT:   $exec = S_MOV_B64 killed $sgpr4_sgpr5
+  ; GCN-NEXT:   SI_RETURN
+  bb.0:
+    liveins: $sgpr12, $sgpr13, $sgpr14, $sgpr15
+
+    %45:vgpr_32 = IMPLICIT_DEF
+    SI_SPILL_S32_SAVE $sgpr15, %stack.0, implicit $exec, implicit $sgpr32 :: (store (s32) into %stack.0, addrspace 5)
+    %16:vgpr_32 = V_AND_B32_e32 1, %45, implicit $exec
+
+  bb.1:
+    successors: %bb.3, %bb.2
+
+    S_CBRANCH_EXECZ %bb.2, implicit $exec
+    S_BRANCH %bb.3
+
+  bb.2:
+    successors: %bb.4(0x04000000), %bb.1(0x7c000000)
+    liveins: $sgpr86, $sgpr87, $sgpr66_sgpr67, $sgpr68_sgpr69, $sgpr70_sgpr71, $sgpr80_sgpr81, $sgpr82_sgpr83, $sgpr84_sgpr85, $sgpr96_sgpr97, $sgpr98_sgpr99
+
+    S_CBRANCH_EXECNZ %bb.1, implicit $exec
+    S_BRANCH %bb.4
+
+  bb.3:
+    ADJCALLSTACKUP 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
+    $sgpr14 = SI_SPILL_S32_RESTORE %stack.1, implicit $exec, implicit $sgpr32 :: (load (s32) from %stack.1, addrspace 5)
+    ADJCALLSTACKDOWN 0, 28, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32
+    S_BRANCH %bb.2
+
+  bb.4:
+    SI_RETURN
+
+...