[AMDGPU] Fix computing live registers in prolog

[sebastian-ne]

Summary

ScratchExecCopy needs to be marked as live, we cannot use that register
while EXEC is stored in there.

Marking SGPRForFPSaveRestoreCopy and SGPRForBPSaveRestoreCopy as
available is unnecessary, they should not be live at that point anway.

llvm/lib/Target/AMDGPU/SIFrameLowering.cpp

static Register buildScratchExecCopy(LivePhysRegs &LiveRegs,
                                      MachineBasicBlock &MBB,
                                      MachineBasicBlock::iterator MBBI,
                                      bool IsProlog) {
   Register ScratchExecCopy;
   MachineRegisterInfo &MRI = MF.getRegInfo();
   const GCNSubtarget &ST = MF.getSubtarget<GCNSubtarget>();
   const SIInstrInfo *TII = ST.getInstrInfo();
   const SIRegisterInfo &TRI = TII->getRegisterInfo();
-  SIMachineFunctionInfo *FuncInfo = MF.getInfo<SIMachineFunctionInfo>();
   DebugLoc DL;
 
   if (LiveRegs.empty()) {
     if (IsProlog) {
       LiveRegs.init(TRI);
       LiveRegs.addLiveIns(MBB);
-      if (FuncInfo->SGPRForFPSaveRestoreCopy)
-        LiveRegs.removeReg(FuncInfo->SGPRForFPSaveRestoreCopy);
-
-      if (FuncInfo->SGPRForBPSaveRestoreCopy)
-        LiveRegs.removeReg(FuncInfo->SGPRForBPSaveRestoreCopy);
     } else {
       // In epilog.
       LiveRegs.init(*ST.getRegisterInfo());
       LiveRegs.addLiveOuts(MBB);
       LiveRegs.stepBackward(*MBBI);
     }
   }
 
   ScratchExecCopy = findScratchNonCalleeSaveRegister(
       MRI, LiveRegs, *TRI.getWaveMaskRegClass());
   if (!ScratchExecCopy)
     report_fatal_error("failed to find free scratch register");
 
-  if (!IsProlog)
-    LiveRegs.removeReg(ScratchExecCopy);
+  LiveRegs.addReg(ScratchExecCopy);
 
   const unsigned OrSaveExec =
       ST.isWave32() ? AMDGPU::S_OR_SAVEEXEC_B32 : AMDGPU::S_OR_SAVEEXEC_B64;
   BuildMI(MBB, MBBI, DL, TII->get(OrSaveExec), ScratchExecCopy).addImm(-1);
 
   return ScratchExecCopy;
 }
 

llvm/test/CodeGen/AMDGPU/pei-scavenge-vgpr-spill.mir

bb.0:
     ; GFX9: $vgpr2 = BUFFER_LOAD_DWORD_OFFEN killed $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 0, 0, 0, 0, implicit $exec :: (load 4 from %stack.3, addrspace 5)
     ; GFX9: $exec = S_MOV_B64 killed $sgpr4_sgpr5
     ; GFX9: $sgpr4 = S_ADD_U32 $sgpr33, 524800, implicit-def $scc
     ; GFX9: $vgpr3 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, killed $sgpr4, 0, 0, 0, 0, implicit $exec :: (load 4 from %stack.4, addrspace 5)
     ; GFX9: S_ENDPGM 0, csr_amdgpu_allvgprs
     ; GFX9-FLATSCR-LABEL: name: pei_scavenge_vgpr_spill
     ; GFX9-FLATSCR: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255, $vgpr2
     ; GFX9-FLATSCR: $sgpr4_sgpr5 = S_OR_SAVEEXEC_B64 -1, implicit-def $exec, implicit-def $scc, implicit $exec
-    ; GFX9-FLATSCR: $sgpr4 = S_ADD_U32 $sgpr32, 8196, implicit-def $scc
-    ; GFX9-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr2, killed $sgpr4, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.3, addrspace 5)
+    ; GFX9-FLATSCR: $sgpr6 = S_ADD_U32 $sgpr32, 8196, implicit-def $scc
+    ; GFX9-FLATSCR: SCRATCH_STORE_DWORD_SADDR killed $vgpr2, killed $sgpr6, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into %stack.3, addrspace 5)
     ; GFX9-FLATSCR: $exec = S_MOV_B64 killed $sgpr4_sgpr5
     ; GFX9-FLATSCR: $vgpr2 = V_WRITELANE_B32 $sgpr33, 0, undef $vgpr2
     ; GFX9-FLATSCR: $sgpr33 = frame-setup S_ADD_U32 $sgpr32, 8191, implicit-def $scc
     ; GFX9-FLATSCR: $sgpr33 = frame-setup S_AND_B32 killed $sgpr33, 4294959104, implicit-def $scc
     ; GFX9-FLATSCR: $sgpr32 = frame-setup S_ADD_U32 $sgpr32, 24576, implicit-def $scc
     ; GFX9-FLATSCR: $vgpr0 = V_MOV_B32_e32 $sgpr33, implicit $exec
     ; GFX9-FLATSCR: $vcc_hi = S_ADD_U32 $sgpr33, 8192, implicit-def $scc
     ; GFX9-FLATSCR: $vgpr0 = V_OR_B32_e32 killed $vcc_hi, $vgpr1, implicit $exec
     ; GFX9-FLATSCR: $sgpr32 = frame-destroy S_SUB_U32 $sgpr32, 24576, implicit-def $scc
     ; GFX9-FLATSCR: $sgpr33 = V_READLANE_B32 $vgpr2, 0
     ; GFX9-FLATSCR: $sgpr4_sgpr5 = S_OR_SAVEEXEC_B64 -1, implicit-def $exec, implicit-def $scc, implicit $exec
-    ; GFX9-FLATSCR: $sgpr4 = S_ADD_U32 $sgpr32, 8196, implicit-def $scc
-    ; GFX9-FLATSCR: $vgpr2 = SCRATCH_LOAD_DWORD_SADDR killed $sgpr4, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %stack.3, addrspace 5)
+    ; GFX9-FLATSCR: $sgpr6 = S_ADD_U32 $sgpr32, 8196, implicit-def $scc
+    ; GFX9-FLATSCR: $vgpr2 = SCRATCH_LOAD_DWORD_SADDR killed $sgpr6, 0, 0, implicit $exec, implicit $flat_scr :: (load 4 from %stack.3, addrspace 5)
     ; GFX9-FLATSCR: $exec = S_MOV_B64 killed $sgpr4_sgpr5
     ; GFX9-FLATSCR: S_ENDPGM 0, csr_amdgpu_allvgprs
     $vgpr0 = V_MOV_B32_e32 %stack.0, implicit $exec
     $vgpr0 = V_OR_B32_e32 %stack.1, $vgpr1, implicit $exec
     S_ENDPGM 0, csr_amdgpu_allvgprs
 ...