From: Nikita Popov Date: Thu, 15 Sep 2022 15:00:55 +0000 (+0200) Subject: [CodeGen] Don't zero callee-save registers with zero-call-used-regs (PR57692) X-Git-Tag: upstream/17.0.6~33374 X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=b4309800e9dc53a84222a6b57c8615d4a3084988;p=platform%2Fupstream%2Fllvm.git [CodeGen] Don't zero callee-save registers with zero-call-used-regs (PR57692) Callee save registers must be preserved, so -fzero-call-used-regs should not be zeroing them. The previous implementation only did not zero callee save registers that were saved&restored inside the function, but we need preserve all of them. Fixes https://github.com/llvm/llvm-project/issues/57692. Differential Revision: https://reviews.llvm.org/D133946 --- diff --git a/llvm/lib/CodeGen/PrologEpilogInserter.cpp b/llvm/lib/CodeGen/PrologEpilogInserter.cpp index 64536bf..b7f764c 100644 --- a/llvm/lib/CodeGen/PrologEpilogInserter.cpp +++ b/llvm/lib/CodeGen/PrologEpilogInserter.cpp @@ -1273,9 +1273,10 @@ void PEI::insertZeroCallUsedRegs(MachineFunction &MF) { } } - // Don't clear registers that are reset before exiting. - for (const CalleeSavedInfo &CSI : MF.getFrameInfo().getCalleeSavedInfo()) - for (MCRegister Reg : TRI.sub_and_superregs_inclusive(CSI.getReg())) + // Don't clear registers that must be preserved. + for (const MCPhysReg *CSRegs = TRI.getCalleeSavedRegs(&MF); + MCPhysReg CSReg = *CSRegs; ++CSRegs) + for (MCRegister Reg : TRI.sub_and_superregs_inclusive(CSReg)) RegsToZero.reset(Reg); const TargetFrameLowering &TFI = *MF.getSubtarget().getFrameLowering(); diff --git a/llvm/test/CodeGen/AArch64/zero-call-used-regs.ll b/llvm/test/CodeGen/AArch64/zero-call-used-regs.ll index c390899..0cbd155 100644 --- a/llvm/test/CodeGen/AArch64/zero-call-used-regs.ll +++ b/llvm/test/CodeGen/AArch64/zero-call-used-regs.ll @@ -220,14 +220,6 @@ define dso_local i32 @all(i32 noundef %a, i32 noundef %b, i32 noundef %c) local_ ; DEFAULT-NEXT: movi v5.2d, #0000000000000000 ; DEFAULT-NEXT: movi v6.2d, #0000000000000000 ; DEFAULT-NEXT: movi v7.2d, #0000000000000000 -; DEFAULT-NEXT: movi v8.2d, #0000000000000000 -; DEFAULT-NEXT: movi v9.2d, #0000000000000000 -; DEFAULT-NEXT: movi v10.2d, #0000000000000000 -; DEFAULT-NEXT: movi v11.2d, #0000000000000000 -; DEFAULT-NEXT: movi v12.2d, #0000000000000000 -; DEFAULT-NEXT: movi v13.2d, #0000000000000000 -; DEFAULT-NEXT: movi v14.2d, #0000000000000000 -; DEFAULT-NEXT: movi v15.2d, #0000000000000000 ; DEFAULT-NEXT: movi v16.2d, #0000000000000000 ; DEFAULT-NEXT: movi v17.2d, #0000000000000000 ; DEFAULT-NEXT: movi v18.2d, #0000000000000000 @@ -276,14 +268,6 @@ define dso_local i32 @all(i32 noundef %a, i32 noundef %b, i32 noundef %c) local_ ; SVE-NEXT: mov z5.d, #0 // =0x0 ; SVE-NEXT: mov z6.d, #0 // =0x0 ; SVE-NEXT: mov z7.d, #0 // =0x0 -; SVE-NEXT: mov z8.d, #0 // =0x0 -; SVE-NEXT: mov z9.d, #0 // =0x0 -; SVE-NEXT: mov z10.d, #0 // =0x0 -; SVE-NEXT: mov z11.d, #0 // =0x0 -; SVE-NEXT: mov z12.d, #0 // =0x0 -; SVE-NEXT: mov z13.d, #0 // =0x0 -; SVE-NEXT: mov z14.d, #0 // =0x0 -; SVE-NEXT: mov z15.d, #0 // =0x0 ; SVE-NEXT: mov z16.d, #0 // =0x0 ; SVE-NEXT: mov z17.d, #0 // =0x0 ; SVE-NEXT: mov z18.d, #0 // =0x0 @@ -548,14 +532,6 @@ define dso_local double @all_float(double noundef %a, float noundef %b) local_un ; DEFAULT-NEXT: movi v5.2d, #0000000000000000 ; DEFAULT-NEXT: movi v6.2d, #0000000000000000 ; DEFAULT-NEXT: movi v7.2d, #0000000000000000 -; DEFAULT-NEXT: movi v8.2d, #0000000000000000 -; DEFAULT-NEXT: movi v9.2d, #0000000000000000 -; DEFAULT-NEXT: movi v10.2d, #0000000000000000 -; DEFAULT-NEXT: movi v11.2d, #0000000000000000 -; DEFAULT-NEXT: movi v12.2d, #0000000000000000 -; DEFAULT-NEXT: movi v13.2d, #0000000000000000 -; DEFAULT-NEXT: movi v14.2d, #0000000000000000 -; DEFAULT-NEXT: movi v15.2d, #0000000000000000 ; DEFAULT-NEXT: movi v16.2d, #0000000000000000 ; DEFAULT-NEXT: movi v17.2d, #0000000000000000 ; DEFAULT-NEXT: movi v18.2d, #0000000000000000 @@ -604,14 +580,6 @@ define dso_local double @all_float(double noundef %a, float noundef %b) local_un ; SVE-NEXT: mov z5.d, #0 // =0x0 ; SVE-NEXT: mov z6.d, #0 // =0x0 ; SVE-NEXT: mov z7.d, #0 // =0x0 -; SVE-NEXT: mov z8.d, #0 // =0x0 -; SVE-NEXT: mov z9.d, #0 // =0x0 -; SVE-NEXT: mov z10.d, #0 // =0x0 -; SVE-NEXT: mov z11.d, #0 // =0x0 -; SVE-NEXT: mov z12.d, #0 // =0x0 -; SVE-NEXT: mov z13.d, #0 // =0x0 -; SVE-NEXT: mov z14.d, #0 // =0x0 -; SVE-NEXT: mov z15.d, #0 // =0x0 ; SVE-NEXT: mov z16.d, #0 // =0x0 ; SVE-NEXT: mov z17.d, #0 // =0x0 ; SVE-NEXT: mov z18.d, #0 // =0x0 diff --git a/llvm/test/CodeGen/X86/zero-call-used-regs.ll b/llvm/test/CodeGen/X86/zero-call-used-regs.ll index 146f5e3..63d51c9 100644 --- a/llvm/test/CodeGen/X86/zero-call-used-regs.ll +++ b/llvm/test/CodeGen/X86/zero-call-used-regs.ll @@ -110,19 +110,13 @@ define dso_local i32 @all_gpr(i32 returned %x) local_unnamed_addr #0 "zero-call- ; I386-LABEL: all_gpr: ; I386: # %bb.0: # %entry ; I386-NEXT: movl {{[0-9]+}}(%esp), %eax -; I386-NEXT: xorl %ebp, %ebp -; I386-NEXT: xorl %ebx, %ebx ; I386-NEXT: xorl %ecx, %ecx -; I386-NEXT: xorl %edi, %edi ; I386-NEXT: xorl %edx, %edx -; I386-NEXT: xorl %esi, %esi ; I386-NEXT: retl ; ; X86-64-LABEL: all_gpr: ; X86-64: # %bb.0: # %entry ; X86-64-NEXT: movl %edi, %eax -; X86-64-NEXT: xorl %ebp, %ebp -; X86-64-NEXT: xorl %ebx, %ebx ; X86-64-NEXT: xorl %ecx, %ecx ; X86-64-NEXT: xorl %edi, %edi ; X86-64-NEXT: xorl %edx, %edx @@ -131,10 +125,6 @@ define dso_local i32 @all_gpr(i32 returned %x) local_unnamed_addr #0 "zero-call- ; X86-64-NEXT: xorl %r9d, %r9d ; X86-64-NEXT: xorl %r10d, %r10d ; X86-64-NEXT: xorl %r11d, %r11d -; X86-64-NEXT: xorl %r12d, %r12d -; X86-64-NEXT: xorl %r13d, %r13d -; X86-64-NEXT: xorl %r14d, %r14d -; X86-64-NEXT: xorl %r15d, %r15d ; X86-64-NEXT: retq entry: @@ -190,12 +180,8 @@ define dso_local i32 @all(i32 returned %x) local_unnamed_addr #0 "zero-call-used ; I386-NEXT: fstp %st(0) ; I386-NEXT: fstp %st(0) ; I386-NEXT: fstp %st(0) -; I386-NEXT: xorl %ebp, %ebp -; I386-NEXT: xorl %ebx, %ebx ; I386-NEXT: xorl %ecx, %ecx -; I386-NEXT: xorl %edi, %edi ; I386-NEXT: xorl %edx, %edx -; I386-NEXT: xorl %esi, %esi ; I386-NEXT: xorps %xmm0, %xmm0 ; I386-NEXT: xorps %xmm1, %xmm1 ; I386-NEXT: xorps %xmm2, %xmm2 @@ -225,8 +211,6 @@ define dso_local i32 @all(i32 returned %x) local_unnamed_addr #0 "zero-call-used ; X86-64-NEXT: fstp %st(0) ; X86-64-NEXT: fstp %st(0) ; X86-64-NEXT: fstp %st(0) -; X86-64-NEXT: xorl %ebp, %ebp -; X86-64-NEXT: xorl %ebx, %ebx ; X86-64-NEXT: xorl %ecx, %ecx ; X86-64-NEXT: xorl %edi, %edi ; X86-64-NEXT: xorl %edx, %edx @@ -235,10 +219,6 @@ define dso_local i32 @all(i32 returned %x) local_unnamed_addr #0 "zero-call-used ; X86-64-NEXT: xorl %r9d, %r9d ; X86-64-NEXT: xorl %r10d, %r10d ; X86-64-NEXT: xorl %r11d, %r11d -; X86-64-NEXT: xorl %r12d, %r12d -; X86-64-NEXT: xorl %r13d, %r13d -; X86-64-NEXT: xorl %r14d, %r14d -; X86-64-NEXT: xorl %r15d, %r15d ; X86-64-NEXT: xorps %xmm0, %xmm0 ; X86-64-NEXT: xorps %xmm1, %xmm1 ; X86-64-NEXT: xorps %xmm2, %xmm2