[STATEPOINT] Force implicit-def for lpr register.

[skatkov]

Summary

STATEPOINT instruction behavior is similar to call instruction.
In aarch64 BL instruction implicitly define lpr register, so
STATEPOINT instruction should do the same.
However STATEPOINT is a general instruction and I could not find
a way to override list of implicit defs for specific architecture.

So this patch post processes inserting STATEPOINT instruction by
adding implicit dead def for lpr.

[reames]

Just to comment, it looks like this covers the same ground as https://reviews.llvm.org/D107301. As I said there, I don't really feel comfortable reviewing this, though it's starting to look like I might need to. Can you try to ping one of the aarch64 maintainers directly? They may have a good answer on how to approach this. I can't imagine statepoint is the only case to ever hit this.

[reames]

LGTM

This is a bit outside my expertise so I'm not thrilled about being the sole reviewer for this, but given no one else has responded and this looks reasonable, I'm approving this to unblock progress.

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

 #ifndef NDEBUG
     MI.dump();
 #endif
     llvm_unreachable("Unexpected instruction for custom inserter!");
 
   case AArch64::F128CSEL:
     return EmitF128CSEL(MI, BB);
 
+  case TargetOpcode::STATEPOINT:
+    // STATEPOINT is a pseudo instruction which has no implicit defs/uses
+    // while bl call instruction (where statepoint will be lowered at the end)
+    // has implicit def. Add this implicit dead def here as a workaround.
+    MI.addOperand(*MI.getMF(), MachineOperand::CreateReg(AArch64::LR, true,
+                                                         true, false, true));
+    LLVM_FALLTHROUGH;
   case TargetOpcode::STACKMAP:
   case TargetOpcode::PATCHPOINT:
-  case TargetOpcode::STATEPOINT:
     return emitPatchPoint(MI, BB);
 
   case AArch64::CATCHRET:
     return EmitLoweredCatchRet(MI, BB);
   }
 }
 
 //===----------------------------------------------------------------------===//

llvm/test/CodeGen/AArch64/statepoint-call-lowering.ll

 declare i32* @return_i32ptr()
 declare float @return_float()
 declare %struct @return_struct()
 declare void @varargf(i32, ...)
 
 define i1 @test_i1_return() gc "statepoint-example" {
 ; CHECK-LABEL: test_i1_return:
 ; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    bl return_i1
-; CHECK-NEXT:  .Ltmp2:
+; CHECK-NEXT:  .Ltmp0:
 ; CHECK-NEXT:    and w0, w0, #0x1
+; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
 ; This is just checking that a i1 gets lowered normally when there's no extra
 ; state arguments to the statepoint
 entry:
   %safepoint_token = tail call token (i64, i32, i1 ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_i1f(i64 0, i32 0, i1 ()* @return_i1, i32 0, i32 0, i32 0, i32 0)
   %call1 = call zeroext i1 @llvm.experimental.gc.result.i1(token %safepoint_token)
   ret i1 %call1
 }
 
 define i32 @test_i32_return() gc "statepoint-example" {
 ; CHECK-LABEL: test_i32_return:
 ; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    bl return_i32
-; CHECK-NEXT:  .Ltmp3:
+; CHECK-NEXT:  .Ltmp1:
+; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
 entry:
   %safepoint_token = tail call token (i64, i32, i32 ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_i32f(i64 0, i32 0, i32 ()* @return_i32, i32 0, i32 0, i32 0, i32 0)
   %call1 = call zeroext i32 @llvm.experimental.gc.result.i32(token %safepoint_token)
   ret i32 %call1
 }
 
 define i32* @test_i32ptr_return() gc "statepoint-example" {
 ; CHECK-LABEL: test_i32ptr_return:
 ; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    bl return_i32ptr
-; CHECK-NEXT:  .Ltmp4:
+; CHECK-NEXT:  .Ltmp2:
+; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
 entry:
   %safepoint_token = tail call token (i64, i32, i32* ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_p0i32f(i64 0, i32 0, i32* ()* @return_i32ptr, i32 0, i32 0, i32 0, i32 0)
   %call1 = call i32* @llvm.experimental.gc.result.p0i32(token %safepoint_token)
   ret i32* %call1
 }
 
 define float @test_float_return() gc "statepoint-example" {
 ; CHECK-LABEL: test_float_return:
 ; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    bl return_float
-; CHECK-NEXT:  .Ltmp5:
+; CHECK-NEXT:  .Ltmp3:
+; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
 entry:
   %safepoint_token = tail call token (i64, i32, float ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_f32f(i64 0, i32 0, float ()* @return_float, i32 0, i32 0, i32 0, i32 0)
   %call1 = call float @llvm.experimental.gc.result.f32(token %safepoint_token)
   ret float %call1
 }
 
 define %struct @test_struct_return() gc "statepoint-example" {
 ; CHECK-LABEL: test_struct_return:
 ; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    bl return_struct
-; CHECK-NEXT:  .Ltmp6:
+; CHECK-NEXT:  .Ltmp4:
+; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
 entry:
   %safepoint_token = tail call token (i64, i32, %struct ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_structf(i64 0, i32 0, %struct ()* @return_struct, i32 0, i32 0, i32 0, i32 0)
   %call1 = call %struct @llvm.experimental.gc.result.struct(token %safepoint_token)
   ret %struct %call1
 }
 
 define i1 @test_relocate(i32 addrspace(1)* %a) gc "statepoint-example" {
 ; CHECK-LABEL: test_relocate:
 ; CHECK:       // %bb.0: // %entry
-; CHECK-NEXT:    sub sp, sp, #16
+; CHECK-NEXT:    stp x30, x0, [sp, #-16]! // 8-byte Folded Spill
 ; CHECK-NEXT:    .cfi_def_cfa_offset 16
-; CHECK-NEXT:    str x0, [sp, #8]
+; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    bl return_i1
-; CHECK-NEXT:  .Ltmp7:
+; CHECK-NEXT:  .Ltmp5:
 ; CHECK-NEXT:    and w0, w0, #0x1
-; CHECK-NEXT:    add sp, sp, #16
+; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
 ; Check that an ununsed relocate has no code-generation impact
 entry:
   %safepoint_token = tail call token (i64, i32, i1 ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_i1f(i64 0, i32 0, i1 ()* @return_i1, i32 0, i32 0, i32 0, i32 0) ["gc-live" (i32 addrspace(1)* %a)]
   %call1 = call i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(token %safepoint_token,  i32 0, i32 0)
   %call2 = call zeroext i1 @llvm.experimental.gc.result.i1(token %safepoint_token)
   ret i1 %call2
 }
 
 define void @test_void_vararg() gc "statepoint-example" {
 ; CHECK-LABEL: test_void_vararg:
 ; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    mov w0, #42
 ; CHECK-NEXT:    mov w1, #43
 ; CHECK-NEXT:    bl varargf
-; CHECK-NEXT:  .Ltmp8:
+; CHECK-NEXT:  .Ltmp6:
+; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
 ; Check a statepoint wrapping a *void* returning vararg function works
 entry:
   %safepoint_token = tail call token (i64, i32, void (i32, ...)*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidi32varargf(i64 0, i32 0, void (i32, ...)* @varargf, i32 2, i32 0, i32 42, i32 43, i32 0, i32 0)
   ;; if we try to use the result from a statepoint wrapping a
   ;; non-void-returning varargf, we will experience a crash.
   ret void
 }
 
 define i1 @test_i1_return_patchable() gc "statepoint-example" {
 ; CHECK-LABEL: test_i1_return_patchable:
 ; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    nop
-; CHECK-NEXT:  .Ltmp9:
+; CHECK-NEXT:  .Ltmp7:
 ; CHECK-NEXT:    and w0, w0, #0x1
+; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
 ; CHECK-NEXT:    ret
 ; A patchable variant of test_i1_return
 entry:
   %safepoint_token = tail call token (i64, i32, i1 ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_i1f(i64 0, i32 4, i1 ()*null, i32 0, i32 0, i32 0, i32 0)
   %call1 = call zeroext i1 @llvm.experimental.gc.result.i1(token %safepoint_token)
   ret i1 %call1
 }
 
 declare void @consume(i32 addrspace(1)* %obj)
 
 define i1 @test_cross_bb(i32 addrspace(1)* %a, i1 %external_cond) gc "statepoint-example" {
 ; CHECK-LABEL: test_cross_bb:
 ; CHECK:       // %bb.0: // %entry
 ; CHECK-NEXT:    str x30, [sp, #-32]! // 8-byte Folded Spill
 ; CHECK-NEXT:    stp x20, x19, [sp, #16] // 16-byte Folded Spill
 ; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset w19, -8
 ; CHECK-NEXT:    .cfi_offset w20, -16
 ; CHECK-NEXT:    .cfi_offset w30, -32
 ; CHECK-NEXT:    mov w20, w1
 ; CHECK-NEXT:    str x0, [sp, #8]
 ; CHECK-NEXT:    bl return_i1
-; CHECK-NEXT:  .Ltmp10:
+; CHECK-NEXT:  .Ltmp8:
 ; CHECK-NEXT:    tbz w20, #0, .LBB8_2
 ; CHECK-NEXT:  // %bb.1: // %left
 ; CHECK-NEXT:    mov w19, w0
 ; CHECK-NEXT:    ldr x0, [sp, #8]
 ; CHECK-NEXT:    bl consume
 ; CHECK-NEXT:    b .LBB8_3
 ; CHECK-NEXT:  .LBB8_2:
 ; CHECK-NEXT:    mov w19, #1

 
 %struct2 = type { i64, i64, i64 }
 
 declare void @consume_attributes(i32, i8* nest, i32, %struct2* byval(%struct2))
 
 define void @test_attributes(%struct2* byval(%struct2) %s) gc "statepoint-example" {
 ; CHECK-LABEL: test_attributes:
 ; CHECK:       // %bb.0: // %entry
-; CHECK-NEXT:    sub sp, sp, #32
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
+; CHECK-NEXT:    sub sp, sp, #48
+; CHECK-NEXT:    str x30, [sp, #32] // 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_def_cfa_offset 48
+; CHECK-NEXT:    .cfi_offset w30, -16
 ; CHECK-NEXT:    mov x18, xzr
-; CHECK-NEXT:    ldr q0, [sp, #32]
-; CHECK-NEXT:    ldr x8, [sp, #48]
+; CHECK-NEXT:    ldr q0, [sp, #48]
+; CHECK-NEXT:    ldr x8, [sp, #64]
 ; CHECK-NEXT:    mov w0, #42
 ; CHECK-NEXT:    mov w1, #17
 ; CHECK-NEXT:    str q0, [sp]
 ; CHECK-NEXT:    str x8, [sp, #16]
 ; CHECK-NEXT:    bl consume_attributes
-; CHECK-NEXT:  .Ltmp11:
-; CHECK-NEXT:    add sp, sp, #32
+; CHECK-NEXT:  .Ltmp9:
+; CHECK-NEXT:    ldr x30, [sp, #32] // 8-byte Folded Reload
+; CHECK-NEXT:    add sp, sp, #48
 ; CHECK-NEXT:    ret
 entry:
 ; Check that arguments with attributes are lowered correctly.
 ; We call a function that has a nest argument and a byval argument.
   %statepoint_token = call token (i64, i32, void (i32, i8*, i32, %struct2*)*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidi32p0i8i32p0s_struct2sf(i64 0, i32 0, void (i32, i8*, i32, %struct2*)* @consume_attributes, i32 4, i32 0, i32 42, i8* nest null, i32 17, %struct2* byval(%struct2) %s, i32 0, i32 0)
   ret void
 }