Use SETNE directly rather than SUB/SETNE 0 for stack guard check

[jrtc27]

Summary

Backends should fold the subtraction into the comparison, but not all
seem to. Moreover, on targets where pointers are not integers, such as
CHERI, an integer subtraction is not appropriate. Instead we should just
compare the two pointers directly, as this should work everywhere and
potentially generate more efficient code.

[lebedev.ri]

This seems obviously correct(C) to me, so LG, https://rise4fun.com/Alive/rR6
Git speluking suggests it was that way since the beginning (rL188755),
so it's not like this was changed the opposite way to fix something..

llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp

if (TLI.useLoadStackGuardNode()) {
     const Value *IRGuard = TLI.getSDagStackGuard(M);
     SDValue GuardPtr = getValue(IRGuard);
 
     Guard = DAG.getLoad(PtrMemTy, dl, Chain, GuardPtr,
                         MachinePointerInfo(IRGuard, 0), Align,
                         MachineMemOperand::MOVolatile);
   }
 
-  // Perform the comparison via a subtract/getsetcc.
-  EVT VT = Guard.getValueType();
-  SDValue Sub = DAG.getNode(ISD::SUB, dl, VT, Guard, GuardVal);
-
+  // Perform the comparison via a getsetcc.
   SDValue Cmp = DAG.getSetCC(dl, TLI.getSetCCResultType(DAG.getDataLayout(),
                                                         *DAG.getContext(),
-                                                        Sub.getValueType()),
-                             Sub, DAG.getConstant(0, dl, VT), ISD::SETNE);
+                                                        Guard.getValueType()),
+                             Guard, GuardVal, ISD::SETNE);
 
-  // If the sub is not 0, then we know the guard/stackslot do not equal, so
-  // branch to failure MBB.
+  // If the guard/stackslot do not equal, branch to failure MBB.
   SDValue BrCond = DAG.getNode(ISD::BRCOND, dl,
                                MVT::Other, GuardVal.getOperand(0),
                                Cmp, DAG.getBasicBlock(SPD.getFailureMBB()));
   // Otherwise branch to success MBB.
   SDValue Br = DAG.getNode(ISD::BR, dl,
                            MVT::Other, BrCond,
                            DAG.getBasicBlock(SPD.getSuccessMBB()));
 

llvm/test/CodeGen/SystemZ/stack-guard.ll

 ; RUN: llc < %s -mtriple=s390x-linux-gnu | FileCheck %s
 
 ; CHECK-LABEL: @test_stack_guard
 ; CHECK: ear [[REG1:%r[1-9][0-9]?]], %a0
 ; CHECK: sllg [[REG1]], [[REG1]], 32
 ; CHECK: ear [[REG1]], %a1
 ; CHECK: lg [[REG1]], 40([[REG1]])
 ; CHECK: stg [[REG1]], {{[0-9]*}}(%r15)
 ; CHECK: brasl %r14, foo3@PLT
 ; CHECK: ear [[REG2:%r[1-9][0-9]?]], %a0
 ; CHECK: sllg [[REG2]], [[REG2]], 32
 ; CHECK: ear [[REG2]], %a1
 ; CHECK: lg [[REG2]], 40([[REG2]])
-; CHECK: sg [[REG2]], {{[0-9]*}}(%r15)
+; CHECK: cg [[REG2]], {{[0-9]*}}(%r15)
 
 define i32 @test_stack_guard() #0 {
 entry:
   %a1 = alloca [256 x i32], align 4
   %0 = bitcast [256 x i32]* %a1 to i8*
   call void @llvm.lifetime.start.p0i8(i64 1024, i8* %0)
   %arraydecay = getelementptr inbounds [256 x i32], [256 x i32]* %a1, i64 0, i64 0
   call void @foo3(i32* %arraydecay)

llvm/test/CodeGen/Thumb/stack_guard_remat.ll

 ; RUN: llc < %s -mtriple=thumb-apple-darwin -relocation-model=pic -no-integrated-as | FileCheck %s -check-prefix=PIC
 ; RUN: llc < %s -mtriple=thumb-apple-darwin -relocation-model=static -no-integrated-as | FileCheck %s -check-prefix=NO-PIC  -check-prefix=STATIC
 ; RUN: llc < %s -mtriple=thumb-apple-darwin -relocation-model=dynamic-no-pic -no-integrated-as | FileCheck %s  -check-prefix=NO-PIC -check-prefix=DYNAMIC-NO-PIC
 
 ;PIC:        foo2
 ;PIC:        ldr [[SAVED_GUARD:r[0-9]+]], [[GUARD_STACK_OFFSET:LCPI[0-9_]+]]
 ;PIC-NEXT:   add [[SAVED_GUARD]], sp
 ;PIC-NEXT:   ldr [[SAVED_GUARD]], {{\[}}[[SAVED_GUARD]]{{\]}}
 ;PIC-NEXT:   ldr [[ORIGINAL_GUARD:r[0-9]+]], [[ORIGINAL_GUARD_LABEL:LCPI[0-9_]+]]
 ;PIC-NEXT: [[LABEL1:LPC[0-9_]+]]:
 ;PIC-NEXT:   add [[ORIGINAL_GUARD]], pc
 ;PIC-NEXT:   ldr [[ORIGINAL_GUARD]], {{\[}}[[ORIGINAL_GUARD]]{{\]}}
 ;PIC-NEXT:   ldr [[ORIGINAL_GUARD]], {{\[}}[[ORIGINAL_GUARD]]{{\]}}
-;PIC-NEXT:   subs {{r[0-9]+}}, [[ORIGINAL_GUARD]], [[SAVED_GUARD]]
+;PIC-NEXT:   cmp [[ORIGINAL_GUARD]], [[SAVED_GUARD]]
 
 ;PIC:      [[GUARD_STACK_OFFSET]]:
 ;PIC-NEXT:   .long 1028
 ;PIC:      [[ORIGINAL_GUARD_LABEL]]:
 ;PIC-NEXT:   .long L___stack_chk_guard$non_lazy_ptr-([[LABEL1]]+4)
 
 ;NO-PIC:   foo2
 ;NO-PIC:                ldr [[SAVED_GUARD:r[0-9]+]], [[GUARD_STACK_OFFSET:LCPI[0-9_]+]]
 ;NO-PIC-NEXT:           add [[SAVED_GUARD]], sp
 ;NO-PIC-NEXT:           ldr [[SAVED_GUARD]], {{\[}}[[SAVED_GUARD]]{{\]}}
 ;NO-PIC-NEXT:           ldr [[ORIGINAL_GUARD:r[0-9]+]], [[ORIGINAL_GUARD_LABEL:LCPI[0-9_]+]]
 ;NO-PIC-NOT: LPC
 ;NO-PIC-NEXT:           ldr [[ORIGINAL_GUARD]], {{\[}}[[ORIGINAL_GUARD]]{{\]}}
 ;DYNAMIC-NO-PIC-NEXT:   ldr [[ORIGINAL_GUARD]], {{\[}}[[ORIGINAL_GUARD]]{{\]}}
-;NO-PIC-NEXT:           subs {{r[0-9]+}}, [[ORIGINAL_GUARD]], [[SAVED_GUARD]]
+;NO-PIC-NEXT:           cmp [[ORIGINAL_GUARD]], [[SAVED_GUARD]]
 
 ;STATIC:      [[GUARD_STACK_OFFSET]]:
 ;STATIC-NEXT:   .long 1028
 ;STATIC:      [[ORIGINAL_GUARD_LABEL]]:
 ;STATIC-NEXT:   .long ___stack_chk_guard
 
 ;DYNAMIC-NO-PIC:      [[GUARD_STACK_OFFSET]]:
 ;DYNAMIC-NO-PIC-NEXT:   .long 1028

llvm/test/CodeGen/WebAssembly/stack-protector.ll

 ; RUN: llc -verify-machineinstrs -mtriple=wasm32-unknown-unknown < %s | FileCheck -check-prefix=WASM32 %s
 
 ; WASM32: i32.load        28
-; WASM32-NEXT: i32.sub
+; WASM32-NEXT: i32.ne
 ; WASM32-NEXT: br_if           0
 
 ; WASM32: __stack_chk_fail
 
 @"\01LC" = internal constant [11 x i8] c"buf == %s\0A\00"    ; <[11 x i8]*> [#uses=1]
 
 define void @test(i8* %a) nounwind ssp {
 entry: