[AArch64][SME] Fix chain for arm_locally_streaming functions.

[sdesmalen]

Summary

The Chain wasn't set correctly in the DAG for functions marked
with aarch64_pstate_sm_body, which meant that SelectionDAG would
dead-code some of the CopyToReg's. This didn't show up in the
existing tests because all uses were in the same block, but when
adding some control-flow, suddenly things would break.

[kmclaughlin]

LGTM!

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

Chain = DAG.getNode(
           DAG.getTargetConstant((int32_t)AArch64SVCR::SVCRSM, DL, MVT::i32),
          DAG.getConstant(0, DL, MVT::i64), DAG.getConstant(1, DL, MVT::i64),
          DAG.getRegisterMask(TRI->getSMStartStopCallPreservedMask()), Glue});
     // Ensure that the SMSTART happens after the CopyWithChain such that its
     // chain result is used.
     for (unsigned I=0; I<InVals.size(); ++I) {
       Register Reg = MF.getRegInfo().createVirtualRegister(
           getRegClassFor(InVals[I].getValueType().getSimpleVT()));
-      SDValue X = DAG.getCopyToReg(Chain, DL, Reg, InVals[I]);
-      InVals[I] = DAG.getCopyFromReg(X, DL, Reg,
+      Chain = DAG.getCopyToReg(Chain, DL, Reg, InVals[I]);
+      InVals[I] = DAG.getCopyFromReg(Chain, DL, Reg,
                                      InVals[I].getValueType());
     }
   }
 
   // varargs
   if (isVarArg) {
     if (!Subtarget->isTargetDarwin() || IsWin64) {
       // The AAPCS variadic function ABI is identical to the non-variadic

llvm/test/CodeGen/AArch64/sme-streaming-body.ll

 ; CHECK-NEXT:    ldp d15, d14, [sp], #80 // 16-byte Folded Reload
 ; CHECK-NEXT:    ret
 entry:
   %0 = call fast double @llvm.cos.f64(double %x)
   ret double %0
 }
 
 declare double @llvm.cos.f64(double)
+
+
+define float @test_arg_survives_loop(float %arg, i32 %N) nounwind "aarch64_pstate_sm_body" {
+; CHECK-LABEL: test_arg_survives_loop:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    sub sp, sp, #80
+; CHECK-NEXT:    stp d15, d14, [sp, #16] // 16-byte Folded Spill
+; CHECK-NEXT:    stp d13, d12, [sp, #32] // 16-byte Folded Spill
+; CHECK-NEXT:    stp d11, d10, [sp, #48] // 16-byte Folded Spill
+; CHECK-NEXT:    stp d9, d8, [sp, #64] // 16-byte Folded Spill
+; CHECK-NEXT:    str s0, [sp, #12] // 4-byte Folded Spill
+; CHECK-NEXT:    smstart sm
+; CHECK-NEXT:  .LBB9_1: // %for.body
+; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    subs w0, w0, #1
+; CHECK-NEXT:    b.ne .LBB9_1
+; CHECK-NEXT:  // %bb.2: // %for.cond.cleanup
+; CHECK-NEXT:    fmov s0, #1.00000000
+; CHECK-NEXT:    ldr s1, [sp, #12] // 4-byte Folded Reload
+; CHECK-NEXT:    fadd s0, s1, s0
+; CHECK-NEXT:    str s0, [sp, #12] // 4-byte Folded Spill
+; CHECK-NEXT:    smstop sm
+; CHECK-NEXT:    ldp d9, d8, [sp, #64] // 16-byte Folded Reload
+; CHECK-NEXT:    ldp d11, d10, [sp, #48] // 16-byte Folded Reload
+; CHECK-NEXT:    ldp d13, d12, [sp, #32] // 16-byte Folded Reload
+; CHECK-NEXT:    ldp d15, d14, [sp, #16] // 16-byte Folded Reload
+; CHECK-NEXT:    ldr s0, [sp, #12] // 4-byte Folded Reload
+; CHECK-NEXT:    add sp, sp, #80
+; CHECK-NEXT:    ret
+entry:
+  br label %for.body
+
+for.body:
+  %i.02 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
+  %inc = add nuw nsw i32 %i.02, 1
+  %exitcond.not = icmp eq i32 %inc, %N
+  br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
+
+for.cond.cleanup:
+  %add = fadd float %arg, 1.000000e+00
+  ret float %add
+
+}