[AArch64][SME] Disable tail calls for callees that require saving ZT0 (#165371)

We may need to load ZT0 after the call, so we can't perform a tail call.

Author: MacDue

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

@@ -9028,11 +9028,12 @@ bool AArch64TargetLowering::isEligibleForTailCallOptimization(
   CallingConv::ID CallerCC = CallerF.getCallingConv();
 
   // SME Streaming functions are not eligible for TCO as they may require
-  // the streaming mode or ZA to be restored after returning from the call.
+  // the streaming mode or ZA/ZT0 to be restored after returning from the call.
   SMECallAttrs CallAttrs =
       getSMECallAttrs(CallerF, getRuntimeLibcallsInfo(), CLI);
   if (CallAttrs.requiresSMChange() || CallAttrs.requiresLazySave() ||
       CallAttrs.requiresPreservingAllZAState() ||
+      CallAttrs.requiresPreservingZT0() ||
       CallAttrs.caller().hasStreamingBody())
     return false;
 

llvm/test/CodeGen/AArch64/sme-zt0-state.ll

@@ -426,3 +426,21 @@ define void @zt0_multiple_private_za_calls(ptr %callee) "aarch64_in_zt0" nounwin
   call void %callee()
   ret void
 }
+
+define void @disable_tailcallopt(ptr %callee) "aarch64_inout_zt0" nounwind {
+; CHECK-COMMON-LABEL: disable_tailcallopt:
+; CHECK-COMMON:       // %bb.0:
+; CHECK-COMMON-NEXT:    sub sp, sp, #80
+; CHECK-COMMON-NEXT:    stp x30, x19, [sp, #64] // 16-byte Folded Spill
+; CHECK-COMMON-NEXT:    mov x19, sp
+; CHECK-COMMON-NEXT:    str zt0, [x19]
+; CHECK-COMMON-NEXT:    smstop za
+; CHECK-COMMON-NEXT:    blr x0
+; CHECK-COMMON-NEXT:    smstart za
+; CHECK-COMMON-NEXT:    ldr zt0, [x19]
+; CHECK-COMMON-NEXT:    ldp x30, x19, [sp, #64] // 16-byte Folded Reload
+; CHECK-COMMON-NEXT:    add sp, sp, #80
+; CHECK-COMMON-NEXT:    ret
+  tail call void %callee()
+  ret void
+}