[llvm] AMDGPU: Fix temporal divergence introduced by machine-sink and performance regression introduced by D155343 (PR #67456)

[Nicolai Hähnle via llvm-commits]

================
@@ -1250,24 +1253,19 @@ MachineSinking::FindSuccToSinkTo(MachineInstr &MI, MachineBasicBlock *MBB,
   if (MBB == SuccToSinkTo)
     return nullptr;
 
-  if (!SuccToSinkTo)
-    return nullptr;
-
   // It's not safe to sink instructions to EH landing pad. Control flow into
   // landing pad is implicitly defined.
-  if (SuccToSinkTo->isEHPad())
+  if (SuccToSinkTo && SuccToSinkTo->isEHPad())
     return nullptr;
 
   // It ought to be okay to sink instructions into an INLINEASM_BR target, but
   // only if we make sure that MI occurs _before_ an INLINEASM_BR instruction in
   // the source block (which this code does not yet do). So for now, forbid
   // doing so.
-  if (SuccToSinkTo->isInlineAsmBrIndirectTarget())
+  if (SuccToSinkTo && SuccToSinkTo->isInlineAsmBrIndirectTarget())
     return nullptr;
 
-  MachineBasicBlock::const_iterator InsertPos =
-      SuccToSinkTo->SkipPHIsAndLabels(SuccToSinkTo->begin());
-  if (blockPrologueInterferes(SuccToSinkTo, InsertPos, MI, TRI, TII, MRI))
+  if (!TII->isSafeToSink(MI, SuccToSinkTo, CI))
----------------
nhaehnle wrote:

So `isSafeToSInk` can be called with SuccToSinkTo == nullptr? That seems like a bad idea.

https://github.com/llvm/llvm-project/pull/67456