[llvm] [AMDGPU] Add a trap lowering workaround for gfx11 (PR #85854)

[Matt Arsenault via llvm-commits]

================
@@ -303,6 +303,12 @@ def FeatureMSAALoadDstSelBug : SubtargetFeature<"msaa-load-dst-sel-bug",
   "MSAA loads not honoring dst_sel bug"
 >;
 
+def FeaturePrivEnabledBug : SubtargetFeature<"priv-enabled-bug",
----------------
arsenm wrote:

Should this mention trap, or is it more general? 

https://github.com/llvm/llvm-project/pull/85854