[clang] [llvm] [BPF] add cast_{user,kern} instructions (PR #79902)

[via cfe-commits]

================
@@ -416,11 +419,124 @@ bool BPFCheckAndAdjustIR::removeGEPBuiltins(Module &M) {
   return Changed;
 }
 
+// Wrap ToWrap with cast to address space zero:
+// - if ToWrap is a getelementptr,
+//   wrap it's base pointer instead and return a copy;
+// - if ToWrap is Instruction, insert address space cast
+//   immediately after ToWrap;
+// - if ToWrap is not an Instruction (function parameter
+//   or a global value), insert address space cast at the
+//   beginning of the Function F;
+// - use Cache to avoid inserting too many casts;
+static Value *aspaceWrapValue(DenseMap<Value *, Value *> &Cache, Function *F,
+                              Value *ToWrap) {
+  auto It = Cache.find(ToWrap);
+  if (It != Cache.end())
+    return It->getSecond();
+
+  if (auto *GEP = dyn_cast<GetElementPtrInst>(ToWrap)) {
+    Value *Ptr = GEP->getPointerOperand();
+    Value *WrappedPtr = aspaceWrapValue(Cache, F, Ptr);
+    auto *GEPTy = cast<PointerType>(GEP->getType());
+    auto *NewGEP = GEP->clone();
+    NewGEP->insertAfter(GEP);
+    NewGEP->mutateType(GEPTy->getPointerTo(0));
+    NewGEP->setOperand(GEP->getPointerOperandIndex(), WrappedPtr);
+    NewGEP->setName(GEP->getName());
+    Cache[ToWrap] = NewGEP;
+    return NewGEP;
+  }
+
+  IRBuilder IB(F->getContext());
+  if (Instruction *InsnPtr = dyn_cast<Instruction>(ToWrap))
+    IB.SetInsertPoint(*InsnPtr->getInsertionPointAfterDef());
+  else
+    IB.SetInsertPoint(F->getEntryBlock().getFirstInsertionPt());
+  auto *PtrTy = cast<PointerType>(ToWrap->getType());
+  auto *ASZeroPtrTy = PtrTy->getPointerTo(0);
+  auto *ACast = IB.CreateAddrSpaceCast(ToWrap, ASZeroPtrTy, ToWrap->getName());
+  Cache[ToWrap] = ACast;
+  return ACast;
+}
+
+// Wrap a pointer operand OpNum of instruction I
+// with cast to address space zero
+static void aspaceWrapOperand(DenseMap<Value *, Value *> &Cache, Instruction *I,
+                              unsigned OpNum) {
+  Value *OldOp = I->getOperand(OpNum);
+  if (OldOp->getType()->getPointerAddressSpace() == 0)
+    return;
+
+  Value *NewOp = aspaceWrapValue(Cache, I->getFunction(), OldOp);
+  I->setOperand(OpNum, NewOp);
+  // Check if there are any remaining users of old GEP,
+  // delete those w/o users
+  for (;;) {
+    auto *OldGEP = dyn_cast<GetElementPtrInst>(OldOp);
+    if (!OldGEP)
+      break;
+    if (!OldGEP->use_empty())
+      break;
+    OldOp = OldGEP->getPointerOperand();
+    OldGEP->eraseFromParent();
+  }
+}
+
+// Support for BPF arenas:
+// - for each function in the module M, update pointer operand of
+//   each memory access instruction (load/store/cmpxchg/atomicrmw)
+//   by casting it from non-zero address space to zero address space, e.g:
+//
+//   (load (ptr addrspace (N) %p) ...)
+//     -> (load (addrspacecast ptr addrspace (N) %p to ptr))
+//
+// - assign section with name .arena.N for globals defined in
+//   non-zero address space N
+bool BPFCheckAndAdjustIR::insertASpaceCasts(Module &M) {
+  bool Changed = false;
+  for (Function &F : M) {
+    DenseMap<Value *, Value *> CastsCache;
----------------
4ast wrote:

Overall looks great. This Cache of ACast is per function. Is it correct to reuse that operand out of every BB ? It won't break 'volatile' pointer derefs ?

https://github.com/llvm/llvm-project/pull/79902