[BasicBlockUtils] Handle funclets when detaching EH pad blocks

llvm/lib/Transforms/Utils/BasicBlockUtils.cpp

@@ -58,6 +58,19 @@ static cl::opt<unsigned> MaxDeoptOrUnreachableSuccessorCheckDepth(
              "is followed by a block that either has a terminating "
              "deoptimizing call or is terminated with an unreachable"));
 
+static void replaceFuncletPadsRetWithUnreachable(Instruction &I) {
+  assert(isa<FuncletPadInst>(I) && "Instruction must be a funclet pad!");
+  for (User *User : make_early_inc_range(I.users())) {
+    Instruction *ReturnInstr = dyn_cast<Instruction>(User);
+    if (isa<CatchReturnInst>(ReturnInstr) ||
+        isa<CleanupReturnInst>(ReturnInstr)) {
+      BasicBlock *ReturnInstrBB = ReturnInstr->getParent();
+      ReturnInstr->eraseFromParent();
+      new UnreachableInst(ReturnInstrBB->getContext(), ReturnInstrBB);
+    }
+  }
+}
+
 void llvm::detachDeadBlocks(
     ArrayRef<BasicBlock *> BBs,
     SmallVectorImpl<DominatorTree::UpdateType> *Updates,
@@ -75,7 +88,36 @@ void llvm::detachDeadBlocks(
     // Zap all the instructions in the block.
     while (!BB->empty()) {
       Instruction &I = BB->back();
-      // If this instruction is used, replace uses with an arbitrary value.
+      // Exception handling funclets need to be explicitly addressed.
+      // These funclets must begin with cleanuppad or catchpad and end with
+      // cleanupred or catchret. The return instructions can be in different
+      // basic blocks than the pad instruction. If we would only delete the
+      // first block, the we would have possible cleanupret and catchret
+      // instructions with poison arguments, which wouldn't be valid.
+      if (isa<FuncletPadInst>(I))
+        replaceFuncletPadsRetWithUnreachable(I);
+
+      // Catchswitch instructions have handlers, that must be catchpads and
+      // an unwind label, that is either a catchpad or catchswitch.
+      if (CatchSwitchInst *CSI = dyn_cast<CatchSwitchInst>(&I)) {
+        // Iterating over the handlers and the unwind basic block and processing
+        // catchpads. If the unwind label is a catchswitch, we just replace the
+        // label with poison later on.
+        for (unsigned I = 0; I < CSI->getNumSuccessors(); I++) {
+          BasicBlock *SucBlock = CSI->getSuccessor(I);
+          Instruction &SucFstInst = *(SucBlock->getFirstNonPHIIt());
+          if (isa<FuncletPadInst>(SucFstInst)) {
+            replaceFuncletPadsRetWithUnreachable(SucFstInst);
+            // There may be catchswitch instructions using the catchpad.
+            // Just replace those with poison.
+            if (!SucFstInst.use_empty())
+              SucFstInst.replaceAllUsesWith(
+                  PoisonValue::get(SucFstInst.getType()));
+            SucFstInst.eraseFromParent();
+          }
+        }
+      }
+
       // Because control flow can't get here, we don't care what we replace the
       // value with.  Note that since this block is unreachable, and all values
       // contained within it must dominate their uses, that all uses will

llvm/test/Transforms/SimplifyCFG/unreachable-multi-basic-block-funclet.ll

@@ -0,0 +1,169 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -passes=simplifycfg -S < %s | FileCheck %s
+
+; cleanuppad/cleanupret
+
+define void @unreachable_cleanuppad_linear(i64 %shapes.1) personality ptr null {
+; CHECK-LABEL: define void @unreachable_cleanuppad_linear(
+; CHECK-SAME: i64 [[SHAPES_1:%.*]]) personality ptr null {
+; CHECK-NEXT:  [[START:.*:]]
+; CHECK-NEXT:    [[_7:%.*]] = icmp ult i64 0, [[SHAPES_1]]
+; CHECK-NEXT:    ret void
+;
+start:
+  %_7 = icmp ult i64 0, %shapes.1
+  ret void
+
+funclet:
+  %cleanuppad = cleanuppad within none []
+  br label %funclet_end
+
+funclet_end:
+  cleanupret from %cleanuppad unwind to caller
+}
+
+define void @unreachable_cleanuppad_multiple_predecessors(i64 %shapes.1) personality ptr null {
+; CHECK-LABEL: define void @unreachable_cleanuppad_multiple_predecessors(
+; CHECK-SAME: i64 [[SHAPES_1:%.*]]) personality ptr null {
+; CHECK-NEXT:  [[START:.*:]]
+; CHECK-NEXT:    [[_7:%.*]] = icmp ult i64 0, [[SHAPES_1]]
+; CHECK-NEXT:    ret void
+;
+start:
+  %_7 = icmp ult i64 0, %shapes.1
+  ret void
+
+funclet:
+  %cleanuppad = cleanuppad within none []
+  switch i64 %shapes.1, label %otherwise [ i64 0, label %one
+  i64 1, label %two
+  i64 42, label %three ]
+one:
+  br label %funclet_end
+
+two:
+  br label %funclet_end
+
+three:
+  br label %funclet_end
+
+otherwise:
+  br label %funclet_end
+
+funclet_end:
+  cleanupret from %cleanuppad unwind to caller
+}
+
+; catchpad/catchret
+
+define void @unreachable_catchpad_linear(i64 %shapes.1) personality ptr null {
+; CHECK-LABEL: define void @unreachable_catchpad_linear(
+; CHECK-SAME: i64 [[SHAPES_1:%.*]]) personality ptr null {
+; CHECK-NEXT:  [[START:.*:]]
+; CHECK-NEXT:    [[_7:%.*]] = icmp ult i64 0, [[SHAPES_1]]
+; CHECK-NEXT:    ret void
+;
+start:
+  %_7 = icmp ult i64 0, %shapes.1
+  ret void
+
+dispatch:
+  %cs = catchswitch within none [label %funclet] unwind to caller
+
+funclet:
+  %cleanuppad = catchpad within %cs []
+  br label %funclet_end
+
+
+funclet_end:
+  catchret from %cleanuppad to label %unreachable
+
+unreachable:
+  unreachable
+}
+
+define void @unreachable_catchpad_multiple_predecessors(i64 %shapes.1) personality ptr null {
+; CHECK-LABEL: define void @unreachable_catchpad_multiple_predecessors(
+; CHECK-SAME: i64 [[SHAPES_1:%.*]]) personality ptr null {
+; CHECK-NEXT:  [[START:.*:]]
+; CHECK-NEXT:    [[_7:%.*]] = icmp ult i64 0, [[SHAPES_1]]
+; CHECK-NEXT:    ret void
+;
+start:
+  %_7 = icmp ult i64 0, %shapes.1
+  ret void
+
+dispatch:
+  %cs = catchswitch within none [label %funclet] unwind to caller
+
+funclet:
+  %cleanuppad = catchpad within %cs []
+  switch i64 %shapes.1, label %otherwise [ i64 0, label %one
+  i64 1, label %two
+  i64 42, label %three ]
+one:
+  br label %funclet_end
+
+two:
+  br label %funclet_end
+
+three:
+  br label %funclet_end
+
+otherwise:
+  br label %funclet_end
+
+funclet_end:
+  catchret from %cleanuppad to label %unreachable
+
+unreachable:
+  unreachable
+}
+
+; Issue reproducer
+
+define void @gh148052(i64 %shapes.1) personality ptr null {
+; CHECK-LABEL: define void @gh148052(
+; CHECK-SAME: i64 [[SHAPES_1:%.*]]) personality ptr null {
+; CHECK-NEXT:  [[START:.*:]]
+; CHECK-NEXT:    [[_7:%.*]] = icmp ult i64 0, [[SHAPES_1]]
+; CHECK-NEXT:    call void @llvm.assume(i1 [[_7]])
+; CHECK-NEXT:    ret void
+;
+start:
+  %_7 = icmp ult i64 0, %shapes.1
+  br i1 %_7, label %bb1, label %panic
+
+bb1:
+  %_11 = icmp ult i64 0, %shapes.1
+  br i1 %_11, label %bb3, label %panic1
+
+panic:
+  unreachable
+
+bb3:
+  ret void
+
+panic1:
+  invoke void @func(i64 0, i64 0, ptr null)
+  to label %unreachable unwind label %funclet_bb14
+
+funclet_bb14:
+  %cleanuppad = cleanuppad within none []
+  br label %bb13
+
+unreachable:
+  unreachable
+
+bb10:
+  cleanupret from %cleanuppad5 unwind to caller
+
+funclet_bb10:
+  %cleanuppad5 = cleanuppad within none []
+  br label %bb10
+
+bb13:
+  cleanupret from %cleanuppad unwind label %funclet_bb10
+}
+
+declare void @func(i64, i64, ptr)