[OpenMP] Fix target data region codegen being omitted for device pass (llvm#85218)

This patch enables the BodyCodeGen callback to still trigger for the
TargetData nested region during the device pass. There maybe Target code
nested within the TargetData region for which this is required.

Also add tests for the same.

Author: TIFitis

llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp

@@ -4883,8 +4883,11 @@ OpenMPIRBuilder::InsertPointTy OpenMPIRBuilder::createTargetData(
     return InsertPointTy();
 
   // Disable TargetData CodeGen on Device pass.
-  if (Config.IsTargetDevice.value_or(false))
+  if (Config.IsTargetDevice.value_or(false)) {
+    if (BodyGenCB)
+      Builder.restoreIP(BodyGenCB(Builder.saveIP(), BodyGenTy::NoPriv));
     return Builder.saveIP();
+  }
 
   Builder.restoreIP(CodeGenIP);
   bool IsStandAlone = !BodyGenCB;

llvm/unittests/Frontend/OpenMPIRBuilderTest.cpp

@@ -5856,6 +5856,23 @@ TEST_F(OpenMPIRBuilderTest, TargetDataRegion) {
   EXPECT_TRUE(TargetDataCall->getOperand(2)->getType()->isIntegerTy(32));
   EXPECT_TRUE(TargetDataCall->getOperand(8)->getType()->isPointerTy());
 
+  // Check that BodyGenCB is still made when IsTargetDevice is set to true.
+  OMPBuilder.Config.setIsTargetDevice(true);
+  bool CheckDevicePassBodyGen = false;
+  auto BodyTargetCB = [&](InsertPointTy CodeGenIP, BodyGenTy BodyGenType) {
+    CheckDevicePassBodyGen = true;
+    Builder.restoreIP(CodeGenIP);
+    CallInst *TargetDataCall =
+        dyn_cast<CallInst>(BB->back().getPrevNode()->getPrevNode());
+    // Make sure no begin_mapper call is present for device pass.
+    EXPECT_EQ(TargetDataCall, nullptr);
+    return Builder.saveIP();
+  };
+  Builder.restoreIP(OMPBuilder.createTargetData(
+      Loc, AllocaIP, Builder.saveIP(), Builder.getInt64(DeviceID),
+      /* IfCond= */ nullptr, Info, GenMapInfoCB, nullptr, BodyTargetCB));
+  EXPECT_TRUE(CheckDevicePassBodyGen);
+
   Builder.CreateRetVoid();
   EXPECT_FALSE(verifyModule(*M, &errs()));
 }

openmp/libomptarget/test/offloading/fortran/target-nested-target-data.f90

@@ -0,0 +1,31 @@
+! Offloading test for target nested inside
+! a target data region
+! REQUIRES: flang
+! UNSUPPORTED: nvptx64-nvidia-cuda-LTO
+! UNSUPPORTED: aarch64-unknown-linux-gnu
+! UNSUPPORTED: aarch64-unknown-linux-gnu-LTO
+! UNSUPPORTED: x86_64-pc-linux-gnu
+! UNSUPPORTED: x86_64-pc-linux-gnu-LTO
+
+! RUN: %libomptarget-compile-fortran-run-and-check-generic
+program main
+   integer :: A(10), B(10), C(10)
+
+   do I = 1, 10
+      A(I) = 1
+      B(I) = 2
+   end do
+   !$omp target data map(to: A, B) map(alloc: C)
+   !$omp target map(from: C)
+   do I = 1, 10
+      C(I) = A(I) + B(I) ! assigns 3, A:1 + B:2
+   end do
+   !$omp end target
+   !$omp target update from(C) ! updates C device -> host
+   !$omp end target data
+
+   print *, C ! should be all 3's
+
+end program
+
+! CHECK: 3 3 3 3 3 3 3 3 3 3