[libomptarget][nextgen-plugin] Add missing mutex lock

[doru1004]

It looks like there is a potentially missing lock in the waitOnStreamOperation.

[llvmbot]

@llvm/pr-subscribers-backend-amdgpu

Author: Gheorghe-Teodor Bercea (doru1004)

Changes

It looks like there is a potentially missing lock in the waitOnStreamOperation.

---

Full diff: https://github.com/llvm/llvm-project/pull/83455.diff

1 Files Affected:

• (modified) openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp (+4-1)

diff --git a/openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp b/openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp
index 81634ae1edc490..92a4b66955c7a5 100644
--- a/openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp
+++ b/openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp
@@ -1093,7 +1093,10 @@ struct AMDGPUStreamTy {
     if (Queue == nullptr)
       return Plugin::error("Target queue was nullptr");
 
-    /// The signal that we must wait from the other stream.
+    // Guard access to the Slots data structure.
+    std::lock_guard<std::mutex> Lock(Mutex);
+
+    // The signal that we must wait from the other stream.
     AMDGPUSignalTy *OtherSignal = OtherStream.Slots[Slot].Signal;
 
     // Prevent the release of the other stream's signal.

[jplehr]

Looks reasonable to me.

[dhruvachak]

In the caller of waitOnStreamOperation, there is below locking. Can you explain why we still need additional locking?

---

Error AMDGPUStreamTy::waitEvent(const AMDGPUEventTy &Event) {
// Retrieve the recorded stream on the event.
AMDGPUStreamTy &RecordedStream = *Event.RecordedStream;

std::scoped_lock<std::mutex, std::mutex> Lock(Mutex, RecordedStream.Mutex);