[Offload] Properly guard modifications to the RPC device array (#126790)

Summary:
If the user deallocates an RPC device this can sometimes fail if the RPC
server is still running. This will happen if the modification happens
while the server is still checking it. This patch adds a mutex to guard
modifications to it.

Author: jhuber6

offload/plugins-nextgen/common/include/RPC.h

@@ -72,6 +72,9 @@ struct RPCServerTy {
   /// Array of associated devices. These must be alive as long as the server is.
   std::unique_ptr<plugin::GenericDeviceTy *[]> Devices;
 
+  /// Mutex that guards accesses to the buffers and device array.
+  std::mutex BufferMutex{};
+
   /// A helper class for running the user thread that handles the RPC interface.
   /// Because we only need to check the RPC server while any kernels are
   /// working, we track submission / completion events to allow the thread to
@@ -90,6 +93,9 @@ struct RPCServerTy {
     std::condition_variable CV;
     std::mutex Mutex;
 
+    /// A reference to the main server's mutex.
+    std::mutex &BufferMutex;
+
     /// A reference to all the RPC interfaces that the server is handling.
     llvm::ArrayRef<void *> Buffers;
 
@@ -98,9 +104,9 @@ struct RPCServerTy {
 
     /// Initialize the worker thread to run in the background.
     ServerThread(void *Buffers[], plugin::GenericDeviceTy *Devices[],
-                 size_t Length)
-        : Running(false), NumUsers(0), CV(), Mutex(), Buffers(Buffers, Length),
-          Devices(Devices, Length) {}
+                 size_t Length, std::mutex &BufferMutex)
+        : Running(false), NumUsers(0), CV(), Mutex(), BufferMutex(BufferMutex),
+          Buffers(Buffers, Length), Devices(Devices, Length) {}
 
     ~ServerThread() { assert(!Running && "Thread not shut down explicitly\n"); }
 

offload/plugins-nextgen/common/src/RPC.cpp

@@ -128,6 +128,7 @@ void RPCServerTy::ServerThread::run() {
     Lock.unlock();
     while (NumUsers.load(std::memory_order_relaxed) > 0 &&
            Running.load(std::memory_order_relaxed)) {
+      std::lock_guard<decltype(Mutex)> Lock(BufferMutex);
       for (const auto &[Buffer, Device] : llvm::zip_equal(Buffers, Devices)) {
         if (!Buffer || !Device)
           continue;
@@ -146,7 +147,7 @@ RPCServerTy::RPCServerTy(plugin::GenericPluginTy &Plugin)
       Devices(std::make_unique<plugin::GenericDeviceTy *[]>(
           Plugin.getNumDevices())),
       Thread(new ServerThread(Buffers.get(), Devices.get(),
-                              Plugin.getNumDevices())) {}
+                              Plugin.getNumDevices(), BufferMutex)) {}
 
 llvm::Error RPCServerTy::startThread() {
   Thread->startThread();
@@ -187,13 +188,15 @@ Error RPCServerTy::initDevice(plugin::GenericDeviceTy &Device,
   if (auto Err = Device.dataSubmit(ClientGlobal.getPtr(), &client,
                                    sizeof(rpc::Client), nullptr))
     return Err;
+  std::lock_guard<decltype(BufferMutex)> Lock(BufferMutex);
   Buffers[Device.getDeviceId()] = RPCBuffer;
   Devices[Device.getDeviceId()] = &Device;
 
   return Error::success();
 }
 
 Error RPCServerTy::deinitDevice(plugin::GenericDeviceTy &Device) {
+  std::lock_guard<decltype(BufferMutex)> Lock(BufferMutex);
   Device.free(Buffers[Device.getDeviceId()], TARGET_ALLOC_HOST);
   Buffers[Device.getDeviceId()] = nullptr;
   Devices[Device.getDeviceId()] = nullptr;