From baf7a3c1e561ff7e3f7da2261ce1012c4f2ba1c0 Mon Sep 17 00:00:00 2001
From: Joseph Huber <huberjn@outlook.com>
Date: Tue, 11 Feb 2025 14:57:31 -0600
Subject: [PATCH] [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.
---
 offload/plugins-nextgen/common/include/RPC.h | 12 +++++++++---
 offload/plugins-nextgen/common/src/RPC.cpp   |  5 ++++-
 2 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/offload/plugins-nextgen/common/include/RPC.h b/offload/plugins-nextgen/common/include/RPC.h
index 7b031083647a..ab110dd88315 100644
--- a/offload/plugins-nextgen/common/include/RPC.h
+++ b/offload/plugins-nextgen/common/include/RPC.h
@@ -72,6 +72,9 @@ private:
   /// 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 @@ private:
     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 @@ private:
 
     /// 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"); }
 
diff --git a/offload/plugins-nextgen/common/src/RPC.cpp b/offload/plugins-nextgen/common/src/RPC.cpp
index 4289f920c0e1..70f572923d4b 100644
--- a/offload/plugins-nextgen/common/src/RPC.cpp
+++ b/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();
@@ -187,6 +188,7 @@ 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;
 
@@ -194,6 +196,7 @@ Error RPCServerTy::initDevice(plugin::GenericDeviceTy &Device,
 }
 
 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;