[libc] Cache ownership of the shared buffer in the port

[jhuber6]

Summary

This patch adds another variable to cache cases where we know that we
own the buffer. This allows us to skip the atomic load on the inbox
because we already know its state. This is legal immediately after
opening a port, or when sending immediately after a recieve. This
caching nets a significant (~17%) speedup for the basic open, send,
recieve combination.

[jhuber6]

Fix

[JonChesterfield]

LG. I think the expected use case of this port is an object that gets disassembled by SROA so there's a decent chance the extra boolean is removed before codegen.

libc/src/__support/RPC/rpc.h

343

This out field could be a bool too, it's a similar sort of thing to receive/owns_buffer

libc/src/__support/RPC/rpc.h

 
 /// The port provides the interface to communicate between the multiple
 /// processes. A port is conceptually an index into the memory provided by the
 /// underlying process that is guarded by a lock bit.
 template <bool T> struct Port {
   LIBC_INLINE Port(Process<T> &process, uint64_t lane_mask, uint64_t index,
                    uint32_t out)
       : process(process), lane_mask(lane_mask), index(index), out(out),
-        receive(false) {}
+        receive(false), owns_buffer(true) {}
   LIBC_INLINE ~Port() = default;
 
 private:
   LIBC_INLINE Port(const Port &) = delete;
   LIBC_INLINE Port &operator=(const Port &) = delete;
   LIBC_INLINE Port(Port &&) = default;
   LIBC_INLINE Port &operator=(Port &&) = default;
 
public:
   template <typename A>
   LIBC_INLINE void recv_n(void **dst, uint64_t *size, A &&alloc);
 
   LIBC_INLINE uint16_t get_opcode() const {
     return process.get_packet(index).header.opcode;
   }
 
   LIBC_INLINE void close() {
-    // If the server last did a receive it needs to exchange ownership before
-    // closing the port.
-    if (receive && T)
+    // The server is passive, if it own the buffer when it closes we need to
+    // give ownership back to the client.
+    if (owns_buffer && T)
       out = process.invert_outbox(index, out);
     process.unlock(lane_mask, index);
   }
 
 private:
   Process<T> &process;
   uint64_t lane_mask;
   uint64_t index;
   uint32_t out;
   bool receive;
+  bool owns_buffer;
 };
 
 /// The RPC client used to make requests to the server.
 struct Client : public Process<false> {
   LIBC_INLINE Client() = default;
   LIBC_INLINE Client(const Client &) = delete;
   LIBC_INLINE Client &operator=(const Client &) = delete;
   LIBC_INLINE ~Client() = default;
struct Server : public Process<true> {
 
   using Port = rpc::Port<true>;
   LIBC_INLINE cpp::optional<Port> try_open();
   LIBC_INLINE Port open();
 };
 
 /// Applies \p fill to the shared buffer and initiates a send operation.
 template <bool T> template <typename F> LIBC_INLINE void Port<T>::send(F fill) {
-  uint32_t in = process.load_inbox(index);
+  uint32_t in = owns_buffer ? out ^ T : process.load_inbox(index);
 
   // We need to wait until we own the buffer before sending.
   while (Process<T>::buffer_unavailable(in, out)) {
     sleep_briefly();
     in = process.load_inbox(index);
   }
 
   // Apply the \p fill function to initialize the buffer and release the memory.
   process.invoke_rpc(fill, process.get_packet(index));
   atomic_thread_fence(cpp::MemoryOrder::RELEASE);
   out = process.invert_outbox(index, out);
+  owns_buffer = false;
   receive = false;
 }
 
 /// Applies \p use to the shared buffer and acknowledges the send.
 template <bool T> template <typename U> LIBC_INLINE void Port<T>::recv(U use) {
   // We only exchange ownership of the buffer during a receive if we are waiting
   // for a previous receive to finish.
-  if (receive)
+  if (receive) {
     out = process.invert_outbox(index, out);
+    owns_buffer = false;
+  }
 
-  uint32_t in = process.load_inbox(index);
+  uint32_t in = owns_buffer ? out ^ T : process.load_inbox(index);
 
   // We need to wait until we own the buffer before receiving.
   while (Process<T>::buffer_unavailable(in, out)) {
     sleep_briefly();
     in = process.load_inbox(index);
   }
   atomic_thread_fence(cpp::MemoryOrder::ACQUIRE);
 
   // Apply the \p use function to read the memory out of the buffer.
   process.invoke_rpc(use, process.get_packet(index));
   receive = true;
+  owns_buffer = true;
 }
 
 /// Combines a send and receive into a single function.
 template <bool T>
 template <typename F, typename U>
 LIBC_INLINE void Port<T>::send_and_recv(F fill, U use) {
   send(fill);
   recv(use);