Implement RDMA receive with memory copying (send remains zero-copy)

This is the simplest and, as usual, the best implementation :)

100% zero-copy implementation is also possible (see rdma-zerocopy branch),
but it requires to create A LOT of queues (~128 per client) to use QPN as a 'tag'
because of the lack of receive tags and the server may simply run out of queues.
Hardware limit is 262144 on Mellanox ConnectX-4 which amounts to only 2048
'connections' per host. And even with that amount of queues it's still less optimal
than the non-zerocopy one.

In fact, newest hardware like Mellanox ConnectX-5 does have Tag Matching
support, but it's still unsuitable for us because it doesn't support scatter/gather
(tm_caps.max_sge=1).

src/msgr_rdma.h

@@ -1,8 +1,14 @@
+// Copyright (c) Vitaliy Filippov, 2019+
+// License: VNPL-1.1 or GNU GPL-2.0+ (see README.md for details)
+
 #pragma once
 #include <infiniband/verbs.h>
 #include <string>
 #include <vector>
 
+// FIXME: Allow to configure this option
+#define RDMA_MAX_MSG 4194304
+
 struct msgr_rdma_address_t
 {
     ibv_gid gid;
@@ -46,6 +52,7 @@ struct msgr_rdma_connection_t
 
     int send_pos = 0, send_buf_pos = 0;
     int recv_pos = 0, recv_buf_pos = 0;
+    std::vector<void*> recv_buffers;
 
     ~msgr_rdma_connection_t();
     static msgr_rdma_connection_t *create(msgr_rdma_context_t *ctx, uint32_t max_send, uint32_t max_recv, uint32_t max_sge);