contrib/rdmacm-mux: Add implementation of RDMA User MAD multiplexer

RDMA MAD kernel module (ibcm) disallow more than one MAD-agent for a
given MAD class.
This does not go hand-by-hand with qemu pvrdma device's requirements
where each VM is MAD agent.
Fix it by adding implementation of RDMA MAD multiplexer service which on
one hand register as a sole MAD agent with the kernel module and on the
other hand gives service to more than one VM.

Design Overview:
Reviewed-by: Shamir Rabinovitch <shamir.rabinovitch@oracle.com>
----------------
A server process is registered to UMAD framework (for this to work the
rdma_cm kernel module needs to be unloaded) and creates a unix socket to
listen to incoming request from clients.
A client process (such as QEMU) connects to this unix socket and
registers with its own GID.

TX:
----
When client needs to send rdma_cm MAD message it construct it the same
way as without this multiplexer, i.e. creates a umad packet but this
time it writes its content to the socket instead of calling umad_send().
The server, upon receiving such a message fetch local_comm_id from it so
a context for this session can be maintain and relay the message to UMAD
layer by calling umad_send().

RX:
----
The server creates a worker thread to process incoming rdma_cm MAD
messages. When an incoming message arrived (umad_recv()) the server,
depending on the message type (attr_id) looks for target client by
either searching in gid->fd table or in local_comm_id->fd table. With
the extracted fd the server relays to incoming message to the client.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Shamir Rabinovitch <shamir.rabinovitch@oracle.com>
Signed-off-by: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>

MAINTAINERS

@@ -2412,6 +2412,7 @@ S: Maintained
 F: hw/rdma/*
 F: hw/rdma/vmw/*
 F: docs/pvrdma.txt
+F: contrib/rdmacm-mux/*
 
 Build and test automation
 -------------------------

Makefile

@@ -362,6 +362,7 @@ dummy := $(call unnest-vars,, \
                 elf2dmp-obj-y \
                 ivshmem-client-obj-y \
                 ivshmem-server-obj-y \
+                rdmacm-mux-obj-y \
                 libvhost-user-obj-y \
                 vhost-user-scsi-obj-y \
                 vhost-user-blk-obj-y \
@@ -579,6 +580,8 @@ vhost-user-scsi$(EXESUF): $(vhost-user-scsi-obj-y) libvhost-user.a
 	$(call LINK, $^)
 vhost-user-blk$(EXESUF): $(vhost-user-blk-obj-y) libvhost-user.a
 	$(call LINK, $^)
+rdmacm-mux$(EXESUF): $(rdmacm-mux-obj-y) $(COMMON_LDADDS)
+	$(call LINK, $^)
 
 module_block.h: $(SRC_PATH)/scripts/modules/module_block.py config-host.mak
 	$(call quiet-command,$(PYTHON) $< $@ \

Makefile.objs

@@ -133,6 +133,7 @@ vhost-user-scsi.o-cflags := $(LIBISCSI_CFLAGS)
 vhost-user-scsi.o-libs := $(LIBISCSI_LIBS)
 vhost-user-scsi-obj-y = contrib/vhost-user-scsi/
 vhost-user-blk-obj-y = contrib/vhost-user-blk/
+rdmacm-mux-obj-y = contrib/rdmacm-mux/
 
 ######################################################################
 trace-events-subdirs =

contrib/rdmacm-mux/Makefile.objs

@@ -0,0 +1,4 @@
+ifdef CONFIG_PVRDMA
+CFLAGS += -libumad -Wno-format-truncation
+rdmacm-mux-obj-y = main.o
+endif

contrib/rdmacm-mux/rdmacm-mux.h

@@ -0,0 +1,61 @@
+/*
+ * QEMU paravirtual RDMA - rdmacm-mux declarations
+ *
+ * Copyright (C) 2018 Oracle
+ * Copyright (C) 2018 Red Hat Inc
+ *
+ * Authors:
+ *     Yuval Shaia <yuval.shaia@oracle.com>
+ *     Marcel Apfelbaum <marcel@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef RDMACM_MUX_H
+#define RDMACM_MUX_H
+
+#include "linux/if.h"
+#include "infiniband/verbs.h"
+#include "infiniband/umad.h"
+#include "rdma/rdma_user_cm.h"
+
+typedef enum RdmaCmMuxMsgType {
+    RDMACM_MUX_MSG_TYPE_REQ   = 0,
+    RDMACM_MUX_MSG_TYPE_RESP  = 1,
+} RdmaCmMuxMsgType;
+
+typedef enum RdmaCmMuxOpCode {
+    RDMACM_MUX_OP_CODE_REG   = 0,
+    RDMACM_MUX_OP_CODE_UNREG = 1,
+    RDMACM_MUX_OP_CODE_MAD   = 2,
+} RdmaCmMuxOpCode;
+
+typedef enum RdmaCmMuxErrCode {
+    RDMACM_MUX_ERR_CODE_OK        = 0,
+    RDMACM_MUX_ERR_CODE_EINVAL    = 1,
+    RDMACM_MUX_ERR_CODE_EEXIST    = 2,
+    RDMACM_MUX_ERR_CODE_EACCES    = 3,
+    RDMACM_MUX_ERR_CODE_ENOTFOUND = 4,
+} RdmaCmMuxErrCode;
+
+typedef struct RdmaCmMuxHdr {
+    RdmaCmMuxMsgType msg_type;
+    RdmaCmMuxOpCode op_code;
+    union ibv_gid sgid;
+    RdmaCmMuxErrCode err_code;
+} RdmaCmUHdr;
+
+typedef struct RdmaCmUMad {
+    struct ib_user_mad hdr;
+    char mad[RDMA_MAX_PRIVATE_DATA];
+} RdmaCmUMad;
+
+typedef struct RdmaCmMuxMsg {
+    RdmaCmUHdr hdr;
+    int umad_len;
+    RdmaCmUMad umad;
+} RdmaCmMuxMsg;
+
+#endif