svcrdma: Introduce local rdma_rw API helpers

The plan is to replace the local bespoke code that constructs and
posts RDMA Read and Write Work Requests with calls to the rdma_rw
API. This shares code with other RDMA-enabled ULPs that manages the
gory details of buffer registration and posting Work Requests.

Some design notes:

 o The structure of RPC-over-RDMA transport headers is flexible,
   allowing multiple segments per Reply with arbitrary alignment,
   each with a unique R_key. Write and Send WRs continue to be
   built and posted in separate code paths. However, one whole
   chunk (with one or more RDMA segments apiece) gets exactly
   one ib_post_send and one work completion.

 o svc_xprt reference counting is modified, since a chain of
   rdma_rw_ctx structs generates one completion, no matter how
   many Write WRs are posted.

 o The current code builds the transport header as it is construct-
   ing Write WRs. I've replaced that with marshaling of transport
   header data items in a separate step. This is because the exact
   structure of client-provided segments may not align with the
   components of the server's reply xdr_buf, or the pages in the
   page list. Thus parts of each client-provided segment may be
   written at different points in the send path.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>

include/linux/sunrpc/svc_rdma.h

@@ -145,12 +145,15 @@ struct svcxprt_rdma {
 	u32		     sc_max_requests;	/* Max requests */
 	u32		     sc_max_bc_requests;/* Backward credits */
 	int                  sc_max_req_size;	/* Size of each RQ WR buf */
+	u8		     sc_port_num;
 
 	struct ib_pd         *sc_pd;
 
 	spinlock_t	     sc_ctxt_lock;
 	struct list_head     sc_ctxts;
 	int		     sc_ctxt_used;
+	spinlock_t	     sc_rw_ctxt_lock;
+	struct list_head     sc_rw_ctxts;
 	spinlock_t	     sc_map_lock;
 	struct list_head     sc_maps;
 
@@ -224,6 +227,14 @@ extern int rdma_read_chunk_frmr(struct svcxprt_rdma *, struct svc_rqst *,
 				struct svc_rdma_op_ctxt *, int *, u32 *,
 				u32, u32, u64, bool);
 
+/* svc_rdma_rw.c */
+extern void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma);
+extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
+				     __be32 *wr_ch, struct xdr_buf *xdr);
+extern int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma,
+				     __be32 *rp_ch, bool writelist,
+				     struct xdr_buf *xdr);
+
 /* svc_rdma_sendto.c */
 extern int svc_rdma_map_xdr(struct svcxprt_rdma *, struct xdr_buf *,
 			    struct svc_rdma_req_map *, bool);

net/sunrpc/Kconfig

@@ -52,6 +52,7 @@ config SUNRPC_XPRT_RDMA
 	tristate "RPC-over-RDMA transport"
 	depends on SUNRPC && INFINIBAND && INFINIBAND_ADDR_TRANS
 	default SUNRPC && INFINIBAND
+	select SG_POOL
 	help
 	  This option allows the NFS client and server to use RDMA
 	  transports (InfiniBand, iWARP, or RoCE).

net/sunrpc/xprtrdma/Makefile

@@ -4,5 +4,5 @@ rpcrdma-y := transport.o rpc_rdma.o verbs.o \
 	fmr_ops.o frwr_ops.o \
 	svc_rdma.o svc_rdma_backchannel.o svc_rdma_transport.o \
 	svc_rdma_marshal.o svc_rdma_sendto.o svc_rdma_recvfrom.o \
-	module.o
+	svc_rdma_rw.o module.o
 rpcrdma-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel.o

net/sunrpc/xprtrdma/svc_rdma_transport.c

@@ -561,6 +561,7 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv,
 	INIT_LIST_HEAD(&cma_xprt->sc_read_complete_q);
 	INIT_LIST_HEAD(&cma_xprt->sc_frmr_q);
 	INIT_LIST_HEAD(&cma_xprt->sc_ctxts);
+	INIT_LIST_HEAD(&cma_xprt->sc_rw_ctxts);
 	INIT_LIST_HEAD(&cma_xprt->sc_maps);
 	init_waitqueue_head(&cma_xprt->sc_send_wait);
 
@@ -568,6 +569,7 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv,
 	spin_lock_init(&cma_xprt->sc_rq_dto_lock);
 	spin_lock_init(&cma_xprt->sc_frmr_q_lock);
 	spin_lock_init(&cma_xprt->sc_ctxt_lock);
+	spin_lock_init(&cma_xprt->sc_rw_ctxt_lock);
 	spin_lock_init(&cma_xprt->sc_map_lock);
 
 	/*
@@ -999,6 +1001,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 		newxprt, newxprt->sc_cm_id);
 
 	dev = newxprt->sc_cm_id->device;
+	newxprt->sc_port_num = newxprt->sc_cm_id->port_num;
 
 	/* Qualify the transport resource defaults with the
 	 * capabilities of this particular device */
@@ -1248,6 +1251,7 @@ static void __svc_rdma_free(struct work_struct *work)
 	}
 
 	rdma_dealloc_frmr_q(rdma);
+	svc_rdma_destroy_rw_ctxts(rdma);
 	svc_rdma_destroy_ctxts(rdma);
 	svc_rdma_destroy_maps(rdma);