xprtrdma: Use gathered Send for large inline messages

An RPC Call message that is sent inline but that has a data payload
(ie, one or more items in rq_snd_buf's page list) must be "pulled
up:"

- call_allocate has to reserve enough RPC Call buffer space to
accommodate the data payload

- call_transmit has to memcopy the rq_snd_buf's page list and tail
into its head iovec before it is sent

As the inline threshold is increased beyond its current 1KB default,
however, this means data payloads of more than a few KB are copied
by the host CPU. For example, if the inline threshold is increased
just to 4KB, then NFS WRITE requests up to 4KB would involve a
memcpy of the NFS WRITE's payload data into the RPC Call buffer.
This is an undesirable amount of participation by the host CPU.

The inline threshold may be much larger than 4KB in the future,
after negotiation with a peer server.

Instead of copying the components of rq_snd_buf into its head iovec,
construct a gather list of these components, and send them all in
place. The same approach is already used in the Linux server's
RPC-over-RDMA reply path.

This mechanism also eliminates the need for rpcrdma_tail_pullup,
which is used to manage the XDR pad and trailing inline content when
a Read list is present.

This requires that the pages in rq_snd_buf's page list be DMA-mapped
during marshaling, and unmapped when a data-bearing RPC is
completed. This is slightly less efficient for very small I/O
payloads, but significantly more efficient as data payload size and
inline threshold increase past a kilobyte.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

1 files changed, 25 insertions, 2 deletions

diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 64b4e22..b2823d9 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -285,16 +285,27 @@ struct rpcrdma_mr_seg {		/* chunk descriptors */
 	char		*mr_offset;	/* kva if no page, else offset */
 };
 
-#define RPCRDMA_MAX_IOVS	(2)
+/* Reserve enough Send SGEs to send a maximum size inline request:
+ * - RPC-over-RDMA header
+ * - xdr_buf head iovec
+ * - RPCRDMA_MAX_INLINE bytes, possibly unaligned, in pages
+ * - xdr_buf tail iovec
+ */
+enum {
+	RPCRDMA_MAX_SEND_PAGES = PAGE_SIZE + RPCRDMA_MAX_INLINE - 1,
+	RPCRDMA_MAX_PAGE_SGES = (RPCRDMA_MAX_SEND_PAGES >> PAGE_SHIFT) + 1,
+	RPCRDMA_MAX_SEND_SGES = 1 + 1 + RPCRDMA_MAX_PAGE_SGES + 1,
+};
 
 struct rpcrdma_buffer;
 struct rpcrdma_req {
 	struct list_head	rl_free;
+	unsigned int		rl_mapped_sges;
 	unsigned int		rl_connect_cookie;
 	struct rpcrdma_buffer	*rl_buffer;
 	struct rpcrdma_rep	*rl_reply;
 	struct ib_send_wr	rl_send_wr;
-	struct ib_sge		rl_send_iov[RPCRDMA_MAX_IOVS];
+	struct ib_sge		rl_send_sge[RPCRDMA_MAX_SEND_SGES];
 	struct rpcrdma_regbuf	*rl_rdmabuf;	/* xprt header */
 	struct rpcrdma_regbuf	*rl_sendbuf;	/* rq_snd_buf */
 	struct rpcrdma_regbuf	*rl_recvbuf;	/* rq_rcv_buf */
@@ -529,6 +540,18 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *);
 /*
  * RPC/RDMA protocol calls - xprtrdma/rpc_rdma.c
  */
+
+enum rpcrdma_chunktype {
+	rpcrdma_noch = 0,
+	rpcrdma_readch,
+	rpcrdma_areadch,
+	rpcrdma_writech,
+	rpcrdma_replych
+};
+
+bool rpcrdma_prepare_send_sges(struct rpcrdma_ia *, struct rpcrdma_req *,
+			       u32, struct xdr_buf *, enum rpcrdma_chunktype);
+void rpcrdma_unmap_sges(struct rpcrdma_ia *, struct rpcrdma_req *);
 int rpcrdma_marshal_req(struct rpc_rqst *);
 void rpcrdma_set_max_header_sizes(struct rpcrdma_xprt *);