[PATCH] RPC: skip over transport-specific heads automatically

 Add a generic mechanism for skipping over transport-specific headers
 when constructing an RPC request.  This removes another "xprt->stream"
 dependency.

 Test-plan:
 Write-intensive workload on a single mount point (try both UDP and
 TCP).

 Signed-off-by: Chuck Lever <cel@netapp.com>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>

2 files changed, 32 insertions, 0 deletions

diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h
index 15f11533238..f43f237360a 100644
--- a/include/linux/sunrpc/msg_prot.h
+++ b/include/linux/sunrpc/msg_prot.h
@@ -76,5 +76,30 @@ enum rpc_auth_stat {
 
 #define RPC_MAXNETNAMELEN	256
 
+/*
+ * From RFC 1831:
+ *
+ * "A record is composed of one or more record fragments.  A record
+ *  fragment is a four-byte header followed by 0 to (2**31) - 1 bytes of
+ *  fragment data.  The bytes encode an unsigned binary number; as with
+ *  XDR integers, the byte order is from highest to lowest.  The number
+ *  encodes two values -- a boolean which indicates whether the fragment
+ *  is the last fragment of the record (bit value 1 implies the fragment
+ *  is the last fragment) and a 31-bit unsigned binary value which is the
+ *  length in bytes of the fragment's data.  The boolean value is the
+ *  highest-order bit of the header; the length is the 31 low-order bits.
+ *  (Note that this record specification is NOT in XDR standard form!)"
+ *
+ * The Linux RPC client always sends its requests in a single record
+ * fragment, limiting the maximum payload size for stream transports to
+ * 2GB.
+ */
+
+typedef u32	rpc_fraghdr;
+
+#define	RPC_LAST_STREAM_FRAGMENT	(1U << 31)
+#define	RPC_FRAGMENT_SIZE_MASK		(~RPC_LAST_STREAM_FRAGMENT)
+#define	RPC_MAX_FRAGMENT_SIZE		((1U << 31) - 1)
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_SUNRPC_MSGPROT_H_ */
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index e73174c7e45..966c456a0f6 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -155,6 +155,8 @@ struct rpc_xprt {
 
 	size_t			max_payload;	/* largest RPC payload size,
 						   in bytes */
+	unsigned int		tsh_size;	/* size of transport specific
+						   header */
 
 	struct rpc_wait_queue	sending;	/* requests waiting to send */
 	struct rpc_wait_queue	resend;		/* requests waiting to resend */
@@ -236,6 +238,11 @@ int			xprt_adjust_timeout(struct rpc_rqst *req);
 void			xprt_release(struct rpc_task *task);
 int			xprt_destroy(struct rpc_xprt *xprt);
 
+static inline u32 *xprt_skip_transport_header(struct rpc_xprt *xprt, u32 *p)
+{
+	return p + xprt->tsh_size;
+}
+
 /*
  * Transport switch helper functions
  */