svc: Add transport hdr size for defer/revisit

Some transports have a header in front of the RPC header. The current
defer/revisit processing considers only the iov_len and arg_len to
determine how much to back up when saving the original request
to revisit. Add a field to the rqstp structure to save the size
of the transport header so svc_defer can correctly compute
the start of a request.

Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Acked-by: Neil Brown <neilb@suse.de>
Reviewed-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Greg Banks <gnb@sgi.com>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>

diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 04eb20e..742ab46 100644 (file)
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -217,6 +217,7 @@ struct svc_rqst {
        void *                  rq_xprt_ctxt;   /* transport specific context ptr */
        struct svc_deferred_req*rq_deferred;    /* deferred request we are replaying */
 
+       size_t                  rq_xprt_hlen;   /* xprt header len */
        struct xdr_buf          rq_arg;
        struct xdr_buf          rq_res;
        struct page *           rq_pages[RPCSVC_MAXPAGES];
@@ -322,6 +323,7 @@ struct svc_deferred_req {
        size_t                  addrlen;
        union svc_addr_u        daddr;  /* where reply must come from */
        struct cache_deferred_req handle;
+       size_t                  xprt_hlen;
        int                     argslen;
        __be32                  args[0];
 };

diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 23165ae..000c7dc 100644 (file)
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -29,7 +29,6 @@
 #include <linux/sunrpc/types.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/xdr.h>
-#include <linux/sunrpc/svcsock.h>
 #include <linux/sunrpc/stats.h>
 #include <linux/sunrpc/svc_xprt.h>
 
@@ -859,10 +858,18 @@ static void svc_revisit(struct cache_deferred_req *dreq, int too_many)
        svc_xprt_put(xprt);
 }
 
+/*
+ * Save the request off for later processing. The request buffer looks
+ * like this:
+ *
+ * <xprt-header><rpc-header><rpc-pagelist><rpc-tail>
+ *
+ * This code can only handle requests that consist of an xprt-header
+ * and rpc-header.
+ */
 static struct cache_deferred_req *svc_defer(struct cache_req *req)
 {
        struct svc_rqst *rqstp = container_of(req, struct svc_rqst, rq_chandle);
-       int size = sizeof(struct svc_deferred_req) + (rqstp->rq_arg.len);
        struct svc_deferred_req *dr;
 
        if (rqstp->rq_arg.page_len)
@@ -871,8 +878,10 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req)
                dr = rqstp->rq_deferred;
                rqstp->rq_deferred = NULL;
        } else {
-               int skip  = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len;
+               size_t skip;
+               size_t size;
                /* FIXME maybe discard if size too large */
+               size = sizeof(struct svc_deferred_req) + rqstp->rq_arg.len;
                dr = kmalloc(size, GFP_KERNEL);
                if (dr == NULL)
                        return NULL;
@@ -883,8 +892,12 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req)
                dr->addrlen = rqstp->rq_addrlen;
                dr->daddr = rqstp->rq_daddr;
                dr->argslen = rqstp->rq_arg.len >> 2;
-               memcpy(dr->args, rqstp->rq_arg.head[0].iov_base-skip,
-                      dr->argslen<<2);
+               dr->xprt_hlen = rqstp->rq_xprt_hlen;
+
+               /* back up head to the start of the buffer and copy */
+               skip = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len;
+               memcpy(dr->args, rqstp->rq_arg.head[0].iov_base - skip,
+                      dr->argslen << 2);
        }
        svc_xprt_get(rqstp->rq_xprt);
        dr->xprt = rqstp->rq_xprt;
@@ -900,16 +913,21 @@ static int svc_deferred_recv(struct svc_rqst *rqstp)
 {
        struct svc_deferred_req *dr = rqstp->rq_deferred;
 
-       rqstp->rq_arg.head[0].iov_base = dr->args;
-       rqstp->rq_arg.head[0].iov_len = dr->argslen<<2;
+       /* setup iov_base past transport header */
+       rqstp->rq_arg.head[0].iov_base = dr->args + (dr->xprt_hlen>>2);
+       /* The iov_len does not include the transport header bytes */
+       rqstp->rq_arg.head[0].iov_len = (dr->argslen<<2) - dr->xprt_hlen;
        rqstp->rq_arg.page_len = 0;
-       rqstp->rq_arg.len = dr->argslen<<2;
+       /* The rq_arg.len includes the transport header bytes */
+       rqstp->rq_arg.len     = dr->argslen<<2;
        rqstp->rq_prot        = dr->prot;
        memcpy(&rqstp->rq_addr, &dr->addr, dr->addrlen);
        rqstp->rq_addrlen     = dr->addrlen;
+       /* Save off transport header len in case we get deferred again */
+       rqstp->rq_xprt_hlen   = dr->xprt_hlen;
        rqstp->rq_daddr       = dr->daddr;
        rqstp->rq_respages    = rqstp->rq_pages;
-       return dr->argslen<<2;
+       return (dr->argslen<<2) - dr->xprt_hlen;
 }
 
 

diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 343a85b..1d3e5fc 100644 (file)
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -315,6 +315,8 @@ static int svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr,
        };
        int len;
 
+       rqstp->rq_xprt_hlen = 0;
+
        len = kernel_recvmsg(svsk->sk_sock, &msg, iov, nr, buflen,
                                msg.msg_flags);