svcrdma: Do not send Write chunk XDR pad with inline content

The NFS server's XDR encoders adds an XDR pad for content in the
xdr_buf page list at the beginning of the xdr_buf's tail buffer.

On RDMA transports, Write chunks are sent separately and without an
XDR pad.

If a Write chunk is being sent, strip off the pad in the tail buffer
so that inline content following the Write chunk remains XDR-aligned
when it is sent to the client.

BugLink: https://bugzilla.linux-nfs.org/show_bug.cgi?id=294
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>

3 files changed, 19 insertions, 7 deletions

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 5322fea6fe4c..40b678584041 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -224,7 +224,7 @@ extern int rdma_read_chunk_frmr(struct svcxprt_rdma *, struct svc_rqst *,
 
 /* svc_rdma_sendto.c */
 extern int svc_rdma_map_xdr(struct svcxprt_rdma *, struct xdr_buf *,
-                            struct svc_rdma_req_map *);
+                            struct svc_rdma_req_map *, bool);
 extern int svc_rdma_sendto(struct svc_rqst *);
 extern struct rpcrdma_read_chunk *
         svc_rdma_get_read_chunk(struct rpcrdma_msg *);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index 65a7c232a345..de3919624fac 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -107,7 +107,7 @@ static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma,
         int ret;
 
         vec = svc_rdma_get_req_map(rdma);
-        ret = svc_rdma_map_xdr(rdma, sndbuf, vec);
+        ret = svc_rdma_map_xdr(rdma, sndbuf, vec, false);
         if (ret)
                 goto out_err;
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 86fea5c59125..a8fab9968891 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -57,7 +57,8 @@ static u32 xdr_padsize(u32 len)
 
 int svc_rdma_map_xdr(struct svcxprt_rdma *xprt,
                      struct xdr_buf *xdr,
-                     struct svc_rdma_req_map *vec)
+                     struct svc_rdma_req_map *vec,
+                     bool write_chunk_present)
 {
         int sge_no;
         u32 sge_bytes;
@@ -97,9 +98,20 @@ int svc_rdma_map_xdr(struct svcxprt_rdma *xprt,
 
         /* Tail SGE */
         if (xdr->tail[0].iov_len) {
-                vec->sge[sge_no].iov_base = xdr->tail[0].iov_base;
-                vec->sge[sge_no].iov_len = xdr->tail[0].iov_len;
-                sge_no++;
+                unsigned char *base = xdr->tail[0].iov_base;
+                size_t len = xdr->tail[0].iov_len;
+                u32 xdr_pad = xdr_padsize(xdr->page_len);
+
+                if (write_chunk_present && xdr_pad) {
+                        base += xdr_pad;
+                        len -= xdr_pad;
+                }
+
+                if (len) {
+                        vec->sge[sge_no].iov_base = base;
+                        vec->sge[sge_no].iov_len = len;
+                        sge_no++;
+                }
         }
 
         dprintk("svcrdma: %s: sge_no %d page_no %d "
@@ -594,7 +606,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
         ctxt = svc_rdma_get_context(rdma);
         ctxt->direction = DMA_TO_DEVICE;
         vec = svc_rdma_get_req_map(rdma);
-        ret = svc_rdma_map_xdr(rdma, &rqstp->rq_res, vec);
+        ret = svc_rdma_map_xdr(rdma, &rqstp->rq_res, vec, wr_ary != NULL);
         if (ret)
                 goto err0;
         inline_bytes = rqstp->rq_res.len;