nfsd: Fix NFSv4 READ on RDMA when using readv

svcrdma expects that the payload falls precisely into the xdr_buf
page vector. This does not seem to be the case for
nfsd4_encode_readv().

This code is called only when fops->splice_read is missing or when
RQ_SPLICE_OK is clear, so it's not a noticeable problem in many
common cases.

Add new transport method: ->xpo_read_payload so that when a READ
payload does not fit exactly in rq_res's page vector, the XDR
encoder can inform the RPC transport exactly where that payload is,
without the payload's XDR pad.

That way, when a Write chunk is present, the transport knows what
byte range in the Reply message is supposed to be matched with the
chunk.

Note that the Linux NFS server implementation of NFS/RDMA can
currently handle only one Write chunk per RPC-over-RDMA message.
This simplifies the implementation of this fix.

Fixes: b04209806384 ("nfsd4: allow exotic read compounds")
Buglink: https://bugzilla.kernel.org/show_bug.cgi?id=198053
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>

1 files changed, 11 insertions, 9 deletions

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index ad38aed6f5c2..eedb62c411a5 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3594,17 +3594,17 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
 	u32 zzz = 0;
 	int pad;
 
+	/*
+	 * svcrdma requires every READ payload to start somewhere
+	 * in xdr->pages.
+	 */
+	if (xdr->iov == xdr->buf->head) {
+		xdr->iov = NULL;
+		xdr->end = xdr->p;
+	}
+
 	len = maxcount;
 	v = 0;
-
-	thislen = min_t(long, len, ((void *)xdr->end - (void *)xdr->p));
-	p = xdr_reserve_space(xdr, (thislen+3)&~3);
-	WARN_ON_ONCE(!p);
-	resp->rqstp->rq_vec[v].iov_base = p;
-	resp->rqstp->rq_vec[v].iov_len = thislen;
-	v++;
-	len -= thislen;
-
 	while (len) {
 		thislen = min_t(long, len, PAGE_SIZE);
 		p = xdr_reserve_space(xdr, (thislen+3)&~3);
@@ -3623,6 +3623,8 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
 	read->rd_length = maxcount;
 	if (nfserr)
 		return nfserr;
+	if (svc_encode_read_payload(resp->rqstp, starting_len + 8, maxcount))
+		return nfserr_io;
 	xdr_truncate_encode(xdr, starting_len + 8 + ((maxcount+3)&~3));
 
 	tmp = htonl(eof);