NFSD: Invoke svc_encode_result_payload() in "read" NFSD encoders

Have the NFSD encoders annotate the boundaries of every
direct-data-placement eligible result data payload. Then change
svcrdma to use that annotation instead of the xdr->page_len
when handling Write chunks.

For NFSv4 on RDMA, that enables the ability to recognize multiple
result payloads per compound. This is a pre-requisite for supporting
multiple Write chunks per RPC transaction.

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

4 files changed, 49 insertions, 29 deletions

diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 2277f83da250..186b07a72373 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -707,6 +707,7 @@ int
 nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
 {
 	struct nfsd3_readlinkres *resp = rqstp->rq_resp;
+	struct kvec *head = rqstp->rq_res.head;
 
 	*p++ = resp->status;
 	p = encode_post_op_attr(rqstp, p, &resp->fh);
@@ -720,6 +721,8 @@ nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
 			*p = 0;
 			rqstp->rq_res.tail[0].iov_len = 4 - (resp->len&3);
 		}
+		if (svc_encode_result_payload(rqstp, head->iov_len, resp->len))
+			return 0;
 		return 1;
 	} else
 		return xdr_ressize_check(rqstp, p);
@@ -730,6 +733,7 @@ int
 nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
 {
 	struct nfsd3_readres *resp = rqstp->rq_resp;
+	struct kvec *head = rqstp->rq_res.head;
 
 	*p++ = resp->status;
 	p = encode_post_op_attr(rqstp, p, &resp->fh);
@@ -746,6 +750,9 @@ nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
 			*p = 0;
 			rqstp->rq_res.tail[0].iov_len = 4 - (resp->count & 3);
 		}
+		if (svc_encode_result_payload(rqstp, head->iov_len,
+					      resp->count))
+			return 0;
 		return 1;
 	} else
 		return xdr_ressize_check(rqstp, p);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 7e24fb3ca36e..1d2c33cd3a87 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3756,8 +3756,8 @@ static __be32 nfsd4_encode_splice_read(
 {
 	struct xdr_stream *xdr = &resp->xdr;
 	struct xdr_buf *buf = xdr->buf;
+	int status, space_left;
 	u32 eof;
-	int space_left;
 	__be32 nfserr;
 	__be32 *p = xdr->p - 2;
 
@@ -3768,14 +3768,13 @@ static __be32 nfsd4_encode_splice_read(
 	nfserr = nfsd_splice_read(read->rd_rqstp, read->rd_fhp,
 				  file, read->rd_offset, &maxcount, &eof);
 	read->rd_length = maxcount;
-	if (nfserr) {
-		/*
-		 * nfsd_splice_actor may have already messed with the
-		 * page length; reset it so as not to confuse
-		 * xdr_truncate_encode:
-		 */
-		buf->page_len = 0;
-		return nfserr;
+	if (nfserr)
+		goto out_err;
+	status = svc_encode_result_payload(read->rd_rqstp,
+					   buf->head[0].iov_len, maxcount);
+	if (status) {
+		nfserr = nfserrno(status);
+		goto out_err;
 	}
 
 	*(p++) = htonl(eof);
@@ -3806,6 +3805,15 @@ static __be32 nfsd4_encode_splice_read(
 	xdr->end = (__be32 *)((void *)xdr->end + space_left);
 
 	return 0;
+
+out_err:
+	/*
+	 * nfsd_splice_actor may have already messed with the
+	 * page length; reset it so as not to confuse
+	 * xdr_truncate_encode in our caller.
+	 */
+	buf->page_len = 0;
+	return nfserr;
 }
 
 static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
@@ -3897,6 +3905,7 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd
 	int zero = 0;
 	struct xdr_stream *xdr = &resp->xdr;
 	int length_offset = xdr->buf->len;
+	int status;
 	__be32 *p;
 
 	p = xdr_reserve_space(xdr, 4);
@@ -3917,9 +3926,13 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd
 						(char *)p, &maxcount);
 	if (nfserr == nfserr_isdir)
 		nfserr = nfserr_inval;
-	if (nfserr) {
-		xdr_truncate_encode(xdr, length_offset);
-		return nfserr;
+	if (nfserr)
+		goto out_err;
+	status = svc_encode_result_payload(readlink->rl_rqstp, length_offset,
+					   maxcount);
+	if (status) {
+		nfserr = nfserrno(status);
+		goto out_err;
 	}
 
 	wire_count = htonl(maxcount);
@@ -3929,6 +3942,10 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd
 		write_bytes_to_xdr_buf(xdr->buf, length_offset + 4 + maxcount,
 						&zero, 4 - (maxcount&3));
 	return 0;
+
+out_err:
+	xdr_truncate_encode(xdr, length_offset);
+	return nfserr;
 }
 
 static __be32
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 8a288c8fcd57..9e00a902113e 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -469,6 +469,7 @@ int
 nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
 {
 	struct nfsd_readlinkres *resp = rqstp->rq_resp;
+	struct kvec *head = rqstp->rq_res.head;
 
 	*p++ = resp->status;
 	if (resp->status != nfs_ok)
@@ -483,6 +484,8 @@ nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
 		*p = 0;
 		rqstp->rq_res.tail[0].iov_len = 4 - (resp->len&3);
 	}
+	if (svc_encode_result_payload(rqstp, head->iov_len, resp->len))
+		return 0;
 	return 1;
 }
 
@@ -490,6 +493,7 @@ int
 nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
 {
 	struct nfsd_readres *resp = rqstp->rq_resp;
+	struct kvec *head = rqstp->rq_res.head;
 
 	*p++ = resp->status;
 	if (resp->status != nfs_ok)
@@ -507,6 +511,8 @@ nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
 		*p = 0;
 		rqstp->rq_res.tail[0].iov_len = 4 - (resp->count&3);
 	}
+	if (svc_encode_result_payload(rqstp, head->iov_len, resp->count))
+		return 0;
 	return 1;
 }
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index c8411b4f3492..d6436c13d5c4 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -448,7 +448,6 @@ static ssize_t svc_rdma_encode_write_chunk(__be32 *src,
  * svc_rdma_encode_write_list - Encode RPC Reply's Write chunk list
  * @rctxt: Reply context with information about the RPC Call
  * @sctxt: Send context for the RPC Reply
- * @length: size in bytes of the payload in the first Write chunk
  *
  * The client provides a Write chunk list in the Call message. Fill
  * in the segments in the first Write chunk in the Reply's transport
@@ -465,12 +464,12 @@ static ssize_t svc_rdma_encode_write_chunk(__be32 *src,
  */
 static ssize_t
 svc_rdma_encode_write_list(const struct svc_rdma_recv_ctxt *rctxt,
-			   struct svc_rdma_send_ctxt *sctxt,
-			   unsigned int length)
+			   struct svc_rdma_send_ctxt *sctxt)
 {
 	ssize_t len, ret;
 
-	ret = svc_rdma_encode_write_chunk(rctxt->rc_write_list, sctxt, length);
+	ret = svc_rdma_encode_write_chunk(rctxt->rc_write_list, sctxt,
+					  rctxt->rc_read_payload_length);
 	if (ret < 0)
 		return ret;
 	len = ret;
@@ -923,21 +922,12 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
 		goto err0;
 	if (wr_lst) {
 		/* XXX: Presume the client sent only one Write chunk */
-		unsigned long offset;
-		unsigned int length;
-
-		if (rctxt->rc_read_payload_length) {
-			offset = rctxt->rc_read_payload_offset;
-			length = rctxt->rc_read_payload_length;
-		} else {
-			offset = xdr->head[0].iov_len;
-			length = xdr->page_len;
-		}
-		ret = svc_rdma_send_write_chunk(rdma, wr_lst, xdr, offset,
-						length);
+		ret = svc_rdma_send_write_chunk(rdma, wr_lst, xdr,
+						rctxt->rc_read_payload_offset,
+						rctxt->rc_read_payload_length);
 		if (ret < 0)
 			goto err2;
-		if (svc_rdma_encode_write_list(rctxt, sctxt, length) < 0)
+		if (svc_rdma_encode_write_list(rctxt, sctxt) < 0)
 			goto err0;
 	} else {
 		if (xdr_stream_encode_item_absent(&sctxt->sc_stream) < 0)