Have the NFSD encoders annotate the boundaries of every
direct-data-placement eligible READ 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
READ payloads per compound. Next step is to support multiple Write
chunks.
Signed-off-by: Chuck Lever <chuck.lever@xxxxxxxxxx>
---
fs/nfsd/nfs3xdr.c | 4 ++++
fs/nfsd/nfs4xdr.c | 3 +++
fs/nfsd/nfsxdr.c | 4 ++++
net/sunrpc/xprtrdma/svc_rdma_sendto.c | 24 +++++++-----------------
4 files changed, 18 insertions(+), 17 deletions(-)
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index aae514d40b64..8c272efbc94e 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -712,6 +712,8 @@ nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
*p = 0;
rqstp->rq_res.tail[0].iov_len = 4 - (resp->len&3);
}
+ svc_encode_read_payload(rqstp, rqstp->rq_res.head[0].iov_len,
+ resp->len);
return 1;
} else
return xdr_ressize_check(rqstp, p);
@@ -737,6 +739,8 @@ nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
*p = 0;
rqstp->rq_res.tail[0].iov_len = 4 - (resp->count & 3);
}
+ svc_encode_read_payload(rqstp, rqstp->rq_res.head[0].iov_len,
+ resp->count);
return 1;
} else
return xdr_ressize_check(rqstp, p);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 996ac01ee977..9c2cfddcc29c 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3547,6 +3547,8 @@ static __be32 nfsd4_encode_splice_read(
buf->page_len = 0;
return nfserr;
}
+ svc_encode_read_payload(read->rd_rqstp, buf->head[0].iov_len,
+ maxcount);
*(p++) = htonl(eof);
*(p++) = htonl(maxcount);
@@ -3713,6 +3715,7 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd
xdr_truncate_encode(xdr, length_offset);
return nfserr;
}
+ svc_encode_read_payload(readlink->rl_rqstp, length_offset, maxcount);
wire_count = htonl(maxcount);
write_bytes_to_xdr_buf(xdr->buf, length_offset, &wire_count, 4);
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index b51fe515f06f..98ea417042a6 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -462,6 +462,8 @@ nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
*p = 0;
rqstp->rq_res.tail[0].iov_len = 4 - (resp->len&3);
}
+ svc_encode_read_payload(rqstp, rqstp->rq_res.head[0].iov_len,
+ resp->len);
return 1;
}
@@ -482,6 +484,8 @@ nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
*p = 0;
rqstp->rq_res.tail[0].iov_len = 4 - (resp->count&3);
}
+ svc_encode_read_payload(rqstp, rqstp->rq_res.head[0].iov_len,
+ resp->count);
return 1;
}
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 90cba3058f04..0e6372a13018 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -445,7 +445,6 @@ 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
@@ -462,12 +461,12 @@ 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;
@@ -890,21 +889,12 @@ 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)
