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>

6 files changed, 83 insertions, 13 deletions

diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 187dd4e73d64..18676d36f490 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1637,6 +1637,22 @@ u32 svc_max_payload(const struct svc_rqst *rqstp)
 EXPORT_SYMBOL_GPL(svc_max_payload);
 
 /**
+ * svc_encode_read_payload - mark a range of bytes as a READ payload
+ * @rqstp: svc_rqst to operate on
+ * @offset: payload's byte offset in rqstp->rq_res
+ * @length: size of payload, in bytes
+ *
+ * Returns zero on success, or a negative errno if a permanent
+ * error occurred.
+ */
+int svc_encode_read_payload(struct svc_rqst *rqstp, unsigned int offset,
+			    unsigned int length)
+{
+	return rqstp->rq_xprt->xpt_ops->xpo_read_payload(rqstp, offset, length);
+}
+EXPORT_SYMBOL_GPL(svc_encode_read_payload);
+
+/**
  * svc_fill_write_vector - Construct data argument for VFS write call
  * @rqstp: svc_rqst to operate on
  * @pages: list of pages containing data payload
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 2934dd711715..758ab10690de 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -279,6 +279,12 @@ out:
 	return len;
 }
 
+static int svc_sock_read_payload(struct svc_rqst *rqstp, unsigned int offset,
+				 unsigned int length)
+{
+	return 0;
+}
+
 /*
  * Report socket names for nfsdfs
  */
@@ -653,6 +659,7 @@ static const struct svc_xprt_ops svc_udp_ops = {
 	.xpo_create = svc_udp_create,
 	.xpo_recvfrom = svc_udp_recvfrom,
 	.xpo_sendto = svc_udp_sendto,
+	.xpo_read_payload = svc_sock_read_payload,
 	.xpo_release_rqst = svc_release_udp_skb,
 	.xpo_detach = svc_sock_detach,
 	.xpo_free = svc_sock_free,
@@ -1171,6 +1178,7 @@ static const struct svc_xprt_ops svc_tcp_ops = {
 	.xpo_create = svc_tcp_create,
 	.xpo_recvfrom = svc_tcp_recvfrom,
 	.xpo_sendto = svc_tcp_sendto,
+	.xpo_read_payload = svc_sock_read_payload,
 	.xpo_release_rqst = svc_release_skb,
 	.xpo_detach = svc_tcp_sock_detach,
 	.xpo_free = svc_sock_free,
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 96bccd398469..71127d898562 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -193,6 +193,7 @@ svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma)
 
 out:
 	ctxt->rc_page_count = 0;
+	ctxt->rc_read_payload_length = 0;
 	return ctxt;
 
 out_empty:
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index 003610ce00bc..927f98995356 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -482,18 +482,19 @@ static int svc_rdma_send_xdr_kvec(struct svc_rdma_write_info *info,
 				     vec->iov_len);
 }
 
-/* Send an xdr_buf's page list by itself. A Write chunk is
- * just the page list. a Reply chunk is the head, page list,
- * and tail. This function is shared between the two types
- * of chunk.
+/* Send an xdr_buf's page list by itself. A Write chunk is just
+ * the page list. A Reply chunk is @xdr's head, page list, and
+ * tail. This function is shared between the two types of chunk.
  */
 static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info,
-				      struct xdr_buf *xdr)
+				      struct xdr_buf *xdr,
+				      unsigned int offset,
+				      unsigned long length)
 {
 	info->wi_xdr = xdr;
-	info->wi_next_off = 0;
+	info->wi_next_off = offset - xdr->head[0].iov_len;
 	return svc_rdma_build_writes(info, svc_rdma_pagelist_to_sg,
-				     xdr->page_len);
+				     length);
 }
 
 /**
@@ -501,6 +502,8 @@ static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info,
  * @rdma: controlling RDMA transport
  * @wr_ch: Write chunk provided by client
  * @xdr: xdr_buf containing the data payload
+ * @offset: payload's byte offset in @xdr
+ * @length: size of payload, in bytes
  *
  * Returns a non-negative number of bytes the chunk consumed, or
  *	%-E2BIG if the payload was larger than the Write chunk,
@@ -510,19 +513,20 @@ static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info,
  *	%-EIO if rdma_rw initialization failed (DMA mapping, etc).
  */
 int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, __be32 *wr_ch,
-			      struct xdr_buf *xdr)
+			      struct xdr_buf *xdr,
+			      unsigned int offset, unsigned long length)
 {
 	struct svc_rdma_write_info *info;
 	int ret;
 
-	if (!xdr->page_len)
+	if (!length)
 		return 0;
 
 	info = svc_rdma_write_info_alloc(rdma, wr_ch);
 	if (!info)
 		return -ENOMEM;
 
-	ret = svc_rdma_send_xdr_pagelist(info, xdr);
+	ret = svc_rdma_send_xdr_pagelist(info, xdr, offset, length);
 	if (ret < 0)
 		goto out_err;
 
@@ -531,7 +535,7 @@ int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, __be32 *wr_ch,
 		goto out_err;
 
 	trace_svcrdma_encode_write(xdr->page_len);
-	return xdr->page_len;
+	return length;
 
 out_err:
 	svc_rdma_write_info_free(info);
@@ -571,7 +575,9 @@ int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma, __be32 *rp_ch,
 	 * client did not provide Write chunks.
 	 */
 	if (!writelist && xdr->page_len) {
-		ret = svc_rdma_send_xdr_pagelist(info, xdr);
+		ret = svc_rdma_send_xdr_pagelist(info, xdr,
+						 xdr->head[0].iov_len,
+						 xdr->page_len);
 		if (ret < 0)
 			goto out_err;
 		consumed += xdr->page_len;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index f3f108090aa4..a11983c2056f 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -858,7 +858,18 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
 
 	if (wr_lst) {
 		/* XXX: Presume the client sent only one Write chunk */
-		ret = svc_rdma_send_write_chunk(rdma, wr_lst, xdr);
+		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);
 		if (ret < 0)
 			goto err2;
 		svc_rdma_xdr_encode_write_list(rdma_resp, wr_lst, ret);
@@ -900,3 +911,30 @@ out:
 	ret = -ENOTCONN;
 	goto out;
 }
+
+/**
+ * svc_rdma_read_payload - special processing for a READ payload
+ * @rqstp: svc_rqst to operate on
+ * @offset: payload's byte offset in @xdr
+ * @length: size of payload, in bytes
+ *
+ * Returns zero on success.
+ *
+ * For the moment, just record the xdr_buf location of the READ
+ * payload. svc_rdma_sendto will use that location later when
+ * we actually send the payload.
+ */
+int svc_rdma_read_payload(struct svc_rqst *rqstp, unsigned int offset,
+			  unsigned int length)
+{
+	struct svc_rdma_recv_ctxt *rctxt = rqstp->rq_xprt_ctxt;
+
+	/* XXX: Just one READ payload slot for now, since our
+	 * transport implementation currently supports only one
+	 * Write chunk.
+	 */
+	rctxt->rc_read_payload_offset = offset;
+	rctxt->rc_read_payload_length = length;
+
+	return 0;
+}
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 145a3615c319..f6aad2798063 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -82,6 +82,7 @@ static const struct svc_xprt_ops svc_rdma_ops = {
 	.xpo_create = svc_rdma_create,
 	.xpo_recvfrom = svc_rdma_recvfrom,
 	.xpo_sendto = svc_rdma_sendto,
+	.xpo_read_payload = svc_rdma_read_payload,
 	.xpo_release_rqst = svc_rdma_release_rqst,
 	.xpo_detach = svc_rdma_detach,
 	.xpo_free = svc_rdma_free,