diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 9243dca3576c..a37b91dab1bf 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -852,6 +852,148 @@ out_err:
 	return;
 }
 
+void
+nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp)
+{
+	struct nfsd4_compoundres *resp = rqstp->rq_resp;
+
+	resp->cstate.statp = statp;
+}
+
+/*
+ * Dereference the result pages.
+ */
+static void
+nfsd4_release_respages(struct page **respages, short resused)
+{
+	int i;
+
+	dprintk("--> %s\n", __func__);
+	for (i = 0; i < resused; i++) {
+		if (!respages[i])
+			continue;
+		put_page(respages[i]);
+		respages[i] = NULL;
+	}
+}
+
+static void
+nfsd4_copy_pages(struct page **topages, struct page **frompages, short count)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		topages[i] = frompages[i];
+		if (!topages[i])
+			continue;
+		get_page(topages[i]);
+	}
+}
+
+/*
+ * Cache the reply pages up to NFSD_PAGES_PER_SLOT + 1, clearing the previous
+ * pages. We add a page to NFSD_PAGES_PER_SLOT for the case where the total
+ * length of the XDR response is less than se_fmaxresp_cached
+ * (NFSD_PAGES_PER_SLOT * PAGE_SIZE) but the xdr_buf pages is used for a
+ * of the reply (e.g. readdir).
+ *
+ * Store the base and length of the rq_req.head[0] page
+ * of the NFSv4.1 data, just past the rpc header.
+ */
+void
+nfsd4_store_cache_entry(struct nfsd4_compoundres *resp)
+{
+	struct nfsd4_cache_entry *entry = &resp->cstate.slot->sl_cache_entry;
+	struct svc_rqst *rqstp = resp->rqstp;
+	struct nfsd4_compoundargs *args = rqstp->rq_argp;
+	struct nfsd4_op *op = &args->ops[resp->opcnt];
+	struct kvec *resv = &rqstp->rq_res.head[0];
+
+	dprintk("--> %s entry %p\n", __func__, entry);
+
+	/* Don't cache a failed OP_SEQUENCE. */
+	if (resp->opcnt == 1 && op->opnum == OP_SEQUENCE && resp->cstate.status)
+		return;
+	nfsd4_release_respages(entry->ce_respages, entry->ce_resused);
+	entry->ce_resused = rqstp->rq_resused;
+	if (entry->ce_resused > NFSD_PAGES_PER_SLOT + 1)
+		entry->ce_resused = NFSD_PAGES_PER_SLOT + 1;
+	nfsd4_copy_pages(entry->ce_respages, rqstp->rq_respages,
+			 entry->ce_resused);
+	entry->ce_status = resp->cstate.status;
+	entry->ce_datav.iov_base = resp->cstate.statp;
+	entry->ce_datav.iov_len = resv->iov_len - ((char *)resp->cstate.statp -
+				(char *)page_address(rqstp->rq_respages[0]));
+	entry->ce_opcnt = resp->opcnt;
+	/* Current request rpc header length*/
+	entry->ce_rpchdrlen = (char *)resp->cstate.statp -
+				(char *)page_address(rqstp->rq_respages[0]);
+}
+
+/*
+ * We keep the rpc header, but take the nfs reply from the replycache.
+ */
+static int
+nfsd41_copy_replay_data(struct nfsd4_compoundres *resp,
+			struct nfsd4_cache_entry *entry)
+{
+	struct svc_rqst *rqstp = resp->rqstp;
+	struct kvec *resv = &resp->rqstp->rq_res.head[0];
+	int len;
+
+	/* Current request rpc header length*/
+	len = (char *)resp->cstate.statp -
+			(char *)page_address(rqstp->rq_respages[0]);
+	if (entry->ce_datav.iov_len + len > PAGE_SIZE) {
+		dprintk("%s v41 cached reply too large (%Zd).\n", __func__,
+			entry->ce_datav.iov_len);
+		return 0;
+	}
+	/* copy the cached reply nfsd data past the current rpc header */
+	memcpy((char *)resv->iov_base + len, entry->ce_datav.iov_base,
+		entry->ce_datav.iov_len);
+	resv->iov_len = len + entry->ce_datav.iov_len;
+	return 1;
+}
+
+/*
+ * Keep the first page of the replay. Copy the NFSv4.1 data from the first
+ * cached page.  Replace any futher replay pages from the cache.
+ */
+__be32
+nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp)
+{
+	struct nfsd4_cache_entry *entry = &resp->cstate.slot->sl_cache_entry;
+	__be32 status;
+
+	dprintk("--> %s entry %p\n", __func__, entry);
+
+
+	if (!nfsd41_copy_replay_data(resp, entry)) {
+		/*
+		 * Not enough room to use the replay rpc header, send the
+		 * cached header. Release all the allocated result pages.
+		 */
+		svc_free_res_pages(resp->rqstp);
+		nfsd4_copy_pages(resp->rqstp->rq_respages, entry->ce_respages,
+			entry->ce_resused);
+	} else {
+		/* Release all but the first allocated result page */
+
+		resp->rqstp->rq_resused--;
+		svc_free_res_pages(resp->rqstp);
+
+		nfsd4_copy_pages(&resp->rqstp->rq_respages[1],
+				 &entry->ce_respages[1],
+				 entry->ce_resused - 1);
+	}
+
+	resp->rqstp->rq_resused = entry->ce_resused;
+	status = entry->ce_status;
+
+	return status;
+}
+
 /*
  * Set the exchange_id flags returned by the server.
  */
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index ef0a3686639d..b5168d1898ec 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -515,6 +515,10 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 		+ rqstp->rq_res.head[0].iov_len;
 	rqstp->rq_res.head[0].iov_len += sizeof(__be32);
 
+	/* NFSv4.1 DRC requires statp */
+	if (rqstp->rq_vers == 4)
+		nfsd4_set_statp(rqstp, statp);
+
 	/* Now call the procedure handler, and encode NFS status. */
 	nfserr = proc->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
 	nfserr = map_new_errors(rqstp->rq_vers, nfserr);
diff --git a/include/linux/nfsd/cache.h b/include/linux/nfsd/cache.h
index 04b355c801d8..a59a2df6d079 100644
--- a/include/linux/nfsd/cache.h
+++ b/include/linux/nfsd/cache.h
@@ -75,5 +75,6 @@ int	nfsd_reply_cache_init(void);
 void	nfsd_reply_cache_shutdown(void);
 int	nfsd_cache_lookup(struct svc_rqst *, int);
 void	nfsd_cache_update(struct svc_rqst *, int, __be32 *);
+void	nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp);
 
 #endif /* NFSCACHE_H */
diff --git a/include/linux/nfsd/state.h b/include/linux/nfsd/state.h
index 90829db76861..f1edb1d98523 100644
--- a/include/linux/nfsd/state.h
+++ b/include/linux/nfsd/state.h
@@ -99,9 +99,22 @@ struct nfs4_callback {
 	struct rpc_clnt *       cb_client;
 };
 
+/* Maximum number of pages per slot cache entry */
+#define NFSD_PAGES_PER_SLOT	1
+
+struct nfsd4_cache_entry {
+	__be32		ce_status;
+	struct kvec	ce_datav; /* encoded NFSv4.1 data in rq_res.head[0] */
+	struct page	*ce_respages[NFSD_PAGES_PER_SLOT + 1];
+	short		ce_resused;
+	int		ce_opcnt;
+	int		ce_rpchdrlen;
+};
+
 struct nfsd4_slot {
 	bool				sl_inuse;
 	u32				sl_seqid;
+	struct nfsd4_cache_entry	sl_cache_entry;
 };
 
 struct nfsd4_session {
diff --git a/include/linux/nfsd/xdr4.h b/include/linux/nfsd/xdr4.h
index 6e28a041008d..d091684325af 100644
--- a/include/linux/nfsd/xdr4.h
+++ b/include/linux/nfsd/xdr4.h
@@ -51,6 +51,8 @@ struct nfsd4_compound_state {
 	/* For sessions DRC */
 	struct nfsd4_session	*session;
 	struct nfsd4_slot	*slot;
+	__be32			*statp;
+	u32			status;
 };
 
 struct nfsd4_change_info {
@@ -487,6 +489,8 @@ extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp,
 extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *,
 		struct nfsd4_setclientid_confirm *setclientid_confirm);
+extern void nfsd4_store_cache_entry(struct nfsd4_compoundres *resp);
+extern __be32 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp);
 extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *,
 struct nfsd4_exchange_id *);