nfsd41: DRC save, restore, and clear functions

Cache all the result pages, including the rpc header in rq_respages[0],
for a request in the slot table cache entry.

Cache the statp pointer from nfsd_dispatch which points into rq_respages[0]
just past the rpc header. When setting a cache entry, calculate and save the
length of the nfs data minus the rpc header for rq_respages[0].

When replaying a cache entry, replace the cached rpc header with the
replayed request rpc result header, unless there is not enough room in the
cached results first page. In that case, use the cached rpc header.

The sessions fore channel maxresponse size cached is set to NFSD_PAGES_PER_SLOT
* PAGE_SIZE. For compounds we are cacheing with operations such as READDIR
that use the xdr_buf->pages to hold data, we choose to cache the extra page of
data rather than copying data from xdr_buf->pages into the xdr_buf->head page.

[nfsd41: limit cache to maxresponsesize_cached]
[nfsd41: mv nfsd4_set_statp under CONFIG_NFSD_V4_1]
[nfsd41: rename nfsd4_move_pages]
[nfsd41: rename page_no variable]
[nfsd41: rename nfsd4_set_cache_entry]
[nfsd41: fix nfsd41_copy_replay_data comment]
[nfsd41: add to nfsd4_set_cache_entry]
Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Benny Halevy <bhalevy@panasas.com>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>

2 files changed, 146 insertions, 0 deletions

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);