nfsd41: replace page based DRC with buffer based DRC

Use NFSD_SLOT_CACHE_SIZE size buffers for sessions DRC instead of holding nfsd
pages in cache.

Connectathon testing has shown that 1024 bytes for encoded compound operation
responses past the sequence operation is sufficient, 512 bytes is a little too
small. Set NFSD_SLOT_CACHE_SIZE to 1024.

Allocate memory for the session DRC in the CREATE_SESSION operation
to guarantee that the memory resource is available for caching responses.
Allocate each slot individually in preparation for slot table size negotiation.

Remove struct nfsd4_cache_entry and helper functions for the old page-based
DRC.

The iov_len calculation in nfs4svc_encode_compoundres is now always
correct.  Replay is now done in nfsd4_sequence under the state lock, so
the session ref count is only bumped on non-replay. Clean up the
nfs4svc_encode_compoundres session logic.

The nfsd4_compound_state statp pointer is also not used.
Remove nfsd4_set_statp().

Move useful nfsd4_cache_entry fields into nfsd4_slot.

Signed-off-by: Andy Adamson <andros@netapp.com
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>

fs/nfsd/nfs4xdr.c

@@ -3057,6 +3057,7 @@ nfsd4_encode_sequence(struct nfsd4_compoundres *resp, int nfserr,
 	WRITE32(0);
 
 	ADJUST_ARGS();
+	resp->cstate.datap = p; /* DRC cache data pointer */
 	return 0;
 }
 
@@ -3159,7 +3160,7 @@ static int nfsd4_check_drc_limit(struct nfsd4_compoundres *resp)
 		return status;
 
 	session = resp->cstate.session;
-	if (session == NULL || slot->sl_cache_entry.ce_cachethis == 0)
+	if (session == NULL || slot->sl_cachethis == 0)
 		return status;
 
 	if (resp->opcnt >= args->opcnt)
@@ -3284,6 +3285,7 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compo
 	/*
 	 * All that remains is to write the tag and operation count...
 	 */
+	struct nfsd4_compound_state *cs = &resp->cstate;
 	struct kvec *iov;
 	p = resp->tagp;
 	*p++ = htonl(resp->taglen);
@@ -3297,15 +3299,10 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compo
 		iov = &rqstp->rq_res.head[0];
 	iov->iov_len = ((char*)resp->p) - (char*)iov->iov_base;
 	BUG_ON(iov->iov_len > PAGE_SIZE);
-	if (nfsd4_has_session(&resp->cstate)) {
-		if (resp->cstate.status == nfserr_replay_cache &&
-				!nfsd4_not_cached(resp)) {
-			iov->iov_len = resp->cstate.iovlen;
-		} else {
-			nfsd4_store_cache_entry(resp);
-			dprintk("%s: SET SLOT STATE TO AVAILABLE\n", __func__);
-			resp->cstate.slot->sl_inuse = 0;
-		}
+	if (nfsd4_has_session(cs) && cs->status != nfserr_replay_cache) {
+		nfsd4_store_cache_entry(resp);
+		dprintk("%s: SET SLOT STATE TO AVAILABLE\n", __func__);
+		resp->cstate.slot->sl_inuse = false;
 		nfsd4_put_session(resp->cstate.session);
 	}
 	return 1;

fs/nfsd/nfssvc.c

@@ -577,10 +577,6 @@ 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);

include/linux/nfsd/state.h

@@ -94,30 +94,23 @@ struct nfs4_cb_conn {
 
 /* Maximum number of slots per session. 160 is useful for long haul TCP */
 #define NFSD_MAX_SLOTS_PER_SESSION     160
-/* Maximum number of pages per slot cache entry */
-#define NFSD_PAGES_PER_SLOT	1
-#define NFSD_SLOT_CACHE_SIZE		PAGE_SIZE
 /* Maximum number of operations per session compound */
 #define NFSD_MAX_OPS_PER_COMPOUND	16
+/* Maximum  session per slot cache size */
+#define NFSD_SLOT_CACHE_SIZE		1024
 /* Maximum number of NFSD_SLOT_CACHE_SIZE slots per session */
 #define NFSD_CACHE_SIZE_SLOTS_PER_SESSION	32
 #define NFSD_MAX_MEM_PER_SESSION  \
 		(NFSD_CACHE_SIZE_SLOTS_PER_SESSION * NFSD_SLOT_CACHE_SIZE)
 
-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];
-	int		ce_cachethis;
-	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;
+	bool	sl_inuse;
+	bool	sl_cachethis;
+	u16	sl_opcnt;
+	u32	sl_seqid;
+	__be32	sl_status;
+	u32	sl_datalen;
+	char	sl_data[];
 };
 
 struct nfsd4_channel_attrs {
@@ -159,7 +152,7 @@ struct nfsd4_session {
 	struct nfs4_sessionid	se_sessionid;
 	struct nfsd4_channel_attrs se_fchannel;
 	struct nfsd4_channel_attrs se_bchannel;
-	struct nfsd4_slot	se_slots[];	/* forward channel slots */
+	struct nfsd4_slot	*se_slots[];	/* forward channel slots */
 };
 
 static inline void

include/linux/nfsd/xdr4.h

@@ -51,7 +51,7 @@ struct nfsd4_compound_state {
 	/* For sessions DRC */
 	struct nfsd4_session	*session;
 	struct nfsd4_slot	*slot;
-	__be32			*statp;
+	__be32			*datap;
 	size_t			iovlen;
 	u32			minorversion;
 	u32			status;
@@ -472,8 +472,7 @@ static inline bool nfsd4_is_solo_sequence(struct nfsd4_compoundres *resp)
 
 static inline bool nfsd4_not_cached(struct nfsd4_compoundres *resp)
 {
-	return !resp->cstate.slot->sl_cache_entry.ce_cachethis ||
-			nfsd4_is_solo_sequence(resp);
+	return !resp->cstate.slot->sl_cachethis || nfsd4_is_solo_sequence(resp);
 }
 
 #define NFS4_SVC_XDRSIZE		sizeof(struct nfsd4_compoundargs)