NFSD add COPY_NOTIFY operation

Introducing the COPY_NOTIFY operation.

Create a new unique stateid that will keep track of the copy
state and the upcoming READs that will use that stateid.
Each associated parent stateid has a list of copy
notify stateids. A copy notify structure makes a copy of
the parent stateid and a clientid and will use it to look
up the parent stateid during the READ request (suggested
by Trond Myklebust <trond.myklebust@hammerspace.com>).

At nfs4_put_stid() time, we walk the list of the associated
copy notify stateids and delete them.

Laundromat thread will traverse globally stored copy notify
stateid in idr and notice if any haven't been referenced in the
lease period, if so, it'll remove them.

Return single netaddr to advertise to the copy.

Suggested-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
Signed-off-by: Andy Adamson <andros@netapp.com>

1 files changed, 96 insertions, 10 deletions

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 369e574c5092..ae3dff210108 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -80,6 +80,7 @@ static u64 current_sessionid = 1;
 static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner);
 static void nfs4_free_ol_stateid(struct nfs4_stid *stid);
 void nfsd4_end_grace(struct nfsd_net *nn);
+static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps);
 
 /* Locking: */
 
@@ -722,6 +723,7 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *sla
 	/* Will be incremented before return to client: */
 	refcount_set(&stid->sc_count, 1);
 	spin_lock_init(&stid->sc_lock);
+	INIT_LIST_HEAD(&stid->sc_cp_list);
 
 	/*
 	 * It shouldn't be a problem to reuse an opaque stateid value.
@@ -741,30 +743,76 @@ out_free:
 /*
  * Create a unique stateid_t to represent each COPY.
  */
-int nfs4_init_cp_state(struct nfsd_net *nn, struct nfsd4_copy *copy)
+static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid,
+			      unsigned char sc_type)
 {
 	int new_id;
 
+	stid->stid.si_opaque.so_clid.cl_boot = nn->boot_time;
+	stid->stid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id;
+	stid->sc_type = sc_type;
+
 	idr_preload(GFP_KERNEL);
 	spin_lock(&nn->s2s_cp_lock);
-	new_id = idr_alloc_cyclic(&nn->s2s_cp_stateids, copy, 0, 0, GFP_NOWAIT);
+	new_id = idr_alloc_cyclic(&nn->s2s_cp_stateids, stid, 0, 0, GFP_NOWAIT);
+	stid->stid.si_opaque.so_id = new_id;
 	spin_unlock(&nn->s2s_cp_lock);
 	idr_preload_end();
 	if (new_id < 0)
 		return 0;
-	copy->cp_stateid.si_opaque.so_id = new_id;
-	copy->cp_stateid.si_opaque.so_clid.cl_boot = nn->boot_time;
-	copy->cp_stateid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id;
 	return 1;
 }
 
-void nfs4_free_cp_state(struct nfsd4_copy *copy)
+int nfs4_init_copy_state(struct nfsd_net *nn, struct nfsd4_copy *copy)
+{
+	return nfs4_init_cp_state(nn, &copy->cp_stateid, NFS4_COPY_STID);
+}
+
+struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn,
+						     struct nfs4_stid *p_stid)
+{
+	struct nfs4_cpntf_state *cps;
+
+	cps = kzalloc(sizeof(struct nfs4_cpntf_state), GFP_KERNEL);
+	if (!cps)
+		return NULL;
+	cps->cpntf_time = get_seconds();
+	refcount_set(&cps->cp_stateid.sc_count, 1);
+	if (!nfs4_init_cp_state(nn, &cps->cp_stateid, NFS4_COPYNOTIFY_STID))
+		goto out_free;
+	spin_lock(&nn->s2s_cp_lock);
+	list_add(&cps->cp_list, &p_stid->sc_cp_list);
+	spin_unlock(&nn->s2s_cp_lock);
+	return cps;
+out_free:
+	kfree(cps);
+	return NULL;
+}
+
+void nfs4_free_copy_state(struct nfsd4_copy *copy)
 {
 	struct nfsd_net *nn;
 
+	WARN_ON_ONCE(copy->cp_stateid.sc_type != NFS4_COPY_STID);
 	nn = net_generic(copy->cp_clp->net, nfsd_net_id);
 	spin_lock(&nn->s2s_cp_lock);
-	idr_remove(&nn->s2s_cp_stateids, copy->cp_stateid.si_opaque.so_id);
+	idr_remove(&nn->s2s_cp_stateids,
+		   copy->cp_stateid.stid.si_opaque.so_id);
+	spin_unlock(&nn->s2s_cp_lock);
+}
+
+static void nfs4_free_cpntf_statelist(struct net *net, struct nfs4_stid *stid)
+{
+	struct nfs4_cpntf_state *cps;
+	struct nfsd_net *nn;
+
+	nn = net_generic(net, nfsd_net_id);
+	spin_lock(&nn->s2s_cp_lock);
+	while (!list_empty(&stid->sc_cp_list)) {
+		cps = list_first_entry(&stid->sc_cp_list,
+				       struct nfs4_cpntf_state, cp_list);
+		_free_cpntf_state_locked(nn, cps);
+	}
 	spin_unlock(&nn->s2s_cp_lock);
 }
 
@@ -915,6 +963,7 @@ nfs4_put_stid(struct nfs4_stid *s)
 		return;
 	}
 	idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id);
+	nfs4_free_cpntf_statelist(clp->net, s);
 	spin_unlock(&clp->cl_lock);
 	s->sc_free(s);
 	if (fp)
@@ -5215,6 +5264,9 @@ nfs4_laundromat(struct nfsd_net *nn)
 	struct list_head *pos, *next, reaplist;
 	time_t cutoff = get_seconds() - nn->nfsd4_lease;
 	time_t t, new_timeo = nn->nfsd4_lease;
+	struct nfs4_cpntf_state *cps;
+	copy_stateid_t *cps_t;
+	int i;
 
 	dprintk("NFSD: laundromat service - starting\n");
 
@@ -5225,6 +5277,17 @@ nfs4_laundromat(struct nfsd_net *nn)
 	dprintk("NFSD: end of grace period\n");
 	nfsd4_end_grace(nn);
 	INIT_LIST_HEAD(&reaplist);
+
+	spin_lock(&nn->s2s_cp_lock);
+	idr_for_each_entry(&nn->s2s_cp_stateids, cps_t, i) {
+		cps = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid);
+		if (cps->cp_stateid.sc_type == NFS4_COPYNOTIFY_STID &&
+				!time_after((unsigned long)cps->cpntf_time,
+				(unsigned long)cutoff))
+			_free_cpntf_state_locked(nn, cps);
+	}
+	spin_unlock(&nn->s2s_cp_lock);
+
 	spin_lock(&nn->client_lock);
 	list_for_each_safe(pos, next, &nn->client_lru) {
 		clp = list_entry(pos, struct nfs4_client, cl_lru);
@@ -5600,6 +5663,24 @@ nfs4_check_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfs4_stid *s,
 out:
 	return status;
 }
+static void
+_free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps)
+{
+	WARN_ON_ONCE(cps->cp_stateid.sc_type != NFS4_COPYNOTIFY_STID);
+	if (!refcount_dec_and_test(&cps->cp_stateid.sc_count))
+		return;
+	list_del(&cps->cp_list);
+	idr_remove(&nn->s2s_cp_stateids,
+		   cps->cp_stateid.stid.si_opaque.so_id);
+	kfree(cps);
+}
+
+void nfs4_put_cpntf_state(struct nfsd_net *nn, struct nfs4_cpntf_state *cps)
+{
+	spin_lock(&nn->s2s_cp_lock);
+	_free_cpntf_state_locked(nn, cps);
+	spin_unlock(&nn->s2s_cp_lock);
+}
 
 /*
  * Checks for stateid operations
@@ -5607,7 +5688,8 @@ out:
 __be32
 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *cstate, struct svc_fh *fhp,
-		stateid_t *stateid, int flags, struct nfsd_file **nfp)
+		stateid_t *stateid, int flags, struct nfsd_file **nfp,
+		struct nfs4_stid **cstid)
 {
 	struct inode *ino = d_inode(fhp->fh_dentry);
 	struct net *net = SVC_NET(rqstp);
@@ -5656,8 +5738,12 @@ done:
 	if (status == nfs_ok && nfp)
 		status = nfs4_check_file(rqstp, fhp, s, nfp, flags);
 out:
-	if (s)
-		nfs4_put_stid(s);
+	if (s) {
+		if (!status && cstid)
+			*cstid = s;
+		else
+			nfs4_put_stid(s);
+	}
 	return status;
 }