Merge branch 'client-4.2' into linux-next

Merge NFSv4.2 client SEEK implementation from Anna

* client-4.2: (55 commits)
  NFS: Implement SEEK
  NFSD: Implement SEEK
  NFSD: Add generic v4.2 infrastructure
  svcrdma: advertise the correct max payload
  nfsd: introduce nfsd4_callback_ops
  nfsd: split nfsd4_callback initialization and use
  nfsd: introduce a generic nfsd4_cb
  nfsd: remove nfsd4_callback.cb_op
  nfsd: do not clear rpc_resp in nfsd4_cb_done_sequence
  nfsd: fix nfsd4_cb_recall_done error handling
  nfsd4: clarify how grace period ends
  nfsd4: stop grace_time update at end of grace period
  nfsd: skip subsequent UMH "create" operations after the first one for v4.0 clients
  nfsd: set and test NFSD4_CLIENT_STABLE bit to reduce nfsdcltrack upcalls
  nfsd: serialize nfsdcltrack upcalls for a particular client
  nfsd: pass extra info in env vars to upcalls to allow for early grace period end
  nfsd: add a v4_end_grace file to /proc/fs/nfsd
  lockd: add a /proc/fs/lockd/nlm_end_grace file
  nfsd: reject reclaim request when client has already sent RECLAIM_COMPLETE
  nfsd: remove redundant boot_time parm from grace_done client tracking op
  ...

1 files changed, 93 insertions, 25 deletions

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 2e80a59e7e91..551f32d7f5c7 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -96,6 +96,8 @@ static struct kmem_cache *deleg_slab;
 
 static void free_session(struct nfsd4_session *);
 
+static struct nfsd4_callback_ops nfsd4_cb_recall_ops;
+
 static bool is_session_dead(struct nfsd4_session *ses)
 {
 	return ses->se_flags & NFS4_SESSION_DEAD;
@@ -645,7 +647,9 @@ alloc_init_deleg(struct nfs4_client *clp, struct svc_fh *current_fh)
 	INIT_LIST_HEAD(&dp->dl_perclnt);
 	INIT_LIST_HEAD(&dp->dl_recall_lru);
 	dp->dl_type = NFS4_OPEN_DELEGATE_READ;
-	INIT_WORK(&dp->dl_recall.cb_work, nfsd4_run_cb_recall);
+	dp->dl_retries = 1;
+	nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client,
+		      &nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL);
 	return dp;
 out_dec:
 	atomic_long_dec(&num_delegations);
@@ -673,15 +677,20 @@ nfs4_put_stid(struct nfs4_stid *s)
 
 static void nfs4_put_deleg_lease(struct nfs4_file *fp)
 {
-	lockdep_assert_held(&state_lock);
+	struct file *filp = NULL;
+	struct file_lock *fl;
 
-	if (!fp->fi_lease)
-		return;
-	if (atomic_dec_and_test(&fp->fi_delegees)) {
-		vfs_setlease(fp->fi_deleg_file, F_UNLCK, &fp->fi_lease);
+	spin_lock(&fp->fi_lock);
+	if (fp->fi_lease && atomic_dec_and_test(&fp->fi_delegees)) {
+		swap(filp, fp->fi_deleg_file);
+		fl = fp->fi_lease;
 		fp->fi_lease = NULL;
-		fput(fp->fi_deleg_file);
-		fp->fi_deleg_file = NULL;
+	}
+	spin_unlock(&fp->fi_lock);
+
+	if (filp) {
+		vfs_setlease(filp, F_UNLCK, &fl);
+		fput(filp);
 	}
 }
 
@@ -717,8 +726,6 @@ unhash_delegation_locked(struct nfs4_delegation *dp)
 	list_del_init(&dp->dl_recall_lru);
 	list_del_init(&dp->dl_perfile);
 	spin_unlock(&fp->fi_lock);
-	if (fp)
-		nfs4_put_deleg_lease(fp);
 }
 
 static void destroy_delegation(struct nfs4_delegation *dp)
@@ -726,6 +733,7 @@ static void destroy_delegation(struct nfs4_delegation *dp)
 	spin_lock(&state_lock);
 	unhash_delegation_locked(dp);
 	spin_unlock(&state_lock);
+	nfs4_put_deleg_lease(dp->dl_stid.sc_file);
 	nfs4_put_stid(&dp->dl_stid);
 }
 
@@ -735,6 +743,8 @@ static void revoke_delegation(struct nfs4_delegation *dp)
 
 	WARN_ON(!list_empty(&dp->dl_recall_lru));
 
+	nfs4_put_deleg_lease(dp->dl_stid.sc_file);
+
 	if (clp->cl_minorversion == 0)
 		nfs4_put_stid(&dp->dl_stid);
 	else {
@@ -1635,6 +1645,7 @@ __destroy_client(struct nfs4_client *clp)
 	while (!list_empty(&reaplist)) {
 		dp = list_entry(reaplist.next, struct nfs4_delegation, dl_recall_lru);
 		list_del_init(&dp->dl_recall_lru);
+		nfs4_put_deleg_lease(dp->dl_stid.sc_file);
 		nfs4_put_stid(&dp->dl_stid);
 	}
 	while (!list_empty(&clp->cl_revoked)) {
@@ -1862,7 +1873,7 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
 		free_client(clp);
 		return NULL;
 	}
-	INIT_WORK(&clp->cl_cb_null.cb_work, nfsd4_run_cb_null);
+	nfsd4_init_cb(&clp->cl_cb_null, clp, NULL, NFSPROC4_CLNT_CB_NULL);
 	clp->cl_time = get_seconds();
 	clear_bit(0, &clp->cl_cb_slot_busy);
 	copy_verf(clp, verf);
@@ -3349,8 +3360,12 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type)
 	return ret;
 }
 
-void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp)
+#define cb_to_delegation(cb) \
+	container_of(cb, struct nfs4_delegation, dl_recall)
+
+static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb)
 {
+	struct nfs4_delegation *dp = cb_to_delegation(cb);
 	struct nfsd_net *nn = net_generic(dp->dl_stid.sc_client->net,
 					  nfsd_net_id);
 
@@ -3371,6 +3386,43 @@ void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp)
 	spin_unlock(&state_lock);
 }
 
+static int nfsd4_cb_recall_done(struct nfsd4_callback *cb,
+		struct rpc_task *task)
+{
+	struct nfs4_delegation *dp = cb_to_delegation(cb);
+
+	switch (task->tk_status) {
+	case 0:
+		return 1;
+	case -EBADHANDLE:
+	case -NFS4ERR_BAD_STATEID:
+		/*
+		 * Race: client probably got cb_recall before open reply
+		 * granting delegation.
+		 */
+		if (dp->dl_retries--) {
+			rpc_delay(task, 2 * HZ);
+			return 0;
+		}
+		/*FALLTHRU*/
+	default:
+		return -1;
+	}
+}
+
+static void nfsd4_cb_recall_release(struct nfsd4_callback *cb)
+{
+	struct nfs4_delegation *dp = cb_to_delegation(cb);
+
+	nfs4_put_stid(&dp->dl_stid);
+}
+
+static struct nfsd4_callback_ops nfsd4_cb_recall_ops = {
+	.prepare	= nfsd4_cb_recall_prepare,
+	.done		= nfsd4_cb_recall_done,
+	.release	= nfsd4_cb_recall_release,
+};
+
 static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
 {
 	/*
@@ -3381,7 +3433,7 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
 	 * it's safe to take a reference.
 	 */
 	atomic_inc(&dp->dl_stid.sc_count);
-	nfsd4_cb_recall(dp);
+	nfsd4_run_cb(&dp->dl_recall);
 }
 
 /* Called from break_lease() with i_lock held. */
@@ -3759,7 +3811,6 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_file *fp, int flag)
 	fl = locks_alloc_lock();
 	if (!fl)
 		return NULL;
-	locks_init_lock(fl);
 	fl->fl_lmops = &nfsd_lease_mng_ops;
 	fl->fl_flags = FL_DELEG;
 	fl->fl_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK;
@@ -4107,7 +4158,7 @@ out:
 	return status;
 }
 
-static void
+void
 nfsd4_end_grace(struct nfsd_net *nn)
 {
 	/* do nothing if grace period already ended */
@@ -4116,14 +4167,28 @@ nfsd4_end_grace(struct nfsd_net *nn)
 
 	dprintk("NFSD: end of grace period\n");
 	nn->grace_ended = true;
-	nfsd4_record_grace_done(nn, nn->boot_time);
+	/*
+	 * If the server goes down again right now, an NFSv4
+	 * client will still be allowed to reclaim after it comes back up,
+	 * even if it hasn't yet had a chance to reclaim state this time.
+	 *
+	 */
+	nfsd4_record_grace_done(nn);
+	/*
+	 * At this point, NFSv4 clients can still reclaim.  But if the
+	 * server crashes, any that have not yet reclaimed will be out
+	 * of luck on the next boot.
+	 *
+	 * (NFSv4.1+ clients are considered to have reclaimed once they
+	 * call RECLAIM_COMPLETE.  NFSv4.0 clients are considered to
+	 * have reclaimed after their first OPEN.)
+	 */
 	locks_end_grace(&nn->nfsd4_manager);
 	/*
-	 * Now that every NFSv4 client has had the chance to recover and
-	 * to see the (possibly new, possibly shorter) lease time, we
-	 * can safely set the next grace time to the current lease time:
+	 * At this point, and once lockd and/or any other containers
+	 * exit their grace period, further reclaims will fail and
+	 * regular locking can resume.
 	 */
-	nn->nfsd4_grace = nn->nfsd4_lease;
 }
 
 static time_t
@@ -5210,7 +5275,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	}
 
 	fp = lock_stp->st_stid.sc_file;
-	locks_init_lock(file_lock);
 	switch (lock->lk_type) {
 		case NFS4_READ_LT:
 		case NFS4_READW_LT:
@@ -5354,7 +5418,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		status = nfserr_jukebox;
 		goto out;
 	}
-	locks_init_lock(file_lock);
+
 	switch (lockt->lt_type) {
 		case NFS4_READ_LT:
 		case NFS4_READW_LT:
@@ -5432,7 +5496,7 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		status = nfserr_jukebox;
 		goto fput;
 	}
-	locks_init_lock(file_lock);
+
 	file_lock->fl_type = F_UNLCK;
 	file_lock->fl_owner = (fl_owner_t)lockowner(stp->st_stateowner);
 	file_lock->fl_pid = current->tgid;
@@ -5645,6 +5709,9 @@ nfs4_check_open_reclaim(clientid_t *clid,
 	if (status)
 		return nfserr_reclaim_bad;
 
+	if (test_bit(NFSD4_CLIENT_RECLAIM_COMPLETE, &cstate->clp->cl_flags))
+		return nfserr_no_grace;
+
 	if (nfsd4_client_record_check(cstate->clp))
 		return nfserr_reclaim_bad;
 
@@ -6342,10 +6409,10 @@ nfs4_state_start_net(struct net *net)
 	ret = nfs4_state_create_net(net);
 	if (ret)
 		return ret;
-	nfsd4_client_tracking_init(net);
 	nn->boot_time = get_seconds();
-	locks_start_grace(net, &nn->nfsd4_manager);
 	nn->grace_ended = false;
+	locks_start_grace(net, &nn->nfsd4_manager);
+	nfsd4_client_tracking_init(net);
 	printk(KERN_INFO "NFSD: starting %ld-second grace period (net %p)\n",
 	       nn->nfsd4_grace, net);
 	queue_delayed_work(laundry_wq, &nn->laundromat_work, nn->nfsd4_grace * HZ);
@@ -6402,6 +6469,7 @@ nfs4_state_shutdown_net(struct net *net)
 	list_for_each_safe(pos, next, &reaplist) {
 		dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
 		list_del_init(&dp->dl_recall_lru);
+		nfs4_put_deleg_lease(dp->dl_stid.sc_file);
 		nfs4_put_stid(&dp->dl_stid);
 	}