Merge tag 'nfs-for-4.15-1' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS client updates from Anna Schumaker:
 "Stable bugfixes:
   - Revalidate "." and ".." correctly on open
   - Avoid RCU usage in tracepoints
   - Fix ugly referral attributes
   - Fix a typo in nomigration mount option
   - Revert "NFS: Move the flock open mode check into nfs_flock()"

  Features:
   - Implement a stronger send queue accounting system for NFS over RDMA
   - Switch some atomics to the new refcount_t type

  Other bugfixes and cleanups:
   - Clean up access mode bits
   - Remove special-case revalidations in nfs_opendir()
   - Improve invalidating NFS over RDMA memory for async operations that
     time out
   - Handle NFS over RDMA replies with a worqueue
   - Handle NFS over RDMA sends with a workqueue
   - Fix up replaying interrupted requests
   - Remove dead NFS over RDMA definitions
   - Update NFS over RDMA copyright information
   - Be more consistent with bool initialization and comparisons
   - Mark expected switch fall throughs
   - Various sunrpc tracepoint cleanups
   - Fix various OPEN races
   - Fix a typo in nfs_rename()
   - Use common error handling code in nfs_lock_and_join_request()
   - Check that some structures are properly cleaned up during
     net_exit()
   - Remove net pointer from dprintk()s"

* tag 'nfs-for-4.15-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (62 commits)
  NFS: Revert "NFS: Move the flock open mode check into nfs_flock()"
  NFS: Fix typo in nomigration mount option
  nfs: Fix ugly referral attributes
  NFS: super: mark expected switch fall-throughs
  sunrpc: remove net pointer from messages
  nfs: remove net pointer from messages
  sunrpc: exit_net cleanup check added
  nfs client: exit_net cleanup check added
  nfs/write: Use common error handling code in nfs_lock_and_join_requests()
  NFSv4: Replace closed stateids with the "invalid special stateid"
  NFSv4: nfs_set_open_stateid must not trigger state recovery for closed state
  NFSv4: Check the open stateid when searching for expired state
  NFSv4: Clean up nfs4_delegreturn_done
  NFSv4: cleanup nfs4_close_done
  NFSv4: Retry NFS4ERR_OLD_STATEID errors in layoutreturn
  pNFS: Retry NFS4ERR_OLD_STATEID errors in layoutreturn-on-close
  NFSv4: Don't try to CLOSE if the stateid 'other' field has changed
  NFSv4: Retry CLOSE and DELEGRETURN on NFS4ERR_OLD_STATEID.
  NFS: Fix a typo in nfs_rename()
  NFSv4: Fix open create exclusive when the server reboots
  ...

fs/nfs/cache_lib.c

@@ -67,7 +67,7 @@ out:
  */
 void nfs_cache_defer_req_put(struct nfs_cache_defer_req *dreq)
 {
-	if (atomic_dec_and_test(&dreq->count))
+	if (refcount_dec_and_test(&dreq->count))
 		kfree(dreq);
 }
 
@@ -87,7 +87,7 @@ static struct cache_deferred_req *nfs_dns_cache_defer(struct cache_req *req)
 
 	dreq = container_of(req, struct nfs_cache_defer_req, req);
 	dreq->deferred_req.revisit = nfs_dns_cache_revisit;
-	atomic_inc(&dreq->count);
+	refcount_inc(&dreq->count);
 
 	return &dreq->deferred_req;
 }
@@ -99,7 +99,7 @@ struct nfs_cache_defer_req *nfs_cache_defer_req_alloc(void)
 	dreq = kzalloc(sizeof(*dreq), GFP_KERNEL);
 	if (dreq) {
 		init_completion(&dreq->completion);
-		atomic_set(&dreq->count, 1);
+		refcount_set(&dreq->count, 1);
 		dreq->req.defer = nfs_dns_cache_defer;
 	}
 	return dreq;

fs/nfs/cache_lib.h

@@ -16,7 +16,7 @@ struct nfs_cache_defer_req {
 	struct cache_req req;
 	struct cache_deferred_req deferred_req;
 	struct completion completion;
-	atomic_t count;
+	refcount_t count;
 };
 
 extern int nfs_cache_upcall(struct cache_detail *cd, char *entry_name);

fs/nfs/callback.c

@@ -49,15 +49,15 @@ static int nfs4_callback_up_net(struct svc_serv *serv, struct net *net)
 	if (ret <= 0)
 		goto out_err;
 	nn->nfs_callback_tcpport = ret;
-	dprintk("NFS: Callback listener port = %u (af %u, net %p)\n",
-			nn->nfs_callback_tcpport, PF_INET, net);
+	dprintk("NFS: Callback listener port = %u (af %u, net %x)\n",
+		nn->nfs_callback_tcpport, PF_INET, net->ns.inum);
 
 	ret = svc_create_xprt(serv, "tcp", net, PF_INET6,
 				nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
 	if (ret > 0) {
 		nn->nfs_callback_tcpport6 = ret;
-		dprintk("NFS: Callback listener port = %u (af %u, net %p)\n",
-				nn->nfs_callback_tcpport6, PF_INET6, net);
+		dprintk("NFS: Callback listener port = %u (af %u, net %x\n",
+			nn->nfs_callback_tcpport6, PF_INET6, net->ns.inum);
 	} else if (ret != -EAFNOSUPPORT)
 		goto out_err;
 	return 0;
@@ -185,7 +185,7 @@ static void nfs_callback_down_net(u32 minorversion, struct svc_serv *serv, struc
 	if (--nn->cb_users[minorversion])
 		return;
 
-	dprintk("NFS: destroy per-net callback data; net=%p\n", net);
+	dprintk("NFS: destroy per-net callback data; net=%x\n", net->ns.inum);
 	svc_shutdown_net(serv, net);
 }
 
@@ -198,7 +198,7 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv,
 	if (nn->cb_users[minorversion]++)
 		return 0;
 
-	dprintk("NFS: create per-net callback data; net=%p\n", net);
+	dprintk("NFS: create per-net callback data; net=%x\n", net->ns.inum);
 
 	ret = svc_bind(serv, net);
 	if (ret < 0) {
@@ -223,7 +223,7 @@ err_socks:
 err_bind:
 	nn->cb_users[minorversion]--;
 	dprintk("NFS: Couldn't create callback socket: err = %d; "
-			"net = %p\n", ret, net);
+			"net = %x\n", ret, net->ns.inum);
 	return ret;
 }
 

fs/nfs/callback_proc.c

@@ -440,7 +440,7 @@ static bool referring_call_exists(struct nfs_client *clp,
 				  uint32_t nrclists,
 				  struct referring_call_list *rclists)
 {
-	bool status = 0;
+	bool status = false;
 	int i, j;
 	struct nfs4_session *session;
 	struct nfs4_slot_table *tbl;

fs/nfs/client.c

@@ -163,7 +163,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
 
 	clp->rpc_ops = clp->cl_nfs_mod->rpc_ops;
 
-	atomic_set(&clp->cl_count, 1);
+	refcount_set(&clp->cl_count, 1);
 	clp->cl_cons_state = NFS_CS_INITING;
 
 	memcpy(&clp->cl_addr, cl_init->addr, cl_init->addrlen);
@@ -269,7 +269,7 @@ void nfs_put_client(struct nfs_client *clp)
 
 	nn = net_generic(clp->cl_net, nfs_net_id);
 
-	if (atomic_dec_and_lock(&clp->cl_count, &nn->nfs_client_lock)) {
+	if (refcount_dec_and_lock(&clp->cl_count, &nn->nfs_client_lock)) {
 		list_del(&clp->cl_share_link);
 		nfs_cb_idr_remove_locked(clp);
 		spin_unlock(&nn->nfs_client_lock);
@@ -314,7 +314,7 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
 							   sap))
 				continue;
 
-		atomic_inc(&clp->cl_count);
+		refcount_inc(&clp->cl_count);
 		return clp;
 	}
 	return NULL;
@@ -1006,7 +1006,7 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source,
 	/* Copy data from the source */
 	server->nfs_client = source->nfs_client;
 	server->destroy = source->destroy;
-	atomic_inc(&server->nfs_client->cl_count);
+	refcount_inc(&server->nfs_client->cl_count);
 	nfs_server_copy_userdata(server, source);
 
 	server->fsid = fattr->fsid;
@@ -1166,7 +1166,7 @@ static int nfs_server_list_show(struct seq_file *m, void *v)
 		   clp->rpc_ops->version,
 		   rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_ADDR),
 		   rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_PORT),
-		   atomic_read(&clp->cl_count),
+		   refcount_read(&clp->cl_count),
 		   clp->cl_hostname);
 	rcu_read_unlock();
 

fs/nfs/delegation.c

@@ -1040,6 +1040,33 @@ int nfs_delegations_present(struct nfs_client *clp)
 	return ret;
 }
 
+/**
+ * nfs4_refresh_delegation_stateid - Update delegation stateid seqid
+ * @dst: stateid to refresh
+ * @inode: inode to check
+ *
+ * Returns "true" and updates "dst->seqid" * if inode had a delegation
+ * that matches our delegation stateid. Otherwise "false" is returned.
+ */
+bool nfs4_refresh_delegation_stateid(nfs4_stateid *dst, struct inode *inode)
+{
+	struct nfs_delegation *delegation;
+	bool ret = false;
+	if (!inode)
+		goto out;
+
+	rcu_read_lock();
+	delegation = rcu_dereference(NFS_I(inode)->delegation);
+	if (delegation != NULL &&
+	    nfs4_stateid_match_other(dst, &delegation->stateid)) {
+		dst->seqid = delegation->stateid.seqid;
+		return ret;
+	}
+	rcu_read_unlock();
+out:
+	return ret;
+}
+
 /**
  * nfs4_copy_delegation_stateid - Copy inode's state ID information
  * @inode: inode to check

fs/nfs/delegation.h

@@ -62,6 +62,7 @@ int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4
 int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid, fmode_t type);
 int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid);
 bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags, nfs4_stateid *dst, struct rpc_cred **cred);
+bool nfs4_refresh_delegation_stateid(nfs4_stateid *dst, struct inode *inode);
 
 void nfs_mark_delegation_referenced(struct nfs_delegation *delegation);
 int nfs4_have_delegation(struct inode *inode, fmode_t flags);

fs/nfs/dir.c

@@ -118,13 +118,6 @@ nfs_opendir(struct inode *inode, struct file *filp)
 		goto out;
 	}
 	filp->private_data = ctx;
-	if (filp->f_path.dentry == filp->f_path.mnt->mnt_root) {
-		/* This is a mountpoint, so d_revalidate will never
-		 * have been called, so we need to refresh the
-		 * inode (for close-open consistency) ourselves.
-		 */
-		__nfs_revalidate_inode(NFS_SERVER(inode), inode);
-	}
 out:
 	put_rpccred(cred);
 	return res;
@@ -253,7 +246,7 @@ int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descri
 	desc->cache_entry_index = index;
 	return 0;
 out_eof:
-	desc->eof = 1;
+	desc->eof = true;
 	return -EBADCOOKIE;
 }
 
@@ -307,7 +300,7 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des
 	if (array->eof_index >= 0) {
 		status = -EBADCOOKIE;
 		if (*desc->dir_cookie == array->last_cookie)
-			desc->eof = 1;
+			desc->eof = true;
 	}
 out:
 	return status;
@@ -761,7 +754,7 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc)
 		ent = &array->array[i];
 		if (!dir_emit(desc->ctx, ent->string.name, ent->string.len,
 		    nfs_compat_user_ino64(ent->ino), ent->d_type)) {
-			desc->eof = 1;
+			desc->eof = true;
 			break;
 		}
 		desc->ctx->pos++;
@@ -773,7 +766,7 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc)
 			ctx->duped = 1;
 	}
 	if (array->eof_index >= 0)
-		desc->eof = 1;
+		desc->eof = true;
 
 	kunmap(desc->page);
 	cache_page_release(desc);
@@ -873,7 +866,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 		if (res == -EBADCOOKIE) {
 			res = 0;
 			/* This means either end of directory */
-			if (*desc->dir_cookie && desc->eof == 0) {
+			if (*desc->dir_cookie && !desc->eof) {
 				/* Or that the server has 'lost' a cookie */
 				res = uncached_readdir(desc);
 				if (res == 0)
@@ -1241,8 +1234,7 @@ static int nfs_weak_revalidate(struct dentry *dentry, unsigned int flags)
 		return 0;
 	}
 
-	if (nfs_mapping_need_revalidate_inode(inode))
-		error = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
+	error = nfs_lookup_verify_inode(inode, flags);
 	dfprintk(LOOKUPCACHE, "NFS: %s: inode %lu is %s\n",
 			__func__, inode->i_ino, error ? "invalid" : "valid");
 	return !error;
@@ -1393,6 +1385,7 @@ static int nfs4_lookup_revalidate(struct dentry *, unsigned int);
 
 const struct dentry_operations nfs4_dentry_operations = {
 	.d_revalidate	= nfs4_lookup_revalidate,
+	.d_weak_revalidate	= nfs_weak_revalidate,
 	.d_delete	= nfs_dentry_delete,
 	.d_iput		= nfs_dentry_iput,
 	.d_automount	= nfs_d_automount,
@@ -2064,7 +2057,7 @@ out:
 		 * should mark the directories for revalidation.
 		 */
 		d_move(old_dentry, new_dentry);
-		nfs_set_verifier(new_dentry,
+		nfs_set_verifier(old_dentry,
 					nfs_save_change_attribute(new_dir));
 	} else if (error == -ENOENT)
 		nfs_dentry_handle_enoent(old_dentry);
@@ -2369,15 +2362,15 @@ void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set)
 }
 EXPORT_SYMBOL_GPL(nfs_access_add_cache);
 
-#define NFS_MAY_READ (NFS4_ACCESS_READ)
-#define NFS_MAY_WRITE (NFS4_ACCESS_MODIFY | \
-		NFS4_ACCESS_EXTEND | \
-		NFS4_ACCESS_DELETE)
-#define NFS_FILE_MAY_WRITE (NFS4_ACCESS_MODIFY | \
-		NFS4_ACCESS_EXTEND)
+#define NFS_MAY_READ (NFS_ACCESS_READ)
+#define NFS_MAY_WRITE (NFS_ACCESS_MODIFY | \
+		NFS_ACCESS_EXTEND | \
+		NFS_ACCESS_DELETE)
+#define NFS_FILE_MAY_WRITE (NFS_ACCESS_MODIFY | \
+		NFS_ACCESS_EXTEND)
 #define NFS_DIR_MAY_WRITE NFS_MAY_WRITE
-#define NFS_MAY_LOOKUP (NFS4_ACCESS_LOOKUP)
-#define NFS_MAY_EXECUTE (NFS4_ACCESS_EXECUTE)
+#define NFS_MAY_LOOKUP (NFS_ACCESS_LOOKUP)
+#define NFS_MAY_EXECUTE (NFS_ACCESS_EXECUTE)
 static int
 nfs_access_calc_mask(u32 access_result, umode_t umode)
 {
@@ -2425,9 +2418,14 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
 	if (!may_block)
 		goto out;
 
-	/* Be clever: ask server to check for all possible rights */
-	cache.mask = NFS_MAY_LOOKUP | NFS_MAY_EXECUTE
-		     | NFS_MAY_WRITE | NFS_MAY_READ;
+	/*
+	 * Determine which access bits we want to ask for...
+	 */
+	cache.mask = NFS_ACCESS_READ | NFS_ACCESS_MODIFY | NFS_ACCESS_EXTEND;
+	if (S_ISDIR(inode->i_mode))
+		cache.mask |= NFS_ACCESS_DELETE | NFS_ACCESS_LOOKUP;
+	else
+		cache.mask |= NFS_ACCESS_EXECUTE;
 	cache.cred = cred;
 	status = NFS_PROTO(inode)->access(inode, &cache);
 	if (status != 0) {

fs/nfs/file.c

@@ -829,23 +829,9 @@ int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
 	if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FLOCK)
 		is_local = 1;
 
-	/*
-	 * VFS doesn't require the open mode to match a flock() lock's type.
-	 * NFS, however, may simulate flock() locking with posix locking which
-	 * requires the open mode to match the lock type.
-	 */
-	switch (fl->fl_type) {
-	case F_UNLCK:
+	/* We're simulating flock() locks using posix locks on the server */
+	if (fl->fl_type == F_UNLCK)
 		return do_unlk(filp, cmd, fl, is_local);
-	case F_RDLCK:
-		if (!(filp->f_mode & FMODE_READ))
-			return -EBADF;
-		break;
-	case F_WRLCK:
-		if (!(filp->f_mode & FMODE_WRITE))
-			return -EBADF;
-	}
-
 	return do_setlk(filp, cmd, fl, is_local);
 }
 EXPORT_SYMBOL_GPL(nfs_flock);

fs/nfs/filelayout/filelayout.c

@@ -471,10 +471,10 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr)
 		return PNFS_NOT_ATTEMPTED;
 
 	dprintk("%s USE DS: %s cl_count %d\n", __func__,
-		ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count));
+		ds->ds_remotestr, refcount_read(&ds->ds_clp->cl_count));
 
 	/* No multipath support. Use first DS */
-	atomic_inc(&ds->ds_clp->cl_count);
+	refcount_inc(&ds->ds_clp->cl_count);
 	hdr->ds_clp = ds->ds_clp;
 	hdr->ds_commit_idx = idx;
 	fh = nfs4_fl_select_ds_fh(lseg, j);
@@ -515,10 +515,10 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 
 	dprintk("%s ino %lu sync %d req %zu@%llu DS: %s cl_count %d\n",
 		__func__, hdr->inode->i_ino, sync, (size_t) hdr->args.count,
-		offset, ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count));
+		offset, ds->ds_remotestr, refcount_read(&ds->ds_clp->cl_count));
 
 	hdr->pgio_done_cb = filelayout_write_done_cb;
-	atomic_inc(&ds->ds_clp->cl_count);
+	refcount_inc(&ds->ds_clp->cl_count);
 	hdr->ds_clp = ds->ds_clp;
 	hdr->ds_commit_idx = idx;
 	fh = nfs4_fl_select_ds_fh(lseg, j);
@@ -1064,9 +1064,9 @@ static int filelayout_initiate_commit(struct nfs_commit_data *data, int how)
 		goto out_err;
 
 	dprintk("%s ino %lu, how %d cl_count %d\n", __func__,
-		data->inode->i_ino, how, atomic_read(&ds->ds_clp->cl_count));
+		data->inode->i_ino, how, refcount_read(&ds->ds_clp->cl_count));
 	data->commit_done_cb = filelayout_commit_done_cb;
-	atomic_inc(&ds->ds_clp->cl_count);
+	refcount_inc(&ds->ds_clp->cl_count);
 	data->ds_clp = ds->ds_clp;
 	fh = select_ds_fh_from_commit(lseg, data->ds_commit_index);
 	if (fh)

fs/nfs/flexfilelayout/flexfilelayout.c

@@ -187,7 +187,7 @@ ff_layout_add_mirror(struct pnfs_layout_hdr *lo,
 			continue;
 		if (!ff_mirror_match_fh(mirror, pos))
 			continue;
-		if (atomic_inc_not_zero(&pos->ref)) {
+		if (refcount_inc_not_zero(&pos->ref)) {
 			spin_unlock(&inode->i_lock);
 			return pos;
 		}
@@ -218,7 +218,7 @@ static struct nfs4_ff_layout_mirror *ff_layout_alloc_mirror(gfp_t gfp_flags)
 	mirror = kzalloc(sizeof(*mirror), gfp_flags);
 	if (mirror != NULL) {
 		spin_lock_init(&mirror->lock);
-		atomic_set(&mirror->ref, 1);
+		refcount_set(&mirror->ref, 1);
 		INIT_LIST_HEAD(&mirror->mirrors);
 	}
 	return mirror;
@@ -242,7 +242,7 @@ static void ff_layout_free_mirror(struct nfs4_ff_layout_mirror *mirror)
 
 static void ff_layout_put_mirror(struct nfs4_ff_layout_mirror *mirror)
 {
-	if (mirror != NULL && atomic_dec_and_test(&mirror->ref))
+	if (mirror != NULL && refcount_dec_and_test(&mirror->ref))
 		ff_layout_free_mirror(mirror);
 }
 
@@ -1726,10 +1726,10 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 	vers = nfs4_ff_layout_ds_version(lseg, idx);
 
 	dprintk("%s USE DS: %s cl_count %d vers %d\n", __func__,
-		ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count), vers);
+		ds->ds_remotestr, refcount_read(&ds->ds_clp->cl_count), vers);
 
 	hdr->pgio_done_cb = ff_layout_read_done_cb;
-	atomic_inc(&ds->ds_clp->cl_count);
+	refcount_inc(&ds->ds_clp->cl_count);
 	hdr->ds_clp = ds->ds_clp;
 	fh = nfs4_ff_layout_select_ds_fh(lseg, idx);
 	if (fh)
@@ -1785,11 +1785,11 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 
 	dprintk("%s ino %lu sync %d req %zu@%llu DS: %s cl_count %d vers %d\n",
 		__func__, hdr->inode->i_ino, sync, (size_t) hdr->args.count,
-		offset, ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count),
+		offset, ds->ds_remotestr, refcount_read(&ds->ds_clp->cl_count),
 		vers);
 
 	hdr->pgio_done_cb = ff_layout_write_done_cb;
-	atomic_inc(&ds->ds_clp->cl_count);
+	refcount_inc(&ds->ds_clp->cl_count);
 	hdr->ds_clp = ds->ds_clp;
 	hdr->ds_commit_idx = idx;
 	fh = nfs4_ff_layout_select_ds_fh(lseg, idx);
@@ -1863,11 +1863,11 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
 	vers = nfs4_ff_layout_ds_version(lseg, idx);
 
 	dprintk("%s ino %lu, how %d cl_count %d vers %d\n", __func__,
-		data->inode->i_ino, how, atomic_read(&ds->ds_clp->cl_count),
+		data->inode->i_ino, how, refcount_read(&ds->ds_clp->cl_count),
 		vers);
 	data->commit_done_cb = ff_layout_commit_done_cb;
 	data->cred = ds_cred;
-	atomic_inc(&ds->ds_clp->cl_count);
+	refcount_inc(&ds->ds_clp->cl_count);
 	data->ds_clp = ds->ds_clp;
 	fh = select_ds_fh_from_commit(lseg, data->ds_commit_index);
 	if (fh)
@@ -2286,7 +2286,7 @@ ff_layout_mirror_prepare_stats(struct pnfs_layout_hdr *lo,
 		if (!test_and_clear_bit(NFS4_FF_MIRROR_STAT_AVAIL, &mirror->flags))
 			continue;
 		/* mirror refcount put in cleanup_layoutstats */
-		if (!atomic_inc_not_zero(&mirror->ref))
+		if (!refcount_inc_not_zero(&mirror->ref))
 			continue;
 		dev = &mirror->mirror_ds->id_node; 
 		memcpy(&devinfo->dev_id, &dev->deviceid, NFS4_DEVICEID4_SIZE);

fs/nfs/flexfilelayout/flexfilelayout.h

@@ -14,6 +14,7 @@
 #define FF_FLAGS_NO_IO_THRU_MDS  2
 #define FF_FLAGS_NO_READ_IO      4
 
+#include <linux/refcount.h>
 #include "../pnfs.h"
 
 /* XXX: Let's filter out insanely large mirror count for now to avoid oom
@@ -82,7 +83,7 @@ struct nfs4_ff_layout_mirror {
 	nfs4_stateid			stateid;
 	struct rpc_cred	__rcu		*ro_cred;
 	struct rpc_cred	__rcu		*rw_cred;
-	atomic_t			ref;
+	refcount_t			ref;
 	spinlock_t			lock;
 	unsigned long			flags;
 	struct nfs4_ff_layoutstat	read_stat;

fs/nfs/inode.c

@@ -783,7 +783,7 @@ EXPORT_SYMBOL_GPL(nfs_getattr);
 
 static void nfs_init_lock_context(struct nfs_lock_context *l_ctx)
 {
-	atomic_set(&l_ctx->count, 1);
+	refcount_set(&l_ctx->count, 1);
 	l_ctx->lockowner = current->files;
 	INIT_LIST_HEAD(&l_ctx->list);
 	atomic_set(&l_ctx->io_count, 0);
@@ -797,7 +797,7 @@ static struct nfs_lock_context *__nfs_find_lock_context(struct nfs_open_context
 	do {
 		if (pos->lockowner != current->files)
 			continue;
-		atomic_inc(&pos->count);
+		refcount_inc(&pos->count);
 		return pos;
 	} while ((pos = list_entry(pos->list.next, typeof(*pos), list)) != head);
 	return NULL;
@@ -836,7 +836,7 @@ void nfs_put_lock_context(struct nfs_lock_context *l_ctx)
 	struct nfs_open_context *ctx = l_ctx->open_context;
 	struct inode *inode = d_inode(ctx->dentry);
 
-	if (!atomic_dec_and_lock(&l_ctx->count, &inode->i_lock))
+	if (!refcount_dec_and_lock(&l_ctx->count, &inode->i_lock))
 		return;
 	list_del(&l_ctx->list);
 	spin_unlock(&inode->i_lock);
@@ -913,7 +913,7 @@ EXPORT_SYMBOL_GPL(alloc_nfs_open_context);
 struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx)
 {
 	if (ctx != NULL)
-		atomic_inc(&ctx->lock_context.count);
+		refcount_inc(&ctx->lock_context.count);
 	return ctx;
 }
 EXPORT_SYMBOL_GPL(get_nfs_open_context);
@@ -924,11 +924,11 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
 	struct super_block *sb = ctx->dentry->d_sb;
 
 	if (!list_empty(&ctx->list)) {
-		if (!atomic_dec_and_lock(&ctx->lock_context.count, &inode->i_lock))
+		if (!refcount_dec_and_lock(&ctx->lock_context.count, &inode->i_lock))
 			return;
 		list_del(&ctx->list);
 		spin_unlock(&inode->i_lock);
-	} else if (!atomic_dec_and_test(&ctx->lock_context.count))
+	} else if (!refcount_dec_and_test(&ctx->lock_context.count))
 		return;
 	if (inode != NULL)
 		NFS_PROTO(inode)->close_context(ctx, is_sync);
@@ -2084,8 +2084,12 @@ static int nfs_net_init(struct net *net)
 
 static void nfs_net_exit(struct net *net)
 {
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+
 	nfs_fs_proc_net_exit(net);
 	nfs_cleanup_cb_ident_idr(net);
+	WARN_ON_ONCE(!list_empty(&nn->nfs_client_list));
+	WARN_ON_ONCE(!list_empty(&nn->nfs_volume_list));
 }
 
 static struct pernet_operations nfs_net_ops = {

fs/nfs/nfs3proc.c

@@ -188,6 +188,7 @@ static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry)
 {
 	struct nfs3_accessargs	arg = {
 		.fh		= NFS_FH(inode),
+		.access		= entry->mask,
 	};
 	struct nfs3_accessres	res;
 	struct rpc_message msg = {
@@ -196,25 +197,9 @@ static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry)
 		.rpc_resp	= &res,
 		.rpc_cred	= entry->cred,
 	};
-	int mode = entry->mask;
 	int status = -ENOMEM;
 
 	dprintk("NFS call  access\n");
-
-	if (mode & MAY_READ)
-		arg.access |= NFS3_ACCESS_READ;
-	if (S_ISDIR(inode->i_mode)) {
-		if (mode & MAY_WRITE)
-			arg.access |= NFS3_ACCESS_MODIFY | NFS3_ACCESS_EXTEND | NFS3_ACCESS_DELETE;
-		if (mode & MAY_EXEC)
-			arg.access |= NFS3_ACCESS_LOOKUP;
-	} else {
-		if (mode & MAY_WRITE)
-			arg.access |= NFS3_ACCESS_MODIFY | NFS3_ACCESS_EXTEND;
-		if (mode & MAY_EXEC)
-			arg.access |= NFS3_ACCESS_EXECUTE;
-	}
-
 	res.fattr = nfs_alloc_fattr();
 	if (res.fattr == NULL)
 		goto out;

fs/nfs/nfs4_fs.h

@@ -145,7 +145,7 @@ struct nfs4_lock_state {
 	unsigned long		ls_flags;
 	struct nfs_seqid_counter	ls_seqid;
 	nfs4_stateid		ls_stateid;
-	atomic_t		ls_count;
+	refcount_t		ls_count;
 	fl_owner_t		ls_owner;
 };
 
@@ -162,6 +162,7 @@ enum {
 	NFS_STATE_POSIX_LOCKS,		/* Posix locks are supported */
 	NFS_STATE_RECOVERY_FAILED,	/* OPEN stateid state recovery failed */
 	NFS_STATE_MAY_NOTIFY_LOCK,	/* server may CB_NOTIFY_LOCK */
+	NFS_STATE_CHANGE_WAIT,		/* A state changing operation is outstanding */
 };
 
 struct nfs4_state {
@@ -185,6 +186,8 @@ struct nfs4_state {
 	unsigned int n_rdwr;		/* Number of read/write references */
 	fmode_t state;			/* State on the server (R,W, or RW) */
 	atomic_t count;
+
+	wait_queue_head_t waitq;
 };
 
 
@@ -458,6 +461,10 @@ extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl);
 extern int nfs4_select_rw_stateid(struct nfs4_state *, fmode_t,
 		const struct nfs_lock_context *, nfs4_stateid *,
 		struct rpc_cred **);
+extern bool nfs4_refresh_open_stateid(nfs4_stateid *dst,
+		struct nfs4_state *state);
+extern bool nfs4_copy_open_stateid(nfs4_stateid *dst,
+		struct nfs4_state *state);
 
 extern struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_mask);
 extern int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task);
@@ -465,7 +472,7 @@ extern void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid);
 extern void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid);
 extern void nfs_release_seqid(struct nfs_seqid *seqid);
 extern void nfs_free_seqid(struct nfs_seqid *seqid);
-extern int nfs4_setup_sequence(const struct nfs_client *client,
+extern int nfs4_setup_sequence(struct nfs_client *client,
 				struct nfs4_sequence_args *args,
 				struct nfs4_sequence_res *res,
 				struct rpc_task *task);
@@ -475,6 +482,7 @@ extern int nfs4_sequence_done(struct rpc_task *task,
 extern void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp);
 
 extern const nfs4_stateid zero_stateid;
+extern const nfs4_stateid invalid_stateid;
 
 /* nfs4super.c */
 struct nfs_mount_info;

fs/nfs/nfs4client.c

@@ -483,7 +483,7 @@ static int nfs4_match_client(struct nfs_client  *pos,  struct nfs_client *new,
 	 * ID and serverowner fields.  Wait for CREATE_SESSION
 	 * to finish. */
 	if (pos->cl_cons_state > NFS_CS_READY) {
-		atomic_inc(&pos->cl_count);
+		refcount_inc(&pos->cl_count);
 		spin_unlock(&nn->nfs_client_lock);
 
 		nfs_put_client(*prev);
@@ -559,7 +559,7 @@ int nfs40_walk_client_list(struct nfs_client *new,
 		 * way that a SETCLIENTID_CONFIRM to pos can succeed is
 		 * if new and pos point to the same server:
 		 */
-		atomic_inc(&pos->cl_count);
+		refcount_inc(&pos->cl_count);
 		spin_unlock(&nn->nfs_client_lock);
 
 		nfs_put_client(prev);
@@ -715,7 +715,7 @@ int nfs41_walk_client_list(struct nfs_client *new,
 			continue;
 
 found:
-		atomic_inc(&pos->cl_count);
+		refcount_inc(&pos->cl_count);
 		*result = pos;
 		status = 0;
 		break;
@@ -749,7 +749,7 @@ nfs4_find_client_ident(struct net *net, int cb_ident)
 	spin_lock(&nn->nfs_client_lock);
 	clp = idr_find(&nn->cb_ident_idr, cb_ident);
 	if (clp)
-		atomic_inc(&clp->cl_count);
+		refcount_inc(&clp->cl_count);
 	spin_unlock(&nn->nfs_client_lock);
 	return clp;
 }
@@ -793,7 +793,7 @@ nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
 
 	spin_lock(&nn->nfs_client_lock);
 	list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
-		if (nfs4_cb_match_client(addr, clp, minorversion) == false)
+		if (!nfs4_cb_match_client(addr, clp, minorversion))
 			continue;
 
 		if (!nfs4_has_session(clp))
@@ -804,7 +804,7 @@ nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
 		    sid->data, NFS4_MAX_SESSIONID_LEN) != 0)
 			continue;
 
-		atomic_inc(&clp->cl_count);
+		refcount_inc(&clp->cl_count);
 		spin_unlock(&nn->nfs_client_lock);
 		return clp;
 	}

fs/nfs/nfs4state.c

@@ -69,6 +69,14 @@ const nfs4_stateid zero_stateid = {
 	{ .data = { 0 } },
 	.type = NFS4_SPECIAL_STATEID_TYPE,
 };
+const nfs4_stateid invalid_stateid = {
+	{
+		.seqid = cpu_to_be32(0xffffffffU),
+		.other = { 0 },
+	},
+	.type = NFS4_INVALID_STATEID_TYPE,
+};
+
 static DEFINE_MUTEX(nfs_clid_init_mutex);
 
 int nfs4_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
@@ -645,6 +653,7 @@ nfs4_alloc_open_state(void)
 	INIT_LIST_HEAD(&state->lock_states);
 	spin_lock_init(&state->state_lock);
 	seqlock_init(&state->seqlock);
+	init_waitqueue_head(&state->waitq);
 	return state;
 }
 
@@ -825,7 +834,7 @@ __nfs4_find_lock_state(struct nfs4_state *state,
 			ret = pos;
 	}
 	if (ret)
-		atomic_inc(&ret->ls_count);
+		refcount_inc(&ret->ls_count);
 	return ret;
 }
 
@@ -843,7 +852,7 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f
 	if (lsp == NULL)
 		return NULL;
 	nfs4_init_seqid_counter(&lsp->ls_seqid);
-	atomic_set(&lsp->ls_count, 1);
+	refcount_set(&lsp->ls_count, 1);
 	lsp->ls_state = state;
 	lsp->ls_owner = fl_owner;
 	lsp->ls_seqid.owner_id = ida_simple_get(&server->lockowner_id, 0, 0, GFP_NOFS);
@@ -907,7 +916,7 @@ void nfs4_put_lock_state(struct nfs4_lock_state *lsp)
 	if (lsp == NULL)
 		return;
 	state = lsp->ls_state;
-	if (!atomic_dec_and_lock(&lsp->ls_count, &state->state_lock))
+	if (!refcount_dec_and_lock(&lsp->ls_count, &state->state_lock))
 		return;
 	list_del(&lsp->ls_locks);
 	if (list_empty(&state->lock_states))
@@ -927,7 +936,7 @@ static void nfs4_fl_copy_lock(struct file_lock *dst, struct file_lock *src)
 	struct nfs4_lock_state *lsp = src->fl_u.nfs4_fl.owner;
 
 	dst->fl_u.nfs4_fl.owner = lsp;
-	atomic_inc(&lsp->ls_count);
+	refcount_inc(&lsp->ls_count);
 }
 
 static void nfs4_fl_release_lock(struct file_lock *fl)
@@ -985,18 +994,39 @@ out:
 	return ret;
 }
 
-static void nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
+bool nfs4_refresh_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
 {
+	bool ret;
+	int seq;
+
+	do {
+		ret = false;
+		seq = read_seqbegin(&state->seqlock);
+		if (nfs4_state_match_open_stateid_other(state, dst)) {
+			dst->seqid = state->open_stateid.seqid;
+			ret = true;
+		}
+	} while (read_seqretry(&state->seqlock, seq));
+	return ret;
+}
+
+bool nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
+{
+	bool ret;
 	const nfs4_stateid *src;
 	int seq;
 
 	do {
+		ret = false;
 		src = &zero_stateid;
 		seq = read_seqbegin(&state->seqlock);
-		if (test_bit(NFS_OPEN_STATE, &state->flags))
+		if (test_bit(NFS_OPEN_STATE, &state->flags)) {
 			src = &state->open_stateid;
+			ret = true;
+		}
 		nfs4_stateid_copy(dst, src);
 	} while (read_seqretry(&state->seqlock, seq));
+	return ret;
 }
 
 /*
@@ -1177,7 +1207,7 @@ void nfs4_schedule_state_manager(struct nfs_client *clp)
 	if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0)
 		return;
 	__module_get(THIS_MODULE);
-	atomic_inc(&clp->cl_count);
+	refcount_inc(&clp->cl_count);
 
 	/* The rcu_read_lock() is not strictly necessary, as the state
 	 * manager is the only thread that ever changes the rpc_xprt
@@ -1269,7 +1299,7 @@ int nfs4_wait_clnt_recover(struct nfs_client *clp)
 
 	might_sleep();
 
-	atomic_inc(&clp->cl_count);
+	refcount_inc(&clp->cl_count);
 	res = wait_on_bit_action(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING,
 				 nfs_wait_bit_killable, TASK_KILLABLE);
 	if (res)
@@ -1409,6 +1439,11 @@ void nfs_inode_find_state_and_recover(struct inode *inode,
 			found = true;
 			continue;
 		}
+		if (nfs4_stateid_match_other(&state->open_stateid, stateid) &&
+		    nfs4_state_mark_reclaim_nograce(clp, state)) {
+			found = true;
+			continue;
+		}
 		if (nfs_state_lock_state_matches_stateid(state, stateid) &&
 		    nfs4_state_mark_reclaim_nograce(clp, state))
 			found = true;
@@ -2510,7 +2545,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
 			break;
 		if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0)
 			break;
-	} while (atomic_read(&clp->cl_count) > 1);
+	} while (refcount_read(&clp->cl_count) > 1);
 	return;
 out_error:
 	if (strlen(section))

fs/nfs/nfs4trace.h

@@ -202,17 +202,13 @@ DECLARE_EVENT_CLASS(nfs4_clientid_event,
 		TP_ARGS(clp, error),
 
 		TP_STRUCT__entry(
-			__string(dstaddr,
-				rpc_peeraddr2str(clp->cl_rpcclient,
-					RPC_DISPLAY_ADDR))
+			__string(dstaddr, clp->cl_hostname)
 			__field(int, error)
 		),
 
 		TP_fast_assign(
 			__entry->error = error;
-			__assign_str(dstaddr,
-				rpc_peeraddr2str(clp->cl_rpcclient,
-						RPC_DISPLAY_ADDR));
+			__assign_str(dstaddr, clp->cl_hostname);
 		),
 
 		TP_printk(
@@ -1066,6 +1062,8 @@ DECLARE_EVENT_CLASS(nfs4_inode_stateid_event,
 
 DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_setattr);
 DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_delegreturn);
+DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_open_stateid_update);
+DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_open_stateid_update_wait);
 
 DECLARE_EVENT_CLASS(nfs4_getattr_event,
 		TP_PROTO(
@@ -1133,9 +1131,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_callback_event,
 			__field(dev_t, dev)
 			__field(u32, fhandle)
 			__field(u64, fileid)
-			__string(dstaddr, clp ?
-				rpc_peeraddr2str(clp->cl_rpcclient,
-					RPC_DISPLAY_ADDR) : "unknown")
+			__string(dstaddr, clp ? clp->cl_hostname : "unknown")
 		),
 
 		TP_fast_assign(
@@ -1148,9 +1144,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_callback_event,
 				__entry->fileid = 0;
 				__entry->dev = 0;
 			}
-			__assign_str(dstaddr, clp ?
-				rpc_peeraddr2str(clp->cl_rpcclient,
-					RPC_DISPLAY_ADDR) : "unknown")
+			__assign_str(dstaddr, clp ? clp->cl_hostname : "unknown")
 		),
 
 		TP_printk(
@@ -1192,9 +1186,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_stateid_callback_event,
 			__field(dev_t, dev)
 			__field(u32, fhandle)
 			__field(u64, fileid)
-			__string(dstaddr, clp ?
-				rpc_peeraddr2str(clp->cl_rpcclient,
-					RPC_DISPLAY_ADDR) : "unknown")
+			__string(dstaddr, clp ? clp->cl_hostname : "unknown")
 			__field(int, stateid_seq)
 			__field(u32, stateid_hash)
 		),
@@ -1209,9 +1201,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_stateid_callback_event,
 				__entry->fileid = 0;
 				__entry->dev = 0;
 			}
-			__assign_str(dstaddr, clp ?
-				rpc_peeraddr2str(clp->cl_rpcclient,
-					RPC_DISPLAY_ADDR) : "unknown")
+			__assign_str(dstaddr, clp ? clp->cl_hostname : "unknown")
 			__entry->stateid_seq =
 				be32_to_cpu(stateid->seqid);
 			__entry->stateid_hash =

fs/nfs/nfs4xdr.c

@@ -4385,6 +4385,14 @@ static int decode_delegation_stateid(struct xdr_stream *xdr, nfs4_stateid *state
 	return decode_stateid(xdr, stateid);
 }
 
+static int decode_invalid_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+{
+	nfs4_stateid dummy;
+
+	nfs4_stateid_copy(stateid, &invalid_stateid);
+	return decode_stateid(xdr, &dummy);
+}
+
 static int decode_close(struct xdr_stream *xdr, struct nfs_closeres *res)
 {
 	int status;
@@ -4393,7 +4401,7 @@ static int decode_close(struct xdr_stream *xdr, struct nfs_closeres *res)
 	if (status != -EIO)
 		nfs_increment_open_seqid(status, res->seqid);
 	if (!status)
-		status = decode_open_stateid(xdr, &res->stateid);
+		status = decode_invalid_stateid(xdr, &res->stateid);
 	return status;
 }
 
@@ -6108,6 +6116,8 @@ static int decode_layoutreturn(struct xdr_stream *xdr,
 	res->lrs_present = be32_to_cpup(p);
 	if (res->lrs_present)
 		status = decode_layout_stateid(xdr, &res->stateid);
+	else
+		nfs4_stateid_copy(&res->stateid, &invalid_stateid);
 	return status;
 out_overflow:
 	print_overflow_msg(__func__, xdr);