Merge tag 'nfs-for-7.0-1' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS client updates from Anna Schumaker:
 "New Features:
   - Use an LRU list for returning unused delegations
   - Introduce a KConfig option to disable NFS v4.0 and make NFS v4.1
     the default

  Bugfixes:
   - NFS/localio:
       - Handle short writes by retrying
       - Prevent direct reclaim recursion into NFS via nfs_writepages
       - Use GFP_NOIO and non-memreclaim workqueue in nfs_local_commit
       - Remove -EAGAIN handling in nfs_local_doio()
   - pNFS: fix a missing wake up while waiting on NFS_LAYOUT_DRAIN
   - fs/nfs: Fix a readdir slow-start regression
   - SUNRPC: fix gss_auth kref leak in gss_alloc_msg error path

  Other cleanups and improvements:
   - A few other NFS/localio cleanups
   - Various other delegation handling cleanups from Christoph
   - Unify security_inode_listsecurity() calls
   - Improvements to NFSv4 lease handling
   - Clean up SUNRPC *_debug fields when CONFIG_SUNRPC_DEBUG is not set"

* tag 'nfs-for-7.0-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (60 commits)
  SUNRPC: fix gss_auth kref leak in gss_alloc_msg error path
  nfs: nfs4proc: Convert comma to semicolon
  SUNRPC: Change list definition method
  sunrpc: rpc_debug and others are defined even if CONFIG_SUNRPC_DEBUG unset
  NFSv4: limit lease period in nfs4_set_lease_period()
  NFSv4: pass lease period in seconds to nfs4_set_lease_period()
  nfs: unify security_inode_listsecurity() calls
  fs/nfs: Fix readdir slow-start regression
  pNFS: fix a missing wake up while waiting on NFS_LAYOUT_DRAIN
  NFS: fix delayed delegation return handling
  NFS: simplify error handling in nfs_end_delegation_return
  NFS: fold nfs_abort_delegation_return into nfs_end_delegation_return
  NFS: remove the delegation == NULL check in nfs_end_delegation_return
  NFS: use bool for the issync argument to nfs_end_delegation_return
  NFS: return void from ->return_delegation
  NFS: return void from nfs4_inode_make_writeable
  NFS: Merge CONFIG_NFS_V4_1 with CONFIG_NFS_V4
  NFS: Add a way to disable NFS v4.0 via KConfig
  NFS: Move sequence slot operations into minorversion operations
  NFS: Pass a struct nfs_client to nfs4_init_sequence()
  ...

fs/nfs/Kconfig

@@ -78,9 +78,10 @@ config NFS_V4
 	tristate "NFS client support for NFS version 4"
 	depends on NFS_FS
 	select KEYS
+	select SUNRPC_BACKCHANNEL
 	help
-	  This option enables support for version 4 of the NFS protocol
-	  (RFC 3530) in the kernel's NFS client.
+	  This option enables support for version 4.1 of the NFS protocol
+	  (RFC 5661) in the kernel's NFS client.
 
 	  To mount NFS servers using NFSv4, you also need to install user
 	  space programs which can be found in the Linux nfs-utils package,
@@ -96,19 +97,18 @@ config NFS_SWAP
 	help
 	  This option enables swapon to work on files located on NFS mounts.
 
-config NFS_V4_1
-	bool "NFS client support for NFSv4.1"
+config NFS_V4_0
+	bool "NFS client support for NFSv4.0"
 	depends on NFS_V4
-	select SUNRPC_BACKCHANNEL
 	help
-	  This option enables support for minor version 1 of the NFSv4 protocol
-	  (RFC 5661) in the kernel's NFS client.
+	  This option enables support for minor version 0 of the NFSv4 protocol
+	  (RFC 3530) in the kernel's NFS client.
 
 	  If unsure, say N.
 
 config NFS_V4_2
 	bool "NFS client support for NFSv4.2"
-	depends on NFS_V4_1
+	depends on NFS_V4
 	help
 	  This option enables support for minor version 2 of the NFSv4 protocol
 	  in the kernel's NFS client.
@@ -117,22 +117,22 @@ config NFS_V4_2
 
 config PNFS_FILE_LAYOUT
 	tristate
-	depends on NFS_V4_1
+	depends on NFS_V4
 	default NFS_V4
 
 config PNFS_BLOCK
 	tristate
-	depends on NFS_V4_1 && BLK_DEV_DM
+	depends on NFS_V4 && BLK_DEV_DM
 	default NFS_V4
 
 config PNFS_FLEXFILE_LAYOUT
 	tristate
-	depends on NFS_V4_1
+	depends on NFS_V4
 	default NFS_V4
 
 config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN
 	string "NFSv4.1 Implementation ID Domain"
-	depends on NFS_V4_1
+	depends on NFS_V4
 	default "kernel.org"
 	help
 	  This option defines the domain portion of the implementation ID that
@@ -144,7 +144,7 @@ config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN
 
 config NFS_V4_1_MIGRATION
 	bool "NFSv4.1 client support for migration"
-	depends on NFS_V4_1
+	depends on NFS_V4
 	default n
 	help
 	  This option makes the NFS client advertise to NFSv4.1 servers that

fs/nfs/Makefile

@@ -27,10 +27,10 @@ CFLAGS_nfs4trace.o += -I$(src)
 nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o \
 	  delegation.o nfs4idmap.o callback.o callback_xdr.o callback_proc.o \
 	  nfs4namespace.o nfs4getroot.o nfs4client.o nfs4session.o \
-	  dns_resolve.o nfs4trace.o
+	  dns_resolve.o nfs4trace.o pnfs.o pnfs_dev.o pnfs_nfs.o
 nfsv4-$(CONFIG_NFS_USE_LEGACY_DNS) += cache_lib.o
 nfsv4-$(CONFIG_SYSCTL)	+= nfs4sysctl.o
-nfsv4-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o pnfs_nfs.o
+nfsv4-$(CONFIG_NFS_V4_0)	+= nfs40client.o nfs40proc.o
 nfsv4-$(CONFIG_NFS_V4_2)	+= nfs42proc.o nfs42xattr.o
 
 obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/

fs/nfs/callback.c

@@ -87,7 +87,6 @@ nfs4_callback_svc(void *vrqstp)
 	return 0;
 }
 
-#if defined(CONFIG_NFS_V4_1)
 static inline void nfs_callback_bc_serv(u32 minorversion, struct rpc_xprt *xprt,
 		struct svc_serv *serv)
 {
@@ -98,12 +97,6 @@ static inline void nfs_callback_bc_serv(u32 minorversion, struct rpc_xprt *xprt,
 		 */
 		xprt->bc_serv = serv;
 }
-#else
-static inline void nfs_callback_bc_serv(u32 minorversion, struct rpc_xprt *xprt,
-		struct svc_serv *serv)
-{
-}
-#endif /* CONFIG_NFS_V4_1 */
 
 static int nfs_callback_start_svc(int minorversion, struct rpc_xprt *xprt,
 				  struct svc_serv *serv)
@@ -157,7 +150,7 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv,
 	}
 
 	ret = 0;
-	if (!IS_ENABLED(CONFIG_NFS_V4_1) || minorversion == 0)
+	if (minorversion == 0)
 		ret = nfs4_callback_up_net(serv, net);
 	else if (xprt->ops->bc_setup)
 		set_bc_enabled(serv);
@@ -198,10 +191,6 @@ static struct svc_serv *nfs_callback_create_svc(int minorversion)
 			cb_info->users);
 
 	threadfn = nfs4_callback_svc;
-#if !defined(CONFIG_NFS_V4_1)
-	if (minorversion)
-		return ERR_PTR(-ENOTSUPP);
-#endif
 	serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE,
 			  threadfn);
 	if (!serv) {

fs/nfs/callback.h

@@ -65,8 +65,6 @@ struct cb_recallargs {
 	uint32_t truncate;
 };
 
-#if defined(CONFIG_NFS_V4_1)
-
 struct referring_call {
 	uint32_t			rc_sequenceid;
 	uint32_t			rc_slotid;
@@ -168,7 +166,6 @@ struct cb_notify_lock_args {
 
 extern __be32 nfs4_callback_notify_lock(void *argp, void *resp,
 					 struct cb_process_state *cps);
-#endif /* CONFIG_NFS_V4_1 */
 #ifdef CONFIG_NFS_V4_2
 struct cb_offloadargs {
 	struct nfs_fh		coa_fh;

fs/nfs/callback_proc.c

@@ -51,12 +51,18 @@ __be32 nfs4_callback_getattr(void *argp, void *resp,
 				-ntohl(res->status));
 		goto out;
 	}
-	rcu_read_lock();
+
 	delegation = nfs4_get_valid_delegation(inode);
-	if (delegation == NULL || (delegation->type & FMODE_WRITE) == 0)
+	if (!delegation)
 		goto out_iput;
-	res->size = i_size_read(inode);
+	if ((delegation->type & FMODE_WRITE) == 0) {
+		nfs_put_delegation(delegation);
+		goto out_iput;
+	}
 	res->change_attr = delegation->change_attr;
+	nfs_put_delegation(delegation);
+
+	res->size = i_size_read(inode);
 	if (nfs_have_writebacks(inode))
 		res->change_attr++;
 	res->atime = inode_get_atime(inode);
@@ -71,7 +77,6 @@ __be32 nfs4_callback_getattr(void *argp, void *resp,
 			  FATTR4_WORD2_TIME_DELEG_MODIFY) & args->bitmap[2];
 	res->status = 0;
 out_iput:
-	rcu_read_unlock();
 	trace_nfs4_cb_getattr(cps->clp, &args->fh, inode, -ntohl(res->status));
 	nfs_iput_and_deactive(inode);
 out:
@@ -121,8 +126,6 @@ out:
 	return res;
 }
 
-#if defined(CONFIG_NFS_V4_1)
-
 /*
  * Lookup a layout inode by stateid
  *
@@ -693,7 +696,6 @@ __be32 nfs4_callback_notify_lock(void *argp, void *resp,
 
 	return htonl(NFS4_OK);
 }
-#endif /* CONFIG_NFS_V4_1 */
 #ifdef CONFIG_NFS_V4_2
 static void nfs4_copy_cb_args(struct nfs4_copy_state *cp_state,
 				struct cb_offloadargs *args)

fs/nfs/callback_xdr.c

@@ -30,7 +30,6 @@
 					 (2 + 2 + 3 + 3 + 3 + 3 + 3) * 4)
 #define CB_OP_RECALL_RES_MAXSZ		(CB_OP_HDR_RES_MAXSZ)
 
-#if defined(CONFIG_NFS_V4_1)
 #define CB_OP_LAYOUTRECALL_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ)
 #define CB_OP_DEVICENOTIFY_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ)
 #define CB_OP_SEQUENCE_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ + \
@@ -39,7 +38,6 @@
 #define CB_OP_RECALLANY_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ)
 #define CB_OP_RECALLSLOT_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ)
 #define CB_OP_NOTIFY_LOCK_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ)
-#endif /* CONFIG_NFS_V4_1 */
 #ifdef CONFIG_NFS_V4_2
 #define CB_OP_OFFLOAD_RES_MAXSZ		(CB_OP_HDR_RES_MAXSZ)
 #endif /* CONFIG_NFS_V4_2 */
@@ -205,7 +203,6 @@ static __be32 decode_recall_args(struct svc_rqst *rqstp,
 	return decode_fh(xdr, &args->fh);
 }
 
-#if defined(CONFIG_NFS_V4_1)
 static __be32 decode_layout_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
 {
 	stateid->type = NFS4_LAYOUT_STATEID_TYPE;
@@ -521,7 +518,6 @@ static __be32 decode_notify_lock_args(struct svc_rqst *rqstp,
 	return decode_lockowner(xdr, args);
 }
 
-#endif /* CONFIG_NFS_V4_1 */
 #ifdef CONFIG_NFS_V4_2
 static __be32 decode_write_response(struct xdr_stream *xdr,
 					struct cb_offloadargs *args)
@@ -747,8 +743,6 @@ out:
 	return status;
 }
 
-#if defined(CONFIG_NFS_V4_1)
-
 static __be32 encode_sessionid(struct xdr_stream *xdr,
 				 const struct nfs4_sessionid *sid)
 {
@@ -846,19 +840,6 @@ static void nfs4_cb_free_slot(struct cb_process_state *cps)
 	}
 }
 
-#else /* CONFIG_NFS_V4_1 */
-
-static __be32
-preprocess_nfs41_op(int nop, unsigned int op_nr, struct callback_op **op)
-{
-	return htonl(NFS4ERR_MINOR_VERS_MISMATCH);
-}
-
-static void nfs4_cb_free_slot(struct cb_process_state *cps)
-{
-}
-#endif /* CONFIG_NFS_V4_1 */
-
 #ifdef CONFIG_NFS_V4_2
 static __be32
 preprocess_nfs42_op(int nop, unsigned int op_nr, struct callback_op **op)
@@ -1051,7 +1032,6 @@ static struct callback_op callback_ops[] = {
 		.decode_args = decode_recall_args,
 		.res_maxsize = CB_OP_RECALL_RES_MAXSZ,
 	},
-#if defined(CONFIG_NFS_V4_1)
 	[OP_CB_LAYOUTRECALL] = {
 		.process_op = nfs4_callback_layoutrecall,
 		.decode_args = decode_layoutrecall_args,
@@ -1083,7 +1063,6 @@ static struct callback_op callback_ops[] = {
 		.decode_args = decode_notify_lock_args,
 		.res_maxsize = CB_OP_NOTIFY_LOCK_RES_MAXSZ,
 	},
-#endif /* CONFIG_NFS_V4_1 */
 #ifdef CONFIG_NFS_V4_2
 	[OP_CB_OFFLOAD] = {
 		.process_op = nfs4_callback_offload,

fs/nfs/client.c

@@ -1060,6 +1060,10 @@ struct nfs_server *nfs_alloc_server(void)
 	INIT_LIST_HEAD(&server->client_link);
 	INIT_LIST_HEAD(&server->master_link);
 	INIT_LIST_HEAD(&server->delegations);
+	spin_lock_init(&server->delegations_lock);
+	INIT_LIST_HEAD(&server->delegations_return);
+	INIT_LIST_HEAD(&server->delegations_lru);
+	INIT_LIST_HEAD(&server->delegations_delayed);
 	INIT_LIST_HEAD(&server->layouts);
 	INIT_LIST_HEAD(&server->state_owners_lru);
 	INIT_LIST_HEAD(&server->ss_copies);
@@ -1263,11 +1267,9 @@ void nfs_clients_init(struct net *net)
 	INIT_LIST_HEAD(&nn->nfs_volume_list);
 #if IS_ENABLED(CONFIG_NFS_V4)
 	idr_init(&nn->cb_ident_idr);
-#endif
-#if IS_ENABLED(CONFIG_NFS_V4_1)
 	INIT_LIST_HEAD(&nn->nfs4_data_server_cache);
 	spin_lock_init(&nn->nfs4_data_server_lock);
-#endif
+#endif /* CONFIG_NFS_V4 */
 	spin_lock_init(&nn->nfs_client_lock);
 	nn->boot_time = ktime_get_real();
 	memset(&nn->rpcstats, 0, sizeof(nn->rpcstats));
@@ -1284,9 +1286,9 @@ void nfs_clients_exit(struct net *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));
-#if IS_ENABLED(CONFIG_NFS_V4_1)
+#if IS_ENABLED(CONFIG_NFS_V4)
 	WARN_ON_ONCE(!list_empty(&nn->nfs4_data_server_cache));
-#endif
+#endif /* CONFIG_NFS_V4 */
 }
 
 #ifdef CONFIG_PROC_FS

fs/nfs/delegation.h

@@ -26,19 +26,17 @@ struct nfs_delegation {
 	unsigned long flags;
 	refcount_t refcount;
 	spinlock_t lock;
+	struct list_head entry;
 	struct rcu_head rcu;
 };
 
 enum {
 	NFS_DELEGATION_NEED_RECLAIM = 0,
-	NFS_DELEGATION_RETURN,
 	NFS_DELEGATION_RETURN_IF_CLOSED,
 	NFS_DELEGATION_REFERENCED,
 	NFS_DELEGATION_RETURNING,
 	NFS_DELEGATION_REVOKED,
 	NFS_DELEGATION_TEST_EXPIRED,
-	NFS_DELEGATION_INODE_FREEING,
-	NFS_DELEGATION_RETURN_DELAYED,
 	NFS_DELEGATION_DELEGTIME,
 };
 
@@ -48,7 +46,7 @@ int nfs_inode_set_delegation(struct inode *inode, const struct cred *cred,
 void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred,
 				  fmode_t type, const nfs4_stateid *stateid,
 				  unsigned long pagemod_limit, u32 deleg_type);
-int nfs4_inode_return_delegation(struct inode *inode);
+void nfs4_inode_return_delegation(struct inode *inode);
 void nfs4_inode_return_delegation_on_close(struct inode *inode);
 void nfs4_inode_set_return_delegation_on_close(struct inode *inode);
 int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid);
@@ -81,13 +79,14 @@ bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags, nfs4_state
 bool nfs4_refresh_delegation_stateid(nfs4_stateid *dst, struct inode *inode);
 
 struct nfs_delegation *nfs4_get_valid_delegation(const struct inode *inode);
+void nfs_put_delegation(struct nfs_delegation *delegation);
 void nfs_mark_delegation_referenced(struct nfs_delegation *delegation);
 int nfs4_have_delegation(struct inode *inode, fmode_t type, int flags);
 int nfs4_check_delegation(struct inode *inode, fmode_t type);
 bool nfs4_delegation_flush_on_close(const struct inode *inode);
 void nfs_inode_find_delegation_state_and_recover(struct inode *inode,
 		const nfs4_stateid *stateid);
-int nfs4_inode_make_writeable(struct inode *inode);
+void nfs4_inode_make_writeable(struct inode *inode);
 
 #endif
 

fs/nfs/dir.c

@@ -72,7 +72,7 @@ const struct address_space_operations nfs_dir_aops = {
 	.free_folio = nfs_readdir_clear_array,
 };
 
-#define NFS_INIT_DTSIZE PAGE_SIZE
+#define NFS_INIT_DTSIZE SZ_64K
 
 static struct nfs_open_dir_context *
 alloc_nfs_open_dir_context(struct inode *dir)
@@ -83,7 +83,7 @@ alloc_nfs_open_dir_context(struct inode *dir)
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL_ACCOUNT);
 	if (ctx != NULL) {
 		ctx->attr_gencount = nfsi->attr_gencount;
-		ctx->dtsize = NFS_INIT_DTSIZE;
+		ctx->dtsize = min(NFS_SERVER(dir)->dtsize, NFS_INIT_DTSIZE);
 		spin_lock(&dir->i_lock);
 		if (list_empty(&nfsi->open_files) &&
 		    (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER))

fs/nfs/fs_context.c

@@ -806,7 +806,8 @@ static int nfs_fs_context_parse_param(struct fs_context *fc,
 		ctx->mount_server.version = result.uint_32;
 		break;
 	case Opt_minorversion:
-		if (result.uint_32 > NFS4_MAX_MINOR_VERSION)
+		if (result.uint_32 < NFS4_MIN_MINOR_VERSION ||
+		    result.uint_32 > NFS4_MAX_MINOR_VERSION)
 			goto out_of_bounds;
 		ctx->minorversion = result.uint_32;
 		break;

fs/nfs/internal.h

@@ -334,17 +334,13 @@ extern int nfs3_decode_dirent(struct xdr_stream *,
 #if IS_ENABLED(CONFIG_NFS_V4)
 extern int nfs4_decode_dirent(struct xdr_stream *,
 				struct nfs_entry *, bool);
-#endif
-#ifdef CONFIG_NFS_V4_1
 extern const u32 nfs41_maxread_overhead;
 extern const u32 nfs41_maxwrite_overhead;
 extern const u32 nfs41_maxgetdevinfo_overhead;
-#endif
 
 /* nfs4proc.c */
-#if IS_ENABLED(CONFIG_NFS_V4)
 extern const struct rpc_procinfo nfs4_procedures[];
-#endif
+#endif /* CONFIG_NFS_V4 */
 
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
 extern struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags);
@@ -639,7 +635,7 @@ void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio);
 int nfs_filemap_write_and_wait_range(struct address_space *mapping,
 		loff_t lstart, loff_t lend);
 
-#ifdef CONFIG_NFS_V4_1
+#ifdef CONFIG_NFS_V4
 static inline void
 pnfs_bucket_clear_pnfs_ds_commit_verifiers(struct pnfs_commit_bucket *buckets,
 		unsigned int nbuckets)
@@ -660,12 +656,12 @@ void nfs_clear_pnfs_ds_commit_verifiers(struct pnfs_ds_commit_info *cinfo)
 				array->nbuckets);
 	rcu_read_unlock();
 }
-#else
+#else /* CONFIG_NFS_V4 */
 static inline
 void nfs_clear_pnfs_ds_commit_verifiers(struct pnfs_ds_commit_info *cinfo)
 {
 }
-#endif
+#endif /* CONFIG_NFS_V4 */
 
 #ifdef CONFIG_MIGRATION
 int nfs_migrate_folio(struct address_space *, struct folio *dst,
@@ -739,9 +735,6 @@ extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq, loff_t offset);
 /* nfs4proc.c */
 extern struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 			    const struct nfs_client_initdata *);
-extern int nfs40_walk_client_list(struct nfs_client *clp,
-				struct nfs_client **result,
-				const struct cred *cred);
 extern int nfs41_walk_client_list(struct nfs_client *clp,
 				struct nfs_client **result,
 				const struct cred *cred);

fs/nfs/localio.c

@@ -58,6 +58,11 @@ struct nfs_local_fsync_ctx {
 static bool localio_enabled __read_mostly = true;
 module_param(localio_enabled, bool, 0644);
 
+static void nfs_local_do_read(struct nfs_local_kiocb *iocb,
+			      const struct rpc_call_ops *call_ops);
+static void nfs_local_do_write(struct nfs_local_kiocb *iocb,
+			       const struct rpc_call_ops *call_ops);
+
 static inline bool nfs_client_is_local(const struct nfs_client *clp)
 {
 	return !!rcu_access_pointer(clp->cl_uuid.net);
@@ -286,6 +291,18 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
 }
 EXPORT_SYMBOL_GPL(nfs_local_open_fh);
 
+/*
+ * Ensure all page cache allocations are done from GFP_NOFS context to
+ * prevent direct reclaim recursion back into NFS via nfs_writepages.
+ */
+static void
+nfs_local_mapping_set_gfp_nofs_context(struct address_space *m)
+{
+	gfp_t gfp_mask = mapping_gfp_mask(m);
+
+	mapping_set_gfp_mask(m, (gfp_mask & ~(__GFP_FS)));
+}
+
 static void
 nfs_local_iocb_free(struct nfs_local_kiocb *iocb)
 {
@@ -310,6 +327,7 @@ nfs_local_iocb_alloc(struct nfs_pgio_header *hdr,
 		return NULL;
 	}
 
+	nfs_local_mapping_set_gfp_nofs_context(file->f_mapping);
 	init_sync_kiocb(&iocb->kiocb, file);
 
 	iocb->hdr = hdr;
@@ -512,8 +530,7 @@ nfs_local_pgio_init(struct nfs_pgio_header *hdr,
 		hdr->task.tk_start = ktime_get();
 }
 
-static bool
-nfs_local_pgio_done(struct nfs_local_kiocb *iocb, long status, bool force)
+static bool nfs_local_pgio_done(struct nfs_local_kiocb *iocb, long status)
 {
 	struct nfs_pgio_header *hdr = iocb->hdr;
 
@@ -528,9 +545,6 @@ nfs_local_pgio_done(struct nfs_local_kiocb *iocb, long status, bool force)
 		hdr->task.tk_status = status;
 	}
 
-	if (force)
-		return true;
-
 	BUG_ON(atomic_read(&iocb->n_iters) <= 0);
 	return atomic_dec_and_test(&iocb->n_iters);
 }
@@ -542,13 +556,50 @@ nfs_local_iocb_release(struct nfs_local_kiocb *iocb)
 	nfs_local_iocb_free(iocb);
 }
 
-static void
-nfs_local_pgio_release(struct nfs_local_kiocb *iocb)
+static void nfs_local_pgio_restart(struct nfs_local_kiocb *iocb,
+				   struct nfs_pgio_header *hdr)
+{
+	int status = 0;
+
+	iocb->kiocb.ki_pos = hdr->args.offset;
+	iocb->kiocb.ki_flags &= ~(IOCB_DSYNC | IOCB_SYNC | IOCB_DIRECT);
+	iocb->kiocb.ki_complete = NULL;
+	iocb->aio_complete_work = NULL;
+	iocb->end_iter_index = -1;
+
+	switch (hdr->rw_mode) {
+	case FMODE_READ:
+		nfs_local_iters_init(iocb, ITER_DEST);
+		nfs_local_do_read(iocb, hdr->task.tk_ops);
+		break;
+	case FMODE_WRITE:
+		nfs_local_iters_init(iocb, ITER_SOURCE);
+		nfs_local_do_write(iocb, hdr->task.tk_ops);
+		break;
+	default:
+		status = -EOPNOTSUPP;
+	}
+
+	if (unlikely(status != 0)) {
+		nfs_local_iocb_release(iocb);
+		hdr->task.tk_status = status;
+		nfs_local_hdr_release(hdr, hdr->task.tk_ops);
+	}
+}
+
+static void nfs_local_pgio_release(struct nfs_local_kiocb *iocb)
 {
 	struct nfs_pgio_header *hdr = iocb->hdr;
+	struct rpc_task *task = &hdr->task;
 
-	nfs_local_iocb_release(iocb);
-	nfs_local_hdr_release(hdr, hdr->task.tk_ops);
+	task->tk_action = NULL;
+	task->tk_ops->rpc_call_done(task, hdr);
+
+	if (task->tk_action == NULL) {
+		nfs_local_iocb_release(iocb);
+		task->tk_ops->rpc_release(hdr);
+	} else
+		nfs_local_pgio_restart(iocb, hdr);
 }
 
 /*
@@ -609,7 +660,7 @@ static void nfs_local_read_aio_complete(struct kiocb *kiocb, long ret)
 		container_of(kiocb, struct nfs_local_kiocb, kiocb);
 
 	/* AIO completion of DIO read should always be last to complete */
-	if (unlikely(!nfs_local_pgio_done(iocb, ret, false)))
+	if (unlikely(!nfs_local_pgio_done(iocb, ret)))
 		return;
 
 	nfs_local_pgio_aio_complete(iocb); /* Calls nfs_local_read_aio_complete_work */
@@ -641,7 +692,7 @@ static void nfs_local_call_read(struct work_struct *work)
 		if (status == -EIOCBQUEUED)
 			continue;
 		/* Break on completion, errors, or short reads */
-		if (nfs_local_pgio_done(iocb, status, false) || status < 0 ||
+		if (nfs_local_pgio_done(iocb, status) || status < 0 ||
 		    (size_t)status < iov_iter_count(&iocb->iters[i])) {
 			nfs_local_read_iocb_done(iocb);
 			break;
@@ -649,9 +700,8 @@ static void nfs_local_call_read(struct work_struct *work)
 	}
 }
 
-static int
-nfs_local_do_read(struct nfs_local_kiocb *iocb,
-		  const struct rpc_call_ops *call_ops)
+static void nfs_local_do_read(struct nfs_local_kiocb *iocb,
+			      const struct rpc_call_ops *call_ops)
 {
 	struct nfs_pgio_header *hdr = iocb->hdr;
 
@@ -663,8 +713,6 @@ nfs_local_do_read(struct nfs_local_kiocb *iocb,
 
 	INIT_WORK(&iocb->work, nfs_local_call_read);
 	queue_work(nfslocaliod_workqueue, &iocb->work);
-
-	return 0;
 }
 
 static void
@@ -773,19 +821,7 @@ static void nfs_local_write_done(struct nfs_local_kiocb *iocb)
 		pr_info_ratelimited("nfs: Unexpected direct I/O write alignment failure\n");
 	}
 
-	/* Handle short writes as if they are ENOSPC */
-	status = hdr->res.count;
-	if (status > 0 && status < hdr->args.count) {
-		hdr->mds_offset += status;
-		hdr->args.offset += status;
-		hdr->args.pgbase += status;
-		hdr->args.count -= status;
-		nfs_set_pgio_error(hdr, -ENOSPC, hdr->args.offset);
-		status = -ENOSPC;
-		/* record -ENOSPC in terms of nfs_local_pgio_done */
-		(void) nfs_local_pgio_done(iocb, status, true);
-	}
-	if (hdr->task.tk_status < 0)
+	if (status < 0)
 		nfs_reset_boot_verifier(hdr->inode);
 }
 
@@ -810,7 +846,7 @@ static void nfs_local_write_aio_complete(struct kiocb *kiocb, long ret)
 		container_of(kiocb, struct nfs_local_kiocb, kiocb);
 
 	/* AIO completion of DIO write should always be last to complete */
-	if (unlikely(!nfs_local_pgio_done(iocb, ret, false)))
+	if (unlikely(!nfs_local_pgio_done(iocb, ret)))
 		return;
 
 	nfs_local_pgio_aio_complete(iocb); /* Calls nfs_local_write_aio_complete_work */
@@ -846,7 +882,7 @@ static void nfs_local_call_write(struct work_struct *work)
 		if (status == -EIOCBQUEUED)
 			continue;
 		/* Break on completion, errors, or short writes */
-		if (nfs_local_pgio_done(iocb, status, false) || status < 0 ||
+		if (nfs_local_pgio_done(iocb, status) || status < 0 ||
 		    (size_t)status < iov_iter_count(&iocb->iters[i])) {
 			nfs_local_write_iocb_done(iocb);
 			break;
@@ -857,9 +893,8 @@ static void nfs_local_call_write(struct work_struct *work)
 	current->flags = old_flags;
 }
 
-static int
-nfs_local_do_write(struct nfs_local_kiocb *iocb,
-		   const struct rpc_call_ops *call_ops)
+static void nfs_local_do_write(struct nfs_local_kiocb *iocb,
+			       const struct rpc_call_ops *call_ops)
 {
 	struct nfs_pgio_header *hdr = iocb->hdr;
 
@@ -883,8 +918,6 @@ nfs_local_do_write(struct nfs_local_kiocb *iocb,
 
 	INIT_WORK(&iocb->work, nfs_local_call_write);
 	queue_work(nfslocaliod_workqueue, &iocb->work);
-
-	return 0;
 }
 
 static struct nfs_local_kiocb *
@@ -934,10 +967,10 @@ int nfs_local_doio(struct nfs_client *clp, struct nfsd_file *localio,
 
 	switch (hdr->rw_mode) {
 	case FMODE_READ:
-		status = nfs_local_do_read(iocb, call_ops);
+		nfs_local_do_read(iocb, call_ops);
 		break;
 	case FMODE_WRITE:
-		status = nfs_local_do_write(iocb, call_ops);
+		nfs_local_do_write(iocb, call_ops);
 		break;
 	default:
 		dprintk("%s: invalid mode: %d\n", __func__,
@@ -945,9 +978,7 @@ int nfs_local_doio(struct nfs_client *clp, struct nfsd_file *localio,
 		status = -EOPNOTSUPP;
 	}
 
-	if (status != 0) {
-		if (status == -EAGAIN)
-			nfs_localio_disable_client(clp);
+	if (unlikely(status != 0)) {
 		nfs_local_iocb_release(iocb);
 		hdr->task.tk_status = status;
 		nfs_local_hdr_release(hdr, call_ops);
@@ -974,6 +1005,8 @@ nfs_local_run_commit(struct file *filp, struct nfs_commit_data *data)
 			end = LLONG_MAX;
 	}
 
+	nfs_local_mapping_set_gfp_nofs_context(filp->f_mapping);
+
 	dprintk("%s: commit %llu - %llu\n", __func__, start, end);
 	return vfs_fsync_range(filp, start, end, 0);
 }
@@ -1015,17 +1048,22 @@ nfs_local_fsync_ctx_free(struct nfs_local_fsync_ctx *ctx)
 static void
 nfs_local_fsync_work(struct work_struct *work)
 {
+	unsigned long old_flags = current->flags;
 	struct nfs_local_fsync_ctx *ctx;
 	int status;
 
 	ctx = container_of(work, struct nfs_local_fsync_ctx, work);
 
+	current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO;
+
 	status = nfs_local_run_commit(nfs_to->nfsd_file_file(ctx->localio),
 				      ctx->data);
 	nfs_local_commit_done(ctx->data, status);
 	if (ctx->done != NULL)
 		complete(ctx->done);
 	nfs_local_fsync_ctx_free(ctx);
+
+	current->flags = old_flags;
 }
 
 static struct nfs_local_fsync_ctx *
@@ -1049,7 +1087,7 @@ int nfs_local_commit(struct nfsd_file *localio,
 {
 	struct nfs_local_fsync_ctx *ctx;
 
-	ctx = nfs_local_fsync_ctx_alloc(data, localio, GFP_KERNEL);
+	ctx = nfs_local_fsync_ctx_alloc(data, localio, GFP_NOIO);
 	if (!ctx) {
 		nfs_local_commit_done(data, -ENOMEM);
 		nfs_local_release_commit_data(localio, data, call_ops);
@@ -1061,10 +1099,10 @@ int nfs_local_commit(struct nfsd_file *localio,
 	if (how & FLUSH_SYNC) {
 		DECLARE_COMPLETION_ONSTACK(done);
 		ctx->done = &done;
-		queue_work(nfsiod_workqueue, &ctx->work);
+		queue_work(nfslocaliod_workqueue, &ctx->work);
 		wait_for_completion(&done);
 	} else
-		queue_work(nfsiod_workqueue, &ctx->work);
+		queue_work(nfslocaliod_workqueue, &ctx->work);
 
 	return 0;
 }

fs/nfs/netns.h

@@ -31,11 +31,9 @@ struct nfs_net {
 	unsigned short nfs_callback_tcpport;
 	unsigned short nfs_callback_tcpport6;
 	int cb_users[NFS4_MAX_MINOR_VERSION + 1];
-#endif /* CONFIG_NFS_V4 */
-#if IS_ENABLED(CONFIG_NFS_V4_1)
 	struct list_head nfs4_data_server_cache;
 	spinlock_t nfs4_data_server_lock;
-#endif /* CONFIG_NFS_V4_1 */
+#endif /* CONFIG_NFS_V4 */
 	struct nfs_netns_client *nfs_client;
 	spinlock_t nfs_client_lock;
 	ktime_t boot_time;

fs/nfs/nfs3proc.c

@@ -1027,11 +1027,10 @@ static int nfs3_have_delegation(struct inode *inode, fmode_t type, int flags)
 	return 0;
 }
 
-static int nfs3_return_delegation(struct inode *inode)
+static void nfs3_return_delegation(struct inode *inode)
 {
 	if (S_ISREG(inode->i_mode))
 		nfs_wb_all(inode);
-	return 0;
 }
 
 static const struct inode_operations nfs3_dir_inode_operations = {

fs/nfs/nfs40.h

@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_FS_NFS_NFS4_0_H
+#define __LINUX_FS_NFS_NFS4_0_H
+
+
+/* nfs40client.c */
+void nfs40_shutdown_client(struct nfs_client *);
+int nfs40_init_client(struct nfs_client *);
+void nfs40_handle_cb_pathdown(struct nfs_client *clp);
+
+/* nfs40proc.c */
+extern const struct nfs4_minor_version_ops nfs_v4_0_minor_ops;
+
+/* nfs40state.c */
+int nfs40_discover_server_trunking(struct nfs_client *clp,
+				   struct nfs_client **result,
+				   const struct cred *cred);
+
+#endif /* __LINUX_FS_NFS_NFS4_0_H */

fs/nfs/nfs40client.c

@@ -0,0 +1,245 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/nfs_fs.h>
+#include "nfs4_fs.h"
+#include "nfs4session.h"
+#include "callback.h"
+#include "delegation.h"
+#include "internal.h"
+#include "netns.h"
+#include "nfs40.h"
+
+#define NFSDBG_FACILITY		NFSDBG_CLIENT
+
+/*
+ * SETCLIENTID just did a callback update with the callback ident in
+ * "drop," but server trunking discovery claims "drop" and "keep" are
+ * actually the same server.  Swap the callback IDs so that "keep"
+ * will continue to use the callback ident the server now knows about,
+ * and so that "keep"'s original callback ident is destroyed when
+ * "drop" is freed.
+ */
+static void nfs4_swap_callback_idents(struct nfs_client *keep,
+				      struct nfs_client *drop)
+{
+	struct nfs_net *nn = net_generic(keep->cl_net, nfs_net_id);
+	unsigned int save = keep->cl_cb_ident;
+
+	if (keep->cl_cb_ident == drop->cl_cb_ident)
+		return;
+
+	dprintk("%s: keeping callback ident %u and dropping ident %u\n",
+		__func__, keep->cl_cb_ident, drop->cl_cb_ident);
+
+	spin_lock(&nn->nfs_client_lock);
+
+	idr_replace(&nn->cb_ident_idr, keep, drop->cl_cb_ident);
+	keep->cl_cb_ident = drop->cl_cb_ident;
+
+	idr_replace(&nn->cb_ident_idr, drop, save);
+	drop->cl_cb_ident = save;
+
+	spin_unlock(&nn->nfs_client_lock);
+}
+
+static bool nfs4_same_verifier(nfs4_verifier *v1, nfs4_verifier *v2)
+{
+	return memcmp(v1->data, v2->data, sizeof(v1->data)) == 0;
+}
+
+void nfs40_shutdown_client(struct nfs_client *clp)
+{
+	if (clp->cl_slot_tbl) {
+		nfs4_shutdown_slot_table(clp->cl_slot_tbl);
+		kfree(clp->cl_slot_tbl);
+	}
+}
+
+/**
+ * nfs40_init_client - nfs_client initialization tasks for NFSv4.0
+ * @clp: nfs_client to initialize
+ *
+ * Returns zero on success, or a negative errno if some error occurred.
+ */
+int nfs40_init_client(struct nfs_client *clp)
+{
+	struct nfs4_slot_table *tbl;
+	int ret;
+
+	tbl = kzalloc(sizeof(*tbl), GFP_NOFS);
+	if (tbl == NULL)
+		return -ENOMEM;
+
+	ret = nfs4_setup_slot_table(tbl, NFS4_MAX_SLOT_TABLE,
+					"NFSv4.0 transport Slot table");
+	if (ret) {
+		nfs4_shutdown_slot_table(tbl);
+		kfree(tbl);
+		return ret;
+	}
+
+	clp->cl_slot_tbl = tbl;
+	return 0;
+}
+
+/*
+ * nfs40_handle_cb_pathdown - return all delegations after NFS4ERR_CB_PATH_DOWN
+ * @clp: client to process
+ *
+ * Set the NFS4CLNT_LEASE_EXPIRED state in order to force a
+ * resend of the SETCLIENTID and hence re-establish the
+ * callback channel. Then return all existing delegations.
+ */
+void nfs40_handle_cb_pathdown(struct nfs_client *clp)
+{
+	set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+	nfs_expire_all_delegations(clp);
+	dprintk("%s: handling CB_PATHDOWN recovery for server %s\n", __func__,
+			clp->cl_hostname);
+}
+
+void nfs4_schedule_path_down_recovery(struct nfs_client *clp)
+{
+	nfs40_handle_cb_pathdown(clp);
+	nfs4_schedule_state_manager(clp);
+}
+
+/**
+ * nfs40_walk_client_list - Find server that recognizes a client ID
+ *
+ * @new: nfs_client with client ID to test
+ * @result: OUT: found nfs_client, or new
+ * @cred: credential to use for trunking test
+ *
+ * Returns zero, a negative errno, or a negative NFS4ERR status.
+ * If zero is returned, an nfs_client pointer is planted in "result."
+ *
+ * NB: nfs40_walk_client_list() relies on the new nfs_client being
+ *     the last nfs_client on the list.
+ */
+static int nfs40_walk_client_list(struct nfs_client *new,
+				  struct nfs_client **result,
+				  const struct cred *cred)
+{
+	struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id);
+	struct nfs_client *pos, *prev = NULL;
+	struct nfs4_setclientid_res clid = {
+		.clientid	= new->cl_clientid,
+		.confirm	= new->cl_confirm,
+	};
+	int status = -NFS4ERR_STALE_CLIENTID;
+
+	spin_lock(&nn->nfs_client_lock);
+	list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) {
+
+		if (pos == new)
+			goto found;
+
+		status = nfs4_match_client(pos, new, &prev, nn);
+		if (status < 0)
+			goto out_unlock;
+		if (status != 0)
+			continue;
+		/*
+		 * We just sent a new SETCLIENTID, which should have
+		 * caused the server to return a new cl_confirm.  So if
+		 * cl_confirm is the same, then this is a different
+		 * server that just returned the same cl_confirm by
+		 * coincidence:
+		 */
+		if ((new != pos) && nfs4_same_verifier(&pos->cl_confirm,
+						       &new->cl_confirm))
+			continue;
+		/*
+		 * But if the cl_confirm's are different, then the only
+		 * way that a SETCLIENTID_CONFIRM to pos can succeed is
+		 * if new and pos point to the same server:
+		 */
+found:
+		refcount_inc(&pos->cl_count);
+		spin_unlock(&nn->nfs_client_lock);
+
+		nfs_put_client(prev);
+		prev = pos;
+
+		status = nfs4_proc_setclientid_confirm(pos, &clid, cred);
+		switch (status) {
+		case -NFS4ERR_STALE_CLIENTID:
+			break;
+		case 0:
+			nfs4_swap_callback_idents(pos, new);
+			pos->cl_confirm = new->cl_confirm;
+			nfs_mark_client_ready(pos, NFS_CS_READY);
+
+			prev = NULL;
+			*result = pos;
+			goto out;
+		case -ERESTARTSYS:
+		case -ETIMEDOUT:
+			/* The callback path may have been inadvertently
+			 * changed. Schedule recovery!
+			 */
+			nfs4_schedule_path_down_recovery(pos);
+			goto out;
+		default:
+			goto out;
+		}
+
+		spin_lock(&nn->nfs_client_lock);
+	}
+out_unlock:
+	spin_unlock(&nn->nfs_client_lock);
+
+	/* No match found. The server lost our clientid */
+out:
+	nfs_put_client(prev);
+	return status;
+}
+
+/**
+ * nfs40_discover_server_trunking - Detect server IP address trunking (mv0)
+ *
+ * @clp: nfs_client under test
+ * @result: OUT: found nfs_client, or clp
+ * @cred: credential to use for trunking test
+ *
+ * Returns zero, a negative errno, or a negative NFS4ERR status.
+ * If zero is returned, an nfs_client pointer is planted in
+ * "result".
+ *
+ * Note: The returned client may not yet be marked ready.
+ */
+int nfs40_discover_server_trunking(struct nfs_client *clp,
+				   struct nfs_client **result,
+				   const struct cred *cred)
+{
+	struct nfs4_setclientid_res clid = {
+		.clientid = clp->cl_clientid,
+		.confirm = clp->cl_confirm,
+	};
+	struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
+	unsigned short port;
+	int status;
+
+	port = nn->nfs_callback_tcpport;
+	if (clp->cl_addr.ss_family == AF_INET6)
+		port = nn->nfs_callback_tcpport6;
+
+	status = nfs4_proc_setclientid(clp, NFS4_CALLBACK, port, cred, &clid);
+	if (status != 0)
+		goto out;
+	clp->cl_clientid = clid.clientid;
+	clp->cl_confirm = clid.confirm;
+
+	status = nfs40_walk_client_list(clp, result, cred);
+	if (status == 0) {
+		/* Sustain the lease, even if it's empty.  If the clientid4
+		 * goes stale it's of no use for trunking discovery. */
+		nfs4_schedule_state_renewal(*result);
+
+		/* If the client state need to recover, do it. */
+		if (clp->cl_state)
+			nfs4_schedule_state_manager(clp);
+	}
+out:
+	return status;
+}

fs/nfs/nfs40proc.c

@@ -0,0 +1,395 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/nfs4.h>
+#include <linux/nfs.h>
+#include <linux/sunrpc/sched.h>
+#include <linux/nfs_fs.h>
+#include "internal.h"
+#include "nfs4_fs.h"
+#include "nfs40.h"
+#include "nfs4session.h"
+#include "nfs4trace.h"
+
+static void nfs40_call_sync_prepare(struct rpc_task *task, void *calldata)
+{
+	struct nfs4_call_sync_data *data = calldata;
+	nfs4_setup_sequence(data->seq_server->nfs_client,
+				data->seq_args, data->seq_res, task);
+}
+
+static void nfs40_call_sync_done(struct rpc_task *task, void *calldata)
+{
+	struct nfs4_call_sync_data *data = calldata;
+	nfs4_sequence_done(task, data->seq_res);
+}
+
+static void nfs40_sequence_free_slot(struct nfs4_sequence_res *res)
+{
+	struct nfs4_slot *slot = res->sr_slot;
+	struct nfs4_slot_table *tbl;
+
+	tbl = slot->table;
+	spin_lock(&tbl->slot_tbl_lock);
+	if (!nfs41_wake_and_assign_slot(tbl, slot))
+		nfs4_free_slot(tbl, slot);
+	spin_unlock(&tbl->slot_tbl_lock);
+
+	res->sr_slot = NULL;
+}
+
+static int nfs40_sequence_done(struct rpc_task *task,
+			       struct nfs4_sequence_res *res)
+{
+	if (res->sr_slot != NULL)
+		nfs40_sequence_free_slot(res);
+	return 1;
+}
+
+static void nfs40_clear_delegation_stateid(struct nfs4_state *state)
+{
+	if (rcu_access_pointer(NFS_I(state->inode)->delegation) != NULL)
+		nfs_finish_clear_delegation_stateid(state, NULL);
+}
+
+static int nfs40_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
+{
+	/* NFSv4.0 doesn't allow for delegation recovery on open expire */
+	nfs40_clear_delegation_stateid(state);
+	nfs_state_clear_open_state_flags(state);
+	return nfs4_open_expired(sp, state);
+}
+
+struct nfs4_renewdata {
+	struct nfs_client	*client;
+	unsigned long		timestamp;
+};
+
+/*
+ * nfs4_proc_async_renew(): This is not one of the nfs_rpc_ops; it is a special
+ * standalone procedure for queueing an asynchronous RENEW.
+ */
+static void nfs4_renew_release(void *calldata)
+{
+	struct nfs4_renewdata *data = calldata;
+	struct nfs_client *clp = data->client;
+
+	if (refcount_read(&clp->cl_count) > 1)
+		nfs4_schedule_state_renewal(clp);
+	nfs_put_client(clp);
+	kfree(data);
+}
+
+static void nfs4_renew_done(struct rpc_task *task, void *calldata)
+{
+	struct nfs4_renewdata *data = calldata;
+	struct nfs_client *clp = data->client;
+	unsigned long timestamp = data->timestamp;
+
+	trace_nfs4_renew_async(clp, task->tk_status);
+	switch (task->tk_status) {
+	case 0:
+		break;
+	case -NFS4ERR_LEASE_MOVED:
+		nfs4_schedule_lease_moved_recovery(clp);
+		break;
+	default:
+		/* Unless we're shutting down, schedule state recovery! */
+		if (test_bit(NFS_CS_RENEWD, &clp->cl_res_state) == 0)
+			return;
+		if (task->tk_status != NFS4ERR_CB_PATH_DOWN) {
+			nfs4_schedule_lease_recovery(clp);
+			return;
+		}
+		nfs4_schedule_path_down_recovery(clp);
+	}
+	do_renew_lease(clp, timestamp);
+}
+
+static const struct rpc_call_ops nfs4_renew_ops = {
+	.rpc_call_done = nfs4_renew_done,
+	.rpc_release = nfs4_renew_release,
+};
+
+static int nfs4_proc_async_renew(struct nfs_client *clp, const struct cred *cred, unsigned renew_flags)
+{
+	struct rpc_message msg = {
+		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_RENEW],
+		.rpc_argp	= clp,
+		.rpc_cred	= cred,
+	};
+	struct nfs4_renewdata *data;
+
+	if (renew_flags == 0)
+		return 0;
+	if (!refcount_inc_not_zero(&clp->cl_count))
+		return -EIO;
+	data = kmalloc(sizeof(*data), GFP_NOFS);
+	if (data == NULL) {
+		nfs_put_client(clp);
+		return -ENOMEM;
+	}
+	data->client = clp;
+	data->timestamp = jiffies;
+	return rpc_call_async(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT,
+			&nfs4_renew_ops, data);
+}
+
+static int nfs4_proc_renew(struct nfs_client *clp, const struct cred *cred)
+{
+	struct rpc_message msg = {
+		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_RENEW],
+		.rpc_argp	= clp,
+		.rpc_cred	= cred,
+	};
+	unsigned long now = jiffies;
+	int status;
+
+	status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
+	if (status < 0)
+		return status;
+	do_renew_lease(clp, now);
+	return 0;
+}
+
+static int nfs40_test_and_free_expired_stateid(struct nfs_server *server,
+					       nfs4_stateid *stateid,
+					       const struct cred *cred)
+{
+	return -NFS4ERR_BAD_STATEID;
+}
+
+/*
+ * This operation also signals the server that this client is
+ * performing migration recovery.  The server can stop returning
+ * NFS4ERR_LEASE_MOVED to this client.  A RENEW operation is
+ * appended to this compound to identify the client ID which is
+ * performing recovery.
+ */
+static int _nfs40_proc_get_locations(struct nfs_server *server,
+				     struct nfs_fh *fhandle,
+				     struct nfs4_fs_locations *locations,
+				     struct page *page, const struct cred *cred)
+{
+	struct rpc_clnt *clnt = server->client;
+	struct nfs_client *clp = server->nfs_client;
+	u32 bitmask[2] = {
+		[0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS,
+	};
+	struct nfs4_fs_locations_arg args = {
+		.clientid	= clp->cl_clientid,
+		.fh		= fhandle,
+		.page		= page,
+		.bitmask	= bitmask,
+		.migration	= 1,		/* skip LOOKUP */
+		.renew		= 1,		/* append RENEW */
+	};
+	struct nfs4_fs_locations_res res = {
+		.fs_locations	= locations,
+		.migration	= 1,
+		.renew		= 1,
+	};
+	struct rpc_message msg = {
+		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_FS_LOCATIONS],
+		.rpc_argp	= &args,
+		.rpc_resp	= &res,
+		.rpc_cred	= cred,
+	};
+	unsigned long now = jiffies;
+	int status;
+
+	nfs_fattr_init(locations->fattr);
+	locations->server = server;
+	locations->nlocations = 0;
+
+	nfs4_init_sequence(clp, &args.seq_args, &res.seq_res, 0, 1);
+	status = nfs4_call_sync_sequence(clnt, server, &msg,
+					&args.seq_args, &res.seq_res);
+	if (status)
+		return status;
+
+	renew_lease(server, now);
+	return 0;
+}
+
+/*
+ * This operation also signals the server that this client is
+ * performing "lease moved" recovery.  The server can stop
+ * returning NFS4ERR_LEASE_MOVED to this client.  A RENEW operation
+ * is appended to this compound to identify the client ID which is
+ * performing recovery.
+ */
+static int _nfs40_proc_fsid_present(struct inode *inode, const struct cred *cred)
+{
+	struct nfs_server *server = NFS_SERVER(inode);
+	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
+	struct rpc_clnt *clnt = server->client;
+	struct nfs4_fsid_present_arg args = {
+		.fh		= NFS_FH(inode),
+		.clientid	= clp->cl_clientid,
+		.renew		= 1,		/* append RENEW */
+	};
+	struct nfs4_fsid_present_res res = {
+		.renew		= 1,
+	};
+	struct rpc_message msg = {
+		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_FSID_PRESENT],
+		.rpc_argp	= &args,
+		.rpc_resp	= &res,
+		.rpc_cred	= cred,
+	};
+	unsigned long now = jiffies;
+	int status;
+
+	res.fh = nfs_alloc_fhandle();
+	if (res.fh == NULL)
+		return -ENOMEM;
+
+	nfs4_init_sequence(clp, &args.seq_args, &res.seq_res, 0, 1);
+	status = nfs4_call_sync_sequence(clnt, server, &msg,
+						&args.seq_args, &res.seq_res);
+	nfs_free_fhandle(res.fh);
+	if (status)
+		return status;
+
+	do_renew_lease(clp, now);
+	return 0;
+}
+
+struct nfs_release_lockowner_data {
+	struct nfs4_lock_state *lsp;
+	struct nfs_server *server;
+	struct nfs_release_lockowner_args args;
+	struct nfs_release_lockowner_res res;
+	unsigned long timestamp;
+};
+
+static void nfs4_release_lockowner_prepare(struct rpc_task *task, void *calldata)
+{
+	struct nfs_release_lockowner_data *data = calldata;
+	struct nfs_server *server = data->server;
+	nfs4_setup_sequence(server->nfs_client, &data->args.seq_args,
+			   &data->res.seq_res, task);
+	data->args.lock_owner.clientid = server->nfs_client->cl_clientid;
+	data->timestamp = jiffies;
+}
+
+static void nfs4_release_lockowner_done(struct rpc_task *task, void *calldata)
+{
+	struct nfs_release_lockowner_data *data = calldata;
+	struct nfs_server *server = data->server;
+
+	nfs40_sequence_done(task, &data->res.seq_res);
+
+	switch (task->tk_status) {
+	case 0:
+		renew_lease(server, data->timestamp);
+		break;
+	case -NFS4ERR_STALE_CLIENTID:
+	case -NFS4ERR_EXPIRED:
+		nfs4_schedule_lease_recovery(server->nfs_client);
+		break;
+	case -NFS4ERR_LEASE_MOVED:
+	case -NFS4ERR_DELAY:
+		if (nfs4_async_handle_error(task, server,
+					    NULL, NULL) == -EAGAIN)
+			rpc_restart_call_prepare(task);
+	}
+}
+
+static void nfs4_release_lockowner_release(void *calldata)
+{
+	struct nfs_release_lockowner_data *data = calldata;
+	nfs4_free_lock_state(data->server, data->lsp);
+	kfree(calldata);
+}
+
+static const struct rpc_call_ops nfs4_release_lockowner_ops = {
+	.rpc_call_prepare = nfs4_release_lockowner_prepare,
+	.rpc_call_done = nfs4_release_lockowner_done,
+	.rpc_release = nfs4_release_lockowner_release,
+};
+
+static void
+nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_state *lsp)
+{
+	struct nfs_release_lockowner_data *data;
+	struct nfs_client *clp = server->nfs_client;
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RELEASE_LOCKOWNER],
+	};
+
+	if (clp->cl_mvops->minor_version != 0)
+		return;
+
+	data = kmalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return;
+	data->lsp = lsp;
+	data->server = server;
+	data->args.lock_owner.clientid = clp->cl_clientid;
+	data->args.lock_owner.id = lsp->ls_seqid.owner_id;
+	data->args.lock_owner.s_dev = server->s_dev;
+
+	msg.rpc_argp = &data->args;
+	msg.rpc_resp = &data->res;
+	nfs4_init_sequence(clp, &data->args.seq_args, &data->res.seq_res, 0, 0);
+	rpc_call_async(server->client, &msg, 0, &nfs4_release_lockowner_ops, data);
+}
+
+static const struct rpc_call_ops nfs40_call_sync_ops = {
+	.rpc_call_prepare = nfs40_call_sync_prepare,
+	.rpc_call_done = nfs40_call_sync_done,
+};
+
+static const struct nfs4_sequence_slot_ops nfs40_sequence_slot_ops = {
+	.process = nfs40_sequence_done,
+	.done = nfs40_sequence_done,
+	.free_slot = nfs40_sequence_free_slot,
+};
+
+static const struct nfs4_state_recovery_ops nfs40_reboot_recovery_ops = {
+	.owner_flag_bit = NFS_OWNER_RECLAIM_REBOOT,
+	.state_flag_bit	= NFS_STATE_RECLAIM_REBOOT,
+	.recover_open	= nfs4_open_reclaim,
+	.recover_lock	= nfs4_lock_reclaim,
+	.establish_clid = nfs4_init_clientid,
+	.detect_trunking = nfs40_discover_server_trunking,
+};
+
+static const struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = {
+	.owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE,
+	.state_flag_bit	= NFS_STATE_RECLAIM_NOGRACE,
+	.recover_open	= nfs40_open_expired,
+	.recover_lock	= nfs4_lock_expired,
+	.establish_clid = nfs4_init_clientid,
+};
+
+static const struct nfs4_state_maintenance_ops nfs40_state_renewal_ops = {
+	.sched_state_renewal = nfs4_proc_async_renew,
+	.get_state_renewal_cred = nfs4_get_renew_cred,
+	.renew_lease = nfs4_proc_renew,
+};
+
+static const struct nfs4_mig_recovery_ops nfs40_mig_recovery_ops = {
+	.get_locations = _nfs40_proc_get_locations,
+	.fsid_present = _nfs40_proc_fsid_present,
+};
+
+const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = {
+	.minor_version = 0,
+	.init_caps = NFS_CAP_READDIRPLUS
+		| NFS_CAP_ATOMIC_OPEN
+		| NFS_CAP_POSIX_LOCK,
+	.init_client = nfs40_init_client,
+	.shutdown_client = nfs40_shutdown_client,
+	.match_stateid = nfs4_match_stateid,
+	.find_root_sec = nfs4_find_root_sec,
+	.free_lock_state = nfs4_release_lockowner,
+	.test_and_free_expired = nfs40_test_and_free_expired_stateid,
+	.alloc_seqid = nfs_alloc_seqid,
+	.call_sync_ops = &nfs40_call_sync_ops,
+	.sequence_slot_ops = &nfs40_sequence_slot_ops,
+	.reboot_recovery_ops = &nfs40_reboot_recovery_ops,
+	.nograce_recovery_ops = &nfs40_nograce_recovery_ops,
+	.state_renewal_ops = &nfs40_state_renewal_ops,
+	.mig_recovery_ops = &nfs40_mig_recovery_ops,
+};

fs/nfs/nfs42proc.c

@@ -670,8 +670,8 @@ static int nfs42_do_offload_cancel_async(struct file *dst,
 	msg.rpc_argp = &data->args;
 	msg.rpc_resp = &data->res;
 	task_setup_data.callback_data = data;
-	nfs4_init_sequence(&data->args.osa_seq_args, &data->res.osr_seq_res,
-			   1, 0);
+	nfs4_init_sequence(dst_server->nfs_client, &data->args.osa_seq_args,
+			   &data->res.osr_seq_res, 1, 0);
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
 		return PTR_ERR(task);
@@ -1072,7 +1072,8 @@ int nfs42_proc_layoutstats_generic(struct nfs_server *server,
 		nfs42_layoutstat_release(data);
 		return -EAGAIN;
 	}
-	nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0, 0);
+	nfs4_init_sequence(server->nfs_client, &data->args.seq_args,
+			   &data->res.seq_res, 0, 0);
 	task = rpc_run_task(&task_setup);
 	if (IS_ERR(task))
 		return PTR_ERR(task);
@@ -1210,6 +1211,7 @@ int nfs42_proc_layouterror(struct pnfs_layout_segment *lseg,
 		const struct nfs42_layout_error *errors, size_t n)
 {
 	struct inode *inode = lseg->pls_layout->plh_inode;
+	struct nfs_server *server = NFS_SERVER(inode);
 	struct nfs42_layouterror_data *data;
 	struct rpc_task *task;
 	struct rpc_message msg = {
@@ -1237,8 +1239,9 @@ int nfs42_proc_layouterror(struct pnfs_layout_segment *lseg,
 	msg.rpc_argp = &data->args;
 	msg.rpc_resp = &data->res;
 	task_setup.callback_data = data;
-	task_setup.rpc_client = NFS_SERVER(inode)->client;
-	nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0, 0);
+	task_setup.rpc_client = server->client;
+	nfs4_init_sequence(server->nfs_client, &data->args.seq_args,
+			   &data->res.seq_res, 0, 0);
 	task = rpc_run_task(&task_setup);
 	if (IS_ERR(task))
 		return PTR_ERR(task);

fs/nfs/nfs4_fs.h

@@ -10,12 +10,16 @@
 #ifndef __LINUX_FS_NFS_NFS4_FS_H
 #define __LINUX_FS_NFS_NFS4_FS_H
 
+#if defined(CONFIG_NFS_V4_0)
+#define NFS4_MIN_MINOR_VERSION 0
+#else
+#define NFS4_MIN_MINOR_VERSION 1
+#endif
+
 #if defined(CONFIG_NFS_V4_2)
 #define NFS4_MAX_MINOR_VERSION 2
-#elif defined(CONFIG_NFS_V4_1)
-#define NFS4_MAX_MINOR_VERSION 1
 #else
-#define NFS4_MAX_MINOR_VERSION 0
+#define NFS4_MAX_MINOR_VERSION 1
 #endif
 
 #if IS_ENABLED(CONFIG_NFS_V4)
@@ -73,6 +77,7 @@ struct nfs4_minor_version_ops {
 	void	(*session_trunk)(struct rpc_clnt *clnt,
 			struct rpc_xprt *xprt, void *data);
 	const struct rpc_call_ops *call_sync_ops;
+	const struct nfs4_sequence_slot_ops *sequence_slot_ops;
 	const struct nfs4_state_recovery_ops *reboot_recovery_ops;
 	const struct nfs4_state_recovery_ops *nograce_recovery_ops;
 	const struct nfs4_state_maintenance_ops *state_renewal_ops;
@@ -256,6 +261,12 @@ struct nfs4_add_xprt_data {
 	const struct cred	*cred;
 };
 
+struct nfs4_sequence_slot_ops {
+	int (*process)(struct rpc_task *, struct nfs4_sequence_res *);
+	int (*done)(struct rpc_task *, struct nfs4_sequence_res *);
+	void (*free_slot)(struct nfs4_sequence_res *);
+};
+
 struct nfs4_state_maintenance_ops {
 	int (*sched_state_renewal)(struct nfs_client *, const struct cred *, unsigned);
 	const struct cred * (*get_state_renewal_cred)(struct nfs_client *);
@@ -277,6 +288,11 @@ int nfs_atomic_open(struct inode *, struct dentry *, struct file *,
 /* fs_context.c */
 extern struct file_system_type nfs4_fs_type;
 
+/* nfs4client.c */
+struct nfs_net;
+int nfs4_match_client(struct nfs_client *pos, struct nfs_client *new,
+		      struct nfs_client **prev, struct nfs_net *nn);
+
 /* nfs4namespace.c */
 struct rpc_clnt *nfs4_negotiate_security(struct rpc_clnt *, struct inode *,
 					 const struct qstr *);
@@ -286,6 +302,12 @@ int nfs4_replace_transport(struct nfs_server *server,
 size_t nfs_parse_server_name(char *string, size_t len, struct sockaddr_storage *ss,
 			     size_t salen, struct net *net, int port);
 /* nfs4proc.c */
+struct nfs4_call_sync_data {
+	const struct nfs_server *seq_server;
+	struct nfs4_sequence_args *seq_args;
+	struct nfs4_sequence_res *seq_res;
+};
+
 extern int nfs4_handle_exception(struct nfs_server *, int, struct nfs4_exception *);
 extern int nfs4_async_handle_error(struct rpc_task *task,
 				   struct nfs_server *server,
@@ -293,9 +315,16 @@ extern int nfs4_async_handle_error(struct rpc_task *task,
 extern int nfs4_call_sync(struct rpc_clnt *, struct nfs_server *,
 			  struct rpc_message *, struct nfs4_sequence_args *,
 			  struct nfs4_sequence_res *, int);
-extern void nfs4_init_sequence(struct nfs4_sequence_args *, struct nfs4_sequence_res *, int, int);
+extern int nfs4_call_sync_sequence(struct rpc_clnt *clnt,
+				   struct nfs_server *server,
+				   struct rpc_message *msg,
+				   struct nfs4_sequence_args *args,
+				   struct nfs4_sequence_res *res);
+extern void nfs4_init_sequence(struct nfs_client *clp, struct nfs4_sequence_args *,
+			       struct nfs4_sequence_res *, int, int);
 extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, const struct cred *, struct nfs4_setclientid_res *);
 extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, const struct cred *);
+extern void renew_lease(const struct nfs_server *server, unsigned long timestamp);
 extern int nfs4_proc_get_rootfh(struct nfs_server *, struct nfs_fh *,
 				struct nfs_fattr *, bool);
 extern int nfs4_proc_bind_conn_to_session(struct nfs_client *, const struct cred *cred);
@@ -339,8 +368,19 @@ extern void nfs4_update_changeattr(struct inode *dir,
 				   unsigned long cache_validity);
 extern int nfs4_buf_to_pages_noslab(const void *buf, size_t buflen,
 				    struct page **pages);
+extern int nfs4_open_reclaim(struct nfs4_state_owner *, struct nfs4_state *);
+extern int nfs4_open_expired(struct nfs4_state_owner *, struct nfs4_state *);
+extern int nfs4_lock_reclaim(struct nfs4_state *state, struct file_lock *request);
+extern int nfs4_lock_expired(struct nfs4_state *state, struct file_lock *request);
+extern void nfs_state_clear_delegation(struct nfs4_state *state);
+extern void nfs_finish_clear_delegation_stateid(struct nfs4_state *state,
+						const nfs4_stateid *stateid);
+extern void nfs_state_clear_open_state_flags(struct nfs4_state *state);
+extern void do_renew_lease(struct nfs_client *clp, unsigned long timestamp);
+extern bool nfs4_match_stateid(const nfs4_stateid *s1, const nfs4_stateid *s2);
+extern int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
+			      struct nfs_fattr *fattr);
 
-#if defined(CONFIG_NFS_V4_1)
 extern int nfs41_sequence_done(struct rpc_task *, struct nfs4_sequence_res *);
 extern int nfs4_proc_create_session(struct nfs_client *, const struct cred *);
 extern int nfs4_proc_destroy_session(struct nfs4_session *, const struct cred *);
@@ -418,31 +458,6 @@ nfs4_state_protect_write(struct nfs_client *clp, struct rpc_clnt **clntp,
 	    !test_bit(NFS_SP4_MACH_CRED_COMMIT, &clp->cl_sp4_flags))
 		hdr->args.stable = NFS_FILE_SYNC;
 }
-#else /* CONFIG_NFS_v4_1 */
-static inline bool
-is_ds_only_client(struct nfs_client *clp)
-{
-	return false;
-}
-
-static inline bool
-is_ds_client(struct nfs_client *clp)
-{
-	return false;
-}
-
-static inline void
-nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_flags,
-		   struct rpc_clnt **clntp, struct rpc_message *msg)
-{
-}
-
-static inline void
-nfs4_state_protect_write(struct nfs_client *clp, struct rpc_clnt **clntp,
-			 struct rpc_message *msg, struct nfs_pgio_header *hdr)
-{
-}
-#endif /* CONFIG_NFS_V4_1 */
 
 extern const struct nfs4_minor_version_ops *nfs_v4_minor_ops[];
 
@@ -452,9 +467,7 @@ extern const u32 nfs4_pathconf_bitmap[3];
 extern const u32 nfs4_fsinfo_bitmap[3];
 extern const u32 nfs4_fs_locations_bitmap[3];
 
-void nfs40_shutdown_client(struct nfs_client *);
 void nfs41_shutdown_client(struct nfs_client *);
-int nfs40_init_client(struct nfs_client *);
 int nfs41_init_client(struct nfs_client *);
 void nfs4_free_client(struct nfs_client *);
 
@@ -464,8 +477,7 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *);
 extern void nfs4_schedule_state_renewal(struct nfs_client *);
 extern void nfs4_kill_renewd(struct nfs_client *);
 extern void nfs4_renew_state(struct work_struct *);
-extern void nfs4_set_lease_period(struct nfs_client *clp, unsigned long lease);
-
+extern void nfs4_set_lease_period(struct nfs_client *clp, u32 period);
 
 /* nfs4state.c */
 extern const nfs4_stateid current_stateid;
@@ -477,18 +489,12 @@ int nfs4_discover_server_trunking(struct nfs_client *clp,
 			struct nfs_client **);
 int nfs40_discover_server_trunking(struct nfs_client *clp,
 			struct nfs_client **, const struct cred *);
-#if defined(CONFIG_NFS_V4_1)
 int nfs41_discover_server_trunking(struct nfs_client *clp,
 			struct nfs_client **, const struct cred *);
 extern void nfs4_schedule_session_recovery(struct nfs4_session *, int);
 extern void nfs41_notify_server(struct nfs_client *);
 bool nfs4_check_serverowner_major_id(struct nfs41_server_owner *o1,
 			struct nfs41_server_owner *o2);
-#else
-static inline void nfs4_schedule_session_recovery(struct nfs4_session *session, int err)
-{
-}
-#endif /* CONFIG_NFS_V4_1 */
 
 extern struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *, const struct cred *, gfp_t);
 extern void nfs4_put_state_owner(struct nfs4_state_owner *);