Merge tag 'nfs-for-6.12-1' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS client updates from Anna Schumaker:
 "New Features:
   - Add a 'noalignwrite' mount option for lock-less 'lost writes' prevention
   - Add support for the LOCALIO protocol extention

  Bugfixes:
   - Fix memory leak in error path of nfs4_do_reclaim()
   - Simplify and guarantee lock owner uniqueness
   - Fix -Wformat-truncation warning
   - Fix folio refcounts by using folio_attach_private()
   - Fix failing the mount system call when the server is down
   - Fix detection of "Proxying of Times" server support

  Cleanups:
   - Annotate struct nfs_cache_array with __counted_by()
   - Remove unnecessary NULL checks before kfree()
   - Convert RPC_TASK_* constants to an enum
   - Remove obsolete or misleading comments and declerations"

* tag 'nfs-for-6.12-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (41 commits)
  nfs: Fix `make htmldocs` warnings in the localio documentation
  nfs: add "NFS Client and Server Interlock" section to localio.rst
  nfs: add FAQ section to Documentation/filesystems/nfs/localio.rst
  nfs: add Documentation/filesystems/nfs/localio.rst
  nfs: implement client support for NFS_LOCALIO_PROGRAM
  nfs/localio: use dedicated workqueues for filesystem read and write
  pnfs/flexfiles: enable localio support
  nfs: enable localio for non-pNFS IO
  nfs: add LOCALIO support
  nfs: pass struct nfsd_file to nfs_init_pgio and nfs_init_commit
  nfsd: implement server support for NFS_LOCALIO_PROGRAM
  nfsd: add LOCALIO support
  nfs_common: prepare for the NFS client to use nfsd_file for LOCALIO
  nfs_common: add NFS LOCALIO auxiliary protocol enablement
  SUNRPC: replace program list with program array
  SUNRPC: add svcauth_map_clnt_to_svc_cred_local
  SUNRPC: remove call_allocate() BUG_ONs
  nfsd: add nfsd_serv_try_get and nfsd_serv_put
  nfsd: add nfsd_file_acquire_local()
  nfsd: factor out __fh_verify to allow NULL rqstp to be passed
  ...

24 files changed, 1073 insertions, 312 deletions

diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 57249f040dfc..0eb20012792f 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -4,6 +4,7 @@ config NFS_FS
 	depends on INET && FILE_LOCKING && MULTIUSER
 	select LOCKD
 	select SUNRPC
+	select NFS_COMMON
 	select NFS_ACL_SUPPORT if NFS_V3_ACL
 	help
 	  Choose Y here if you want to access files residing on other
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 5f6db37f461e..9fb2f2cac87e 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -13,6 +13,7 @@ nfs-y 			:= client.o dir.o file.o getroot.o inode.o super.o \
 nfs-$(CONFIG_ROOT_NFS)	+= nfsroot.o
 nfs-$(CONFIG_SYSCTL)	+= sysctl.o
 nfs-$(CONFIG_NFS_FSCACHE) += fscache.o
+nfs-$(CONFIG_NFS_LOCALIO) += localio.o
 
 obj-$(CONFIG_NFS_V2) += nfsv2.o
 nfsv2-y := nfs2super.o proc.o nfs2xdr.o
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 8286edd6062d..a1d21c4be0ac 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -178,6 +178,14 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
 	clp->cl_max_connect = cl_init->max_connect ? cl_init->max_connect : 1;
 	clp->cl_net = get_net(cl_init->net);
 
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+	seqlock_init(&clp->cl_boot_lock);
+	ktime_get_real_ts64(&clp->cl_nfssvc_boot);
+	clp->cl_uuid.net = NULL;
+	clp->cl_uuid.dom = NULL;
+	spin_lock_init(&clp->cl_localio_lock);
+#endif /* CONFIG_NFS_LOCALIO */
+
 	clp->cl_principal = "*";
 	clp->cl_xprtsec = cl_init->xprtsec;
 	return clp;
@@ -233,6 +241,8 @@ static void pnfs_init_server(struct nfs_server *server)
  */
 void nfs_free_client(struct nfs_client *clp)
 {
+	nfs_local_disable(clp);
+
 	/* -EIO all pending I/O */
 	if (!IS_ERR(clp->cl_rpcclient))
 		rpc_shutdown_client(clp->cl_rpcclient);
@@ -424,7 +434,10 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init)
 			list_add_tail(&new->cl_share_link,
 					&nn->nfs_client_list);
 			spin_unlock(&nn->nfs_client_lock);
-			return rpc_ops->init_client(new, cl_init);
+			new = rpc_ops->init_client(new, cl_init);
+			if (!IS_ERR(new))
+				 nfs_local_probe(new);
+			return new;
 		}
 
 		spin_unlock(&nn->nfs_client_lock);
@@ -997,8 +1010,8 @@ struct nfs_server *nfs_alloc_server(void)
 	init_waitqueue_head(&server->write_congestion_wait);
 	atomic_long_set(&server->writeback, 0);
 
-	ida_init(&server->openowner_id);
-	ida_init(&server->lockowner_id);
+	atomic64_set(&server->owner_ctr, 0);
+
 	pnfs_init_server(server);
 	rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC");
 
@@ -1037,8 +1050,6 @@ void nfs_free_server(struct nfs_server *server)
 	}
 	ida_free(&s_sysfs_ids, server->s_sysfs_id);
 
-	ida_destroy(&server->lockowner_id);
-	ida_destroy(&server->openowner_id);
 	put_cred(server->cred);
 	nfs_release_automount_timer();
 	call_rcu(&server->rcu, delayed_free);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 4cb97ef41350..492cffd9d3d8 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -151,7 +151,7 @@ struct nfs_cache_array {
 	unsigned char folio_full : 1,
 		      folio_is_eof : 1,
 		      cookies_are_ordered : 1;
-	struct nfs_cache_array_entry array[];
+	struct nfs_cache_array_entry array[] __counted_by(size);
 };
 
 struct nfs_readdir_descriptor {
@@ -328,7 +328,8 @@ static int nfs_readdir_folio_array_append(struct folio *folio,
 		goto out;
 	}
 
-	cache_entry = &array->array[array->size];
+	array->size++;
+	cache_entry = &array->array[array->size - 1];
 	cache_entry->cookie = array->last_cookie;
 	cache_entry->ino = entry->ino;
 	cache_entry->d_type = entry->d_type;
@@ -337,7 +338,6 @@ static int nfs_readdir_folio_array_append(struct folio *folio,
 	array->last_cookie = entry->cookie;
 	if (array->last_cookie <= cache_entry->cookie)
 		array->cookies_are_ordered = 0;
-	array->size++;
 	if (entry->eof != 0)
 		nfs_readdir_array_set_eof(array);
 out:
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index b6e9aeaf4ce2..d39a1f58e18d 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -488,7 +488,7 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr)
 	/* Perform an asynchronous read to ds */
 	nfs_initiate_pgio(ds_clnt, hdr, hdr->cred,
 			  NFS_PROTO(hdr->inode), &filelayout_read_call_ops,
-			  0, RPC_TASK_SOFTCONN);
+			  0, RPC_TASK_SOFTCONN, NULL);
 	return PNFS_ATTEMPTED;
 }
 
@@ -530,7 +530,7 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	/* Perform an asynchronous write */
 	nfs_initiate_pgio(ds_clnt, hdr, hdr->cred,
 			  NFS_PROTO(hdr->inode), &filelayout_write_call_ops,
-			  sync, RPC_TASK_SOFTCONN);
+			  sync, RPC_TASK_SOFTCONN, NULL);
 	return PNFS_ATTEMPTED;
 }
 
@@ -1011,7 +1011,7 @@ static int filelayout_initiate_commit(struct nfs_commit_data *data, int how)
 		data->args.fh = fh;
 	return nfs_initiate_commit(ds_clnt, data, NFS_PROTO(data->inode),
 				   &filelayout_commit_call_ops, how,
-				   RPC_TASK_SOFTCONN);
+				   RPC_TASK_SOFTCONN, NULL);
 out_err:
 	pnfs_generic_prepare_to_resend_writes(data);
 	pnfs_generic_commit_release(data);
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 39ba9f4208aa..f78115c6c2c1 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -11,6 +11,7 @@
 #include <linux/nfs_mount.h>
 #include <linux/nfs_page.h>
 #include <linux/module.h>
+#include <linux/file.h>
 #include <linux/sched/mm.h>
 
 #include <linux/sunrpc/metrics.h>
@@ -162,6 +163,21 @@ decode_name(struct xdr_stream *xdr, u32 *id)
 	return 0;
 }
 
+static struct nfsd_file *
+ff_local_open_fh(struct nfs_client *clp, const struct cred *cred,
+		 struct nfs_fh *fh, fmode_t mode)
+{
+	if (mode & FMODE_WRITE) {
+		/*
+		 * Always request read and write access since this corresponds
+		 * to a rw layout.
+		 */
+		mode |= FMODE_READ;
+	}
+
+	return nfs_local_open_fh(clp, cred, fh, mode);
+}
+
 static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1,
 		const struct nfs4_ff_layout_mirror *m2)
 {
@@ -237,7 +253,7 @@ static struct nfs4_ff_layout_mirror *ff_layout_alloc_mirror(gfp_t gfp_flags)
 
 static void ff_layout_free_mirror(struct nfs4_ff_layout_mirror *mirror)
 {
-	const struct cred	*cred;
+	const struct cred *cred;
 
 	ff_layout_remove_mirror(mirror);
 	kfree(mirror->fh_versions);
@@ -1756,6 +1772,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 	struct pnfs_layout_segment *lseg = hdr->lseg;
 	struct nfs4_pnfs_ds *ds;
 	struct rpc_clnt *ds_clnt;
+	struct nfsd_file *localio;
 	struct nfs4_ff_layout_mirror *mirror;
 	const struct cred *ds_cred;
 	loff_t offset = hdr->args.offset;
@@ -1802,11 +1819,18 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 	hdr->args.offset = offset;
 	hdr->mds_offset = offset;
 
+	/* Start IO accounting for local read */
+	localio = ff_local_open_fh(ds->ds_clp, ds_cred, fh, FMODE_READ);
+	if (localio) {
+		hdr->task.tk_start = ktime_get();
+		ff_layout_read_record_layoutstats_start(&hdr->task, hdr);
+	}
+
 	/* Perform an asynchronous read to ds */
 	nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops,
 			  vers == 3 ? &ff_layout_read_call_ops_v3 :
 				      &ff_layout_read_call_ops_v4,
-			  0, RPC_TASK_SOFTCONN);
+			  0, RPC_TASK_SOFTCONN, localio);
 	put_cred(ds_cred);
 	return PNFS_ATTEMPTED;
 
@@ -1826,6 +1850,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	struct pnfs_layout_segment *lseg = hdr->lseg;
 	struct nfs4_pnfs_ds *ds;
 	struct rpc_clnt *ds_clnt;
+	struct nfsd_file *localio;
 	struct nfs4_ff_layout_mirror *mirror;
 	const struct cred *ds_cred;
 	loff_t offset = hdr->args.offset;
@@ -1870,11 +1895,19 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	 */
 	hdr->args.offset = offset;
 
+	/* Start IO accounting for local write */
+	localio = ff_local_open_fh(ds->ds_clp, ds_cred, fh,
+				   FMODE_READ|FMODE_WRITE);
+	if (localio) {
+		hdr->task.tk_start = ktime_get();
+		ff_layout_write_record_layoutstats_start(&hdr->task, hdr);
+	}
+
 	/* Perform an asynchronous write */
 	nfs_initiate_pgio(ds_clnt, hdr, ds_cred, ds->ds_clp->rpc_ops,
 			  vers == 3 ? &ff_layout_write_call_ops_v3 :
 				      &ff_layout_write_call_ops_v4,
-			  sync, RPC_TASK_SOFTCONN);
+			  sync, RPC_TASK_SOFTCONN, localio);
 	put_cred(ds_cred);
 	return PNFS_ATTEMPTED;
 
@@ -1908,6 +1941,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
 	struct pnfs_layout_segment *lseg = data->lseg;
 	struct nfs4_pnfs_ds *ds;
 	struct rpc_clnt *ds_clnt;
+	struct nfsd_file *localio;
 	struct nfs4_ff_layout_mirror *mirror;
 	const struct cred *ds_cred;
 	u32 idx;
@@ -1946,10 +1980,18 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
 	if (fh)
 		data->args.fh = fh;
 
+	/* Start IO accounting for local commit */
+	localio = ff_local_open_fh(ds->ds_clp, ds_cred, fh,
+				   FMODE_READ|FMODE_WRITE);
+	if (localio) {
+		data->task.tk_start = ktime_get();
+		ff_layout_commit_record_layoutstats_start(&data->task, data);
+	}
+
 	ret = nfs_initiate_commit(ds_clnt, data, ds->ds_clp->rpc_ops,
 				   vers == 3 ? &ff_layout_commit_call_ops_v3 :
 					       &ff_layout_commit_call_ops_v4,
-				   how, RPC_TASK_SOFTCONN);
+				   how, RPC_TASK_SOFTCONN, localio);
 	put_cred(ds_cred);
 	return ret;
 out_err:
@@ -2087,12 +2129,6 @@ static int ff_layout_encode_ioerr(struct xdr_stream *xdr,
 }
 
 static void
-encode_opaque_fixed(struct xdr_stream *xdr, const void *buf, size_t len)
-{
-	WARN_ON_ONCE(xdr_stream_encode_opaque_fixed(xdr, buf, len) < 0);
-}
-
-static void
 ff_layout_encode_ff_iostat_head(struct xdr_stream *xdr,
 			    const nfs4_stateid *stateid,
 			    const struct nfs42_layoutstat_devinfo *devinfo)
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index e028f5a0ef5f..e58bedfb1dcc 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -395,6 +395,12 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg,
 
 	/* connect success, check rsize/wsize limit */
 	if (!status) {
+		/*
+		 * ds_clp is put in destroy_ds().
+		 * keep ds_clp even if DS is local, so that if local IO cannot
+		 * proceed somehow, we can fall back to NFS whenever we want.
+		 */
+		nfs_local_probe(ds->ds_clp);
 		max_payload =
 			nfs_block_size(rpc_max_payload(ds->ds_clp->cl_rpcclient),
 				       NULL);
diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c
index 6c9f3f6645dd..7e000d782e28 100644
--- a/fs/nfs/fs_context.c
+++ b/fs/nfs/fs_context.c
@@ -49,6 +49,7 @@ enum nfs_param {
 	Opt_bsize,
 	Opt_clientaddr,
 	Opt_cto,
+	Opt_alignwrite,
 	Opt_fg,
 	Opt_fscache,
 	Opt_fscache_flag,
@@ -149,6 +150,7 @@ static const struct fs_parameter_spec nfs_fs_parameters[] = {
 	fsparam_u32   ("bsize",		Opt_bsize),
 	fsparam_string("clientaddr",	Opt_clientaddr),
 	fsparam_flag_no("cto",		Opt_cto),
+	fsparam_flag_no("alignwrite",	Opt_alignwrite),
 	fsparam_flag  ("fg",		Opt_fg),
 	fsparam_flag_no("fsc",		Opt_fscache_flag),
 	fsparam_string("fsc",		Opt_fscache),
@@ -592,6 +594,12 @@ static int nfs_fs_context_parse_param(struct fs_context *fc,
 		else
 			ctx->flags |= NFS_MOUNT_TRUNK_DISCOVERY;
 		break;
+	case Opt_alignwrite:
+		if (result.negated)
+			ctx->flags |= NFS_MOUNT_NO_ALIGNWRITE;
+		else
+			ctx->flags &= ~NFS_MOUNT_NO_ALIGNWRITE;
+		break;
 	case Opt_ac:
 		if (result.negated)
 			ctx->flags |= NFS_MOUNT_NOAC;
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index 11ff2b2e060f..f13d25d95b85 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -62,7 +62,7 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i
 }
 
 /*
- * get an NFS2/NFS3 root dentry from the root filehandle
+ * get a root dentry from the root filehandle
  */
 int nfs_get_root(struct super_block *s, struct fs_context *fc)
 {
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index b4914a11c3c2..542c7d97b235 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -2461,35 +2461,54 @@ static void nfs_destroy_inodecache(void)
 	kmem_cache_destroy(nfs_inode_cachep);
 }
 
+struct workqueue_struct *nfslocaliod_workqueue;
 struct workqueue_struct *nfsiod_workqueue;
 EXPORT_SYMBOL_GPL(nfsiod_workqueue);
 
 /*
- * start up the nfsiod workqueue
+ * Destroy the nfsiod workqueues
  */
-static int nfsiod_start(void)
+static void nfsiod_stop(void)
 {
 	struct workqueue_struct *wq;
-	dprintk("RPC:       creating workqueue nfsiod\n");
-	wq = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
-	if (wq == NULL)
-		return -ENOMEM;
-	nfsiod_workqueue = wq;
-	return 0;
+
+	wq = nfsiod_workqueue;
+	if (wq != NULL) {
+		nfsiod_workqueue = NULL;
+		destroy_workqueue(wq);
+	}
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+	wq = nfslocaliod_workqueue;
+	if (wq != NULL) {
+		nfslocaliod_workqueue = NULL;
+		destroy_workqueue(wq);
+	}
+#endif /* CONFIG_NFS_LOCALIO */
 }
 
 /*
- * Destroy the nfsiod workqueue
+ * Start the nfsiod workqueues
  */
-static void nfsiod_stop(void)
+static int nfsiod_start(void)
 {
-	struct workqueue_struct *wq;
-
-	wq = nfsiod_workqueue;
-	if (wq == NULL)
-		return;
-	nfsiod_workqueue = NULL;
-	destroy_workqueue(wq);
+	dprintk("RPC:       creating workqueue nfsiod\n");
+	nfsiod_workqueue = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
+	if (nfsiod_workqueue == NULL)
+		return -ENOMEM;
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+	/*
+	 * localio writes need to use a normal (non-memreclaim) workqueue.
+	 * When we start getting low on space, XFS goes and calls flush_work() on
+	 * a non-memreclaim work queue, which causes a priority inversion problem.
+	 */
+	dprintk("RPC:       creating workqueue nfslocaliod\n");
+	nfslocaliod_workqueue = alloc_workqueue("nfslocaliod", WQ_UNBOUND, 0);
+	if (unlikely(nfslocaliod_workqueue == NULL)) {
+		nfsiod_stop();
+		return -ENOMEM;
+	}
+#endif /* CONFIG_NFS_LOCALIO */
+	return 0;
 }
 
 unsigned int nfs_net_id;
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 5902a9beca1f..430733e3eff2 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -9,6 +9,7 @@
 #include <linux/crc32.h>
 #include <linux/sunrpc/addr.h>
 #include <linux/nfs_page.h>
+#include <linux/nfslocalio.h>
 #include <linux/wait_bit.h>
 
 #define NFS_SB_MASK (SB_RDONLY|SB_NOSUID|SB_NODEV|SB_NOEXEC|SB_SYNCHRONOUS)
@@ -308,7 +309,8 @@ void nfs_pgio_header_free(struct nfs_pgio_header *);
 int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *);
 int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
 		      const struct cred *cred, const struct nfs_rpc_ops *rpc_ops,
-		      const struct rpc_call_ops *call_ops, int how, int flags);
+		      const struct rpc_call_ops *call_ops, int how, int flags,
+		      struct nfsd_file *localio);
 void nfs_free_request(struct nfs_page *req);
 struct nfs_pgio_mirror *
 nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc);
@@ -438,6 +440,7 @@ int nfs_check_flags(int);
 
 /* inode.c */
 extern struct workqueue_struct *nfsiod_workqueue;
+extern struct workqueue_struct *nfslocaliod_workqueue;
 extern struct inode *nfs_alloc_inode(struct super_block *sb);
 extern void nfs_free_inode(struct inode *);
 extern int nfs_write_inode(struct inode *, struct writeback_control *);
@@ -449,6 +452,51 @@ extern void nfs_set_cache_invalid(struct inode *inode, unsigned long flags);
 extern bool nfs_check_cache_invalid(struct inode *, unsigned long);
 extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode);
 
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+/* localio.c */
+extern void nfs_local_disable(struct nfs_client *);
+extern void nfs_local_probe(struct nfs_client *);
+extern struct nfsd_file *nfs_local_open_fh(struct nfs_client *,
+					   const struct cred *,
+					   struct nfs_fh *,
+					   const fmode_t);
+extern int nfs_local_doio(struct nfs_client *,
+			  struct nfsd_file *,
+			  struct nfs_pgio_header *,
+			  const struct rpc_call_ops *);
+extern int nfs_local_commit(struct nfsd_file *,
+			    struct nfs_commit_data *,
+			    const struct rpc_call_ops *, int);
+extern bool nfs_server_is_local(const struct nfs_client *clp);
+
+#else /* CONFIG_NFS_LOCALIO */
+static inline void nfs_local_disable(struct nfs_client *clp) {}
+static inline void nfs_local_probe(struct nfs_client *clp) {}
+static inline struct nfsd_file *
+nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
+		  struct nfs_fh *fh, const fmode_t mode)
+{
+	return NULL;
+}
+static inline int nfs_local_doio(struct nfs_client *clp,
+				 struct nfsd_file *localio,
+				 struct nfs_pgio_header *hdr,
+				 const struct rpc_call_ops *call_ops)
+{
+	return -EINVAL;
+}
+static inline int nfs_local_commit(struct nfsd_file *localio,
+				struct nfs_commit_data *data,
+				const struct rpc_call_ops *call_ops, int how)
+{
+	return -EINVAL;
+}
+static inline bool nfs_server_is_local(const struct nfs_client *clp)
+{
+	return false;
+}
+#endif /* CONFIG_NFS_LOCALIO */
+
 /* super.c */
 extern const struct super_operations nfs_sops;
 bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t);
@@ -505,7 +553,6 @@ extern int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio,
 			       struct nfs_open_context *ctx,
 			       struct folio *folio);
 extern void nfs_pageio_complete_read(struct nfs_pageio_descriptor *pgio);
-extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
 extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
 
 /* super.c */
@@ -528,7 +575,8 @@ extern int nfs_initiate_commit(struct rpc_clnt *clnt,
 			       struct nfs_commit_data *data,
 			       const struct nfs_rpc_ops *nfs_ops,
 			       const struct rpc_call_ops *call_ops,
-			       int how, int flags);
+			       int how, int flags,
+			       struct nfsd_file *localio);
 extern void nfs_init_commit(struct nfs_commit_data *data,
 			    struct list_head *head,
 			    struct pnfs_layout_segment *lseg,
diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
new file mode 100644
index 000000000000..c29cdf51c458
--- /dev/null
+++ b/fs/nfs/localio.c
@@ -0,0 +1,757 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * NFS client support for local clients to bypass network stack
+ *
+ * Copyright (C) 2014 Weston Andros Adamson <dros@primarydata.com>
+ * Copyright (C) 2019 Trond Myklebust <trond.myklebust@hammerspace.com>
+ * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com>
+ * Copyright (C) 2024 NeilBrown <neilb@suse.de>
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/vfs.h>
+#include <linux/file.h>
+#include <linux/inet.h>
+#include <linux/sunrpc/addr.h>
+#include <linux/inetdevice.h>
+#include <net/addrconf.h>
+#include <linux/nfs_common.h>
+#include <linux/nfslocalio.h>
+#include <linux/module.h>
+#include <linux/bvec.h>
+
+#include <linux/nfs.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_xdr.h>
+
+#include "internal.h"
+#include "pnfs.h"
+#include "nfstrace.h"
+
+#define NFSDBG_FACILITY		NFSDBG_VFS
+
+struct nfs_local_kiocb {
+	struct kiocb		kiocb;
+	struct bio_vec		*bvec;
+	struct nfs_pgio_header	*hdr;
+	struct work_struct	work;
+	struct nfsd_file	*localio;
+};
+
+struct nfs_local_fsync_ctx {
+	struct nfsd_file	*localio;
+	struct nfs_commit_data	*data;
+	struct work_struct	work;
+	struct kref		kref;
+	struct completion	*done;
+};
+static void nfs_local_fsync_work(struct work_struct *work);
+
+static bool localio_enabled __read_mostly = true;
+module_param(localio_enabled, bool, 0644);
+
+static inline bool nfs_client_is_local(const struct nfs_client *clp)
+{
+	return !!test_bit(NFS_CS_LOCAL_IO, &clp->cl_flags);
+}
+
+bool nfs_server_is_local(const struct nfs_client *clp)
+{
+	return nfs_client_is_local(clp) && localio_enabled;
+}
+EXPORT_SYMBOL_GPL(nfs_server_is_local);
+
+/*
+ * UUID_IS_LOCAL XDR functions
+ */
+
+static void localio_xdr_enc_uuidargs(struct rpc_rqst *req,
+				     struct xdr_stream *xdr,
+				     const void *data)
+{
+	const u8 *uuid = data;
+
+	encode_opaque_fixed(xdr, uuid, UUID_SIZE);
+}
+
+static int localio_xdr_dec_uuidres(struct rpc_rqst *req,
+				   struct xdr_stream *xdr,
+				   void *result)
+{
+	/* void return */
+	return 0;
+}
+
+static const struct rpc_procinfo nfs_localio_procedures[] = {
+	[LOCALIOPROC_UUID_IS_LOCAL] = {
+		.p_proc = LOCALIOPROC_UUID_IS_LOCAL,
+		.p_encode = localio_xdr_enc_uuidargs,
+		.p_decode = localio_xdr_dec_uuidres,
+		.p_arglen = XDR_QUADLEN(UUID_SIZE),
+		.p_replen = 0,
+		.p_statidx = LOCALIOPROC_UUID_IS_LOCAL,
+		.p_name = "UUID_IS_LOCAL",
+	},
+};
+
+static unsigned int nfs_localio_counts[ARRAY_SIZE(nfs_localio_procedures)];
+static const struct rpc_version nfslocalio_version1 = {
+	.number			= 1,
+	.nrprocs		= ARRAY_SIZE(nfs_localio_procedures),
+	.procs			= nfs_localio_procedures,
+	.counts			= nfs_localio_counts,
+};
+
+static const struct rpc_version *nfslocalio_version[] = {
+       [1]			= &nfslocalio_version1,
+};
+
+extern const struct rpc_program nfslocalio_program;
+static struct rpc_stat		nfslocalio_rpcstat = { &nfslocalio_program };
+
+const struct rpc_program nfslocalio_program = {
+	.name			= "nfslocalio",
+	.number			= NFS_LOCALIO_PROGRAM,
+	.nrvers			= ARRAY_SIZE(nfslocalio_version),
+	.version		= nfslocalio_version,
+	.stats			= &nfslocalio_rpcstat,
+};
+
+/*
+ * nfs_local_enable - enable local i/o for an nfs_client
+ */
+static void nfs_local_enable(struct nfs_client *clp)
+{
+	spin_lock(&clp->cl_localio_lock);
+	set_bit(NFS_CS_LOCAL_IO, &clp->cl_flags);
+	trace_nfs_local_enable(clp);
+	spin_unlock(&clp->cl_localio_lock);
+}
+
+/*
+ * nfs_local_disable - disable local i/o for an nfs_client
+ */
+void nfs_local_disable(struct nfs_client *clp)
+{
+	spin_lock(&clp->cl_localio_lock);
+	if (test_and_clear_bit(NFS_CS_LOCAL_IO, &clp->cl_flags)) {
+		trace_nfs_local_disable(clp);
+		nfs_uuid_invalidate_one_client(&clp->cl_uuid);
+	}
+	spin_unlock(&clp->cl_localio_lock);
+}
+
+/*
+ * nfs_init_localioclient - Initialise an NFS localio client connection
+ */
+static struct rpc_clnt *nfs_init_localioclient(struct nfs_client *clp)
+{
+	struct rpc_clnt *rpcclient_localio;
+
+	rpcclient_localio = rpc_bind_new_program(clp->cl_rpcclient,
+						 &nfslocalio_program, 1);
+
+	dprintk_rcu("%s: server (%s) %s NFS LOCALIO.\n",
+		__func__, rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR),
+		(IS_ERR(rpcclient_localio) ? "does not support" : "supports"));
+
+	return rpcclient_localio;
+}
+
+static bool nfs_server_uuid_is_local(struct nfs_client *clp)
+{
+	u8 uuid[UUID_SIZE];
+	struct rpc_message msg = {
+		.rpc_argp = &uuid,
+	};
+	struct rpc_clnt *rpcclient_localio;
+	int status;
+
+	rpcclient_localio = nfs_init_localioclient(clp);
+	if (IS_ERR(rpcclient_localio))
+		return false;
+
+	export_uuid(uuid, &clp->cl_uuid.uuid);
+
+	msg.rpc_proc = &nfs_localio_procedures[LOCALIOPROC_UUID_IS_LOCAL];
+	status = rpc_call_sync(rpcclient_localio, &msg, 0);
+	dprintk("%s: NFS reply UUID_IS_LOCAL: status=%d\n",
+		__func__, status);
+	rpc_shutdown_client(rpcclient_localio);
+
+	/* Server is only local if it initialized required struct members */
+	if (status || !clp->cl_uuid.net || !clp->cl_uuid.dom)
+		return false;
+
+	return true;
+}
+
+/*
+ * nfs_local_probe - probe local i/o support for an nfs_server and nfs_client
+ * - called after alloc_client and init_client (so cl_rpcclient exists)
+ * - this function is idempotent, it can be called for old or new clients
+ */
+void nfs_local_probe(struct nfs_client *clp)
+{
+	/* Disallow localio if disabled via sysfs or AUTH_SYS isn't used */
+	if (!localio_enabled ||
+	    clp->cl_rpcclient->cl_auth->au_flavor != RPC_AUTH_UNIX) {
+		nfs_local_disable(clp);
+		return;
+	}
+
+	if (nfs_client_is_local(clp)) {
+		/* If already enabled, disable and re-enable */
+		nfs_local_disable(clp);
+	}
+
+	nfs_uuid_begin(&clp->cl_uuid);
+	if (nfs_server_uuid_is_local(clp))
+		nfs_local_enable(clp);
+	nfs_uuid_end(&clp->cl_uuid);
+}
+EXPORT_SYMBOL_GPL(nfs_local_probe);
+
+/*
+ * nfs_local_open_fh - open a local filehandle in terms of nfsd_file
+ *
+ * Returns a pointer to a struct nfsd_file or NULL
+ */
+struct nfsd_file *
+nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
+		  struct nfs_fh *fh, const fmode_t mode)
+{
+	struct nfsd_file *localio;
+	int status;
+
+	if (!nfs_server_is_local(clp))
+		return NULL;
+	if (mode & ~(FMODE_READ | FMODE_WRITE))
+		return NULL;
+
+	localio = nfs_open_local_fh(&clp->cl_uuid, clp->cl_rpcclient,
+				    cred, fh, mode);
+	if (IS_ERR(localio)) {
+		status = PTR_ERR(localio);
+		trace_nfs_local_open_fh(fh, mode, status);
+		switch (status) {
+		case -ENOMEM:
+		case -ENXIO:
+		case -ENOENT:
+			/* Revalidate localio, will disable if unsupported */
+			nfs_local_probe(clp);
+		}
+		return NULL;
+	}
+	return localio;
+}
+EXPORT_SYMBOL_GPL(nfs_local_open_fh);
+
+static struct bio_vec *
+nfs_bvec_alloc_and_import_pagevec(struct page **pagevec,
+		unsigned int npages, gfp_t flags)
+{
+	struct bio_vec *bvec, *p;
+
+	bvec = kmalloc_array(npages, sizeof(*bvec), flags);
+	if (bvec != NULL) {
+		for (p = bvec; npages > 0; p++, pagevec++, npages--) {
+			p->bv_page = *pagevec;
+			p->bv_len = PAGE_SIZE;
+			p->bv_offset = 0;
+		}
+	}
+	return bvec;
+}
+
+static void
+nfs_local_iocb_free(struct nfs_local_kiocb *iocb)
+{
+	kfree(iocb->bvec);
+	kfree(iocb);
+}
+
+static struct nfs_local_kiocb *
+nfs_local_iocb_alloc(struct nfs_pgio_header *hdr,
+		     struct nfsd_file *localio, gfp_t flags)
+{
+	struct nfs_local_kiocb *iocb;
+
+	iocb = kmalloc(sizeof(*iocb), flags);
+	if (iocb == NULL)
+		return NULL;
+	iocb->bvec = nfs_bvec_alloc_and_import_pagevec(hdr->page_array.pagevec,
+			hdr->page_array.npages, flags);
+	if (iocb->bvec == NULL) {
+		kfree(iocb);
+		return NULL;
+	}
+	init_sync_kiocb(&iocb->kiocb, nfs_to->nfsd_f