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

…inux-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
  ...

Documentation/filesystems/nfs/index.rst

@@ -8,6 +8,7 @@ NFS
 
    client-identifier
    exporting
+   localio
    pnfs
    rpc-cache
    rpc-server-gss

fs/Kconfig

@@ -386,6 +386,29 @@ config NFS_COMMON
 	depends on NFSD || NFS_FS || LOCKD
 	default y
 
+config NFS_COMMON_LOCALIO_SUPPORT
+	tristate
+	default n
+	default y if NFSD=y || NFS_FS=y
+	default m if NFSD=m && NFS_FS=m
+	select SUNRPC
+
+config NFS_LOCALIO
+	bool "NFS client and server support for LOCALIO auxiliary protocol"
+	depends on NFSD && NFS_FS
+	select NFS_COMMON_LOCALIO_SUPPORT
+	default n
+	help
+	  Some NFS servers support an auxiliary NFS LOCALIO protocol
+	  that is not an official part of the NFS protocol.
+
+	  This option enables support for the LOCALIO protocol in the
+	  kernel's NFS server and client. Enable this to permit local
+	  NFS clients to bypass the network when issuing reads and
+	  writes to the local NFS server.
+
+	  If unsure, say N.
+
 config NFS_V4_2_SSC_HELPER
 	bool
 	default y if NFS_V4_2

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

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

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);

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:

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);

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:
@@ -2086,12 +2128,6 @@ static int ff_layout_encode_ioerr(struct xdr_stream *xdr,
 	return ff_layout_encode_ds_ioerr(xdr, &ff_args->errors);
 }
 
-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,

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);

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;

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)
 {