Resguardo inicial

linux-7.2.3/fs/nfsd/Kconfig

@@ -0,0 +1,197 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config NFSD
+	tristate "NFS server support"
+	depends on INET
+	depends on FILE_LOCKING
+	depends on FSNOTIFY
+	select CRC32
+	select CRYPTO_LIB_MD5 if NFSD_LEGACY_CLIENT_TRACKING
+	select CRYPTO_LIB_SHA256 if NFSD_V4
+	select CRYPTO # required by RPCSEC_GSS_KRB5 and signed filehandles
+	select LOCKD
+	select SUNRPC
+	select EXPORTFS
+	select NFS_COMMON
+	select NFS_ACL_SUPPORT if NFSD_V2_ACL
+	select NFS_ACL_SUPPORT if NFSD_V3_ACL
+	depends on MULTIUSER
+	help
+	  Choose Y here if you want to allow other computers to access
+	  files residing on this system using Sun's Network File System
+	  protocol.  To compile the NFS server support as a module,
+	  choose M here: the module will be called nfsd.
+
+	  You may choose to use a user-space NFS server instead, in which
+	  case you can choose N here.
+
+	  To export local file systems using NFS, you also need to install
+	  user space programs which can be found in the Linux nfs-utils
+	  package, available from http://linux-nfs.org/.  More detail about
+	  the Linux NFS server implementation is available via the
+	  exports(5) man page.
+
+	  Below you can choose which versions of the NFS protocol are
+	  available to clients mounting the NFS server on this system.
+	  Support for NFS version 3 (RFC 1813) is always available when
+	  CONFIG_NFSD is selected.
+
+	  If unsure, say N.
+
+config NFSD_V2
+	bool "NFS server support for NFS version 2 (DEPRECATED)"
+	depends on NFSD
+	default n
+	help
+	  NFSv2 (RFC 1094) was the first publicly-released version of NFS.
+	  Unless you are hosting ancient (1990's era) NFS clients, you don't
+	  need this.
+
+	  If unsure, say N.
+
+config NFSD_V2_ACL
+	bool "NFS server support for the NFSv2 ACL protocol extension"
+	depends on NFSD_V2
+
+config NFSD_V3_ACL
+	bool "NFS server support for the NFSv3 ACL protocol extension"
+	depends on NFSD
+	help
+	  Solaris NFS servers support an auxiliary NFSv3 ACL protocol that
+	  never became an official part of the NFS version 3 protocol.
+	  This protocol extension allows applications on NFS clients to
+	  manipulate POSIX Access Control Lists on files residing on NFS
+	  servers.  NFS servers enforce POSIX ACLs on local files whether
+	  this protocol is available or not.
+
+	  This option enables support in your system's NFS server for the
+	  NFSv3 ACL protocol extension allowing NFS clients to manipulate
+	  POSIX ACLs on files exported by your system's NFS server.  NFS
+	  clients which support the Solaris NFSv3 ACL protocol can then
+	  access and modify ACLs on your NFS server.
+
+	  To store ACLs on your NFS server, you also need to enable ACL-
+	  related CONFIG options for your local file systems of choice.
+
+	  If unsure, say N.
+
+config NFSD_V4
+	bool "NFS server support for NFS version 4"
+	depends on NFSD && PROC_FS
+	select FS_POSIX_ACL
+	select RPCSEC_GSS_KRB5
+	select GRACE_PERIOD
+	select NFS_V4_2_SSC_HELPER if NFS_V4_2
+	help
+	  This option enables support in your system's NFS server for
+	  version 4 of the NFS protocol (RFC 3530).
+
+	  To export files using NFSv4, you need to install additional user
+	  space programs which can be found in the Linux nfs-utils package,
+	  available from http://linux-nfs.org/.
+
+	  If unsure, say N.
+
+config NFSD_PNFS
+	bool
+
+config NFSD_BLOCKLAYOUT
+	bool "NFSv4.1 server support for pNFS block layouts"
+	depends on NFSD_V4 && BLOCK
+	select NFSD_PNFS
+	select EXPORTFS_BLOCK_OPS
+	help
+	  This option enables support for the exporting pNFS block layouts
+	  in the kernel's NFS server. The pNFS block layout enables NFS
+	  clients to directly perform I/O to block devices accessible to both
+	  the server and the clients.  See RFC 5663 for more details.
+
+	  If unsure, say N.
+
+config NFSD_SCSILAYOUT
+	bool "NFSv4.1 server support for pNFS SCSI layouts"
+	depends on NFSD_V4 && BLOCK
+	select NFSD_PNFS
+	select EXPORTFS_BLOCK_OPS
+	help
+	  This option enables support for the exporting pNFS SCSI layouts
+	  in the kernel's NFS server. The pNFS SCSI layout enables NFS
+	  clients to directly perform I/O to SCSI devices accessible to both
+	  the server and the clients.  See draft-ietf-nfsv4-scsi-layout for
+	  more details.
+
+	  If unsure, say N.
+
+config NFSD_FLEXFILELAYOUT
+	bool "NFSv4.1 server support for pNFS Flex File layouts"
+	depends on NFSD_V4
+	select NFSD_PNFS
+	help
+	  This option enables support for the exporting pNFS Flex File
+	  layouts in the kernel's NFS server. The pNFS Flex File  layout
+	  enables NFS clients to directly perform I/O to NFSv3 devices
+	  accessible to both the server and the clients.  See
+	  draft-ietf-nfsv4-flex-files for more details.
+
+	  Warning, this server implements the bare minimum functionality
+	  to be a flex file server - it is for testing the client,
+	  not for use in production.
+
+	  If unsure, say N.
+
+config NFSD_V4_2_INTER_SSC
+	bool "NFSv4.2 inter server to server COPY"
+	depends on NFSD_V4 && NFS_V4_2
+	help
+	  This option enables support for NFSv4.2 inter server to
+	  server copy where the destination server calls the NFSv4.2
+	  client to read the data to copy from the source server.
+
+	  If unsure, say N.
+
+config NFSD_V4_SECURITY_LABEL
+	bool "Provide Security Label support for NFSv4 server"
+	depends on NFSD_V4 && SECURITY
+	help
+
+	Say Y here if you want enable fine-grained security label attribute
+	support for NFS version 4.  Security labels allow security modules like
+	SELinux and Smack to label files to facilitate enforcement of their policies.
+	Without this an NFSv4 mount will have the same label on each file.
+
+	If you do not wish to enable fine-grained security labels SELinux or
+	Smack policies on NFSv4 files, say N.
+
+config NFSD_LEGACY_CLIENT_TRACKING
+	bool "Support legacy NFSv4 client tracking methods (DEPRECATED)"
+	depends on NFSD_V4
+	default n
+	help
+	  The NFSv4 server needs to store a small amount of information on
+	  stable storage in order to handle state recovery after reboot. Most
+	  modern deployments upcall to a userland daemon for this (nfsdcld),
+	  but older NFS servers may store information directly in a
+	  recoverydir, or spawn a process directly using a usermodehelper
+	  upcall.
+
+	  These legacy client tracking methods have proven to be problematic
+	  and will be removed in the future. Say Y here if you need support
+	  for them in the interim.
+
+config NFSD_V4_POSIX_ACLS
+	bool "Support NFSv4 POSIX draft ACLs"
+	depends on NFSD_V4
+	default n
+	help
+	  Include experimental support for POSIX Access Control Lists
+	  (ACLs) in NFSv4 as specified in the IETF draft
+	  draft-ietf-nfsv4-posix-acls. This protocol extension enables
+	  NFSv4 clients to retrieve and modify POSIX ACLs on exported
+	  filesystems that support them.
+
+	  This feature is based on an unratified IETF draft
+	  specification that may change in ways that impact
+	  interoperability with existing clients. Enable only for
+	  testing environments or when interoperability with specific
+	  clients that implement this draft is required.
+
+	  If unsure, say N.

linux-7.2.3/fs/nfsd/Makefile

@@ -0,0 +1,49 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the Linux nfs server
+#
+
+ccflags-y += -I$(src)			# needed for trace events
+
+obj-$(CONFIG_NFSD)	+= nfsd.o
+
+# this one should be compiled first, as the tracing macros can easily blow up
+nfsd-y			+= trace.o
+
+nfsd-y 			+= nfssvc.o nfsctl.o nfsfh.o vfs.o \
+			   export.o auth.o lockd.o nfscache.o \
+			   stats.o filecache.o nfs3proc.o nfs3xdr.o \
+			   netlink.o
+nfsd-$(CONFIG_NFSD_V2) += nfsproc.o nfsxdr.o
+nfsd-$(CONFIG_NFSD_V2_ACL) += nfs2acl.o
+nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o
+nfsd-$(CONFIG_NFSD_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \
+			   nfs4acl.o nfs4callback.o nfs4recover.o nfs4xdr_gen.o
+nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o
+nfsd-$(CONFIG_NFSD_BLOCKLAYOUT) += blocklayout.o blocklayoutxdr.o
+nfsd-$(CONFIG_NFSD_SCSILAYOUT) += blocklayout.o blocklayoutxdr.o
+nfsd-$(CONFIG_NFSD_FLEXFILELAYOUT) += flexfilelayout.o flexfilelayoutxdr.o
+nfsd-$(CONFIG_NFS_LOCALIO) += localio.o
+nfsd-$(CONFIG_DEBUG_FS) += debugfs.o
+
+#
+# XDR code generation (requires Python and additional packages)
+#
+# The generated *xdr_gen.{h,c} files are checked into git. Normal kernel
+# builds do not require the xdrgen tool or its Python dependencies.
+#
+# Developers modifying .x files in Documentation/sunrpc/xdr/ should run
+# "make xdrgen" to regenerate the affected files.
+#
+.PHONY: xdrgen
+
+xdrgen: ../../include/linux/sunrpc/xdrgen/nfs4_1.h nfs4xdr_gen.h nfs4xdr_gen.c
+
+../../include/linux/sunrpc/xdrgen/nfs4_1.h: ../../Documentation/sunrpc/xdr/nfs4_1.x
+	../../tools/net/sunrpc/xdrgen/xdrgen definitions $< > $@
+
+nfs4xdr_gen.h: ../../Documentation/sunrpc/xdr/nfs4_1.x
+	../../tools/net/sunrpc/xdrgen/xdrgen declarations $< > $@
+
+nfs4xdr_gen.c: ../../Documentation/sunrpc/xdr/nfs4_1.x
+	../../tools/net/sunrpc/xdrgen/xdrgen source $< > $@

linux-7.2.3/fs/nfsd/acl.h

@@ -0,0 +1,54 @@
+/*
+ *  Common NFSv4 ACL handling definitions.
+ *
+ *  Copyright (c) 2002 The Regents of the University of Michigan.
+ *  All rights reserved.
+ *
+ *  Marius Aamodt Eriksen <marius@umich.edu>
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the University nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef LINUX_NFS4_ACL_H
+#define LINUX_NFS4_ACL_H
+
+struct nfs4_acl;
+struct svc_fh;
+struct svc_rqst;
+struct nfsd_attrs;
+enum nfs_ftype4;
+
+int nfs4_acl_bytes(int entries);
+int nfs4_acl_get_whotype(char *, u32);
+__be32 nfs4_acl_write_who(struct xdr_stream *xdr, int who);
+
+int nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry,
+		struct nfs4_acl **acl);
+__be32 nfsd4_acl_to_attr(enum nfs_ftype4 type, struct nfs4_acl *acl,
+			 struct nfsd_attrs *attr);
+void sort_pacl_range(struct posix_acl *pacl, int start, int end);
+
+#endif /* LINUX_NFS4_ACL_H */

linux-7.2.3/fs/nfsd/auth.c

@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> */
+
+#include <linux/sched.h>
+#include "nfsd.h"
+#include "auth.h"
+
+int nfsexp_flags(struct svc_cred *cred, struct svc_export *exp)
+{
+	struct exp_flavor_info *f;
+	struct exp_flavor_info *end = exp->ex_flavors + exp->ex_nflavors;
+
+	for (f = exp->ex_flavors; f < end; f++) {
+		if (f->pseudoflavor == cred->cr_flavor)
+			return f->flags;
+	}
+	return exp->ex_flags;
+
+}
+
+int nfsd_setuser(struct svc_cred *cred, struct svc_export *exp)
+{
+	struct group_info *rqgi;
+	struct group_info *gi;
+	struct cred *new;
+	int i;
+	int flags = nfsexp_flags(cred, exp);
+
+	/* discard any old override before preparing the new set */
+	put_cred(revert_creds(get_cred(current_real_cred())));
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	new->fsuid = cred->cr_uid;
+	new->fsgid = cred->cr_gid;
+
+	rqgi = cred->cr_group_info;
+
+	if (flags & NFSEXP_ALLSQUASH) {
+		new->fsuid = exp->ex_anon_uid;
+		new->fsgid = exp->ex_anon_gid;
+		gi = groups_alloc(0);
+		if (!gi)
+			goto oom;
+	} else if (flags & NFSEXP_ROOTSQUASH) {
+		if (uid_eq(new->fsuid, GLOBAL_ROOT_UID))
+			new->fsuid = exp->ex_anon_uid;
+		if (gid_eq(new->fsgid, GLOBAL_ROOT_GID))
+			new->fsgid = exp->ex_anon_gid;
+
+		gi = groups_alloc(rqgi->ngroups);
+		if (!gi)
+			goto oom;
+
+		for (i = 0; i < rqgi->ngroups; i++) {
+			if (gid_eq(GLOBAL_ROOT_GID, rqgi->gid[i]))
+				gi->gid[i] = exp->ex_anon_gid;
+			else
+				gi->gid[i] = rqgi->gid[i];
+		}
+
+		/* Each thread allocates its own gi, no race */
+		groups_sort(gi);
+	} else {
+		gi = get_group_info(rqgi);
+	}
+
+	if (uid_eq(new->fsuid, INVALID_UID))
+		new->fsuid = exp->ex_anon_uid;
+	if (gid_eq(new->fsgid, INVALID_GID))
+		new->fsgid = exp->ex_anon_gid;
+
+	set_groups(new, gi);
+	put_group_info(gi);
+
+	if (!uid_eq(new->fsuid, GLOBAL_ROOT_UID))
+		new->cap_effective = cap_drop_nfsd_set(new->cap_effective);
+	else
+		new->cap_effective = cap_raise_nfsd_set(new->cap_effective,
+							new->cap_permitted);
+	put_cred(override_creds(new));
+	return 0;
+
+oom:
+	abort_creds(new);
+	return -ENOMEM;
+}
+

linux-7.2.3/fs/nfsd/auth.h

@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * nfsd-specific authentication stuff.
+ *
+ * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#ifndef LINUX_NFSD_AUTH_H
+#define LINUX_NFSD_AUTH_H
+
+/*
+ * Set the current process's fsuid/fsgid etc to those of the NFS
+ * client user
+ */
+int nfsd_setuser(struct svc_cred *cred, struct svc_export *exp);
+
+#endif /* LINUX_NFSD_AUTH_H */

linux-7.2.3/fs/nfsd/blocklayout.c

@@ -0,0 +1,526 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2014-2016 Christoph Hellwig.
+ */
+#include <linux/exportfs_block.h>
+#include <linux/iomap.h>
+#include <linux/slab.h>
+#include <linux/pr.h>
+
+#include <linux/nfsd/debug.h>
+
+#include "blocklayoutxdr.h"
+#include "pnfs.h"
+#include "filecache.h"
+#include "vfs.h"
+#include "trace.h"
+
+#define NFSDDBG_FACILITY	NFSDDBG_PNFS
+
+
+/*
+ * Get an extent from the file system that starts at offset or below
+ * and may be shorter than the requested length.
+ */
+static __be32
+nfsd4_block_map_extent(struct inode *inode, const struct svc_fh *fhp,
+		u64 offset, u64 length, u32 iomode, u64 minlength,
+		struct pnfs_block_extent *bex)
+{
+	struct super_block *sb = inode->i_sb;
+	struct iomap iomap;
+	u32 device_generation = 0;
+	int error;
+
+	error = sb->s_export_op->block_ops->map_blocks(inode, offset, length,
+			&iomap, iomode != IOMODE_READ, &device_generation);
+	if (error) {
+		if (error == -ENXIO)
+			return nfserr_layoutunavailable;
+		return nfserrno(error);
+	}
+
+	switch (iomap.type) {
+	case IOMAP_MAPPED:
+		if (iomode == IOMODE_READ)
+			bex->es = PNFS_BLOCK_READ_DATA;
+		else
+			bex->es = PNFS_BLOCK_READWRITE_DATA;
+		bex->soff = iomap.addr;
+		break;
+	case IOMAP_UNWRITTEN:
+		if (iomode & IOMODE_RW) {
+			/*
+			 * Crack monkey special case from section 2.3.1.
+			 */
+			if (minlength == 0) {
+				dprintk("pnfsd: no soup for you!\n");
+				return nfserr_layoutunavailable;
+			}
+
+			bex->es = PNFS_BLOCK_INVALID_DATA;
+			bex->soff = iomap.addr;
+			break;
+		}
+		fallthrough;
+	case IOMAP_HOLE:
+		if (iomode == IOMODE_READ) {
+			bex->es = PNFS_BLOCK_NONE_DATA;
+			break;
+		}
+		fallthrough;
+	case IOMAP_DELALLOC:
+	default:
+		WARN(1, "pnfsd: filesystem returned %d extent\n", iomap.type);
+		return nfserr_layoutunavailable;
+	}
+
+	error = nfsd4_set_deviceid(&bex->vol_id, fhp, device_generation);
+	if (error)
+		return nfserrno(error);
+
+	bex->foff = iomap.offset;
+	bex->len = iomap.length;
+	return nfs_ok;
+}
+
+static __be32
+nfsd4_block_proc_layoutget(struct svc_rqst *rqstp, struct inode *inode,
+		const struct svc_fh *fhp, struct nfsd4_layoutget *args)
+{
+	struct nfsd4_layout_seg *seg = &args->lg_seg;
+	struct pnfs_block_layout *bl;
+	struct pnfs_block_extent *first_bex, *last_bex;
+	u64 offset = seg->offset, length = seg->length;
+	u32 i, nr_extents_max, block_size = i_blocksize(inode);
+	__be32 nfserr;
+
+	if (locks_in_grace(SVC_NET(rqstp)))
+		return nfserr_grace;
+
+	nfserr = nfserr_layoutunavailable;
+	if (seg->offset & (block_size - 1)) {
+		dprintk("pnfsd: I/O misaligned\n");
+		goto out_error;
+	}
+
+	/*
+	 * RFC 8881, section 3.3.17:
+	 *   The layout4 data type defines a layout for a file.
+	 *
+	 * RFC 8881, section 18.43.3:
+	 *   The loga_maxcount field specifies the maximum layout size
+	 *   (in bytes) that the client can handle. If the size of the
+	 *   layout structure exceeds the size specified by maxcount,
+	 *   the metadata server will return the NFS4ERR_TOOSMALL error.
+	 */
+	nfserr = nfserr_toosmall;
+	if (args->lg_maxcount < PNFS_BLOCK_LAYOUT4_SIZE +
+				PNFS_BLOCK_EXTENT_SIZE)
+		goto out_error;
+
+	/*
+	 * Limit the maximum layout size to avoid allocating
+	 * a large buffer on the server for each layout request.
+	 */
+	nr_extents_max = (min(args->lg_maxcount, PAGE_SIZE) -
+			  PNFS_BLOCK_LAYOUT4_SIZE) / PNFS_BLOCK_EXTENT_SIZE;
+
+	/*
+	 * Some clients barf on non-zero block numbers for NONE or INVALID
+	 * layouts, so make sure to zero the whole structure.
+	 */
+	nfserr = nfserrno(-ENOMEM);
+	bl = kzalloc_flex(*bl, extents, nr_extents_max);
+	if (!bl)
+		goto out_error;
+	bl->nr_extents = nr_extents_max;
+	args->lg_content = bl;
+
+	for (i = 0; i < bl->nr_extents; i++) {
+		struct pnfs_block_extent *bex = bl->extents + i;
+		u64 bex_length;
+
+		nfserr = nfsd4_block_map_extent(inode, fhp, offset, length,
+				seg->iomode, args->lg_minlength, bex);
+		if (nfserr != nfs_ok)
+			goto out_error;
+
+		bex_length = bex->len - (offset - bex->foff);
+		if (bex_length >= length) {
+			bl->nr_extents = i + 1;
+			break;
+		}
+
+		offset = bex->foff + bex->len;
+		length -= bex_length;
+	}
+
+	first_bex = bl->extents;
+	last_bex = bl->extents + bl->nr_extents - 1;
+
+	nfserr = nfserr_layoutunavailable;
+	length = last_bex->foff + last_bex->len - seg->offset;
+	if (length < args->lg_minlength) {
+		dprintk("pnfsd: extent smaller than minlength\n");
+		goto out_error;
+	}
+
+	seg->offset = first_bex->foff;
+	seg->length = last_bex->foff - first_bex->foff + last_bex->len;
+	return nfs_ok;
+
+out_error:
+	seg->length = 0;
+	return nfserr;
+}
+
+static __be32
+nfsd4_block_commit_blocks(struct inode *inode, struct nfsd4_layoutcommit *lcp,
+		struct iomap *iomaps, int nr_iomaps)
+{
+	int error;
+
+	/*
+	 * This ignores the client provided mtime in loca_time_modify, as a
+	 * fully client specified mtime doesn't really fit into the Linux
+	 * multi-grain timestamp architecture.
+	 *
+	 * RFC 8881 Section 18.42 makes it clear that the client provided
+	 * timestamp is a "may" condition, and clients that want to force a
+	 * specific timestamp should send a separate SETATTR in the compound.
+	 */
+	error = inode->i_sb->s_export_op->block_ops->commit_blocks(inode,
+			iomaps, nr_iomaps,
+			lcp->lc_size_chg ? lcp->lc_newsize : 0);
+	kfree(iomaps);
+	return nfserrno(error);
+}
+
+#ifdef CONFIG_NFSD_BLOCKLAYOUT
+static int
+nfsd4_block_get_device_info_simple(struct super_block *sb,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	struct pnfs_block_deviceaddr *dev;
+	struct pnfs_block_volume *b;
+
+	dev = kzalloc_flex(*dev, volumes, 1);
+	if (!dev)
+		return -ENOMEM;
+	gdp->gd_device = dev;
+
+	dev->nr_volumes = 1;
+	b = &dev->volumes[0];
+
+	b->type = PNFS_BLOCK_VOLUME_SIMPLE;
+	b->simple.sig_len = PNFS_BLOCK_UUID_LEN;
+	return sb->s_export_op->block_ops->get_uuid(sb, b->simple.sig,
+			&b->simple.sig_len, &b->simple.offset);
+}
+
+static __be32
+nfsd4_block_proc_getdeviceinfo(struct super_block *sb,
+		struct svc_rqst *rqstp,
+		struct nfs4_client *clp,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	if (bdev_is_partition(sb->s_bdev))
+		return nfserr_inval;
+	return nfserrno(nfsd4_block_get_device_info_simple(sb, gdp));
+}
+
+static __be32
+nfsd4_block_proc_layoutcommit(struct inode *inode, struct svc_rqst *rqstp,
+		struct nfsd4_layoutcommit *lcp)
+{
+	struct iomap *iomaps;
+	int nr_iomaps;
+	__be32 nfserr;
+
+	rqstp->rq_arg = lcp->lc_up_layout;
+	svcxdr_init_decode(rqstp);
+
+	nfserr = nfsd4_block_decode_layoutupdate(&rqstp->rq_arg_stream,
+			&iomaps, &nr_iomaps, i_blocksize(inode));
+	if (nfserr != nfs_ok)
+		return nfserr;
+
+	return nfsd4_block_commit_blocks(inode, lcp, iomaps, nr_iomaps);
+}
+
+const struct nfsd4_layout_ops bl_layout_ops = {
+	/*
+	 * Pretend that we send notification to the client.  This is a blatant
+	 * lie to force recent Linux clients to cache our device IDs.
+	 * We rarely ever change the device ID, so the harm of leaking deviceids
+	 * for a while isn't too bad.  Unfortunately RFC5661 is a complete mess
+	 * in this regard, but I filed errata 4119 for this a while ago, and
+	 * hopefully the Linux client will eventually start caching deviceids
+	 * without this again.
+	 */
+	.notify_types		=
+			NOTIFY_DEVICEID4_DELETE | NOTIFY_DEVICEID4_CHANGE,
+	.proc_getdeviceinfo	= nfsd4_block_proc_getdeviceinfo,
+	.encode_getdeviceinfo	= nfsd4_block_encode_getdeviceinfo,
+	.proc_layoutget		= nfsd4_block_proc_layoutget,
+	.encode_layoutget	= nfsd4_block_encode_layoutget,
+	.proc_layoutcommit	= nfsd4_block_proc_layoutcommit,
+};
+#endif /* CONFIG_NFSD_BLOCKLAYOUT */
+
+#ifdef CONFIG_NFSD_SCSILAYOUT
+
+#define NFSD_MDS_PR_FENCED	XA_MARK_0
+
+/*
+ * Clear the fence flag if the device already has an entry. This occurs
+ * when a client re-registers after a previous fence, allowing new
+ * layouts for this device.
+ *
+ * Insert only on first registration. This bounds cl_dev_fences to the
+ * count of devices this client has accessed, preventing unbounded growth.
+ */
+static inline int nfsd4_scsi_fence_insert(struct nfs4_client *clp,
+					  dev_t device)
+{
+	struct xarray *xa = &clp->cl_dev_fences;
+	int ret;
+
+	xa_lock(xa);
+	ret = __xa_insert(xa, device, XA_ZERO_ENTRY, GFP_KERNEL);
+	if (ret == -EBUSY) {
+		__xa_clear_mark(xa, device, NFSD_MDS_PR_FENCED);
+		ret = 0;
+	}
+	xa_unlock(xa);
+	clp->cl_fence_retry_warn = false;
+	return ret;
+}
+
+static inline bool nfsd4_scsi_fence_set(struct nfs4_client *clp, dev_t device)
+{
+	struct xarray *xa = &clp->cl_dev_fences;
+	bool skip;
+
+	xa_lock(xa);
+	skip = xa_get_mark(xa, device, NFSD_MDS_PR_FENCED);
+	if (!skip)
+		__xa_set_mark(xa, device, NFSD_MDS_PR_FENCED);
+	xa_unlock(xa);
+	return skip;
+}
+
+static inline void nfsd4_scsi_fence_clear(struct nfs4_client *clp, dev_t device)
+{
+	xa_clear_mark(&clp->cl_dev_fences, device, NFSD_MDS_PR_FENCED);
+}
+
+#define NFSD_MDS_PR_KEY		0x0100000000000000ULL
+
+/*
+ * We use the client ID as a unique key for the reservations.
+ * This allows us to easily fence a client when recalls fail.
+ */
+static u64 nfsd4_scsi_pr_key(struct nfs4_client *clp)
+{
+	return ((u64)clp->cl_clientid.cl_boot << 32) | clp->cl_clientid.cl_id;
+}
+
+static const u8 designator_types[] = {
+	PS_DESIGNATOR_EUI64,
+	PS_DESIGNATOR_NAA,
+};
+
+static int
+nfsd4_block_get_unique_id(struct gendisk *disk, struct pnfs_block_volume *b)
+{
+	int ret, i;
+
+	for (i = 0; i < ARRAY_SIZE(designator_types); i++) {
+		u8 type = designator_types[i];
+
+		ret = disk->fops->get_unique_id(disk, b->scsi.designator, type);
+		if (ret > 0) {
+			b->scsi.code_set = PS_CODE_SET_BINARY;
+			b->scsi.designator_type = type;
+			b->scsi.designator_len = ret;
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+static int
+nfsd4_block_get_device_info_scsi(struct super_block *sb,
+		struct nfs4_client *clp,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	struct pnfs_block_deviceaddr *dev;
+	struct pnfs_block_volume *b;
+	const struct pr_ops *ops;
+	int ret;
+
+	dev = kzalloc_flex(*dev, volumes, 1);
+	if (!dev)
+		return -ENOMEM;
+	gdp->gd_device = dev;
+
+	dev->nr_volumes = 1;
+	b = &dev->volumes[0];
+
+	b->type = PNFS_BLOCK_VOLUME_SCSI;
+	b->scsi.pr_key = nfsd4_scsi_pr_key(clp);
+
+	ret = nfsd4_block_get_unique_id(sb->s_bdev->bd_disk, b);
+	if (ret < 0)
+		goto out_free_dev;
+
+	ret = -EINVAL;
+	ops = sb->s_bdev->bd_disk->fops->pr_ops;
+	if (!ops) {
+		pr_err("pNFS: device %s does not support PRs.\n",
+			sb->s_id);
+		goto out_free_dev;
+	}
+
+	ret = nfsd4_scsi_fence_insert(clp, sb->s_bdev->bd_dev);
+	if (ret < 0)
+		goto out_free_dev;
+
+	ret = ops->pr_register(sb->s_bdev, 0, NFSD_MDS_PR_KEY, true);
+	if (ret) {
+		pr_err("pNFS: failed to register key for device %s.\n",
+			sb->s_id);
+		goto out_free_dev;
+	}
+
+	ret = ops->pr_reserve(sb->s_bdev, NFSD_MDS_PR_KEY,
+			PR_EXCLUSIVE_ACCESS_REG_ONLY, 0);
+	if (ret) {
+		pr_err("pNFS: failed to reserve device %s.\n",
+			sb->s_id);
+		goto out_free_dev;
+	}
+
+	return 0;
+
+out_free_dev:
+	kfree(dev);
+	gdp->gd_device = NULL;
+	return ret;
+}
+
+static __be32
+nfsd4_scsi_proc_getdeviceinfo(struct super_block *sb,
+		struct svc_rqst *rqstp,
+		struct nfs4_client *clp,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	if (bdev_is_partition(sb->s_bdev))
+		return nfserr_inval;
+	return nfserrno(nfsd4_block_get_device_info_scsi(sb, clp, gdp));
+}
+static __be32
+nfsd4_scsi_proc_layoutcommit(struct inode *inode, struct svc_rqst *rqstp,
+		struct nfsd4_layoutcommit *lcp)
+{
+	struct iomap *iomaps;
+	int nr_iomaps;
+	__be32 nfserr;
+
+	rqstp->rq_arg = lcp->lc_up_layout;
+	svcxdr_init_decode(rqstp);
+
+	nfserr = nfsd4_scsi_decode_layoutupdate(&rqstp->rq_arg_stream,
+			&iomaps, &nr_iomaps, i_blocksize(inode));
+	if (nfserr != nfs_ok)
+		return nfserr;
+
+	return nfsd4_block_commit_blocks(inode, lcp, iomaps, nr_iomaps);
+}
+
+/*
+ * Perform the fence operation to prevent the client from accessing the
+ * block device. If a fence operation is already in progress, wait for
+ * it to complete before checking the NFSD_MDS_PR_FENCED flag. Once the
+ * operation is complete, check the flag. If NFSD_MDS_PR_FENCED is set,
+ * update the layout stateid by setting the ls_fenced flag to indicate
+ * that the client has been fenced.
+ *
+ * The cl_fence_mutex ensures that the fence operation has been fully
+ * completed, rather than just in progress, when returning from this
+ * function.
+ *
+ * Return true if client was fenced otherwise return false.
+ */
+static bool
+nfsd4_scsi_fence_client(struct nfs4_layout_stateid *ls, struct nfsd_file *file)
+{
+	struct nfs4_client *clp = ls->ls_stid.sc_client;
+	struct block_device *bdev = file->nf_file->f_path.mnt->mnt_sb->s_bdev;
+	int status;
+	bool ret;
+
+	mutex_lock(&clp->cl_fence_mutex);
+	if (nfsd4_scsi_fence_set(clp, bdev->bd_dev)) {
+		mutex_unlock(&clp->cl_fence_mutex);
+		return true;
+	}
+
+	status = bdev->bd_disk->fops->pr_ops->pr_preempt(bdev, NFSD_MDS_PR_KEY,
+			nfsd4_scsi_pr_key(clp),
+			PR_EXCLUSIVE_ACCESS_REG_ONLY, true);
+	/*
+	 * Reset to allow retry only when the command could not have
+	 * reached the device. Negative status means a local error
+	 * (e.g., -ENOMEM) prevented the command from being sent.
+	 * PR_STS_PATH_FAILED, PR_STS_PATH_FAST_FAILED, and
+	 * PR_STS_RETRY_PATH_FAILURE indicate transport path failures
+	 * before device delivery.
+	 *
+	 * For all other errors, the command may have reached the device
+	 * and the preempt may have succeeded. Avoid resetting, since
+	 * retrying a successful preempt returns PR_STS_IOERR or
+	 * PR_STS_RESERVATION_CONFLICT, which would cause an infinite
+	 * retry loop.
+	 */
+	switch (status) {
+	case 0:
+	case PR_STS_IOERR:
+	case PR_STS_RESERVATION_CONFLICT:
+		ret = true;
+		break;
+	default:
+		/* retry-able and other errors */
+		ret = false;
+		nfsd4_scsi_fence_clear(clp, bdev->bd_dev);
+		break;
+	}
+	mutex_unlock(&clp->cl_fence_mutex);
+
+	trace_nfsd_pnfs_fence(clp, bdev->bd_disk->disk_name, status);
+	return ret;
+}
+
+const struct nfsd4_layout_ops scsi_layout_ops = {
+	/*
+	 * Pretend that we send notification to the client.  This is a blatant
+	 * lie to force recent Linux clients to cache our device IDs.
+	 * We rarely ever change the device ID, so the harm of leaking deviceids
+	 * for a while isn't too bad.  Unfortunately RFC5661 is a complete mess
+	 * in this regard, but I filed errata 4119 for this a while ago, and
+	 * hopefully the Linux client will eventually start caching deviceids
+	 * without this again.
+	 */
+	.notify_types		=
+			NOTIFY_DEVICEID4_DELETE | NOTIFY_DEVICEID4_CHANGE,
+	.proc_getdeviceinfo	= nfsd4_scsi_proc_getdeviceinfo,
+	.encode_getdeviceinfo	= nfsd4_block_encode_getdeviceinfo,
+	.proc_layoutget		= nfsd4_block_proc_layoutget,
+	.encode_layoutget	= nfsd4_block_encode_layoutget,
+	.proc_layoutcommit	= nfsd4_scsi_proc_layoutcommit,
+	.fence_client		= nfsd4_scsi_fence_client,
+};
+#endif /* CONFIG_NFSD_SCSILAYOUT */

linux-7.2.3/fs/nfsd/blocklayoutxdr.c

@@ -0,0 +1,295 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2014-2016 Christoph Hellwig.
+ */
+#include <linux/sunrpc/svc.h>
+#include <linux/exportfs.h>
+#include <linux/iomap.h>
+#include <linux/nfs4.h>
+
+#include "nfsd.h"
+#include "blocklayoutxdr.h"
+#include "vfs.h"
+
+#define NFSDDBG_FACILITY	NFSDDBG_PNFS
+
+
+/**
+ * nfsd4_block_encode_layoutget - encode block/scsi layout extent array
+ * @xdr: stream for data encoding
+ * @lgp: layoutget content, actually an array of extents to encode
+ *
+ * Encode the opaque loc_body field in the layoutget response. Since the
+ * pnfs_block_layout4 and pnfs_scsi_layout4 structures on the wire are
+ * the same, this function is used by both layout drivers.
+ *
+ * Return values:
+ *   %nfs_ok: Success, all extents encoded into @xdr
+ *   %nfserr_toosmall: Not enough space in @xdr to encode all the data
+ */
+__be32
+nfsd4_block_encode_layoutget(struct xdr_stream *xdr,
+		const struct nfsd4_layoutget *lgp)
+{
+	const struct pnfs_block_layout *bl = lgp->lg_content;
+	u32 i, len = sizeof(__be32) + bl->nr_extents * PNFS_BLOCK_EXTENT_SIZE;
+	__be32 *p;
+
+	p = xdr_reserve_space(xdr, sizeof(__be32) + len);
+	if (!p)
+		return nfserr_toosmall;
+
+	*p++ = cpu_to_be32(len);
+	*p++ = cpu_to_be32(bl->nr_extents);
+
+	for (i = 0; i < bl->nr_extents; i++) {
+		const struct pnfs_block_extent *bex = bl->extents + i;
+
+		p = svcxdr_encode_deviceid4(p, &bex->vol_id);
+		p = xdr_encode_hyper(p, bex->foff);
+		p = xdr_encode_hyper(p, bex->len);
+		p = xdr_encode_hyper(p, bex->soff);
+		*p++ = cpu_to_be32(bex->es);
+	}
+
+	return nfs_ok;
+}
+
+static int
+nfsd4_block_encode_volume(struct xdr_stream *xdr, struct pnfs_block_volume *b)
+{
+	__be32 *p;
+	int len;
+
+	switch (b->type) {
+	case PNFS_BLOCK_VOLUME_SIMPLE:
+		len = 4 + 4 + 8 + 4 + (XDR_QUADLEN(b->simple.sig_len) << 2);
+		p = xdr_reserve_space(xdr, len);
+		if (!p)
+			return -ETOOSMALL;
+
+		*p++ = cpu_to_be32(b->type);
+		*p++ = cpu_to_be32(1);	/* single signature */
+		p = xdr_encode_hyper(p, b->simple.offset);
+		p = xdr_encode_opaque(p, b->simple.sig, b->simple.sig_len);
+		break;
+	case PNFS_BLOCK_VOLUME_SCSI:
+		len = 4 + 4 + 4 + 4 + (XDR_QUADLEN(b->scsi.designator_len) << 2) + 8;
+		p = xdr_reserve_space(xdr, len);
+		if (!p)
+			return -ETOOSMALL;
+
+		*p++ = cpu_to_be32(b->type);
+		*p++ = cpu_to_be32(b->scsi.code_set);
+		*p++ = cpu_to_be32(b->scsi.designator_type);
+		p = xdr_encode_opaque(p, b->scsi.designator, b->scsi.designator_len);
+		p = xdr_encode_hyper(p, b->scsi.pr_key);
+		break;
+	default:
+		return -ENOTSUPP;
+	}
+
+	return len;
+}
+
+__be32
+nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr,
+		const struct nfsd4_getdeviceinfo *gdp)
+{
+	struct pnfs_block_deviceaddr *dev = gdp->gd_device;
+	int len = sizeof(__be32), ret, i;
+	__be32 *p;
+
+	/*
+	 * See paragraph 5 of RFC 8881 S18.40.3.
+	 */
+	if (!gdp->gd_maxcount) {
+		if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT)
+			return nfserr_resource;
+		return nfs_ok;
+	}
+
+	p = xdr_reserve_space(xdr, len + sizeof(__be32));
+	if (!p)
+		return nfserr_resource;
+
+	for (i = 0; i < dev->nr_volumes; i++) {
+		ret = nfsd4_block_encode_volume(xdr, &dev->volumes[i]);
+		if (ret < 0)
+			return nfserrno(ret);
+		len += ret;
+	}
+
+	/*
+	 * Fill in the overall length and number of volumes at the beginning
+	 * of the layout.
+	 */
+	*p++ = cpu_to_be32(len);
+	*p++ = cpu_to_be32(dev->nr_volumes);
+	return 0;
+}
+
+/**
+ * nfsd4_block_decode_layoutupdate - decode the block layout extent array
+ * @xdr: subbuf set to the encoded array
+ * @iomapp: pointer to store the decoded extent array
+ * @nr_iomapsp: pointer to store the number of extents
+ * @block_size: alignment of extent offset and length
+ *
+ * This function decodes the opaque field of the layoutupdate4 structure
+ * in a layoutcommit request for the block layout driver. The field is
+ * actually an array of extents sent by the client. It also checks that
+ * the file offset, storage offset and length of each extent are aligned
+ * by @block_size.
+ *
+ * Return values:
+ *   %nfs_ok: Successful decoding, @iomapp and @nr_iomapsp are valid
+ *   %nfserr_bad_xdr: The encoded array in @xdr is invalid
+ *   %nfserr_inval: An unaligned extent found
+ *   %nfserr_delay: Failed to allocate memory for @iomapp
+ */
+__be32
+nfsd4_block_decode_layoutupdate(struct xdr_stream *xdr, struct iomap **iomapp,
+		int *nr_iomapsp, u32 block_size)
+{
+	struct iomap *iomaps;
+	u32 nr_iomaps, expected, len, i;
+	__be32 nfserr;
+
+	if (xdr_stream_decode_u32(xdr, &nr_iomaps))
+		return nfserr_bad_xdr;
+
+	len = sizeof(__be32) + xdr_stream_remaining(xdr);
+	expected = sizeof(__be32) + nr_iomaps * PNFS_BLOCK_EXTENT_SIZE;
+	if (len != expected)
+		return nfserr_bad_xdr;
+
+	iomaps = kzalloc_objs(*iomaps, nr_iomaps);
+	if (!iomaps)
+		return nfserr_delay;
+
+	for (i = 0; i < nr_iomaps; i++) {
+		struct pnfs_block_extent bex;
+
+		if (nfsd4_decode_deviceid4(xdr, &bex.vol_id)) {
+			nfserr = nfserr_bad_xdr;
+			goto fail;
+		}
+
+		if (xdr_stream_decode_u64(xdr, &bex.foff)) {
+			nfserr = nfserr_bad_xdr;
+			goto fail;
+		}
+		if (bex.foff & (block_size - 1)) {
+			nfserr = nfserr_inval;
+			goto fail;
+		}
+
+		if (xdr_stream_decode_u64(xdr, &bex.len)) {
+			nfserr = nfserr_bad_xdr;
+			goto fail;
+		}
+		if (bex.len & (block_size - 1)) {
+			nfserr = nfserr_inval;
+			goto fail;
+		}
+
+		if (xdr_stream_decode_u64(xdr, &bex.soff)) {
+			nfserr = nfserr_bad_xdr;
+			goto fail;
+		}
+		if (bex.soff & (block_size - 1)) {
+			nfserr = nfserr_inval;
+			goto fail;
+		}
+
+		if (xdr_stream_decode_u32(xdr, &bex.es)) {
+			nfserr = nfserr_bad_xdr;
+			goto fail;
+		}
+		if (bex.es != PNFS_BLOCK_READWRITE_DATA) {
+			nfserr = nfserr_inval;
+			goto fail;
+		}
+
+		iomaps[i].offset = bex.foff;
+		iomaps[i].length = bex.len;
+	}
+
+	*iomapp = iomaps;
+	*nr_iomapsp = nr_iomaps;
+	return nfs_ok;
+fail:
+	kfree(iomaps);
+	return nfserr;
+}
+
+/**
+ * nfsd4_scsi_decode_layoutupdate - decode the scsi layout extent array
+ * @xdr: subbuf set to the encoded array
+ * @iomapp: pointer to store the decoded extent array
+ * @nr_iomapsp: pointer to store the number of extents
+ * @block_size: alignment of extent offset and length
+ *
+ * This function decodes the opaque field of the layoutupdate4 structure
+ * in a layoutcommit request for the scsi layout driver. The field is
+ * actually an array of extents sent by the client. It also checks that
+ * the offset and length of each extent are aligned by @block_size.
+ *
+ * Return values:
+ *   %nfs_ok: Successful decoding, @iomapp and @nr_iomapsp are valid
+ *   %nfserr_bad_xdr: The encoded array in @xdr is invalid
+ *   %nfserr_inval: An unaligned extent found
+ *   %nfserr_delay: Failed to allocate memory for @iomapp
+ */
+__be32
+nfsd4_scsi_decode_layoutupdate(struct xdr_stream *xdr, struct iomap **iomapp,
+		int *nr_iomapsp, u32 block_size)
+{
+	struct iomap *iomaps;
+	u32 nr_iomaps, expected, len, i;
+	__be32 nfserr;
+
+	if (xdr_stream_decode_u32(xdr, &nr_iomaps))
+		return nfserr_bad_xdr;
+
+	len = sizeof(__be32) + xdr_stream_remaining(xdr);
+	expected = sizeof(__be32) + nr_iomaps * PNFS_SCSI_RANGE_SIZE;
+	if (len != expected)
+		return nfserr_bad_xdr;
+
+	iomaps = kzalloc_objs(*iomaps, nr_iomaps);
+	if (!iomaps)
+		return nfserr_delay;
+
+	for (i = 0; i < nr_iomaps; i++) {
+		u64 val;
+
+		if (xdr_stream_decode_u64(xdr, &val)) {
+			nfserr = nfserr_bad_xdr;
+			goto fail;
+		}
+		if (val & (block_size - 1)) {
+			nfserr = nfserr_inval;
+			goto fail;
+		}
+		iomaps[i].offset = val;
+
+		if (xdr_stream_decode_u64(xdr, &val)) {
+			nfserr = nfserr_bad_xdr;
+			goto fail;
+		}
+		if (val & (block_size - 1)) {
+			nfserr = nfserr_inval;
+			goto fail;
+		}
+		iomaps[i].length = val;
+	}
+
+	*iomapp = iomaps;
+	*nr_iomapsp = nr_iomaps;
+	return nfs_ok;
+fail:
+	kfree(iomaps);
+	return nfserr;
+}

linux-7.2.3/fs/nfsd/blocklayoutxdr.h

@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _NFSD_BLOCKLAYOUTXDR_H
+#define _NFSD_BLOCKLAYOUTXDR_H 1
+
+#include <linux/blkdev.h>
+#include "xdr4.h"
+
+struct iomap;
+struct xdr_stream;
+
+/* On the wire size of the layout4 struct with zero number of extents */
+#define PNFS_BLOCK_LAYOUT4_SIZE \
+	(sizeof(__be32) * 2 +	/* offset4 */ \
+	 sizeof(__be32) * 2 +	/* length4 */ \
+	 sizeof(__be32) +	/* layoutiomode4 */ \
+	 sizeof(__be32) +	/* layouttype4 */ \
+	 sizeof(__be32) +	/* number of bytes */ \
+	 sizeof(__be32))	/* number of extents */
+
+struct pnfs_block_extent {
+	struct nfsd4_deviceid		vol_id;
+	u64				foff;
+	u64				len;
+	u64				soff;
+	enum pnfs_block_extent_state	es;
+};
+
+struct pnfs_block_range {
+	u64				foff;
+	u64				len;
+};
+
+struct pnfs_block_layout {
+	u32				nr_extents;
+	struct pnfs_block_extent	extents[] __counted_by(nr_extents);
+};
+
+/*
+ * Random upper cap for the uuid length to avoid unbounded allocation.
+ * Not actually limited by the protocol.
+ */
+#define PNFS_BLOCK_UUID_LEN	128
+
+struct pnfs_block_volume {
+	enum pnfs_block_volume_type	type;
+	union {
+		struct {
+			u64		offset;
+			u32		sig_len;
+			u8		sig[PNFS_BLOCK_UUID_LEN];
+		} simple;
+		struct {
+			enum scsi_code_set		code_set;
+			enum scsi_designator_type	designator_type;
+			int				designator_len;
+			u8				designator[256];
+			u64				pr_key;
+		} scsi;
+	};
+};
+
+struct pnfs_block_deviceaddr {
+	u32				nr_volumes;
+	struct pnfs_block_volume	volumes[] __counted_by(nr_volumes);
+};
+
+__be32 nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr,
+		const struct nfsd4_getdeviceinfo *gdp);
+__be32 nfsd4_block_encode_layoutget(struct xdr_stream *xdr,
+		const struct nfsd4_layoutget *lgp);
+__be32 nfsd4_block_decode_layoutupdate(struct xdr_stream *xdr,
+		struct iomap **iomapp, int *nr_iomapsp, u32 block_size);
+__be32 nfsd4_scsi_decode_layoutupdate(struct xdr_stream *xdr,
+		struct iomap **iomapp, int *nr_iomapsp, u32 block_size);
+
+#endif /* _NFSD_BLOCKLAYOUTXDR_H */

linux-7.2.3/fs/nfsd/cache.h

@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Request reply cache. This was heavily inspired by the
+ * implementation in 4.3BSD/4.4BSD.
+ *
+ * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#ifndef NFSCACHE_H
+#define NFSCACHE_H
+
+#include <linux/sunrpc/svc.h>
+#include "nfsd.h"
+
+/*
+ * Representation of a reply cache entry.
+ *
+ * Note that we use a sockaddr_in6 to hold the address instead of the more
+ * typical sockaddr_storage. This is for space reasons, since sockaddr_storage
+ * is much larger than a sockaddr_in6.
+ */
+struct nfsd_cacherep {
+	struct {
+		/* Keep often-read xid, csum in the same cache line: */
+		__be32			k_xid;
+		__wsum			k_csum;
+		u32			k_proc;
+		u32			k_prot;
+		u32			k_vers;
+		unsigned int		k_len;
+		struct sockaddr_in6	k_addr;
+	} c_key;
+
+	struct rb_node		c_node;
+	struct list_head	c_lru;
+	unsigned char		c_state,	/* unused, inprog, done */
+				c_type,		/* status, buffer */
+				c_secure : 1;	/* req came from port < 1024 */
+	unsigned long		c_timestamp;
+	union {
+		struct kvec	u_vec;
+		__be32		u_status;
+	}			c_u;
+};
+
+#define c_replvec		c_u.u_vec
+#define c_replstat		c_u.u_status
+
+/* cache entry states */
+enum {
+	RC_UNUSED,
+	RC_INPROG,
+	RC_DONE
+};
+
+/* return values */
+enum {
+	RC_DROPIT,
+	RC_REPLY,
+	RC_DOIT
+};
+
+/*
+ * Cache types.
+ * We may want to add more types one day, e.g. for diropres and
+ * attrstat replies. Using cache entries with fixed length instead
+ * of buffer pointers may be more efficient.
+ */
+enum {
+	RC_NOCACHE,
+	RC_REPLSTAT,
+	RC_REPLBUFF,
+};
+
+/* Cache entries expire after this time period */
+#define RC_EXPIRE		(120 * HZ)
+
+/* Checksum this amount of the request */
+#define RC_CSUMLEN		(256U)
+
+int	nfsd_drc_slab_create(void);
+void	nfsd_drc_slab_free(void);
+int	nfsd_reply_cache_init(struct nfsd_net *);
+void	nfsd_reply_cache_shutdown(struct nfsd_net *);
+int	nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start,
+			  unsigned int len, struct nfsd_cacherep **cacherep);
+void	nfsd_cache_update(struct svc_rqst *rqstp, struct nfsd_cacherep *rp,
+			  int cachetype, __be32 *statp);
+int	nfsd_reply_cache_stats_show(struct seq_file *m, void *v);
+
+#endif /* NFSCACHE_H */

linux-7.2.3/fs/nfsd/current_stateid.h

@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _NFSD4_CURRENT_STATE_H
+#define _NFSD4_CURRENT_STATE_H
+
+#include "state.h"
+#include "xdr4.h"
+
+extern void clear_current_stateid(struct nfsd4_compound_state *cstate);
+/*
+ * functions to set current state id
+ */
+extern void nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+extern void nfsd4_set_openstateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+extern void nfsd4_set_lockstateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+extern void nfsd4_set_closestateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+
+/*
+ * functions to consume current state id
+ */
+extern void nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+extern void nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+extern void nfsd4_get_freestateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+extern void nfsd4_get_setattrstateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+extern void nfsd4_get_closestateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+extern void nfsd4_get_lockustateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+extern void nfsd4_get_readstateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+extern void nfsd4_get_writestateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+
+#endif   /* _NFSD4_CURRENT_STATE_H */

linux-7.2.3/fs/nfsd/debugfs.c

@@ -0,0 +1,147 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/debugfs.h>
+
+#include "nfsd.h"
+
+static struct dentry *nfsd_top_dir __read_mostly;
+
+/*
+ * /sys/kernel/debug/nfsd/disable-splice-read
+ *
+ * Contents:
+ *   %0: NFS READ is allowed to use page splicing
+ *   %1: NFS READ uses only iov iter read
+ *
+ * The default value of this setting is zero (page splicing is
+ * allowed). This setting takes immediate effect for all NFS
+ * versions, all exports, and in all NFSD net namespaces.
+ */
+
+static int nfsd_dsr_get(void *data, u64 *val)
+{
+	*val = nfsd_disable_splice_read ? 1 : 0;
+	return 0;
+}
+
+static int nfsd_dsr_set(void *data, u64 val)
+{
+	nfsd_disable_splice_read = (val > 0);
+	if (!nfsd_disable_splice_read) {
+		/*
+		 * Must use buffered I/O if splice_read is enabled.
+		 */
+		nfsd_io_cache_read = NFSD_IO_BUFFERED;
+	}
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(nfsd_dsr_fops, nfsd_dsr_get, nfsd_dsr_set, "%llu\n");
+
+/*
+ * /sys/kernel/debug/nfsd/io_cache_read
+ *
+ * Contents:
+ *   %0: NFS READ will use buffered IO
+ *   %1: NFS READ will use dontcache (buffered IO w/ dropbehind)
+ *   %2: NFS READ will use direct IO
+ *
+ * This setting takes immediate effect for all NFS versions,
+ * all exports, and in all NFSD net namespaces.
+ */
+
+static int nfsd_io_cache_read_get(void *data, u64 *val)
+{
+	*val = nfsd_io_cache_read;
+	return 0;
+}
+
+static int nfsd_io_cache_read_set(void *data, u64 val)
+{
+	int ret = 0;
+
+	switch (val) {
+	case NFSD_IO_BUFFERED:
+		nfsd_io_cache_read = NFSD_IO_BUFFERED;
+		break;
+	case NFSD_IO_DONTCACHE:
+	case NFSD_IO_DIRECT:
+		/*
+		 * Must disable splice_read when enabling
+		 * NFSD_IO_DONTCACHE.
+		 */
+		nfsd_disable_splice_read = true;
+		nfsd_io_cache_read = val;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(nfsd_io_cache_read_fops, nfsd_io_cache_read_get,
+			 nfsd_io_cache_read_set, "%llu\n");
+
+/*
+ * /sys/kernel/debug/nfsd/io_cache_write
+ *
+ * Contents:
+ *   %0: NFS WRITE will use buffered IO
+ *   %1: NFS WRITE will use dontcache (buffered IO w/ dropbehind)
+ *
+ * This setting takes immediate effect for all NFS versions,
+ * all exports, and in all NFSD net namespaces.
+ */
+
+static int nfsd_io_cache_write_get(void *data, u64 *val)
+{
+	*val = nfsd_io_cache_write;
+	return 0;
+}
+
+static int nfsd_io_cache_write_set(void *data, u64 val)
+{
+	int ret = 0;
+
+	switch (val) {
+	case NFSD_IO_BUFFERED:
+	case NFSD_IO_DONTCACHE:
+	case NFSD_IO_DIRECT:
+		nfsd_io_cache_write = val;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(nfsd_io_cache_write_fops, nfsd_io_cache_write_get,
+			 nfsd_io_cache_write_set, "%llu\n");
+
+void nfsd_debugfs_exit(void)
+{
+	debugfs_remove_recursive(nfsd_top_dir);
+	nfsd_top_dir = NULL;
+}
+
+void nfsd_debugfs_init(void)
+{
+	nfsd_top_dir = debugfs_create_dir("nfsd", NULL);
+
+	debugfs_create_file("disable-splice-read", S_IWUSR | S_IRUGO,
+			    nfsd_top_dir, NULL, &nfsd_dsr_fops);
+
+	debugfs_create_file("io_cache_read", 0644, nfsd_top_dir, NULL,
+			    &nfsd_io_cache_read_fops);
+
+	debugfs_create_file("io_cache_write", 0644, nfsd_top_dir, NULL,
+			    &nfsd_io_cache_write_fops);
+#ifdef CONFIG_NFSD_V4
+	debugfs_create_bool("delegated_timestamps", 0644, nfsd_top_dir,
+			    &nfsd_delegts_enabled);
+#endif
+}

linux-7.2.3/fs/nfsd/export.h

@@ -0,0 +1,139 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 1995-1997 Olaf Kirch <okir@monad.swb.de>
+ */
+#ifndef NFSD_EXPORT_H
+#define NFSD_EXPORT_H
+
+#include <linux/sunrpc/cache.h>
+#include <linux/percpu_counter.h>
+#include <uapi/linux/nfsd/export.h>
+#include <linux/nfs4.h>
+
+struct knfsd_fh;
+struct svc_fh;
+struct svc_rqst;
+
+/*
+ * FS Locations
+ */
+
+#define MAX_FS_LOCATIONS	128
+
+struct nfsd4_fs_location {
+	char *hosts; /* colon separated list of hosts */
+	char *path;  /* slash separated list of path components */
+};
+
+struct nfsd4_fs_locations {
+	uint32_t locations_count;
+	struct nfsd4_fs_location *locations;
+/* If we're not actually serving this data ourselves (only providing a
+ * list of replicas that do serve it) then we set "migrated": */
+	int migrated;
+};
+
+/*
+ * We keep an array of pseudoflavors with the export, in order from most
+ * to least preferred.  For the foreseeable future, we don't expect more
+ * than the eight pseudoflavors null, unix, krb5, krb5i, krb5p, skpm3,
+ * spkm3i, and spkm3p (and using all 8 at once should be rare).
+ */
+#define MAX_SECINFO_LIST	8
+#define EX_UUID_LEN		16
+
+struct exp_flavor_info {
+	u32	pseudoflavor;
+	u32	flags;
+};
+
+/* Per-export stats */
+enum {
+	EXP_STATS_FH_STALE,
+	EXP_STATS_IO_READ,
+	EXP_STATS_IO_WRITE,
+	EXP_STATS_COUNTERS_NUM
+};
+
+struct export_stats {
+	time64_t		start_time;
+	struct percpu_counter	counter[EXP_STATS_COUNTERS_NUM];
+};
+
+struct svc_export {
+	struct cache_head	h;
+	struct auth_domain *	ex_client;
+	int			ex_flags;
+	int			ex_fsid;
+	struct path		ex_path;
+	kuid_t			ex_anon_uid;
+	kgid_t			ex_anon_gid;
+	unsigned char *		ex_uuid; /* 16 byte fsid */
+	struct nfsd4_fs_locations ex_fslocs;
+	uint32_t		ex_nflavors;
+	struct exp_flavor_info	ex_flavors[MAX_SECINFO_LIST];
+	u32			ex_layout_types;
+	struct nfsd4_deviceid_map *ex_devid_map;
+	struct cache_detail	*cd;
+	struct rcu_head		ex_rcu;
+	unsigned long		ex_xprtsec_modes;
+	struct export_stats	*ex_stats;
+};
+
+/* an "export key" (expkey) maps a filehandlefragement to an
+ * svc_export for a given client.  There can be several per export,
+ * for the different fsid types.
+ */
+struct svc_expkey {
+	struct cache_head	h;
+
+	struct auth_domain *	ek_client;
+	u8			ek_fsidtype;
+	u32			ek_fsid[6];
+
+	struct path		ek_path;
+	struct rcu_head		ek_rcu;
+};
+
+#define EX_ISSYNC(exp)		(!((exp)->ex_flags & NFSEXP_ASYNC))
+#define EX_NOHIDE(exp)		((exp)->ex_flags & NFSEXP_NOHIDE)
+#define EX_WGATHER(exp)		((exp)->ex_flags & NFSEXP_GATHERED_WRITES)
+
+struct svc_cred;
+int nfsexp_flags(struct svc_cred *cred, struct svc_export *exp);
+__be32 check_xprtsec_policy(struct svc_export *exp, struct svc_rqst *rqstp);
+__be32 check_security_flavor(struct svc_export *exp, struct svc_rqst *rqstp,
+			     bool may_bypass_gss);
+__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp,
+			 bool may_bypass_gss);
+
+/*
+ * Function declarations
+ */
+int			nfsd_export_init(struct net *);
+void			nfsd_export_shutdown(struct net *);
+void			nfsd_export_flush(struct net *);
+struct svc_export *	rqst_exp_get_by_name(struct svc_rqst *,
+					     const struct path *);
+struct svc_export *	rqst_exp_parent(struct svc_rqst *,
+					struct path *);
+struct svc_export *	rqst_find_fsidzero_export(struct svc_rqst *);
+int			exp_rootfh(struct net *, struct auth_domain *,
+					char *path, struct knfsd_fh *, int maxsize);
+__be32			exp_pseudoroot(struct svc_rqst *, struct svc_fh *);
+
+static inline void exp_put(struct svc_export *exp)
+{
+	cache_put(&exp->h, exp->cd);
+}
+
+static inline struct svc_export *exp_get(struct svc_export *exp)
+{
+	cache_get(&exp->h);
+	return exp;
+}
+struct svc_export *rqst_exp_find(struct cache_req *reqp, struct net *net,
+				 struct auth_domain *cl, struct auth_domain *gsscl,
+				 int fsid_type, u32 *fsidv);
+
+#endif /* NFSD_EXPORT_H */

linux-7.2.3/fs/nfsd/filecache.h

@@ -0,0 +1,89 @@
+#ifndef _FS_NFSD_FILECACHE_H
+#define _FS_NFSD_FILECACHE_H
+
+#include <linux/fsnotify_backend.h>
+
+/*
+ * Limit the time that the list_lru_one lock is held during
+ * an LRU scan.
+ */
+#define NFSD_FILE_GC_BATCH     (16UL)
+
+/*
+ * This is the fsnotify_mark container that nfsd attaches to the files that it
+ * is holding open. Note that we have a separate refcount here aside from the
+ * one in the fsnotify_mark. We only want a single fsnotify_mark attached to
+ * the inode, and for each nfsd_file to hold a reference to it.
+ *
+ * The fsnotify_mark is itself refcounted, but that's not sufficient to tell us
+ * how to put that reference. If there are still outstanding nfsd_files that
+ * reference the mark, then we would want to call fsnotify_put_mark on it.
+ * If there were not, then we'd need to call fsnotify_destroy_mark. Since we
+ * can't really tell the difference, we use the nfm_mark to keep track of how
+ * many nfsd_files hold references to the mark. When that counter goes to zero
+ * then we know to call fsnotify_destroy_mark on it.
+ */
+struct nfsd_file_mark {
+	struct fsnotify_mark	nfm_mark;
+	refcount_t		nfm_ref;
+};
+
+/*
+ * A representation of a file that has been opened by knfsd. These are hashed
+ * in the hashtable by inode pointer value. Note that this object doesn't
+ * hold a reference to the inode by itself, so the nf_inode pointer should
+ * never be dereferenced, only used for comparison.
+ */
+struct nfsd_file {
+	struct rhlist_head	nf_rlist;
+	void			*nf_inode;
+	struct file		*nf_file;
+	const struct cred	*nf_cred;
+	struct net		*nf_net;
+#define NFSD_FILE_HASHED	(0)
+#define NFSD_FILE_PENDING	(1)
+#define NFSD_FILE_REFERENCED	(2)
+#define NFSD_FILE_GC		(3)
+#define NFSD_FILE_RECENT	(4)
+	unsigned long		nf_flags;
+	refcount_t		nf_ref;
+	unsigned char		nf_may;
+
+	struct nfsd_file_mark	*nf_mark;
+	struct list_head	nf_lru;
+	struct list_head	nf_gc;
+	struct rcu_head		nf_rcu;
+	ktime_t			nf_birthtime;
+
+	u32			nf_dio_mem_align;
+	u32			nf_dio_offset_align;
+	u32			nf_dio_read_offset_align;
+};
+
+int nfsd_file_cache_init(void);
+void nfsd_file_cache_purge(struct net *);
+void nfsd_file_cache_shutdown(void);
+int nfsd_file_cache_start_net(struct net *net);
+void nfsd_file_cache_shutdown_net(struct net *net);
+void nfsd_file_put(struct nfsd_file *nf);
+struct net *nfsd_file_put_local(struct nfsd_file __rcu **nf);
+struct nfsd_file *nfsd_file_get(struct nfsd_file *nf);
+struct file *nfsd_file_file(struct nfsd_file *nf);
+void nfsd_file_close_inode_sync(struct inode *inode);
+void nfsd_file_close_export(struct net *net, const struct path *path);
+void nfsd_file_net_dispose(struct nfsd_net *nn);
+bool nfsd_file_is_cached(struct inode *inode);
+__be32 nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		  unsigned int may_flags, struct nfsd_file **nfp);
+__be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		  unsigned int may_flags, struct nfsd_file **nfp);
+__be32 nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		  unsigned int may_flags, struct file *file,
+		  struct nfsd_file **nfp);
+__be32 nfsd_file_acquire_local(struct net *net, struct svc_cred *cred,
+			       struct auth_domain *client, struct svc_fh *fhp,
+			       unsigned int may_flags, struct nfsd_file **pnf);
+__be32 nfsd_file_acquire_dir(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		  struct nfsd_file **pnf);
+int nfsd_file_cache_stats_show(struct seq_file *m, void *v);
+#endif /* _FS_NFSD_FILECACHE_H */

linux-7.2.3/fs/nfsd/flexfilelayout.c

@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2016 Tom Haynes <loghyr@primarydata.com>
+ *
+ * The following implements a super-simple flex-file server
+ * where the NFSv4.1 mds is also the ds. And the storage is
+ * the same. I.e., writing to the mds via a NFSv4.1 WRITE
+ * goes to the same location as the NFSv3 WRITE.
+ */
+#include <linux/slab.h>
+
+#include <linux/nfsd/debug.h>
+
+#include <linux/sunrpc/addr.h>
+
+#include "flexfilelayoutxdr.h"
+#include "pnfs.h"
+#include "vfs.h"
+
+#define NFSDDBG_FACILITY	NFSDDBG_PNFS
+
+static __be32
+nfsd4_ff_proc_layoutget(struct svc_rqst *rqstp, struct inode *inode,
+		const struct svc_fh *fhp, struct nfsd4_layoutget *args)
+{
+	struct nfsd4_layout_seg *seg = &args->lg_seg;
+	u32 device_generation = 0;
+	int error;
+	uid_t u;
+
+	struct pnfs_ff_layout *fl;
+
+	/*
+	 * The super simple flex file server has 1 mirror, 1 data server,
+	 * and 1 file handle. So instead of 4 allocs, do 1 for now.
+	 * Zero it out for the stateid - don't want junk in there!
+	 */
+	error = -ENOMEM;
+	fl = kzalloc_obj(*fl);
+	if (!fl)
+		goto out_error;
+	args->lg_content = fl;
+
+	/*
+	 * Avoid layout commit, try to force the I/O to the DS,
+	 * and for fun, cause all IOMODE_RW layout segments to
+	 * effectively be WRITE only.
+	 */
+	fl->flags = FF_FLAGS_NO_LAYOUTCOMMIT | FF_FLAGS_NO_IO_THRU_MDS |
+		    FF_FLAGS_NO_READ_IO;
+
+	/* Do not allow a IOMODE_READ segment to have write pemissions */
+	if (seg->iomode == IOMODE_READ) {
+		u = from_kuid(&init_user_ns, inode->i_uid) + 1;
+		fl->uid = make_kuid(&init_user_ns, u);
+	} else
+		fl->uid = inode->i_uid;
+	fl->gid = inode->i_gid;
+
+	error = nfsd4_set_deviceid(&fl->deviceid, fhp, device_generation);
+	if (error)
+		goto out_error;
+
+	fl->fh.size = fhp->fh_handle.fh_size;
+	memcpy(fl->fh.data, &fhp->fh_handle.fh_raw, fl->fh.size);
+
+	/* Give whole file layout segments */
+	seg->offset = 0;
+	seg->length = NFS4_MAX_UINT64;
+
+	dprintk("GET: 0x%llx:0x%llx %d\n", seg->offset, seg->length,
+		seg->iomode);
+	return 0;
+
+out_error:
+	seg->length = 0;
+	return nfserrno(error);
+}
+
+static __be32
+nfsd4_ff_proc_getdeviceinfo(struct super_block *sb, struct svc_rqst *rqstp,
+		struct nfs4_client *clp, struct nfsd4_getdeviceinfo *gdp)
+{
+	struct pnfs_ff_device_addr *da;
+
+	u16 port;
+	char addr[INET6_ADDRSTRLEN];
+
+	da = kzalloc_obj(struct pnfs_ff_device_addr);
+	if (!da)
+		return nfserrno(-ENOMEM);
+
+	gdp->gd_device = da;
+
+	da->version = 3;
+	da->minor_version = 0;
+
+	da->rsize = svc_max_payload(rqstp);
+	da->wsize = da->rsize;
+
+	rpc_ntop((struct sockaddr *)&rqstp->rq_daddr,
+		 addr, INET6_ADDRSTRLEN);
+	if (rqstp->rq_daddr.ss_family == AF_INET) {
+		struct sockaddr_in *sin;
+
+		sin = (struct sockaddr_in *)&rqstp->rq_daddr;
+		port = ntohs(sin->sin_port);
+		snprintf(da->netaddr.netid, FF_NETID_LEN + 1, "tcp");
+		da->netaddr.netid_len = 3;
+	} else {
+		struct sockaddr_in6 *sin6;
+
+		sin6 = (struct sockaddr_in6 *)&rqstp->rq_daddr;
+		port = ntohs(sin6->sin6_port);
+		snprintf(da->netaddr.netid, FF_NETID_LEN + 1, "tcp6");
+		da->netaddr.netid_len = 4;
+	}
+
+	da->netaddr.addr_len =
+		snprintf(da->netaddr.addr, FF_ADDR_LEN + 1,
+			 "%s.%d.%d", addr, port >> 8, port & 0xff);
+
+	da->tightly_coupled = false;
+
+	return 0;
+}
+
+static __be32
+nfsd4_ff_proc_layoutcommit(struct inode *inode, struct svc_rqst *rqstp,
+		struct nfsd4_layoutcommit *lcp)
+{
+	return nfs_ok;
+}
+
+const struct nfsd4_layout_ops ff_layout_ops = {
+	.notify_types		=
+			NOTIFY_DEVICEID4_DELETE | NOTIFY_DEVICEID4_CHANGE,
+	.disable_recalls	= true,
+	.proc_getdeviceinfo	= nfsd4_ff_proc_getdeviceinfo,
+	.encode_getdeviceinfo	= nfsd4_ff_encode_getdeviceinfo,
+	.proc_layoutget		= nfsd4_ff_proc_layoutget,
+	.encode_layoutget	= nfsd4_ff_encode_layoutget,
+	.proc_layoutcommit	= nfsd4_ff_proc_layoutcommit,
+};

linux-7.2.3/fs/nfsd/flexfilelayoutxdr.c

@@ -0,0 +1,124 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2016 Tom Haynes <loghyr@primarydata.com>
+ */
+#include <linux/sunrpc/svc.h>
+#include <linux/nfs4.h>
+
+#include "nfsd.h"
+#include "flexfilelayoutxdr.h"
+
+#define NFSDDBG_FACILITY	NFSDDBG_PNFS
+
+struct ff_idmap {
+	char buf[11];
+	int len;
+};
+
+__be32
+nfsd4_ff_encode_layoutget(struct xdr_stream *xdr,
+		const struct nfsd4_layoutget *lgp)
+{
+	const struct pnfs_ff_layout *fl = lgp->lg_content;
+	int len, mirror_len, ds_len, fh_len;
+	__be32 *p;
+
+	/*
+	 * Unlike nfsd4_encode_user, we know these will
+	 * always be stringified.
+	 */
+	struct ff_idmap uid;
+	struct ff_idmap gid;
+
+	fh_len = 4 + fl->fh.size;
+
+	uid.len = sprintf(uid.buf, "%u", from_kuid(&init_user_ns, fl->uid));
+	gid.len = sprintf(gid.buf, "%u", from_kgid(&init_user_ns, fl->gid));
+
+	/* 8 + len for recording the length, name, and padding */
+	ds_len = 20 + sizeof(stateid_opaque_t) + 4 + fh_len +
+		 8 + uid.len + 8 + gid.len;
+
+	mirror_len = 4 + ds_len;
+
+	/* The layout segment */
+	len = 20 + mirror_len;
+
+	p = xdr_reserve_space(xdr, sizeof(__be32) + len);
+	if (!p)
+		return nfserr_toosmall;
+
+	*p++ = cpu_to_be32(len);
+	p = xdr_encode_hyper(p, 0);		/* stripe unit of 1 */
+
+	*p++ = cpu_to_be32(1);			/* single mirror */
+	*p++ = cpu_to_be32(1);			/* single data server */
+
+	p = svcxdr_encode_deviceid4(p, &fl->deviceid);
+
+	*p++ = cpu_to_be32(1);			/* efficiency */
+
+	*p++ = cpu_to_be32(fl->stateid.si_generation);
+	p = xdr_encode_opaque_fixed(p, &fl->stateid.si_opaque,
+				    sizeof(stateid_opaque_t));
+
+	*p++ = cpu_to_be32(1);			/* single file handle */
+	p = xdr_encode_opaque(p, fl->fh.data, fl->fh.size);
+
+	p = xdr_encode_opaque(p, uid.buf, uid.len);
+	p = xdr_encode_opaque(p, gid.buf, gid.len);
+
+	*p++ = cpu_to_be32(fl->flags);
+	*p++ = cpu_to_be32(0);			/* No stats collect hint */
+
+	return 0;
+}
+
+__be32
+nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr,
+		const struct nfsd4_getdeviceinfo *gdp)
+{
+	struct pnfs_ff_device_addr *da = gdp->gd_device;
+	int len;
+	int ver_len;
+	int addr_len;
+	__be32 *p;
+
+	/*
+	 * See paragraph 5 of RFC 8881 S18.40.3.
+	 */
+	if (!gdp->gd_maxcount) {
+		if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT)
+			return nfserr_resource;
+		return nfs_ok;
+	}
+
+	/* len + padding for two strings */
+	addr_len = 16 + da->netaddr.netid_len + da->netaddr.addr_len;
+	ver_len = 20;
+
+	len = 4 + ver_len + 4 + addr_len;
+
+	p = xdr_reserve_space(xdr, len + sizeof(__be32));
+	if (!p)
+		return nfserr_resource;
+
+	/*
+	 * Fill in the overall length and number of volumes at the beginning
+	 * of the layout.
+	 */
+	*p++ = cpu_to_be32(len);
+	*p++ = cpu_to_be32(1);			/* 1 netaddr */
+	p = xdr_encode_opaque(p, da->netaddr.netid, da->netaddr.netid_len);
+	p = xdr_encode_opaque(p, da->netaddr.addr, da->netaddr.addr_len);
+
+	*p++ = cpu_to_be32(1);			/* 1 versions */
+
+	*p++ = cpu_to_be32(da->version);
+	*p++ = cpu_to_be32(da->minor_version);
+	*p++ = cpu_to_be32(da->rsize);
+	*p++ = cpu_to_be32(da->wsize);
+	*p++ = cpu_to_be32(da->tightly_coupled);
+
+	return 0;
+}

linux-7.2.3/fs/nfsd/flexfilelayoutxdr.h

@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2016 Tom Haynes <loghyr@primarydata.com>
+ */
+#ifndef _NFSD_FLEXFILELAYOUTXDR_H
+#define _NFSD_FLEXFILELAYOUTXDR_H 1
+
+#include <linux/inet.h>
+#include "xdr4.h"
+
+#define FF_FLAGS_NO_LAYOUTCOMMIT 1
+#define FF_FLAGS_NO_IO_THRU_MDS  2
+#define FF_FLAGS_NO_READ_IO      4
+
+struct xdr_stream;
+
+#define FF_NETID_LEN		(4)
+#define FF_ADDR_LEN		(INET6_ADDRSTRLEN + 8)
+struct pnfs_ff_netaddr {
+	char				netid[FF_NETID_LEN + 1];
+	char				addr[FF_ADDR_LEN + 1];
+	u32				netid_len;
+	u32				addr_len;
+};
+
+struct pnfs_ff_device_addr {
+	struct pnfs_ff_netaddr		netaddr;
+	u32				version;
+	u32				minor_version;
+	u32				rsize;
+	u32				wsize;
+	bool				tightly_coupled;
+};
+
+struct pnfs_ff_layout {
+	u32				flags;
+	u32				stats_collect_hint;
+	kuid_t				uid;
+	kgid_t				gid;
+	struct nfsd4_deviceid		deviceid;
+	stateid_t			stateid;
+	struct nfs_fh			fh;
+};
+
+__be32 nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr,
+		const struct nfsd4_getdeviceinfo *gdp);
+__be32 nfsd4_ff_encode_layoutget(struct xdr_stream *xdr,
+		const struct nfsd4_layoutget *lgp);
+
+#endif /* _NFSD_FLEXFILELAYOUTXDR_H */

linux-7.2.3/fs/nfsd/idmap.h

@@ -0,0 +1,60 @@
+/*
+ *  Mapping of UID to name and vice versa.
+ *
+ *  Copyright (c) 2002, 2003 The Regents of the University of
+ *  Michigan.  All rights reserved.
+> *
+ *  Marius Aamodt Eriksen <marius@umich.edu>
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the University nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef LINUX_NFSD_IDMAP_H
+#define LINUX_NFSD_IDMAP_H
+
+#include <linux/in.h>
+#include <linux/sunrpc/svc.h>
+#include <linux/nfs_idmap.h>
+
+#ifdef CONFIG_NFSD_V4
+int nfsd_idmap_init(struct net *);
+void nfsd_idmap_shutdown(struct net *);
+#else
+static inline int nfsd_idmap_init(struct net *net)
+{
+	return 0;
+}
+static inline void nfsd_idmap_shutdown(struct net *net)
+{
+}
+#endif
+
+__be32 nfsd_map_name_to_uid(struct svc_rqst *, const char *, size_t, kuid_t *);
+__be32 nfsd_map_name_to_gid(struct svc_rqst *, const char *, size_t, kgid_t *);
+__be32 nfsd4_encode_user(struct xdr_stream *, struct svc_rqst *, kuid_t);
+__be32 nfsd4_encode_group(struct xdr_stream *, struct svc_rqst *, kgid_t);
+
+#endif /* LINUX_NFSD_IDMAP_H */

linux-7.2.3/fs/nfsd/localio.c

@@ -0,0 +1,217 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * NFS server 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/exportfs.h>
+#include <linux/sunrpc/svcauth.h>
+#include <linux/sunrpc/clnt.h>
+#include <linux/nfs.h>
+#include <linux/nfs_common.h>
+#include <linux/nfslocalio.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_xdr.h>
+#include <linux/string.h>
+
+#include "nfsd.h"
+#include "vfs.h"
+#include "netns.h"
+#include "filecache.h"
+#include "cache.h"
+
+/**
+ * nfsd_open_local_fh - lookup a local filehandle @nfs_fh and map to nfsd_file
+ *
+ * @net: 'struct net' to get the proper nfsd_net required for LOCALIO access
+ * @dom: 'struct auth_domain' required for LOCALIO access
+ * @rpc_clnt: rpc_clnt that the client established
+ * @cred: cred that the client established
+ * @nfs_fh: filehandle to lookup
+ * @pnf: place to find the nfsd_file, or store it if it was non-NULL
+ * @fmode: fmode_t to use for open
+ *
+ * This function maps a local fh to a path on a local filesystem.
+ * This is useful when the nfs client has the local server mounted - it can
+ * avoid all the NFS overhead with reads, writes and commits.
+ *
+ * On successful return, returned nfsd_file will have its nf_net member
+ * set. Caller (NFS client) is responsible for calling nfsd_net_put and
+ * nfsd_file_put (via nfs_to_nfsd_file_put_local).
+ */
+static struct nfsd_file *
+nfsd_open_local_fh(struct net *net, struct auth_domain *dom,
+		   struct rpc_clnt *rpc_clnt, const struct cred *cred,
+		   const struct nfs_fh *nfs_fh, struct nfsd_file __rcu **pnf,
+		   const fmode_t fmode)
+{
+	int mayflags = NFSD_MAY_LOCALIO;
+	struct svc_cred rq_cred;
+	struct svc_fh fh;
+	struct nfsd_file *localio;
+	__be32 beres;
+
+	if (nfs_fh->size > NFS4_FHSIZE)
+		return ERR_PTR(-EINVAL);
+
+	if (!nfsd_net_try_get(net))
+		return ERR_PTR(-ENXIO);
+
+	rcu_read_lock();
+	localio = nfsd_file_get(rcu_dereference(*pnf));
+	rcu_read_unlock();
+	if (localio)
+		return localio;
+
+	/* nfs_fh -> svc_fh */
+	fh_init(&fh, NFS4_FHSIZE);
+	fh.fh_handle.fh_size = nfs_fh->size;
+	memcpy(fh.fh_handle.fh_raw, nfs_fh->data, nfs_fh->size);
+
+	if (fmode & FMODE_READ)
+		mayflags |= NFSD_MAY_READ;
+	if (fmode & FMODE_WRITE)
+		mayflags |= NFSD_MAY_WRITE;
+
+	svcauth_map_clnt_to_svc_cred_local(rpc_clnt, cred, &rq_cred);
+
+	beres = nfsd_file_acquire_local(net, &rq_cred, dom,
+					&fh, mayflags, &localio);
+	if (beres)
+		localio = ERR_PTR(nfs_stat_to_errno(be32_to_cpu(beres)));
+
+	fh_put(&fh);
+	if (rq_cred.cr_group_info)
+		put_group_info(rq_cred.cr_group_info);
+
+	if (!IS_ERR(localio)) {
+		struct nfsd_file *new;
+		if (!nfsd_net_try_get(net)) {
+			nfsd_file_put(localio);
+			nfsd_net_put(net);
+			return ERR_PTR(-ENXIO);
+		}
+		nfsd_file_get(localio);
+	again:
+		new = unrcu_pointer(cmpxchg(pnf, NULL, RCU_INITIALIZER(localio)));
+		if (new) {
+			/* Some other thread installed an nfsd_file */
+			if (nfsd_file_get(new) == NULL)
+				goto again;
+			/*
+			 * Drop the ref we were going to install (both file and
+			 * net) and the one we were going to return (only file).
+			 */
+			nfsd_file_put(localio);
+			nfsd_net_put(net);
+			nfsd_file_put(localio);
+			localio = new;
+		}
+	} else
+		nfsd_net_put(net);
+
+	return localio;
+}
+
+static void nfsd_file_dio_alignment(struct nfsd_file *nf,
+				    u32 *nf_dio_mem_align,
+				    u32 *nf_dio_offset_align,
+				    u32 *nf_dio_read_offset_align)
+{
+	*nf_dio_mem_align = nf->nf_dio_mem_align;
+	*nf_dio_offset_align = nf->nf_dio_offset_align;
+	*nf_dio_read_offset_align = nf->nf_dio_read_offset_align;
+}
+
+static const struct nfsd_localio_operations nfsd_localio_ops = {
+	.nfsd_net_try_get  = nfsd_net_try_get,
+	.nfsd_net_put  = nfsd_net_put,
+	.nfsd_open_local_fh = nfsd_open_local_fh,
+	.nfsd_file_put_local = nfsd_file_put_local,
+	.nfsd_file_file = nfsd_file_file,
+	.nfsd_file_dio_alignment = nfsd_file_dio_alignment,
+};
+
+void nfsd_localio_ops_init(void)
+{
+	nfs_to = &nfsd_localio_ops;
+}
+
+/*
+ * UUID_IS_LOCAL XDR functions
+ */
+
+static __be32 localio_proc_null(struct svc_rqst *rqstp)
+{
+	return rpc_success;
+}
+
+struct localio_uuidarg {
+	uuid_t			uuid;
+};
+
+static __be32 localio_proc_uuid_is_local(struct svc_rqst *rqstp)
+{
+	struct localio_uuidarg *argp = rqstp->rq_argp;
+	struct net *net = SVC_NET(rqstp);
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	nfs_uuid_is_local(&argp->uuid, &nn->local_clients,
+			  &nn->local_clients_lock,
+			  net, rqstp->rq_client, THIS_MODULE);
+
+	return rpc_success;
+}
+
+static bool localio_decode_uuidarg(struct svc_rqst *rqstp,
+				   struct xdr_stream *xdr)
+{
+	struct localio_uuidarg *argp = rqstp->rq_argp;
+	u8 uuid[UUID_SIZE];
+
+	if (decode_opaque_fixed(xdr, uuid, UUID_SIZE))
+		return false;
+	import_uuid(&argp->uuid, uuid);
+
+	return true;
+}
+
+static const struct svc_procedure localio_procedures1[] = {
+	[LOCALIOPROC_NULL] = {
+		.pc_func = localio_proc_null,
+		.pc_decode = nfssvc_decode_voidarg,
+		.pc_encode = nfssvc_encode_voidres,
+		.pc_argsize = sizeof(struct nfsd_voidargs),
+		.pc_ressize = sizeof(struct nfsd_voidres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = 0,
+		.pc_name = "NULL",
+	},
+	[LOCALIOPROC_UUID_IS_LOCAL] = {
+		.pc_func = localio_proc_uuid_is_local,
+		.pc_decode = localio_decode_uuidarg,
+		.pc_encode = nfssvc_encode_voidres,
+		.pc_argsize = sizeof(struct localio_uuidarg),
+		.pc_argzero = sizeof(struct localio_uuidarg),
+		.pc_ressize = sizeof(struct nfsd_voidres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_name = "UUID_IS_LOCAL",
+	},
+};
+
+#define LOCALIO_NR_PROCEDURES ARRAY_SIZE(localio_procedures1)
+static DEFINE_PER_CPU_ALIGNED(unsigned long,
+			      localio_count[LOCALIO_NR_PROCEDURES]);
+const struct svc_version localio_version1 = {
+	.vs_vers	= 1,
+	.vs_nproc	= LOCALIO_NR_PROCEDURES,
+	.vs_proc	= localio_procedures1,
+	.vs_dispatch	= nfsd_dispatch,
+	.vs_count	= localio_count,
+	.vs_xdrsize	= XDR_QUADLEN(UUID_SIZE),
+	.vs_hidden	= true,
+};

linux-7.2.3/fs/nfsd/lockd.c

@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This file contains all the stubs needed when communicating with lockd.
+ * This level of indirection is necessary so we can run nfsd+lockd without
+ * requiring the nfs client to be compiled in/loaded, and vice versa.
+ *
+ * Copyright (C) 1996, Olaf Kirch <okir@monad.swb.de>
+ */
+
+#include <linux/file.h>
+#include <linux/lockd/bind.h>
+#include "nfsd.h"
+#include "vfs.h"
+
+#define NFSDDBG_FACILITY		NFSDDBG_LOCKD
+
+/**
+ * nlm_fopen - Open an NFSD file
+ * @rqstp: NLM RPC procedure execution context
+ * @f: NFS file handle to be opened
+ * @filp: OUT: an opened struct file
+ * @flags: the POSIX open flags to use
+ *
+ * nlm_fopen() holds the dentry reference until nlm_fclose() releases it.
+ *
+ * Returns zero on success or a negative errno value if the file
+ * cannot be opened.
+ */
+static int nlm_fopen(struct svc_rqst *rqstp, struct nfs_fh *f,
+		     struct file **filp, int flags)
+{
+	__be32		nfserr;
+	int		access;
+	struct svc_fh	fh;
+
+	/* must initialize before using! but maxsize doesn't matter */
+	fh_init(&fh,0);
+	fh.fh_handle.fh_size = f->size;
+	memcpy(&fh.fh_handle.fh_raw, f->data, f->size);
+	fh.fh_export = NULL;
+
+	/*
+	 * Allow BYPASS_GSS as some client implementations use AUTH_SYS
+	 * for NLM even when GSS is used for NFS.
+	 * Allow OWNER_OVERRIDE as permission might have been changed
+	 * after the file was opened.
+	 * Pass MAY_NLM so that authentication can be completely bypassed
+	 * if NFSEXP_NOAUTHNLM is set.  Some older clients use AUTH_NULL
+	 * for NLM requests.
+	 */
+	access = (flags == O_WRONLY) ? NFSD_MAY_WRITE : NFSD_MAY_READ;
+	access |= NFSD_MAY_NLM | NFSD_MAY_OWNER_OVERRIDE | NFSD_MAY_BYPASS_GSS;
+	nfserr = nfsd_open(rqstp, &fh, S_IFREG, access, filp);
+	fh_put(&fh);
+
+	switch (nfserr) {
+	case nfs_ok:
+		break;
+	case nfserr_jukebox:
+		/*
+		 * This error can indicate a presence of a conflicting
+		 * delegation to an NLM lock request. Options are:
+		 * (1) For now, drop this request and make the client
+		 * retry. When delegation is returned, client's lock retry
+		 * will complete.
+		 * (2) NLM4_DENIED as per "spec" signals to the client
+		 * that the lock is unavailable now but client can retry.
+		 * Linux client implementation does not. It treats
+		 * NLM4_DENIED same as NLM4_FAILED and fails the request.
+		 * (3) For the future, treat this as blocked lock and try
+		 * to callback when the delegation is returned but might
+		 * not have a proper lock request to block on.
+		 */
+		return -EWOULDBLOCK;
+	case nfserr_stale:
+		return -ESTALE;
+	default:
+		return -ENOLCK;
+	}
+
+	return 0;
+}
+
+/**
+ * nlm_fclose - Close an NFSD file
+ * @filp: a struct file that was opened by nlm_fopen()
+ */
+static void
+nlm_fclose(struct file *filp)
+{
+	fput(filp);
+}
+
+static const struct nlmsvc_binding nfsd_nlm_ops = {
+	.fopen		= nlm_fopen,		/* open file for locking */
+	.fclose		= nlm_fclose,		/* close file */
+};
+
+void
+nfsd_lockd_init(void)
+{
+	dprintk("nfsd: initializing lockd\n");
+	nlmsvc_ops = &nfsd_nlm_ops;
+}
+
+void
+nfsd_lockd_shutdown(void)
+{
+	nlmsvc_ops = NULL;
+}

linux-7.2.3/fs/nfsd/netlink.c

@@ -0,0 +1,245 @@
+// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/nfsd.yaml */
+/* YNL-GEN kernel source */
+/* To regenerate run: tools/net/ynl/ynl-regen.sh */
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include "netlink.h"
+
+#include <uapi/linux/nfsd_netlink.h>
+
+/* Common nested types */
+const struct nla_policy nfsd_auth_flavor_nl_policy[NFSD_A_AUTH_FLAVOR_FLAGS + 1] = {
+	[NFSD_A_AUTH_FLAVOR_PSEUDOFLAVOR] = { .type = NLA_U32, },
+	[NFSD_A_AUTH_FLAVOR_FLAGS] = NLA_POLICY_MASK(NLA_U32, 0x3ffff),
+};
+
+const struct nla_policy nfsd_expkey_nl_policy[NFSD_A_EXPKEY_PATH + 1] = {
+	[NFSD_A_EXPKEY_SEQNO] = { .type = NLA_U64, },
+	[NFSD_A_EXPKEY_CLIENT] = { .type = NLA_NUL_STRING, },
+	[NFSD_A_EXPKEY_FSIDTYPE] = { .type = NLA_U8, },
+	[NFSD_A_EXPKEY_FSID] = { .type = NLA_BINARY, },
+	[NFSD_A_EXPKEY_NEGATIVE] = { .type = NLA_FLAG, },
+	[NFSD_A_EXPKEY_EXPIRY] = { .type = NLA_U64, },
+	[NFSD_A_EXPKEY_PATH] = { .type = NLA_NUL_STRING, },
+};
+
+const struct nla_policy nfsd_fslocation_nl_policy[NFSD_A_FSLOCATION_PATH + 1] = {
+	[NFSD_A_FSLOCATION_HOST] = { .type = NLA_NUL_STRING, },
+	[NFSD_A_FSLOCATION_PATH] = { .type = NLA_NUL_STRING, },
+};
+
+const struct nla_policy nfsd_fslocations_nl_policy[NFSD_A_FSLOCATIONS_LOCATION + 1] = {
+	[NFSD_A_FSLOCATIONS_LOCATION] = NLA_POLICY_NESTED(nfsd_fslocation_nl_policy),
+};
+
+const struct nla_policy nfsd_sock_nl_policy[NFSD_A_SOCK_TRANSPORT_NAME + 1] = {
+	[NFSD_A_SOCK_ADDR] = { .type = NLA_BINARY, },
+	[NFSD_A_SOCK_TRANSPORT_NAME] = { .type = NLA_NUL_STRING, },
+};
+
+const struct nla_policy nfsd_svc_export_nl_policy[NFSD_A_SVC_EXPORT_FSID + 1] = {
+	[NFSD_A_SVC_EXPORT_SEQNO] = { .type = NLA_U64, },
+	[NFSD_A_SVC_EXPORT_CLIENT] = { .type = NLA_NUL_STRING, },
+	[NFSD_A_SVC_EXPORT_PATH] = { .type = NLA_NUL_STRING, },
+	[NFSD_A_SVC_EXPORT_NEGATIVE] = { .type = NLA_FLAG, },
+	[NFSD_A_SVC_EXPORT_EXPIRY] = { .type = NLA_U64, },
+	[NFSD_A_SVC_EXPORT_ANON_UID] = { .type = NLA_U32, },
+	[NFSD_A_SVC_EXPORT_ANON_GID] = { .type = NLA_U32, },
+	[NFSD_A_SVC_EXPORT_FSLOCATIONS] = NLA_POLICY_NESTED(nfsd_fslocations_nl_policy),
+	[NFSD_A_SVC_EXPORT_UUID] = { .type = NLA_BINARY, },
+	[NFSD_A_SVC_EXPORT_SECINFO] = NLA_POLICY_NESTED(nfsd_auth_flavor_nl_policy),
+	[NFSD_A_SVC_EXPORT_XPRTSEC] = NLA_POLICY_MASK(NLA_U32, 0x7),
+	[NFSD_A_SVC_EXPORT_FLAGS] = NLA_POLICY_MASK(NLA_U32, 0x3ffff),
+	[NFSD_A_SVC_EXPORT_FSID] = { .type = NLA_S32, },
+};
+
+const struct nla_policy nfsd_version_nl_policy[NFSD_A_VERSION_ENABLED + 1] = {
+	[NFSD_A_VERSION_MAJOR] = { .type = NLA_U32, },
+	[NFSD_A_VERSION_MINOR] = { .type = NLA_U32, },
+	[NFSD_A_VERSION_ENABLED] = { .type = NLA_FLAG, },
+};
+
+/* NFSD_CMD_THREADS_SET - do */
+static const struct nla_policy nfsd_threads_set_nl_policy[NFSD_A_SERVER_FH_KEY + 1] = {
+	[NFSD_A_SERVER_THREADS] = { .type = NLA_U32, },
+	[NFSD_A_SERVER_GRACETIME] = { .type = NLA_U32, },
+	[NFSD_A_SERVER_LEASETIME] = { .type = NLA_U32, },
+	[NFSD_A_SERVER_SCOPE] = { .type = NLA_NUL_STRING, },
+	[NFSD_A_SERVER_MIN_THREADS] = { .type = NLA_U32, },
+	[NFSD_A_SERVER_FH_KEY] = NLA_POLICY_EXACT_LEN(16),
+};
+
+/* NFSD_CMD_VERSION_SET - do */
+static const struct nla_policy nfsd_version_set_nl_policy[NFSD_A_SERVER_PROTO_VERSION + 1] = {
+	[NFSD_A_SERVER_PROTO_VERSION] = NLA_POLICY_NESTED(nfsd_version_nl_policy),
+};
+
+/* NFSD_CMD_LISTENER_SET - do */
+static const struct nla_policy nfsd_listener_set_nl_policy[NFSD_A_SERVER_SOCK_ADDR + 1] = {
+	[NFSD_A_SERVER_SOCK_ADDR] = NLA_POLICY_NESTED(nfsd_sock_nl_policy),
+};
+
+/* NFSD_CMD_POOL_MODE_SET - do */
+static const struct nla_policy nfsd_pool_mode_set_nl_policy[NFSD_A_POOL_MODE_MODE + 1] = {
+	[NFSD_A_POOL_MODE_MODE] = { .type = NLA_NUL_STRING, },
+};
+
+/* NFSD_CMD_SVC_EXPORT_SET_REQS - do */
+static const struct nla_policy nfsd_svc_export_set_reqs_nl_policy[NFSD_A_SVC_EXPORT_REQS_REQUESTS + 1] = {
+	[NFSD_A_SVC_EXPORT_REQS_REQUESTS] = NLA_POLICY_NESTED(nfsd_svc_export_nl_policy),
+};
+
+/* NFSD_CMD_EXPKEY_SET_REQS - do */
+static const struct nla_policy nfsd_expkey_set_reqs_nl_policy[NFSD_A_EXPKEY_REQS_REQUESTS + 1] = {
+	[NFSD_A_EXPKEY_REQS_REQUESTS] = NLA_POLICY_NESTED(nfsd_expkey_nl_policy),
+};
+
+/* NFSD_CMD_CACHE_FLUSH - do */
+static const struct nla_policy nfsd_cache_flush_nl_policy[NFSD_A_CACHE_FLUSH_MASK + 1] = {
+	[NFSD_A_CACHE_FLUSH_MASK] = NLA_POLICY_MASK(NLA_U32, 0x3),
+};
+
+/* NFSD_CMD_UNLOCK_IP - do */
+static const struct nla_policy nfsd_unlock_ip_nl_policy[NFSD_A_UNLOCK_IP_ADDRESS + 1] = {
+	[NFSD_A_UNLOCK_IP_ADDRESS] = NLA_POLICY_MIN_LEN(16),
+};
+
+/* NFSD_CMD_UNLOCK_FILESYSTEM - do */
+static const struct nla_policy nfsd_unlock_filesystem_nl_policy[NFSD_A_UNLOCK_FILESYSTEM_PATH + 1] = {
+	[NFSD_A_UNLOCK_FILESYSTEM_PATH] = { .type = NLA_NUL_STRING, },
+};
+
+/* NFSD_CMD_UNLOCK_EXPORT - do */
+static const struct nla_policy nfsd_unlock_export_nl_policy[NFSD_A_UNLOCK_EXPORT_PATH + 1] = {
+	[NFSD_A_UNLOCK_EXPORT_PATH] = { .type = NLA_NUL_STRING, },
+};
+
+/* Ops table for nfsd */
+static const struct genl_split_ops nfsd_nl_ops[] = {
+	{
+		.cmd	= NFSD_CMD_RPC_STATUS_GET,
+		.dumpit	= nfsd_nl_rpc_status_get_dumpit,
+		.flags	= GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= NFSD_CMD_THREADS_SET,
+		.doit		= nfsd_nl_threads_set_doit,
+		.policy		= nfsd_threads_set_nl_policy,
+		.maxattr	= NFSD_A_SERVER_FH_KEY,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd	= NFSD_CMD_THREADS_GET,
+		.doit	= nfsd_nl_threads_get_doit,
+		.flags	= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= NFSD_CMD_VERSION_SET,
+		.doit		= nfsd_nl_version_set_doit,
+		.policy		= nfsd_version_set_nl_policy,
+		.maxattr	= NFSD_A_SERVER_PROTO_VERSION,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd	= NFSD_CMD_VERSION_GET,
+		.doit	= nfsd_nl_version_get_doit,
+		.flags	= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= NFSD_CMD_LISTENER_SET,
+		.doit		= nfsd_nl_listener_set_doit,
+		.policy		= nfsd_listener_set_nl_policy,
+		.maxattr	= NFSD_A_SERVER_SOCK_ADDR,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd	= NFSD_CMD_LISTENER_GET,
+		.doit	= nfsd_nl_listener_get_doit,
+		.flags	= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= NFSD_CMD_POOL_MODE_SET,
+		.doit		= nfsd_nl_pool_mode_set_doit,
+		.policy		= nfsd_pool_mode_set_nl_policy,
+		.maxattr	= NFSD_A_POOL_MODE_MODE,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd	= NFSD_CMD_POOL_MODE_GET,
+		.doit	= nfsd_nl_pool_mode_get_doit,
+		.flags	= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd	= NFSD_CMD_SVC_EXPORT_GET_REQS,
+		.dumpit	= nfsd_nl_svc_export_get_reqs_dumpit,
+		.flags	= GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= NFSD_CMD_SVC_EXPORT_SET_REQS,
+		.doit		= nfsd_nl_svc_export_set_reqs_doit,
+		.policy		= nfsd_svc_export_set_reqs_nl_policy,
+		.maxattr	= NFSD_A_SVC_EXPORT_REQS_REQUESTS,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd	= NFSD_CMD_EXPKEY_GET_REQS,
+		.dumpit	= nfsd_nl_expkey_get_reqs_dumpit,
+		.flags	= GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= NFSD_CMD_EXPKEY_SET_REQS,
+		.doit		= nfsd_nl_expkey_set_reqs_doit,
+		.policy		= nfsd_expkey_set_reqs_nl_policy,
+		.maxattr	= NFSD_A_EXPKEY_REQS_REQUESTS,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= NFSD_CMD_CACHE_FLUSH,
+		.doit		= nfsd_nl_cache_flush_doit,
+		.policy		= nfsd_cache_flush_nl_policy,
+		.maxattr	= NFSD_A_CACHE_FLUSH_MASK,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= NFSD_CMD_UNLOCK_IP,
+		.doit		= nfsd_nl_unlock_ip_doit,
+		.policy		= nfsd_unlock_ip_nl_policy,
+		.maxattr	= NFSD_A_UNLOCK_IP_ADDRESS,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= NFSD_CMD_UNLOCK_FILESYSTEM,
+		.doit		= nfsd_nl_unlock_filesystem_doit,
+		.policy		= nfsd_unlock_filesystem_nl_policy,
+		.maxattr	= NFSD_A_UNLOCK_FILESYSTEM_PATH,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= NFSD_CMD_UNLOCK_EXPORT,
+		.doit		= nfsd_nl_unlock_export_doit,
+		.policy		= nfsd_unlock_export_nl_policy,
+		.maxattr	= NFSD_A_UNLOCK_EXPORT_PATH,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+};
+
+static const struct genl_multicast_group nfsd_nl_mcgrps[] = {
+	[NFSD_NLGRP_NONE] = { "none", },
+	[NFSD_NLGRP_EXPORTD] = { "exportd", },
+};
+
+struct genl_family nfsd_nl_family __ro_after_init = {
+	.name		= NFSD_FAMILY_NAME,
+	.version	= NFSD_FAMILY_VERSION,
+	.netnsok	= true,
+	.parallel_ops	= true,
+	.module		= THIS_MODULE,
+	.split_ops	= nfsd_nl_ops,
+	.n_split_ops	= ARRAY_SIZE(nfsd_nl_ops),
+	.mcgrps		= nfsd_nl_mcgrps,
+	.n_mcgrps	= ARRAY_SIZE(nfsd_nl_mcgrps),
+};

linux-7.2.3/fs/nfsd/netlink.h

@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/nfsd.yaml */
+/* YNL-GEN kernel header */
+/* To regenerate run: tools/net/ynl/ynl-regen.sh */
+
+#ifndef _LINUX_NFSD_GEN_H
+#define _LINUX_NFSD_GEN_H
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include <uapi/linux/nfsd_netlink.h>
+
+/* Common nested types */
+extern const struct nla_policy nfsd_auth_flavor_nl_policy[NFSD_A_AUTH_FLAVOR_FLAGS + 1];
+extern const struct nla_policy nfsd_expkey_nl_policy[NFSD_A_EXPKEY_PATH + 1];
+extern const struct nla_policy nfsd_fslocation_nl_policy[NFSD_A_FSLOCATION_PATH + 1];
+extern const struct nla_policy nfsd_fslocations_nl_policy[NFSD_A_FSLOCATIONS_LOCATION + 1];
+extern const struct nla_policy nfsd_sock_nl_policy[NFSD_A_SOCK_TRANSPORT_NAME + 1];
+extern const struct nla_policy nfsd_svc_export_nl_policy[NFSD_A_SVC_EXPORT_FSID + 1];
+extern const struct nla_policy nfsd_version_nl_policy[NFSD_A_VERSION_ENABLED + 1];
+
+int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb,
+				  struct netlink_callback *cb);
+int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info);
+int nfsd_nl_threads_get_doit(struct sk_buff *skb, struct genl_info *info);
+int nfsd_nl_version_set_doit(struct sk_buff *skb, struct genl_info *info);
+int nfsd_nl_version_get_doit(struct sk_buff *skb, struct genl_info *info);
+int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info);
+int nfsd_nl_listener_get_doit(struct sk_buff *skb, struct genl_info *info);
+int nfsd_nl_pool_mode_set_doit(struct sk_buff *skb, struct genl_info *info);
+int nfsd_nl_pool_mode_get_doit(struct sk_buff *skb, struct genl_info *info);
+int nfsd_nl_svc_export_get_reqs_dumpit(struct sk_buff *skb,
+				       struct netlink_callback *cb);
+int nfsd_nl_svc_export_set_reqs_doit(struct sk_buff *skb,
+				     struct genl_info *info);
+int nfsd_nl_expkey_get_reqs_dumpit(struct sk_buff *skb,
+				   struct netlink_callback *cb);
+int nfsd_nl_expkey_set_reqs_doit(struct sk_buff *skb, struct genl_info *info);
+int nfsd_nl_cache_flush_doit(struct sk_buff *skb, struct genl_info *info);
+int nfsd_nl_unlock_ip_doit(struct sk_buff *skb, struct genl_info *info);
+int nfsd_nl_unlock_filesystem_doit(struct sk_buff *skb, struct genl_info *info);
+int nfsd_nl_unlock_export_doit(struct sk_buff *skb, struct genl_info *info);
+
+enum {
+	NFSD_NLGRP_NONE,
+	NFSD_NLGRP_EXPORTD,
+};
+
+extern struct genl_family nfsd_nl_family;
+
+#endif /* _LINUX_NFSD_GEN_H */

linux-7.2.3/fs/nfsd/netns.h

@@ -0,0 +1,247 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * per net namespace data structures for nfsd
+ *
+ * Copyright (C) 2012, Jeff Layton <jlayton@redhat.com>
+ */
+
+#ifndef __NFSD_NETNS_H__
+#define __NFSD_NETNS_H__
+
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <linux/filelock.h>
+#include <linux/nfs4.h>
+#include <linux/percpu_counter.h>
+#include <linux/percpu-refcount.h>
+#include <linux/siphash.h>
+#include <linux/sunrpc/stats.h>
+
+/* Hash tables for nfs4_clientid state */
+#define CLIENT_HASH_BITS                 4
+#define CLIENT_HASH_SIZE                (1 << CLIENT_HASH_BITS)
+#define CLIENT_HASH_MASK                (CLIENT_HASH_SIZE - 1)
+
+#define SESSION_HASH_SIZE	512
+
+struct cld_net;
+struct nfsd_net_cb;
+struct nfsd4_client_tracking_ops;
+
+enum {
+	/* cache misses due only to checksum comparison failures */
+	NFSD_STATS_PAYLOAD_MISSES,
+	/* amount of memory (in bytes) currently consumed by the DRC */
+	NFSD_STATS_DRC_MEM_USAGE,
+	NFSD_STATS_RC_HITS,		/* repcache hits */
+	NFSD_STATS_RC_MISSES,		/* repcache misses */
+	NFSD_STATS_RC_NOCACHE,		/* uncached reqs */
+	NFSD_STATS_FH_STALE,		/* FH stale error */
+	NFSD_STATS_IO_READ,		/* bytes returned to read requests */
+	NFSD_STATS_IO_WRITE,		/* bytes passed in write requests */
+#ifdef CONFIG_NFSD_V4
+	NFSD_STATS_FIRST_NFS4_OP,	/* count of individual nfsv4 operations */
+	NFSD_STATS_LAST_NFS4_OP = NFSD_STATS_FIRST_NFS4_OP + LAST_NFS4_OP,
+#define NFSD_STATS_NFS4_OP(op)	(NFSD_STATS_FIRST_NFS4_OP + (op))
+	NFSD_STATS_WDELEG_GETATTR,	/* count of getattr conflict with wdeleg */
+#endif
+	NFSD_STATS_COUNTERS_NUM
+};
+
+/*
+ * Represents a nfsd "container". With respect to nfsv4 state tracking, the
+ * fields of interest are the *_id_hashtbls and the *_name_tree. These track
+ * the nfs4_client objects by either short or long form clientid.
+ *
+ * Each nfsd_net runs a nfs4_laundromat workqueue job when necessary to clean
+ * up expired clients and delegations within the container.
+ */
+struct nfsd_net {
+	struct cld_net *cld_net;
+
+	struct cache_detail *svc_expkey_cache;
+	struct cache_detail *svc_export_cache;
+
+	struct cache_detail *idtoname_cache;
+	struct cache_detail *nametoid_cache;
+
+	struct lock_manager nfsd4_manager;
+	bool grace_ended;
+	bool grace_end_forced;
+	time64_t boot_time;
+
+	struct dentry *nfsd_client_dir;
+
+	/*
+	 * reclaim_str_hashtbl[] holds known client info from previous reset/reboot
+	 * used in reboot/reset lease grace period processing
+	 *
+	 * conf_id_hashtbl[], and conf_name_tree hold confirmed
+	 * setclientid_confirmed info.
+	 *
+	 * unconf_str_hastbl[] and unconf_name_tree hold unconfirmed
+	 * setclientid info.
+	 */
+	struct list_head *reclaim_str_hashtbl;
+	int reclaim_str_hashtbl_size;
+	struct list_head *conf_id_hashtbl;
+	struct rb_root conf_name_tree;
+	struct list_head *unconf_id_hashtbl;
+	struct rb_root unconf_name_tree;
+	struct list_head *sessionid_hashtbl;
+	/*
+	 * client_lru holds client queue ordered by nfs4_client.cl_time
+	 * for lease renewal.
+	 *
+	 * close_lru holds (open) stateowner queue ordered by nfs4_stateowner.so_time
+	 * for last close replay.
+	 *
+	 * All of the above fields are protected by the client_mutex.
+	 */
+	struct list_head client_lru;
+	struct list_head close_lru;
+
+	/* protects del_recall_lru and delegation hash/unhash */
+	spinlock_t deleg_lock ____cacheline_aligned;
+	struct list_head del_recall_lru;
+
+	/* protected by blocked_locks_lock */
+	struct list_head blocked_locks_lru;
+
+	struct delayed_work laundromat_work;
+
+	/* client_lock protects the client lru list and session hash table */
+	spinlock_t client_lock;
+
+	/* protects blocked_locks_lru */
+	spinlock_t blocked_locks_lock;
+
+	struct file *rec_file;
+	bool in_grace;
+	const struct nfsd4_client_tracking_ops *client_tracking_ops;
+
+	time64_t nfsd4_lease;
+	time64_t nfsd4_grace;
+	bool somebody_reclaimed;
+
+	bool track_reclaim_completes;
+	atomic_t nr_reclaim_complete;
+
+	bool nfsd_net_up;
+	bool lockd_up;
+
+	seqlock_t writeverf_lock;
+	unsigned char writeverf[8];
+
+	/*
+	 * Minimum number of threads to run per pool.  If 0 then the
+	 * min == max requested number of threads.
+	 */
+	unsigned int min_threads;
+
+	u32 clientid_base;
+	u32 clientid_counter;
+	u32 clverifier_counter;
+
+	struct svc_info nfsd_info;
+#define nfsd_serv nfsd_info.serv
+
+	struct percpu_ref nfsd_net_ref;
+	struct completion nfsd_net_confirm_done;
+	struct completion nfsd_net_free_done;
+
+	/*
+	 * clientid and stateid data for construction of net unique COPY
+	 * stateids.
+	 */
+	u32		s2s_cp_cl_id;
+	struct idr	s2s_cp_stateids;
+	spinlock_t	s2s_cp_lock;
+	atomic_t	pending_async_copies;
+
+	/*
+	 * Version information
+	 */
+	bool nfsd_versions[NFSD_MAXVERS + 1];
+	bool nfsd4_minorversions[NFSD_SUPPORTED_MINOR_VERSION + 1];
+
+	/*
+	 * Duplicate reply cache
+	 */
+	struct nfsd_drc_bucket   *drc_hashtbl;
+
+	/* max number of entries allowed in the cache */
+	unsigned int             max_drc_entries;
+
+	/* number of significant bits in the hash value */
+	unsigned int             maskbits;
+	unsigned int             drc_hashsize;
+
+	/*
+	 * Stats and other tracking of on the duplicate reply cache.
+	 * The longest_chain* fields are modified with only the per-bucket
+	 * cache lock, which isn't really safe and should be fixed if we want
+	 * these statistics to be completely accurate.
+	 */
+
+	/* total number of entries */
+	atomic_t                 num_drc_entries;
+
+	/* Per-netns stats counters */
+	struct percpu_counter    counter[NFSD_STATS_COUNTERS_NUM];
+
+	/* sunrpc svc stats */
+	struct svc_stat          nfsd_svcstats;
+
+	/* longest hash chain seen */
+	unsigned int             longest_chain;
+
+	/* size of cache when we saw the longest hash chain */
+	unsigned int             longest_chain_cachesize;
+
+	struct shrinker		*nfsd_reply_cache_shrinker;
+
+	/* tracking server-to-server copy mounts */
+	spinlock_t              nfsd_ssc_lock;
+	struct list_head        nfsd_ssc_mount_list;
+	wait_queue_head_t       nfsd_ssc_waitq;
+
+	/* utsname taken from the process that starts the server */
+	char			nfsd_name[UNX_MAXNODENAME+1];
+
+	struct nfsd_fcache_disposal *fcache_disposal;
+
+	siphash_key_t		siphash_key;
+
+	atomic_t		nfs4_client_count;
+	int			nfs4_max_clients;
+
+	atomic_t		nfsd_courtesy_clients;
+	struct shrinker		*nfsd_client_shrinker;
+	struct work_struct	nfsd_shrinker_work;
+
+	/* last time an admin-revoke happened for NFSv4.0 */
+	time64_t		nfs40_last_revoke;
+
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+	/* Local clients to be invalidated when net is shut down */
+	spinlock_t              local_clients_lock;
+	struct list_head	local_clients;
+#endif
+	siphash_key_t		*fh_key;
+
+	struct nfsd_net_cb	*nfsd_cb;
+};
+
+/* Simple check to find out if a given net was properly initialized */
+#define nfsd_netns_ready(nn) ((nn)->sessionid_hashtbl)
+
+extern bool nfsd_support_version(int vers);
+extern unsigned int nfsd_net_id;
+
+bool nfsd_net_try_get(struct net *net);
+void nfsd_net_put(struct net *net);
+
+void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn);
+void nfsd_reset_write_verifier(struct nfsd_net *nn);
+#endif /* __NFSD_NETNS_H__ */

linux-7.2.3/fs/nfsd/nfs2acl.c

@@ -0,0 +1,396 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Process version 2 NFSACL requests.
+ *
+ * Copyright (C) 2002-2003 Andreas Gruenbacher <agruen@suse.de>
+ */
+
+#include "nfsd.h"
+/* FIXME: nfsacl.h is a broken header */
+#include <linux/nfsacl.h>
+#include <linux/gfp.h>
+#include "cache.h"
+#include "xdr3.h"
+#include "vfs.h"
+
+#define NFSDDBG_FACILITY		NFSDDBG_PROC
+
+/*
+ * NULL call.
+ */
+static __be32
+nfsacld_proc_null(struct svc_rqst *rqstp)
+{
+	return rpc_success;
+}
+
+/*
+ * Get the Access and/or Default ACL of a file.
+ */
+static __be32 nfsacld_proc_getacl(struct svc_rqst *rqstp)
+{
+	struct nfsd3_getaclargs *argp = rqstp->rq_argp;
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
+	struct posix_acl *acl;
+	struct inode *inode;
+	svc_fh *fh;
+
+	dprintk("nfsd: GETACL(2acl)   %s\n", SVCFH_fmt(&argp->fh));
+
+	fh = fh_copy(&resp->fh, &argp->fh);
+	resp->status = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP);
+	if (resp->status != nfs_ok)
+		goto out;
+
+	inode = d_inode(fh->fh_dentry);
+
+	if (argp->mask & ~NFS_ACL_MASK) {
+		resp->status = nfserr_io;
+		goto out;
+	}
+	resp->mask = argp->mask;
+
+	resp->status = fh_getattr(fh, &resp->stat);
+	if (resp->status != nfs_ok)
+		goto out;
+
+	if (resp->mask & (NFS_ACL|NFS_ACLCNT)) {
+		acl = get_inode_acl(inode, ACL_TYPE_ACCESS);
+		if (acl == NULL) {
+			/* Solaris returns the inode's minimum ACL. */
+			acl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
+		}
+		if (IS_ERR(acl)) {
+			resp->status = nfserrno(PTR_ERR(acl));
+			goto fail;
+		}
+		resp->acl_access = acl;
+	}
+	if (resp->mask & (NFS_DFACL|NFS_DFACLCNT)) {
+		/* Check how Solaris handles requests for the Default ACL
+		   of a non-directory! */
+		acl = get_inode_acl(inode, ACL_TYPE_DEFAULT);
+		if (IS_ERR(acl)) {
+			resp->status = nfserrno(PTR_ERR(acl));
+			goto fail;
+		}
+		resp->acl_default = acl;
+	}
+
+	/* resp->acl_{access,default} are released in nfssvc_release_getacl. */
+out:
+	return rpc_success;
+
+fail:
+	posix_acl_release(resp->acl_access);
+	posix_acl_release(resp->acl_default);
+	resp->acl_access = NULL;
+	resp->acl_default = NULL;
+	goto out;
+}
+
+/*
+ * Set the Access and/or Default ACL of a file.
+ */
+static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp)
+{
+	struct nfsd3_setaclargs *argp = rqstp->rq_argp;
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
+	struct inode *inode;
+	svc_fh *fh;
+	int error;
+
+	dprintk("nfsd: SETACL(2acl)   %s\n", SVCFH_fmt(&argp->fh));
+
+	fh = fh_copy(&resp->fh, &argp->fh);
+	resp->status = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_SATTR);
+	if (resp->status != nfs_ok)
+		goto out;
+
+	inode = d_inode(fh->fh_dentry);
+
+	error = fh_want_write(fh);
+	if (error)
+		goto out_errno;
+
+	inode_lock(inode);
+
+	error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_ACCESS,
+			      argp->acl_access);
+	if (error)
+		goto out_drop_lock;
+	error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_DEFAULT,
+			      argp->acl_default);
+	if (error)
+		goto out_drop_lock;
+
+	inode_unlock(inode);
+
+	fh_drop_write(fh);
+
+	resp->status = fh_getattr(fh, &resp->stat);
+
+out:
+	/* argp->acl_{access,default} are released in nfsaclsvc_release_setacl. */
+	return rpc_success;
+
+out_drop_lock:
+	inode_unlock(inode);
+	fh_drop_write(fh);
+out_errno:
+	resp->status = nfserrno(error);
+	goto out;
+}
+
+/*
+ * Check file attributes
+ */
+static __be32 nfsacld_proc_getattr(struct svc_rqst *rqstp)
+{
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
+
+	dprintk("nfsd: GETATTR  %s\n", SVCFH_fmt(&argp->fh));
+
+	fh_copy(&resp->fh, &argp->fh);
+	resp->status = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP);
+	if (resp->status != nfs_ok)
+		goto out;
+	resp->status = fh_getattr(&resp->fh, &resp->stat);
+out:
+	return rpc_success;
+}
+
+/*
+ * Check file access
+ */
+static __be32 nfsacld_proc_access(struct svc_rqst *rqstp)
+{
+	struct nfsd3_accessargs *argp = rqstp->rq_argp;
+	struct nfsd3_accessres *resp = rqstp->rq_resp;
+
+	dprintk("nfsd: ACCESS(2acl)   %s 0x%x\n",
+			SVCFH_fmt(&argp->fh),
+			argp->access);
+
+	fh_copy(&resp->fh, &argp->fh);
+	resp->access = argp->access;
+	resp->status = nfsd_access(rqstp, &resp->fh, &resp->access, NULL);
+	if (resp->status != nfs_ok)
+		goto out;
+	resp->status = fh_getattr(&resp->fh, &resp->stat);
+out:
+	return rpc_success;
+}
+
+/*
+ * XDR decode functions
+ */
+
+static bool
+nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd3_getaclargs *argp = rqstp->rq_argp;
+
+	if (!svcxdr_decode_fhandle(xdr, &argp->fh))
+		return false;
+	if (xdr_stream_decode_u32(xdr, &argp->mask) < 0)
+		return false;
+
+	return true;
+}
+
+static bool
+nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd3_setaclargs *argp = rqstp->rq_argp;
+
+	if (!svcxdr_decode_fhandle(xdr, &argp->fh))
+		return false;
+	if (xdr_stream_decode_u32(xdr, &argp->mask) < 0)
+		return false;
+	if (argp->mask & ~NFS_ACL_MASK)
+		return false;
+	if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_ACL) ?
+				   &argp->acl_access : NULL))
+		return false;
+	if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_DFACL) ?
+				   &argp->acl_default : NULL))
+		return false;
+
+	return true;
+}
+
+static bool
+nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd3_accessargs *args = rqstp->rq_argp;
+
+	if (!svcxdr_decode_fhandle(xdr, &args->fh))
+		return false;
+	if (xdr_stream_decode_u32(xdr, &args->access) < 0)
+		return false;
+
+	return true;
+}
+
+/*
+ * XDR encode functions
+ */
+
+/* GETACL */
+static bool
+nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
+	struct dentry *dentry = resp->fh.fh_dentry;
+	struct inode *inode;
+
+	if (!svcxdr_encode_stat(xdr, resp->status))
+		return false;
+
+	if (dentry == NULL || d_really_is_negative(dentry))
+		return true;
+	inode = d_inode(dentry);
+
+	if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat))
+		return false;
+	if (xdr_stream_encode_u32(xdr, resp->mask) < 0)
+		return false;
+
+	if (!nfs_stream_encode_acl(xdr, inode, resp->acl_access,
+				   resp->mask & NFS_ACL, 0))
+		return false;
+	if (!nfs_stream_encode_acl(xdr, inode, resp->acl_default,
+				   resp->mask & NFS_DFACL, NFS_ACL_DEFAULT))
+		return false;
+
+	return true;
+}
+
+/* ACCESS */
+static bool
+nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd3_accessres *resp = rqstp->rq_resp;
+
+	if (!svcxdr_encode_stat(xdr, resp->status))
+		return false;
+	switch (resp->status) {
+	case nfs_ok:
+		if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat))
+			return false;
+		if (xdr_stream_encode_u32(xdr, resp->access) < 0)
+			return false;
+		break;
+	}
+
+	return true;
+}
+
+/*
+ * XDR release functions
+ */
+static void nfsaclsvc_release_getacl(struct svc_rqst *rqstp)
+{
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
+
+	fh_put(&resp->fh);
+	posix_acl_release(resp->acl_access);
+	posix_acl_release(resp->acl_default);
+}
+
+static void nfsaclsvc_release_access(struct svc_rqst *rqstp)
+{
+	struct nfsd3_accessres *resp = rqstp->rq_resp;
+
+	fh_put(&resp->fh);
+}
+
+static void nfsaclsvc_release_setacl(struct svc_rqst *rqstp)
+{
+	struct nfsd3_setaclargs *argp = rqstp->rq_argp;
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
+
+	fh_put(&resp->fh);
+	posix_acl_release(argp->acl_access);
+	posix_acl_release(argp->acl_default);
+}
+
+#define ST 1		/* status*/
+#define AT 21		/* attributes */
+#define pAT (1+AT)	/* post attributes - conditional */
+#define ACL (1+NFS_ACL_MAX_ENTRIES*3)  /* Access Control List */
+
+static const struct svc_procedure nfsd_acl_procedures2[5] = {
+	[ACLPROC2_NULL] = {
+		.pc_func = nfsacld_proc_null,
+		.pc_decode = nfssvc_decode_voidarg,
+		.pc_encode = nfssvc_encode_voidres,
+		.pc_argsize = sizeof(struct nfsd_voidargs),
+		.pc_argzero = sizeof(struct nfsd_voidargs),
+		.pc_ressize = sizeof(struct nfsd_voidres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST,
+		.pc_name = "NULL",
+	},
+	[ACLPROC2_GETACL] = {
+		.pc_func = nfsacld_proc_getacl,
+		.pc_decode = nfsaclsvc_decode_getaclargs,
+		.pc_encode = nfsaclsvc_encode_getaclres,
+		.pc_release = nfsaclsvc_release_getacl,
+		.pc_argsize = sizeof(struct nfsd3_getaclargs),
+		.pc_argzero = sizeof(struct nfsd3_getaclargs),
+		.pc_ressize = sizeof(struct nfsd3_getaclres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+1+2*(1+ACL),
+		.pc_name = "GETACL",
+	},
+	[ACLPROC2_SETACL] = {
+		.pc_func = nfsacld_proc_setacl,
+		.pc_decode = nfsaclsvc_decode_setaclargs,
+		.pc_encode = nfssvc_encode_attrstatres,
+		.pc_release = nfsaclsvc_release_setacl,
+		.pc_argsize = sizeof(struct nfsd3_setaclargs),
+		.pc_argzero = sizeof(struct nfsd3_setaclargs),
+		.pc_ressize = sizeof(struct nfsd_attrstat),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+AT,
+		.pc_name = "SETACL",
+	},
+	[ACLPROC2_GETATTR] = {
+		.pc_func = nfsacld_proc_getattr,
+		.pc_decode = nfssvc_decode_fhandleargs,
+		.pc_encode = nfssvc_encode_attrstatres,
+		.pc_release = nfssvc_release_attrstat,
+		.pc_argsize = sizeof(struct nfsd_fhandle),
+		.pc_argzero = sizeof(struct nfsd_fhandle),
+		.pc_ressize = sizeof(struct nfsd_attrstat),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+AT,
+		.pc_name = "GETATTR",
+	},
+	[ACLPROC2_ACCESS] = {
+		.pc_func = nfsacld_proc_access,
+		.pc_decode = nfsaclsvc_decode_accessargs,
+		.pc_encode = nfsaclsvc_encode_accessres,
+		.pc_release = nfsaclsvc_release_access,
+		.pc_argsize = sizeof(struct nfsd3_accessargs),
+		.pc_argzero = sizeof(struct nfsd3_accessargs),
+		.pc_ressize = sizeof(struct nfsd3_accessres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+AT+1,
+		.pc_name = "SETATTR",
+	},
+};
+
+static DEFINE_PER_CPU_ALIGNED(unsigned long,
+			      nfsd_acl_count2[ARRAY_SIZE(nfsd_acl_procedures2)]);
+const struct svc_version nfsd_acl_version2 = {
+	.vs_vers	= 2,
+	.vs_nproc	= ARRAY_SIZE(nfsd_acl_procedures2),
+	.vs_proc	= nfsd_acl_procedures2,
+	.vs_count	= nfsd_acl_count2,
+	.vs_dispatch	= nfsd_dispatch,
+	.vs_xdrsize	= NFS3_SVC_XDRSIZE,
+};

linux-7.2.3/fs/nfsd/nfs3acl.c

@@ -0,0 +1,286 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Process version 3 NFSACL requests.
+ *
+ * Copyright (C) 2002-2003 Andreas Gruenbacher <agruen@suse.de>
+ */
+
+#include "nfsd.h"
+/* FIXME: nfsacl.h is a broken header */
+#include <linux/nfsacl.h>
+#include <linux/gfp.h>
+#include "cache.h"
+#include "xdr3.h"
+#include "vfs.h"
+
+/*
+ * NULL call.
+ */
+static __be32
+nfsd3_proc_null(struct svc_rqst *rqstp)
+{
+	return rpc_success;
+}
+
+/*
+ * Get the Access and/or Default ACL of a file.
+ */
+static __be32 nfsd3_proc_getacl(struct svc_rqst *rqstp)
+{
+	struct nfsd3_getaclargs *argp = rqstp->rq_argp;
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
+	struct posix_acl *acl;
+	struct inode *inode;
+	svc_fh *fh;
+
+	fh = fh_copy(&resp->fh, &argp->fh);
+	resp->status = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP);
+	if (resp->status != nfs_ok)
+		goto out;
+
+	inode = d_inode(fh->fh_dentry);
+
+	if (argp->mask & ~NFS_ACL_MASK) {
+		resp->status = nfserr_inval;
+		goto out;
+	}
+	resp->mask = argp->mask;
+
+	if (resp->mask & (NFS_ACL|NFS_ACLCNT)) {
+		acl = get_inode_acl(inode, ACL_TYPE_ACCESS);
+		if (acl == NULL) {
+			/* Solaris returns the inode's minimum ACL. */
+			acl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
+		}
+		if (IS_ERR(acl)) {
+			resp->status = nfserrno(PTR_ERR(acl));
+			goto fail;
+		}
+		resp->acl_access = acl;
+	}
+	if (resp->mask & (NFS_DFACL|NFS_DFACLCNT)) {
+		/* Check how Solaris handles requests for the Default ACL
+		   of a non-directory! */
+		acl = get_inode_acl(inode, ACL_TYPE_DEFAULT);
+		if (IS_ERR(acl)) {
+			resp->status = nfserrno(PTR_ERR(acl));
+			goto fail;
+		}
+		resp->acl_default = acl;
+	}
+
+	/* resp->acl_{access,default} are released in nfs3svc_release_getacl. */
+out:
+	return rpc_success;
+
+fail:
+	posix_acl_release(resp->acl_access);
+	posix_acl_release(resp->acl_default);
+	resp->acl_access = NULL;
+	resp->acl_default = NULL;
+	goto out;
+}
+
+/*
+ * Set the Access and/or Default ACL of a file.
+ */
+static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp)
+{
+	struct nfsd3_setaclargs *argp = rqstp->rq_argp;
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
+	struct inode *inode;
+	svc_fh *fh;
+	int error;
+
+	fh = fh_copy(&resp->fh, &argp->fh);
+	resp->status = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_SATTR);
+	if (resp->status != nfs_ok)
+		goto out;
+
+	inode = d_inode(fh->fh_dentry);
+
+	error = fh_want_write(fh);
+	if (error)
+		goto out_errno;
+
+	inode_lock(inode);
+
+	error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_ACCESS,
+			      argp->acl_access);
+	if (error)
+		goto out_drop_lock;
+	error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_DEFAULT,
+			      argp->acl_default);
+
+out_drop_lock:
+	inode_unlock(inode);
+	fh_drop_write(fh);
+out_errno:
+	resp->status = nfserrno(error);
+out:
+	/* argp->acl_{access,default} are released in nfs3svc_release_setacl. */
+	return rpc_success;
+}
+
+/*
+ * XDR decode functions
+ */
+
+static bool
+nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd3_getaclargs *args = rqstp->rq_argp;
+
+	if (!svcxdr_decode_nfs_fh3(xdr, &args->fh))
+		return false;
+	if (xdr_stream_decode_u32(xdr, &args->mask) < 0)
+		return false;
+
+	return true;
+}
+
+static bool
+nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd3_setaclargs *argp = rqstp->rq_argp;
+
+	if (!svcxdr_decode_nfs_fh3(xdr, &argp->fh))
+		return false;
+	if (xdr_stream_decode_u32(xdr, &argp->mask) < 0)
+		return false;
+	if (argp->mask & ~NFS_ACL_MASK)
+		return false;
+	if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_ACL) ?
+				   &argp->acl_access : NULL))
+		return false;
+	if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_DFACL) ?
+				   &argp->acl_default : NULL))
+		return false;
+
+	return true;
+}
+
+/*
+ * XDR encode functions
+ */
+
+/* GETACL */
+static bool
+nfs3svc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
+	struct dentry *dentry = resp->fh.fh_dentry;
+	struct inode *inode;
+
+	if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+		return false;
+	switch (resp->status) {
+	case nfs_ok:
+		inode = d_inode(dentry);
+		if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
+			return false;
+		if (xdr_stream_encode_u32(xdr, resp->mask) < 0)
+			return false;
+
+		if (!nfs_stream_encode_acl(xdr, inode, resp->acl_access,
+					   resp->mask & NFS_ACL, 0))
+			return false;
+		if (!nfs_stream_encode_acl(xdr, inode, resp->acl_default,
+					   resp->mask & NFS_DFACL,
+					   NFS_ACL_DEFAULT))
+			return false;
+		break;
+	default:
+		if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
+			return false;
+	}
+
+	return true;
+}
+
+/* SETACL */
+static bool
+nfs3svc_encode_setaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
+
+	return svcxdr_encode_nfsstat3(xdr, resp->status) &&
+		svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh);
+}
+
+/*
+ * XDR release functions
+ */
+static void nfs3svc_release_getacl(struct svc_rqst *rqstp)
+{
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
+
+	fh_put(&resp->fh);
+	posix_acl_release(resp->acl_access);
+	posix_acl_release(resp->acl_default);
+}
+
+static void nfs3svc_release_setacl(struct svc_rqst *rqstp)
+{
+	struct nfsd3_setaclargs *argp = rqstp->rq_argp;
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
+
+	fh_put(&resp->fh);
+	posix_acl_release(argp->acl_access);
+	posix_acl_release(argp->acl_default);
+}
+
+#define ST 1		/* status*/
+#define AT 21		/* attributes */
+#define pAT (1+AT)	/* post attributes - conditional */
+#define ACL (1+NFS_ACL_MAX_ENTRIES*3)  /* Access Control List */
+
+static const struct svc_procedure nfsd_acl_procedures3[3] = {
+	[ACLPROC3_NULL] = {
+		.pc_func = nfsd3_proc_null,
+		.pc_decode = nfssvc_decode_voidarg,
+		.pc_encode = nfssvc_encode_voidres,
+		.pc_argsize = sizeof(struct nfsd_voidargs),
+		.pc_argzero = sizeof(struct nfsd_voidargs),
+		.pc_ressize = sizeof(struct nfsd_voidres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST,
+		.pc_name = "NULL",
+	},
+	[ACLPROC3_GETACL] = {
+		.pc_func = nfsd3_proc_getacl,
+		.pc_decode = nfs3svc_decode_getaclargs,
+		.pc_encode = nfs3svc_encode_getaclres,
+		.pc_release = nfs3svc_release_getacl,
+		.pc_argsize = sizeof(struct nfsd3_getaclargs),
+		.pc_argzero = sizeof(struct nfsd3_getaclargs),
+		.pc_ressize = sizeof(struct nfsd3_getaclres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+1+2*(1+ACL),
+		.pc_name = "GETACL",
+	},
+	[ACLPROC3_SETACL] = {
+		.pc_func = nfsd3_proc_setacl,
+		.pc_decode = nfs3svc_decode_setaclargs,
+		.pc_encode = nfs3svc_encode_setaclres,
+		.pc_release = nfs3svc_release_setacl,
+		.pc_argsize = sizeof(struct nfsd3_setaclargs),
+		.pc_argzero = sizeof(struct nfsd3_setaclargs),
+		.pc_ressize = sizeof(struct nfsd3_attrstat),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+pAT,
+		.pc_name = "SETACL",
+	},
+};
+
+static DEFINE_PER_CPU_ALIGNED(unsigned long,
+			      nfsd_acl_count3[ARRAY_SIZE(nfsd_acl_procedures3)]);
+const struct svc_version nfsd_acl_version3 = {
+	.vs_vers	= 3,
+	.vs_nproc	= ARRAY_SIZE(nfsd_acl_procedures3),
+	.vs_proc	= nfsd_acl_procedures3,
+	.vs_count	= nfsd_acl_count3,
+	.vs_dispatch	= nfsd_dispatch,
+	.vs_xdrsize	= NFS3_SVC_XDRSIZE,
+};
+

linux-7.2.3/fs/nfsd/nfs4acl.c

@@ -0,0 +1,884 @@
+/*
+ *  Common NFSv4 ACL handling code.
+ *
+ *  Copyright (c) 2002, 2003 The Regents of the University of Michigan.
+ *  All rights reserved.
+ *
+ *  Marius Aamodt Eriksen <marius@umich.edu>
+ *  Jeff Sedlak <jsedlak@umich.edu>
+ *  J. Bruce Fields <bfields@umich.edu>
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the University nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/posix_acl.h>
+
+#include "nfsfh.h"
+#include "nfsd.h"
+#include "acl.h"
+#include "vfs.h"
+
+#define NFS4_ACL_TYPE_DEFAULT	0x01
+#define NFS4_ACL_DIR		0x02
+#define NFS4_ACL_OWNER		0x04
+
+/* mode bit translations: */
+#define NFS4_READ_MODE (NFS4_ACE_READ_DATA)
+#define NFS4_WRITE_MODE (NFS4_ACE_WRITE_DATA | NFS4_ACE_APPEND_DATA)
+#define NFS4_EXECUTE_MODE NFS4_ACE_EXECUTE
+#define NFS4_ANYONE_MODE (NFS4_ACE_READ_ATTRIBUTES | NFS4_ACE_READ_ACL | NFS4_ACE_SYNCHRONIZE)
+#define NFS4_OWNER_MODE (NFS4_ACE_WRITE_ATTRIBUTES | NFS4_ACE_WRITE_ACL)
+
+/* flags used to simulate posix default ACLs */
+#define NFS4_INHERITANCE_FLAGS (NFS4_ACE_FILE_INHERIT_ACE \
+		| NFS4_ACE_DIRECTORY_INHERIT_ACE)
+
+#define NFS4_SUPPORTED_FLAGS (NFS4_INHERITANCE_FLAGS \
+		| NFS4_ACE_INHERIT_ONLY_ACE \
+		| NFS4_ACE_IDENTIFIER_GROUP)
+
+static u32
+mask_from_posix(unsigned short perm, unsigned int flags)
+{
+	int mask = NFS4_ANYONE_MODE;
+
+	if (flags & NFS4_ACL_OWNER)
+		mask |= NFS4_OWNER_MODE;
+	if (perm & ACL_READ)
+		mask |= NFS4_READ_MODE;
+	if (perm & ACL_WRITE)
+		mask |= NFS4_WRITE_MODE;
+	if ((perm & ACL_WRITE) && (flags & NFS4_ACL_DIR))
+		mask |= NFS4_ACE_DELETE_CHILD;
+	if (perm & ACL_EXECUTE)
+		mask |= NFS4_EXECUTE_MODE;
+	return mask;
+}
+
+static u32
+deny_mask_from_posix(unsigned short perm, u32 flags)
+{
+	u32 mask = 0;
+
+	if (perm & ACL_READ)
+		mask |= NFS4_READ_MODE;
+	if (perm & ACL_WRITE)
+		mask |= NFS4_WRITE_MODE;
+	if ((perm & ACL_WRITE) && (flags & NFS4_ACL_DIR))
+		mask |= NFS4_ACE_DELETE_CHILD;
+	if (perm & ACL_EXECUTE)
+		mask |= NFS4_EXECUTE_MODE;
+	return mask;
+}
+
+/* XXX: modify functions to return NFS errors; they're only ever
+ * used by nfs code, after all.... */
+
+/* We only map from NFSv4 to POSIX ACLs when setting ACLs, when we err on the
+ * side of being more restrictive, so the mode bit mapping below is
+ * pessimistic.  An optimistic version would be needed to handle DENY's,
+ * but we expect to coalesce all ALLOWs and DENYs before mapping to mode
+ * bits. */
+
+static void
+low_mode_from_nfs4(u32 perm, unsigned short *mode, unsigned int flags)
+{
+	u32 write_mode = NFS4_WRITE_MODE;
+
+	if (flags & NFS4_ACL_DIR)
+		write_mode |= NFS4_ACE_DELETE_CHILD;
+	*mode = 0;
+	if ((perm & NFS4_READ_MODE) == NFS4_READ_MODE)
+		*mode |= ACL_READ;
+	if ((perm & write_mode) == write_mode)
+		*mode |= ACL_WRITE;
+	if ((perm & NFS4_EXECUTE_MODE) == NFS4_EXECUTE_MODE)
+		*mode |= ACL_EXECUTE;
+}
+
+static short ace2type(struct nfs4_ace *);
+static void _posix_to_nfsv4_one(struct posix_acl *, struct nfs4_acl *,
+				unsigned int);
+
+int
+nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry,
+		struct nfs4_acl **acl)
+{
+	struct inode *inode = d_inode(dentry);
+	int error = 0;
+	struct posix_acl *pacl = NULL, *dpacl = NULL;
+	unsigned int flags = 0;
+	int size = 0;
+
+	pacl = get_inode_acl(inode, ACL_TYPE_ACCESS);
+	if (!pacl)
+		pacl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
+
+	if (IS_ERR(pacl))
+		return PTR_ERR(pacl);
+
+	/* allocate for worst case: one (deny, allow) pair each: */
+	size += 2 * pacl->a_count;
+
+	if (S_ISDIR(inode->i_mode)) {
+		flags = NFS4_ACL_DIR;
+		dpacl = get_inode_acl(inode, ACL_TYPE_DEFAULT);
+		if (IS_ERR(dpacl)) {
+			error = PTR_ERR(dpacl);
+			goto rel_pacl;
+		}
+
+		if (dpacl)
+			size += 2 * dpacl->a_count;
+	}
+
+	*acl = kmalloc(nfs4_acl_bytes(size), GFP_KERNEL);
+	if (*acl == NULL) {
+		error = -ENOMEM;
+		goto out;
+	}
+	(*acl)->naces = 0;
+
+	_posix_to_nfsv4_one(pacl, *acl, flags & ~NFS4_ACL_TYPE_DEFAULT);
+
+	if (dpacl)
+		_posix_to_nfsv4_one(dpacl, *acl, flags | NFS4_ACL_TYPE_DEFAULT);
+
+out:
+	posix_acl_release(dpacl);
+rel_pacl:
+	posix_acl_release(pacl);
+	return error;
+}
+
+struct posix_acl_summary {
+	unsigned short owner;
+	unsigned short users;
+	unsigned short group;
+	unsigned short groups;
+	unsigned short other;
+	unsigned short mask;
+};
+
+static void
+summarize_posix_acl(struct posix_acl *acl, struct posix_acl_summary *pas)
+{
+	struct posix_acl_entry *pa, *pe;
+
+	/*
+	 * Only pas.users and pas.groups need initialization; previous
+	 * posix_acl_valid() calls ensure that the other fields will be
+	 * initialized in the following loop.  But, just to placate gcc:
+	 */
+	memset(pas, 0, sizeof(*pas));
+	pas->mask = 07;
+
+	FOREACH_ACL_ENTRY(pa, acl, pe) {
+		switch (pa->e_tag) {
+			case ACL_USER_OBJ:
+				pas->owner = pa->e_perm;
+				break;
+			case ACL_GROUP_OBJ:
+				pas->group = pa->e_perm;
+				break;
+			case ACL_USER:
+				pas->users |= pa->e_perm;
+				break;
+			case ACL_GROUP:
+				pas->groups |= pa->e_perm;
+				break;
+			case ACL_OTHER:
+				pas->other = pa->e_perm;
+				break;
+			case ACL_MASK:
+				pas->mask = pa->e_perm;
+				break;
+		}
+	}
+	/* We'll only care about effective permissions: */
+	pas->users &= pas->mask;
+	pas->group &= pas->mask;
+	pas->groups &= pas->mask;
+}
+
+/* We assume the acl has been verified with posix_acl_valid. */
+static void
+_posix_to_nfsv4_one(struct posix_acl *pacl, struct nfs4_acl *acl,
+						unsigned int flags)
+{
+	struct posix_acl_entry *pa, *group_owner_entry;
+	struct nfs4_ace *ace;
+	struct posix_acl_summary pas;
+	unsigned short deny;
+	int eflag = ((flags & NFS4_ACL_TYPE_DEFAULT) ?
+		NFS4_INHERITANCE_FLAGS | NFS4_ACE_INHERIT_ONLY_ACE : 0);
+
+	BUG_ON(pacl->a_count < 3);
+	summarize_posix_acl(pacl, &pas);
+
+	pa = pacl->a_entries;
+	ace = acl->aces + acl->naces;
+
+	/* We could deny everything not granted by the owner: */
+	deny = ~pas.owner;
+	/*
+	 * but it is equivalent (and simpler) to deny only what is not
+	 * granted by later entries:
+	 */
+	deny &= pas.users | pas.group | pas.groups | pas.other;
+	if (deny) {
+		ace->type = NFS4_ACE_ACCESS_DENIED_ACE_TYPE;
+		ace->flag = eflag;
+		ace->access_mask = deny_mask_from_posix(deny, flags);
+		ace->whotype = NFS4_ACL_WHO_OWNER;
+		ace++;
+		acl->naces++;
+	}
+
+	ace->type = NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE;
+	ace->flag = eflag;
+	ace->access_mask = mask_from_posix(pa->e_perm, flags | NFS4_ACL_OWNER);
+	ace->whotype = NFS4_ACL_WHO_OWNER;
+	ace++;
+	acl->naces++;
+	pa++;
+
+	while (pa->e_tag == ACL_USER) {
+		deny = ~(pa->e_perm & pas.mask);
+		deny &= pas.groups | pas.group | pas.other;
+		if (deny) {
+			ace->type = NFS4_ACE_ACCESS_DENIED_ACE_TYPE;
+			ace->flag = eflag;
+			ace->access_mask = deny_mask_from_posix(deny, flags);
+			ace->whotype = NFS4_ACL_WHO_NAMED;
+			ace->who_uid = pa->e_uid;
+			ace++;
+			acl->naces++;
+		}
+		ace->type = NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE;
+		ace->flag = eflag;
+		ace->access_mask = mask_from_posix(pa->e_perm & pas.mask,
+						   flags);
+		ace->whotype = NFS4_ACL_WHO_NAMED;
+		ace->who_uid = pa->e_uid;
+		ace++;
+		acl->naces++;
+		pa++;
+	}
+
+	/* In the case of groups, we apply allow ACEs first, then deny ACEs,
+	 * since a user can be in more than one group.  */
+
+	/* allow ACEs */
+
+	group_owner_entry = pa;
+
+	ace->type = NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE;
+	ace->flag = eflag;
+	ace->access_mask = mask_from_posix(pas.group, flags);
+	ace->whotype = NFS4_ACL_WHO_GROUP;
+	ace++;
+	acl->naces++;
+	pa++;
+
+	while (pa->e_tag == ACL_GROUP) {
+		ace->type = NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE;
+		ace->flag = eflag | NFS4_ACE_IDENTIFIER_GROUP;
+		ace->access_mask = mask_from_posix(pa->e_perm & pas.mask,
+						   flags);
+		ace->whotype = NFS4_ACL_WHO_NAMED;
+		ace->who_gid = pa->e_gid;
+		ace++;
+		acl->naces++;
+		pa++;
+	}
+
+	/* deny ACEs */
+
+	pa = group_owner_entry;
+
+	deny = ~pas.group & pas.other;
+	if (deny) {
+		ace->type = NFS4_ACE_ACCESS_DENIED_ACE_TYPE;
+		ace->flag = eflag;
+		ace->access_mask = deny_mask_from_posix(deny, flags);
+		ace->whotype = NFS4_ACL_WHO_GROUP;
+		ace++;
+		acl->naces++;
+	}
+	pa++;
+
+	while (pa->e_tag == ACL_GROUP) {
+		deny = ~(pa->e_perm & pas.mask);
+		deny &= pas.other;
+		if (deny) {
+			ace->type = NFS4_ACE_ACCESS_DENIED_ACE_TYPE;
+			ace->flag = eflag | NFS4_ACE_IDENTIFIER_GROUP;
+			ace->access_mask = deny_mask_from_posix(deny, flags);
+			ace->whotype = NFS4_ACL_WHO_NAMED;
+			ace->who_gid = pa->e_gid;
+			ace++;
+			acl->naces++;
+		}
+		pa++;
+	}
+
+	if (pa->e_tag == ACL_MASK)
+		pa++;
+	ace->type = NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE;
+	ace->flag = eflag;
+	ace->access_mask = mask_from_posix(pa->e_perm, flags);
+	ace->whotype = NFS4_ACL_WHO_EVERYONE;
+	acl->naces++;
+}
+
+static bool
+pace_gt(struct posix_acl_entry *pace1, struct posix_acl_entry *pace2)
+{
+	if (pace1->e_tag != pace2->e_tag)
+		return pace1->e_tag > pace2->e_tag;
+	if (pace1->e_tag == ACL_USER)
+		return uid_gt(pace1->e_uid, pace2->e_uid);
+	if (pace1->e_tag == ACL_GROUP)
+		return gid_gt(pace1->e_gid, pace2->e_gid);
+	return false;
+}
+
+/**
+ * sort_pacl_range - sort a range of POSIX ACL entries by tag and id
+ * @pacl: POSIX ACL containing entries to sort
+ * @start: starting index of range to sort
+ * @end: ending index of range to sort (inclusive)
+ *
+ * Sorts ACL entries in place so that USER entries are ordered by UID
+ * and GROUP entries are ordered by GID. Required before calling
+ * posix_acl_valid().
+ */
+void sort_pacl_range(struct posix_acl *pacl, int start, int end)
+{
+	int sorted = 0, i;
+
+	/* Bubble sort: acceptable here because ACLs are typically short. */
+	while (!sorted) {
+		sorted = 1;
+		for (i = start; i < end; i++) {
+			if (pace_gt(&pacl->a_entries[i],
+				    &pacl->a_entries[i+1])) {
+				sorted = 0;
+				swap(pacl->a_entries[i],
+				     pacl->a_entries[i + 1]);
+			}
+		}
+	}
+}
+
+static void
+sort_pacl(struct posix_acl *pacl)
+{
+	/* posix_acl_valid requires that users and groups be in order
+	 * by uid/gid. */
+	int i, j;
+
+	/* no users or groups */
+	if (!pacl || pacl->a_count <= 4)
+		return;
+
+	i = 1;
+	while (pacl->a_entries[i].e_tag == ACL_USER)
+		i++;
+	sort_pacl_range(pacl, 1, i-1);
+
+	BUG_ON(pacl->a_entries[i].e_tag != ACL_GROUP_OBJ);
+	j = ++i;
+	while (pacl->a_entries[j].e_tag == ACL_GROUP)
+		j++;
+	sort_pacl_range(pacl, i, j-1);
+	return;
+}
+
+/*
+ * While processing the NFSv4 ACE, this maintains bitmasks representing
+ * which permission bits have been allowed and which denied to a given
+ * entity: */
+struct posix_ace_state {
+	u32 allow;
+	u32 deny;
+};
+
+struct posix_user_ace_state {
+	union {
+		kuid_t uid;
+		kgid_t gid;
+	};
+	struct posix_ace_state perms;
+};
+
+struct posix_ace_state_array {
+	int n;
+	struct posix_user_ace_state aces[];
+};
+
+/*
+ * While processing the NFSv4 ACE, this maintains the partial permissions
+ * calculated so far: */
+
+struct posix_acl_state {
+	unsigned char valid;
+	struct posix_ace_state owner;
+	struct posix_ace_state group;
+	struct posix_ace_state other;
+	struct posix_ace_state everyone;
+	struct posix_ace_state mask; /* Deny unused in this case */
+	struct posix_ace_state_array *users;
+	struct posix_ace_state_array *groups;
+};
+
+static int
+init_state(struct posix_acl_state *state, int cnt)
+{
+	int alloc;
+
+	memset(state, 0, sizeof(struct posix_acl_state));
+	/*
+	 * In the worst case, each individual acl could be for a distinct
+	 * named user or group, but we don't know which, so we allocate
+	 * enough space for either:
+	 */
+	alloc = sizeof(struct posix_ace_state_array)
+		+ cnt*sizeof(struct posix_user_ace_state);
+	state->users = kzalloc(alloc, GFP_KERNEL);
+	if (!state->users)
+		return -ENOMEM;
+	state->groups = kzalloc(alloc, GFP_KERNEL);
+	if (!state->groups) {
+		kfree(state->users);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+static void
+free_state(struct posix_acl_state *state) {
+	kfree(state->users);
+	kfree(state->groups);
+}
+
+static inline void add_to_mask(struct posix_acl_state *state, struct posix_ace_state *astate)
+{
+	state->mask.allow |= astate->allow;
+}
+
+static struct posix_acl *
+posix_state_to_acl(struct posix_acl_state *state, unsigned int flags)
+{
+	struct posix_acl_entry *pace;
+	struct posix_acl *pacl;
+	int nace;
+	int i;
+
+	/*
+	 * ACLs with no ACEs are treated differently in the inheritable
+	 * and effective cases: when there are no inheritable ACEs,
+	 * calls ->set_acl with a NULL ACL structure.
+	 */
+	if (!state->valid && (flags & NFS4_ACL_TYPE_DEFAULT))
+		return NULL;
+
+	/*
+	 * When there are no effective ACEs, the following will end
+	 * up setting a 3-element effective posix ACL with all
+	 * permissions zero.
+	 */
+	if (!state->users->n && !state->groups->n)
+		nace = 3;
+	else /* Note we also include a MASK ACE in this case: */
+		nace = 4 + state->users->n + state->groups->n;
+	pacl = posix_acl_alloc(nace, GFP_KERNEL);
+	if (!pacl)
+		return ERR_PTR(-ENOMEM);
+
+	pace = pacl->a_entries;
+	pace->e_tag = ACL_USER_OBJ;
+	low_mode_from_nfs4(state->owner.allow, &pace->e_perm, flags);
+
+	for (i=0; i < state->users->n; i++) {
+		pace++;
+		pace->e_tag = ACL_USER;
+		low_mode_from_nfs4(state->users->aces[i].perms.allow,
+					&pace->e_perm, flags);
+		pace->e_uid = state->users->aces[i].uid;
+		add_to_mask(state, &state->users->aces[i].perms);
+	}
+
+	pace++;
+	pace->e_tag = ACL_GROUP_OBJ;
+	low_mode_from_nfs4(state->group.allow, &pace->e_perm, flags);
+	add_to_mask(state, &state->group);
+
+	for (i=0; i < state->groups->n; i++) {
+		pace++;
+		pace->e_tag = ACL_GROUP;
+		low_mode_from_nfs4(state->groups->aces[i].perms.allow,
+					&pace->e_perm, flags);
+		pace->e_gid = state->groups->aces[i].gid;
+		add_to_mask(state, &state->groups->aces[i].perms);
+	}
+
+	if (state->users->n || state->groups->n) {
+		pace++;
+		pace->e_tag = ACL_MASK;
+		low_mode_from_nfs4(state->mask.allow, &pace->e_perm, flags);
+	}
+
+	pace++;
+	pace->e_tag = ACL_OTHER;
+	low_mode_from_nfs4(state->other.allow, &pace->e_perm, flags);
+
+	return pacl;
+}
+
+static inline void allow_bits(struct posix_ace_state *astate, u32 mask)
+{
+	/* Allow all bits in the mask not already denied: */
+	astate->allow |= mask & ~astate->deny;
+}
+
+static inline void deny_bits(struct posix_ace_state *astate, u32 mask)
+{
+	/* Deny all bits in the mask not already allowed: */
+	astate->deny |= mask & ~astate->allow;
+}
+
+static int find_uid(struct posix_acl_state *state, kuid_t uid)
+{
+	struct posix_ace_state_array *a = state->users;
+	int i;
+
+	for (i = 0; i < a->n; i++)
+		if (uid_eq(a->aces[i].uid, uid))
+			return i;
+	/* Not found: */
+	a->n++;
+	a->aces[i].uid = uid;
+	a->aces[i].perms.allow = state->everyone.allow;
+	a->aces[i].perms.deny  = state->everyone.deny;
+
+	return i;
+}
+
+static int find_gid(struct posix_acl_state *state, kgid_t gid)
+{
+	struct posix_ace_state_array *a = state->groups;
+	int i;
+
+	for (i = 0; i < a->n; i++)
+		if (gid_eq(a->aces[i].gid, gid))
+			return i;
+	/* Not found: */
+	a->n++;
+	a->aces[i].gid = gid;
+	a->aces[i].perms.allow = state->everyone.allow;
+	a->aces[i].perms.deny  = state->everyone.deny;
+
+	return i;
+}
+
+static void deny_bits_array(struct posix_ace_state_array *a, u32 mask)
+{
+	int i;
+
+	for (i=0; i < a->n; i++)
+		deny_bits(&a->aces[i].perms, mask);
+}
+
+static void allow_bits_array(struct posix_ace_state_array *a, u32 mask)
+{
+	int i;
+
+	for (i=0; i < a->n; i++)
+		allow_bits(&a->aces[i].perms, mask);
+}
+
+static void process_one_v4_ace(struct posix_acl_state *state,
+				struct nfs4_ace *ace)
+{
+	u32 mask = ace->access_mask;
+	short type = ace2type(ace);
+	int i;
+
+	state->valid |= type;
+
+	switch (type) {
+	case ACL_USER_OBJ:
+		if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
+			allow_bits(&state->owner, mask);
+		} else {
+			deny_bits(&state->owner, mask);
+		}
+		break;
+	case ACL_USER:
+		i = find_uid(state, ace->who_uid);
+		if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
+			allow_bits(&state->users->aces[i].perms, mask);
+		} else {
+			deny_bits(&state->users->aces[i].perms, mask);
+			mask = state->users->aces[i].perms.deny;
+			deny_bits(&state->owner, mask);
+		}
+		break;
+	case ACL_GROUP_OBJ:
+		if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
+			allow_bits(&state->group, mask);
+		} else {
+			deny_bits(&state->group, mask);
+			mask = state->group.deny;
+			deny_bits(&state->owner, mask);
+			deny_bits(&state->everyone, mask);
+			deny_bits_array(state->users, mask);
+			deny_bits_array(state->groups, mask);
+		}
+		break;
+	case ACL_GROUP:
+		i = find_gid(state, ace->who_gid);
+		if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
+			allow_bits(&state->groups->aces[i].perms, mask);
+		} else {
+			deny_bits(&state->groups->aces[i].perms, mask);
+			mask = state->groups->aces[i].perms.deny;
+			deny_bits(&state->owner, mask);
+			deny_bits(&state->group, mask);
+			deny_bits(&state->everyone, mask);
+			deny_bits_array(state->users, mask);
+			deny_bits_array(state->groups, mask);
+		}
+		break;
+	case ACL_OTHER:
+		if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
+			allow_bits(&state->owner, mask);
+			allow_bits(&state->group, mask);
+			allow_bits(&state->other, mask);
+			allow_bits(&state->everyone, mask);
+			allow_bits_array(state->users, mask);
+			allow_bits_array(state->groups, mask);
+		} else {
+			deny_bits(&state->owner, mask);
+			deny_bits(&state->group, mask);
+			deny_bits(&state->other, mask);
+			deny_bits(&state->everyone, mask);
+			deny_bits_array(state->users, mask);
+			deny_bits_array(state->groups, mask);
+		}
+	}
+}
+
+static int nfs4_acl_nfsv4_to_posix(struct nfs4_acl *acl,
+		struct posix_acl **pacl, struct posix_acl **dpacl,
+		unsigned int flags)
+{
+	struct posix_acl_state effective_acl_state, default_acl_state;
+	struct nfs4_ace *ace;
+	int ret;
+
+	ret = init_state(&effective_acl_state, acl->naces);
+	if (ret)
+		return ret;
+	ret = init_state(&default_acl_state, acl->naces);
+	if (ret)
+		goto out_estate;
+	ret = -EINVAL;
+	for (ace = acl->aces; ace < acl->aces + acl->naces; ace++) {
+		if (ace->type != NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE &&
+		    ace->type != NFS4_ACE_ACCESS_DENIED_ACE_TYPE)
+			goto out_dstate;
+		if (ace->flag & ~NFS4_SUPPORTED_FLAGS)
+			goto out_dstate;
+		if ((ace->flag & NFS4_INHERITANCE_FLAGS) == 0) {
+			process_one_v4_ace(&effective_acl_state, ace);
+			continue;
+		}
+		if (!(flags & NFS4_ACL_DIR))
+			goto out_dstate;
+		/*
+		 * Note that when only one of FILE_INHERIT or DIRECTORY_INHERIT
+		 * is set, we're effectively turning on the other.  That's OK,
+		 * according to rfc 3530.
+		 */
+		process_one_v4_ace(&default_acl_state, ace);
+
+		if (!(ace->flag & NFS4_ACE_INHERIT_ONLY_ACE))
+			process_one_v4_ace(&effective_acl_state, ace);
+	}
+
+	/*
+	 * At this point, the default ACL may have zeroed-out entries for owner,
+	 * group and other. That usually results in a non-sensical resulting ACL
+	 * that denies all access except to any ACE that was explicitly added.
+	 *
+	 * The setfacl command solves a similar problem with this logic:
+	 *
+	 * "If  a  Default  ACL  entry is created, and the Default ACL contains
+	 *  no owner, owning group, or others entry,  a  copy of  the  ACL
+	 *  owner, owning group, or others entry is added to the Default ACL."
+	 *
+	 * Copy any missing ACEs from the effective set, if any ACEs were
+	 * explicitly set.
+	 */
+	if (default_acl_state.valid) {
+		if (!(default_acl_state.valid & ACL_USER_OBJ))
+			default_acl_state.owner = effective_acl_state.owner;
+		if (!(default_acl_state.valid & ACL_GROUP_OBJ))
+			default_acl_state.group = effective_acl_state.group;
+		if (!(default_acl_state.valid & ACL_OTHER))
+			default_acl_state.other = effective_acl_state.other;
+	}
+
+	*pacl = posix_state_to_acl(&effective_acl_state, flags);
+	if (IS_ERR(*pacl)) {
+		ret = PTR_ERR(*pacl);
+		*pacl = NULL;
+		goto out_dstate;
+	}
+	*dpacl = posix_state_to_acl(&default_acl_state,
+						flags | NFS4_ACL_TYPE_DEFAULT);
+	if (IS_ERR(*dpacl)) {
+		ret = PTR_ERR(*dpacl);
+		*dpacl = NULL;
+		posix_acl_release(*pacl);
+		*pacl = NULL;
+		goto out_dstate;
+	}
+	sort_pacl(*pacl);
+	sort_pacl(*dpacl);
+	ret = 0;
+out_dstate:
+	free_state(&default_acl_state);
+out_estate:
+	free_state(&effective_acl_state);
+	return ret;
+}
+
+__be32 nfsd4_acl_to_attr(enum nfs_ftype4 type, struct nfs4_acl *acl,
+			 struct nfsd_attrs *attr)
+{
+	int host_error;
+	unsigned int flags = 0;
+
+	if (!acl)
+		return nfs_ok;
+
+	if (type == NF4DIR)
+		flags = NFS4_ACL_DIR;
+
+	host_error = nfs4_acl_nfsv4_to_posix(acl, &attr->na_pacl,
+					     &attr->na_dpacl, flags);
+	if (host_error == -EINVAL)
+		return nfserr_attrnotsupp;
+	else
+		return nfserrno(host_error);
+}
+
+static short
+ace2type(struct nfs4_ace *ace)
+{
+	switch (ace->whotype) {
+		case NFS4_ACL_WHO_NAMED:
+			return (ace->flag & NFS4_ACE_IDENTIFIER_GROUP ?
+					ACL_GROUP : ACL_USER);
+		case NFS4_ACL_WHO_OWNER:
+			return ACL_USER_OBJ;
+		case NFS4_ACL_WHO_GROUP:
+			return ACL_GROUP_OBJ;
+		case NFS4_ACL_WHO_EVERYONE:
+			return ACL_OTHER;
+	}
+	BUG();
+	return -1;
+}
+
+/*
+ * return the size of the struct nfs4_acl required to represent an acl
+ * with @entries entries.
+ */
+int nfs4_acl_bytes(int entries)
+{
+	return sizeof(struct nfs4_acl) + entries * sizeof(struct nfs4_ace);
+}
+
+static struct {
+	char *string;
+	int   stringlen;
+	int type;
+} s2t_map[] = {
+	{
+		.string    = "OWNER@",
+		.stringlen = sizeof("OWNER@") - 1,
+		.type      = NFS4_ACL_WHO_OWNER,
+	},
+	{
+		.string    = "GROUP@",
+		.stringlen = sizeof("GROUP@") - 1,
+		.type      = NFS4_ACL_WHO_GROUP,
+	},
+	{
+		.string    = "EVERYONE@",
+		.stringlen = sizeof("EVERYONE@") - 1,
+		.type      = NFS4_ACL_WHO_EVERYONE,
+	},
+};
+
+int
+nfs4_acl_get_whotype(char *p, u32 len)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(s2t_map); i++) {
+		if (s2t_map[i].stringlen == len &&
+				0 == memcmp(s2t_map[i].string, p, len))
+			return s2t_map[i].type;
+	}
+	return NFS4_ACL_WHO_NAMED;
+}
+
+__be32 nfs4_acl_write_who(struct xdr_stream *xdr, int who)
+{
+	__be32 *p;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(s2t_map); i++) {
+		if (s2t_map[i].type != who)
+			continue;
+		p = xdr_reserve_space(xdr, s2t_map[i].stringlen + 4);
+		if (!p)
+			return nfserr_resource;
+		p = xdr_encode_opaque(p, s2t_map[i].string,
+					s2t_map[i].stringlen);
+		return 0;
+	}
+	WARN_ON_ONCE(1);
+	return nfserr_serverfault;
+}

linux-7.2.3/fs/nfsd/nfs4idmap.c

@@ -0,0 +1,732 @@
+/*
+ *  Mapping of UID/GIDs to name and vice versa.
+ *
+ *  Copyright (c) 2002, 2003 The Regents of the University of
+ *  Michigan.  All rights reserved.
+ *
+ *  Marius Aamodt Eriksen <marius@umich.edu>
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the University nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/sunrpc/svc_xprt.h>
+#include <net/net_namespace.h>
+#include "idmap.h"
+#include "nfsd.h"
+#include "netns.h"
+#include "vfs.h"
+
+/*
+ * Turn off idmapping when using AUTH_SYS.
+ */
+static bool nfs4_disable_idmapping = true;
+module_param(nfs4_disable_idmapping, bool, 0644);
+MODULE_PARM_DESC(nfs4_disable_idmapping,
+		"Turn off server's NFSv4 idmapping when using 'sec=sys'");
+
+/*
+ * Cache entry
+ */
+
+/*
+ * XXX we know that IDMAP_NAMESZ < PAGE_SIZE, but it's ugly to rely on
+ * that.
+ */
+
+struct ent {
+	struct cache_head h;
+	int               type;		       /* User / Group */
+	u32               id;
+	char              name[IDMAP_NAMESZ];
+	char              authname[IDMAP_NAMESZ];
+	struct rcu_head	  rcu_head;
+};
+
+/* Common entry handling */
+
+#define ENT_HASHBITS          8
+#define ENT_HASHMAX           (1 << ENT_HASHBITS)
+
+static void
+ent_init(struct cache_head *cnew, struct cache_head *citm)
+{
+	struct ent *new = container_of(cnew, struct ent, h);
+	struct ent *itm = container_of(citm, struct ent, h);
+
+	new->id = itm->id;
+	new->type = itm->type;
+
+	strscpy(new->name, itm->name, sizeof(new->name));
+	strscpy(new->authname, itm->authname, sizeof(new->authname));
+}
+
+static void
+ent_put(struct kref *ref)
+{
+	struct ent *map = container_of(ref, struct ent, h.ref);
+	kfree_rcu(map, rcu_head);
+}
+
+static struct cache_head *
+ent_alloc(void)
+{
+	struct ent *e = kmalloc_obj(*e);
+	if (e)
+		return &e->h;
+	else
+		return NULL;
+}
+
+/*
+ * ID -> Name cache
+ */
+
+static uint32_t
+idtoname_hash(struct ent *ent)
+{
+	uint32_t hash;
+
+	hash = hash_str(ent->authname, ENT_HASHBITS);
+	hash = hash_long(hash ^ ent->id, ENT_HASHBITS);
+
+	/* Flip LSB for user/group */
+	if (ent->type == IDMAP_TYPE_GROUP)
+		hash ^= 1;
+
+	return hash;
+}
+
+static int
+idtoname_upcall(struct cache_detail *cd, struct cache_head *h)
+{
+	return sunrpc_cache_upcall_warn(cd, h);
+}
+
+static void
+idtoname_request(struct cache_detail *cd, struct cache_head *ch, char **bpp,
+    int *blen)
+{
+ 	struct ent *ent = container_of(ch, struct ent, h);
+	char idstr[11];
+
+	qword_add(bpp, blen, ent->authname);
+	snprintf(idstr, sizeof(idstr), "%u", ent->id);
+	qword_add(bpp, blen, ent->type == IDMAP_TYPE_GROUP ? "group" : "user");
+	qword_add(bpp, blen, idstr);
+
+	(*bpp)[-1] = '\n';
+}
+
+static int
+idtoname_match(struct cache_head *ca, struct cache_head *cb)
+{
+	struct ent *a = container_of(ca, struct ent, h);
+	struct ent *b = container_of(cb, struct ent, h);
+
+	return (a->id == b->id && a->type == b->type &&
+	    strcmp(a->authname, b->authname) == 0);
+}
+
+static int
+idtoname_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h)
+{
+	struct ent *ent;
+
+	if (h == NULL) {
+		seq_puts(m, "#domain type id [name]\n");
+		return 0;
+	}
+	ent = container_of(h, struct ent, h);
+	seq_printf(m, "%s %s %u", ent->authname,
+			ent->type == IDMAP_TYPE_GROUP ? "group" : "user",
+			ent->id);
+	if (test_bit(CACHE_VALID, &h->flags))
+		seq_printf(m, " %s", ent->name);
+	seq_putc(m, '\n');
+	return 0;
+}
+
+static void
+warn_no_idmapd(struct cache_detail *detail, int has_died)
+{
+	printk("nfsd: nfsv4 idmapping failing: has idmapd %s?\n",
+			has_died ? "died" : "not been started");
+}
+
+
+static int         idtoname_parse(struct cache_detail *, char *, int);
+static struct ent *idtoname_lookup(struct cache_detail *, struct ent *);
+static struct ent *idtoname_update(struct cache_detail *, struct ent *,
+				   struct ent *);
+
+static const struct cache_detail idtoname_cache_template = {
+	.owner		= THIS_MODULE,
+	.hash_size	= ENT_HASHMAX,
+	.name		= "nfs4.idtoname",
+	.cache_put	= ent_put,
+	.cache_upcall	= idtoname_upcall,
+	.cache_request	= idtoname_request,
+	.cache_parse	= idtoname_parse,
+	.cache_show	= idtoname_show,
+	.warn_no_listener = warn_no_idmapd,
+	.match		= idtoname_match,
+	.init		= ent_init,
+	.update		= ent_init,
+	.alloc		= ent_alloc,
+};
+
+static int
+idtoname_parse(struct cache_detail *cd, char *buf, int buflen)
+{
+	struct ent ent, *res;
+	char *buf1, *bp;
+	int len;
+	int error = -EINVAL;
+
+	if (buf[buflen - 1] != '\n')
+		return (-EINVAL);
+	buf[buflen - 1]= '\0';
+
+	buf1 = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (buf1 == NULL)
+		return (-ENOMEM);
+
+	memset(&ent, 0, sizeof(ent));
+
+	/* Authentication name */
+	len = qword_get(&buf, buf1, PAGE_SIZE);
+	if (len <= 0 || len >= IDMAP_NAMESZ)
+		goto out;
+	memcpy(ent.authname, buf1, sizeof(ent.authname));
+
+	/* Type */
+	if (qword_get(&buf, buf1, PAGE_SIZE) <= 0)
+		goto out;
+	ent.type = strcmp(buf1, "user") == 0 ?
+		IDMAP_TYPE_USER : IDMAP_TYPE_GROUP;
+
+	/* ID */
+	if (qword_get(&buf, buf1, PAGE_SIZE) <= 0)
+		goto out;
+	ent.id = simple_strtoul(buf1, &bp, 10);
+	if (bp == buf1)
+		goto out;
+
+	/* expiry */
+	error = get_expiry(&buf, &ent.h.expiry_time);
+	if (error)
+		goto out;
+
+	error = -ENOMEM;
+	res = idtoname_lookup(cd, &ent);
+	if (!res)
+		goto out;
+
+	/* Name */
+	error = -EINVAL;
+	len = qword_get(&buf, buf1, PAGE_SIZE);
+	if (len < 0 || len >= IDMAP_NAMESZ)
+		goto out;
+	if (len == 0)
+		set_bit(CACHE_NEGATIVE, &ent.h.flags);
+	else
+		memcpy(ent.name, buf1, sizeof(ent.name));
+	error = -ENOMEM;
+	res = idtoname_update(cd, &ent, res);
+	if (res == NULL)
+		goto out;
+
+	cache_put(&res->h, cd);
+	error = 0;
+out:
+	kfree(buf1);
+	return error;
+}
+
+static struct ent *
+idtoname_lookup(struct cache_detail *cd, struct ent *item)
+{
+	struct cache_head *ch = sunrpc_cache_lookup_rcu(cd, &item->h,
+							idtoname_hash(item));
+	if (ch)
+		return container_of(ch, struct ent, h);
+	else
+		return NULL;
+}
+
+static struct ent *
+idtoname_update(struct cache_detail *cd, struct ent *new, struct ent *old)
+{
+	struct cache_head *ch = sunrpc_cache_update(cd, &new->h, &old->h,
+						    idtoname_hash(new));
+	if (ch)
+		return container_of(ch, struct ent, h);
+	else
+		return NULL;
+}
+
+
+/*
+ * Name -> ID cache
+ */
+
+static inline int
+nametoid_hash(struct ent *ent)
+{
+	return hash_str(ent->name, ENT_HASHBITS);
+}
+
+static int
+nametoid_upcall(struct cache_detail *cd, struct cache_head *h)
+{
+	return sunrpc_cache_upcall_warn(cd, h);
+}
+
+static void
+nametoid_request(struct cache_detail *cd, struct cache_head *ch, char **bpp,
+    int *blen)
+{
+ 	struct ent *ent = container_of(ch, struct ent, h);
+
+	qword_add(bpp, blen, ent->authname);
+	qword_add(bpp, blen, ent->type == IDMAP_TYPE_GROUP ? "group" : "user");
+	qword_add(bpp, blen, ent->name);
+
+	(*bpp)[-1] = '\n';
+}
+
+static int
+nametoid_match(struct cache_head *ca, struct cache_head *cb)
+{
+	struct ent *a = container_of(ca, struct ent, h);
+	struct ent *b = container_of(cb, struct ent, h);
+
+	return (a->type == b->type && strcmp(a->name, b->name) == 0 &&
+	    strcmp(a->authname, b->authname) == 0);
+}
+
+static int
+nametoid_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h)
+{
+	struct ent *ent;
+
+	if (h == NULL) {
+		seq_puts(m, "#domain type name [id]\n");
+		return 0;
+	}
+	ent = container_of(h, struct ent, h);
+	seq_printf(m, "%s %s %s", ent->authname,
+			ent->type == IDMAP_TYPE_GROUP ? "group" : "user",
+			ent->name);
+	if (test_bit(CACHE_VALID, &h->flags))
+		seq_printf(m, " %u", ent->id);
+	seq_putc(m, '\n');
+	return 0;
+}
+
+static struct ent *nametoid_lookup(struct cache_detail *, struct ent *);
+static struct ent *nametoid_update(struct cache_detail *, struct ent *,
+				   struct ent *);
+static int         nametoid_parse(struct cache_detail *, char *, int);
+
+static const struct cache_detail nametoid_cache_template = {
+	.owner		= THIS_MODULE,
+	.hash_size	= ENT_HASHMAX,
+	.name		= "nfs4.nametoid",
+	.cache_put	= ent_put,
+	.cache_upcall	= nametoid_upcall,
+	.cache_request	= nametoid_request,
+	.cache_parse	= nametoid_parse,
+	.cache_show	= nametoid_show,
+	.warn_no_listener = warn_no_idmapd,
+	.match		= nametoid_match,
+	.init		= ent_init,
+	.update		= ent_init,
+	.alloc		= ent_alloc,
+};
+
+static int
+nametoid_parse(struct cache_detail *cd, char *buf, int buflen)
+{
+	struct ent ent, *res;
+	char *buf1;
+	int len, error = -EINVAL;
+
+	if (buf[buflen - 1] != '\n')
+		return (-EINVAL);
+	buf[buflen - 1]= '\0';
+
+	buf1 = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (buf1 == NULL)
+		return (-ENOMEM);
+
+	memset(&ent, 0, sizeof(ent));
+
+	/* Authentication name */
+	len = qword_get(&buf, buf1, PAGE_SIZE);
+	if (len <= 0 || len >= IDMAP_NAMESZ)
+		goto out;
+	memcpy(ent.authname, buf1, sizeof(ent.authname));
+
+	/* Type */
+	if (qword_get(&buf, buf1, PAGE_SIZE) <= 0)
+		goto out;
+	ent.type = strcmp(buf1, "user") == 0 ?
+		IDMAP_TYPE_USER : IDMAP_TYPE_GROUP;
+
+	/* Name */
+	len = qword_get(&buf, buf1, PAGE_SIZE);
+	if (len <= 0 || len >= IDMAP_NAMESZ)
+		goto out;
+	memcpy(ent.name, buf1, sizeof(ent.name));
+
+	/* expiry */
+	error = get_expiry(&buf, &ent.h.expiry_time);
+	if (error)
+		goto out;
+
+	/* ID */
+	error = get_int(&buf, &ent.id);
+	if (error == -EINVAL)
+		goto out;
+	if (error == -ENOENT)
+		set_bit(CACHE_NEGATIVE, &ent.h.flags);
+
+	error = -ENOMEM;
+	res = nametoid_lookup(cd, &ent);
+	if (res == NULL)
+		goto out;
+	res = nametoid_update(cd, &ent, res);
+	if (res == NULL)
+		goto out;
+
+	cache_put(&res->h, cd);
+	error = 0;
+out:
+	kfree(buf1);
+	return (error);
+}
+
+
+static struct ent *
+nametoid_lookup(struct cache_detail *cd, struct ent *item)
+{
+	struct cache_head *ch = sunrpc_cache_lookup_rcu(cd, &item->h,
+							nametoid_hash(item));
+	if (ch)
+		return container_of(ch, struct ent, h);
+	else
+		return NULL;
+}
+
+static struct ent *
+nametoid_update(struct cache_detail *cd, struct ent *new, struct ent *old)
+{
+	struct cache_head *ch = sunrpc_cache_update(cd, &new->h, &old->h,
+						    nametoid_hash(new));
+	if (ch)
+		return container_of(ch, struct ent, h);
+	else
+		return NULL;
+}
+
+/*
+ * Exported API
+ */
+
+int
+nfsd_idmap_init(struct net *net)
+{
+	int rv;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	nn->idtoname_cache = cache_create_net(&idtoname_cache_template, net);
+	if (IS_ERR(nn->idtoname_cache))
+		return PTR_ERR(nn->idtoname_cache);
+	rv = cache_register_net(nn->idtoname_cache, net);
+	if (rv)
+		goto destroy_idtoname_cache;
+	nn->nametoid_cache = cache_create_net(&nametoid_cache_template, net);
+	if (IS_ERR(nn->nametoid_cache)) {
+		rv = PTR_ERR(nn->nametoid_cache);
+		goto unregister_idtoname_cache;
+	}
+	rv = cache_register_net(nn->nametoid_cache, net);
+	if (rv)
+		goto destroy_nametoid_cache;
+	return 0;
+
+destroy_nametoid_cache:
+	cache_destroy_net(nn->nametoid_cache, net);
+unregister_idtoname_cache:
+	cache_unregister_net(nn->idtoname_cache, net);
+destroy_idtoname_cache:
+	cache_destroy_net(nn->idtoname_cache, net);
+	return rv;
+}
+
+void
+nfsd_idmap_shutdown(struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	cache_unregister_net(nn->idtoname_cache, net);
+	cache_unregister_net(nn->nametoid_cache, net);
+	cache_destroy_net(nn->idtoname_cache, net);
+	cache_destroy_net(nn->nametoid_cache, net);
+}
+
+static int
+idmap_lookup(struct svc_rqst *rqstp,
+		struct ent *(*lookup_fn)(struct cache_detail *, struct ent *),
+		struct ent *key, struct cache_detail *detail, struct ent **item)
+{
+	int ret;
+
+	*item = lookup_fn(detail, key);
+	if (!*item)
+		return -ENOMEM;
+ retry:
+	ret = cache_check(detail, &(*item)->h, &rqstp->rq_chandle);
+
+	if (ret == -ETIMEDOUT) {
+		struct ent *prev_item = *item;
+		*item = lookup_fn(detail, key);
+		if (*item != prev_item)
+			goto retry;
+		cache_put(&(*item)->h, detail);
+	}
+	return ret;
+}
+
+static char *
+rqst_authname(struct svc_rqst *rqstp)
+{
+	struct auth_domain *clp;
+
+	clp = rqstp->rq_gssclient ? rqstp->rq_gssclient : rqstp->rq_client;
+	return clp->name;
+}
+
+static __be32
+idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen,
+		u32 *id)
+{
+	struct ent *item, key = {
+		.type = type,
+	};
+	int ret;
+	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+
+	if (namelen + 1 > sizeof(key.name))
+		return nfserr_badowner;
+	memcpy(key.name, name, namelen);
+	key.name[namelen] = '\0';
+	strscpy(key.authname, rqst_authname(rqstp), sizeof(key.authname));
+	ret = idmap_lookup(rqstp, nametoid_lookup, &key, nn->nametoid_cache, &item);
+	if (ret == -ENOENT)
+		return nfserr_badowner;
+	if (ret)
+		return nfserrno(ret);
+	*id = item->id;
+	cache_put(&item->h, nn->nametoid_cache);
+	return 0;
+}
+
+static __be32 encode_ascii_id(struct xdr_stream *xdr, u32 id)
+{
+	char buf[11];
+	int len;
+	__be32 *p;
+
+	len = sprintf(buf, "%u", id);
+	p = xdr_reserve_space(xdr, len + 4);
+	if (!p)
+		return nfserr_resource;
+	p = xdr_encode_opaque(p, buf, len);
+	return 0;
+}
+
+static __be32 idmap_id_to_name(struct xdr_stream *xdr,
+			       struct svc_rqst *rqstp, int type, u32 id)
+{
+	struct ent *item, key = {
+		.id = id,
+		.type = type,
+	};
+	__be32 status = nfs_ok;
+	__be32 *p;
+	int ret;
+	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+
+	strscpy(key.authname, rqst_authname(rqstp), sizeof(key.authname));
+	ret = idmap_lookup(rqstp, idtoname_lookup, &key, nn->idtoname_cache, &item);
+	if (ret == -ENOENT)
+		return encode_ascii_id(xdr, id);
+	if (ret)
+		return nfserrno(ret);
+	ret = strlen(item->name);
+	WARN_ON_ONCE(ret > IDMAP_NAMESZ);
+
+	p = xdr_reserve_space(xdr, ret + 4);
+	if (unlikely(!p)) {
+		status = nfserr_resource;
+		goto out_put;
+	}
+	xdr_encode_opaque(p, item->name, ret);
+out_put:
+	cache_put(&item->h, nn->idtoname_cache);
+	return status;
+}
+
+static bool
+numeric_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, u32 *id)
+{
+	int ret;
+	char buf[11];
+
+	if (namelen + 1 > sizeof(buf))
+		/* too long to represent a 32-bit id: */
+		return false;
+	/* Just to make sure it's null-terminated: */
+	memcpy(buf, name, namelen);
+	buf[namelen] = '\0';
+	ret = kstrtouint(buf, 10, id);
+	return ret == 0;
+}
+
+static __be32
+do_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, u32 *id)
+{
+	if (nfs4_disable_idmapping && rqstp->rq_cred.cr_flavor < RPC_AUTH_GSS)
+		if (numeric_name_to_id(rqstp, type, name, namelen, id))
+			return 0;
+		/*
+		 * otherwise, fall through and try idmapping, for
+		 * backwards compatibility with clients sending names:
+		 */
+	return idmap_name_to_id(rqstp, type, name, namelen, id);
+}
+
+static __be32 encode_name_from_id(struct xdr_stream *xdr,
+				  struct svc_rqst *rqstp, int type, u32 id)
+{
+	if (nfs4_disable_idmapping && rqstp->rq_cred.cr_flavor < RPC_AUTH_GSS)
+		return encode_ascii_id(xdr, id);
+	return idmap_id_to_name(xdr, rqstp, type, id);
+}
+
+/**
+ * nfsd_map_name_to_uid - Map user@domain to local UID
+ * @rqstp: RPC execution context
+ * @name: user@domain name to be mapped
+ * @namelen: length of name, in bytes
+ * @uid: OUT: mapped local UID value
+ *
+ * Returns nfs_ok on success or an NFSv4 status code on failure.
+ */
+__be32 nfsd_map_name_to_uid(struct svc_rqst *rqstp, const char *name,
+			    size_t namelen, kuid_t *uid)
+{
+	__be32 status;
+	u32 id = -1;
+
+	/*
+	 * The idmap lookup below triggers an upcall that invokes
+	 * cache_check(). RQ_USEDEFERRAL must be clear to prevent
+	 * cache_check() from setting RQ_DROPME via svc_defer().
+	 * NFSv4 servers are not permitted to drop requests. Also
+	 * RQ_DROPME will force NFSv4.1 session slot processing to
+	 * be skipped.
+	 */
+	WARN_ON_ONCE(test_bit(RQ_USEDEFERRAL, &rqstp->rq_flags));
+
+	if (name == NULL || namelen == 0)
+		return nfserr_inval;
+
+	status = do_name_to_id(rqstp, IDMAP_TYPE_USER, name, namelen, &id);
+	if (status)
+		return status;
+	*uid = make_kuid(nfsd_user_namespace(rqstp), id);
+	if (!uid_valid(*uid))
+		status = nfserr_badowner;
+	return status;
+}
+
+/**
+ * nfsd_map_name_to_gid - Map user@domain to local GID
+ * @rqstp: RPC execution context
+ * @name: user@domain name to be mapped
+ * @namelen: length of name, in bytes
+ * @gid: OUT: mapped local GID value
+ *
+ * Returns nfs_ok on success or an NFSv4 status code on failure.
+ */
+__be32 nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name,
+			    size_t namelen, kgid_t *gid)
+{
+	__be32 status;
+	u32 id = -1;
+
+	/*
+	 * The idmap lookup below triggers an upcall that invokes
+	 * cache_check(). RQ_USEDEFERRAL must be clear to prevent
+	 * cache_check() from setting RQ_DROPME via svc_defer().
+	 * NFSv4 servers are not permitted to drop requests. Also
+	 * RQ_DROPME will force NFSv4.1 session slot processing to
+	 * be skipped.
+	 */
+	WARN_ON_ONCE(test_bit(RQ_USEDEFERRAL, &rqstp->rq_flags));
+
+	if (name == NULL || namelen == 0)
+		return nfserr_inval;
+
+	status = do_name_to_id(rqstp, IDMAP_TYPE_GROUP, name, namelen, &id);
+	if (status)
+		return status;
+	*gid = make_kgid(nfsd_user_namespace(rqstp), id);
+	if (!gid_valid(*gid))
+		status = nfserr_badowner;
+	return status;
+}
+
+__be32 nfsd4_encode_user(struct xdr_stream *xdr, struct svc_rqst *rqstp,
+			 kuid_t uid)
+{
+	u32 id = from_kuid_munged(nfsd_user_namespace(rqstp), uid);
+	return encode_name_from_id(xdr, rqstp, IDMAP_TYPE_USER, id);
+}
+
+__be32 nfsd4_encode_group(struct xdr_stream *xdr, struct svc_rqst *rqstp,
+			  kgid_t gid)
+{
+	u32 id = from_kgid_munged(nfsd_user_namespace(rqstp), gid);
+	return encode_name_from_id(xdr, rqstp, IDMAP_TYPE_GROUP, id);
+}

linux-7.2.3/fs/nfsd/nfs4layouts.c

@@ -0,0 +1,956 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+#include <linux/exportfs_block.h>
+#include <linux/kmod.h>
+#include <linux/file.h>
+#include <linux/jhash.h>
+#include <linux/sched.h>
+#include <linux/sunrpc/addr.h>
+
+#include "pnfs.h"
+#include "netns.h"
+#include "trace.h"
+
+#define NFSDDBG_FACILITY                NFSDDBG_PNFS
+
+struct nfs4_layout {
+	struct list_head		lo_perstate;
+	struct nfs4_layout_stateid	*lo_state;
+	struct nfsd4_layout_seg		lo_seg;
+};
+
+static struct kmem_cache *nfs4_layout_cache;
+static struct kmem_cache *nfs4_layout_stateid_cache;
+
+static const struct nfsd4_callback_ops nfsd4_cb_layout_ops;
+static const struct lease_manager_operations nfsd4_layouts_lm_ops;
+
+static void nfsd4_layout_fence_worker(struct work_struct *work);
+
+const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] =  {
+#ifdef CONFIG_NFSD_FLEXFILELAYOUT
+	[LAYOUT_FLEX_FILES]	= &ff_layout_ops,
+#endif
+#ifdef CONFIG_NFSD_BLOCKLAYOUT
+	[LAYOUT_BLOCK_VOLUME]	= &bl_layout_ops,
+#endif
+#ifdef CONFIG_NFSD_SCSILAYOUT
+	[LAYOUT_SCSI]		= &scsi_layout_ops,
+#endif
+};
+
+/* pNFS device ID to export fsid mapping */
+#define DEVID_HASH_BITS	8
+#define DEVID_HASH_SIZE	(1 << DEVID_HASH_BITS)
+#define DEVID_HASH_MASK	(DEVID_HASH_SIZE - 1)
+static u64 nfsd_devid_seq = 1;
+static struct list_head nfsd_devid_hash[DEVID_HASH_SIZE];
+static DEFINE_SPINLOCK(nfsd_devid_lock);
+
+static inline u32 devid_hashfn(u64 idx)
+{
+	return jhash_2words(idx, idx >> 32, 0) & DEVID_HASH_MASK;
+}
+
+static void
+nfsd4_alloc_devid_map(const struct svc_fh *fhp)
+{
+	const struct knfsd_fh *fh = &fhp->fh_handle;
+	size_t fsid_len = key_len(fh->fh_fsid_type);
+	struct nfsd4_deviceid_map *map, *old;
+	int i;
+
+	map = kzalloc(sizeof(*map) + fsid_len, GFP_KERNEL);
+	if (!map)
+		return;
+
+	map->fsid_type = fh->fh_fsid_type;
+	memcpy(&map->fsid, fh_fsid(fh), fsid_len);
+
+	spin_lock(&nfsd_devid_lock);
+	if (fhp->fh_export->ex_devid_map)
+		goto out_unlock;
+
+	for (i = 0; i < DEVID_HASH_SIZE; i++) {
+		list_for_each_entry(old, &nfsd_devid_hash[i], hash) {
+			if (old->fsid_type != fh->fh_fsid_type)
+				continue;
+			if (memcmp(old->fsid, fh_fsid(fh),
+					key_len(old->fsid_type)))
+				continue;
+
+			fhp->fh_export->ex_devid_map = old;
+			goto out_unlock;
+		}
+	}
+
+	map->idx = nfsd_devid_seq++;
+	list_add_tail_rcu(&map->hash, &nfsd_devid_hash[devid_hashfn(map->idx)]);
+	fhp->fh_export->ex_devid_map = map;
+	map = NULL;
+
+out_unlock:
+	spin_unlock(&nfsd_devid_lock);
+	kfree(map);
+}
+
+struct nfsd4_deviceid_map *
+nfsd4_find_devid_map(int idx)
+{
+	struct nfsd4_deviceid_map *map, *ret = NULL;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(map, &nfsd_devid_hash[devid_hashfn(idx)], hash)
+		if (map->idx == idx)
+			ret = map;
+	rcu_read_unlock();
+
+	return ret;
+}
+
+int
+nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp,
+		u32 device_generation)
+{
+	if (!fhp->fh_export->ex_devid_map) {
+		nfsd4_alloc_devid_map(fhp);
+		if (!fhp->fh_export->ex_devid_map)
+			return -ENOMEM;
+	}
+
+	id->fsid_idx = fhp->fh_export->ex_devid_map->idx;
+	id->generation = device_generation;
+	return 0;
+}
+
+void nfsd4_setup_layout_type(struct svc_export *exp)
+{
+	struct super_block *sb = exp->ex_path.mnt->mnt_sb;
+	expfs_block_layouts_t block_supported = exportfs_layouts_supported(sb);
+
+	if (IS_ENABLED(CONFIG_NFSD_FLEXFILELAYOUT))
+		exp->ex_layout_types |= 1 << LAYOUT_FLEX_FILES;
+	if (IS_ENABLED(CONFIG_NFSD_BLOCKLAYOUT) &&
+	    (block_supported & EXPFS_BLOCK_IN_BAND_ID))
+		exp->ex_layout_types |= 1 << LAYOUT_BLOCK_VOLUME;
+	if (IS_ENABLED(CONFIG_NFSD_SCSILAYOUT) &&
+	    (block_supported & EXPFS_BLOCK_OUT_OF_BAND_ID))
+		exp->ex_layout_types |= 1 << LAYOUT_SCSI;
+}
+
+void nfsd4_close_layout(struct nfs4_layout_stateid *ls)
+{
+	struct nfsd_file *fl;
+
+	spin_lock(&ls->ls_stid.sc_file->fi_lock);
+	fl = ls->ls_file;
+	ls->ls_file = NULL;
+	spin_unlock(&ls->ls_stid.sc_file->fi_lock);
+
+	if (fl) {
+		if (!nfsd4_layout_ops[ls->ls_layout_type]->disable_recalls)
+			kernel_setlease(fl->nf_file, F_UNLCK, NULL,
+					(void **)&ls);
+		nfsd_file_put(fl);
+	}
+}
+
+static void
+nfsd4_free_layout_stateid(struct nfs4_stid *stid)
+{
+	struct nfs4_layout_stateid *ls = layoutstateid(stid);
+	struct nfs4_client *clp = ls->ls_stid.sc_client;
+	struct nfs4_file *fp = ls->ls_stid.sc_file;
+
+	trace_nfsd_layoutstate_free(&ls->ls_stid.sc_stateid);
+
+	spin_lock(&ls->ls_lock);
+	if (delayed_work_pending(&ls->ls_fence_work)) {
+		spin_unlock(&ls->ls_lock);
+		cancel_delayed_work_sync(&ls->ls_fence_work);
+	} else
+		spin_unlock(&ls->ls_lock);
+
+	spin_lock(&clp->cl_lock);
+	list_del_init(&ls->ls_perclnt);
+	spin_unlock(&clp->cl_lock);
+
+	spin_lock(&fp->fi_lock);
+	list_del_init(&ls->ls_perfile);
+	spin_unlock(&fp->fi_lock);
+
+	nfsd4_close_layout(ls);
+
+	if (ls->ls_recalled)
+		atomic_dec(&ls->ls_stid.sc_file->fi_lo_recalls);
+
+	kmem_cache_free(nfs4_layout_stateid_cache, ls);
+}
+
+static int
+nfsd4_layout_setlease(struct nfs4_layout_stateid *ls)
+{
+	struct file_lease *fl;
+	int status;
+
+	if (nfsd4_layout_ops[ls->ls_layout_type]->disable_recalls)
+		return 0;
+
+	fl = locks_alloc_lease();
+	if (!fl)
+		return -ENOMEM;
+	locks_init_lease(fl);
+	fl->fl_lmops = &nfsd4_layouts_lm_ops;
+	fl->c.flc_flags = FL_LAYOUT;
+	fl->c.flc_type = F_RDLCK;
+	fl->c.flc_owner = ls;
+	fl->c.flc_pid = current->tgid;
+	fl->c.flc_file = ls->ls_file->nf_file;
+
+	status = kernel_setlease(fl->c.flc_file, fl->c.flc_type, &fl, NULL);
+	if (status) {
+		locks_free_lease(fl);
+		return status;
+	}
+	BUG_ON(fl != NULL);
+	return 0;
+}
+
+static struct nfs4_layout_stateid *
+nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate,
+		struct nfs4_stid *parent, u32 layout_type)
+{
+	struct nfs4_client *clp = cstate->clp;
+	struct nfs4_file *fp = parent->sc_file;
+	struct nfs4_layout_stateid *ls;
+	struct nfs4_stid *stp;
+
+	stp = nfs4_alloc_stid(cstate->clp, nfs4_layout_stateid_cache,
+					nfsd4_free_layout_stateid);
+	if (!stp)
+		return NULL;
+
+	get_nfs4_file(fp);
+	stp->sc_file = fp;
+	if (parent->sc_export)
+		stp->sc_export = exp_get(parent->sc_export);
+
+	ls = layoutstateid(stp);
+	INIT_LIST_HEAD(&ls->ls_perclnt);
+	INIT_LIST_HEAD(&ls->ls_perfile);
+	spin_lock_init(&ls->ls_lock);
+	INIT_LIST_HEAD(&ls->ls_layouts);
+	mutex_init(&ls->ls_mutex);
+	ls->ls_layout_type = layout_type;
+	nfsd4_init_cb(&ls->ls_recall, clp, &nfsd4_cb_layout_ops,
+			NFSPROC4_CLNT_CB_LAYOUT);
+
+	if (parent->sc_type == SC_TYPE_DELEG)
+		ls->ls_file = nfsd_file_get(fp->fi_deleg_file);
+	else
+		ls->ls_file = find_any_file(fp);
+	BUG_ON(!ls->ls_file);
+
+	ls->ls_fenced = false;
+	ls->ls_fence_delay = 0;
+	INIT_DELAYED_WORK(&ls->ls_fence_work, nfsd4_layout_fence_worker);
+
+	if (nfsd4_layout_setlease(ls)) {
+		nfs4_put_stid(stp);
+		return NULL;
+	}
+
+	spin_lock(&clp->cl_lock);
+	stp->sc_type = SC_TYPE_LAYOUT;
+	list_add(&ls->ls_perclnt, &clp->cl_lo_states);
+	spin_unlock(&clp->cl_lock);
+
+	spin_lock(&fp->fi_lock);
+	list_add(&ls->ls_perfile, &fp->fi_lo_states);
+	spin_unlock(&fp->fi_lock);
+
+	trace_nfsd_layoutstate_alloc(&ls->ls_stid.sc_stateid);
+	return ls;
+}
+
+__be32
+nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate, stateid_t *stateid,
+		bool create, u32 layout_type, struct nfs4_layout_stateid **lsp)
+{
+	struct nfs4_layout_stateid *ls;
+	struct nfs4_stid *stid;
+	unsigned short typemask = SC_TYPE_LAYOUT;
+	__be32 status;
+
+	if (create)
+		typemask |= (SC_TYPE_OPEN | SC_TYPE_LOCK | SC_TYPE_DELEG);
+
+	status = nfsd4_lookup_stateid(cstate, stateid, typemask, 0, &stid,
+			net_generic(SVC_NET(rqstp), nfsd_net_id));
+	if (status)
+		goto out;
+
+	if (!fh_match(&cstate->current_fh.fh_handle,
+		      &stid->sc_file->fi_fhandle)) {
+		status = nfserr_bad_stateid;
+		goto out_put_stid;
+	}
+
+	if (stid->sc_type != SC_TYPE_LAYOUT) {
+		ls = nfsd4_alloc_layout_stateid(cstate, stid, layout_type);
+		nfs4_put_stid(stid);
+
+		status = nfserr_jukebox;
+		if (!ls)
+			goto out;
+		mutex_lock(&ls->ls_mutex);
+	} else {
+		ls = container_of(stid, struct nfs4_layout_stateid, ls_stid);
+
+		status = nfserr_bad_stateid;
+		mutex_lock(&ls->ls_mutex);
+		if (nfsd4_stateid_generation_after(stateid, &stid->sc_stateid))
+			goto out_unlock_stid;
+		if (layout_type != ls->ls_layout_type)
+			goto out_unlock_stid;
+	}
+
+	*lsp = ls;
+	return 0;
+
+out_unlock_stid:
+	mutex_unlock(&ls->ls_mutex);
+out_put_stid:
+	nfs4_put_stid(stid);
+out:
+	return status;
+}
+
+static void
+nfsd4_recall_file_layout(struct nfs4_layout_stateid *ls)
+{
+	spin_lock(&ls->ls_lock);
+	if (ls->ls_recalled)
+		goto out_unlock;
+
+	if (list_empty(&ls->ls_layouts))
+		goto out_unlock;
+
+	ls->ls_recalled = true;
+	atomic_inc(&ls->ls_stid.sc_file->fi_lo_recalls);
+	trace_nfsd_layout_recall(&ls->ls_stid.sc_stateid);
+
+	if (!test_and_set_bit(NFSD4_CALLBACK_RUNNING, &ls->ls_recall.cb_flags)) {
+		refcount_inc(&ls->ls_stid.sc_count);
+		nfsd4_run_cb(&ls->ls_recall);
+	}
+out_unlock:
+	spin_unlock(&ls->ls_lock);
+}
+
+static inline u64
+layout_end(struct nfsd4_layout_seg *seg)
+{
+	u64 end = seg->offset + seg->length;
+	return end >= seg->offset ? end : NFS4_MAX_UINT64;
+}
+
+static void
+layout_update_len(struct nfsd4_layout_seg *lo, u64 end)
+{
+	if (end == NFS4_MAX_UINT64)
+		lo->length = NFS4_MAX_UINT64;
+	else
+		lo->length = end - lo->offset;
+}
+
+static bool
+layouts_overlapping(struct nfs4_layout *lo, struct nfsd4_layout_seg *s)
+{
+	if (s->iomode != IOMODE_ANY && s->iomode != lo->lo_seg.iomode)
+		return false;
+	if (layout_end(&lo->lo_seg) <= s->offset)
+		return false;
+	if (layout_end(s) <= lo->lo_seg.offset)
+		return false;
+	return true;
+}
+
+static bool
+layouts_try_merge(struct nfsd4_layout_seg *lo, struct nfsd4_layout_seg *new)
+{
+	if (lo->iomode != new->iomode)
+		return false;
+	if (layout_end(new) < lo->offset)
+		return false;
+	if (layout_end(lo) < new->offset)
+		return false;
+
+	lo->offset = min(lo->offset, new->offset);
+	layout_update_len(lo, max(layout_end(lo), layout_end(new)));
+	return true;
+}
+
+static __be32
+nfsd4_recall_conflict(struct nfs4_layout_stateid *ls)
+{
+	struct nfs4_file *fp = ls->ls_stid.sc_file;
+	struct nfs4_layout_stateid *l, *n;
+	__be32 nfserr = nfs_ok;
+
+	assert_spin_locked(&fp->fi_lock);
+
+	list_for_each_entry_safe(l, n, &fp->fi_lo_states, ls_perfile) {
+		if (l != ls) {
+			nfsd4_recall_file_layout(l);
+			nfserr = nfserr_recallconflict;
+		}
+	}
+
+	return nfserr;
+}
+
+__be32
+nfsd4_insert_layout(struct nfsd4_layoutget *lgp, struct nfs4_layout_stateid *ls)
+{
+	struct nfsd4_layout_seg *seg = &lgp->lg_seg;
+	struct nfs4_file *fp = ls->ls_stid.sc_file;
+	struct nfs4_layout *lp, *new = NULL;
+	__be32 nfserr;
+
+	spin_lock(&fp->fi_lock);
+	nfserr = nfsd4_recall_conflict(ls);
+	if (nfserr)
+		goto out;
+	spin_lock(&ls->ls_lock);
+	list_for_each_entry(lp, &ls->ls_layouts, lo_perstate) {
+		if (layouts_try_merge(&lp->lo_seg, seg))
+			goto done;
+	}
+	spin_unlock(&ls->ls_lock);
+	spin_unlock(&fp->fi_lock);
+
+	new = kmem_cache_alloc(nfs4_layout_cache, GFP_KERNEL);
+	if (!new)
+		return nfserr_jukebox;
+	memcpy(&new->lo_seg, seg, sizeof(new->lo_seg));
+	new->lo_state = ls;
+
+	spin_lock(&fp->fi_lock);
+	nfserr = nfsd4_recall_conflict(ls);
+	if (nfserr)
+		goto out;
+	spin_lock(&ls->ls_lock);
+	list_for_each_entry(lp, &ls->ls_layouts, lo_perstate) {
+		if (layouts_try_merge(&lp->lo_seg, seg))
+			goto done;
+	}
+
+	refcount_inc(&ls->ls_stid.sc_count);
+	list_add_tail(&new->lo_perstate, &ls->ls_layouts);
+	new = NULL;
+done:
+	nfs4_inc_and_copy_stateid(&lgp->lg_sid, &ls->ls_stid);
+	spin_unlock(&ls->ls_lock);
+out:
+	spin_unlock(&fp->fi_lock);
+	if (new)
+		kmem_cache_free(nfs4_layout_cache, new);
+	return nfserr;
+}
+
+static void
+nfsd4_free_layouts(struct list_head *reaplist)
+{
+	while (!list_empty(reaplist)) {
+		struct nfs4_layout *lp = list_first_entry(reaplist,
+				struct nfs4_layout, lo_perstate);
+
+		list_del(&lp->lo_perstate);
+		nfs4_put_stid(&lp->lo_state->ls_stid);
+		kmem_cache_free(nfs4_layout_cache, lp);
+	}
+}
+
+static void
+nfsd4_return_file_layout(struct nfs4_layout *lp, struct nfsd4_layout_seg *seg,
+		struct list_head *reaplist)
+{
+	struct nfsd4_layout_seg *lo = &lp->lo_seg;
+	u64 end = layout_end(lo);
+
+	if (seg->offset <= lo->offset) {
+		if (layout_end(seg) >= end) {
+			list_move_tail(&lp->lo_perstate, reaplist);
+			return;
+		}
+		lo->offset = layout_end(seg);
+	} else {
+		/* retain the whole layout segment on a split. */
+		if (layout_end(seg) < end) {
+			dprintk("%s: split not supported\n", __func__);
+			return;
+		}
+		end = seg->offset;
+	}
+
+	layout_update_len(lo, end);
+}
+
+__be32
+nfsd4_return_file_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp)
+{
+	struct nfs4_layout_stateid *ls;
+	struct nfs4_layout *lp, *n;
+	LIST_HEAD(reaplist);
+	__be32 nfserr;
+	int found = 0;
+
+	nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lrp->lr_sid,
+						false, lrp->lr_layout_type,
+						&ls);
+	if (nfserr) {
+		trace_nfsd_layout_return_lookup_fail(&lrp->lr_sid);
+		return nfserr;
+	}
+
+	spin_lock(&ls->ls_lock);
+	list_for_each_entry_safe(lp, n, &ls->ls_layouts, lo_perstate) {
+		if (layouts_overlapping(lp, &lrp->lr_seg)) {
+			nfsd4_return_file_layout(lp, &lrp->lr_seg, &reaplist);
+			found++;
+		}
+	}
+	if (!list_empty(&ls->ls_layouts)) {
+		if (found)
+			nfs4_inc_and_copy_stateid(&lrp->lr_sid, &ls->ls_stid);
+		lrp->lrs_present = true;
+	} else {
+		trace_nfsd_layoutstate_unhash(&ls->ls_stid.sc_stateid);
+		ls->ls_stid.sc_status |= SC_STATUS_CLOSED;
+		lrp->lrs_present = false;
+	}
+	spin_unlock(&ls->ls_lock);
+
+	mutex_unlock(&ls->ls_mutex);
+	nfs4_put_stid(&ls->ls_stid);
+	nfsd4_free_layouts(&reaplist);
+	return nfs_ok;
+}
+
+__be32
+nfsd4_return_client_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp)
+{
+	struct nfs4_layout_stateid *ls, *n;
+	struct nfs4_client *clp = cstate->clp;
+	struct nfs4_layout *lp, *t;
+	LIST_HEAD(reaplist);
+
+	lrp->lrs_present = false;
+
+	spin_lock(&clp->cl_lock);
+	list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt) {
+		if (ls->ls_layout_type != lrp->lr_layout_type)
+			continue;
+
+		if (lrp->lr_return_type == RETURN_FSID &&
+		    !fh_fsid_match(&ls->ls_stid.sc_file->fi_fhandle,
+				   &cstate->current_fh.fh_handle))
+			continue;
+
+		spin_lock(&ls->ls_lock);
+		list_for_each_entry_safe(lp, t, &ls->ls_layouts, lo_perstate) {
+			if (lrp->lr_seg.iomode == IOMODE_ANY ||
+			    lrp->lr_seg.iomode == lp->lo_seg.iomode)
+				list_move_tail(&lp->lo_perstate, &reaplist);
+		}
+		spin_unlock(&ls->ls_lock);
+	}
+	spin_unlock(&clp->cl_lock);
+
+	nfsd4_free_layouts(&reaplist);
+	return 0;
+}
+
+static void
+nfsd4_return_all_layouts(struct nfs4_layout_stateid *ls,
+		struct list_head *reaplist)
+{
+	spin_lock(&ls->ls_lock);
+	list_splice_init(&ls->ls_layouts, reaplist);
+	spin_unlock(&ls->ls_lock);
+}
+
+void
+nfsd4_return_all_client_layouts(struct nfs4_client *clp)
+{
+	struct nfs4_layout_stateid *ls, *n;
+	LIST_HEAD(reaplist);
+
+	spin_lock(&clp->cl_lock);
+	list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt)
+		nfsd4_return_all_layouts(ls, &reaplist);
+	spin_unlock(&clp->cl_lock);
+
+	nfsd4_free_layouts(&reaplist);
+}
+
+void
+nfsd4_return_all_file_layouts(struct nfs4_client *clp, struct nfs4_file *fp)
+{
+	struct nfs4_layout_stateid *ls, *n;
+	LIST_HEAD(reaplist);
+
+	spin_lock(&fp->fi_lock);
+	list_for_each_entry_safe(ls, n, &fp->fi_lo_states, ls_perfile) {
+		if (ls->ls_stid.sc_client == clp)
+			nfsd4_return_all_layouts(ls, &reaplist);
+	}
+	spin_unlock(&fp->fi_lock);
+
+	nfsd4_free_layouts(&reaplist);
+}
+
+static void
+nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls, struct nfsd_file *file)
+{
+	struct nfs4_client *clp = ls->ls_stid.sc_client;
+	char addr_str[INET6_ADDRSTRLEN];
+	static char const nfsd_recall_failed[] = "/sbin/nfsd-recall-failed";
+	static char *envp[] = {
+		"HOME=/",
+		"TERM=linux",
+		"PATH=/sbin:/usr/sbin:/bin:/usr/bin",
+		NULL
+	};
+	char *argv[8];
+	int error;
+
+	rpc_ntop((struct sockaddr *)&clp->cl_addr, addr_str, sizeof(addr_str));
+
+	printk(KERN_WARNING
+		"nfsd: client %s failed to respond to layout recall. "
+		"  Fencing..\n", addr_str);
+
+	argv[0] = (char *)nfsd_recall_failed;
+	argv[1] = addr_str;
+	argv[2] = file->nf_file->f_path.mnt->mnt_sb->s_id;
+	argv[3] = NULL;
+
+	error = call_usermodehelper(nfsd_recall_failed, argv, envp,
+				    UMH_WAIT_PROC);
+	if (error) {
+		printk(KERN_ERR "nfsd: fence failed for client %s: %d!\n",
+			addr_str, error);
+	}
+}
+
+static void
+nfsd4_cb_layout_prepare(struct nfsd4_callback *cb)
+{
+	struct nfs4_layout_stateid *ls =
+		container_of(cb, struct nfs4_layout_stateid, ls_recall);
+
+	mutex_lock(&ls->ls_mutex);
+	nfs4_inc_and_copy_stateid(&ls->ls_recall_sid, &ls->ls_stid);
+	mutex_unlock(&ls->ls_mutex);
+}
+
+static int
+nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task)
+{
+	struct nfs4_layout_stateid *ls =
+		container_of(cb, struct nfs4_layout_stateid, ls_recall);
+	struct nfsd_net *nn;
+	ktime_t now, cutoff;
+	const struct nfsd4_layout_ops *ops;
+	struct nfsd_file *fl;
+
+	trace_nfsd_cb_layout_done(&ls->ls_stid.sc_stateid, task);
+	switch (task->tk_status) {
+	case 0:
+	case -NFS4ERR_DELAY:
+		/*
+		 * Anything left? If not, then call it done. Note that we don't
+		 * take the spinlock since this is an optimization and nothing
+		 * should get added until the cb counter goes to zero.
+		 */
+		if (list_empty(&ls->ls_layouts))
+			return 1;
+
+		/* Poll the client until it's done with the layout */
+		now = ktime_get();
+		nn = net_generic(ls->ls_stid.sc_client->net, nfsd_net_id);
+
+		/* Client gets 2 lease periods to return it */
+		cutoff = ktime_add_ns(task->tk_start,
+					 (u64)nn->nfsd4_lease * NSEC_PER_SEC * 2);
+
+		if (ktime_before(now, cutoff)) {
+			rpc_delay(task, HZ/100); /* 10 mili-seconds */
+			return 0;
+		}
+		fallthrough;
+	default:
+		/*
+		 * Unknown error or non-responding client, we'll need to fence.
+		 */
+		trace_nfsd_layout_recall_fail(&ls->ls_stid.sc_stateid);
+		rcu_read_lock();
+		fl = nfsd_file_get(ls->ls_file);
+		rcu_read_unlock();
+		if (fl) {
+			ops = nfsd4_layout_ops[ls->ls_layout_type];
+			if (ops->fence_client)
+				ops->fence_client(ls, fl);
+			else
+				nfsd4_cb_layout_fail(ls, fl);
+			nfsd_file_put(fl);
+		}
+		return 1;
+	case -NFS4ERR_NOMATCHING_LAYOUT:
+		trace_nfsd_layout_recall_done(&ls->ls_stid.sc_stateid);
+		task->tk_status = 0;
+		return 1;
+	}
+}
+
+static void
+nfsd4_cb_layout_release(struct nfsd4_callback *cb)
+{
+	struct nfs4_layout_stateid *ls =
+		container_of(cb, struct nfs4_layout_stateid, ls_recall);
+	LIST_HEAD(reaplist);
+
+	trace_nfsd_layout_recall_release(&ls->ls_stid.sc_stateid);
+
+	nfsd4_return_all_layouts(ls, &reaplist);
+	nfsd4_free_layouts(&reaplist);
+	nfs4_put_stid(&ls->ls_stid);
+}
+
+static const struct nfsd4_callback_ops nfsd4_cb_layout_ops = {
+	.prepare	= nfsd4_cb_layout_prepare,
+	.done		= nfsd4_cb_layout_done,
+	.release	= nfsd4_cb_layout_release,
+	.opcode		= OP_CB_LAYOUTRECALL,
+};
+
+static bool
+nfsd4_layout_lm_break(struct file_lease *fl)
+{
+	/*
+	 * Enforce break lease timeout to prevent NFSD
+	 * thread from hanging in __break_lease.
+	 */
+	nfsd4_recall_file_layout(fl->c.flc_owner);
+	return false;
+}
+
+static int
+nfsd4_layout_lm_change(struct file_lease *onlist, int arg,
+		struct list_head *dispose)
+{
+	BUG_ON(!(arg & F_UNLCK));
+	return lease_modify(onlist, arg, dispose);
+}
+
+/**
+ *  nfsd4_layout_lm_open_conflict - see if the given file points to an inode that has
+ *				    an existing open that would conflict with the
+ *				    desired lease.
+ * @filp:	file to check
+ * @arg:	type of lease that we're trying to acquire
+ *
+ * The kernel will call into this operation to determine whether there
+ * are conflicting opens that may prevent the layout from being granted.
+ * For nfsd, that check is done at a higher level, so this trivially
+ * returns 0.
+ */
+static int
+nfsd4_layout_lm_open_conflict(struct file *filp, int arg)
+{
+	return 0;
+}
+
+static void
+nfsd4_layout_fence_worker(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct nfs4_layout_stateid *ls = container_of(dwork,
+			struct nfs4_layout_stateid, ls_fence_work);
+	struct nfsd_file *nf;
+	struct block_device *bdev;
+	struct nfs4_client *clp;
+	struct nfsd_net *nn;
+
+	/*
+	 * The workqueue clears WORK_STRUCT_PENDING before invoking
+	 * this callback. Re-arm immediately so that
+	 * delayed_work_pending() returns true while the fence
+	 * operation is in progress, preventing
+	 * lm_breaker_timedout() from taking a duplicate reference.
+	 */
+	mod_delayed_work(system_dfl_wq, &ls->ls_fence_work, 0);
+
+	spin_lock(&ls->ls_lock);
+	if (list_empty(&ls->ls_layouts)) {
+		spin_unlock(&ls->ls_lock);
+dispose:
+		cancel_delayed_work(&ls->ls_fence_work);
+		/* unlock the lease so that tasks waiting on it can proceed */
+		nfsd4_close_layout(ls);
+
+		ls->ls_fenced = true;
+		nfs4_put_stid(&ls->ls_stid);
+		return;
+	}
+	spin_unlock(&ls->ls_lock);
+
+	rcu_read_lock();
+	nf = nfsd_file_get(ls->ls_file);
+	rcu_read_unlock();
+	if (!nf)
+		goto dispose;
+
+	clp = ls->ls_stid.sc_client;
+	nn = net_generic(clp->net, nfsd_net_id);
+	bdev = nf->nf_file->f_path.mnt->mnt_sb->s_bdev;
+	if (nfsd4_layout_ops[ls->ls_layout_type]->fence_client(ls, nf)) {
+		/* fenced ok */
+		nfsd_file_put(nf);
+		pr_warn("%s: FENCED client[%pISpc] clid[%d] to device[%s]\n",
+			__func__, (struct sockaddr *)&clp->cl_addr,
+			clp->cl_clientid.cl_id - nn->clientid_base,
+			bdev->bd_disk->disk_name);
+		goto dispose;
+	}
+	/* fence failed */
+	nfsd_file_put(nf);
+
+	if (!clp->cl_fence_retry_warn) {
+		pr_warn("%s: FENCE failed client[%pISpc] clid[%d] device[%s]\n",
+			__func__, (struct sockaddr *)&clp->cl_addr,
+			clp->cl_clientid.cl_id - nn->clientid_base,
+			bdev->bd_disk->disk_name);
+		clp->cl_fence_retry_warn = true;
+	}
+	/*
+	 * The fence worker retries the fencing operation indefinitely to
+	 * prevent data corruption. The admin needs to take the following
+	 * actions to restore access to the file for other clients:
+	 *
+	 *  . shutdown or power off the client being fenced.
+	 *  . manually expire the client to release all its state on the server;
+	 *    echo 'expire' > /proc/fs/nfsd/clients/clid/ctl'.
+	 *
+	 *    Where:
+	 *
+	 *    clid: is the unique client identifier displayed in
+	 *          the warning message above.
+	 */
+	if (!ls->ls_fence_delay)
+		ls->ls_fence_delay = HZ;
+	else
+		ls->ls_fence_delay = min(ls->ls_fence_delay << 1,
+					 MAX_FENCE_DELAY);
+	mod_delayed_work(system_dfl_wq, &ls->ls_fence_work, ls->ls_fence_delay);
+}
+
+/**
+ * nfsd4_layout_lm_breaker_timedout - The layout recall has timed out.
+ * @fl: file to check
+ *
+ * If the layout type supports a fence operation, schedule a worker to
+ * fence the client from accessing the block device.
+ *
+ * This function runs under the protection of the spin_lock flc_lock.
+ * At this time, the file_lease associated with the layout stateid is
+ * on the flc_list. A reference count is incremented on the layout
+ * stateid to prevent it from being freed while the fence worker is
+ * executing. Once the fence worker finishes its operation, it releases
+ * this reference.
+ *
+ * The fence worker continues to run until either the client has been
+ * fenced or the layout becomes invalid. The layout can become invalid
+ * as a result of a LAYOUTRETURN or when the CB_LAYOUT recall callback
+ * has completed.
+ *
+ * Return true if the file_lease should be disposed of by the caller;
+ * otherwise, return false.
+ */
+static bool
+nfsd4_layout_lm_breaker_timedout(struct file_lease *fl)
+{
+	struct nfs4_layout_stateid *ls = fl->c.flc_owner;
+
+	if ((!nfsd4_layout_ops[ls->ls_layout_type]->fence_client) ||
+			ls->ls_fenced)
+		return true;
+	if (delayed_work_pending(&ls->ls_fence_work))
+		return false;
+	/*
+	 * Make sure layout has not been returned yet before
+	 * taking a reference count on the layout stateid.
+	 */
+	spin_lock(&ls->ls_lock);
+	if (list_empty(&ls->ls_layouts) ||
+			!refcount_inc_not_zero(&ls->ls_stid.sc_count)) {
+		spin_unlock(&ls->ls_lock);
+		return true;
+	}
+	spin_unlock(&ls->ls_lock);
+
+	mod_delayed_work(system_dfl_wq, &ls->ls_fence_work, 0);
+	return false;
+}
+
+static const struct lease_manager_operations nfsd4_layouts_lm_ops = {
+	.lm_break		= nfsd4_layout_lm_break,
+	.lm_change		= nfsd4_layout_lm_change,
+	.lm_open_conflict	= nfsd4_layout_lm_open_conflict,
+	.lm_breaker_timedout	= nfsd4_layout_lm_breaker_timedout,
+};
+
+int
+nfsd4_init_pnfs(void)
+{
+	int i;
+
+	for (i = 0; i < DEVID_HASH_SIZE; i++)
+		INIT_LIST_HEAD(&nfsd_devid_hash[i]);
+
+	nfs4_layout_cache = KMEM_CACHE(nfs4_layout, 0);
+	if (!nfs4_layout_cache)
+		return -ENOMEM;
+
+	nfs4_layout_stateid_cache = KMEM_CACHE(nfs4_layout_stateid, 0);
+	if (!nfs4_layout_stateid_cache) {
+		kmem_cache_destroy(nfs4_layout_cache);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void
+nfsd4_exit_pnfs(void)
+{
+	int i;
+
+	kmem_cache_destroy(nfs4_layout_cache);
+	kmem_cache_destroy(nfs4_layout_stateid_cache);
+
+	for (i = 0; i < DEVID_HASH_SIZE; i++) {
+		struct nfsd4_deviceid_map *map, *n;
+
+		list_for_each_entry_safe(map, n, &nfsd_devid_hash[i], hash)
+			kfree(map);
+	}
+}

linux-7.2.3/fs/nfsd/nfs4xdr_gen.c

@@ -0,0 +1,569 @@
+// SPDX-License-Identifier: GPL-2.0
+// Generated by xdrgen. Manual edits will be lost.
+// XDR specification file: ../../Documentation/sunrpc/xdr/nfs4_1.x
+// XDR specification modification time: Thu Jan  8 23:12:07 2026
+
+#include <linux/sunrpc/svc.h>
+
+#include "nfs4xdr_gen.h"
+
+static bool __maybe_unused
+xdrgen_decode_int64_t(struct xdr_stream *xdr, int64_t *ptr)
+{
+	return xdrgen_decode_hyper(xdr, ptr);
+}
+
+static bool __maybe_unused
+xdrgen_decode_uint32_t(struct xdr_stream *xdr, uint32_t *ptr)
+{
+	return xdrgen_decode_unsigned_int(xdr, ptr);
+}
+
+static bool __maybe_unused
+xdrgen_decode_bitmap4(struct xdr_stream *xdr, bitmap4 *ptr)
+{
+	if (xdr_stream_decode_u32(xdr, &ptr->count) < 0)
+		return false;
+	for (u32 i = 0; i < ptr->count; i++)
+		if (!xdrgen_decode_uint32_t(xdr, &ptr->element[i]))
+			return false;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_decode_utf8string(struct xdr_stream *xdr, utf8string *ptr)
+{
+	return xdrgen_decode_opaque(xdr, ptr, 0);
+}
+
+static bool __maybe_unused
+xdrgen_decode_utf8str_cis(struct xdr_stream *xdr, utf8str_cis *ptr)
+{
+	return xdrgen_decode_utf8string(xdr, ptr);
+}
+
+static bool __maybe_unused
+xdrgen_decode_utf8str_cs(struct xdr_stream *xdr, utf8str_cs *ptr)
+{
+	return xdrgen_decode_utf8string(xdr, ptr);
+}
+
+static bool __maybe_unused
+xdrgen_decode_utf8str_mixed(struct xdr_stream *xdr, utf8str_mixed *ptr)
+{
+	return xdrgen_decode_utf8string(xdr, ptr);
+}
+
+static bool __maybe_unused
+xdrgen_decode_nfstime4(struct xdr_stream *xdr, struct nfstime4 *ptr)
+{
+	if (!xdrgen_decode_int64_t(xdr, &ptr->seconds))
+		return false;
+	if (!xdrgen_decode_uint32_t(xdr, &ptr->nseconds))
+		return false;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_decode_fattr4_offline(struct xdr_stream *xdr, fattr4_offline *ptr)
+{
+	return xdrgen_decode_bool(xdr, ptr);
+}
+
+static bool __maybe_unused
+xdrgen_decode_open_arguments4(struct xdr_stream *xdr, struct open_arguments4 *ptr)
+{
+	if (!xdrgen_decode_bitmap4(xdr, &ptr->oa_share_access))
+		return false;
+	if (!xdrgen_decode_bitmap4(xdr, &ptr->oa_share_deny))
+		return false;
+	if (!xdrgen_decode_bitmap4(xdr, &ptr->oa_share_access_want))
+		return false;
+	if (!xdrgen_decode_bitmap4(xdr, &ptr->oa_open_claim))
+		return false;
+	if (!xdrgen_decode_bitmap4(xdr, &ptr->oa_create_mode))
+		return false;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_decode_open_args_share_access4(struct xdr_stream *xdr, open_args_share_access4 *ptr)
+{
+	u32 val;
+
+	if (xdr_stream_decode_u32(xdr, &val) < 0)
+		return false;
+	/* Compiler may optimize to a range check for dense enums */
+	switch (val) {
+	case OPEN_ARGS_SHARE_ACCESS_READ:
+	case OPEN_ARGS_SHARE_ACCESS_WRITE:
+	case OPEN_ARGS_SHARE_ACCESS_BOTH:
+		break;
+	default:
+		return false;
+	}
+	*ptr = val;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_decode_open_args_share_deny4(struct xdr_stream *xdr, open_args_share_deny4 *ptr)
+{
+	u32 val;
+
+	if (xdr_stream_decode_u32(xdr, &val) < 0)
+		return false;
+	/* Compiler may optimize to a range check for dense enums */
+	switch (val) {
+	case OPEN_ARGS_SHARE_DENY_NONE:
+	case OPEN_ARGS_SHARE_DENY_READ:
+	case OPEN_ARGS_SHARE_DENY_WRITE:
+	case OPEN_ARGS_SHARE_DENY_BOTH:
+		break;
+	default:
+		return false;
+	}
+	*ptr = val;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_decode_open_args_share_access_want4(struct xdr_stream *xdr, open_args_share_access_want4 *ptr)
+{
+	u32 val;
+
+	if (xdr_stream_decode_u32(xdr, &val) < 0)
+		return false;
+	/* Compiler may optimize to a range check for dense enums */
+	switch (val) {
+	case OPEN_ARGS_SHARE_ACCESS_WANT_ANY_DELEG:
+	case OPEN_ARGS_SHARE_ACCESS_WANT_NO_DELEG:
+	case OPEN_ARGS_SHARE_ACCESS_WANT_CANCEL:
+	case OPEN_ARGS_SHARE_ACCESS_WANT_SIGNAL_DELEG_WHEN_RESRC_AVAIL:
+	case OPEN_ARGS_SHARE_ACCESS_WANT_PUSH_DELEG_WHEN_UNCONTENDED:
+	case OPEN_ARGS_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS:
+	case OPEN_ARGS_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION:
+		break;
+	default:
+		return false;
+	}
+	*ptr = val;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_decode_open_args_open_claim4(struct xdr_stream *xdr, open_args_open_claim4 *ptr)
+{
+	u32 val;
+
+	if (xdr_stream_decode_u32(xdr, &val) < 0)
+		return false;
+	/* Compiler may optimize to a range check for dense enums */
+	switch (val) {
+	case OPEN_ARGS_OPEN_CLAIM_NULL:
+	case OPEN_ARGS_OPEN_CLAIM_PREVIOUS:
+	case OPEN_ARGS_OPEN_CLAIM_DELEGATE_CUR:
+	case OPEN_ARGS_OPEN_CLAIM_DELEGATE_PREV:
+	case OPEN_ARGS_OPEN_CLAIM_FH:
+	case OPEN_ARGS_OPEN_CLAIM_DELEG_CUR_FH:
+	case OPEN_ARGS_OPEN_CLAIM_DELEG_PREV_FH:
+		break;
+	default:
+		return false;
+	}
+	*ptr = val;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_decode_open_args_createmode4(struct xdr_stream *xdr, open_args_createmode4 *ptr)
+{
+	u32 val;
+
+	if (xdr_stream_decode_u32(xdr, &val) < 0)
+		return false;
+	/* Compiler may optimize to a range check for dense enums */
+	switch (val) {
+	case OPEN_ARGS_CREATEMODE_UNCHECKED4:
+	case OPEN_ARGS_CREATE_MODE_GUARDED:
+	case OPEN_ARGS_CREATEMODE_EXCLUSIVE4:
+	case OPEN_ARGS_CREATE_MODE_EXCLUSIVE4_1:
+		break;
+	default:
+		return false;
+	}
+	*ptr = val;
+	return true;
+}
+
+bool
+xdrgen_decode_fattr4_open_arguments(struct xdr_stream *xdr, fattr4_open_arguments *ptr)
+{
+	return xdrgen_decode_open_arguments4(xdr, ptr);
+}
+
+/*
+ * Determine what OPEN supports.
+ */
+
+bool
+xdrgen_decode_fattr4_time_deleg_access(struct xdr_stream *xdr, fattr4_time_deleg_access *ptr)
+{
+	return xdrgen_decode_nfstime4(xdr, ptr);
+}
+
+bool
+xdrgen_decode_fattr4_time_deleg_modify(struct xdr_stream *xdr, fattr4_time_deleg_modify *ptr)
+{
+	return xdrgen_decode_nfstime4(xdr, ptr);
+}
+
+/*
+ * New RECOMMENDED Attribute for
+ * delegation caching of times
+ */
+
+static bool __maybe_unused
+xdrgen_decode_open_delegation_type4(struct xdr_stream *xdr, open_delegation_type4 *ptr)
+{
+	u32 val;
+
+	if (xdr_stream_decode_u32(xdr, &val) < 0)
+		return false;
+	/* Compiler may optimize to a range check for dense enums */
+	switch (val) {
+	case OPEN_DELEGATE_NONE:
+	case OPEN_DELEGATE_READ:
+	case OPEN_DELEGATE_WRITE:
+	case OPEN_DELEGATE_NONE_EXT:
+	case OPEN_DELEGATE_READ_ATTRS_DELEG:
+	case OPEN_DELEGATE_WRITE_ATTRS_DELEG:
+		break;
+	default:
+		return false;
+	}
+	*ptr = val;
+	return true;
+}
+
+bool
+xdrgen_decode_aclmodel4(struct xdr_stream *xdr, aclmodel4 *ptr)
+{
+	u32 val;
+
+	if (xdr_stream_decode_u32(xdr, &val) < 0)
+		return false;
+	/* Compiler may optimize to a range check for dense enums */
+	switch (val) {
+	case ACL_MODEL_NFS4:
+	case ACL_MODEL_POSIX_DRAFT:
+	case ACL_MODEL_NONE:
+		break;
+	default:
+		return false;
+	}
+	*ptr = val;
+	return true;
+}
+
+bool
+xdrgen_decode_aclscope4(struct xdr_stream *xdr, aclscope4 *ptr)
+{
+	u32 val;
+
+	if (xdr_stream_decode_u32(xdr, &val) < 0)
+		return false;
+	/* Compiler may optimize to a range check for dense enums */
+	switch (val) {
+	case ACL_SCOPE_FILE_OBJECT:
+	case ACL_SCOPE_FILE_SYSTEM:
+	case ACL_SCOPE_SERVER:
+		break;
+	default:
+		return false;
+	}
+	*ptr = val;
+	return true;
+}
+
+bool
+xdrgen_decode_posixacetag4(struct xdr_stream *xdr, posixacetag4 *ptr)
+{
+	u32 val;
+
+	if (xdr_stream_decode_u32(xdr, &val) < 0)
+		return false;
+	/* Compiler may optimize to a range check for dense enums */
+	switch (val) {
+	case POSIXACE4_TAG_USER_OBJ:
+	case POSIXACE4_TAG_USER:
+	case POSIXACE4_TAG_GROUP_OBJ:
+	case POSIXACE4_TAG_GROUP:
+	case POSIXACE4_TAG_MASK:
+	case POSIXACE4_TAG_OTHER:
+		break;
+	default:
+		return false;
+	}
+	*ptr = val;
+	return true;
+}
+
+bool
+xdrgen_decode_posixaceperm4(struct xdr_stream *xdr, posixaceperm4 *ptr)
+{
+	return xdrgen_decode_uint32_t(xdr, ptr);
+}
+
+static bool __maybe_unused
+xdrgen_decode_posixace4(struct xdr_stream *xdr, struct posixace4 *ptr)
+{
+	if (!xdrgen_decode_posixacetag4(xdr, &ptr->tag))
+		return false;
+	if (!xdrgen_decode_posixaceperm4(xdr, &ptr->perm))
+		return false;
+	if (!xdrgen_decode_utf8str_mixed(xdr, &ptr->who))
+		return false;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_decode_fattr4_acl_trueform(struct xdr_stream *xdr, fattr4_acl_trueform *ptr)
+{
+	return xdrgen_decode_aclmodel4(xdr, ptr);
+}
+
+static bool __maybe_unused
+xdrgen_decode_fattr4_acl_trueform_scope(struct xdr_stream *xdr, fattr4_acl_trueform_scope *ptr)
+{
+	return xdrgen_decode_aclscope4(xdr, ptr);
+}
+
+static bool __maybe_unused
+xdrgen_decode_fattr4_posix_default_acl(struct xdr_stream *xdr, fattr4_posix_default_acl *ptr)
+{
+	if (xdr_stream_decode_u32(xdr, &ptr->count) < 0)
+		return false;
+	for (u32 i = 0; i < ptr->count; i++)
+		if (!xdrgen_decode_posixace4(xdr, &ptr->element[i]))
+			return false;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_decode_fattr4_posix_access_acl(struct xdr_stream *xdr, fattr4_posix_access_acl *ptr)
+{
+	if (xdr_stream_decode_u32(xdr, &ptr->count) < 0)
+		return false;
+	for (u32 i = 0; i < ptr->count; i++)
+		if (!xdrgen_decode_posixace4(xdr, &ptr->element[i]))
+			return false;
+	return true;
+}
+
+/*
+ * New for POSIX ACL extension
+ */
+
+static bool __maybe_unused
+xdrgen_encode_int64_t(struct xdr_stream *xdr, const int64_t value)
+{
+	return xdrgen_encode_hyper(xdr, value);
+}
+
+static bool __maybe_unused
+xdrgen_encode_uint32_t(struct xdr_stream *xdr, const uint32_t value)
+{
+	return xdrgen_encode_unsigned_int(xdr, value);
+}
+
+static bool __maybe_unused
+xdrgen_encode_bitmap4(struct xdr_stream *xdr, const bitmap4 value)
+{
+	if (xdr_stream_encode_u32(xdr, value.count) != XDR_UNIT)
+		return false;
+	for (u32 i = 0; i < value.count; i++)
+		if (!xdrgen_encode_uint32_t(xdr, value.element[i]))
+			return false;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_encode_utf8string(struct xdr_stream *xdr, const utf8string value)
+{
+	return xdr_stream_encode_opaque(xdr, value.data, value.len) >= 0;
+}
+
+static bool __maybe_unused
+xdrgen_encode_utf8str_cis(struct xdr_stream *xdr, const utf8str_cis value)
+{
+	return xdrgen_encode_utf8string(xdr, value);
+}
+
+static bool __maybe_unused
+xdrgen_encode_utf8str_cs(struct xdr_stream *xdr, const utf8str_cs value)
+{
+	return xdrgen_encode_utf8string(xdr, value);
+}
+
+static bool __maybe_unused
+xdrgen_encode_utf8str_mixed(struct xdr_stream *xdr, const utf8str_mixed value)
+{
+	return xdrgen_encode_utf8string(xdr, value);
+}
+
+static bool __maybe_unused
+xdrgen_encode_nfstime4(struct xdr_stream *xdr, const struct nfstime4 *value)
+{
+	if (!xdrgen_encode_int64_t(xdr, value->seconds))
+		return false;
+	if (!xdrgen_encode_uint32_t(xdr, value->nseconds))
+		return false;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_encode_fattr4_offline(struct xdr_stream *xdr, const fattr4_offline value)
+{
+	return xdrgen_encode_bool(xdr, value);
+}
+
+static bool __maybe_unused
+xdrgen_encode_open_arguments4(struct xdr_stream *xdr, const struct open_arguments4 *value)
+{
+	if (!xdrgen_encode_bitmap4(xdr, value->oa_share_access))
+		return false;
+	if (!xdrgen_encode_bitmap4(xdr, value->oa_share_deny))
+		return false;
+	if (!xdrgen_encode_bitmap4(xdr, value->oa_share_access_want))
+		return false;
+	if (!xdrgen_encode_bitmap4(xdr, value->oa_open_claim))
+		return false;
+	if (!xdrgen_encode_bitmap4(xdr, value->oa_create_mode))
+		return false;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_encode_open_args_share_access4(struct xdr_stream *xdr, open_args_share_access4 value)
+{
+	return xdr_stream_encode_u32(xdr, value) == XDR_UNIT;
+}
+
+static bool __maybe_unused
+xdrgen_encode_open_args_share_deny4(struct xdr_stream *xdr, open_args_share_deny4 value)
+{
+	return xdr_stream_encode_u32(xdr, value) == XDR_UNIT;
+}
+
+static bool __maybe_unused
+xdrgen_encode_open_args_share_access_want4(struct xdr_stream *xdr, open_args_share_access_want4 value)
+{
+	return xdr_stream_encode_u32(xdr, value) == XDR_UNIT;
+}
+
+static bool __maybe_unused
+xdrgen_encode_open_args_open_claim4(struct xdr_stream *xdr, open_args_open_claim4 value)
+{
+	return xdr_stream_encode_u32(xdr, value) == XDR_UNIT;
+}
+
+static bool __maybe_unused
+xdrgen_encode_open_args_createmode4(struct xdr_stream *xdr, open_args_createmode4 value)
+{
+	return xdr_stream_encode_u32(xdr, value) == XDR_UNIT;
+}
+
+bool
+xdrgen_encode_fattr4_open_arguments(struct xdr_stream *xdr, const fattr4_open_arguments *value)
+{
+	return xdrgen_encode_open_arguments4(xdr, value);
+}
+
+bool
+xdrgen_encode_fattr4_time_deleg_access(struct xdr_stream *xdr, const fattr4_time_deleg_access *value)
+{
+	return xdrgen_encode_nfstime4(xdr, value);
+}
+
+bool
+xdrgen_encode_fattr4_time_deleg_modify(struct xdr_stream *xdr, const fattr4_time_deleg_modify *value)
+{
+	return xdrgen_encode_nfstime4(xdr, value);
+}
+
+static bool __maybe_unused
+xdrgen_encode_open_delegation_type4(struct xdr_stream *xdr, open_delegation_type4 value)
+{
+	return xdr_stream_encode_u32(xdr, value) == XDR_UNIT;
+}
+
+bool
+xdrgen_encode_aclmodel4(struct xdr_stream *xdr, aclmodel4 value)
+{
+	return xdr_stream_encode_u32(xdr, value) == XDR_UNIT;
+}
+
+bool
+xdrgen_encode_aclscope4(struct xdr_stream *xdr, aclscope4 value)
+{
+	return xdr_stream_encode_u32(xdr, value) == XDR_UNIT;
+}
+
+bool
+xdrgen_encode_posixacetag4(struct xdr_stream *xdr, posixacetag4 value)
+{
+	return xdr_stream_encode_u32(xdr, value) == XDR_UNIT;
+}
+
+bool
+xdrgen_encode_posixaceperm4(struct xdr_stream *xdr, const posixaceperm4 value)
+{
+	return xdrgen_encode_uint32_t(xdr, value);
+}
+
+static bool __maybe_unused
+xdrgen_encode_posixace4(struct xdr_stream *xdr, const struct posixace4 *value)
+{
+	if (!xdrgen_encode_posixacetag4(xdr, value->tag))
+		return false;
+	if (!xdrgen_encode_posixaceperm4(xdr, value->perm))
+		return false;
+	if (!xdrgen_encode_utf8str_mixed(xdr, value->who))
+		return false;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_encode_fattr4_acl_trueform(struct xdr_stream *xdr, const fattr4_acl_trueform value)
+{
+	return xdrgen_encode_aclmodel4(xdr, value);
+}
+
+static bool __maybe_unused
+xdrgen_encode_fattr4_acl_trueform_scope(struct xdr_stream *xdr, const fattr4_acl_trueform_scope value)
+{
+	return xdrgen_encode_aclscope4(xdr, value);
+}
+
+static bool __maybe_unused
+xdrgen_encode_fattr4_posix_default_acl(struct xdr_stream *xdr, const fattr4_posix_default_acl value)
+{
+	if (xdr_stream_encode_u32(xdr, value.count) != XDR_UNIT)
+		return false;
+	for (u32 i = 0; i < value.count; i++)
+		if (!xdrgen_encode_posixace4(xdr, &value.element[i]))
+			return false;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_encode_fattr4_posix_access_acl(struct xdr_stream *xdr, const fattr4_posix_access_acl value)
+{
+	if (xdr_stream_encode_u32(xdr, value.count) != XDR_UNIT)
+		return false;
+	for (u32 i = 0; i < value.count; i++)
+		if (!xdrgen_encode_posixace4(xdr, &value.element[i]))
+			return false;
+	return true;
+}

linux-7.2.3/fs/nfsd/nfs4xdr_gen.h

@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Generated by xdrgen. Manual edits will be lost. */
+/* XDR specification file: ../../Documentation/sunrpc/xdr/nfs4_1.x */
+/* XDR specification modification time: Thu Jan  8 23:12:07 2026 */
+
+#ifndef _LINUX_XDRGEN_NFS4_1_DECL_H
+#define _LINUX_XDRGEN_NFS4_1_DECL_H
+
+#include <linux/types.h>
+
+#include <linux/sunrpc/xdr.h>
+#include <linux/sunrpc/xdrgen/_defs.h>
+#include <linux/sunrpc/xdrgen/_builtins.h>
+#include <linux/sunrpc/xdrgen/nfs4_1.h>
+
+bool xdrgen_decode_fattr4_open_arguments(struct xdr_stream *xdr, fattr4_open_arguments *ptr);
+bool xdrgen_encode_fattr4_open_arguments(struct xdr_stream *xdr, const fattr4_open_arguments *value);
+
+bool xdrgen_decode_fattr4_time_deleg_access(struct xdr_stream *xdr, fattr4_time_deleg_access *ptr);
+bool xdrgen_encode_fattr4_time_deleg_access(struct xdr_stream *xdr, const fattr4_time_deleg_access *value);
+
+bool xdrgen_decode_fattr4_time_deleg_modify(struct xdr_stream *xdr, fattr4_time_deleg_modify *ptr);
+bool xdrgen_encode_fattr4_time_deleg_modify(struct xdr_stream *xdr, const fattr4_time_deleg_modify *value);
+bool xdrgen_decode_aclmodel4(struct xdr_stream *xdr, aclmodel4 *ptr);
+bool xdrgen_encode_aclmodel4(struct xdr_stream *xdr, aclmodel4 value);
+bool xdrgen_decode_aclscope4(struct xdr_stream *xdr, aclscope4 *ptr);
+bool xdrgen_encode_aclscope4(struct xdr_stream *xdr, aclscope4 value);
+bool xdrgen_decode_posixacetag4(struct xdr_stream *xdr, posixacetag4 *ptr);
+bool xdrgen_encode_posixacetag4(struct xdr_stream *xdr, posixacetag4 value);
+
+bool xdrgen_decode_posixaceperm4(struct xdr_stream *xdr, posixaceperm4 *ptr);
+bool xdrgen_encode_posixaceperm4(struct xdr_stream *xdr, const posixaceperm4 value);
+
+
+#endif /* _LINUX_XDRGEN_NFS4_1_DECL_H */

linux-7.2.3/fs/nfsd/nfscache.c

@@ -0,0 +1,667 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Request reply cache. This is currently a global cache, but this may
+ * change in the future and be a per-client cache.
+ *
+ * This code is heavily inspired by the 44BSD implementation, although
+ * it does things a bit differently.
+ *
+ * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#include <linux/sunrpc/svc_xprt.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/sunrpc/addr.h>
+#include <linux/highmem.h>
+#include <linux/log2.h>
+#include <linux/hash.h>
+#include <net/checksum.h>
+
+#include "nfsd.h"
+#include "cache.h"
+#include "trace.h"
+
+/*
+ * We use this value to determine the number of hash buckets from the max
+ * cache size, the idea being that when the cache is at its maximum number
+ * of entries, then this should be the average number of entries per bucket.
+ */
+#define TARGET_BUCKET_SIZE	8
+
+struct nfsd_drc_bucket {
+	struct rb_root rb_head;
+	struct list_head lru_head;
+	spinlock_t cache_lock;
+};
+
+static struct kmem_cache	*drc_slab;
+
+static int	nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec);
+static unsigned long nfsd_reply_cache_count(struct shrinker *shrink,
+					    struct shrink_control *sc);
+static unsigned long nfsd_reply_cache_scan(struct shrinker *shrink,
+					   struct shrink_control *sc);
+
+/*
+ * Put a cap on the size of the DRC based on the amount of available
+ * low memory in the machine.
+ *
+ *  64MB:    8192
+ * 128MB:   11585
+ * 256MB:   16384
+ * 512MB:   23170
+ *   1GB:   32768
+ *   2GB:   46340
+ *   4GB:   65536
+ *   8GB:   92681
+ *  16GB:  131072
+ *
+ * ...with a hard cap of 256k entries. In the worst case, each entry will be
+ * ~1k, so the above numbers should give a rough max of the amount of memory
+ * used in k.
+ *
+ * XXX: these limits are per-container, so memory used will increase
+ * linearly with number of containers.  Maybe that's OK.
+ */
+static unsigned int
+nfsd_cache_size_limit(void)
+{
+	unsigned int limit;
+	unsigned long low_pages = totalram_pages() - totalhigh_pages();
+
+	limit = (16 * int_sqrt(low_pages)) << (PAGE_SHIFT-10);
+	return min_t(unsigned int, limit, 256*1024);
+}
+
+/*
+ * Compute the number of hash buckets we need. Divide the max cachesize by
+ * the "target" max bucket size, and round up to next power of two.
+ */
+static unsigned int
+nfsd_hashsize(unsigned int limit)
+{
+	return roundup_pow_of_two(limit / TARGET_BUCKET_SIZE);
+}
+
+static struct nfsd_cacherep *
+nfsd_cacherep_alloc(struct svc_rqst *rqstp, __wsum csum,
+		    struct nfsd_net *nn)
+{
+	struct nfsd_cacherep *rp;
+
+	rp = kmem_cache_alloc(drc_slab, GFP_KERNEL);
+	if (rp) {
+		rp->c_state = RC_UNUSED;
+		rp->c_type = RC_NOCACHE;
+		RB_CLEAR_NODE(&rp->c_node);
+		INIT_LIST_HEAD(&rp->c_lru);
+
+		memset(&rp->c_key, 0, sizeof(rp->c_key));
+		rp->c_key.k_xid = rqstp->rq_xid;
+		rp->c_key.k_proc = rqstp->rq_proc;
+		rpc_copy_addr((struct sockaddr *)&rp->c_key.k_addr, svc_addr(rqstp));
+		rpc_set_port((struct sockaddr *)&rp->c_key.k_addr, rpc_get_port(svc_addr(rqstp)));
+		rp->c_key.k_prot = rqstp->rq_prot;
+		rp->c_key.k_vers = rqstp->rq_vers;
+		rp->c_key.k_len = rqstp->rq_arg.len;
+		rp->c_key.k_csum = csum;
+	}
+	return rp;
+}
+
+static void nfsd_cacherep_free(struct nfsd_cacherep *rp)
+{
+	if (rp->c_type == RC_REPLBUFF)
+		kfree(rp->c_replvec.iov_base);
+	kmem_cache_free(drc_slab, rp);
+}
+
+static unsigned long
+nfsd_cacherep_dispose(struct list_head *dispose)
+{
+	struct nfsd_cacherep *rp;
+	unsigned long freed = 0;
+
+	while (!list_empty(dispose)) {
+		rp = list_first_entry(dispose, struct nfsd_cacherep, c_lru);
+		list_del(&rp->c_lru);
+		nfsd_cacherep_free(rp);
+		freed++;
+	}
+	return freed;
+}
+
+static void
+nfsd_cacherep_unlink_locked(struct nfsd_net *nn, struct nfsd_drc_bucket *b,
+			    struct nfsd_cacherep *rp)
+{
+	if (rp->c_type == RC_REPLBUFF && rp->c_replvec.iov_base)
+		nfsd_stats_drc_mem_usage_sub(nn, rp->c_replvec.iov_len);
+	if (rp->c_state != RC_UNUSED) {
+		rb_erase(&rp->c_node, &b->rb_head);
+		list_del(&rp->c_lru);
+		atomic_dec(&nn->num_drc_entries);
+		nfsd_stats_drc_mem_usage_sub(nn, sizeof(*rp));
+	}
+}
+
+static void
+nfsd_reply_cache_free_locked(struct nfsd_drc_bucket *b, struct nfsd_cacherep *rp,
+				struct nfsd_net *nn)
+{
+	nfsd_cacherep_unlink_locked(nn, b, rp);
+	nfsd_cacherep_free(rp);
+}
+
+static void
+nfsd_reply_cache_free(struct nfsd_drc_bucket *b, struct nfsd_cacherep *rp,
+			struct nfsd_net *nn)
+{
+	spin_lock(&b->cache_lock);
+	nfsd_cacherep_unlink_locked(nn, b, rp);
+	spin_unlock(&b->cache_lock);
+	nfsd_cacherep_free(rp);
+}
+
+int nfsd_drc_slab_create(void)
+{
+	drc_slab = KMEM_CACHE(nfsd_cacherep, 0);
+	return drc_slab ? 0: -ENOMEM;
+}
+
+void nfsd_drc_slab_free(void)
+{
+	kmem_cache_destroy(drc_slab);
+}
+
+int nfsd_reply_cache_init(struct nfsd_net *nn)
+{
+	unsigned int hashsize;
+	unsigned int i;
+
+	nn->max_drc_entries = nfsd_cache_size_limit();
+	atomic_set(&nn->num_drc_entries, 0);
+	hashsize = nfsd_hashsize(nn->max_drc_entries);
+	nn->maskbits = ilog2(hashsize);
+
+	nn->drc_hashtbl = kvzalloc(array_size(hashsize,
+				sizeof(*nn->drc_hashtbl)), GFP_KERNEL);
+	if (!nn->drc_hashtbl)
+		return -ENOMEM;
+
+	nn->nfsd_reply_cache_shrinker = shrinker_alloc(0, "nfsd-reply:%s",
+						       nn->nfsd_name);
+	if (!nn->nfsd_reply_cache_shrinker)
+		goto out_shrinker;
+
+	nn->nfsd_reply_cache_shrinker->scan_objects = nfsd_reply_cache_scan;
+	nn->nfsd_reply_cache_shrinker->count_objects = nfsd_reply_cache_count;
+	nn->nfsd_reply_cache_shrinker->seeks = 1;
+	nn->nfsd_reply_cache_shrinker->private_data = nn;
+
+	shrinker_register(nn->nfsd_reply_cache_shrinker);
+
+	for (i = 0; i < hashsize; i++) {
+		INIT_LIST_HEAD(&nn->drc_hashtbl[i].lru_head);
+		spin_lock_init(&nn->drc_hashtbl[i].cache_lock);
+	}
+	nn->drc_hashsize = hashsize;
+
+	return 0;
+out_shrinker:
+	kvfree(nn->drc_hashtbl);
+	printk(KERN_ERR "nfsd: failed to allocate reply cache\n");
+	return -ENOMEM;
+}
+
+void nfsd_reply_cache_shutdown(struct nfsd_net *nn)
+{
+	struct nfsd_cacherep *rp;
+	unsigned int i;
+
+	shrinker_free(nn->nfsd_reply_cache_shrinker);
+
+	for (i = 0; i < nn->drc_hashsize; i++) {
+		struct list_head *head = &nn->drc_hashtbl[i].lru_head;
+		while (!list_empty(head)) {
+			rp = list_first_entry(head, struct nfsd_cacherep, c_lru);
+			nfsd_reply_cache_free_locked(&nn->drc_hashtbl[i],
+									rp, nn);
+		}
+	}
+
+	kvfree(nn->drc_hashtbl);
+	nn->drc_hashtbl = NULL;
+	nn->drc_hashsize = 0;
+
+}
+
+static void
+lru_put_end(struct nfsd_drc_bucket *b, struct nfsd_cacherep *rp)
+{
+	rp->c_timestamp = jiffies;
+	list_move_tail(&rp->c_lru, &b->lru_head);
+}
+
+static noinline struct nfsd_drc_bucket *
+nfsd_cache_bucket_find(__be32 xid, struct nfsd_net *nn)
+{
+	unsigned int hash = hash_32((__force u32)xid, nn->maskbits);
+
+	return &nn->drc_hashtbl[hash];
+}
+
+/*
+ * Remove and return no more than @max expired entries in bucket @b.
+ * If @max is zero, do not limit the number of removed entries.
+ */
+static void
+nfsd_prune_bucket_locked(struct nfsd_net *nn, struct nfsd_drc_bucket *b,
+			 unsigned int max, struct list_head *dispose)
+{
+	unsigned long expiry = jiffies - RC_EXPIRE;
+	struct nfsd_cacherep *rp, *tmp;
+	unsigned int freed = 0;
+
+	lockdep_assert_held(&b->cache_lock);
+
+	/* The bucket LRU is ordered oldest-first. */
+	list_for_each_entry_safe(rp, tmp, &b->lru_head, c_lru) {
+		if (atomic_read(&nn->num_drc_entries) <= nn->max_drc_entries &&
+		    time_before(expiry, rp->c_timestamp))
+			break;
+
+		nfsd_cacherep_unlink_locked(nn, b, rp);
+		list_add(&rp->c_lru, dispose);
+
+		if (max && ++freed > max)
+			break;
+	}
+}
+
+/**
+ * nfsd_reply_cache_count - count_objects method for the DRC shrinker
+ * @shrink: our registered shrinker context
+ * @sc: garbage collection parameters
+ *
+ * Returns the total number of entries in the duplicate reply cache. To
+ * keep things simple and quick, this is not the number of expired entries
+ * in the cache (ie, the number that would be removed by a call to
+ * nfsd_reply_cache_scan).
+ */
+static unsigned long
+nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+	struct nfsd_net *nn = shrink->private_data;
+
+	return atomic_read(&nn->num_drc_entries);
+}
+
+/**
+ * nfsd_reply_cache_scan - scan_objects method for the DRC shrinker
+ * @shrink: our registered shrinker context
+ * @sc: garbage collection parameters
+ *
+ * Free expired entries on each bucket's LRU list until we've released
+ * nr_to_scan freed objects. Nothing will be released if the cache
+ * has not exceeded it's max_drc_entries limit.
+ *
+ * Returns the number of entries released by this call.
+ */
+static unsigned long
+nfsd_reply_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
+{
+	struct nfsd_net *nn = shrink->private_data;
+	unsigned long freed = 0;
+	LIST_HEAD(dispose);
+	unsigned int i;
+
+	for (i = 0; i < nn->drc_hashsize; i++) {
+		struct nfsd_drc_bucket *b = &nn->drc_hashtbl[i];
+
+		if (list_empty(&b->lru_head))
+			continue;
+
+		spin_lock(&b->cache_lock);
+		nfsd_prune_bucket_locked(nn, b, 0, &dispose);
+		spin_unlock(&b->cache_lock);
+
+		freed += nfsd_cacherep_dispose(&dispose);
+		if (freed > sc->nr_to_scan)
+			break;
+	}
+	return freed;
+}
+
+/**
+ * nfsd_cache_csum - Checksum incoming NFS Call arguments
+ * @buf: buffer containing a whole RPC Call message
+ * @start: starting byte of the NFS Call header
+ * @remaining: size of the NFS Call header, in bytes
+ *
+ * Compute a weak checksum of the leading bytes of an NFS procedure
+ * call header to help verify that a retransmitted Call matches an
+ * entry in the duplicate reply cache.
+ *
+ * To avoid assumptions about how the RPC message is laid out in
+ * @buf and what else it might contain (eg, a GSS MIC suffix), the
+ * caller passes us the exact location and length of the NFS Call
+ * header.
+ *
+ * Returns a 32-bit checksum value, as defined in RFC 793.
+ */
+static __wsum nfsd_cache_csum(struct xdr_buf *buf, unsigned int start,
+			      unsigned int remaining)
+{
+	unsigned int base, len;
+	struct xdr_buf subbuf;
+	__wsum csum = 0;
+	void *p;
+	int idx;
+
+	if (remaining > RC_CSUMLEN)
+		remaining = RC_CSUMLEN;
+	if (xdr_buf_subsegment(buf, &subbuf, start, remaining))
+		return csum;
+
+	/* rq_arg.head first */
+	if (subbuf.head[0].iov_len) {
+		len = min_t(unsigned int, subbuf.head[0].iov_len, remaining);
+		csum = csum_partial(subbuf.head[0].iov_base, len, csum);
+		remaining -= len;
+	}
+
+	/* Continue into page array */
+	idx = subbuf.page_base / PAGE_SIZE;
+	base = subbuf.page_base & ~PAGE_MASK;
+	while (remaining) {
+		p = page_address(subbuf.pages[idx]) + base;
+		len = min_t(unsigned int, PAGE_SIZE - base, remaining);
+		csum = csum_partial(p, len, csum);
+		remaining -= len;
+		base = 0;
+		++idx;
+	}
+	return csum;
+}
+
+static int
+nfsd_cache_key_cmp(const struct nfsd_cacherep *key,
+		   const struct nfsd_cacherep *rp, struct nfsd_net *nn)
+{
+	if (key->c_key.k_xid == rp->c_key.k_xid &&
+	    key->c_key.k_csum != rp->c_key.k_csum) {
+		nfsd_stats_payload_misses_inc(nn);
+		trace_nfsd_drc_mismatch(nn, key, rp);
+	}
+
+	return memcmp(&key->c_key, &rp->c_key, sizeof(key->c_key));
+}
+
+/*
+ * Search the request hash for an entry that matches the given rqstp.
+ * Must be called with cache_lock held. Returns the found entry or
+ * inserts an empty key on failure.
+ */
+static struct nfsd_cacherep *
+nfsd_cache_insert(struct nfsd_drc_bucket *b, struct nfsd_cacherep *key,
+			struct nfsd_net *nn)
+{
+	struct nfsd_cacherep	*rp, *ret = key;
+	struct rb_node		**p = &b->rb_head.rb_node,
+				*parent = NULL;
+	unsigned int		entries = 0;
+	int cmp;
+
+	while (*p != NULL) {
+		++entries;
+		parent = *p;
+		rp = rb_entry(parent, struct nfsd_cacherep, c_node);
+
+		cmp = nfsd_cache_key_cmp(key, rp, nn);
+		if (cmp < 0)
+			p = &parent->rb_left;
+		else if (cmp > 0)
+			p = &parent->rb_right;
+		else {
+			ret = rp;
+			goto out;
+		}
+	}
+	rb_link_node(&key->c_node, parent, p);
+	rb_insert_color(&key->c_node, &b->rb_head);
+out:
+	/* tally hash chain length stats */
+	if (entries > nn->longest_chain) {
+		nn->longest_chain = entries;
+		nn->longest_chain_cachesize = atomic_read(&nn->num_drc_entries);
+	} else if (entries == nn->longest_chain) {
+		/* prefer to keep the smallest cachesize possible here */
+		nn->longest_chain_cachesize = min_t(unsigned int,
+				nn->longest_chain_cachesize,
+				atomic_read(&nn->num_drc_entries));
+	}
+	return ret;
+}
+
+/**
+ * nfsd_cache_lookup - Find an entry in the duplicate reply cache
+ * @rqstp: Incoming Call to find
+ * @start: starting byte in @rqstp->rq_arg of the NFS Call header
+ * @len: size of the NFS Call header, in bytes
+ * @cacherep: OUT: DRC entry for this request
+ *
+ * Try to find an entry matching the current call in the cache. When none
+ * is found, we try to grab the oldest expired entry off the LRU list. If
+ * a suitable one isn't there, then drop the cache_lock and allocate a
+ * new one, then search again in case one got inserted while this thread
+ * didn't hold the lock.
+ *
+ * Return values:
+ *   %RC_DOIT: Process the request normally
+ *   %RC_REPLY: Reply from cache
+ *   %RC_DROPIT: Do not process the request further
+ */
+int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start,
+		      unsigned int len, struct nfsd_cacherep **cacherep)
+{
+	struct nfsd_net		*nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+	struct nfsd_thread_local_info *ntli = rqstp->rq_private;
+	struct nfsd_cacherep	*rp, *found;
+	__wsum			csum;
+	struct nfsd_drc_bucket	*b;
+	int type = ntli->ntli_cachetype;
+	LIST_HEAD(dispose);
+	int rtn = RC_DOIT;
+
+	if (type == RC_NOCACHE) {
+		nfsd_stats_rc_nocache_inc(nn);
+		goto out;
+	}
+
+	csum = nfsd_cache_csum(&rqstp->rq_arg, start, len);
+
+	/*
+	 * Since the common case is a cache miss followed by an insert,
+	 * preallocate an entry.
+	 */
+	rp = nfsd_cacherep_alloc(rqstp, csum, nn);
+	if (!rp)
+		goto out;
+
+	b = nfsd_cache_bucket_find(rqstp->rq_xid, nn);
+	spin_lock(&b->cache_lock);
+	found = nfsd_cache_insert(b, rp, nn);
+	if (found != rp)
+		goto found_entry;
+	*cacherep = rp;
+	rp->c_state = RC_INPROG;
+	nfsd_prune_bucket_locked(nn, b, 3, &dispose);
+	spin_unlock(&b->cache_lock);
+
+	nfsd_cacherep_dispose(&dispose);
+
+	nfsd_stats_rc_misses_inc(nn);
+	atomic_inc(&nn->num_drc_entries);
+	nfsd_stats_drc_mem_usage_add(nn, sizeof(*rp));
+	goto out;
+
+found_entry:
+	/* We found a matching entry which is either in progress or done. */
+	nfsd_reply_cache_free_locked(NULL, rp, nn);
+	nfsd_stats_rc_hits_inc(nn);
+	rtn = RC_DROPIT;
+	rp = found;
+
+	/* Request being processed */
+	if (rp->c_state == RC_INPROG)
+		goto out_trace;
+
+	/* From the hall of fame of impractical attacks:
+	 * Is this a user who tries to snoop on the cache? */
+	rtn = RC_DOIT;
+	if (!test_bit(RQ_SECURE, &rqstp->rq_flags) && rp->c_secure)
+		goto out_trace;
+
+	/* Compose RPC reply header */
+	switch (rp->c_type) {
+	case RC_NOCACHE:
+		break;
+	case RC_REPLSTAT:
+		xdr_stream_encode_be32(&rqstp->rq_res_stream, rp->c_replstat);
+		rtn = RC_REPLY;
+		break;
+	case RC_REPLBUFF:
+		if (!nfsd_cache_append(rqstp, &rp->c_replvec))
+			goto out_unlock; /* should not happen */
+		rtn = RC_REPLY;
+		break;
+	default:
+		WARN_ONCE(1, "nfsd: bad repcache type %d\n", rp->c_type);
+	}
+
+out_trace:
+	trace_nfsd_drc_found(nn, rqstp, rtn);
+out_unlock:
+	spin_unlock(&b->cache_lock);
+out:
+	return rtn;
+}
+
+/**
+ * nfsd_cache_update - Update an entry in the duplicate reply cache.
+ * @rqstp: svc_rqst with a finished Reply
+ * @rp: IN: DRC entry for this request
+ * @cachetype: which cache to update
+ * @statp: pointer to Reply's NFS status code, or NULL
+ *
+ * This is called from nfsd_dispatch when the procedure has been
+ * executed and the complete reply is in rqstp->rq_res.
+ *
+ * We're copying around data here rather than swapping buffers because
+ * the toplevel loop requires max-sized buffers, which would be a waste
+ * of memory for a cache with a max reply size of 100 bytes (diropokres).
+ *
+ * If we should start to use different types of cache entries tailored
+ * specifically for attrstat and fh's, we may save even more space.
+ *
+ * Also note that a cachetype of RC_NOCACHE can legally be passed when
+ * nfsd failed to encode a reply that otherwise would have been cached.
+ * In this case, nfsd_cache_update is called with statp == NULL.
+ */
+void nfsd_cache_update(struct svc_rqst *rqstp, struct nfsd_cacherep *rp,
+		       int cachetype, __be32 *statp)
+{
+	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+	struct kvec	*resv = &rqstp->rq_res.head[0], *cachv;
+	struct nfsd_drc_bucket *b;
+	int		len;
+	size_t		bufsize = 0;
+
+	if (!rp)
+		return;
+
+	b = nfsd_cache_bucket_find(rp->c_key.k_xid, nn);
+
+	len = resv->iov_len - ((char*)statp - (char*)resv->iov_base);
+	len >>= 2;
+
+	/* Don't cache excessive amounts of data and XDR failures */
+	if (!statp || len > (256 >> 2)) {
+		nfsd_reply_cache_free(b, rp, nn);
+		return;
+	}
+
+	switch (cachetype) {
+	case RC_REPLSTAT:
+		if (len != 1)
+			printk("nfsd: RC_REPLSTAT/reply len %d!\n",len);
+		rp->c_replstat = *statp;
+		break;
+	case RC_REPLBUFF:
+		cachv = &rp->c_replvec;
+		bufsize = len << 2;
+		cachv->iov_base = kmalloc(bufsize, GFP_KERNEL);
+		if (!cachv->iov_base) {
+			nfsd_reply_cache_free(b, rp, nn);
+			return;
+		}
+		cachv->iov_len = bufsize;
+		memcpy(cachv->iov_base, statp, bufsize);
+		break;
+	case RC_NOCACHE:
+		nfsd_reply_cache_free(b, rp, nn);
+		return;
+	}
+	spin_lock(&b->cache_lock);
+	nfsd_stats_drc_mem_usage_add(nn, bufsize);
+	lru_put_end(b, rp);
+	rp->c_secure = test_bit(RQ_SECURE, &rqstp->rq_flags);
+	rp->c_type = cachetype;
+	rp->c_state = RC_DONE;
+	spin_unlock(&b->cache_lock);
+	return;
+}
+
+static int
+nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *data)
+{
+	__be32 *p;
+
+	p = xdr_reserve_space(&rqstp->rq_res_stream, data->iov_len);
+	if (unlikely(!p))
+		return false;
+	memcpy(p, data->iov_base, data->iov_len);
+	xdr_commit_encode(&rqstp->rq_res_stream);
+	return true;
+}
+
+/*
+ * Note that fields may be added, removed or reordered in the future. Programs
+ * scraping this file for info should test the labels to ensure they're
+ * getting the correct field.
+ */
+int nfsd_reply_cache_stats_show(struct seq_file *m, void *v)
+{
+	struct nfsd_net *nn = net_generic(file_inode(m->file)->i_sb->s_fs_info,
+					  nfsd_net_id);
+
+	seq_printf(m, "max entries:           %u\n", nn->max_drc_entries);
+	seq_printf(m, "num entries:           %u\n",
+		   atomic_read(&nn->num_drc_entries));
+	seq_printf(m, "hash buckets:          %u\n", 1 << nn->maskbits);
+	seq_printf(m, "mem usage:             %lld\n",
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_DRC_MEM_USAGE]));
+	seq_printf(m, "cache hits:            %lld\n",
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_HITS]));
+	seq_printf(m, "cache misses:          %lld\n",
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_MISSES]));
+	seq_printf(m, "not cached:            %lld\n",
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_NOCACHE]));
+	seq_printf(m, "payload misses:        %lld\n",
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_PAYLOAD_MISSES]));
+	seq_printf(m, "longest chain len:     %u\n", nn->longest_chain);
+	seq_printf(m, "cachesize at longest:  %u\n", nn->longest_chain_cachesize);
+	return 0;
+}

linux-7.2.3/fs/nfsd/nfsd.h

@@ -0,0 +1,592 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Hodge-podge collection of knfsd-related stuff.
+ * I will sort this out later.
+ *
+ * Copyright (C) 1995-1997 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#ifndef LINUX_NFSD_NFSD_H
+#define LINUX_NFSD_NFSD_H
+
+#include <linux/types.h>
+#include <linux/mount.h>
+
+#include <linux/nfs.h>
+#include <linux/nfs2.h>
+#include <linux/nfs3.h>
+#include <linux/nfs4.h>
+#include <linux/sunrpc/svc.h>
+#include <linux/sunrpc/svc_xprt.h>
+#include <linux/sunrpc/msg_prot.h>
+#include <linux/sunrpc/addr.h>
+
+#include <uapi/linux/nfsd/debug.h>
+
+#include "export.h"
+
+#undef ifdebug
+#ifdef CONFIG_SUNRPC_DEBUG
+# define ifdebug(flag)		if (nfsd_debug & NFSDDBG_##flag)
+#else
+# define ifdebug(flag)		if (0)
+#endif
+
+/*
+ * nfsd version
+ */
+#define NFSD_MINVERS			2
+#define	NFSD_MAXVERS			4
+#define NFSD_SUPPORTED_MINOR_VERSION	2
+bool nfsd_support_version(int vers);
+
+#include "netns.h"
+#include "stats.h"
+
+/*
+ * Default and maximum payload size (NFS READ or WRITE), in bytes.
+ * The maximum is an implementation limit.
+ */
+enum {
+	NFSSVC_DEFBLKSIZE       = 4 * 1024 * 1024,
+	NFSSVC_MAXBLKSIZE       = RPCSVC_MAXPAYLOAD,
+};
+
+struct readdir_cd {
+	__be32			err;	/* 0, nfserr, or nfserr_eof */
+};
+
+/* Maximum number of operations per session compound */
+#define NFSD_MAX_OPS_PER_COMPOUND	200
+
+extern struct svc_program	nfsd_programs[];
+extern const struct svc_version	nfsd_version2, nfsd_version3, nfsd_version4;
+extern struct mutex		nfsd_mutex;
+extern atomic_t			nfsd_th_cnt;		/* number of available threads */
+
+extern const struct seq_operations nfs_exports_op;
+
+struct nfsd_thread_local_info {
+	struct nfs4_client	**ntli_lease_breaker;
+	int			ntli_cachetype;
+};
+
+/*
+ * Common void argument and result helpers
+ */
+struct nfsd_voidargs { };
+struct nfsd_voidres { };
+bool		nfssvc_decode_voidarg(struct svc_rqst *rqstp,
+				      struct xdr_stream *xdr);
+bool		nfssvc_encode_voidres(struct svc_rqst *rqstp,
+				      struct xdr_stream *xdr);
+
+/*
+ * Function prototypes.
+ */
+int		nfsd_svc(int n, int *nservers, struct net *net,
+			 const struct cred *cred, const char *scope);
+int		nfsd_dispatch(struct svc_rqst *rqstp);
+
+int		nfsd_nrthreads(struct net *);
+int		nfsd_nrpools(struct net *);
+int		nfsd_get_nrthreads(int n, int *, struct net *);
+int		nfsd_set_nrthreads(int n, int *, struct net *);
+void		nfsd_shutdown_threads(struct net *net);
+
+struct svc_rqst *nfsd_current_rqst(void);
+
+struct nfsdfs_client {
+	struct kref cl_ref;
+	void (*cl_release)(struct kref *kref);
+};
+
+struct nfsdfs_client *get_nfsdfs_client(struct inode *);
+struct dentry *nfsd_client_mkdir(struct nfsd_net *nn,
+				 struct nfsdfs_client *ncl, u32 id,
+				 const struct tree_descr *,
+				 struct dentry **fdentries);
+void nfsd_client_rmdir(struct dentry *dentry);
+int nfsd_cache_notify(struct cache_detail *cd, struct cache_head *h, u32 cache_type);
+
+#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
+#ifdef CONFIG_NFSD_V2_ACL
+extern const struct svc_version nfsd_acl_version2;
+#else
+#define nfsd_acl_version2 NULL
+#endif
+#ifdef CONFIG_NFSD_V3_ACL
+extern const struct svc_version nfsd_acl_version3;
+#else
+#define nfsd_acl_version3 NULL
+#endif
+#endif
+
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+extern const struct svc_version localio_version1;
+#endif
+
+struct nfsd_net;
+
+enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL };
+int nfsd_vers(struct nfsd_net *nn, int vers, enum vers_op change);
+int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change);
+void nfsd_reset_versions(struct nfsd_net *nn);
+int nfsd_create_serv(struct net *net);
+void nfsd_destroy_serv(struct net *net);
+
+#ifdef CONFIG_DEBUG_FS
+void nfsd_debugfs_init(void);
+void nfsd_debugfs_exit(void);
+#else
+static inline void nfsd_debugfs_init(void) {}
+static inline void nfsd_debugfs_exit(void) {}
+#endif
+
+extern bool nfsd_disable_splice_read __read_mostly;
+extern bool nfsd_delegts_enabled __read_mostly;
+
+enum {
+	/* Any new NFSD_IO enum value must be added at the end */
+	NFSD_IO_BUFFERED,
+	NFSD_IO_DONTCACHE,
+	NFSD_IO_DIRECT,
+};
+
+extern u64 nfsd_io_cache_read __read_mostly;
+extern u64 nfsd_io_cache_write __read_mostly;
+
+extern int nfsd_max_blksize;
+
+static inline int nfsd_v4client(struct svc_rqst *rq)
+{
+	return rq && rq->rq_prog == NFS_PROGRAM && rq->rq_vers == 4;
+}
+static inline struct user_namespace *
+nfsd_user_namespace(const struct svc_rqst *rqstp)
+{
+	const struct cred *cred = rqstp->rq_xprt->xpt_cred;
+	return cred ? cred->user_ns : &init_user_ns;
+}
+
+/* 
+ * NFSv4 State
+ */
+#ifdef CONFIG_NFSD_V4
+extern unsigned long max_delegations;
+int nfsd4_init_slabs(void);
+void nfsd4_free_slabs(void);
+int nfs4_state_start(void);
+int nfs4_state_start_net(struct net *net);
+void nfs4_state_shutdown(void);
+void nfs4_state_shutdown_net(struct net *net);
+int nfs4_reset_recoverydir(char *recdir);
+char * nfs4_recoverydir(void);
+bool nfsd4_spo_must_allow(struct svc_rqst *rqstp);
+int nfsd4_create_laundry_wq(void);
+void nfsd4_destroy_laundry_wq(void);
+bool nfsd_wait_for_delegreturn(struct svc_rqst *rqstp, struct inode *inode);
+#else
+static inline int nfsd4_init_slabs(void) { return 0; }
+static inline void nfsd4_free_slabs(void) { }
+static inline int nfs4_state_start(void) { return 0; }
+static inline int nfs4_state_start_net(struct net *net) { return 0; }
+static inline void nfs4_state_shutdown(void) { }
+static inline void nfs4_state_shutdown_net(struct net *net) { }
+static inline int nfs4_reset_recoverydir(char *recdir) { return 0; }
+static inline char * nfs4_recoverydir(void) {return NULL; }
+static inline bool nfsd4_spo_must_allow(struct svc_rqst *rqstp)
+{
+	return false;
+}
+static inline int nfsd4_create_laundry_wq(void) { return 0; };
+static inline void nfsd4_destroy_laundry_wq(void) {};
+static inline bool nfsd_wait_for_delegreturn(struct svc_rqst *rqstp,
+					      struct inode *inode)
+{
+	return false;
+}
+#endif
+
+/*
+ * lockd binding
+ */
+void		nfsd_lockd_init(void);
+void		nfsd_lockd_shutdown(void);
+
+
+/*
+ * These macros provide pre-xdr'ed values for faster operation.
+ */
+#define	nfs_ok			cpu_to_be32(NFS_OK)
+#define	nfserr_perm		cpu_to_be32(NFSERR_PERM)
+#define	nfserr_noent		cpu_to_be32(NFSERR_NOENT)
+#define	nfserr_io		cpu_to_be32(NFSERR_IO)
+#define	nfserr_nxio		cpu_to_be32(NFSERR_NXIO)
+#define	nfserr_acces		cpu_to_be32(NFSERR_ACCES)
+#define	nfserr_exist		cpu_to_be32(NFSERR_EXIST)
+#define	nfserr_xdev		cpu_to_be32(NFSERR_XDEV)
+#define	nfserr_nodev		cpu_to_be32(NFSERR_NODEV)
+#define	nfserr_notdir		cpu_to_be32(NFSERR_NOTDIR)
+#define	nfserr_isdir		cpu_to_be32(NFSERR_ISDIR)
+#define	nfserr_inval		cpu_to_be32(NFSERR_INVAL)
+#define	nfserr_fbig		cpu_to_be32(NFSERR_FBIG)
+#define	nfserr_nospc		cpu_to_be32(NFSERR_NOSPC)
+#define	nfserr_rofs		cpu_to_be32(NFSERR_ROFS)
+#define	nfserr_mlink		cpu_to_be32(NFSERR_MLINK)
+#define	nfserr_nametoolong	cpu_to_be32(NFSERR_NAMETOOLONG)
+#define	nfserr_notempty		cpu_to_be32(NFSERR_NOTEMPTY)
+#define	nfserr_dquot		cpu_to_be32(NFSERR_DQUOT)
+#define	nfserr_stale		cpu_to_be32(NFSERR_STALE)
+#define	nfserr_remote		cpu_to_be32(NFSERR_REMOTE)
+#define	nfserr_wflush		cpu_to_be32(NFSERR_WFLUSH)
+#define	nfserr_badhandle	cpu_to_be32(NFSERR_BADHANDLE)
+#define	nfserr_notsync		cpu_to_be32(NFSERR_NOT_SYNC)
+#define	nfserr_badcookie	cpu_to_be32(NFSERR_BAD_COOKIE)
+#define	nfserr_notsupp		cpu_to_be32(NFSERR_NOTSUPP)
+#define	nfserr_toosmall		cpu_to_be32(NFSERR_TOOSMALL)
+#define	nfserr_serverfault	cpu_to_be32(NFSERR_SERVERFAULT)
+#define	nfserr_badtype		cpu_to_be32(NFSERR_BADTYPE)
+#define	nfserr_jukebox		cpu_to_be32(NFSERR_JUKEBOX)
+#define	nfserr_denied		cpu_to_be32(NFSERR_DENIED)
+#define	nfserr_deadlock		cpu_to_be32(NFSERR_DEADLOCK)
+#define nfserr_expired          cpu_to_be32(NFSERR_EXPIRED)
+#define	nfserr_bad_cookie	cpu_to_be32(NFSERR_BAD_COOKIE)
+#define	nfserr_same		cpu_to_be32(NFSERR_SAME)
+#define	nfserr_clid_inuse	cpu_to_be32(NFSERR_CLID_INUSE)
+#define	nfserr_stale_clientid	cpu_to_be32(NFSERR_STALE_CLIENTID)
+#define	nfserr_resource		cpu_to_be32(NFSERR_RESOURCE)
+#define	nfserr_moved		cpu_to_be32(NFSERR_MOVED)
+#define	nfserr_nofilehandle	cpu_to_be32(NFSERR_NOFILEHANDLE)
+#define	nfserr_minor_vers_mismatch	cpu_to_be32(NFSERR_MINOR_VERS_MISMATCH)
+#define nfserr_share_denied	cpu_to_be32(NFSERR_SHARE_DENIED)
+#define nfserr_stale_stateid	cpu_to_be32(NFSERR_STALE_STATEID)
+#define nfserr_old_stateid	cpu_to_be32(NFSERR_OLD_STATEID)
+#define nfserr_bad_stateid	cpu_to_be32(NFSERR_BAD_STATEID)
+#define nfserr_bad_seqid	cpu_to_be32(NFSERR_BAD_SEQID)
+#define	nfserr_symlink		cpu_to_be32(NFSERR_SYMLINK)
+#define	nfserr_not_same		cpu_to_be32(NFSERR_NOT_SAME)
+#define nfserr_lock_range	cpu_to_be32(NFSERR_LOCK_RANGE)
+#define	nfserr_restorefh	cpu_to_be32(NFSERR_RESTOREFH)
+#define	nfserr_attrnotsupp	cpu_to_be32(NFSERR_ATTRNOTSUPP)
+#define	nfserr_bad_xdr		cpu_to_be32(NFSERR_BAD_XDR)
+#define	nfserr_openmode		cpu_to_be32(NFSERR_OPENMODE)
+#define	nfserr_badowner		cpu_to_be32(NFSERR_BADOWNER)
+#define	nfserr_locks_held	cpu_to_be32(NFSERR_LOCKS_HELD)
+#define	nfserr_op_illegal	cpu_to_be32(NFSERR_OP_ILLEGAL)
+#define	nfserr_grace		cpu_to_be32(NFSERR_GRACE)
+#define	nfserr_no_grace		cpu_to_be32(NFSERR_NO_GRACE)
+#define	nfserr_reclaim_bad	cpu_to_be32(NFSERR_RECLAIM_BAD)
+#define	nfserr_badname		cpu_to_be32(NFSERR_BADNAME)
+#define	nfserr_admin_revoked	cpu_to_be32(NFS4ERR_ADMIN_REVOKED)
+#define	nfserr_cb_path_down	cpu_to_be32(NFSERR_CB_PATH_DOWN)
+#define	nfserr_locked		cpu_to_be32(NFSERR_LOCKED)
+#define	nfserr_wrongsec		cpu_to_be32(NFSERR_WRONGSEC)
+#define nfserr_delay			cpu_to_be32(NFS4ERR_DELAY)
+#define nfserr_badiomode		cpu_to_be32(NFS4ERR_BADIOMODE)
+#define nfserr_badlayout		cpu_to_be32(NFS4ERR_BADLAYOUT)
+#define nfserr_bad_session_digest	cpu_to_be32(NFS4ERR_BAD_SESSION_DIGEST)
+#define nfserr_badsession		cpu_to_be32(NFS4ERR_BADSESSION)
+#define nfserr_badslot			cpu_to_be32(NFS4ERR_BADSLOT)
+#define nfserr_complete_already		cpu_to_be32(NFS4ERR_COMPLETE_ALREADY)
+#define nfserr_conn_not_bound_to_session cpu_to_be32(NFS4ERR_CONN_NOT_BOUND_TO_SESSION)
+#define nfserr_deleg_already_wanted	cpu_to_be32(NFS4ERR_DELEG_ALREADY_WANTED)
+#define nfserr_back_chan_busy		cpu_to_be32(NFS4ERR_BACK_CHAN_BUSY)
+#define nfserr_layouttrylater		cpu_to_be32(NFS4ERR_LAYOUTTRYLATER)
+#define nfserr_layoutunavailable	cpu_to_be32(NFS4ERR_LAYOUTUNAVAILABLE)
+#define nfserr_nomatching_layout	cpu_to_be32(NFS4ERR_NOMATCHING_LAYOUT)
+#define nfserr_recallconflict		cpu_to_be32(NFS4ERR_RECALLCONFLICT)
+#define nfserr_unknown_layouttype	cpu_to_be32(NFS4ERR_UNKNOWN_LAYOUTTYPE)
+#define nfserr_seq_misordered		cpu_to_be32(NFS4ERR_SEQ_MISORDERED)
+#define nfserr_sequence_pos		cpu_to_be32(NFS4ERR_SEQUENCE_POS)
+#define nfserr_req_too_big		cpu_to_be32(NFS4ERR_REQ_TOO_BIG)
+#define nfserr_rep_too_big		cpu_to_be32(NFS4ERR_REP_TOO_BIG)
+#define nfserr_rep_too_big_to_cache	cpu_to_be32(NFS4ERR_REP_TOO_BIG_TO_CACHE)
+#define nfserr_retry_uncached_rep	cpu_to_be32(NFS4ERR_RETRY_UNCACHED_REP)
+#define nfserr_unsafe_compound		cpu_to_be32(NFS4ERR_UNSAFE_COMPOUND)
+#define nfserr_too_many_ops		cpu_to_be32(NFS4ERR_TOO_MANY_OPS)
+#define nfserr_op_not_in_session	cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION)
+#define nfserr_hash_alg_unsupp		cpu_to_be32(NFS4ERR_HASH_ALG_UNSUPP)
+#define nfserr_clientid_busy		cpu_to_be32(NFS4ERR_CLIENTID_BUSY)
+#define nfserr_pnfs_io_hole		cpu_to_be32(NFS4ERR_PNFS_IO_HOLE)
+#define nfserr_seq_false_retry		cpu_to_be32(NFS4ERR_SEQ_FALSE_RETRY)
+#define nfserr_bad_high_slot		cpu_to_be32(NFS4ERR_BAD_HIGH_SLOT)
+#define nfserr_deadsession		cpu_to_be32(NFS4ERR_DEADSESSION)
+#define nfserr_encr_alg_unsupp		cpu_to_be32(NFS4ERR_ENCR_ALG_UNSUPP)
+#define nfserr_pnfs_no_layout		cpu_to_be32(NFS4ERR_PNFS_NO_LAYOUT)
+#define nfserr_not_only_op		cpu_to_be32(NFS4ERR_NOT_ONLY_OP)
+#define nfserr_wrong_cred		cpu_to_be32(NFS4ERR_WRONG_CRED)
+#define nfserr_wrong_type		cpu_to_be32(NFS4ERR_WRONG_TYPE)
+#define nfserr_dirdeleg_unavail		cpu_to_be32(NFS4ERR_DIRDELEG_UNAVAIL)
+#define nfserr_reject_deleg		cpu_to_be32(NFS4ERR_REJECT_DELEG)
+#define nfserr_returnconflict		cpu_to_be32(NFS4ERR_RETURNCONFLICT)
+#define nfserr_deleg_revoked		cpu_to_be32(NFS4ERR_DELEG_REVOKED)
+#define nfserr_partner_notsupp		cpu_to_be32(NFS4ERR_PARTNER_NOTSUPP)
+#define nfserr_partner_no_auth		cpu_to_be32(NFS4ERR_PARTNER_NO_AUTH)
+#define nfserr_union_notsupp		cpu_to_be32(NFS4ERR_UNION_NOTSUPP)
+#define nfserr_offload_denied		cpu_to_be32(NFS4ERR_OFFLOAD_DENIED)
+#define nfserr_wrong_lfs		cpu_to_be32(NFS4ERR_WRONG_LFS)
+#define nfserr_badlabel			cpu_to_be32(NFS4ERR_BADLABEL)
+#define nfserr_file_open		cpu_to_be32(NFS4ERR_FILE_OPEN)
+#define nfserr_xattr2big		cpu_to_be32(NFS4ERR_XATTR2BIG)
+#define nfserr_noxattr			cpu_to_be32(NFS4ERR_NOXATTR)
+
+/*
+ * Error codes for internal use.  We use enum to choose numbers that are
+ * not already assigned, then covert to be32 resulting in a number that
+ * cannot conflict with any existing be32 nfserr value.
+ */
+enum {
+/* end-of-file indicator in readdir */
+	NFSERR_EOF = NFS4ERR_FIRST_FREE,
+#define	nfserr_eof		cpu_to_be32(NFSERR_EOF)
+
+/* replay detected */
+	NFSERR_REPLAY_ME,
+#define	nfserr_replay_me	cpu_to_be32(NFSERR_REPLAY_ME)
+
+/* nfs41 replay detected */
+	NFSERR_REPLAY_CACHE,
+#define	nfserr_replay_cache	cpu_to_be32(NFSERR_REPLAY_CACHE)
+
+/* symlink found where dir expected - handled differently to
+ * other symlink found errors by NFSv3.
+ */
+	NFSERR_SYMLINK_NOT_DIR,
+#define	nfserr_symlink_not_dir	cpu_to_be32(NFSERR_SYMLINK_NOT_DIR)
+};
+
+/* Check for dir entries '.' and '..' */
+#define isdotent(n, l)	(l < 3 && n[0] == '.' && (l == 1 || n[1] == '.'))
+
+#ifdef CONFIG_NFSD_V4
+
+/* before processing a COMPOUND operation, we have to check that there
+ * is enough space in the buffer for XDR encode to succeed.  otherwise,
+ * we might process an operation with side effects, and be unable to
+ * tell the client that the operation succeeded.
+ *
+ * COMPOUND_SLACK_SPACE - this is the minimum bytes of buffer space
+ * needed to encode an "ordinary" _successful_ operation.  (GETATTR,
+ * READ, READDIR, and READLINK have their own buffer checks.)  if we
+ * fall below this level, we fail the next operation with NFS4ERR_RESOURCE.
+ *
+ * COMPOUND_ERR_SLACK_SPACE - this is the minimum bytes of buffer space
+ * needed to encode an operation which has failed with NFS4ERR_RESOURCE.
+ * care is taken to ensure that we never fall below this level for any
+ * reason.
+ */
+#define	COMPOUND_SLACK_SPACE		140    /* OP_GETFH */
+#define COMPOUND_ERR_SLACK_SPACE	16     /* OP_SETATTR */
+
+#define NFSD_LAUNDROMAT_MINTIMEOUT      1   /* seconds */
+#define	NFSD_COURTESY_CLIENT_TIMEOUT	(24 * 60 * 60)	/* seconds */
+#define	NFSD_CLIENT_MAX_TRIM_PER_RUN	128
+#define	NFS4_CLIENTS_PER_GB		1024
+#define NFSD_DELEGRETURN_TIMEOUT	(HZ / 34)	/* 30ms */
+#define	NFSD_CB_GETATTR_TIMEOUT		NFSD_DELEGRETURN_TIMEOUT
+
+/*
+ * The following attributes are not implemented by NFSD:
+ *    ARCHIVE       (deprecated anyway)
+ *    HIDDEN        (unlikely to be supported any time soon)
+ *    MIMETYPE      (unlikely to be supported any time soon)
+ *    QUOTA_*       (will be supported in a forthcoming patch)
+ *    SYSTEM        (unlikely to be supported any time soon)
+ *    TIME_BACKUP   (unlikely to be supported any time soon)
+ */
+#define NFSD4_SUPPORTED_ATTRS_WORD0                                                         \
+(FATTR4_WORD0_SUPPORTED_ATTRS   | FATTR4_WORD0_TYPE         | FATTR4_WORD0_FH_EXPIRE_TYPE   \
+ | FATTR4_WORD0_CHANGE          | FATTR4_WORD0_SIZE         | FATTR4_WORD0_LINK_SUPPORT     \
+ | FATTR4_WORD0_SYMLINK_SUPPORT | FATTR4_WORD0_NAMED_ATTR   | FATTR4_WORD0_FSID             \
+ | FATTR4_WORD0_UNIQUE_HANDLES  | FATTR4_WORD0_LEASE_TIME   | FATTR4_WORD0_RDATTR_ERROR     \
+ | FATTR4_WORD0_ACLSUPPORT      | FATTR4_WORD0_CANSETTIME   | FATTR4_WORD0_CASE_INSENSITIVE \
+ | FATTR4_WORD0_CASE_PRESERVING | FATTR4_WORD0_CHOWN_RESTRICTED                             \
+ | FATTR4_WORD0_FILEHANDLE      | FATTR4_WORD0_FILEID       | FATTR4_WORD0_FILES_AVAIL      \
+ | FATTR4_WORD0_FILES_FREE      | FATTR4_WORD0_FILES_TOTAL  | FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_HOMOGENEOUS      \
+ | FATTR4_WORD0_MAXFILESIZE     | FATTR4_WORD0_MAXLINK      | FATTR4_WORD0_MAXNAME          \
+ | FATTR4_WORD0_MAXREAD         | FATTR4_WORD0_MAXWRITE     | FATTR4_WORD0_ACL)
+
+#define NFSD4_SUPPORTED_ATTRS_WORD1                                                         \
+(FATTR4_WORD1_MODE              | FATTR4_WORD1_NO_TRUNC     | FATTR4_WORD1_NUMLINKS         \
+ | FATTR4_WORD1_OWNER	        | FATTR4_WORD1_OWNER_GROUP  | FATTR4_WORD1_RAWDEV           \
+ | FATTR4_WORD1_SPACE_AVAIL     | FATTR4_WORD1_SPACE_FREE   | FATTR4_WORD1_SPACE_TOTAL      \
+ | FATTR4_WORD1_SPACE_USED      | FATTR4_WORD1_TIME_ACCESS  | FATTR4_WORD1_TIME_ACCESS_SET  \
+ | FATTR4_WORD1_TIME_DELTA      | FATTR4_WORD1_TIME_METADATA   | FATTR4_WORD1_TIME_CREATE      \
+ | FATTR4_WORD1_TIME_MODIFY     | FATTR4_WORD1_TIME_MODIFY_SET | FATTR4_WORD1_MOUNTED_ON_FILEID)
+
+#define NFSD4_SUPPORTED_ATTRS_WORD2 0
+
+/* 4.1 */
+#ifdef CONFIG_NFSD_PNFS
+#define PNFSD_SUPPORTED_ATTRS_WORD1	FATTR4_WORD1_FS_LAYOUT_TYPES
+#define PNFSD_SUPPORTED_ATTRS_WORD2 \
+(FATTR4_WORD2_LAYOUT_BLKSIZE	| FATTR4_WORD2_LAYOUT_TYPES)
+#else
+#define PNFSD_SUPPORTED_ATTRS_WORD1	0
+#define PNFSD_SUPPORTED_ATTRS_WORD2	0
+#endif /* CONFIG_NFSD_PNFS */
+
+#define NFSD4_1_SUPPORTED_ATTRS_WORD0 \
+	NFSD4_SUPPORTED_ATTRS_WORD0
+
+#define NFSD4_1_SUPPORTED_ATTRS_WORD1 \
+	(NFSD4_SUPPORTED_ATTRS_WORD1	| PNFSD_SUPPORTED_ATTRS_WORD1)
+
+#define NFSD4_1_SUPPORTED_ATTRS_WORD2 \
+	(NFSD4_SUPPORTED_ATTRS_WORD2	| PNFSD_SUPPORTED_ATTRS_WORD2 | \
+	 FATTR4_WORD2_SUPPATTR_EXCLCREAT)
+
+/* 4.2 */
+#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
+#define NFSD4_2_SECURITY_ATTRS		FATTR4_WORD2_SECURITY_LABEL
+#else
+#define NFSD4_2_SECURITY_ATTRS		0
+#endif
+
+#ifdef CONFIG_NFSD_V4_POSIX_ACLS
+#define NFSD4_2_POSIX_ACL_ATTRS \
+	(FATTR4_WORD2_ACL_TRUEFORM | \
+	FATTR4_WORD2_ACL_TRUEFORM_SCOPE | \
+	FATTR4_WORD2_POSIX_DEFAULT_ACL | \
+	FATTR4_WORD2_POSIX_ACCESS_ACL)
+#else
+#define NFSD4_2_POSIX_ACL_ATTRS		0
+#endif
+
+#define NFSD4_2_SUPPORTED_ATTRS_WORD2 \
+	(NFSD4_1_SUPPORTED_ATTRS_WORD2 | \
+	FATTR4_WORD2_MODE_UMASK | \
+	FATTR4_WORD2_CLONE_BLKSIZE | \
+	NFSD4_2_SECURITY_ATTRS | \
+	FATTR4_WORD2_XATTR_SUPPORT | \
+	FATTR4_WORD2_TIME_DELEG_ACCESS | \
+	FATTR4_WORD2_TIME_DELEG_MODIFY | \
+	FATTR4_WORD2_OPEN_ARGUMENTS | \
+	NFSD4_2_POSIX_ACL_ATTRS)
+
+extern const u32 nfsd_suppattrs[3][3];
+
+static inline __be32 nfsd4_set_netaddr(struct sockaddr *addr,
+				    struct nfs42_netaddr *netaddr)
+{
+	struct sockaddr_in *sin = (struct sockaddr_in *)addr;
+	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr;
+	unsigned int port;
+	size_t ret_addr, ret_port;
+
+	switch (addr->sa_family) {
+	case AF_INET:
+		port = ntohs(sin->sin_port);
+		sprintf(netaddr->netid, "tcp");
+		netaddr->netid_len = 3;
+		break;
+	case AF_INET6:
+		port = ntohs(sin6->sin6_port);
+		sprintf(netaddr->netid, "tcp6");
+		netaddr->netid_len = 4;
+		break;
+	default:
+		return nfserr_inval;
+	}
+	ret_addr = rpc_ntop(addr, netaddr->addr, sizeof(netaddr->addr));
+	ret_port = snprintf(netaddr->addr + ret_addr,
+			    RPCBIND_MAXUADDRLEN + 1 - ret_addr,
+			    ".%u.%u", port >> 8, port & 0xff);
+	WARN_ON(ret_port >= RPCBIND_MAXUADDRLEN + 1 - ret_addr);
+	netaddr->addr_len = ret_addr + ret_port;
+	return 0;
+}
+
+static inline bool bmval_is_subset(const u32 *bm1, const u32 *bm2)
+{
+	return !((bm1[0] & ~bm2[0]) ||
+	         (bm1[1] & ~bm2[1]) ||
+		 (bm1[2] & ~bm2[2]));
+}
+
+static inline bool nfsd_attrs_supported(u32 minorversion, const u32 *bmval)
+{
+	return bmval_is_subset(bmval, nfsd_suppattrs[minorversion]);
+}
+
+/* These will return ERR_INVAL if specified in GETATTR or READDIR. */
+#define NFSD_WRITEONLY_ATTRS_WORD1 \
+	(FATTR4_WORD1_TIME_ACCESS_SET   | FATTR4_WORD1_TIME_MODIFY_SET)
+
+/*
+ * These are the only attrs allowed in CREATE/OPEN/SETATTR. Don't add
+ * a writeable attribute here without also adding code to parse it to
+ * nfsd4_decode_fattr().
+ */
+#define NFSD_WRITEABLE_ATTRS_WORD0 \
+	(FATTR4_WORD0_SIZE | FATTR4_WORD0_ACL)
+#define NFSD_WRITEABLE_ATTRS_WORD1 \
+	(FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP \
+	| FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_CREATE \
+	| FATTR4_WORD1_TIME_MODIFY_SET)
+#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
+#define MAYBE_FATTR4_WORD2_SECURITY_LABEL \
+	FATTR4_WORD2_SECURITY_LABEL
+#else
+#define MAYBE_FATTR4_WORD2_SECURITY_LABEL 0
+#endif
+#ifdef CONFIG_NFSD_V4_POSIX_ACLS
+#define MAYBE_FATTR4_WORD2_POSIX_ACL_ATTRS \
+	FATTR4_WORD2_POSIX_DEFAULT_ACL | FATTR4_WORD2_POSIX_ACCESS_ACL
+#else
+#define MAYBE_FATTR4_WORD2_POSIX_ACL_ATTRS 0
+#endif
+#define NFSD_WRITEABLE_ATTRS_WORD2 \
+	(FATTR4_WORD2_MODE_UMASK \
+	| MAYBE_FATTR4_WORD2_SECURITY_LABEL \
+	| FATTR4_WORD2_TIME_DELEG_ACCESS \
+	| FATTR4_WORD2_TIME_DELEG_MODIFY \
+	| MAYBE_FATTR4_WORD2_POSIX_ACL_ATTRS \
+	)
+
+#define NFSD_SUPPATTR_EXCLCREAT_WORD0 \
+	NFSD_WRITEABLE_ATTRS_WORD0
+/*
+ * we currently store the exclusive create verifier in the v_{a,m}time
+ * attributes so the client can't set these at create time using EXCLUSIVE4_1
+ */
+#define NFSD_SUPPATTR_EXCLCREAT_WORD1 \
+	(NFSD_WRITEABLE_ATTRS_WORD1 & \
+	 ~(FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET))
+/*
+ * The FATTR4_WORD2_TIME_DELEG attributes are not to be allowed for
+ * OPEN(create) with EXCLUSIVE4_1. It doesn't make sense to set a
+ * delegated timestamp on a new file.
+ *
+ * This mask includes NFSv4.2-only attributes (e.g., POSIX ACLs).
+ * Version filtering occurs via nfsd_suppattrs[] before this mask
+ * is applied, so pre-4.2 clients never see unsupported attributes.
+ */
+#define NFSD_SUPPATTR_EXCLCREAT_WORD2 \
+	(NFSD_WRITEABLE_ATTRS_WORD2 & \
+	~(FATTR4_WORD2_TIME_DELEG_ACCESS | FATTR4_WORD2_TIME_DELEG_MODIFY))
+
+extern int nfsd4_is_junction(struct dentry *dentry);
+extern int register_cld_notifier(void);
+extern void unregister_cld_notifier(void);
+#ifdef CONFIG_NFSD_V4_2_INTER_SSC
+extern void nfsd4_ssc_init_umount_work(struct nfsd_net *nn);
+#endif
+
+extern void nfsd4_init_leases_net(struct nfsd_net *nn);
+
+#else /* CONFIG_NFSD_V4 */
+static inline int nfsd4_is_junction(struct dentry *dentry)
+{
+	return 0;
+}
+
+static inline void nfsd4_init_leases_net(struct nfsd_net *nn) { };
+
+#define register_cld_notifier() 0
+#define unregister_cld_notifier() do { } while(0)
+
+#endif /* CONFIG_NFSD_V4 */
+
+#endif /* LINUX_NFSD_NFSD_H */

linux-7.2.3/fs/nfsd/nfsfh.c

@@ -0,0 +1,962 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NFS server file handle treatment.
+ *
+ * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
+ * Portions Copyright (C) 1999 G. Allen Morris III <gam3@acm.org>
+ * Extensive rewrite by Neil Brown <neilb@cse.unsw.edu.au> Southern-Spring 1999
+ * ... and again Southern-Winter 2001 to support export_operations
+ */
+
+#include <linux/exportfs.h>
+
+#include <linux/sunrpc/svcauth_gss.h>
+#include <crypto/utils.h>
+#include "nfsd.h"
+#include "vfs.h"
+#include "auth.h"
+#include "trace.h"
+
+#define NFSDDBG_FACILITY		NFSDDBG_FH
+
+
+/*
+ * our acceptability function.
+ * if NOSUBTREECHECK, accept anything
+ * if not, require that we can walk up to exp->ex_dentry
+ * doing some checks on the 'x' bits
+ */
+static int nfsd_acceptable(void *expv, struct dentry *dentry)
+{
+	struct svc_export *exp = expv;
+	int rv;
+	struct dentry *tdentry;
+	struct dentry *parent;
+
+	if (exp->ex_flags & NFSEXP_NOSUBTREECHECK)
+		return 1;
+
+	tdentry = dget(dentry);
+	while (tdentry != exp->ex_path.dentry && !IS_ROOT(tdentry)) {
+		/* make sure parents give x permission to user */
+		int err;
+		parent = dget_parent(tdentry);
+		err = inode_permission(&nop_mnt_idmap,
+				       d_inode(parent), MAY_EXEC);
+		if (err < 0) {
+			dput(parent);
+			break;
+		}
+		dput(tdentry);
+		tdentry = parent;
+	}
+	if (tdentry != exp->ex_path.dentry)
+		dprintk("nfsd_acceptable failed at %p %pd\n", tdentry, tdentry);
+	rv = (tdentry == exp->ex_path.dentry);
+	dput(tdentry);
+	return rv;
+}
+
+/* Type check. The correct error return for type mismatches does not seem to be
+ * generally agreed upon. SunOS seems to use EISDIR if file isn't S_IFREG; a
+ * comment in the NFSv3 spec says this is incorrect (implementation notes for
+ * the write call).
+ */
+static inline __be32
+nfsd_mode_check(struct dentry *dentry, umode_t requested)
+{
+	umode_t mode = d_inode(dentry)->i_mode & S_IFMT;
+
+	if (requested == 0) /* the caller doesn't care */
+		return nfs_ok;
+	if (mode == requested) {
+		if (mode == S_IFDIR && !d_can_lookup(dentry)) {
+			WARN_ON_ONCE(1);
+			return nfserr_notdir;
+		}
+		return nfs_ok;
+	}
+	if (mode == S_IFLNK) {
+		if (requested == S_IFDIR)
+			return nfserr_symlink_not_dir;
+		return nfserr_symlink;
+	}
+	if (requested == S_IFDIR)
+		return nfserr_notdir;
+	if (mode == S_IFDIR)
+		return nfserr_isdir;
+	return nfserr_wrong_type;
+}
+
+static bool nfsd_originating_port_ok(struct svc_rqst *rqstp,
+				     struct svc_cred *cred,
+				     struct svc_export *exp)
+{
+	if (nfsexp_flags(cred, exp) & NFSEXP_INSECURE_PORT)
+		return true;
+	/* We don't require gss requests to use low ports: */
+	if (cred->cr_flavor >= RPC_AUTH_GSS)
+		return true;
+	return test_bit(RQ_SECURE, &rqstp->rq_flags);
+}
+
+static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp,
+					  struct svc_cred *cred,
+					  struct svc_export *exp)
+{
+	/* Check if the request originated from a secure port. */
+	if (rqstp && !nfsd_originating_port_ok(rqstp, cred, exp)) {
+		if (IS_ENABLED(CONFIG_SUNRPC_DEBUG)) {
+			char buf[RPC_MAX_ADDRBUFLEN];
+
+			dprintk("nfsd: request from insecure port %s!\n",
+			        svc_print_addr(rqstp, buf, sizeof(buf)));
+		}
+		return nfserr_perm;
+	}
+
+	/* Set user creds for this exportpoint */
+	return nfserrno(nfsd_setuser(cred, exp));
+}
+
+static inline __be32 check_pseudo_root(struct dentry *dentry,
+				       struct svc_export *exp)
+{
+	if (!(exp->ex_flags & NFSEXP_V4ROOT))
+		return nfs_ok;
+	/*
+	 * We're exposing only the directories and symlinks that have to be
+	 * traversed on the way to real exports:
+	 */
+	if (unlikely(!d_is_dir(dentry) &&
+		     !d_is_symlink(dentry)))
+		return nfserr_stale;
+	/*
+	 * A pseudoroot export gives permission to access only one
+	 * single directory; the kernel has to make another upcall
+	 * before granting access to anything else under it:
+	 */
+	if (unlikely(dentry != exp->ex_path.dentry))
+		return nfserr_stale;
+	return nfs_ok;
+}
+
+/* Size of a file handle MAC, in 4-octet words */
+#define FH_MAC_WORDS (sizeof(__le64) / 4)
+
+static bool fh_append_mac(struct svc_fh *fhp, struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct knfsd_fh *fh = &fhp->fh_handle;
+	siphash_key_t *fh_key = nn->fh_key;
+	__le64 hash;
+
+	if (!fh_key)
+		goto out_no_key;
+	if (fh->fh_size + sizeof(hash) > fhp->fh_maxsize)
+		goto out_no_space;
+
+	hash = cpu_to_le64(siphash(&fh->fh_raw, fh->fh_size, fh_key));
+	memcpy(&fh->fh_raw[fh->fh_size], &hash, sizeof(hash));
+	fh->fh_size += sizeof(hash);
+	return true;
+
+out_no_key:
+	pr_warn_ratelimited("NFSD: unable to sign filehandles, fh_key not set.\n");
+	return false;
+
+out_no_space:
+	pr_warn_ratelimited("NFSD: unable to sign filehandles, fh_size %zu would be greater than fh_maxsize %d.\n",
+			    fh->fh_size + sizeof(hash), fhp->fh_maxsize);
+	return false;
+}
+
+/*
+ * Verify that the filehandle's MAC was hashed from this filehandle
+ * given the server's fh_key:
+ */
+static bool fh_verify_mac(struct svc_fh *fhp, struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct knfsd_fh *fh = &fhp->fh_handle;
+	siphash_key_t *fh_key = nn->fh_key;
+	__le64 hash;
+
+	if (!fh_key) {
+		pr_warn_ratelimited("NFSD: unable to verify signed filehandles, fh_key not set.\n");
+		return false;
+	}
+
+	hash = cpu_to_le64(siphash(&fh->fh_raw, fh->fh_size - sizeof(hash),  fh_key));
+	return crypto_memneq(&fh->fh_raw[fh->fh_size - sizeof(hash)],
+					&hash, sizeof(hash)) == 0;
+}
+
+/*
+ * Use the given filehandle to look up the corresponding export and
+ * dentry.  On success, the results are used to set fh_export and
+ * fh_dentry.
+ */
+static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct net *net,
+				 struct svc_cred *cred,
+				 struct auth_domain *client,
+				 struct auth_domain *gssclient,
+				 struct svc_fh *fhp)
+{
+	struct knfsd_fh	*fh = &fhp->fh_handle;
+	struct fid *fid = NULL;
+	struct svc_export *exp;
+	struct dentry *dentry;
+	int fileid_type;
+	int data_left = fh->fh_size/4;
+	int len;
+	__be32 error;
+
+	error = nfserr_badhandle;
+	if (fh->fh_size == 0)
+		return nfserr_nofilehandle;
+
+	if (fh->fh_version != 1)
+		return error;
+
+	if (--data_left < 0)
+		return error;
+	if (fh->fh_auth_type != 0)
+		return error;
+	len = key_len(fh->fh_fsid_type) / 4;
+	if (len == 0)
+		return error;
+	if (fh->fh_fsid_type == FSID_MAJOR_MINOR) {
+		u32 *fsid = fh_fsid(fh);
+
+		/* deprecated, convert to type 3 */
+		len = key_len(FSID_ENCODE_DEV)/4;
+		fh->fh_fsid_type = FSID_ENCODE_DEV;
+		/*
+		 * struct knfsd_fh uses host-endian fields, which are
+		 * sometimes used to hold net-endian values. This
+		 * confuses sparse, so we must use __force here to
+		 * keep it from complaining.
+		 */
+		fsid[0] = new_encode_dev(MKDEV(ntohl((__force __be32)fsid[0]),
+					       ntohl((__force __be32)fsid[1])));
+		fsid[1] = fsid[2];
+	}
+	data_left -= len;
+	if (data_left < 0)
+		return error;
+	exp = rqst_exp_find(rqstp ? &rqstp->rq_chandle : NULL,
+			    net, client, gssclient,
+			    fh->fh_fsid_type, fh_fsid(fh));
+	fid = (struct fid *)(fh_fsid(fh) + len);
+
+	error = nfserr_stale;
+	if (IS_ERR(exp)) {
+		trace_nfsd_set_fh_dentry_badexport(rqstp, fhp, PTR_ERR(exp));
+
+		if (PTR_ERR(exp) == -ENOENT)
+			return error;
+
+		return nfserrno(PTR_ERR(exp));
+	}
+
+	if (exp->ex_flags & NFSEXP_NOSUBTREECHECK) {
+		/* Elevate privileges so that the lack of 'r' or 'x'
+		 * permission on some parent directory will
+		 * not stop exportfs_decode_fh from being able
+		 * to reconnect a directory into the dentry cache.
+		 * The same problem can affect "SUBTREECHECK" exports,
+		 * but as nfsd_acceptable depends on correct
+		 * access control settings being in effect, we cannot
+		 * fix that case easily.
+		 */
+		struct cred *new = prepare_creds();
+		if (!new) {
+			error =  nfserrno(-ENOMEM);
+			goto out;
+		}
+		new->cap_effective =
+			cap_raise_nfsd_set(new->cap_effective,
+					   new->cap_permitted);
+		put_cred(override_creds(new));
+	} else {
+		error = nfsd_setuser_and_check_port(rqstp, cred, exp);
+		if (error)
+			goto out;
+	}
+
+	/*
+	 * Look up the dentry using the NFS file handle.
+	 */
+	fileid_type = fh->fh_fileid_type;
+	error = nfserr_stale;
+
+	if (fileid_type == FILEID_ROOT) {
+		/* We don't sign or verify the root, no per-file identity */
+		dentry = dget(exp->ex_path.dentry);
+	} else {
+		if (exp->ex_flags & NFSEXP_SIGN_FH) {
+			if (!fh_verify_mac(fhp, net)) {
+				trace_nfsd_set_fh_dentry_badmac(rqstp, fhp, -ESTALE);
+				goto out;
+			}
+			data_left -= FH_MAC_WORDS;
+		}
+
+		dentry = exportfs_decode_fh_raw(exp->ex_path.mnt, fid,
+						data_left, fileid_type, 0,
+						nfsd_acceptable, exp);
+		if (IS_ERR_OR_NULL(dentry)) {
+			trace_nfsd_set_fh_dentry_badhandle(rqstp, fhp,
+					dentry ?  PTR_ERR(dentry) : -ESTALE);
+			switch (PTR_ERR(dentry)) {
+			case -ENOMEM:
+			case -ETIMEDOUT:
+				break;
+			default:
+				dentry = ERR_PTR(-ESTALE);
+			}
+		}
+	}
+
+	error = nfserr_badhandle;
+	if (dentry == NULL)
+		goto out;
+	if (IS_ERR(dentry)) {
+		if (PTR_ERR(dentry) != -EINVAL)
+			error = nfserrno(PTR_ERR(dentry));
+		goto out;
+	}
+
+	if (d_is_dir(dentry) &&
+			(dentry->d_flags & DCACHE_DISCONNECTED)) {
+		printk("nfsd: find_fh_dentry returned a DISCONNECTED directory: %pd2\n",
+				dentry);
+	}
+
+	switch (fhp->fh_maxsize) {
+	case NFS4_FHSIZE:
+		if (dentry->d_sb->s_export_op->flags & EXPORT_OP_NOATOMIC_ATTR)
+			fhp->fh_no_atomic_attr = true;
+		fhp->fh_64bit_cookies = true;
+		break;
+	case NFS3_FHSIZE:
+		if (dentry->d_sb->s_export_op->flags & EXPORT_OP_NOWCC)
+			fhp->fh_no_wcc = true;
+		fhp->fh_64bit_cookies = true;
+		if (exp->ex_flags & NFSEXP_V4ROOT)
+			goto out;
+		break;
+	case NFS_FHSIZE:
+		fhp->fh_no_wcc = true;
+		if (EX_WGATHER(exp))
+			fhp->fh_use_wgather = true;
+		if (exp->ex_flags & NFSEXP_V4ROOT)
+			goto out;
+	}
+
+	fhp->fh_dentry = dentry;
+	fhp->fh_export = exp;
+
+	return 0;
+out:
+	exp_put(exp);
+	return error;
+}
+
+/**
+ * __fh_verify - filehandle lookup and access checking
+ * @rqstp: RPC transaction context, or NULL
+ * @net: net namespace in which to perform the export lookup
+ * @cred: RPC user credential
+ * @client: RPC auth domain
+ * @gssclient: RPC GSS auth domain, or NULL
+ * @fhp: filehandle to be verified
+ * @type: expected type of object pointed to by filehandle
+ * @access: type of access needed to object
+ *
+ * See fh_verify() for further descriptions of @fhp, @type, and @access.
+ */
+static __be32
+__fh_verify(struct svc_rqst *rqstp,
+	    struct net *net, struct svc_cred *cred,
+	    struct auth_domain *client,
+	    struct auth_domain *gssclient,
+	    struct svc_fh *fhp, umode_t type, int access)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct svc_export *exp = NULL;
+	bool may_bypass_gss = false;
+	struct dentry	*dentry;
+	__be32		error;
+
+	if (!fhp->fh_dentry) {
+		error = nfsd_set_fh_dentry(rqstp, net, cred, client,
+					   gssclient, fhp);
+		if (error)
+			goto out;
+	}
+	dentry = fhp->fh_dentry;
+	exp = fhp->fh_export;
+
+	trace_nfsd_fh_verify(rqstp, fhp, type, access);
+
+	/*
+	 * We still have to do all these permission checks, even when
+	 * fh_dentry is already set:
+	 * 	- fh_verify may be called multiple times with different
+	 * 	  "access" arguments (e.g. nfsd_proc_create calls
+	 * 	  fh_verify(...,NFSD_MAY_EXEC) first, then later (in
+	 * 	  nfsd_create) calls fh_verify(...,NFSD_MAY_CREATE).
+	 *	- in the NFSv4 case, the filehandle may have been filled
+	 *	  in by fh_compose, and given a dentry, but further
+	 *	  compound operations performed with that filehandle
+	 *	  still need permissions checks.  In the worst case, a
+	 *	  mountpoint crossing may have changed the export
+	 *	  options, and we may now need to use a different uid
+	 *	  (for example, if different id-squashing options are in
+	 *	  effect on the new filesystem).
+	 */
+	error = check_pseudo_root(dentry, exp);
+	if (error)
+		goto out;
+
+	error = nfsd_setuser_and_check_port(rqstp, cred, exp);
+	if (error)
+		goto out;
+
+	error = nfsd_mode_check(dentry, type);
+	if (error)
+		goto out;
+
+	/*
+	 * If rqstp is NULL, this is a LOCALIO request which will only
+	 * ever use a filehandle/credential pair for which access has
+	 * been affirmed (by ACCESS or OPEN NFS requests) over the
+	 * wire.  Skip both the xprtsec policy and the security flavor
+	 * checks.
+	 */
+	if (!rqstp)
+		goto check_permissions;
+
+	if ((access & NFSD_MAY_NLM) && (exp->ex_flags & NFSEXP_NOAUTHNLM))
+		/* NLM is allowed to fully bypass authentication */
+		goto out;
+
+	/*
+	 * NLM is allowed to bypass the xprtsec policy check because lockd
+	 * doesn't support xprtsec.
+	 */
+	if (!(access & NFSD_MAY_NLM)) {
+		error = check_xprtsec_policy(exp, rqstp);
+		if (error)
+			goto out;
+	}
+
+	if (access & NFSD_MAY_BYPASS_GSS)
+		may_bypass_gss = true;
+	/*
+	 * Clients may expect to be able to use auth_sys during mount,
+	 * even if they use gss for everything else; see section 2.3.2
+	 * of rfc 2623.
+	 */
+	if (access & NFSD_MAY_BYPASS_GSS_ON_ROOT
+			&& exp->ex_path.dentry == dentry)
+		may_bypass_gss = true;
+
+	error = check_security_flavor(exp, rqstp, may_bypass_gss);
+	if (error)
+		goto out;
+
+	svc_xprt_set_valid(rqstp->rq_xprt);
+
+check_permissions:
+	/* Finally, check access permissions. */
+	error = nfsd_permission(cred, exp, dentry, access);
+out:
+	trace_nfsd_fh_verify_err(rqstp, fhp, type, access, error);
+	if (error == nfserr_stale)
+		nfsd_stats_fh_stale_inc(nn, exp);
+	return error;
+}
+
+/**
+ * fh_verify_local - filehandle lookup and access checking
+ * @net: net namespace in which to perform the export lookup
+ * @cred: RPC user credential
+ * @client: RPC auth domain
+ * @fhp: filehandle to be verified
+ * @type: expected type of object pointed to by filehandle
+ * @access: type of access needed to object
+ *
+ * This API can be used by callers who do not have an RPC
+ * transaction context (ie are not running in an nfsd thread).
+ *
+ * See fh_verify() for further descriptions of @fhp, @type, and @access.
+ */
+__be32
+fh_verify_local(struct net *net, struct svc_cred *cred,
+		struct auth_domain *client, struct svc_fh *fhp,
+		umode_t type, int access)
+{
+	return __fh_verify(NULL, net, cred, client, NULL,
+			   fhp, type, access);
+}
+
+/**
+ * fh_verify - filehandle lookup and access checking
+ * @rqstp: pointer to current rpc request
+ * @fhp: filehandle to be verified
+ * @type: expected type of object pointed to by filehandle
+ * @access: type of access needed to object
+ *
+ * Look up a dentry from the on-the-wire filehandle, check the client's
+ * access to the export, and set the current task's credentials.
+ *
+ * Regardless of success or failure of fh_verify(), fh_put() should be
+ * called on @fhp when the caller is finished with the filehandle.
+ *
+ * fh_verify() may be called multiple times on a given filehandle, for
+ * example, when processing an NFSv4 compound.  The first call will look
+ * up a dentry using the on-the-wire filehandle.  Subsequent calls will
+ * skip the lookup and just perform the other checks and possibly change
+ * the current task's credentials.
+ *
+ * @type specifies the type of object expected using one of the S_IF*
+ * constants defined in include/linux/stat.h.  The caller may use zero
+ * to indicate that it doesn't care, or a negative integer to indicate
+ * that it expects something not of the given type.
+ *
+ * @access is formed from the NFSD_MAY_* constants defined in
+ * fs/nfsd/vfs.h.
+ */
+__be32
+fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int access)
+{
+	return __fh_verify(rqstp, SVC_NET(rqstp), &rqstp->rq_cred,
+			   rqstp->rq_client, rqstp->rq_gssclient,
+			   fhp, type, access);
+}
+
+/*
+ * Compose a file handle for an NFS reply.
+ *
+ * Note that when first composed, the dentry may not yet have
+ * an inode.  In this case a call to fh_update should be made
+ * before the fh goes out on the wire ...
+ */
+static void _fh_update(struct svc_fh *fhp, struct svc_export *exp,
+		struct dentry *dentry)
+{
+	if (dentry != exp->ex_path.dentry) {
+		struct fid *fid = (struct fid *)
+			(fh_fsid(&fhp->fh_handle) + fhp->fh_handle.fh_size/4 - 1);
+		int maxsize = (fhp->fh_maxsize - fhp->fh_handle.fh_size)/4;
+		int fh_flags = (exp->ex_flags & NFSEXP_NOSUBTREECHECK) ? 0 :
+				EXPORT_FH_CONNECTABLE;
+		int fileid_type =
+			exportfs_encode_fh(dentry, fid, &maxsize, fh_flags);
+
+		fhp->fh_handle.fh_fileid_type =
+			fileid_type > 0 ? fileid_type : FILEID_INVALID;
+		fhp->fh_handle.fh_size += maxsize * 4;
+
+		if (exp->ex_flags & NFSEXP_SIGN_FH)
+			if (!fh_append_mac(fhp, exp->cd->net))
+				fhp->fh_handle.fh_fileid_type = FILEID_INVALID;
+	} else {
+		fhp->fh_handle.fh_fileid_type = FILEID_ROOT;
+	}
+}
+
+static bool is_root_export(struct svc_export *exp)
+{
+	return exp->ex_path.dentry == exp->ex_path.dentry->d_sb->s_root;
+}
+
+static struct super_block *exp_sb(struct svc_export *exp)
+{
+	return exp->ex_path.dentry->d_sb;
+}
+
+static bool fsid_type_ok_for_exp(u8 fsid_type, struct svc_export *exp)
+{
+	switch (fsid_type) {
+	case FSID_DEV:
+		if (!old_valid_dev(exp_sb(exp)->s_dev))
+			return false;
+		fallthrough;
+	case FSID_MAJOR_MINOR:
+	case FSID_ENCODE_DEV:
+		return exp_sb(exp)->s_type->fs_flags & FS_REQUIRES_DEV;
+	case FSID_NUM:
+		return exp->ex_flags & NFSEXP_FSID;
+	case FSID_UUID8:
+	case FSID_UUID16:
+		if (!is_root_export(exp))
+			return false;
+		fallthrough;
+	case FSID_UUID4_INUM:
+	case FSID_UUID16_INUM:
+		return exp->ex_uuid != NULL;
+	}
+	return true;
+}
+
+
+static void set_version_and_fsid_type(struct svc_fh *fhp, struct svc_export *exp, struct svc_fh *ref_fh)
+{
+	u8 version;
+	u8 fsid_type;
+retry:
+	version = 1;
+	if (ref_fh && ref_fh->fh_export == exp) {
+		version = ref_fh->fh_handle.fh_version;
+		fsid_type = ref_fh->fh_handle.fh_fsid_type;
+
+		ref_fh = NULL;
+
+		switch (version) {
+		case 0xca:
+			fsid_type = FSID_DEV;
+			break;
+		case 1:
+			break;
+		default:
+			goto retry;
+		}
+
+		/*
+		 * As the fsid -> filesystem mapping was guided by
+		 * user-space, there is no guarantee that the filesystem
+		 * actually supports that fsid type. If it doesn't we
+		 * loop around again without ref_fh set.
+		 */
+		if (!fsid_type_ok_for_exp(fsid_type, exp))
+			goto retry;
+	} else if (exp->ex_flags & NFSEXP_FSID) {
+		fsid_type = FSID_NUM;
+	} else if (exp->ex_uuid) {
+		if (fhp->fh_maxsize >= 64) {
+			if (is_root_export(exp))
+				fsid_type = FSID_UUID16;
+			else
+				fsid_type = FSID_UUID16_INUM;
+		} else {
+			if (is_root_export(exp))
+				fsid_type = FSID_UUID8;
+			else
+				fsid_type = FSID_UUID4_INUM;
+		}
+	} else if (!old_valid_dev(exp_sb(exp)->s_dev))
+		/* for newer device numbers, we must use a newer fsid format */
+		fsid_type = FSID_ENCODE_DEV;
+	else
+		fsid_type = FSID_DEV;
+	fhp->fh_handle.fh_version = version;
+	if (version)
+		fhp->fh_handle.fh_fsid_type = fsid_type;
+}
+
+__be32
+fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
+	   struct svc_fh *ref_fh)
+{
+	/* ref_fh is a reference file handle.
+	 * if it is non-null and for the same filesystem, then we should compose
+	 * a filehandle which is of the same version, where possible.
+	 */
+
+	struct inode * inode = d_inode(dentry);
+	dev_t ex_dev = exp_sb(exp)->s_dev;
+
+	dprintk("nfsd: fh_compose(exp %02x:%02x/%llu %pd2, ino=%llu)\n",
+		MAJOR(ex_dev), MINOR(ex_dev),
+		d_inode(exp->ex_path.dentry)->i_ino,
+		dentry,
+		(inode ? inode->i_ino : 0));
+
+	/* Choose filehandle version and fsid type based on
+	 * the reference filehandle (if it is in the same export)
+	 * or the export options.
+	 */
+	set_version_and_fsid_type(fhp, exp, ref_fh);
+
+	/* If we have a ref_fh, then copy the fh_no_wcc setting from it. */
+	fhp->fh_no_wcc = ref_fh ? ref_fh->fh_no_wcc : false;
+
+	if (ref_fh == fhp)
+		fh_put(ref_fh);
+
+	if (fhp->fh_dentry) {
+		printk(KERN_ERR "fh_compose: fh %pd2 not initialized!\n",
+		       dentry);
+	}
+	if (fhp->fh_maxsize < NFS_FHSIZE)
+		printk(KERN_ERR "fh_compose: called with maxsize %d! %pd2\n",
+		       fhp->fh_maxsize,
+		       dentry);
+
+	fhp->fh_dentry = dget(dentry); /* our internal copy */
+	fhp->fh_export = exp_get(exp);
+
+	fhp->fh_handle.fh_size =
+		key_len(fhp->fh_handle.fh_fsid_type) + 4;
+	fhp->fh_handle.fh_auth_type = 0;
+
+	mk_fsid(fhp->fh_handle.fh_fsid_type,
+		fh_fsid(&fhp->fh_handle),
+		ex_dev,
+		d_inode(exp->ex_path.dentry)->i_ino,
+		exp->ex_fsid, exp->ex_uuid);
+
+	if (inode)
+		_fh_update(fhp, exp, dentry);
+	if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) {
+		fh_put(fhp);
+		return nfserr_stale;
+	}
+
+	return 0;
+}
+
+/*
+ * Update file handle information after changing a dentry.
+ * This is only called by nfsd_create, nfsd_create_v3 and nfsd_proc_create
+ */
+__be32
+fh_update(struct svc_fh *fhp)
+{
+	struct dentry *dentry;
+
+	if (!fhp->fh_dentry)
+		goto out_bad;
+
+	dentry = fhp->fh_dentry;
+	if (d_really_is_negative(dentry))
+		goto out_negative;
+	if (fhp->fh_handle.fh_fileid_type != FILEID_ROOT)
+		return 0;
+
+	_fh_update(fhp, fhp->fh_export, dentry);
+	if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID)
+		return nfserr_stale;
+	return 0;
+out_bad:
+	printk(KERN_ERR "fh_update: fh not verified!\n");
+	return nfserr_serverfault;
+out_negative:
+	printk(KERN_ERR "fh_update: %pd2 still negative!\n",
+		dentry);
+	return nfserr_serverfault;
+}
+
+/**
+ * fh_getattr - Retrieve attributes on a local file
+ * @fhp: File handle of target file
+ * @stat: Caller-supplied kstat buffer to be filled in
+ *
+ * Returns nfs_ok on success, otherwise an NFS status code is
+ * returned.
+ */
+__be32 fh_getattr(const struct svc_fh *fhp, struct kstat *stat)
+{
+	struct path p = {
+		.mnt		= fhp->fh_export->ex_path.mnt,
+		.dentry		= fhp->fh_dentry,
+	};
+	struct inode *inode = d_inode(p.dentry);
+	u32 request_mask = STATX_BASIC_STATS;
+
+	if (S_ISREG(inode->i_mode))
+		request_mask |= (STATX_DIOALIGN | STATX_DIO_READ_ALIGN);
+
+	if (fhp->fh_maxsize == NFS4_FHSIZE)
+		request_mask |= (STATX_BTIME | STATX_CHANGE_COOKIE);
+
+	return nfserrno(vfs_getattr(&p, stat, request_mask,
+				    AT_STATX_SYNC_AS_STAT));
+}
+
+/**
+ * fh_fill_pre_attrs - Fill in pre-op attributes
+ * @fhp: file handle to be updated
+ *
+ */
+__be32 __must_check fh_fill_pre_attrs(struct svc_fh *fhp)
+{
+	bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE);
+	struct kstat stat;
+	__be32 err;
+
+	if (fhp->fh_no_wcc || fhp->fh_pre_saved)
+		return nfs_ok;
+
+	err = fh_getattr(fhp, &stat);
+	if (err)
+		return err;
+
+	if (v4)
+		fhp->fh_pre_change = nfsd4_change_attribute(&stat);
+
+	fhp->fh_pre_mtime = stat.mtime;
+	fhp->fh_pre_ctime = stat.ctime;
+	fhp->fh_pre_size  = stat.size;
+	fhp->fh_pre_saved = true;
+	return nfs_ok;
+}
+
+/**
+ * fh_fill_post_attrs - Fill in post-op attributes
+ * @fhp: file handle to be updated
+ *
+ */
+__be32 fh_fill_post_attrs(struct svc_fh *fhp)
+{
+	bool v4 = (fhp->fh_maxsize == NFS4_FHSIZE);
+	__be32 err;
+
+	if (fhp->fh_no_wcc)
+		return nfs_ok;
+
+	if (fhp->fh_post_saved)
+		printk("nfsd: inode locked twice during operation.\n");
+
+	err = fh_getattr(fhp, &fhp->fh_post_attr);
+	if (err)
+		return err;
+
+	fhp->fh_post_saved = true;
+	if (v4)
+		fhp->fh_post_change =
+			nfsd4_change_attribute(&fhp->fh_post_attr);
+	return nfs_ok;
+}
+
+/**
+ * fh_fill_both_attrs - Fill pre-op and post-op attributes
+ * @fhp: file handle to be updated
+ *
+ * This is used when the directory wasn't changed, but wcc attributes
+ * are needed anyway.
+ */
+__be32 __must_check fh_fill_both_attrs(struct svc_fh *fhp)
+{
+	__be32 err;
+
+	err = fh_fill_post_attrs(fhp);
+	if (err)
+		return err;
+
+	fhp->fh_pre_change = fhp->fh_post_change;
+	fhp->fh_pre_mtime = fhp->fh_post_attr.mtime;
+	fhp->fh_pre_ctime = fhp->fh_post_attr.ctime;
+	fhp->fh_pre_size = fhp->fh_post_attr.size;
+	fhp->fh_pre_saved = true;
+	return nfs_ok;
+}
+
+/*
+ * Release a file handle.
+ */
+void
+fh_put(struct svc_fh *fhp)
+{
+	struct dentry * dentry = fhp->fh_dentry;
+	struct svc_export * exp = fhp->fh_export;
+	if (dentry) {
+		fhp->fh_dentry = NULL;
+		dput(dentry);
+		fh_clear_pre_post_attrs(fhp);
+	}
+	fh_drop_write(fhp);
+	if (exp) {
+		exp_put(exp);
+		fhp->fh_export = NULL;
+	}
+	fhp->fh_no_wcc = false;
+	return;
+}
+
+/*
+ * Shorthand for dprintk()'s
+ */
+char * SVCFH_fmt(struct svc_fh *fhp)
+{
+	struct knfsd_fh *fh = &fhp->fh_handle;
+	static char buf[2+1+1+64*3+1];
+
+	if (fh->fh_size > 64)
+		return "bad-fh";
+	sprintf(buf, "%d: %*ph", fh->fh_size, fh->fh_size, fh->fh_raw);
+	return buf;
+}
+
+enum fsid_source fsid_source(const struct svc_fh *fhp)
+{
+	if (fhp->fh_handle.fh_version != 1)
+		return FSIDSOURCE_DEV;
+	switch(fhp->fh_handle.fh_fsid_type) {
+	case FSID_DEV:
+	case FSID_ENCODE_DEV:
+	case FSID_MAJOR_MINOR:
+		if (exp_sb(fhp->fh_export)->s_type->fs_flags & FS_REQUIRES_DEV)
+			return FSIDSOURCE_DEV;
+		break;
+	case FSID_NUM:
+		if (fhp->fh_export->ex_flags & NFSEXP_FSID)
+			return FSIDSOURCE_FSID;
+		break;
+	default:
+		break;
+	}
+	/* either a UUID type filehandle, or the filehandle doesn't
+	 * match the export.
+	 */
+	if (fhp->fh_export->ex_flags & NFSEXP_FSID)
+		return FSIDSOURCE_FSID;
+	if (fhp->fh_export->ex_uuid)
+		return FSIDSOURCE_UUID;
+	return FSIDSOURCE_DEV;
+}
+
+/**
+ * nfsd4_change_attribute - Generate an NFSv4 change_attribute value
+ * @stat: inode attributes
+ *
+ * Caller must fill in @stat before calling, typically by invoking
+ * vfs_getattr() with STATX_MODE, STATX_CTIME, and STATX_CHANGE_COOKIE.
+ * Returns an unsigned 64-bit changeid4 value (RFC 8881 Section 3.2).
+ *
+ * We could use i_version alone as the change attribute.  However, i_version
+ * can go backwards on a regular file after an unclean shutdown.  On its own
+ * that doesn't necessarily cause a problem, but if i_version goes backwards
+ * and then is incremented again it could reuse a value that was previously
+ * used before boot, and a client who queried the two values might incorrectly
+ * assume nothing changed.
+ *
+ * By using both ctime and the i_version counter we guarantee that as long as
+ * time doesn't go backwards we never reuse an old value. If the filesystem
+ * advertises STATX_ATTR_CHANGE_MONOTONIC, then this mitigation is not
+ * needed.
+ *
+ * We only need to do this for regular files as well. For directories, we
+ * assume that the new change attr is always logged to stable storage in some
+ * fashion before the results can be seen.
+ */
+u64 nfsd4_change_attribute(const struct kstat *stat)
+{
+	u64 chattr;
+
+	if (stat->result_mask & STATX_CHANGE_COOKIE) {
+		chattr = stat->change_cookie;
+		if (S_ISREG(stat->mode) &&
+		    !(stat->attributes & STATX_ATTR_CHANGE_MONOTONIC)) {
+			chattr += (u64)stat->ctime.tv_sec << 30;
+			chattr += stat->ctime.tv_nsec;
+		}
+	} else {
+		chattr = time_to_chattr(&stat->ctime);
+	}
+	return chattr;
+}

linux-7.2.3/fs/nfsd/nfsfh.h

@@ -0,0 +1,339 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de>
+ *
+ * This file describes the layout of the file handles as passed
+ * over the wire.
+ */
+#ifndef _LINUX_NFSD_NFSFH_H
+#define _LINUX_NFSD_NFSFH_H
+
+#include <linux/crc32.h>
+#include <linux/sunrpc/svc.h>
+#include <linux/iversion.h>
+#include <linux/exportfs.h>
+#include <linux/nfs4.h>
+
+#include "export.h"
+
+/*
+ * The file handle starts with a sequence of four-byte words.
+ * The first word contains a version number (1) and three descriptor bytes
+ * that tell how the remaining 3 variable length fields should be handled.
+ * These three bytes are auth_type, fsid_type and fileid_type.
+ *
+ * All four-byte values are in host-byte-order.
+ *
+ * The auth_type field is deprecated and must be set to 0.
+ *
+ * The fsid_type identifies how the filesystem (or export point) is
+ *    encoded.
+ *  Current values:
+ *     0  - 4 byte device id (ms-2-bytes major, ls-2-bytes minor), 4byte inode number
+ *        NOTE: we cannot use the kdev_t device id value, because kdev_t.h
+ *              says we mustn't.  We must break it up and reassemble.
+ *     1  - 4 byte user specified identifier
+ *     2  - 4 byte major, 4 byte minor, 4 byte inode number - DEPRECATED
+ *     3  - 4 byte device id, encoded for user-space, 4 byte inode number
+ *     4  - 4 byte inode number and 4 byte uuid
+ *     5  - 8 byte uuid
+ *     6  - 16 byte uuid
+ *     7  - 8 byte inode number and 16 byte uuid
+ *
+ * The fileid_type identifies how the file within the filesystem is encoded.
+ *   The values for this field are filesystem specific, exccept that
+ *   filesystems must not use the values '0' or '0xff'. 'See enum fid_type'
+ *   in include/linux/exportfs.h for currently registered values.
+ */
+
+struct knfsd_fh {
+	unsigned int	fh_size;	/*
+					 * Points to the current size while
+					 * building a new file handle.
+					 */
+	u8		fh_raw[NFS4_FHSIZE];
+};
+
+#define fh_version		fh_raw[0]
+#define fh_auth_type		fh_raw[1]
+#define fh_fsid_type		fh_raw[2]
+#define fh_fileid_type		fh_raw[3]
+
+static inline u32 *fh_fsid(const struct knfsd_fh *fh)
+{
+	return (u32 *)&fh->fh_raw[4];
+}
+
+static inline __u32 ino_t_to_u32(ino_t ino)
+{
+	return (__u32) ino;
+}
+
+static inline ino_t u32_to_ino_t(__u32 uino)
+{
+	return (ino_t) uino;
+}
+
+/*
+ * This is the internal representation of an NFS handle used in knfsd.
+ * pre_mtime/post_version will be used to support wcc_attr's in NFSv3.
+ */
+typedef struct svc_fh {
+	struct knfsd_fh		fh_handle;	/* FH data */
+	int			fh_maxsize;	/* max size for fh_handle */
+	struct dentry *		fh_dentry;	/* validated dentry */
+	struct svc_export *	fh_export;	/* export pointer */
+
+	bool			fh_want_write;	/* remount protection taken */
+	bool			fh_no_wcc;	/* no wcc data needed */
+	bool			fh_no_atomic_attr;
+						/*
+						 * wcc data is not atomic with
+						 * operation
+						 */
+	bool			fh_use_wgather;	/* NFSv2 wgather option */
+	bool			fh_64bit_cookies;/* readdir cookie size */
+	int			fh_flags;	/* FH flags */
+	bool			fh_post_saved;	/* post-op attrs saved */
+	bool			fh_pre_saved;	/* pre-op attrs saved */
+
+	/* Pre-op attributes saved when inode is locked */
+	__u64			fh_pre_size;	/* size before operation */
+	struct timespec64	fh_pre_mtime;	/* mtime before oper */
+	struct timespec64	fh_pre_ctime;	/* ctime before oper */
+	/*
+	 * pre-op nfsv4 change attr: note must check IS_I_VERSION(inode)
+	 *  to find out if it is valid.
+	 */
+	u64			fh_pre_change;
+
+	/* Post-op attributes saved in fh_fill_post_attrs() */
+	struct kstat		fh_post_attr;	/* full attrs after operation */
+	u64			fh_post_change; /* nfsv4 change; see above */
+} svc_fh;
+#define NFSD4_FH_FOREIGN (1<<0)
+#define SET_FH_FLAG(c, f) ((c)->fh_flags |= (f))
+#define HAS_FH_FLAG(c, f) ((c)->fh_flags & (f))
+
+enum nfsd_fsid {
+	FSID_DEV = 0,
+	FSID_NUM,
+	FSID_MAJOR_MINOR,
+	FSID_ENCODE_DEV,
+	FSID_UUID4_INUM,
+	FSID_UUID8,
+	FSID_UUID16,
+	FSID_UUID16_INUM,
+};
+
+enum fsid_source {
+	FSIDSOURCE_DEV,
+	FSIDSOURCE_FSID,
+	FSIDSOURCE_UUID,
+};
+extern enum fsid_source fsid_source(const struct svc_fh *fhp);
+
+
+/*
+ * This might look a little large to "inline" but in all calls except
+ * one, 'vers' is constant so moste of the function disappears.
+ *
+ * In some cases the values are considered to be host endian and in
+ * others, net endian. fsidv is always considered to be u32 as the
+ * callers don't know which it will be. So we must use __force to keep
+ * sparse from complaining. Since these values are opaque to the
+ * client, that shouldn't be a problem.
+ */
+static inline void mk_fsid(int vers, u32 *fsidv, dev_t dev, ino_t ino,
+			   u32 fsid, unsigned char *uuid)
+{
+	u32 *up;
+	switch(vers) {
+	case FSID_DEV:
+		fsidv[0] = (__force __u32)htonl((MAJOR(dev)<<16) |
+				 MINOR(dev));
+		fsidv[1] = ino_t_to_u32(ino);
+		break;
+	case FSID_NUM:
+		fsidv[0] = fsid;
+		break;
+	case FSID_MAJOR_MINOR:
+		fsidv[0] = (__force __u32)htonl(MAJOR(dev));
+		fsidv[1] = (__force __u32)htonl(MINOR(dev));
+		fsidv[2] = ino_t_to_u32(ino);
+		break;
+
+	case FSID_ENCODE_DEV:
+		fsidv[0] = new_encode_dev(dev);
+		fsidv[1] = ino_t_to_u32(ino);
+		break;
+
+	case FSID_UUID4_INUM:
+		/* 4 byte fsid and inode number */
+		up = (u32*)uuid;
+		fsidv[0] = ino_t_to_u32(ino);
+		fsidv[1] = up[0] ^ up[1] ^ up[2] ^ up[3];
+		break;
+
+	case FSID_UUID8:
+		/* 8 byte fsid  */
+		up = (u32*)uuid;
+		fsidv[0] = up[0] ^ up[2];
+		fsidv[1] = up[1] ^ up[3];
+		break;
+
+	case FSID_UUID16:
+		/* 16 byte fsid - NFSv3+ only */
+		memcpy(fsidv, uuid, 16);
+		break;
+
+	case FSID_UUID16_INUM:
+		/* 8 byte inode and 16 byte fsid */
+		*(u64*)fsidv = (u64)ino;
+		memcpy(fsidv+2, uuid, 16);
+		break;
+	default: BUG();
+	}
+}
+
+static inline int key_len(int type)
+{
+	switch(type) {
+	case FSID_DEV:		return 8;
+	case FSID_NUM: 		return 4;
+	case FSID_MAJOR_MINOR:	return 12;
+	case FSID_ENCODE_DEV:	return 8;
+	case FSID_UUID4_INUM:	return 8;
+	case FSID_UUID8:	return 8;
+	case FSID_UUID16:	return 16;
+	case FSID_UUID16_INUM:	return 24;
+	default: return 0;
+	}
+}
+
+/*
+ * Shorthand for dprintk()'s
+ */
+extern char * SVCFH_fmt(struct svc_fh *fhp);
+
+/*
+ * Function prototypes
+ */
+__be32	fh_verify(struct svc_rqst *, struct svc_fh *, umode_t, int);
+__be32	fh_verify_local(struct net *, struct svc_cred *, struct auth_domain *,
+			struct svc_fh *, umode_t, int);
+__be32	fh_getattr(const struct svc_fh *fhp, struct kstat *stat);
+__be32	fh_compose(struct svc_fh *, struct svc_export *, struct dentry *, struct svc_fh *);
+__be32	fh_update(struct svc_fh *);
+void	fh_put(struct svc_fh *);
+
+static __inline__ struct svc_fh *
+fh_copy(struct svc_fh *dst, const struct svc_fh *src)
+{
+	WARN_ON(src->fh_dentry);
+
+	*dst = *src;
+	return dst;
+}
+
+static inline void
+fh_copy_shallow(struct knfsd_fh *dst, const struct knfsd_fh *src)
+{
+	dst->fh_size = src->fh_size;
+	memcpy(&dst->fh_raw, &src->fh_raw, src->fh_size);
+}
+
+static __inline__ struct svc_fh *
+fh_init(struct svc_fh *fhp, int maxsize)
+{
+	memset(fhp, 0, sizeof(*fhp));
+	fhp->fh_maxsize = maxsize;
+	return fhp;
+}
+
+static inline bool fh_match(const struct knfsd_fh *fh1,
+			    const struct knfsd_fh *fh2)
+{
+	if (fh1->fh_size != fh2->fh_size)
+		return false;
+	if (memcmp(fh1->fh_raw, fh2->fh_raw, fh1->fh_size) != 0)
+		return false;
+	return true;
+}
+
+static inline bool fh_fsid_match(const struct knfsd_fh *fh1,
+				 const struct knfsd_fh *fh2)
+{
+	u32 *fsid1 = fh_fsid(fh1);
+	u32 *fsid2 = fh_fsid(fh2);
+
+	if (fh1->fh_fsid_type != fh2->fh_fsid_type)
+		return false;
+	if (memcmp(fsid1, fsid2, key_len(fh1->fh_fsid_type)) != 0)
+		return false;
+	return true;
+}
+
+/**
+ * fh_want_write - Get write access to an export
+ * @fhp: File handle of file to be written
+ *
+ * Caller must invoke fh_drop_write() when its write operation
+ * is complete.
+ *
+ * Returns 0 if the file handle's export can be written to. Otherwise
+ * the export is not prepared for updates, and the returned negative
+ * errno value reflects the reason for the failure.
+ */
+static inline int fh_want_write(struct svc_fh *fhp)
+{
+	int ret;
+
+	if (fhp->fh_want_write)
+		return 0;
+	ret = mnt_want_write(fhp->fh_export->ex_path.mnt);
+	if (!ret)
+		fhp->fh_want_write = true;
+	return ret;
+}
+
+/**
+ * fh_drop_write - Release write access on an export
+ * @fhp: File handle of file on which fh_want_write() was previously called
+ */
+static inline void fh_drop_write(struct svc_fh *fhp)
+{
+	if (fhp->fh_want_write) {
+		fhp->fh_want_write = false;
+		mnt_drop_write(fhp->fh_export->ex_path.mnt);
+	}
+}
+
+/**
+ * knfsd_fh_hash - calculate the crc32 hash for the filehandle
+ * @fh - pointer to filehandle
+ *
+ * returns a crc32 hash for the filehandle that is compatible with
+ * the one displayed by "wireshark".
+ */
+static inline u32 knfsd_fh_hash(const struct knfsd_fh *fh)
+{
+	return ~crc32_le(0xFFFFFFFF, fh->fh_raw, fh->fh_size);
+}
+
+/**
+ * fh_clear_pre_post_attrs - Reset pre/post attributes
+ * @fhp: file handle to be updated
+ *
+ */
+static inline void fh_clear_pre_post_attrs(struct svc_fh *fhp)
+{
+	fhp->fh_post_saved = false;
+	fhp->fh_pre_saved = false;
+}
+
+u64 nfsd4_change_attribute(const struct kstat *stat);
+__be32 __must_check fh_fill_pre_attrs(struct svc_fh *fhp);
+__be32 fh_fill_post_attrs(struct svc_fh *fhp);
+__be32 __must_check fh_fill_both_attrs(struct svc_fh *fhp);
+#endif /* _LINUX_NFSD_NFSFH_H */

linux-7.2.3/fs/nfsd/nfsproc.c

@@ -0,0 +1,850 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Process version 2 NFS requests.
+ *
+ * Copyright (C) 1995-1997 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#include <linux/namei.h>
+
+#include "cache.h"
+#include "xdr.h"
+#include "vfs.h"
+#include "trace.h"
+
+#define NFSDDBG_FACILITY		NFSDDBG_PROC
+
+static __be32 nfsd_map_status(__be32 status)
+{
+	switch (status) {
+	case nfs_ok:
+		break;
+	case nfserr_nofilehandle:
+	case nfserr_badhandle:
+		status = nfserr_stale;
+		break;
+	case nfserr_wrongsec:
+	case nfserr_xdev:
+	case nfserr_file_open:
+		status = nfserr_acces;
+		break;
+	case nfserr_symlink_not_dir:
+		status = nfserr_notdir;
+		break;
+	case nfserr_symlink:
+	case nfserr_wrong_type:
+		status = nfserr_io;
+		break;
+	}
+	return status;
+}
+
+static __be32
+nfsd_proc_null(struct svc_rqst *rqstp)
+{
+	return rpc_success;
+}
+
+/*
+ * Get a file's attributes
+ * N.B. After this call resp->fh needs an fh_put
+ */
+static __be32
+nfsd_proc_getattr(struct svc_rqst *rqstp)
+{
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
+
+	trace_nfsd_vfs_getattr(rqstp, &argp->fh);
+
+	fh_copy(&resp->fh, &argp->fh);
+	resp->status = fh_verify(rqstp, &resp->fh, 0,
+				 NFSD_MAY_NOP | NFSD_MAY_BYPASS_GSS_ON_ROOT);
+	if (resp->status != nfs_ok)
+		goto out;
+	resp->status = fh_getattr(&resp->fh, &resp->stat);
+out:
+	resp->status = nfsd_map_status(resp->status);
+	return rpc_success;
+}
+
+/*
+ * Set a file's attributes
+ * N.B. After this call resp->fh needs an fh_put
+ */
+static __be32
+nfsd_proc_setattr(struct svc_rqst *rqstp)
+{
+	struct nfsd_sattrargs *argp = rqstp->rq_argp;
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
+	struct iattr *iap = &argp->attrs;
+	struct nfsd_attrs attrs = {
+		.na_iattr	= iap,
+	};
+	struct svc_fh *fhp;
+
+	dprintk("nfsd: SETATTR  %s, valid=%x, size=%ld\n",
+		SVCFH_fmt(&argp->fh),
+		argp->attrs.ia_valid, (long) argp->attrs.ia_size);
+
+	fhp = fh_copy(&resp->fh, &argp->fh);
+
+	/*
+	 * NFSv2 does not differentiate between "set-[ac]time-to-now"
+	 * which only requires access, and "set-[ac]time-to-X" which
+	 * requires ownership.
+	 * So if it looks like it might be "set both to the same time which
+	 * is close to now", and if setattr_prepare fails, then we
+	 * convert to "set to now" instead of "set to explicit time"
+	 *
+	 * We only call setattr_prepare as the last test as technically
+	 * it is not an interface that we should be using.
+	 */
+#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET)
+#define	MAX_TOUCH_TIME_ERROR (30*60)
+	if ((iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET &&
+	    iap->ia_mtime.tv_sec == iap->ia_atime.tv_sec) {
+		/*
+		 * Looks probable.
+		 *
+		 * Now just make sure time is in the right ballpark.
+		 * Solaris, at least, doesn't seem to care what the time
+		 * request is.  We require it be within 30 minutes of now.
+		 */
+		time64_t delta = iap->ia_atime.tv_sec - ktime_get_real_seconds();
+
+		resp->status = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP);
+		if (resp->status != nfs_ok)
+			goto out;
+
+		if (delta < 0)
+			delta = -delta;
+		if (delta < MAX_TOUCH_TIME_ERROR &&
+		    setattr_prepare(&nop_mnt_idmap, fhp->fh_dentry, iap) != 0) {
+			/*
+			 * Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME.
+			 * This will cause notify_change to set these times
+			 * to "now"
+			 */
+			iap->ia_valid &= ~BOTH_TIME_SET;
+		}
+	}
+
+	resp->status = nfsd_setattr(rqstp, fhp, &attrs, NULL);
+	if (resp->status != nfs_ok)
+		goto out;
+
+	resp->status = fh_getattr(&resp->fh, &resp->stat);
+out:
+	resp->status = nfsd_map_status(resp->status);
+	return rpc_success;
+}
+
+/* Obsolete, replaced by MNTPROC_MNT. */
+static __be32
+nfsd_proc_root(struct svc_rqst *rqstp)
+{
+	return rpc_success;
+}
+
+/*
+ * Look up a path name component
+ * Note: the dentry in the resp->fh may be negative if the file
+ * doesn't exist yet.
+ * N.B. After this call resp->fh needs an fh_put
+ */
+static __be32
+nfsd_proc_lookup(struct svc_rqst *rqstp)
+{
+	struct nfsd_diropargs *argp = rqstp->rq_argp;
+	struct nfsd_diropres *resp = rqstp->rq_resp;
+
+	dprintk("nfsd: LOOKUP   %s %.*s\n",
+		SVCFH_fmt(&argp->fh), argp->len, argp->name);
+
+	fh_init(&resp->fh, NFS_FHSIZE);
+	resp->status = nfsd_lookup(rqstp, &argp->fh, argp->name, argp->len,
+				   &resp->fh);
+	fh_put(&argp->fh);
+	if (resp->status != nfs_ok)
+		goto out;
+
+	resp->status = fh_getattr(&resp->fh, &resp->stat);
+out:
+	resp->status = nfsd_map_status(resp->status);
+	return rpc_success;
+}
+
+/*
+ * Read a symlink.
+ */
+static __be32
+nfsd_proc_readlink(struct svc_rqst *rqstp)
+{
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd_readlinkres *resp = rqstp->rq_resp;
+
+	dprintk("nfsd: READLINK %s\n", SVCFH_fmt(&argp->fh));
+
+	/* Read the symlink. */
+	resp->len = NFS_MAXPATHLEN;
+	resp->page = *(rqstp->rq_next_page++);
+	resp->status = nfsd_readlink(rqstp, &argp->fh,
+				     page_address(resp->page), &resp->len);
+
+	fh_put(&argp->fh);
+	resp->status = nfsd_map_status(resp->status);
+	return rpc_success;
+}
+
+/*
+ * Read a portion of a file.
+ * N.B. After this call resp->fh needs an fh_put
+ */
+static __be32
+nfsd_proc_read(struct svc_rqst *rqstp)
+{
+	struct nfsd_readargs *argp = rqstp->rq_argp;
+	struct nfsd_readres *resp = rqstp->rq_resp;
+	u32 eof;
+
+	dprintk("nfsd: READ    %s %d bytes at %d\n",
+		SVCFH_fmt(&argp->fh),
+		argp->count, argp->offset);
+
+	argp->count = min_t(u32, argp->count, NFS_MAXDATA);
+	argp->count = min_t(u32, argp->count, rqstp->rq_res.buflen);
+
+	resp->pages = rqstp->rq_next_page;
+
+	/* Obtain buffer pointer for payload. 19 is 1 word for
+	 * status, 17 words for fattr, and 1 word for the byte count.
+	 */
+	svc_reserve_auth(rqstp, (19<<2) + argp->count + 4);
+
+	resp->count = argp->count;
+	fh_copy(&resp->fh, &argp->fh);
+	resp->status = nfsd_read(rqstp, &resp->fh, argp->offset,
+				 &resp->count, &eof);
+	if (resp->status == nfs_ok)
+		resp->status = fh_getattr(&resp->fh, &resp->stat);
+	else if (resp->status == nfserr_jukebox)
+		set_bit(RQ_DROPME, &rqstp->rq_flags);
+	resp->status = nfsd_map_status(resp->status);
+	return rpc_success;
+}
+
+/* Reserved */
+static __be32
+nfsd_proc_writecache(struct svc_rqst *rqstp)
+{
+	return rpc_success;
+}
+
+/*
+ * Write data to a file
+ * N.B. After this call resp->fh needs an fh_put
+ */
+static __be32
+nfsd_proc_write(struct svc_rqst *rqstp)
+{
+	struct nfsd_writeargs *argp = rqstp->rq_argp;
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
+	unsigned long cnt = argp->len;
+
+	dprintk("nfsd: WRITE    %s %u bytes at %d\n",
+		SVCFH_fmt(&argp->fh),
+		argp->len, argp->offset);
+
+	fh_copy(&resp->fh, &argp->fh);
+	resp->status = nfsd_write(rqstp, &resp->fh, argp->offset,
+				  &argp->payload, &cnt, NFS_DATA_SYNC, NULL);
+	if (resp->status == nfs_ok)
+		resp->status = fh_getattr(&resp->fh, &resp->stat);
+	else if (resp->status == nfserr_jukebox)
+		set_bit(RQ_DROPME, &rqstp->rq_flags);
+	resp->status = nfsd_map_status(resp->status);
+	return rpc_success;
+}
+
+/*
+ * CREATE processing is complicated. The keyword here is `overloaded.'
+ * The parent directory is kept locked between the check for existence
+ * and the actual create() call in compliance with VFS protocols.
+ * N.B. After this call _both_ argp->fh and resp->fh need an fh_put
+ */
+static __be32
+nfsd_proc_create(struct svc_rqst *rqstp)
+{
+	struct nfsd_createargs *argp = rqstp->rq_argp;
+	struct nfsd_diropres *resp = rqstp->rq_resp;
+	svc_fh		*dirfhp = &argp->fh;
+	svc_fh		*newfhp = &resp->fh;
+	struct iattr	*attr = &argp->attrs;
+	struct nfsd_attrs attrs = {
+		.na_iattr	= attr,
+	};
+	struct inode	*inode;
+	struct dentry	*dchild;
+	int		type, mode;
+	int		hosterr;
+	dev_t		rdev = 0, wanted = new_decode_dev(attr->ia_size);
+
+	/* First verify the parent file handle */
+	resp->status = fh_verify(rqstp, dirfhp, S_IFDIR, NFSD_MAY_EXEC);
+	if (resp->status != nfs_ok)
+		goto done; /* must fh_put dirfhp even on error */
+
+	/* Check for NFSD_MAY_WRITE in nfsd_create if necessary */
+
+	resp->status = nfserr_exist;
+	if (isdotent(argp->name, argp->len))
+		goto done;
+	hosterr = fh_want_write(dirfhp);
+	if (hosterr) {
+		resp->status = nfserrno(hosterr);
+		goto done;
+	}
+
+	dchild = start_creating(&nop_mnt_idmap, dirfhp->fh_dentry,
+				&QSTR_LEN(argp->name, argp->len));
+	if (IS_ERR(dchild)) {
+		resp->status = nfserrno(PTR_ERR(dchild));
+		goto out_write;
+	}
+	fh_init(newfhp, NFS_FHSIZE);
+	resp->status = fh_compose(newfhp, dirfhp->fh_export, dchild, dirfhp);
+	if (!resp->status && d_really_is_negative(dchild))
+		resp->status = nfserr_noent;
+	if (resp->status) {
+		if (resp->status != nfserr_noent)
+			goto out_unlock;
+		/*
+		 * If the new file handle wasn't verified, we can't tell
+		 * whether the file exists or not. Time to bail ...
+		 */
+		resp->status = nfserr_acces;
+		if (!newfhp->fh_dentry) {
+			printk(KERN_WARNING
+				"nfsd_proc_create: file handle not verified\n");
+			goto out_unlock;
+		}
+	}
+
+	inode = d_inode(newfhp->fh_dentry);
+
+	/* Unfudge the mode bits */
+	if (attr->ia_valid & ATTR_MODE) {
+		type = attr->ia_mode & S_IFMT;
+		mode = attr->ia_mode & ~S_IFMT;
+		if (!type) {
+			/* no type, so if target exists, assume same as that,
+			 * else assume a file */
+			if (inode) {
+				type = inode->i_mode & S_IFMT;
+				switch(type) {
+				case S_IFCHR:
+				case S_IFBLK:
+					/* reserve rdev for later checking */
+					rdev = inode->i_rdev;
+					attr->ia_valid |= ATTR_SIZE;
+
+					fallthrough;
+				case S_IFIFO:
+					/* this is probably a permission check..
+					 * at least IRIX implements perm checking on
+					 *   echo thing > device-special-file-or-pipe
+					 * by doing a CREATE with type==0
+					 */
+					resp->status = nfsd_permission(
+						&rqstp->rq_cred,
+						newfhp->fh_export,
+						newfhp->fh_dentry,
+						NFSD_MAY_WRITE|NFSD_MAY_LOCAL_ACCESS);
+					if (resp->status && resp->status != nfserr_rofs)
+						goto out_unlock;
+				}
+			} else
+				type = S_IFREG;
+		}
+	} else if (inode) {
+		type = inode->i_mode & S_IFMT;
+		mode = inode->i_mode & ~S_IFMT;
+	} else {
+		type = S_IFREG;
+		mode = 0;	/* ??? */
+	}
+
+	attr->ia_valid |= ATTR_MODE;
+	attr->ia_mode = mode;
+
+	/* Special treatment for non-regular files according to the
+	 * gospel of sun micro
+	 */
+	if (type != S_IFREG) {
+		if (type != S_IFBLK && type != S_IFCHR) {
+			rdev = 0;
+		} else if (type == S_IFCHR && !(attr->ia_valid & ATTR_SIZE)) {
+			/* If you think you've seen the worst, grok this. */
+			type = S_IFIFO;
+		} else {
+			/* Okay, char or block special */
+			if (!rdev)
+				rdev = wanted;
+		}
+
+		/* we've used the SIZE information, so discard it */
+		attr->ia_valid &= ~ATTR_SIZE;
+
+		/* Make sure the type and device matches */
+		resp->status = nfserr_exist;
+		if (inode && inode_wrong_type(inode, type))
+			goto out_unlock;
+	}
+
+	resp->status = nfs_ok;
+	if (!inode) {
+		/* File doesn't exist. Create it and set attrs */
+		resp->status = nfsd_create_locked(rqstp, dirfhp, &attrs, type,
+						  rdev, newfhp);
+		/* nfsd_create_locked() unlocked the parent */
+		dput(dchild);
+		goto out_write;
+	} else if (type == S_IFREG) {
+		dprintk("nfsd:   existing %s, valid=%x, size=%ld\n",
+			argp->name, attr->ia_valid, (long) attr->ia_size);
+		/* File already exists. We ignore all attributes except
+		 * size, so that creat() behaves exactly like
+		 * open(..., O_CREAT|O_TRUNC|O_WRONLY).
+		 */
+		attr->ia_valid &= ATTR_SIZE;
+		if (attr->ia_valid)
+			resp->status = nfsd_setattr(rqstp, newfhp, &attrs,
+						    NULL);
+	}
+
+out_unlock:
+	end_creating(dchild);
+out_write:
+	fh_drop_write(dirfhp);
+done:
+	fh_put(dirfhp);
+	if (resp->status != nfs_ok)
+		goto out;
+	resp->status = fh_getattr(&resp->fh, &resp->stat);
+out:
+	resp->status = nfsd_map_status(resp->status);
+	return rpc_success;
+}
+
+static __be32
+nfsd_proc_remove(struct svc_rqst *rqstp)
+{
+	struct nfsd_diropargs *argp = rqstp->rq_argp;
+	struct nfsd_stat *resp = rqstp->rq_resp;
+
+	/* Unlink. -SIFDIR means file must not be a directory */
+	resp->status = nfsd_unlink(rqstp, &argp->fh, -S_IFDIR,
+				   argp->name, argp->len);
+	fh_put(&argp->fh);
+	resp->status = nfsd_map_status(resp->status);
+	return rpc_success;
+}
+
+static __be32
+nfsd_proc_rename(struct svc_rqst *rqstp)
+{
+	struct nfsd_renameargs *argp = rqstp->rq_argp;
+	struct nfsd_stat *resp = rqstp->rq_resp;
+
+	resp->status = nfsd_rename(rqstp, &argp->ffh, argp->fname, argp->flen,
+				   &argp->tfh, argp->tname, argp->tlen);
+	fh_put(&argp->ffh);
+	fh_put(&argp->tfh);
+	resp->status = nfsd_map_status(resp->status);
+	return rpc_success;
+}
+
+static __be32
+nfsd_proc_link(struct svc_rqst *rqstp)
+{
+	struct nfsd_linkargs *argp = rqstp->rq_argp;
+	struct nfsd_stat *resp = rqstp->rq_resp;
+
+	resp->status = nfsd_link(rqstp, &argp->tfh, argp->tname, argp->tlen,
+				 &argp->ffh);
+	fh_put(&argp->ffh);
+	fh_put(&argp->tfh);
+	resp->status = nfsd_map_status(resp->status);
+	return rpc_success;
+}
+
+static __be32
+nfsd_proc_symlink(struct svc_rqst *rqstp)
+{
+	struct nfsd_symlinkargs *argp = rqstp->rq_argp;
+	struct nfsd_stat *resp = rqstp->rq_resp;
+	struct nfsd_attrs attrs = {
+		.na_iattr	= &argp->attrs,
+	};
+	struct svc_fh	newfh;
+
+	if (argp->tlen > NFS_MAXPATHLEN) {
+		resp->status = nfserr_nametoolong;
+		goto out;
+	}
+
+	argp->tname = svc_fill_symlink_pathname(rqstp, &argp->first,
+						page_address(rqstp->rq_arg.pages[0]),
+						argp->tlen);
+	if (IS_ERR(argp->tname)) {
+		resp->status = nfserrno(PTR_ERR(argp->tname));
+		goto out;
+	}
+
+	fh_init(&newfh, NFS_FHSIZE);
+	resp->status = nfsd_symlink(rqstp, &argp->ffh, argp->fname, argp->flen,
+				    argp->tname, &attrs, &newfh);
+
+	kfree(argp->tname);
+	fh_put(&argp->ffh);
+	fh_put(&newfh);
+out:
+	resp->status = nfsd_map_status(resp->status);
+	return rpc_success;
+}
+
+/*
+ * Make directory. This operation is not idempotent.
+ * N.B. After this call resp->fh needs an fh_put
+ */
+static __be32
+nfsd_proc_mkdir(struct svc_rqst *rqstp)
+{
+	struct nfsd_createargs *argp = rqstp->rq_argp;
+	struct nfsd_diropres *resp = rqstp->rq_resp;
+	struct nfsd_attrs attrs = {
+		.na_iattr	= &argp->attrs,
+	};
+
+	if (resp->fh.fh_dentry) {
+		printk(KERN_WARNING
+			"nfsd_proc_mkdir: response already verified??\n");
+	}
+
+	argp->attrs.ia_valid &= ~ATTR_SIZE;
+	fh_init(&resp->fh, NFS_FHSIZE);
+	resp->status = nfsd_create(rqstp, &argp->fh, argp->name, argp->len,
+				   &attrs, S_IFDIR, 0, &resp->fh);
+	fh_put(&argp->fh);
+	if (resp->status != nfs_ok)
+		goto out;
+
+	resp->status = fh_getattr(&resp->fh, &resp->stat);
+out:
+	resp->status = nfsd_map_status(resp->status);
+	return rpc_success;
+}
+
+/*
+ * Remove a directory
+ */
+static __be32
+nfsd_proc_rmdir(struct svc_rqst *rqstp)
+{
+	struct nfsd_diropargs *argp = rqstp->rq_argp;
+	struct nfsd_stat *resp = rqstp->rq_resp;
+
+	resp->status = nfsd_unlink(rqstp, &argp->fh, S_IFDIR,
+				   argp->name, argp->len);
+	fh_put(&argp->fh);
+	resp->status = nfsd_map_status(resp->status);
+	return rpc_success;
+}
+
+static void nfsd_init_dirlist_pages(struct svc_rqst *rqstp,
+				    struct nfsd_readdirres *resp,
+				    u32 count)
+{
+	struct xdr_buf *buf = &resp->dirlist;
+	struct xdr_stream *xdr = &resp->xdr;
+
+	memset(buf, 0, sizeof(*buf));
+
+	/* Reserve room for the NULL ptr & eof flag (-2 words) */
+	buf->buflen = clamp(count, (u32)(XDR_UNIT * 2), (u32)PAGE_SIZE);
+	buf->buflen -= XDR_UNIT * 2;
+	buf->pages = rqstp->rq_next_page;
+	rqstp->rq_next_page++;
+
+	xdr_init_encode_pages(xdr, buf);
+}
+
+/*
+ * Read a portion of a directory.
+ */
+static __be32
+nfsd_proc_readdir(struct svc_rqst *rqstp)
+{
+	struct nfsd_readdirargs *argp = rqstp->rq_argp;
+	struct nfsd_readdirres *resp = rqstp->rq_resp;
+	loff_t		offset;
+
+	trace_nfsd_vfs_readdir(rqstp, &argp->fh, argp->count, argp->cookie);
+
+	nfsd_init_dirlist_pages(rqstp, resp, argp->count);
+
+	resp->common.err = nfs_ok;
+	resp->cookie_offset = 0;
+	offset = argp->cookie;
+	resp->status = nfsd_readdir(rqstp, &argp->fh, &offset,
+				    &resp->common, nfssvc_encode_entry);
+	nfssvc_encode_nfscookie(resp, offset);
+
+	fh_put(&argp->fh);
+	resp->status = nfsd_map_status(resp->status);
+	return rpc_success;
+}
+
+/*
+ * Get file system info
+ */
+static __be32
+nfsd_proc_statfs(struct svc_rqst *rqstp)
+{
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd_statfsres *resp = rqstp->rq_resp;
+
+	resp->status = nfsd_statfs(rqstp, &argp->fh, &resp->stats,
+				   NFSD_MAY_BYPASS_GSS_ON_ROOT);
+	fh_put(&argp->fh);
+	resp->status = nfsd_map_status(resp->status);
+	return rpc_success;
+}
+
+/*
+ * NFSv2 Server procedures.
+ * Only the results of non-idempotent operations are cached.
+ */
+
+#define ST 1		/* status */
+#define FH 8		/* filehandle */
+#define	AT 18		/* attributes */
+
+static const struct svc_procedure nfsd_procedures2[18] = {
+	[NFSPROC_NULL] = {
+		.pc_func = nfsd_proc_null,
+		.pc_decode = nfssvc_decode_voidarg,
+		.pc_encode = nfssvc_encode_voidres,
+		.pc_argsize = sizeof(struct nfsd_voidargs),
+		.pc_argzero = sizeof(struct nfsd_voidargs),
+		.pc_ressize = sizeof(struct nfsd_voidres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = 0,
+		.pc_name = "NULL",
+	},
+	[NFSPROC_GETATTR] = {
+		.pc_func = nfsd_proc_getattr,
+		.pc_decode = nfssvc_decode_fhandleargs,
+		.pc_encode = nfssvc_encode_attrstatres,
+		.pc_release = nfssvc_release_attrstat,
+		.pc_argsize = sizeof(struct nfsd_fhandle),
+		.pc_argzero = sizeof(struct nfsd_fhandle),
+		.pc_ressize = sizeof(struct nfsd_attrstat),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+AT,
+		.pc_name = "GETATTR",
+	},
+	[NFSPROC_SETATTR] = {
+		.pc_func = nfsd_proc_setattr,
+		.pc_decode = nfssvc_decode_sattrargs,
+		.pc_encode = nfssvc_encode_attrstatres,
+		.pc_release = nfssvc_release_attrstat,
+		.pc_argsize = sizeof(struct nfsd_sattrargs),
+		.pc_argzero = sizeof(struct nfsd_sattrargs),
+		.pc_ressize = sizeof(struct nfsd_attrstat),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+AT,
+		.pc_name = "SETATTR",
+	},
+	[NFSPROC_ROOT] = {
+		.pc_func = nfsd_proc_root,
+		.pc_decode = nfssvc_decode_voidarg,
+		.pc_encode = nfssvc_encode_voidres,
+		.pc_argsize = sizeof(struct nfsd_voidargs),
+		.pc_argzero = sizeof(struct nfsd_voidargs),
+		.pc_ressize = sizeof(struct nfsd_voidres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = 0,
+		.pc_name = "ROOT",
+	},
+	[NFSPROC_LOOKUP] = {
+		.pc_func = nfsd_proc_lookup,
+		.pc_decode = nfssvc_decode_diropargs,
+		.pc_encode = nfssvc_encode_diropres,
+		.pc_release = nfssvc_release_diropres,
+		.pc_argsize = sizeof(struct nfsd_diropargs),
+		.pc_argzero = sizeof(struct nfsd_diropargs),
+		.pc_ressize = sizeof(struct nfsd_diropres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+FH+AT,
+		.pc_name = "LOOKUP",
+	},
+	[NFSPROC_READLINK] = {
+		.pc_func = nfsd_proc_readlink,
+		.pc_decode = nfssvc_decode_fhandleargs,
+		.pc_encode = nfssvc_encode_readlinkres,
+		.pc_argsize = sizeof(struct nfsd_fhandle),
+		.pc_argzero = sizeof(struct nfsd_fhandle),
+		.pc_ressize = sizeof(struct nfsd_readlinkres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+1+NFS_MAXPATHLEN/4,
+		.pc_name = "READLINK",
+	},
+	[NFSPROC_READ] = {
+		.pc_func = nfsd_proc_read,
+		.pc_decode = nfssvc_decode_readargs,
+		.pc_encode = nfssvc_encode_readres,
+		.pc_release = nfssvc_release_readres,
+		.pc_argsize = sizeof(struct nfsd_readargs),
+		.pc_argzero = sizeof(struct nfsd_readargs),
+		.pc_ressize = sizeof(struct nfsd_readres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+AT+1+NFS_MAXDATA/4,
+		.pc_name = "READ",
+	},
+	[NFSPROC_WRITECACHE] = {
+		.pc_func = nfsd_proc_writecache,
+		.pc_decode = nfssvc_decode_voidarg,
+		.pc_encode = nfssvc_encode_voidres,
+		.pc_argsize = sizeof(struct nfsd_voidargs),
+		.pc_argzero = sizeof(struct nfsd_voidargs),
+		.pc_ressize = sizeof(struct nfsd_voidres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = 0,
+		.pc_name = "WRITECACHE",
+	},
+	[NFSPROC_WRITE] = {
+		.pc_func = nfsd_proc_write,
+		.pc_decode = nfssvc_decode_writeargs,
+		.pc_encode = nfssvc_encode_attrstatres,
+		.pc_release = nfssvc_release_attrstat,
+		.pc_argsize = sizeof(struct nfsd_writeargs),
+		.pc_argzero = sizeof(struct nfsd_writeargs),
+		.pc_ressize = sizeof(struct nfsd_attrstat),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+AT,
+		.pc_name = "WRITE",
+	},
+	[NFSPROC_CREATE] = {
+		.pc_func = nfsd_proc_create,
+		.pc_decode = nfssvc_decode_createargs,
+		.pc_encode = nfssvc_encode_diropres,
+		.pc_release = nfssvc_release_diropres,
+		.pc_argsize = sizeof(struct nfsd_createargs),
+		.pc_argzero = sizeof(struct nfsd_createargs),
+		.pc_ressize = sizeof(struct nfsd_diropres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+FH+AT,
+		.pc_name = "CREATE",
+	},
+	[NFSPROC_REMOVE] = {
+		.pc_func = nfsd_proc_remove,
+		.pc_decode = nfssvc_decode_diropargs,
+		.pc_encode = nfssvc_encode_statres,
+		.pc_argsize = sizeof(struct nfsd_diropargs),
+		.pc_argzero = sizeof(struct nfsd_diropargs),
+		.pc_ressize = sizeof(struct nfsd_stat),
+		.pc_cachetype = RC_REPLSTAT,
+		.pc_xdrressize = ST,
+		.pc_name = "REMOVE",
+	},
+	[NFSPROC_RENAME] = {
+		.pc_func = nfsd_proc_rename,
+		.pc_decode = nfssvc_decode_renameargs,
+		.pc_encode = nfssvc_encode_statres,
+		.pc_argsize = sizeof(struct nfsd_renameargs),
+		.pc_argzero = sizeof(struct nfsd_renameargs),
+		.pc_ressize = sizeof(struct nfsd_stat),
+		.pc_cachetype = RC_REPLSTAT,
+		.pc_xdrressize = ST,
+		.pc_name = "RENAME",
+	},
+	[NFSPROC_LINK] = {
+		.pc_func = nfsd_proc_link,
+		.pc_decode = nfssvc_decode_linkargs,
+		.pc_encode = nfssvc_encode_statres,
+		.pc_argsize = sizeof(struct nfsd_linkargs),
+		.pc_argzero = sizeof(struct nfsd_linkargs),
+		.pc_ressize = sizeof(struct nfsd_stat),
+		.pc_cachetype = RC_REPLSTAT,
+		.pc_xdrressize = ST,
+		.pc_name = "LINK",
+	},
+	[NFSPROC_SYMLINK] = {
+		.pc_func = nfsd_proc_symlink,
+		.pc_decode = nfssvc_decode_symlinkargs,
+		.pc_encode = nfssvc_encode_statres,
+		.pc_argsize = sizeof(struct nfsd_symlinkargs),
+		.pc_argzero = sizeof(struct nfsd_symlinkargs),
+		.pc_ressize = sizeof(struct nfsd_stat),
+		.pc_cachetype = RC_REPLSTAT,
+		.pc_xdrressize = ST,
+		.pc_name = "SYMLINK",
+	},
+	[NFSPROC_MKDIR] = {
+		.pc_func = nfsd_proc_mkdir,
+		.pc_decode = nfssvc_decode_createargs,
+		.pc_encode = nfssvc_encode_diropres,
+		.pc_release = nfssvc_release_diropres,
+		.pc_argsize = sizeof(struct nfsd_createargs),
+		.pc_argzero = sizeof(struct nfsd_createargs),
+		.pc_ressize = sizeof(struct nfsd_diropres),
+		.pc_cachetype = RC_REPLBUFF,
+		.pc_xdrressize = ST+FH+AT,
+		.pc_name = "MKDIR",
+	},
+	[NFSPROC_RMDIR] = {
+		.pc_func = nfsd_proc_rmdir,
+		.pc_decode = nfssvc_decode_diropargs,
+		.pc_encode = nfssvc_encode_statres,
+		.pc_argsize = sizeof(struct nfsd_diropargs),
+		.pc_argzero = sizeof(struct nfsd_diropargs),
+		.pc_ressize = sizeof(struct nfsd_stat),
+		.pc_cachetype = RC_REPLSTAT,
+		.pc_xdrressize = ST,
+		.pc_name = "RMDIR",
+	},
+	[NFSPROC_READDIR] = {
+		.pc_func = nfsd_proc_readdir,
+		.pc_decode = nfssvc_decode_readdirargs,
+		.pc_encode = nfssvc_encode_readdirres,
+		.pc_argsize = sizeof(struct nfsd_readdirargs),
+		.pc_argzero = sizeof(struct nfsd_readdirargs),
+		.pc_ressize = sizeof(struct nfsd_readdirres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_name = "READDIR",
+	},
+	[NFSPROC_STATFS] = {
+		.pc_func = nfsd_proc_statfs,
+		.pc_decode = nfssvc_decode_fhandleargs,
+		.pc_encode = nfssvc_encode_statfsres,
+		.pc_argsize = sizeof(struct nfsd_fhandle),
+		.pc_argzero = sizeof(struct nfsd_fhandle),
+		.pc_ressize = sizeof(struct nfsd_statfsres),
+		.pc_cachetype = RC_NOCACHE,
+		.pc_xdrressize = ST+5,
+		.pc_name = "STATFS",
+	},
+};
+
+static DEFINE_PER_CPU_ALIGNED(unsigned long,
+			      nfsd_count2[ARRAY_SIZE(nfsd_procedures2)]);
+const struct svc_version nfsd_version2 = {
+	.vs_vers	= 2,
+	.vs_nproc	= ARRAY_SIZE(nfsd_procedures2),
+	.vs_proc	= nfsd_procedures2,
+	.vs_count	= nfsd_count2,
+	.vs_dispatch	= nfsd_dispatch,
+	.vs_xdrsize	= NFS2_SVC_XDRSIZE,
+};

linux-7.2.3/fs/nfsd/nfsxdr.c

@@ -0,0 +1,663 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * XDR support for nfsd
+ *
+ * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#include "vfs.h"
+#include "xdr.h"
+#include "auth.h"
+
+/*
+ * Mapping of S_IF* types to NFS file types
+ */
+static const u32 nfs_ftypes[] = {
+	NFNON,  NFCHR,  NFCHR, NFBAD,
+	NFDIR,  NFBAD,  NFBLK, NFBAD,
+	NFREG,  NFBAD,  NFLNK, NFBAD,
+	NFSOCK, NFBAD,  NFLNK, NFBAD,
+};
+
+
+/*
+ * Basic NFSv2 data types (RFC 1094 Section 2.3)
+ */
+
+/**
+ * svcxdr_encode_stat - Encode an NFSv2 status code
+ * @xdr: XDR stream
+ * @status: status value to encode
+ *
+ * Return values:
+ *   %false: Send buffer space was exhausted
+ *   %true: Success
+ */
+bool
+svcxdr_encode_stat(struct xdr_stream *xdr, __be32 status)
+{
+	__be32 *p;
+
+	p = xdr_reserve_space(xdr, sizeof(status));
+	if (!p)
+		return false;
+	*p = status;
+
+	return true;
+}
+
+/**
+ * svcxdr_decode_fhandle - Decode an NFSv2 file handle
+ * @xdr: XDR stream positioned at an encoded NFSv2 FH
+ * @fhp: OUT: filled-in server file handle
+ *
+ * Return values:
+ *  %false: The encoded file handle was not valid
+ *  %true: @fhp has been initialized
+ */
+bool
+svcxdr_decode_fhandle(struct xdr_stream *xdr, struct svc_fh *fhp)
+{
+	__be32 *p;
+
+	p = xdr_inline_decode(xdr, NFS_FHSIZE);
+	if (!p)
+		return false;
+	fh_init(fhp, NFS_FHSIZE);
+	memcpy(&fhp->fh_handle.fh_raw, p, NFS_FHSIZE);
+	fhp->fh_handle.fh_size = NFS_FHSIZE;
+
+	return true;
+}
+
+static bool
+svcxdr_encode_fhandle(struct xdr_stream *xdr, const struct svc_fh *fhp)
+{
+	__be32 *p;
+
+	p = xdr_reserve_space(xdr, NFS_FHSIZE);
+	if (!p)
+		return false;
+	memcpy(p, &fhp->fh_handle.fh_raw, NFS_FHSIZE);
+
+	return true;
+}
+
+static __be32 *
+encode_timeval(__be32 *p, const struct timespec64 *time)
+{
+	*p++ = cpu_to_be32((u32)time->tv_sec);
+	if (time->tv_nsec)
+		*p++ = cpu_to_be32(time->tv_nsec / NSEC_PER_USEC);
+	else
+		*p++ = xdr_zero;
+	return p;
+}
+
+static bool
+svcxdr_decode_filename(struct xdr_stream *xdr, char **name, unsigned int *len)
+{
+	u32 size, i;
+	__be32 *p;
+	char *c;
+
+	if (xdr_stream_decode_u32(xdr, &size) < 0)
+		return false;
+	if (size == 0 || size > NFS_MAXNAMLEN)
+		return false;
+	p = xdr_inline_decode(xdr, size);
+	if (!p)
+		return false;
+
+	*len = size;
+	*name = (char *)p;
+	for (i = 0, c = *name; i < size; i++, c++)
+		if (*c == '\0' || *c == '/')
+			return false;
+
+	return true;
+}
+
+static bool
+svcxdr_decode_diropargs(struct xdr_stream *xdr, struct svc_fh *fhp,
+			char **name, unsigned int *len)
+{
+	return svcxdr_decode_fhandle(xdr, fhp) &&
+		svcxdr_decode_filename(xdr, name, len);
+}
+
+static bool
+svcxdr_decode_sattr(struct svc_rqst *rqstp, struct xdr_stream *xdr,
+		    struct iattr *iap)
+{
+	u32 tmp1, tmp2;
+	__be32 *p;
+
+	p = xdr_inline_decode(xdr, XDR_UNIT * 8);
+	if (!p)
+		return false;
+
+	iap->ia_valid = 0;
+
+	/*
+	 * Some Sun clients put 0xffff in the mode field when they
+	 * mean 0xffffffff.
+	 */
+	tmp1 = be32_to_cpup(p++);
+	if (tmp1 != (u32)-1 && tmp1 != 0xffff) {
+		iap->ia_valid |= ATTR_MODE;
+		iap->ia_mode = tmp1;
+	}
+
+	tmp1 = be32_to_cpup(p++);
+	if (tmp1 != (u32)-1) {
+		iap->ia_uid = make_kuid(nfsd_user_namespace(rqstp), tmp1);
+		if (uid_valid(iap->ia_uid))
+			iap->ia_valid |= ATTR_UID;
+	}
+
+	tmp1 = be32_to_cpup(p++);
+	if (tmp1 != (u32)-1) {
+		iap->ia_gid = make_kgid(nfsd_user_namespace(rqstp), tmp1);
+		if (gid_valid(iap->ia_gid))
+			iap->ia_valid |= ATTR_GID;
+	}
+
+	tmp1 = be32_to_cpup(p++);
+	if (tmp1 != (u32)-1) {
+		iap->ia_valid |= ATTR_SIZE;
+		iap->ia_size = tmp1;
+	}
+
+	tmp1 = be32_to_cpup(p++);
+	tmp2 = be32_to_cpup(p++);
+	if (tmp1 != (u32)-1 && tmp2 != (u32)-1) {
+		iap->ia_valid |= ATTR_ATIME | ATTR_ATIME_SET;
+		iap->ia_atime.tv_sec = tmp1;
+		iap->ia_atime.tv_nsec = tmp2 * NSEC_PER_USEC;
+	}
+
+	tmp1 = be32_to_cpup(p++);
+	tmp2 = be32_to_cpup(p++);
+	if (tmp1 != (u32)-1 && tmp2 != (u32)-1) {
+		iap->ia_valid |= ATTR_MTIME | ATTR_MTIME_SET;
+		iap->ia_mtime.tv_sec = tmp1;
+		iap->ia_mtime.tv_nsec = tmp2 * NSEC_PER_USEC;
+		/*
+		 * Passing the invalid value useconds=1000000 for mtime
+		 * is a Sun convention for "set both mtime and atime to
+		 * current server time".  It's needed to make permissions
+		 * checks for the "touch" program across v2 mounts to
+		 * Solaris and Irix boxes work correctly. See description of
+		 * sattr in section 6.1 of "NFS Illustrated" by
+		 * Brent Callaghan, Addison-Wesley, ISBN 0-201-32750-5
+		 */
+		if (tmp2 == 1000000)
+			iap->ia_valid &= ~(ATTR_ATIME_SET|ATTR_MTIME_SET);
+	}
+
+	return true;
+}
+
+/**
+ * svcxdr_encode_fattr - Encode NFSv2 file attributes
+ * @rqstp: Context of a completed RPC transaction
+ * @xdr: XDR stream
+ * @fhp: File handle to encode
+ * @stat: Attributes to encode
+ *
+ * Return values:
+ *   %false: Send buffer space was exhausted
+ *   %true: Success
+ */
+bool
+svcxdr_encode_fattr(struct svc_rqst *rqstp, struct xdr_stream *xdr,
+		    const struct svc_fh *fhp, const struct kstat *stat)
+{
+	struct user_namespace *userns = nfsd_user_namespace(rqstp);
+	struct dentry *dentry = fhp->fh_dentry;
+	int type = stat->mode & S_IFMT;
+	struct timespec64 time;
+	__be32 *p;
+	u32 fsid;
+
+	p = xdr_reserve_space(xdr, XDR_UNIT * 17);
+	if (!p)
+		return false;
+
+	*p++ = cpu_to_be32(nfs_ftypes[type >> 12]);
+	*p++ = cpu_to_be32((u32)stat->mode);
+	*p++ = cpu_to_be32((u32)stat->nlink);
+	*p++ = cpu_to_be32((u32)from_kuid_munged(userns, stat->uid));
+	*p++ = cpu_to_be32((u32)from_kgid_munged(userns, stat->gid));
+
+	if (S_ISLNK(type) && stat->size > NFS_MAXPATHLEN)
+		*p++ = cpu_to_be32(NFS_MAXPATHLEN);
+	else
+		*p++ = cpu_to_be32((u32) stat->size);
+	*p++ = cpu_to_be32((u32) stat->blksize);
+	if (S_ISCHR(type) || S_ISBLK(type))
+		*p++ = cpu_to_be32(new_encode_dev(stat->rdev));
+	else
+		*p++ = cpu_to_be32(0xffffffff);
+	*p++ = cpu_to_be32((u32)stat->blocks);
+
+	switch (fsid_source(fhp)) {
+	case FSIDSOURCE_FSID:
+		fsid = (u32)fhp->fh_export->ex_fsid;
+		break;
+	case FSIDSOURCE_UUID:
+		fsid = ((u32 *)fhp->fh_export->ex_uuid)[0];
+		fsid ^= ((u32 *)fhp->fh_export->ex_uuid)[1];
+		fsid ^= ((u32 *)fhp->fh_export->ex_uuid)[2];
+		fsid ^= ((u32 *)fhp->fh_export->ex_uuid)[3];
+		break;
+	default:
+		fsid = new_encode_dev(stat->dev);
+		break;
+	}
+	*p++ = cpu_to_be32(fsid);
+
+	*p++ = cpu_to_be32((u32)stat->ino);
+	p = encode_timeval(p, &stat->atime);
+	time = stat->mtime;
+	lease_get_mtime(d_inode(dentry), &time);
+	p = encode_timeval(p, &time);
+	encode_timeval(p, &stat->ctime);
+
+	return true;
+}
+
+/*
+ * XDR decode functions
+ */
+
+bool
+nfssvc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd_fhandle *args = rqstp->rq_argp;
+
+	return svcxdr_decode_fhandle(xdr, &args->fh);
+}
+
+bool
+nfssvc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd_sattrargs *args = rqstp->rq_argp;
+
+	return svcxdr_decode_fhandle(xdr, &args->fh) &&
+		svcxdr_decode_sattr(rqstp, xdr, &args->attrs);
+}
+
+bool
+nfssvc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd_diropargs *args = rqstp->rq_argp;
+
+	return svcxdr_decode_diropargs(xdr, &args->fh, &args->name, &args->len);
+}
+
+bool
+nfssvc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd_readargs *args = rqstp->rq_argp;
+	u32 totalcount;
+
+	if (!svcxdr_decode_fhandle(xdr, &args->fh))
+		return false;
+	if (xdr_stream_decode_u32(xdr, &args->offset) < 0)
+		return false;
+	if (xdr_stream_decode_u32(xdr, &args->count) < 0)
+		return false;
+	/* totalcount is ignored */
+	if (xdr_stream_decode_u32(xdr, &totalcount) < 0)
+		return false;
+
+	return true;
+}
+
+bool
+nfssvc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd_writeargs *args = rqstp->rq_argp;
+	u32 beginoffset, totalcount;
+
+	if (!svcxdr_decode_fhandle(xdr, &args->fh))
+		return false;
+	/* beginoffset is ignored */
+	if (xdr_stream_decode_u32(xdr, &beginoffset) < 0)
+		return false;
+	if (xdr_stream_decode_u32(xdr, &args->offset) < 0)
+		return false;
+	/* totalcount is ignored */
+	if (xdr_stream_decode_u32(xdr, &totalcount) < 0)
+		return false;
+
+	/* opaque data */
+	if (xdr_stream_decode_u32(xdr, &args->len) < 0)
+		return false;
+	if (args->len > NFS_MAXDATA)
+		return false;
+
+	return xdr_stream_subsegment(xdr, &args->payload, args->len);
+}
+
+bool
+nfssvc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd_createargs *args = rqstp->rq_argp;
+
+	return svcxdr_decode_diropargs(xdr, &args->fh,
+				       &args->name, &args->len) &&
+		svcxdr_decode_sattr(rqstp, xdr, &args->attrs);
+}
+
+bool
+nfssvc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd_renameargs *args = rqstp->rq_argp;
+
+	return svcxdr_decode_diropargs(xdr, &args->ffh,
+				       &args->fname, &args->flen) &&
+		svcxdr_decode_diropargs(xdr, &args->tfh,
+					&args->tname, &args->tlen);
+}
+
+bool
+nfssvc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd_linkargs *args = rqstp->rq_argp;
+
+	return svcxdr_decode_fhandle(xdr, &args->ffh) &&
+		svcxdr_decode_diropargs(xdr, &args->tfh,
+					&args->tname, &args->tlen);
+}
+
+bool
+nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd_symlinkargs *args = rqstp->rq_argp;
+	struct kvec *head = rqstp->rq_arg.head;
+
+	if (!svcxdr_decode_diropargs(xdr, &args->ffh, &args->fname, &args->flen))
+		return false;
+	if (xdr_stream_decode_u32(xdr, &args->tlen) < 0)
+		return false;
+	if (args->tlen == 0)
+		return false;
+
+	args->first.iov_len = head->iov_len - xdr_stream_pos(xdr);
+	args->first.iov_base = xdr_inline_decode(xdr, args->tlen);
+	if (!args->first.iov_base)
+		return false;
+	return svcxdr_decode_sattr(rqstp, xdr, &args->attrs);
+}
+
+bool
+nfssvc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd_readdirargs *args = rqstp->rq_argp;
+
+	if (!svcxdr_decode_fhandle(xdr, &args->fh))
+		return false;
+	if (xdr_stream_decode_u32(xdr, &args->cookie) < 0)
+		return false;
+	if (xdr_stream_decode_u32(xdr, &args->count) < 0)
+		return false;
+
+	return true;
+}
+
+/*
+ * XDR encode functions
+ */
+
+bool
+nfssvc_encode_statres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd_stat *resp = rqstp->rq_resp;
+
+	return svcxdr_encode_stat(xdr, resp->status);
+}
+
+bool
+nfssvc_encode_attrstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
+
+	if (!svcxdr_encode_stat(xdr, resp->status))
+		return false;
+	switch (resp->status) {
+	case nfs_ok:
+		if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat))
+			return false;
+		break;
+	}
+
+	return true;
+}
+
+bool
+nfssvc_encode_diropres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd_diropres *resp = rqstp->rq_resp;
+
+	if (!svcxdr_encode_stat(xdr, resp->status))
+		return false;
+	switch (resp->status) {
+	case nfs_ok:
+		if (!svcxdr_encode_fhandle(xdr, &resp->fh))
+			return false;
+		if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat))
+			return false;
+		break;
+	}
+
+	return true;
+}
+
+bool
+nfssvc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd_readlinkres *resp = rqstp->rq_resp;
+	struct kvec *head = rqstp->rq_res.head;
+
+	if (!svcxdr_encode_stat(xdr, resp->status))
+		return false;
+	switch (resp->status) {
+	case nfs_ok:
+		if (xdr_stream_encode_u32(xdr, resp->len) < 0)
+			return false;
+		svcxdr_encode_opaque_pages(rqstp, xdr, &resp->page, 0,
+					   resp->len);
+		if (svc_encode_result_payload(rqstp, head->iov_len, resp->len) < 0)
+			return false;
+		break;
+	}
+
+	return true;
+}
+
+bool
+nfssvc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd_readres *resp = rqstp->rq_resp;
+	struct kvec *head = rqstp->rq_res.head;
+
+	if (!svcxdr_encode_stat(xdr, resp->status))
+		return false;
+	switch (resp->status) {
+	case nfs_ok:
+		if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat))
+			return false;
+		if (xdr_stream_encode_u32(xdr, resp->count) < 0)
+			return false;
+		svcxdr_encode_opaque_pages(rqstp, xdr, resp->pages,
+					   rqstp->rq_res.page_base,
+					   resp->count);
+		if (svc_encode_result_payload(rqstp, head->iov_len, resp->count) < 0)
+			return false;
+		break;
+	}
+
+	return true;
+}
+
+bool
+nfssvc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd_readdirres *resp = rqstp->rq_resp;
+	struct xdr_buf *dirlist = &resp->dirlist;
+
+	if (!svcxdr_encode_stat(xdr, resp->status))
+		return false;
+	switch (resp->status) {
+	case nfs_ok:
+		svcxdr_encode_opaque_pages(rqstp, xdr, dirlist->pages, 0,
+					   dirlist->len);
+		/* no more entries */
+		if (xdr_stream_encode_item_absent(xdr) < 0)
+			return false;
+		if (xdr_stream_encode_bool(xdr, resp->common.err == nfserr_eof) < 0)
+			return false;
+		break;
+	}
+
+	return true;
+}
+
+bool
+nfssvc_encode_statfsres(struct svc_rqst *rqstp, struct xdr_stream *xdr)
+{
+	struct nfsd_statfsres *resp = rqstp->rq_resp;
+	struct kstatfs	*stat = &resp->stats;
+	__be32 *p;
+
+	if (!svcxdr_encode_stat(xdr, resp->status))
+		return false;
+	switch (resp->status) {
+	case nfs_ok:
+		p = xdr_reserve_space(xdr, XDR_UNIT * 5);
+		if (!p)
+			return false;
+		*p++ = cpu_to_be32(NFS_MAXDATA);
+		*p++ = cpu_to_be32(stat->f_bsize);
+		*p++ = cpu_to_be32(stat->f_blocks);
+		*p++ = cpu_to_be32(stat->f_bfree);
+		*p = cpu_to_be32(stat->f_bavail);
+		break;
+	}
+
+	return true;
+}
+
+/**
+ * nfssvc_encode_nfscookie - Encode a directory offset cookie
+ * @resp: readdir result context
+ * @offset: offset cookie to encode
+ *
+ * The buffer space for the offset cookie has already been reserved
+ * by svcxdr_encode_entry_common().
+ */
+void nfssvc_encode_nfscookie(struct nfsd_readdirres *resp, u32 offset)
+{
+	__be32 cookie = cpu_to_be32(offset);
+
+	if (!resp->cookie_offset)
+		return;
+
+	write_bytes_to_xdr_buf(&resp->dirlist, resp->cookie_offset, &cookie,
+			       sizeof(cookie));
+	resp->cookie_offset = 0;
+}
+
+static bool
+svcxdr_encode_entry_common(struct nfsd_readdirres *resp, const char *name,
+			   int namlen, loff_t offset, u64 ino)
+{
+	struct xdr_buf *dirlist = &resp->dirlist;
+	struct xdr_stream *xdr = &resp->xdr;
+
+	if (xdr_stream_encode_item_present(xdr) < 0)
+		return false;
+	/* fileid */
+	if (xdr_stream_encode_u32(xdr, (u32)ino) < 0)
+		return false;
+	/* name */
+	if (xdr_stream_encode_opaque(xdr, name, min(namlen, NFS2_MAXNAMLEN)) < 0)
+		return false;
+	/* cookie */
+	resp->cookie_offset = dirlist->len;
+	if (xdr_stream_encode_u32(xdr, ~0U) < 0)
+		return false;
+
+	return true;
+}
+
+/**
+ * nfssvc_encode_entry - encode one NFSv2 READDIR entry
+ * @data: directory context
+ * @name: name of the object to be encoded
+ * @namlen: length of that name, in bytes
+ * @offset: the offset of the previous entry
+ * @ino: the fileid of this entry
+ * @d_type: unused
+ *
+ * Return values:
+ *   %0: Entry was successfully encoded.
+ *   %-EINVAL: An encoding problem occurred, secondary status code in resp->common.err
+ *
+ * On exit, the following fields are updated:
+ *   - resp->xdr
+ *   - resp->common.err
+ *   - resp->cookie_offset
+ */
+int nfssvc_encode_entry(void *data, const char *name, int namlen,
+			loff_t offset, u64 ino, unsigned int d_type)
+{
+	struct readdir_cd *ccd = data;
+	struct nfsd_readdirres *resp = container_of(ccd,
+						    struct nfsd_readdirres,
+						    common);
+	unsigned int starting_length = resp->dirlist.len;
+
+	/* The offset cookie for the previous entry */
+	nfssvc_encode_nfscookie(resp, offset);
+
+	if (!svcxdr_encode_entry_common(resp, name, namlen, offset, ino))
+		goto out_toosmall;
+
+	xdr_commit_encode(&resp->xdr);
+	resp->common.err = nfs_ok;
+	return 0;
+
+out_toosmall:
+	resp->cookie_offset = 0;
+	resp->common.err = nfserr_toosmall;
+	resp->dirlist.len = starting_length;
+	return -EINVAL;
+}
+
+/*
+ * XDR release functions
+ */
+void nfssvc_release_attrstat(struct svc_rqst *rqstp)
+{
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
+
+	fh_put(&resp->fh);
+}
+
+void nfssvc_release_diropres(struct svc_rqst *rqstp)
+{
+	struct nfsd_diropres *resp = rqstp->rq_resp;
+
+	fh_put(&resp->fh);
+}
+
+void nfssvc_release_readres(struct svc_rqst *rqstp)
+{
+	struct nfsd_readres *resp = rqstp->rq_resp;
+
+	fh_put(&resp->fh);
+}

linux-7.2.3/fs/nfsd/pnfs.h

@@ -0,0 +1,110 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _FS_NFSD_PNFS_H
+#define _FS_NFSD_PNFS_H 1
+
+#ifdef CONFIG_NFSD_V4
+#include <linux/exportfs.h>
+#include <linux/nfsd/export.h>
+
+#include "state.h"
+#include "xdr4.h"
+
+struct xdr_stream;
+
+/* Cap exponential backoff between fence retries at 3 minutes */
+#define	MAX_FENCE_DELAY		((unsigned int)(3 * 60 * HZ))
+
+struct nfsd4_deviceid_map {
+	struct list_head	hash;
+	u64			idx;
+	int			fsid_type;
+	u32			fsid[];
+};
+
+struct nfsd4_layout_ops {
+	u32		notify_types;
+	bool		disable_recalls;
+
+	__be32 (*proc_getdeviceinfo)(struct super_block *sb,
+			struct svc_rqst *rqstp,
+			struct nfs4_client *clp,
+			struct nfsd4_getdeviceinfo *gdevp);
+	__be32 (*encode_getdeviceinfo)(struct xdr_stream *xdr,
+			const struct nfsd4_getdeviceinfo *gdevp);
+
+	__be32 (*proc_layoutget)(struct svc_rqst *rqstp, struct inode *inode,
+			const struct svc_fh *fhp, struct nfsd4_layoutget *lgp);
+	__be32 (*encode_layoutget)(struct xdr_stream *xdr,
+			const struct nfsd4_layoutget *lgp);
+
+	__be32 (*proc_layoutcommit)(struct inode *inode,
+			struct svc_rqst *rqstp,
+			struct nfsd4_layoutcommit *lcp);
+
+	bool (*fence_client)(struct nfs4_layout_stateid *ls,
+			     struct nfsd_file *file);
+};
+
+extern const struct nfsd4_layout_ops *nfsd4_layout_ops[];
+#ifdef CONFIG_NFSD_BLOCKLAYOUT
+extern const struct nfsd4_layout_ops bl_layout_ops;
+#endif
+#ifdef CONFIG_NFSD_SCSILAYOUT
+extern const struct nfsd4_layout_ops scsi_layout_ops;
+#endif
+#ifdef CONFIG_NFSD_FLEXFILELAYOUT
+extern const struct nfsd4_layout_ops ff_layout_ops;
+#endif
+
+__be32 nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate, stateid_t *stateid,
+		bool create, u32 layout_type, struct nfs4_layout_stateid **lsp);
+__be32 nfsd4_insert_layout(struct nfsd4_layoutget *lgp,
+		struct nfs4_layout_stateid *ls);
+__be32 nfsd4_return_file_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp);
+__be32 nfsd4_return_client_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp);
+int nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp,
+		u32 device_generation);
+struct nfsd4_deviceid_map *nfsd4_find_devid_map(int idx);
+#endif /* CONFIG_NFSD_V4 */
+
+#ifdef CONFIG_NFSD_PNFS
+void nfsd4_setup_layout_type(struct svc_export *exp);
+void nfsd4_return_all_client_layouts(struct nfs4_client *);
+void nfsd4_return_all_file_layouts(struct nfs4_client *clp,
+		struct nfs4_file *fp);
+void nfsd4_close_layout(struct nfs4_layout_stateid *ls);
+int nfsd4_init_pnfs(void);
+void nfsd4_exit_pnfs(void);
+#else
+struct nfs4_client;
+struct nfs4_file;
+struct nfs4_layout_stateid;
+
+static inline void nfsd4_setup_layout_type(struct svc_export *exp)
+{
+}
+
+static inline void nfsd4_return_all_client_layouts(struct nfs4_client *clp)
+{
+}
+static inline void nfsd4_return_all_file_layouts(struct nfs4_client *clp,
+		struct nfs4_file *fp)
+{
+}
+static inline void nfsd4_close_layout(struct nfs4_layout_stateid *ls)
+{
+}
+static inline void nfsd4_exit_pnfs(void)
+{
+}
+static inline int nfsd4_init_pnfs(void)
+{
+	return 0;
+}
+#endif /* CONFIG_NFSD_PNFS */
+#endif /* _FS_NFSD_PNFS_H */

linux-7.2.3/fs/nfsd/state.h

@@ -0,0 +1,914 @@
+/*
+ *  Copyright (c) 2001 The Regents of the University of Michigan.
+ *  All rights reserved.
+ *
+ *  Kendrick Smith <kmsmith@umich.edu>
+ *  Andy Adamson <andros@umich.edu>
+ *  
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *  
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the University nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+#ifndef _NFSD4_STATE_H
+#define _NFSD4_STATE_H
+
+#include <crypto/md5.h>
+#include <linux/idr.h>
+#include <linux/refcount.h>
+#include <linux/sunrpc/svc_xprt.h>
+#include "nfsfh.h"
+#include "nfsd.h"
+
+typedef struct {
+	u32             cl_boot;
+	u32             cl_id;
+} clientid_t;
+
+typedef struct {
+	clientid_t	so_clid;
+	u32		so_id;
+} stateid_opaque_t;
+
+typedef struct {
+	u32                     si_generation;
+	stateid_opaque_t        si_opaque;
+} stateid_t;
+
+typedef struct {
+	stateid_t		cs_stid;
+#define NFS4_COPY_STID 1
+#define NFS4_COPYNOTIFY_STID 2
+	unsigned char		cs_type;
+	refcount_t		cs_count;
+} copy_stateid_t;
+
+struct nfsd4_referring_call {
+	struct list_head	__list;
+
+	u32			rc_sequenceid;
+	u32			rc_slotid;
+};
+
+struct nfsd4_referring_call_list {
+	struct list_head	__list;
+
+	struct nfs4_sessionid	rcl_sessionid;
+	int			__nr_referring_calls;
+	struct list_head	rcl_referring_calls;
+};
+
+struct nfsd4_callback {
+	struct nfs4_client *cb_clp;
+	struct rpc_message cb_msg;
+#define NFSD4_CALLBACK_RUNNING		(0)
+#define NFSD4_CALLBACK_WAKE		(1)
+#define NFSD4_CALLBACK_REQUEUE		(2)
+	unsigned long cb_flags;
+	const struct nfsd4_callback_ops *cb_ops;
+	struct work_struct cb_work;
+	int cb_seq_status;
+	int cb_status;
+	int cb_held_slot;
+
+	int cb_nr_referring_call_list;
+	struct list_head cb_referring_call_list;
+};
+
+struct nfsd4_callback_ops {
+	void (*prepare)(struct nfsd4_callback *);
+	int (*done)(struct nfsd4_callback *, struct rpc_task *);
+	void (*release)(struct nfsd4_callback *);
+	uint32_t opcode;
+};
+
+/*
+ * A core object that represents a "common" stateid. These are generally
+ * embedded within the different (more specific) stateid objects and contain
+ * fields that are of general use to any stateid.
+ */
+struct nfs4_stid {
+	refcount_t		sc_count;
+
+	/* A new stateid is added to the cl_stateids idr early before it
+	 * is fully initialised.  Its sc_type is then zero.  After
+	 * initialisation the sc_type it set under cl_lock, and then
+	 * never changes.
+	 */
+#define SC_TYPE_OPEN		BIT(0)
+#define SC_TYPE_LOCK		BIT(1)
+#define SC_TYPE_DELEG		BIT(2)
+#define SC_TYPE_LAYOUT		BIT(3)
+	unsigned short		sc_type;
+
+/* nn->deleg_lock protects sc_status for delegation stateids.
+ * ->cl_lock protects sc_status for open and lock stateids.
+ * ->st_mutex also protect sc_status for open stateids.
+ * ->ls_lock protects sc_status for layout stateids.
+ */
+/*
+ * For an open stateid kept around *only* to process close replays.
+ * For deleg stateid, kept in idr until last reference is dropped.
+ */
+#define SC_STATUS_CLOSED	BIT(0)
+/* For a deleg stateid kept around only to process free_stateid's: */
+#define SC_STATUS_REVOKED	BIT(1)
+#define SC_STATUS_ADMIN_REVOKED	BIT(2)
+#define SC_STATUS_FREEABLE	BIT(3)
+#define SC_STATUS_FREED		BIT(4)
+	unsigned short		sc_status;
+
+	struct list_head	sc_cp_list;
+	stateid_t		sc_stateid;
+	spinlock_t		sc_lock;
+	struct nfs4_client	*sc_client;
+	struct nfs4_file	*sc_file;
+	struct svc_export	*sc_export;
+	void			(*sc_free)(struct nfs4_stid *);
+};
+
+/* Keep a list of stateids issued by the COPY_NOTIFY, associate it with the
+ * parent OPEN/LOCK/DELEG stateid.
+ */
+struct nfs4_cpntf_state {
+	copy_stateid_t		cp_stateid;
+	struct list_head	cp_list;	/* per parent nfs4_stid */
+	stateid_t		cp_p_stateid;	/* copy of parent's stateid */
+	clientid_t		cp_p_clid;	/* copy of parent's clid */
+	time64_t		cpntf_time;	/* last time stateid used */
+};
+
+/*
+ * RFC 7862 Section 4.8 states:
+ *
+ * | A copy offload stateid will be valid until either (A) the client
+ * | or server restarts or (B) the client returns the resource by
+ * | issuing an OFFLOAD_CANCEL operation or the client replies to a
+ * | CB_OFFLOAD operation.
+ *
+ * Because a client might not reply to a CB_OFFLOAD, or a reply
+ * might get lost due to connection loss, NFSD purges async copy
+ * state after a short period to prevent it from accumulating
+ * over time.
+ */
+#define NFSD_COPY_INITIAL_TTL 10
+
+struct nfs4_cb_fattr {
+	struct nfsd4_callback ncf_getattr;
+	u32 ncf_cb_status;
+
+	/* from CB_GETATTR reply */
+	u64 ncf_cb_change;
+	u64 ncf_cb_fsize;
+	struct timespec64 ncf_cb_mtime;
+	struct timespec64 ncf_cb_atime;
+
+	bool ncf_file_modified;
+	u64 ncf_initial_cinfo;
+	u64 ncf_cur_fsize;
+};
+
+/*
+ * Represents a delegation stateid. The nfs4_client holds references to these
+ * and they are put when it is being destroyed or when the delegation is
+ * returned by the client:
+ *
+ * o 1 reference as long as a delegation is still in force (taken when it's
+ *   alloc'd, put when it's returned or revoked)
+ *
+ * o 1 reference as long as a recall rpc is in progress (taken when the lease
+ *   is broken, put when the rpc exits)
+ *
+ * o 1 more ephemeral reference for each nfsd thread currently doing something
+ *   with that delegation without holding the cl_lock
+ *
+ * If the server attempts to recall a delegation and the client doesn't do so
+ * before a timeout, the server may also revoke the delegation. In that case,
+ * the object will either be destroyed (v4.0) or moved to a per-client list of
+ * revoked delegations (v4.1+).
+ *
+ * This object is a superset of the nfs4_stid.
+ */
+struct nfs4_delegation {
+	struct nfs4_stid	dl_stid; /* must be first field */
+	struct list_head	dl_perfile;
+	struct list_head	dl_perclnt;
+	struct list_head	dl_recall_lru;  /* delegation recalled */
+	struct nfs4_clnt_odstate *dl_clnt_odstate;
+	time64_t		dl_time;
+	u32			dl_type;
+	/* For recall: */
+	int			dl_retries;
+	struct nfsd4_callback	dl_recall;
+	bool			dl_recalled;
+	bool			dl_written;
+	bool			dl_setattr;
+
+	/* for CB_GETATTR */
+	struct nfs4_cb_fattr    dl_cb_fattr;
+
+	/* For delegated timestamps */
+	struct timespec64	dl_atime;
+	struct timespec64	dl_mtime;
+	struct timespec64	dl_ctime;
+};
+
+static inline bool deleg_is_read(u32 dl_type)
+{
+	return (dl_type == OPEN_DELEGATE_READ || dl_type == OPEN_DELEGATE_READ_ATTRS_DELEG);
+}
+
+static inline bool deleg_is_write(u32 dl_type)
+{
+	return (dl_type == OPEN_DELEGATE_WRITE || dl_type == OPEN_DELEGATE_WRITE_ATTRS_DELEG);
+}
+
+static inline bool deleg_attrs_deleg(u32 dl_type)
+{
+	return dl_type == OPEN_DELEGATE_READ_ATTRS_DELEG ||
+	       dl_type == OPEN_DELEGATE_WRITE_ATTRS_DELEG;
+}
+
+bool nfsd4_vet_deleg_time(struct timespec64 *cb, const struct timespec64 *orig,
+			  const struct timespec64 *now);
+
+#define cb_to_delegation(cb) \
+	container_of(cb, struct nfs4_delegation, dl_recall)
+
+/* client delegation callback info */
+struct nfs4_cb_conn {
+	/* SETCLIENTID info */
+	struct sockaddr_storage	cb_addr;
+	struct sockaddr_storage	cb_saddr;
+	size_t			cb_addrlen;
+	u32                     cb_prog; /* used only in 4.0 case;
+					    per-session otherwise */
+	u32                     cb_ident;	/* minorversion 0 only */
+	struct svc_xprt		*cb_xprt;	/* minorversion 1 only */
+};
+
+static inline struct nfs4_delegation *delegstateid(struct nfs4_stid *s)
+{
+	return container_of(s, struct nfs4_delegation, dl_stid);
+}
+
+/* Maximum number of slots per session.  This is for sanity-check only.
+ * It could be increased if we had a mechanism to shutdown misbehaving clients.
+ * A large number can be needed to get good throughput on high-latency servers.
+ */
+#define NFSD_MAX_SLOTS_PER_SESSION	2048
+/* Maximum  session per slot cache size */
+#define NFSD_SLOT_CACHE_SIZE		2048
+/* Maximum number of NFSD_SLOT_CACHE_SIZE slots per session */
+#define NFSD_CACHE_SIZE_SLOTS_PER_SESSION	32
+#define NFSD_MAX_MEM_PER_SESSION  \
+		(NFSD_CACHE_SIZE_SLOTS_PER_SESSION * NFSD_SLOT_CACHE_SIZE)
+
+struct nfsd4_slot {
+	u32	sl_seqid;
+	__be32	sl_status;
+	struct svc_cred sl_cred;
+	u32	sl_index;
+	u32	sl_datalen;
+	u16	sl_opcnt;
+	u16	sl_generation;
+#define NFSD4_SLOT_INUSE	(1 << 0)
+#define NFSD4_SLOT_CACHETHIS	(1 << 1)
+#define NFSD4_SLOT_INITIALIZED	(1 << 2)
+#define NFSD4_SLOT_CACHED	(1 << 3)
+#define NFSD4_SLOT_REUSED	(1 << 4)
+	u8	sl_flags;
+	char	sl_data[];
+};
+
+struct nfsd4_channel_attrs {
+	u32		headerpadsz;
+	u32		maxreq_sz;
+	u32		maxresp_sz;
+	u32		maxresp_cached;
+	u32		maxops;
+	u32		maxreqs;
+	u32		nr_rdma_attrs;
+	u32		rdma_attrs;
+};
+
+struct nfsd4_cb_sec {
+	u32	flavor; /* (u32)(-1) used to mean "no valid flavor" */
+	kuid_t	uid;
+	kgid_t	gid;
+};
+
+struct nfsd4_create_session {
+	clientid_t			clientid;
+	struct nfs4_sessionid		sessionid;
+	u32				seqid;
+	u32				flags;
+	struct nfsd4_channel_attrs	fore_channel;
+	struct nfsd4_channel_attrs	back_channel;
+	u32				callback_prog;
+	struct nfsd4_cb_sec		cb_sec;
+};
+
+struct nfsd4_backchannel_ctl {
+	u32	bc_cb_program;
+	struct nfsd4_cb_sec		bc_cb_sec;
+};
+
+struct nfsd4_bind_conn_to_session {
+	struct nfs4_sessionid		sessionid;
+	u32				dir;
+};
+
+/* The single slot clientid cache structure */
+struct nfsd4_clid_slot {
+	u32				sl_seqid;
+	__be32				sl_status;
+	struct nfsd4_create_session	sl_cr_ses;
+};
+
+struct nfsd4_conn {
+	struct list_head cn_persession;
+	struct svc_xprt *cn_xprt;
+	struct svc_xpt_user cn_xpt_user;
+	struct nfsd4_session *cn_session;
+/* CDFC4_FORE, CDFC4_BACK: */
+	unsigned char cn_flags;
+};
+
+/* Maximum number of slots that nfsd will use in the backchannel */
+#define NFSD_BC_SLOT_TABLE_SIZE		(sizeof(u32) * 8)
+
+/*
+ * Representation of a v4.1+ session. These are refcounted in a similar fashion
+ * to the nfs4_client. References are only taken when the server is actively
+ * working on the object (primarily during the processing of compounds).
+ */
+struct nfsd4_session {
+	atomic_t		se_ref;
+	spinlock_t		se_lock;
+	u32			se_cb_slot_avail; /* bitmap of available slots */
+	u32			se_cb_highest_slot;	/* highest slot client wants */
+	u32			se_cb_prog;
+	struct list_head	se_hash;	/* hash by sessionid */
+	struct list_head	se_perclnt;
+	struct list_head	se_all_sessions;/* global list of sessions */
+	struct nfs4_client	*se_client;
+	struct nfs4_sessionid	se_sessionid;
+	struct nfsd4_channel_attrs se_fchannel;
+	struct nfsd4_cb_sec	se_cb_sec;
+	struct list_head	se_conns;
+	u32			se_cb_seq_nr[NFSD_BC_SLOT_TABLE_SIZE];
+	struct xarray		se_slots;	/* forward channel slots */
+	u16			se_slot_gen;
+	bool			se_dead;
+	u32			se_target_maxslots;
+};
+
+/* formatted contents of nfs4_sessionid */
+struct nfsd4_sessionid {
+	clientid_t	clientid;
+	u32		sequence;
+	u32		reserved;
+};
+
+/* Length of MD5 digest as hex, plus terminating '\0' */
+#define HEXDIR_LEN	(2 * MD5_DIGEST_SIZE + 1)
+
+/*
+ *       State                Meaning                  Where set
+ * --------------------------------------------------------------------------
+ * | NFSD4_ACTIVE      | Confirmed, active    | Default                     |
+ * |------------------- ----------------------------------------------------|
+ * | NFSD4_COURTESY    | Courtesy state.      | nfs4_get_client_reaplist    |
+ * |                   | Lease/lock/share     |                             |
+ * |                   | reservation conflict |                             |
+ * |                   | can cause Courtesy   |                             |
+ * |                   | client to be expired |                             |
+ * |------------------------------------------------------------------------|
+ * | NFSD4_EXPIRABLE   | Courtesy client to be| nfs4_laundromat             |
+ * |                   | expired by Laundromat| try_to_expire_client        |
+ * |                   | due to conflict      |                             |
+ * |------------------------------------------------------------------------|
+ */
+enum {
+	NFSD4_ACTIVE = 0,
+	NFSD4_COURTESY,
+	NFSD4_EXPIRABLE,
+};
+
+/*
+ * struct nfs4_client - one per client.  Clientids live here.
+ *
+ * The initial object created by an NFS client using SETCLIENTID (for NFSv4.0)
+ * or EXCHANGE_ID (for NFSv4.1+). These objects are refcounted and timestamped.
+ * Each nfsd_net_ns object contains a set of these and they are tracked via
+ * short and long form clientid. They are hashed and searched for under the
+ * per-nfsd_net client_lock spinlock.
+ *
+ * References to it are only held during the processing of compounds, and in
+ * certain other operations. In their "resting state" they have a refcount of
+ * 0. If they are not renewed within a lease period, they become eligible for
+ * destruction by the laundromat.
+ *
+ * These objects can also be destroyed if the client sends certain forms of
+ * SETCLIENTID or EXCHANGE_ID operations.
+ *
+ * Care is taken *not* to do this however when the objects have an elevated
+ * refcount.
+ *
+ * o Each nfs4_client is hashed by clientid
+ *
+ * o Each nfs4_clients is also hashed by name (the opaque quantity initially
+ *   sent by the client to identify itself).
+ *
+ * o cl_perclient list is used to ensure no dangling stateowner references
+ *   when we expire the nfs4_client
+ */
+struct nfs4_client {
+	struct list_head	cl_idhash; 	/* hash by cl_clientid.id */
+	struct rb_node		cl_namenode;	/* link into by-name trees */
+	struct list_head	*cl_ownerstr_hashtbl;
+	struct list_head	cl_openowners;
+	struct idr		cl_stateids;	/* stateid lookup */
+	struct list_head	cl_delegations;
+	struct list_head	cl_revoked;	/* unacknowledged, revoked 4.1 state */
+	struct list_head        cl_lru;         /* tail queue */
+#ifdef CONFIG_NFSD_PNFS
+	struct list_head	cl_lo_states;	/* outstanding layout states */
+	bool			cl_fence_retry_warn;
+#endif
+	struct xdr_netobj	cl_name; 	/* id generated by client */
+	nfs4_verifier		cl_verifier; 	/* generated by client */
+	time64_t		cl_time;	/* time of last lease renewal */
+	struct sockaddr_storage	cl_addr; 	/* client ipaddress */
+	bool			cl_mach_cred;	/* SP4_MACH_CRED in force */
+	struct svc_cred		cl_cred; 	/* setclientid principal */
+	clientid_t		cl_clientid;	/* generated by server */
+	nfs4_verifier		cl_confirm;	/* generated by server */
+	u32			cl_minorversion;
+	atomic_t		cl_admin_revoked; /* count of admin-revoked states */
+	/* NFSv4.1 client implementation id: */
+	struct xdr_netobj	cl_nii_domain;
+	struct xdr_netobj	cl_nii_name;
+	struct timespec64	cl_nii_time;
+
+	/* for v4.0 and v4.1 callbacks: */
+	struct nfs4_cb_conn	cl_cb_conn;
+#define NFSD4_CLIENT_CB_UPDATE		(0)
+#define NFSD4_CLIENT_CB_KILL		(1)
+#define NFSD4_CLIENT_STABLE		(2)	/* client on stable storage */
+#define NFSD4_CLIENT_RECLAIM_COMPLETE	(3)	/* reclaim_complete done */
+#define NFSD4_CLIENT_CONFIRMED		(4)	/* client is confirmed */
+#define NFSD4_CLIENT_UPCALL_LOCK	(5)	/* upcall serialization */
+#define NFSD4_CLIENT_CB_FLAG_MASK	(1 << NFSD4_CLIENT_CB_UPDATE | \
+					 1 << NFSD4_CLIENT_CB_KILL)
+	unsigned long		cl_flags;
+
+	struct workqueue_struct *cl_callback_wq;
+	const struct cred	*cl_cb_cred;
+	struct rpc_clnt		*cl_cb_client;
+	u32			cl_cb_ident;
+#define NFSD4_CB_UP		0
+#define NFSD4_CB_UNKNOWN	1
+#define NFSD4_CB_DOWN		2
+#define NFSD4_CB_FAULT		3
+	int			cl_cb_state;
+	struct nfsd4_callback	cl_cb_null;
+	struct nfsd4_session	*cl_cb_session;
+
+	/* for all client information that callback code might need: */
+	spinlock_t		cl_lock;
+
+	/* for nfs41 */
+	struct list_head	cl_sessions;
+	struct nfsd4_clid_slot	cl_cs_slot;	/* create_session slot */
+	u32			cl_exchange_flags;
+	/* number of rpc's in progress over an associated session: */
+	atomic_t		cl_rpc_users;
+	struct nfsdfs_client	cl_nfsdfs;
+	struct nfs4_op_map      cl_spo_must_allow;
+
+	/* debugging info directory under nfsd/clients/ : */
+	struct dentry		*cl_nfsd_dentry;
+	/* 'info' file within that directory. Ref is not counted,
+	 * but will remain valid iff cl_nfsd_dentry != NULL
+	 */
+	struct dentry		*cl_nfsd_info_dentry;
+
+	struct rpc_wait_queue	cl_cb_waitq;	/* backchannel callers may */
+						/* wait here for slots */
+	struct net		*net;
+	struct list_head	async_copies;	/* list of async copies */
+	spinlock_t		async_lock;	/* lock for async copies */
+	atomic_t		cl_cb_inflight;	/* Outstanding callbacks */
+
+	unsigned int		cl_state;
+	atomic_t		cl_delegs_in_recall;
+
+	struct nfsd4_cb_recall_any	*cl_ra;
+	time64_t		cl_ra_time;
+#ifdef CONFIG_NFSD_SCSILAYOUT
+	struct xarray		cl_dev_fences;
+	struct mutex		cl_fence_mutex;
+#endif
+};
+
+/* struct nfs4_client_reset
+ * one per old client. Populates reset_str_hashtbl. Filled from conf_id_hashtbl
+ * upon lease reset, or from upcall to state_daemon (to read in state
+ * from non-volitile storage) upon reboot.
+ */
+struct nfs4_client_reclaim {
+	struct list_head	cr_strhash;	/* hash by cr_name */
+	struct nfs4_client	*cr_clp;	/* pointer to associated clp */
+	struct xdr_netobj	cr_name;	/* recovery dir name */
+	struct xdr_netobj	cr_princhash;
+};
+
+/*
+ * REPLAY_ISIZE is sized for an OPEN response with delegation:
+ *   4(status) + 8(stateid) + 20(changeinfo) + 4(rflags) +
+ *   8(verifier) + 4(deleg. type) + 8(deleg. stateid) +
+ *   4(deleg. recall flag) + 20(deleg. space limit) +
+ *   ~32(deleg. ace) = 112 bytes
+ *
+ * Some responses can exceed this. A LOCK denial includes the conflicting
+ * lock owner, which can be up to 1024 bytes (NFS4_OPAQUE_LIMIT). When a
+ * response exceeds REPLAY_ISIZE, a buffer is dynamically allocated. If
+ * that allocation fails, only rp_status is saved. Enlarging this constant
+ * increases the size of every nfs4_stateowner.
+ */
+
+#define NFSD4_REPLAY_ISIZE       112 
+
+/*
+ * Replay buffer, where the result of the last seqid-mutating operation 
+ * is cached. 
+ */
+struct nfs4_replay {
+	__be32			rp_status;
+	unsigned int		rp_buflen;
+	char			*rp_buf; /* rp_ibuf or kmalloc'd */
+	struct knfsd_fh		rp_openfh;
+	int			rp_locked;
+	char			rp_ibuf[NFSD4_REPLAY_ISIZE];
+};
+
+extern void nfs4_replay_free_cache(struct nfs4_replay *rp);
+
+struct nfs4_stateowner;
+
+struct nfs4_stateowner_operations {
+	void (*so_unhash)(struct nfs4_stateowner *);
+	void (*so_free)(struct nfs4_stateowner *);
+};
+
+/*
+ * A core object that represents either an open or lock owner. The object and
+ * lock owner objects have one of these embedded within them. Refcounts and
+ * other fields common to both owner types are contained within these
+ * structures.
+ */
+struct nfs4_stateowner {
+	struct list_head			so_strhash;
+	struct list_head			so_stateids;
+	struct nfs4_client			*so_client;
+	const struct nfs4_stateowner_operations	*so_ops;
+	/* after increment in nfsd4_bump_seqid, represents the next
+	 * sequence id expected from the client: */
+	atomic_t				so_count;
+	u32					so_seqid;
+	struct xdr_netobj			so_owner; /* open owner name */
+	struct nfs4_replay			so_replay;
+	bool					so_is_open_owner;
+};
+
+/*
+ * When a file is opened, the client provides an open state owner opaque string
+ * that indicates the "owner" of that open. These objects are refcounted.
+ * References to it are held by each open state associated with it. This object
+ * is a superset of the nfs4_stateowner struct.
+ */
+struct nfs4_openowner {
+	struct nfs4_stateowner	oo_owner; /* must be first field */
+	struct list_head        oo_perclient;
+	/*
+	 * We keep around openowners a little while after last close,
+	 * which saves clients from having to confirm, and allows us to
+	 * handle close replays if they come soon enough.  The close_lru
+	 * is a list of such openowners, to be reaped by the laundromat
+	 * thread eventually if they remain unused:
+	 */
+	struct list_head	oo_close_lru;
+	struct nfs4_ol_stateid *oo_last_closed_stid;
+	time64_t		oo_time; /* time of placement on so_close_lru */
+#define NFS4_OO_CONFIRMED   1
+	unsigned char		oo_flags;
+};
+
+/*
+ * Represents a generic "lockowner". Similar to an openowner. References to it
+ * are held by the lock stateids that are created on its behalf. This object is
+ * a superset of the nfs4_stateowner struct.
+ */
+struct nfs4_lockowner {
+	struct nfs4_stateowner	lo_owner;	/* must be first element */
+	struct list_head	lo_blocked;	/* blocked file_locks */
+};
+
+static inline struct nfs4_openowner * openowner(struct nfs4_stateowner *so)
+{
+	return container_of(so, struct nfs4_openowner, oo_owner);
+}
+
+static inline struct nfs4_lockowner * lockowner(struct nfs4_stateowner *so)
+{
+	return container_of(so, struct nfs4_lockowner, lo_owner);
+}
+
+/*
+ * Per-client state indicating no. of opens and outstanding delegations
+ * on a file from a particular client.'od' stands for 'open & delegation'
+ */
+struct nfs4_clnt_odstate {
+	struct nfs4_client	*co_client;
+	struct nfs4_file	*co_file;
+	struct list_head	co_perfile;
+	refcount_t		co_odcount;
+};
+
+/*
+ * nfs4_file: a file opened by some number of (open) nfs4_stateowners.
+ *
+ * These objects are global. nfsd keeps one instance of a nfs4_file per
+ * filehandle (though it may keep multiple file descriptors for each). Each
+ * inode can have multiple filehandles associated with it, so there is
+ * (potentially) a many to one relationship between this struct and struct
+ * inode.
+ */
+struct nfs4_file {
+	refcount_t		fi_ref;
+	struct inode *		fi_inode;
+	bool			fi_aliased;
+	spinlock_t		fi_lock;
+	struct rhlist_head	fi_rlist;
+	struct list_head        fi_stateids;
+	union {
+		struct list_head	fi_delegations;
+		struct rcu_head		fi_rcu;
+	};
+	struct list_head	fi_clnt_odstate;
+	/* One each for O_RDONLY, O_WRONLY, O_RDWR: */
+	struct nfsd_file	*fi_fds[3];
+	/*
+	 * Each open or lock stateid contributes 0-4 to the counts
+	 * below depending on which bits are set in st_access_bitmap:
+	 *     1 to fi_access[O_RDONLY] if NFS4_SHARE_ACCES_READ is set
+	 *   + 1 to fi_access[O_WRONLY] if NFS4_SHARE_ACCESS_WRITE is set
+	 *   + 1 to both of the above if NFS4_SHARE_ACCESS_BOTH is set.
+	 */
+	atomic_t		fi_access[2];
+	u32			fi_share_deny;
+	struct nfsd_file	*fi_deleg_file;
+	struct nfsd_file	*fi_rdeleg_file;
+	int			fi_delegees;
+	struct knfsd_fh		fi_fhandle;
+	bool			fi_had_conflict;
+#ifdef CONFIG_NFSD_PNFS
+	struct list_head	fi_lo_states;
+	atomic_t		fi_lo_recalls;
+#endif
+};
+
+/*
+ * A generic struct representing either a open or lock stateid. The nfs4_client
+ * holds a reference to each of these objects, and they in turn hold a
+ * reference to their respective stateowners. The client's reference is
+ * released in response to a close or unlock (depending on whether it's an open
+ * or lock stateid) or when the client is being destroyed.
+ *
+ * In the case of v4.0 open stateids, these objects are preserved for a little
+ * while after close in order to handle CLOSE replays. Those are eventually
+ * reclaimed via a LRU scheme by the laundromat.
+ *
+ * This object is a superset of the nfs4_stid. "ol" stands for "Open or Lock".
+ * Better suggestions welcome.
+ */
+struct nfs4_ol_stateid {
+	struct nfs4_stid		st_stid;
+	struct list_head		st_perfile;
+	struct list_head		st_perstateowner;
+	struct list_head		st_locks;
+	struct nfs4_stateowner		*st_stateowner;
+	struct nfs4_clnt_odstate	*st_clnt_odstate;
+/*
+ * These bitmasks use 3 separate bits for READ, ALLOW, and BOTH; see the
+ * comment above bmap_to_share_mode() for explanation:
+ */
+	unsigned char			st_access_bmap;
+	unsigned char			st_deny_bmap;
+	struct nfs4_ol_stateid		*st_openstp;
+	struct mutex			st_mutex;
+};
+
+static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)
+{
+	return container_of(s, struct nfs4_ol_stateid, st_stid);
+}
+
+struct nfs4_layout_stateid {
+	struct nfs4_stid		ls_stid;
+	struct list_head		ls_perclnt;
+	struct list_head		ls_perfile;
+	spinlock_t			ls_lock;
+	struct list_head		ls_layouts;
+	u32				ls_layout_type;
+	struct nfsd_file		*ls_file;
+	struct nfsd4_callback		ls_recall;
+	stateid_t			ls_recall_sid;
+	bool				ls_recalled;
+	struct mutex			ls_mutex;
+
+	struct delayed_work		ls_fence_work;
+	unsigned int			ls_fence_delay;
+	bool				ls_fenced;
+};
+
+static inline struct nfs4_layout_stateid *layoutstateid(struct nfs4_stid *s)
+{
+	return container_of(s, struct nfs4_layout_stateid, ls_stid);
+}
+
+/* flags for preprocess_seqid_op() */
+#define RD_STATE	        0x00000010
+#define WR_STATE	        0x00000020
+
+enum nfsd4_cb_op {
+	NFSPROC4_CLNT_CB_NULL = 0,
+	NFSPROC4_CLNT_CB_RECALL,
+	NFSPROC4_CLNT_CB_LAYOUT,
+	NFSPROC4_CLNT_CB_OFFLOAD,
+	NFSPROC4_CLNT_CB_SEQUENCE,
+	NFSPROC4_CLNT_CB_NOTIFY_LOCK,
+	NFSPROC4_CLNT_CB_RECALL_ANY,
+	NFSPROC4_CLNT_CB_GETATTR,
+};
+
+/* Returns true iff a is later than b: */
+static inline bool nfsd4_stateid_generation_after(stateid_t *a, stateid_t *b)
+{
+	return (s32)(a->si_generation - b->si_generation) > 0;
+}
+
+/*
+ * When a client tries to get a lock on a file, we set one of these objects
+ * on the blocking lock. When the lock becomes free, we can then issue a
+ * CB_NOTIFY_LOCK to the server.
+ */
+struct nfsd4_blocked_lock {
+	struct list_head	nbl_list;
+	struct list_head	nbl_lru;
+	time64_t		nbl_time;
+	struct file_lock	nbl_lock;
+	struct knfsd_fh		nbl_fh;
+	struct nfsd4_callback	nbl_cb;
+	struct kref		nbl_kref;
+};
+
+struct nfsd4_compound_state;
+struct nfsd_net;
+struct nfsd4_copy;
+
+extern __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate, struct svc_fh *fhp,
+		stateid_t *stateid, int flags, struct nfsd_file **filp,
+		struct nfs4_stid **cstid);
+__be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
+			    stateid_t *stateid, unsigned short typemask,
+			    unsigned short statusmask,
+			    struct nfs4_stid **s, struct nfsd_net *nn);
+struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab,
+				  void (*sc_free)(struct nfs4_stid *));
+int nfs4_init_copy_state(struct nfsd_net *nn, struct nfsd4_copy *copy);
+void nfs4_free_copy_state(struct nfsd4_copy *copy);
+struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn,
+			struct nfs4_stid *p_stid);
+void nfs4_put_stid(struct nfs4_stid *s);
+void nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid);
+void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *, struct nfsd_net *);
+extern void nfs4_release_reclaim(struct nfsd_net *);
+extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(struct xdr_netobj name,
+							struct nfsd_net *nn);
+extern __be32 nfs4_check_open_reclaim(struct nfs4_client *);
+extern void nfsd4_probe_callback(struct nfs4_client *clp);
+extern void nfsd4_probe_callback_sync(struct nfs4_client *clp);
+extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *);
+extern void nfsd41_cb_referring_call(struct nfsd4_callback *cb,
+				     struct nfs4_sessionid *sessionid,
+				     u32 slotid, u32 seqno);
+extern void nfsd41_cb_destroy_referring_call_list(struct nfsd4_callback *cb);
+extern void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
+		const struct nfsd4_callback_ops *ops, enum nfsd4_cb_op op);
+extern bool nfsd4_run_cb(struct nfsd4_callback *cb);
+
+static inline void nfsd4_try_run_cb(struct nfsd4_callback *cb)
+{
+	if (!test_and_set_bit(NFSD4_CALLBACK_RUNNING, &cb->cb_flags))
+		WARN_ON_ONCE(!nfsd4_run_cb(cb));
+}
+
+extern void nfsd4_shutdown_callback(struct nfs4_client *);
+extern void nfsd4_shutdown_copy(struct nfs4_client *clp);
+void nfsd4_put_client(struct nfs4_client *clp);
+void nfsd4_async_copy_reaper(struct nfsd_net *nn);
+bool nfsd4_has_active_async_copies(struct nfs4_client *clp);
+void nfsd_update_cmtime_attr(struct file *f, unsigned int flags);
+extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(struct xdr_netobj name,
+				struct xdr_netobj princhash, struct nfsd_net *nn);
+extern bool nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn);
+
+void put_nfs4_file(struct nfs4_file *fi);
+extern void nfs4_put_cpntf_state(struct nfsd_net *nn,
+				 struct nfs4_cpntf_state *cps);
+extern __be32 manage_cpntf_state(struct nfsd_net *nn, stateid_t *st,
+				 struct nfs4_client *clp,
+				 struct nfs4_cpntf_state **cps);
+static inline void get_nfs4_file(struct nfs4_file *fi)
+{
+	refcount_inc(&fi->fi_ref);
+}
+struct nfsd_file *find_any_file(struct nfs4_file *f);
+
+#ifdef CONFIG_NFSD_V4
+void nfsd4_revoke_states(struct nfsd_net *nn, struct super_block *sb);
+void nfsd4_revoke_export_states(struct nfsd_net *nn, const struct path *path);
+void nfsd4_cancel_copy_by_sb(struct net *net, struct super_block *sb);
+int nfsd_net_cb_init(struct nfsd_net *nn);
+void nfsd_net_cb_shutdown(struct nfsd_net *nn);
+#else
+static inline void nfsd4_revoke_states(struct nfsd_net *nn, struct super_block *sb)
+{
+}
+static inline void nfsd4_revoke_export_states(struct nfsd_net *nn,
+					      const struct path *path)
+{
+}
+static inline void nfsd4_cancel_copy_by_sb(struct net *net, struct super_block *sb)
+{
+}
+static inline int nfsd_net_cb_init(struct nfsd_net *nn)
+{
+	return 0;
+}
+static inline void nfsd_net_cb_shutdown(struct nfsd_net *nn)
+{
+}
+#endif
+
+/* grace period management */
+bool nfsd4_force_end_grace(struct nfsd_net *nn);
+
+/* nfs4recover operations */
+extern int nfsd4_client_tracking_init(struct net *net);
+extern void nfsd4_client_tracking_exit(struct net *net);
+extern void nfsd4_client_record_create(struct nfs4_client *clp);
+extern void nfsd4_client_record_remove(struct nfs4_client *clp);
+extern int nfsd4_client_record_check(struct nfs4_client *clp);
+extern void nfsd4_record_grace_done(struct nfsd_net *nn);
+
+static inline bool try_to_expire_client(struct nfs4_client *clp)
+{
+	cmpxchg(&clp->cl_state, NFSD4_COURTESY, NFSD4_EXPIRABLE);
+	return clp->cl_state == NFSD4_EXPIRABLE;
+}
+
+extern __be32 nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp,
+		struct dentry *dentry, struct nfs4_delegation **pdp);
+
+struct nfsd4_get_dir_delegation;
+struct nfs4_delegation *nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate,
+						struct nfsd4_get_dir_delegation *gdd,
+						struct nfsd_file *nf);
+#endif   /* NFSD4_STATE_H */

linux-7.2.3/fs/nfsd/stats.c

@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * procfs-based user access to knfsd statistics
+ *
+ * /proc/net/rpc/nfsd
+ *
+ * Format:
+ *	rc <hits> <misses> <nocache>
+ *			Statistsics for the reply cache
+ *	fh <stale> <deprecated filehandle cache stats>
+ *			statistics for filehandle lookup
+ *	io <bytes-read> <bytes-written>
+ *			statistics for IO throughput
+ *	th <threads> <deprecated thread usage histogram stats>
+ *			number of threads
+ *	ra <deprecated ra-cache stats>
+ *
+ *	plus generic RPC stats (see net/sunrpc/stats.c)
+ *
+ * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#include <linux/seq_file.h>
+#include <linux/module.h>
+#include <linux/sunrpc/stats.h>
+#include <net/net_namespace.h>
+
+#include "nfsd.h"
+
+static int nfsd_show(struct seq_file *seq, void *v)
+{
+	struct net *net = pde_data(file_inode(seq->file));
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	int i;
+
+	seq_printf(seq, "rc %lld %lld %lld\nfh %lld 0 0 0 0\nio %lld %lld\n",
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_HITS]),
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_MISSES]),
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_RC_NOCACHE]),
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_FH_STALE]),
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_IO_READ]),
+		   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_IO_WRITE]));
+
+	/* thread usage: */
+	seq_printf(seq, "th %u 0", atomic_read(&nfsd_th_cnt));
+
+	/* deprecated thread usage histogram stats */
+	for (i = 0; i < 10; i++)
+		seq_puts(seq, " 0.000");
+
+	/* deprecated ra-cache stats */
+	seq_puts(seq, "\nra 0 0 0 0 0 0 0 0 0 0 0 0\n");
+
+	/* show my rpc info */
+	svc_seq_show(seq, &nn->nfsd_svcstats);
+
+#ifdef CONFIG_NFSD_V4
+	/* Show count for individual nfsv4 operations */
+	/* Writing operation numbers 0 1 2 also for maintaining uniformity */
+	seq_printf(seq, "proc4ops %u", LAST_NFS4_OP + 1);
+	for (i = 0; i <= LAST_NFS4_OP; i++) {
+		seq_printf(seq, " %lld",
+			   percpu_counter_sum_positive(&nn->counter[NFSD_STATS_NFS4_OP(i)]));
+	}
+	seq_printf(seq, "\nwdeleg_getattr %lld",
+		percpu_counter_sum_positive(&nn->counter[NFSD_STATS_WDELEG_GETATTR]));
+
+	seq_putc(seq, '\n');
+#endif
+
+	return 0;
+}
+
+DEFINE_PROC_SHOW_ATTRIBUTE(nfsd);
+
+struct proc_dir_entry *nfsd_proc_stat_init(struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	return svc_proc_register(net, &nn->nfsd_svcstats, &nfsd_proc_ops);
+}
+
+void nfsd_proc_stat_shutdown(struct net *net)
+{
+	svc_proc_unregister(net, "nfsd");
+}

linux-7.2.3/fs/nfsd/stats.h

@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Statistics for NFS server.
+ *
+ * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
+ */
+#ifndef _NFSD_STATS_H
+#define _NFSD_STATS_H
+
+#include <uapi/linux/nfsd/stats.h>
+#include <linux/percpu_counter.h>
+
+struct proc_dir_entry *nfsd_proc_stat_init(struct net *net);
+void nfsd_proc_stat_shutdown(struct net *net);
+
+static inline void nfsd_stats_rc_hits_inc(struct nfsd_net *nn)
+{
+	percpu_counter_inc(&nn->counter[NFSD_STATS_RC_HITS]);
+}
+
+static inline void nfsd_stats_rc_misses_inc(struct nfsd_net *nn)
+{
+	percpu_counter_inc(&nn->counter[NFSD_STATS_RC_MISSES]);
+}
+
+static inline void nfsd_stats_rc_nocache_inc(struct nfsd_net *nn)
+{
+	percpu_counter_inc(&nn->counter[NFSD_STATS_RC_NOCACHE]);
+}
+
+static inline void nfsd_stats_fh_stale_inc(struct nfsd_net *nn,
+					   struct svc_export *exp)
+{
+	percpu_counter_inc(&nn->counter[NFSD_STATS_FH_STALE]);
+	if (exp && exp->ex_stats)
+		percpu_counter_inc(&exp->ex_stats->counter[EXP_STATS_FH_STALE]);
+}
+
+static inline void nfsd_stats_io_read_add(struct nfsd_net *nn,
+					  struct svc_export *exp, s64 amount)
+{
+	percpu_counter_add(&nn->counter[NFSD_STATS_IO_READ], amount);
+	if (exp && exp->ex_stats)
+		percpu_counter_add(&exp->ex_stats->counter[EXP_STATS_IO_READ], amount);
+}
+
+static inline void nfsd_stats_io_write_add(struct nfsd_net *nn,
+					   struct svc_export *exp, s64 amount)
+{
+	percpu_counter_add(&nn->counter[NFSD_STATS_IO_WRITE], amount);
+	if (exp && exp->ex_stats)
+		percpu_counter_add(&exp->ex_stats->counter[EXP_STATS_IO_WRITE], amount);
+}
+
+static inline void nfsd_stats_payload_misses_inc(struct nfsd_net *nn)
+{
+	percpu_counter_inc(&nn->counter[NFSD_STATS_PAYLOAD_MISSES]);
+}
+
+static inline void nfsd_stats_drc_mem_usage_add(struct nfsd_net *nn, s64 amount)
+{
+	percpu_counter_add(&nn->counter[NFSD_STATS_DRC_MEM_USAGE], amount);
+}
+
+static inline void nfsd_stats_drc_mem_usage_sub(struct nfsd_net *nn, s64 amount)
+{
+	percpu_counter_sub(&nn->counter[NFSD_STATS_DRC_MEM_USAGE], amount);
+}
+
+#ifdef CONFIG_NFSD_V4
+static inline void nfsd_stats_wdeleg_getattr_inc(struct nfsd_net *nn)
+{
+	percpu_counter_inc(&nn->counter[NFSD_STATS_WDELEG_GETATTR]);
+}
+#endif
+#endif /* _NFSD_STATS_H */

linux-7.2.3/fs/nfsd/trace.c

@@ -0,0 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define CREATE_TRACE_POINTS
+#include "trace.h"

linux-7.2.3/fs/nfsd/vfs.h

@@ -0,0 +1,168 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 1995-1997 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#ifndef LINUX_NFSD_VFS_H
+#define LINUX_NFSD_VFS_H
+
+#include <linux/fs.h>
+#include <linux/posix_acl.h>
+#include "nfsfh.h"
+#include "nfsd.h"
+
+/*
+ * Flags for nfsd_permission
+ */
+#define NFSD_MAY_NOP			0
+#define NFSD_MAY_EXEC			0x001 /* == MAY_EXEC */
+#define NFSD_MAY_WRITE			0x002 /* == MAY_WRITE */
+#define NFSD_MAY_READ			0x004 /* == MAY_READ */
+#define NFSD_MAY_SATTR			0x008
+#define NFSD_MAY_TRUNC			0x010
+#define NFSD_MAY_NLM			0x020 /* request is from lockd */
+#define NFSD_MAY_MASK			0x03f
+
+/* extra hints to permission and open routines: */
+#define NFSD_MAY_OWNER_OVERRIDE		0x040
+#define NFSD_MAY_LOCAL_ACCESS		0x080 /* for device special files */
+#define NFSD_MAY_BYPASS_GSS_ON_ROOT	0x100
+#define NFSD_MAY_NOT_BREAK_LEASE	0x200
+#define NFSD_MAY_BYPASS_GSS		0x400
+#define NFSD_MAY_READ_IF_EXEC		0x800
+
+#define NFSD_MAY_64BIT_COOKIE		0x1000 /* 64 bit readdir cookies for >= NFSv3 */
+
+#define NFSD_MAY_LOCALIO		0x2000 /* for tracing, reflects when localio used */
+
+#define NFSD_MAY_CREATE		(NFSD_MAY_EXEC|NFSD_MAY_WRITE)
+#define NFSD_MAY_REMOVE		(NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC)
+
+struct nfsd_file;
+
+/*
+ * Callback function for readdir
+ */
+typedef int (*nfsd_filldir_t)(void *, const char *, int, loff_t, u64, unsigned);
+
+/* nfsd/vfs.c */
+struct nfsd_attrs {
+	struct iattr		*na_iattr;	/* input */
+	struct xdr_netobj	*na_seclabel;	/* input */
+	struct posix_acl	*na_pacl;	/* input */
+	struct posix_acl	*na_dpacl;	/* input */
+
+	int			na_labelerr;	/* output */
+	int			na_dpaclerr;	/* output */
+	int			na_paclerr;	/* output */
+};
+
+static inline void nfsd_attrs_free(struct nfsd_attrs *attrs)
+{
+	posix_acl_release(attrs->na_pacl);
+	posix_acl_release(attrs->na_dpacl);
+}
+
+static inline bool nfsd_attrs_valid(struct nfsd_attrs *attrs)
+{
+	struct iattr *iap = attrs->na_iattr;
+
+	return (iap->ia_valid || (attrs->na_seclabel &&
+		attrs->na_seclabel->len) ||
+		attrs->na_pacl || attrs->na_dpacl);
+}
+
+__be32		nfserrno (int errno);
+int		nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
+		                struct svc_export **expp);
+__be32		nfsd_lookup(struct svc_rqst *, struct svc_fh *,
+				const char *, unsigned int, struct svc_fh *);
+__be32		 nfsd_lookup_dentry(struct svc_rqst *, struct svc_fh *,
+				const char *, unsigned int,
+				struct svc_export **, struct dentry **);
+__be32		nfsd_setattr(struct svc_rqst *, struct svc_fh *,
+			     struct nfsd_attrs *, const struct timespec64 *);
+int nfsd_mountpoint(struct dentry *, struct svc_export *);
+#ifdef CONFIG_NFSD_V4
+__be32		nfsd4_vfs_fallocate(struct svc_rqst *, struct svc_fh *,
+				    struct file *, loff_t, loff_t, int);
+__be32		nfsd4_clone_file_range(struct svc_rqst *rqstp,
+				       struct nfsd_file *nf_src, u64 src_pos,
+				       struct nfsd_file *nf_dst, u64 dst_pos,
+				       u64 count, bool sync);
+#endif /* CONFIG_NFSD_V4 */
+__be32		nfsd_create_locked(struct svc_rqst *, struct svc_fh *,
+				struct nfsd_attrs *attrs, int type, dev_t rdev,
+				struct svc_fh *res);
+__be32		nfsd_create(struct svc_rqst *, struct svc_fh *,
+				char *name, int len, struct nfsd_attrs *attrs,
+				int type, dev_t rdev, struct svc_fh *res);
+__be32		nfsd_access(struct svc_rqst *, struct svc_fh *, u32 *, u32 *);
+__be32		nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
+				struct svc_fh *resfhp, struct nfsd_attrs *iap);
+__be32		nfsd_commit(struct svc_rqst *rqst, struct svc_fh *fhp,
+				struct nfsd_file *nf, u64 offset, u32 count,
+				__be32 *verf);
+#ifdef CONFIG_NFSD_V4
+__be32		nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
+			    char *name, void **bufp, int *lenp);
+__be32		nfsd_listxattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
+			    char **bufp, int *lenp);
+__be32		nfsd_removexattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
+			    char *name);
+__be32		nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
+			    char *name, void *buf, u32 len, u32 flags);
+#endif
+int 		nfsd_open_break_lease(struct inode *, int);
+__be32		nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t,
+				int, struct file **);
+int		nfsd_open_verified(struct svc_fh *fhp, umode_t type, int may_flags,
+				struct file **filp);
+__be32		nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
+				struct file *file, loff_t offset,
+				unsigned long *count,
+				u32 *eof);
+__be32		nfsd_iter_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
+				struct nfsd_file *nf, loff_t offset,
+				unsigned long *count, unsigned int base,
+				u32 *eof);
+bool		nfsd_read_splice_ok(struct svc_rqst *rqstp);
+__be32		nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
+				loff_t offset, unsigned long *count,
+				u32 *eof);
+__be32		nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp,
+				loff_t offset, const struct xdr_buf *payload,
+				unsigned long *cnt, int stable, __be32 *verf);
+__be32		nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp,
+				struct nfsd_file *nf, loff_t offset,
+				const struct xdr_buf *payload,
+				unsigned long *cnt, int stable, __be32 *verf);
+__be32		nfsd_readlink(struct svc_rqst *, struct svc_fh *,
+				char *, int *);
+__be32		nfsd_symlink(struct svc_rqst *, struct svc_fh *,
+			     char *name, int len, char *path,
+			     struct nfsd_attrs *attrs,
+			     struct svc_fh *res);
+__be32		nfsd_link(struct svc_rqst *, struct svc_fh *,
+				char *, int, struct svc_fh *);
+ssize_t		nfsd_copy_file_range(struct file *, u64,
+				     struct file *, u64, u64);
+__be32		nfsd_rename(struct svc_rqst *,
+				struct svc_fh *, char *, int,
+				struct svc_fh *, char *, int);
+__be32		nfsd_unlink(struct svc_rqst *, struct svc_fh *, int type,
+				char *name, int len);
+__be32		nfsd_readdir(struct svc_rqst *, struct svc_fh *,
+			     loff_t *, struct readdir_cd *, nfsd_filldir_t);
+__be32		nfsd_statfs(struct svc_rqst *, struct svc_fh *,
+				struct kstatfs *, int access);
+int		nfsd_get_case_info(struct dentry *dentry,
+				   bool *case_insensitive,
+				   bool *case_preserving);
+
+__be32		nfsd_permission(struct svc_cred *cred, struct svc_export *exp,
+				struct dentry *dentry, int acc);
+
+void		nfsd_filp_close(struct file *fp);
+
+#endif /* LINUX_NFSD_VFS_H */

linux-7.2.3/fs/nfsd/xdr.h

@@ -0,0 +1,177 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* XDR types for nfsd. This is mainly a typing exercise. */
+
+#ifndef LINUX_NFSD_H
+#define LINUX_NFSD_H
+
+#include <linux/vfs.h>
+#include "nfsd.h"
+#include "nfsfh.h"
+
+struct nfsd_fhandle {
+	struct svc_fh		fh;
+};
+
+struct nfsd_sattrargs {
+	struct svc_fh		fh;
+	struct iattr		attrs;
+};
+
+struct nfsd_diropargs {
+	struct svc_fh		fh;
+	char *			name;
+	unsigned int		len;
+};
+
+struct nfsd_readargs {
+	struct svc_fh		fh;
+	__u32			offset;
+	__u32			count;
+};
+
+struct nfsd_writeargs {
+	svc_fh			fh;
+	__u32			offset;
+	__u32			len;
+	struct xdr_buf		payload;
+};
+
+struct nfsd_createargs {
+	struct svc_fh		fh;
+	char *			name;
+	unsigned int		len;
+	struct iattr		attrs;
+};
+
+struct nfsd_renameargs {
+	struct svc_fh		ffh;
+	char *			fname;
+	unsigned int		flen;
+	struct svc_fh		tfh;
+	char *			tname;
+	unsigned int		tlen;
+};
+
+struct nfsd_linkargs {
+	struct svc_fh		ffh;
+	struct svc_fh		tfh;
+	char *			tname;
+	unsigned int		tlen;
+};
+
+struct nfsd_symlinkargs {
+	struct svc_fh		ffh;
+	char *			fname;
+	unsigned int		flen;
+	char *			tname;
+	unsigned int		tlen;
+	struct iattr		attrs;
+	struct kvec		first;
+};
+
+struct nfsd_readdirargs {
+	struct svc_fh		fh;
+	__u32			cookie;
+	__u32			count;
+};
+
+struct nfsd_stat {
+	__be32			status;
+};
+
+struct nfsd_attrstat {
+	__be32			status;
+	struct svc_fh		fh;
+	struct kstat		stat;
+};
+
+struct nfsd_diropres  {
+	__be32			status;
+	struct svc_fh		fh;
+	struct kstat		stat;
+};
+
+struct nfsd_readlinkres {
+	__be32			status;
+	int			len;
+	struct page		*page;
+};
+
+struct nfsd_readres {
+	__be32			status;
+	struct svc_fh		fh;
+	unsigned long		count;
+	struct kstat		stat;
+	struct page		**pages;
+};
+
+struct nfsd_readdirres {
+	/* Components of the reply */
+	__be32			status;
+
+	int			count;
+
+	/* Used to encode the reply's entry list */
+	struct xdr_stream	xdr;
+	struct xdr_buf		dirlist;
+	struct readdir_cd	common;
+	unsigned int		cookie_offset;
+};
+
+struct nfsd_statfsres {
+	__be32			status;
+	struct kstatfs		stats;
+};
+
+/*
+ * Storage requirements for XDR arguments and results.
+ */
+union nfsd_xdrstore {
+	struct nfsd_sattrargs	sattr;
+	struct nfsd_diropargs	dirop;
+	struct nfsd_readargs	read;
+	struct nfsd_writeargs	write;
+	struct nfsd_createargs	create;
+	struct nfsd_renameargs	rename;
+	struct nfsd_linkargs	link;
+	struct nfsd_symlinkargs	symlink;
+	struct nfsd_readdirargs	readdir;
+};
+
+#define NFS2_SVC_XDRSIZE	sizeof(union nfsd_xdrstore)
+
+
+bool nfssvc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+
+bool nfssvc_encode_statres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_encode_attrstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_encode_diropres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_encode_statfsres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfssvc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+
+void nfssvc_encode_nfscookie(struct nfsd_readdirres *resp, u32 offset);
+int nfssvc_encode_entry(void *data, const char *name, int namlen,
+			loff_t offset, u64 ino, unsigned int d_type);
+
+void nfssvc_release_attrstat(struct svc_rqst *rqstp);
+void nfssvc_release_diropres(struct svc_rqst *rqstp);
+void nfssvc_release_readres(struct svc_rqst *rqstp);
+
+/* Helper functions for NFSv2 ACL code */
+bool svcxdr_decode_fhandle(struct xdr_stream *xdr, struct svc_fh *fhp);
+bool svcxdr_encode_stat(struct xdr_stream *xdr, __be32 status);
+bool svcxdr_encode_fattr(struct svc_rqst *rqstp, struct xdr_stream *xdr,
+			 const struct svc_fh *fhp, const struct kstat *stat);
+
+#endif /* LINUX_NFSD_H */

linux-7.2.3/fs/nfsd/xdr3.h

@@ -0,0 +1,314 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * XDR types for NFSv3 in nfsd.
+ *
+ * Copyright (C) 1996-1998, Olaf Kirch <okir@monad.swb.de>
+ */
+
+#ifndef _LINUX_NFSD_XDR3_H
+#define _LINUX_NFSD_XDR3_H
+
+#include "xdr.h"
+
+struct nfsd3_sattrargs {
+	struct svc_fh		fh;
+	struct iattr		attrs;
+	int			check_guard;
+	struct timespec64	guardtime;
+};
+
+struct nfsd3_diropargs {
+	struct svc_fh		fh;
+	char *			name;
+	unsigned int		len;
+};
+
+struct nfsd3_accessargs {
+	struct svc_fh		fh;
+	__u32			access;
+};
+
+struct nfsd3_readargs {
+	struct svc_fh		fh;
+	__u64			offset;
+	__u32			count;
+};
+
+struct nfsd3_writeargs {
+	svc_fh			fh;
+	__u64			offset;
+	__u32			count;
+	int			stable;
+	__u32			len;
+	struct xdr_buf		payload;
+};
+
+struct nfsd3_createargs {
+	struct svc_fh		fh;
+	char *			name;
+	unsigned int		len;
+	int			createmode;
+	struct iattr		attrs;
+	__be32 *		verf;
+};
+
+struct nfsd3_mknodargs {
+	struct svc_fh		fh;
+	char *			name;
+	unsigned int		len;
+	__u32			ftype;
+	__u32			major, minor;
+	struct iattr		attrs;
+};
+
+struct nfsd3_renameargs {
+	struct svc_fh		ffh;
+	char *			fname;
+	unsigned int		flen;
+	struct svc_fh		tfh;
+	char *			tname;
+	unsigned int		tlen;
+};
+
+struct nfsd3_linkargs {
+	struct svc_fh		ffh;
+	struct svc_fh		tfh;
+	char *			tname;
+	unsigned int		tlen;
+};
+
+struct nfsd3_symlinkargs {
+	struct svc_fh		ffh;
+	char *			fname;
+	unsigned int		flen;
+	char *			tname;
+	unsigned int		tlen;
+	struct iattr		attrs;
+	struct kvec		first;
+};
+
+struct nfsd3_readdirargs {
+	struct svc_fh		fh;
+	__u64			cookie;
+	__u32			count;
+	__be32 *		verf;
+};
+
+struct nfsd3_commitargs {
+	struct svc_fh		fh;
+	__u64			offset;
+	__u32			count;
+};
+
+struct nfsd3_getaclargs {
+	struct svc_fh		fh;
+	__u32			mask;
+};
+
+struct posix_acl;
+struct nfsd3_setaclargs {
+	struct svc_fh		fh;
+	__u32			mask;
+	struct posix_acl	*acl_access;
+	struct posix_acl	*acl_default;
+};
+
+struct nfsd3_attrstat {
+	__be32			status;
+	struct svc_fh		fh;
+	struct kstat            stat;
+};
+
+/* LOOKUP, CREATE, MKDIR, SYMLINK, MKNOD */
+struct nfsd3_diropres  {
+	__be32			status;
+	struct svc_fh		dirfh;
+	struct svc_fh		fh;
+};
+
+struct nfsd3_accessres {
+	__be32			status;
+	struct svc_fh		fh;
+	__u32			access;
+	struct kstat		stat;
+};
+
+struct nfsd3_readlinkres {
+	__be32			status;
+	struct svc_fh		fh;
+	__u32			len;
+	struct page		**pages;
+};
+
+struct nfsd3_readres {
+	__be32			status;
+	struct svc_fh		fh;
+	unsigned long		count;
+	__u32			eof;
+	struct page		**pages;
+};
+
+struct nfsd3_writeres {
+	__be32			status;
+	struct svc_fh		fh;
+	unsigned long		count;
+	int			committed;
+	__be32			verf[2];
+};
+
+struct nfsd3_renameres {
+	__be32			status;
+	struct svc_fh		ffh;
+	struct svc_fh		tfh;
+};
+
+struct nfsd3_linkres {
+	__be32			status;
+	struct svc_fh		tfh;
+	struct svc_fh		fh;
+};
+
+struct nfsd3_readdirres {
+	/* Components of the reply */
+	__be32			status;
+	struct svc_fh		fh;
+	__be32			verf[2];
+
+	/* Used to encode the reply's entry list */
+	struct xdr_stream	xdr;
+	struct xdr_buf		dirlist;
+	struct svc_fh		scratch;
+	struct readdir_cd	common;
+	unsigned int		cookie_offset;
+	struct svc_rqst *	rqstp;
+
+};
+
+struct nfsd3_fsstatres {
+	__be32			status;
+	struct kstatfs		stats;
+	__u32			invarsec;
+};
+
+struct nfsd3_fsinfores {
+	__be32			status;
+	__u32			f_rtmax;
+	__u32			f_rtpref;
+	__u32			f_rtmult;
+	__u32			f_wtmax;
+	__u32			f_wtpref;
+	__u32			f_wtmult;
+	__u32			f_dtpref;
+	__u64			f_maxfilesize;
+	__u32			f_properties;
+};
+
+struct nfsd3_pathconfres {
+	__be32			status;
+	__u32			p_link_max;
+	__u32			p_name_max;
+	__u32			p_no_trunc;
+	__u32			p_chown_restricted;
+	bool			p_case_insensitive;
+	bool			p_case_preserving;
+};
+
+struct nfsd3_commitres {
+	__be32			status;
+	struct svc_fh		fh;
+	__be32			verf[2];
+};
+
+struct nfsd3_getaclres {
+	__be32			status;
+	struct svc_fh		fh;
+	int			mask;
+	struct posix_acl	*acl_access;
+	struct posix_acl	*acl_default;
+	struct kstat		stat;
+};
+
+/* dummy type for release */
+struct nfsd3_fhandle_pair {
+	__u32			dummy;
+	struct svc_fh		fh1;
+	struct svc_fh		fh2;
+};
+
+/*
+ * Storage requirements for XDR arguments and results.
+ */
+union nfsd3_xdrstore {
+	struct nfsd3_sattrargs		sattrargs;
+	struct nfsd3_diropargs		diropargs;
+	struct nfsd3_readargs		readargs;
+	struct nfsd3_writeargs		writeargs;
+	struct nfsd3_createargs		createargs;
+	struct nfsd3_renameargs		renameargs;
+	struct nfsd3_linkargs		linkargs;
+	struct nfsd3_symlinkargs	symlinkargs;
+	struct nfsd3_readdirargs	readdirargs;
+	struct nfsd3_diropres 		diropres;
+	struct nfsd3_accessres		accessres;
+	struct nfsd3_readlinkres	readlinkres;
+	struct nfsd3_readres		readres;
+	struct nfsd3_writeres		writeres;
+	struct nfsd3_renameres		renameres;
+	struct nfsd3_linkres		linkres;
+	struct nfsd3_readdirres		readdirres;
+	struct nfsd3_fsstatres		fsstatres;
+	struct nfsd3_fsinfores		fsinfores;
+	struct nfsd3_pathconfres	pathconfres;
+	struct nfsd3_commitres		commitres;
+	struct nfsd3_getaclres		getaclres;
+};
+
+#define NFS3_SVC_XDRSIZE		sizeof(union nfsd3_xdrstore)
+
+bool nfs3svc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_accessargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_decode_commitargs(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+
+bool nfs3svc_encode_getattrres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_wccstat(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_lookupres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_writeres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_createres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_renameres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_linkres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+bool nfs3svc_encode_commitres(struct svc_rqst *rqstp, struct xdr_stream *xdr);
+
+void nfs3svc_release_fhandle(struct svc_rqst *);
+void nfs3svc_release_fhandle2(struct svc_rqst *);
+
+void nfs3svc_encode_cookie3(struct nfsd3_readdirres *resp, u64 offset);
+int nfs3svc_encode_entry3(void *data, const char *name, int namlen,
+			  loff_t offset, u64 ino, unsigned int d_type);
+int nfs3svc_encode_entryplus3(void *data, const char *name, int namlen,
+			      loff_t offset, u64 ino, unsigned int d_type);
+/* Helper functions for NFSv3 ACL code */
+bool svcxdr_decode_nfs_fh3(struct xdr_stream *xdr, struct svc_fh *fhp);
+bool svcxdr_encode_nfsstat3(struct xdr_stream *xdr, __be32 status);
+bool svcxdr_encode_post_op_attr(struct svc_rqst *rqstp, struct xdr_stream *xdr,
+				const struct svc_fh *fhp);
+
+#endif /* _LINUX_NFSD_XDR3_H */

linux-7.2.3/fs/nfsd/xdr4cb.h

@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#define NFS4_MAXTAGLEN		20
+
+#define NFS4_enc_cb_null_sz		0
+#define NFS4_dec_cb_null_sz		0
+#define cb_compound_enc_hdr_sz		4
+#define cb_compound_dec_hdr_sz		(3 + (NFS4_MAXTAGLEN >> 2))
+#define sessionid_sz			(NFS4_MAX_SESSIONID_LEN >> 2)
+#define enc_referring_call4_sz		(1 + 1)
+#define enc_referring_call_list4_sz	(sessionid_sz + 1 + \
+					enc_referring_call4_sz)
+#define cb_sequence_enc_sz		(sessionid_sz + 4 +             \
+					enc_referring_call_list4_sz)
+#define cb_sequence_dec_sz		(op_dec_sz + sessionid_sz + 4)
+
+#define op_enc_sz			1
+#define op_dec_sz			2
+#define enc_nfs4_fh_sz			(1 + (NFS4_FHSIZE >> 2))
+#define enc_stateid_sz			(NFS4_STATEID_SIZE >> 2)
+#define NFS4_enc_cb_recall_sz		(cb_compound_enc_hdr_sz +       \
+					cb_sequence_enc_sz +            \
+					1 + enc_stateid_sz +            \
+					enc_nfs4_fh_sz)
+
+#define NFS4_dec_cb_recall_sz		(cb_compound_dec_hdr_sz  +      \
+					cb_sequence_dec_sz +            \
+					op_dec_sz)
+#define NFS4_enc_cb_layout_sz		(cb_compound_enc_hdr_sz +       \
+					cb_sequence_enc_sz +            \
+					1 + 3 +                         \
+					enc_nfs4_fh_sz + 4)
+#define NFS4_dec_cb_layout_sz		(cb_compound_dec_hdr_sz  +      \
+					cb_sequence_dec_sz +            \
+					op_dec_sz)
+
+#define NFS4_enc_cb_notify_lock_sz	(cb_compound_enc_hdr_sz +        \
+					cb_sequence_enc_sz +             \
+					2 + 1 +				 \
+					XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + \
+					enc_nfs4_fh_sz)
+#define NFS4_dec_cb_notify_lock_sz	(cb_compound_dec_hdr_sz  +      \
+					cb_sequence_dec_sz +            \
+					op_dec_sz)
+#define enc_cb_offload_info_sz		(1 + 1 + 2 + 1 +		\
+					XDR_QUADLEN(NFS4_VERIFIER_SIZE))
+#define NFS4_enc_cb_offload_sz		(cb_compound_enc_hdr_sz +       \
+					cb_sequence_enc_sz +            \
+					enc_nfs4_fh_sz +		\
+					enc_stateid_sz +		\
+					enc_cb_offload_info_sz)
+#define NFS4_dec_cb_offload_sz		(cb_compound_dec_hdr_sz  +      \
+					cb_sequence_dec_sz +            \
+					op_dec_sz)
+#define NFS4_enc_cb_recall_any_sz	(cb_compound_enc_hdr_sz +       \
+					cb_sequence_enc_sz +            \
+					1 + 1 + 1)
+#define NFS4_dec_cb_recall_any_sz	(cb_compound_dec_hdr_sz  +      \
+					cb_sequence_dec_sz +            \
+					op_dec_sz)
+
+/*
+ * 1: CB_GETATTR opcode (32-bit)
+ * N: file_handle
+ * 1: number of entry in attribute array (32-bit)
+ * 3: entry 0-2 in attribute array (32-bit * 3)
+ */
+#define NFS4_enc_cb_getattr_sz		(cb_compound_enc_hdr_sz +       \
+					cb_sequence_enc_sz +            \
+					1 + enc_nfs4_fh_sz + 1 + 3)
+/*
+ * 4: fattr_bitmap_maxsz
+ * 1: attribute array len
+ * 2: change attr (64-bit)
+ * 2: size (64-bit)
+ * 2: atime.seconds (64-bit)
+ * 1: atime.nanoseconds (32-bit)
+ * 2: mtime.seconds (64-bit)
+ * 1: mtime.nanoseconds (32-bit)
+ */
+#define NFS4_dec_cb_getattr_sz		(cb_compound_dec_hdr_sz  +      \
+			cb_sequence_dec_sz + 4 + 1 + 2 + 2 + 2 + 1 + 2 + 1 + op_dec_sz)