summaryrefslogtreecommitdiffstats
path: root/fs/9p
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-07 18:49:45 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-07 18:49:45 +0000
commit2c3c1048746a4622d8c89a29670120dc8fab93c4 (patch)
tree848558de17fb3008cdf4d861b01ac7781903ce39 /fs/9p
parentInitial commit. (diff)
downloadlinux-2c3c1048746a4622d8c89a29670120dc8fab93c4.tar.xz
linux-2c3c1048746a4622d8c89a29670120dc8fab93c4.zip
Adding upstream version 6.1.76.upstream/6.1.76upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'fs/9p')
-rw-r--r--fs/9p/Kconfig45
-rw-r--r--fs/9p/Makefile17
-rw-r--r--fs/9p/acl.c330
-rw-r--r--fs/9p/acl.h48
-rw-r--r--fs/9p/cache.c76
-rw-r--r--fs/9p/cache.h27
-rw-r--r--fs/9p/fid.c327
-rw-r--r--fs/9p/fid.h35
-rw-r--r--fs/9p/v9fs.c735
-rw-r--r--fs/9p/v9fs.h232
-rw-r--r--fs/9p/v9fs_vfs.h92
-rw-r--r--fs/9p/vfs_addr.c360
-rw-r--r--fs/9p/vfs_dentry.c109
-rw-r--r--fs/9p/vfs_dir.c250
-rw-r--r--fs/9p/vfs_file.c711
-rw-r--r--fs/9p/vfs_inode.c1465
-rw-r--r--fs/9p/vfs_inode_dotl.c1001
-rw-r--r--fs/9p/vfs_super.c369
-rw-r--r--fs/9p/xattr.c194
-rw-r--r--fs/9p/xattr.h27
20 files changed, 6450 insertions, 0 deletions
diff --git a/fs/9p/Kconfig b/fs/9p/Kconfig
new file mode 100644
index 000000000..d7bc93447
--- /dev/null
+++ b/fs/9p/Kconfig
@@ -0,0 +1,45 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config 9P_FS
+ tristate "Plan 9 Resource Sharing Support (9P2000)"
+ depends on INET && NET_9P
+ select NETFS_SUPPORT
+ help
+ If you say Y here, you will get experimental support for
+ Plan 9 resource sharing via the 9P2000 protocol.
+
+ See <http://v9fs.sf.net> for more information.
+
+ If unsure, say N.
+
+if 9P_FS
+config 9P_FSCACHE
+ bool "Enable 9P client caching support"
+ depends on 9P_FS=m && FSCACHE || 9P_FS=y && FSCACHE=y
+ help
+ Choose Y here to enable persistent, read-only local
+ caching support for 9p clients using FS-Cache
+
+
+config 9P_FS_POSIX_ACL
+ bool "9P POSIX Access Control Lists"
+ select FS_POSIX_ACL
+ help
+ POSIX Access Control Lists (ACLs) support permissions for users and
+ groups beyond the owner/group/world scheme.
+
+ If you don't know what Access Control Lists are, say N
+
+endif
+
+
+config 9P_FS_SECURITY
+ bool "9P Security Labels"
+ depends on 9P_FS
+ help
+ Security labels support alternative access control models
+ implemented by security modules like SELinux. This option
+ enables an extended attribute handler for file security
+ labels in the 9P filesystem.
+
+ If you are not using a security module that requires using
+ extended attributes for file security labels, say N.
diff --git a/fs/9p/Makefile b/fs/9p/Makefile
new file mode 100644
index 000000000..e7800a5c7
--- /dev/null
+++ b/fs/9p/Makefile
@@ -0,0 +1,17 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_9P_FS) := 9p.o
+
+9p-objs := \
+ vfs_super.o \
+ vfs_inode.o \
+ vfs_inode_dotl.o \
+ vfs_addr.o \
+ vfs_file.o \
+ vfs_dir.o \
+ vfs_dentry.o \
+ v9fs.o \
+ fid.o \
+ xattr.o
+
+9p-$(CONFIG_9P_FSCACHE) += cache.o
+9p-$(CONFIG_9P_FS_POSIX_ACL) += acl.o
diff --git a/fs/9p/acl.c b/fs/9p/acl.c
new file mode 100644
index 000000000..4dac4a0dc
--- /dev/null
+++ b/fs/9p/acl.c
@@ -0,0 +1,330 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/posix_acl_xattr.h>
+#include "xattr.h"
+#include "acl.h"
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+
+static struct posix_acl *__v9fs_get_acl(struct p9_fid *fid, char *name)
+{
+ ssize_t size;
+ void *value = NULL;
+ struct posix_acl *acl = NULL;
+
+ size = v9fs_fid_xattr_get(fid, name, NULL, 0);
+ if (size > 0) {
+ value = kzalloc(size, GFP_NOFS);
+ if (!value)
+ return ERR_PTR(-ENOMEM);
+ size = v9fs_fid_xattr_get(fid, name, value, size);
+ if (size > 0) {
+ acl = posix_acl_from_xattr(&init_user_ns, value, size);
+ if (IS_ERR(acl))
+ goto err_out;
+ }
+ } else if (size == -ENODATA || size == 0 ||
+ size == -ENOSYS || size == -EOPNOTSUPP) {
+ acl = NULL;
+ } else
+ acl = ERR_PTR(-EIO);
+
+err_out:
+ kfree(value);
+ return acl;
+}
+
+int v9fs_get_acl(struct inode *inode, struct p9_fid *fid)
+{
+ int retval = 0;
+ struct posix_acl *pacl, *dacl;
+ struct v9fs_session_info *v9ses;
+
+ v9ses = v9fs_inode2v9ses(inode);
+ if (((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) ||
+ ((v9ses->flags & V9FS_ACL_MASK) != V9FS_POSIX_ACL)) {
+ set_cached_acl(inode, ACL_TYPE_DEFAULT, NULL);
+ set_cached_acl(inode, ACL_TYPE_ACCESS, NULL);
+ return 0;
+ }
+ /* get the default/access acl values and cache them */
+ dacl = __v9fs_get_acl(fid, XATTR_NAME_POSIX_ACL_DEFAULT);
+ pacl = __v9fs_get_acl(fid, XATTR_NAME_POSIX_ACL_ACCESS);
+
+ if (!IS_ERR(dacl) && !IS_ERR(pacl)) {
+ set_cached_acl(inode, ACL_TYPE_DEFAULT, dacl);
+ set_cached_acl(inode, ACL_TYPE_ACCESS, pacl);
+ } else
+ retval = -EIO;
+
+ if (!IS_ERR(dacl))
+ posix_acl_release(dacl);
+
+ if (!IS_ERR(pacl))
+ posix_acl_release(pacl);
+
+ return retval;
+}
+
+static struct posix_acl *v9fs_get_cached_acl(struct inode *inode, int type)
+{
+ struct posix_acl *acl;
+ /*
+ * 9p Always cache the acl value when
+ * instantiating the inode (v9fs_inode_from_fid)
+ */
+ acl = get_cached_acl(inode, type);
+ BUG_ON(is_uncached_acl(acl));
+ return acl;
+}
+
+struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type, bool rcu)
+{
+ struct v9fs_session_info *v9ses;
+
+ if (rcu)
+ return ERR_PTR(-ECHILD);
+
+ v9ses = v9fs_inode2v9ses(inode);
+ if (((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) ||
+ ((v9ses->flags & V9FS_ACL_MASK) != V9FS_POSIX_ACL)) {
+ /*
+ * On access = client and acl = on mode get the acl
+ * values from the server
+ */
+ return NULL;
+ }
+ return v9fs_get_cached_acl(inode, type);
+
+}
+
+static int v9fs_set_acl(struct p9_fid *fid, int type, struct posix_acl *acl)
+{
+ int retval;
+ char *name;
+ size_t size;
+ void *buffer;
+
+ if (!acl)
+ return 0;
+
+ /* Set a setxattr request to server */
+ size = posix_acl_xattr_size(acl->a_count);
+ buffer = kmalloc(size, GFP_KERNEL);
+ if (!buffer)
+ return -ENOMEM;
+ retval = posix_acl_to_xattr(&init_user_ns, acl, buffer, size);
+ if (retval < 0)
+ goto err_free_out;
+ switch (type) {
+ case ACL_TYPE_ACCESS:
+ name = XATTR_NAME_POSIX_ACL_ACCESS;
+ break;
+ case ACL_TYPE_DEFAULT:
+ name = XATTR_NAME_POSIX_ACL_DEFAULT;
+ break;
+ default:
+ BUG();
+ }
+ retval = v9fs_fid_xattr_set(fid, name, buffer, size, 0);
+err_free_out:
+ kfree(buffer);
+ return retval;
+}
+
+int v9fs_acl_chmod(struct inode *inode, struct p9_fid *fid)
+{
+ int retval = 0;
+ struct posix_acl *acl;
+
+ if (S_ISLNK(inode->i_mode))
+ return -EOPNOTSUPP;
+ acl = v9fs_get_cached_acl(inode, ACL_TYPE_ACCESS);
+ if (acl) {
+ retval = __posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode);
+ if (retval)
+ return retval;
+ set_cached_acl(inode, ACL_TYPE_ACCESS, acl);
+ retval = v9fs_set_acl(fid, ACL_TYPE_ACCESS, acl);
+ posix_acl_release(acl);
+ }
+ return retval;
+}
+
+int v9fs_set_create_acl(struct inode *inode, struct p9_fid *fid,
+ struct posix_acl *dacl, struct posix_acl *acl)
+{
+ set_cached_acl(inode, ACL_TYPE_DEFAULT, dacl);
+ set_cached_acl(inode, ACL_TYPE_ACCESS, acl);
+ v9fs_set_acl(fid, ACL_TYPE_DEFAULT, dacl);
+ v9fs_set_acl(fid, ACL_TYPE_ACCESS, acl);
+ return 0;
+}
+
+void v9fs_put_acl(struct posix_acl *dacl,
+ struct posix_acl *acl)
+{
+ posix_acl_release(dacl);
+ posix_acl_release(acl);
+}
+
+int v9fs_acl_mode(struct inode *dir, umode_t *modep,
+ struct posix_acl **dpacl, struct posix_acl **pacl)
+{
+ int retval = 0;
+ umode_t mode = *modep;
+ struct posix_acl *acl = NULL;
+
+ if (!S_ISLNK(mode)) {
+ acl = v9fs_get_cached_acl(dir, ACL_TYPE_DEFAULT);
+ if (IS_ERR(acl))
+ return PTR_ERR(acl);
+ if (!acl)
+ mode &= ~current_umask();
+ }
+ if (acl) {
+ if (S_ISDIR(mode))
+ *dpacl = posix_acl_dup(acl);
+ retval = __posix_acl_create(&acl, GFP_NOFS, &mode);
+ if (retval < 0)
+ return retval;
+ if (retval > 0)
+ *pacl = acl;
+ else
+ posix_acl_release(acl);
+ }
+ *modep = mode;
+ return 0;
+}
+
+static int v9fs_xattr_get_acl(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, void *buffer, size_t size)
+{
+ struct v9fs_session_info *v9ses;
+ struct posix_acl *acl;
+ int error;
+
+ v9ses = v9fs_dentry2v9ses(dentry);
+ /*
+ * We allow set/get/list of acl when access=client is not specified
+ */
+ if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT)
+ return v9fs_xattr_get(dentry, handler->name, buffer, size);
+
+ acl = v9fs_get_cached_acl(inode, handler->flags);
+ if (IS_ERR(acl))
+ return PTR_ERR(acl);
+ if (acl == NULL)
+ return -ENODATA;
+ error = posix_acl_to_xattr(&init_user_ns, acl, buffer, size);
+ posix_acl_release(acl);
+
+ return error;
+}
+
+static int v9fs_xattr_set_acl(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
+{
+ int retval;
+ struct posix_acl *acl;
+ struct v9fs_session_info *v9ses;
+
+ v9ses = v9fs_dentry2v9ses(dentry);
+ /*
+ * set the attribute on the remote. Without even looking at the
+ * xattr value. We leave it to the server to validate
+ */
+ if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT)
+ return v9fs_xattr_set(dentry, handler->name, value, size,
+ flags);
+
+ if (S_ISLNK(inode->i_mode))
+ return -EOPNOTSUPP;
+ if (!inode_owner_or_capable(&init_user_ns, inode))
+ return -EPERM;
+ if (value) {
+ /* update the cached acl value */
+ acl = posix_acl_from_xattr(&init_user_ns, value, size);
+ if (IS_ERR(acl))
+ return PTR_ERR(acl);
+ else if (acl) {
+ retval = posix_acl_valid(inode->i_sb->s_user_ns, acl);
+ if (retval)
+ goto err_out;
+ }
+ } else
+ acl = NULL;
+
+ switch (handler->flags) {
+ case ACL_TYPE_ACCESS:
+ if (acl) {
+ struct iattr iattr = { 0 };
+ struct posix_acl *old_acl = acl;
+
+ retval = posix_acl_update_mode(&init_user_ns, inode,
+ &iattr.ia_mode, &acl);
+ if (retval)
+ goto err_out;
+ if (!acl) {
+ /*
+ * ACL can be represented
+ * by the mode bits. So don't
+ * update ACL.
+ */
+ posix_acl_release(old_acl);
+ value = NULL;
+ size = 0;
+ }
+ iattr.ia_valid = ATTR_MODE;
+ /* FIXME should we update ctime ?
+ * What is the following setxattr update the
+ * mode ?
+ */
+ v9fs_vfs_setattr_dotl(&init_user_ns, dentry, &iattr);
+ }
+ break;
+ case ACL_TYPE_DEFAULT:
+ if (!S_ISDIR(inode->i_mode)) {
+ retval = acl ? -EINVAL : 0;
+ goto err_out;
+ }
+ break;
+ default:
+ BUG();
+ }
+ retval = v9fs_xattr_set(dentry, handler->name, value, size, flags);
+ if (!retval)
+ set_cached_acl(inode, handler->flags, acl);
+err_out:
+ posix_acl_release(acl);
+ return retval;
+}
+
+const struct xattr_handler v9fs_xattr_acl_access_handler = {
+ .name = XATTR_NAME_POSIX_ACL_ACCESS,
+ .flags = ACL_TYPE_ACCESS,
+ .get = v9fs_xattr_get_acl,
+ .set = v9fs_xattr_set_acl,
+};
+
+const struct xattr_handler v9fs_xattr_acl_default_handler = {
+ .name = XATTR_NAME_POSIX_ACL_DEFAULT,
+ .flags = ACL_TYPE_DEFAULT,
+ .get = v9fs_xattr_get_acl,
+ .set = v9fs_xattr_set_acl,
+};
diff --git a/fs/9p/acl.h b/fs/9p/acl.h
new file mode 100644
index 000000000..ce5175d46
--- /dev/null
+++ b/fs/9p/acl.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ */
+#ifndef FS_9P_ACL_H
+#define FS_9P_ACL_H
+
+#ifdef CONFIG_9P_FS_POSIX_ACL
+int v9fs_get_acl(struct inode *inode, struct p9_fid *fid);
+struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type,
+ bool rcu);
+int v9fs_acl_chmod(struct inode *inode, struct p9_fid *fid);
+int v9fs_set_create_acl(struct inode *inode, struct p9_fid *fid,
+ struct posix_acl *dacl, struct posix_acl *acl);
+int v9fs_acl_mode(struct inode *dir, umode_t *modep,
+ struct posix_acl **dpacl, struct posix_acl **pacl);
+void v9fs_put_acl(struct posix_acl *dacl, struct posix_acl *acl);
+#else
+#define v9fs_iop_get_acl NULL
+static inline int v9fs_get_acl(struct inode *inode, struct p9_fid *fid)
+{
+ return 0;
+}
+static inline int v9fs_acl_chmod(struct inode *inode, struct p9_fid *fid)
+{
+ return 0;
+}
+static inline int v9fs_set_create_acl(struct inode *inode,
+ struct p9_fid *fid,
+ struct posix_acl *dacl,
+ struct posix_acl *acl)
+{
+ return 0;
+}
+static inline void v9fs_put_acl(struct posix_acl *dacl,
+ struct posix_acl *acl)
+{
+}
+static inline int v9fs_acl_mode(struct inode *dir, umode_t *modep,
+ struct posix_acl **dpacl,
+ struct posix_acl **pacl)
+{
+ return 0;
+}
+
+#endif
+#endif /* FS_9P_XATTR_H */
diff --git a/fs/9p/cache.c b/fs/9p/cache.c
new file mode 100644
index 000000000..12c0ae29f
--- /dev/null
+++ b/fs/9p/cache.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * V9FS cache definitions.
+ *
+ * Copyright (C) 2009 by Abhishek Kulkarni <adkulkar@umail.iu.edu>
+ */
+
+#include <linux/jiffies.h>
+#include <linux/file.h>
+#include <linux/slab.h>
+#include <linux/stat.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+#include <net/9p/9p.h>
+
+#include "v9fs.h"
+#include "cache.h"
+
+int v9fs_cache_session_get_cookie(struct v9fs_session_info *v9ses,
+ const char *dev_name)
+{
+ struct fscache_volume *vcookie;
+ char *name, *p;
+
+ name = kasprintf(GFP_KERNEL, "9p,%s,%s",
+ dev_name, v9ses->cachetag ?: v9ses->aname);
+ if (!name)
+ return -ENOMEM;
+
+ for (p = name; *p; p++)
+ if (*p == '/')
+ *p = ';';
+
+ vcookie = fscache_acquire_volume(name, NULL, NULL, 0);
+ p9_debug(P9_DEBUG_FSC, "session %p get volume %p (%s)\n",
+ v9ses, vcookie, name);
+ if (IS_ERR(vcookie)) {
+ if (vcookie != ERR_PTR(-EBUSY)) {
+ kfree(name);
+ return PTR_ERR(vcookie);
+ }
+ pr_err("Cache volume key already in use (%s)\n", name);
+ vcookie = NULL;
+ }
+ v9ses->fscache = vcookie;
+ kfree(name);
+ return 0;
+}
+
+void v9fs_cache_inode_get_cookie(struct inode *inode)
+{
+ struct v9fs_inode *v9inode = V9FS_I(inode);
+ struct v9fs_session_info *v9ses;
+ __le32 version;
+ __le64 path;
+
+ if (!S_ISREG(inode->i_mode))
+ return;
+ if (WARN_ON(v9fs_inode_cookie(v9inode)))
+ return;
+
+ version = cpu_to_le32(v9inode->qid.version);
+ path = cpu_to_le64(v9inode->qid.path);
+ v9ses = v9fs_inode2v9ses(inode);
+ v9inode->netfs.cache =
+ fscache_acquire_cookie(v9fs_session_cache(v9ses),
+ 0,
+ &path, sizeof(path),
+ &version, sizeof(version),
+ i_size_read(&v9inode->netfs.inode));
+ if (v9inode->netfs.cache)
+ mapping_set_release_always(inode->i_mapping);
+
+ p9_debug(P9_DEBUG_FSC, "inode %p get cookie %p\n",
+ inode, v9fs_inode_cookie(v9inode));
+}
diff --git a/fs/9p/cache.h b/fs/9p/cache.h
new file mode 100644
index 000000000..1923affcd
--- /dev/null
+++ b/fs/9p/cache.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * V9FS cache definitions.
+ *
+ * Copyright (C) 2009 by Abhishek Kulkarni <adkulkar@umail.iu.edu>
+ */
+
+#ifndef _9P_CACHE_H
+#define _9P_CACHE_H
+
+#include <linux/fscache.h>
+
+#ifdef CONFIG_9P_FSCACHE
+
+extern int v9fs_cache_session_get_cookie(struct v9fs_session_info *v9ses,
+ const char *dev_name);
+
+extern void v9fs_cache_inode_get_cookie(struct inode *inode);
+
+#else /* CONFIG_9P_FSCACHE */
+
+static inline void v9fs_cache_inode_get_cookie(struct inode *inode)
+{
+}
+
+#endif /* CONFIG_9P_FSCACHE */
+#endif /* _9P_CACHE_H */
diff --git a/fs/9p/fid.c b/fs/9p/fid.c
new file mode 100644
index 000000000..23cf9b2fb
--- /dev/null
+++ b/fs/9p/fid.c
@@ -0,0 +1,327 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * V9FS FID Management
+ *
+ * Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net>
+ * Copyright (C) 2005, 2006 by Eric Van Hensbergen <ericvh@gmail.com>
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/idr.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+
+static inline void __add_fid(struct dentry *dentry, struct p9_fid *fid)
+{
+ hlist_add_head(&fid->dlist, (struct hlist_head *)&dentry->d_fsdata);
+}
+
+
+/**
+ * v9fs_fid_add - add a fid to a dentry
+ * @dentry: dentry that the fid is being added to
+ * @pfid: fid to add, NULLed out
+ *
+ */
+void v9fs_fid_add(struct dentry *dentry, struct p9_fid **pfid)
+{
+ struct p9_fid *fid = *pfid;
+
+ spin_lock(&dentry->d_lock);
+ __add_fid(dentry, fid);
+ spin_unlock(&dentry->d_lock);
+
+ *pfid = NULL;
+}
+
+/**
+ * v9fs_fid_find_inode - search for an open fid off of the inode list
+ * @inode: return a fid pointing to a specific inode
+ * @uid: return a fid belonging to the specified user
+ *
+ */
+
+static struct p9_fid *v9fs_fid_find_inode(struct inode *inode, kuid_t uid)
+{
+ struct hlist_head *h;
+ struct p9_fid *fid, *ret = NULL;
+
+ p9_debug(P9_DEBUG_VFS, " inode: %p\n", inode);
+
+ spin_lock(&inode->i_lock);
+ h = (struct hlist_head *)&inode->i_private;
+ hlist_for_each_entry(fid, h, ilist) {
+ if (uid_eq(fid->uid, uid)) {
+ p9_fid_get(fid);
+ ret = fid;
+ break;
+ }
+ }
+ spin_unlock(&inode->i_lock);
+ return ret;
+}
+
+/**
+ * v9fs_open_fid_add - add an open fid to an inode
+ * @inode: inode that the fid is being added to
+ * @pfid: fid to add, NULLed out
+ *
+ */
+
+void v9fs_open_fid_add(struct inode *inode, struct p9_fid **pfid)
+{
+ struct p9_fid *fid = *pfid;
+
+ spin_lock(&inode->i_lock);
+ hlist_add_head(&fid->ilist, (struct hlist_head *)&inode->i_private);
+ spin_unlock(&inode->i_lock);
+
+ *pfid = NULL;
+}
+
+
+/**
+ * v9fs_fid_find - retrieve a fid that belongs to the specified uid
+ * @dentry: dentry to look for fid in
+ * @uid: return fid that belongs to the specified user
+ * @any: if non-zero, return any fid associated with the dentry
+ *
+ */
+
+static struct p9_fid *v9fs_fid_find(struct dentry *dentry, kuid_t uid, int any)
+{
+ struct p9_fid *fid, *ret;
+
+ p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p) uid %d any %d\n",
+ dentry, dentry, from_kuid(&init_user_ns, uid),
+ any);
+ ret = NULL;
+ /* we'll recheck under lock if there's anything to look in */
+ if (dentry->d_fsdata) {
+ struct hlist_head *h = (struct hlist_head *)&dentry->d_fsdata;
+
+ spin_lock(&dentry->d_lock);
+ hlist_for_each_entry(fid, h, dlist) {
+ if (any || uid_eq(fid->uid, uid)) {
+ ret = fid;
+ p9_fid_get(ret);
+ break;
+ }
+ }
+ spin_unlock(&dentry->d_lock);
+ } else {
+ if (dentry->d_inode)
+ ret = v9fs_fid_find_inode(dentry->d_inode, uid);
+ }
+
+ return ret;
+}
+
+/*
+ * We need to hold v9ses->rename_sem as long as we hold references
+ * to returned path array. Array element contain pointers to
+ * dentry names.
+ */
+static int build_path_from_dentry(struct v9fs_session_info *v9ses,
+ struct dentry *dentry, const unsigned char ***names)
+{
+ int n = 0, i;
+ const unsigned char **wnames;
+ struct dentry *ds;
+
+ for (ds = dentry; !IS_ROOT(ds); ds = ds->d_parent)
+ n++;
+
+ wnames = kmalloc_array(n, sizeof(char *), GFP_KERNEL);
+ if (!wnames)
+ goto err_out;
+
+ for (ds = dentry, i = (n-1); i >= 0; i--, ds = ds->d_parent)
+ wnames[i] = ds->d_name.name;
+
+ *names = wnames;
+ return n;
+err_out:
+ return -ENOMEM;
+}
+
+static struct p9_fid *v9fs_fid_lookup_with_uid(struct dentry *dentry,
+ kuid_t uid, int any)
+{
+ struct dentry *ds;
+ const unsigned char **wnames, *uname;
+ int i, n, l, access;
+ struct v9fs_session_info *v9ses;
+ struct p9_fid *fid, *root_fid, *old_fid;
+
+ v9ses = v9fs_dentry2v9ses(dentry);
+ access = v9ses->flags & V9FS_ACCESS_MASK;
+ fid = v9fs_fid_find(dentry, uid, any);
+ if (fid)
+ return fid;
+ /*
+ * we don't have a matching fid. To do a TWALK we need
+ * parent fid. We need to prevent rename when we want to
+ * look at the parent.
+ */
+ down_read(&v9ses->rename_sem);
+ ds = dentry->d_parent;
+ fid = v9fs_fid_find(ds, uid, any);
+ if (fid) {
+ /* Found the parent fid do a lookup with that */
+ old_fid = fid;
+
+ fid = p9_client_walk(old_fid, 1, &dentry->d_name.name, 1);
+ p9_fid_put(old_fid);
+ goto fid_out;
+ }
+ up_read(&v9ses->rename_sem);
+
+ /* start from the root and try to do a lookup */
+ root_fid = v9fs_fid_find(dentry->d_sb->s_root, uid, any);
+ if (!root_fid) {
+ /* the user is not attached to the fs yet */
+ if (access == V9FS_ACCESS_SINGLE)
+ return ERR_PTR(-EPERM);
+
+ if (v9fs_proto_dotu(v9ses) || v9fs_proto_dotl(v9ses))
+ uname = NULL;
+ else
+ uname = v9ses->uname;
+
+ fid = p9_client_attach(v9ses->clnt, NULL, uname, uid,
+ v9ses->aname);
+ if (IS_ERR(fid))
+ return fid;
+
+ root_fid = p9_fid_get(fid);
+ v9fs_fid_add(dentry->d_sb->s_root, &fid);
+ }
+ /* If we are root ourself just return that */
+ if (dentry->d_sb->s_root == dentry)
+ return root_fid;
+
+ /*
+ * Do a multipath walk with attached root.
+ * When walking parent we need to make sure we
+ * don't have a parallel rename happening
+ */
+ down_read(&v9ses->rename_sem);
+ n = build_path_from_dentry(v9ses, dentry, &wnames);
+ if (n < 0) {
+ fid = ERR_PTR(n);
+ goto err_out;
+ }
+ fid = root_fid;
+ old_fid = root_fid;
+ i = 0;
+ while (i < n) {
+ l = min(n - i, P9_MAXWELEM);
+ /*
+ * We need to hold rename lock when doing a multipath
+ * walk to ensure none of the path components change
+ */
+ fid = p9_client_walk(old_fid, l, &wnames[i],
+ old_fid == root_fid /* clone */);
+ /* non-cloning walk will return the same fid */
+ if (fid != old_fid) {
+ p9_fid_put(old_fid);
+ old_fid = fid;
+ }
+ if (IS_ERR(fid)) {
+ kfree(wnames);
+ goto err_out;
+ }
+ i += l;
+ }
+ kfree(wnames);
+fid_out:
+ if (!IS_ERR(fid)) {
+ spin_lock(&dentry->d_lock);
+ if (d_unhashed(dentry)) {
+ spin_unlock(&dentry->d_lock);
+ p9_fid_put(fid);
+ fid = ERR_PTR(-ENOENT);
+ } else {
+ __add_fid(dentry, fid);
+ p9_fid_get(fid);
+ spin_unlock(&dentry->d_lock);
+ }
+ }
+err_out:
+ up_read(&v9ses->rename_sem);
+ return fid;
+}
+
+/**
+ * v9fs_fid_lookup - lookup for a fid, try to walk if not found
+ * @dentry: dentry to look for fid in
+ *
+ * Look for a fid in the specified dentry for the current user.
+ * If no fid is found, try to create one walking from a fid from the parent
+ * dentry (if it has one), or the root dentry. If the user haven't accessed
+ * the fs yet, attach now and walk from the root.
+ */
+
+struct p9_fid *v9fs_fid_lookup(struct dentry *dentry)
+{
+ kuid_t uid;
+ int any, access;
+ struct v9fs_session_info *v9ses;
+
+ v9ses = v9fs_dentry2v9ses(dentry);
+ access = v9ses->flags & V9FS_ACCESS_MASK;
+ switch (access) {
+ case V9FS_ACCESS_SINGLE:
+ case V9FS_ACCESS_USER:
+ case V9FS_ACCESS_CLIENT:
+ uid = current_fsuid();
+ any = 0;
+ break;
+
+ case V9FS_ACCESS_ANY:
+ uid = v9ses->uid;
+ any = 1;
+ break;
+
+ default:
+ uid = INVALID_UID;
+ any = 0;
+ break;
+ }
+ return v9fs_fid_lookup_with_uid(dentry, uid, any);
+}
+
+struct p9_fid *v9fs_writeback_fid(struct dentry *dentry)
+{
+ int err;
+ struct p9_fid *fid, *ofid;
+
+ ofid = v9fs_fid_lookup_with_uid(dentry, GLOBAL_ROOT_UID, 0);
+ fid = clone_fid(ofid);
+ if (IS_ERR(fid))
+ goto error_out;
+ p9_fid_put(ofid);
+ /*
+ * writeback fid will only be used to write back the
+ * dirty pages. We always request for the open fid in read-write
+ * mode so that a partial page write which result in page
+ * read can work.
+ */
+ err = p9_client_open(fid, O_RDWR);
+ if (err < 0) {
+ p9_fid_put(fid);
+ fid = ERR_PTR(err);
+ goto error_out;
+ }
+error_out:
+ return fid;
+}
diff --git a/fs/9p/fid.h b/fs/9p/fid.h
new file mode 100644
index 000000000..8a4e8cd12
--- /dev/null
+++ b/fs/9p/fid.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * V9FS FID Management
+ *
+ * Copyright (C) 2005 by Eric Van Hensbergen <ericvh@gmail.com>
+ */
+#ifndef FS_9P_FID_H
+#define FS_9P_FID_H
+#include <linux/list.h>
+
+struct p9_fid *v9fs_fid_lookup(struct dentry *dentry);
+static inline struct p9_fid *v9fs_parent_fid(struct dentry *dentry)
+{
+ return v9fs_fid_lookup(dentry->d_parent);
+}
+void v9fs_fid_add(struct dentry *dentry, struct p9_fid **fid);
+struct p9_fid *v9fs_writeback_fid(struct dentry *dentry);
+void v9fs_open_fid_add(struct inode *inode, struct p9_fid **fid);
+static inline struct p9_fid *clone_fid(struct p9_fid *fid)
+{
+ return IS_ERR(fid) ? fid : p9_client_walk(fid, 0, NULL, 1);
+}
+static inline struct p9_fid *v9fs_fid_clone(struct dentry *dentry)
+{
+ struct p9_fid *fid, *nfid;
+
+ fid = v9fs_fid_lookup(dentry);
+ if (!fid || IS_ERR(fid))
+ return fid;
+
+ nfid = clone_fid(fid);
+ p9_fid_put(fid);
+ return nfid;
+}
+#endif
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
new file mode 100644
index 000000000..0129de2ea
--- /dev/null
+++ b/fs/9p/v9fs.c
@@ -0,0 +1,735 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * This file contains functions assisting in mapping VFS to 9P2000
+ *
+ * Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com>
+ * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/cred.h>
+#include <linux/parser.h>
+#include <linux/idr.h>
+#include <linux/slab.h>
+#include <linux/seq_file.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+#include <net/9p/transport.h>
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "cache.h"
+
+static DEFINE_SPINLOCK(v9fs_sessionlist_lock);
+static LIST_HEAD(v9fs_sessionlist);
+struct kmem_cache *v9fs_inode_cache;
+
+/*
+ * Option Parsing (code inspired by NFS code)
+ * NOTE: each transport will parse its own options
+ */
+
+enum {
+ /* Options that take integer arguments */
+ Opt_debug, Opt_dfltuid, Opt_dfltgid, Opt_afid,
+ /* String options */
+ Opt_uname, Opt_remotename, Opt_cache, Opt_cachetag,
+ /* Options that take no arguments */
+ Opt_nodevmap,
+ /* Cache options */
+ Opt_cache_loose, Opt_fscache, Opt_mmap,
+ /* Access options */
+ Opt_access, Opt_posixacl,
+ /* Lock timeout option */
+ Opt_locktimeout,
+ /* Error token */
+ Opt_err
+};
+
+static const match_table_t tokens = {
+ {Opt_debug, "debug=%x"},
+ {Opt_dfltuid, "dfltuid=%u"},
+ {Opt_dfltgid, "dfltgid=%u"},
+ {Opt_afid, "afid=%u"},
+ {Opt_uname, "uname=%s"},
+ {Opt_remotename, "aname=%s"},
+ {Opt_nodevmap, "nodevmap"},
+ {Opt_cache, "cache=%s"},
+ {Opt_cache_loose, "loose"},
+ {Opt_fscache, "fscache"},
+ {Opt_mmap, "mmap"},
+ {Opt_cachetag, "cachetag=%s"},
+ {Opt_access, "access=%s"},
+ {Opt_posixacl, "posixacl"},
+ {Opt_locktimeout, "locktimeout=%u"},
+ {Opt_err, NULL}
+};
+
+static const char *const v9fs_cache_modes[nr__p9_cache_modes] = {
+ [CACHE_NONE] = "none",
+ [CACHE_MMAP] = "mmap",
+ [CACHE_LOOSE] = "loose",
+ [CACHE_FSCACHE] = "fscache",
+};
+
+/* Interpret mount options for cache mode */
+static int get_cache_mode(char *s)
+{
+ int version = -EINVAL;
+
+ if (!strcmp(s, "loose")) {
+ version = CACHE_LOOSE;
+ p9_debug(P9_DEBUG_9P, "Cache mode: loose\n");
+ } else if (!strcmp(s, "fscache")) {
+ version = CACHE_FSCACHE;
+ p9_debug(P9_DEBUG_9P, "Cache mode: fscache\n");
+ } else if (!strcmp(s, "mmap")) {
+ version = CACHE_MMAP;
+ p9_debug(P9_DEBUG_9P, "Cache mode: mmap\n");
+ } else if (!strcmp(s, "none")) {
+ version = CACHE_NONE;
+ p9_debug(P9_DEBUG_9P, "Cache mode: none\n");
+ } else
+ pr_info("Unknown Cache mode %s\n", s);
+ return version;
+}
+
+/*
+ * Display the mount options in /proc/mounts.
+ */
+int v9fs_show_options(struct seq_file *m, struct dentry *root)
+{
+ struct v9fs_session_info *v9ses = root->d_sb->s_fs_info;
+
+ if (v9ses->debug)
+ seq_printf(m, ",debug=%x", v9ses->debug);
+ if (!uid_eq(v9ses->dfltuid, V9FS_DEFUID))
+ seq_printf(m, ",dfltuid=%u",
+ from_kuid_munged(&init_user_ns, v9ses->dfltuid));
+ if (!gid_eq(v9ses->dfltgid, V9FS_DEFGID))
+ seq_printf(m, ",dfltgid=%u",
+ from_kgid_munged(&init_user_ns, v9ses->dfltgid));
+ if (v9ses->afid != ~0)
+ seq_printf(m, ",afid=%u", v9ses->afid);
+ if (strcmp(v9ses->uname, V9FS_DEFUSER) != 0)
+ seq_printf(m, ",uname=%s", v9ses->uname);
+ if (strcmp(v9ses->aname, V9FS_DEFANAME) != 0)
+ seq_printf(m, ",aname=%s", v9ses->aname);
+ if (v9ses->nodev)
+ seq_puts(m, ",nodevmap");
+ if (v9ses->cache)
+ seq_printf(m, ",%s", v9fs_cache_modes[v9ses->cache]);
+#ifdef CONFIG_9P_FSCACHE
+ if (v9ses->cachetag && v9ses->cache == CACHE_FSCACHE)
+ seq_printf(m, ",cachetag=%s", v9ses->cachetag);
+#endif
+
+ switch (v9ses->flags & V9FS_ACCESS_MASK) {
+ case V9FS_ACCESS_USER:
+ seq_puts(m, ",access=user");
+ break;
+ case V9FS_ACCESS_ANY:
+ seq_puts(m, ",access=any");
+ break;
+ case V9FS_ACCESS_CLIENT:
+ seq_puts(m, ",access=client");
+ break;
+ case V9FS_ACCESS_SINGLE:
+ seq_printf(m, ",access=%u",
+ from_kuid_munged(&init_user_ns, v9ses->uid));
+ break;
+ }
+
+ if (v9ses->flags & V9FS_POSIX_ACL)
+ seq_puts(m, ",posixacl");
+
+ return p9_show_client_options(m, v9ses->clnt);
+}
+
+/**
+ * v9fs_parse_options - parse mount options into session structure
+ * @v9ses: existing v9fs session information
+ * @opts: The mount option string
+ *
+ * Return 0 upon success, -ERRNO upon failure.
+ */
+
+static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
+{
+ char *options, *tmp_options;
+ substring_t args[MAX_OPT_ARGS];
+ char *p;
+ int option = 0;
+ char *s;
+ int ret = 0;
+
+ /* setup defaults */
+ v9ses->afid = ~0;
+ v9ses->debug = 0;
+ v9ses->cache = CACHE_NONE;
+#ifdef CONFIG_9P_FSCACHE
+ v9ses->cachetag = NULL;
+#endif
+ v9ses->session_lock_timeout = P9_LOCK_TIMEOUT;
+
+ if (!opts)
+ return 0;
+
+ tmp_options = kstrdup(opts, GFP_KERNEL);
+ if (!tmp_options) {
+ ret = -ENOMEM;
+ goto fail_option_alloc;
+ }
+ options = tmp_options;
+
+ while ((p = strsep(&options, ",")) != NULL) {
+ int token, r;
+
+ if (!*p)
+ continue;
+
+ token = match_token(p, tokens, args);
+ switch (token) {
+ case Opt_debug:
+ r = match_int(&args[0], &option);
+ if (r < 0) {
+ p9_debug(P9_DEBUG_ERROR,
+ "integer field, but no integer?\n");
+ ret = r;
+ } else {
+ v9ses->debug = option;
+#ifdef CONFIG_NET_9P_DEBUG
+ p9_debug_level = option;
+#endif
+ }
+ break;
+
+ case Opt_dfltuid:
+ r = match_int(&args[0], &option);
+ if (r < 0) {
+ p9_debug(P9_DEBUG_ERROR,
+ "integer field, but no integer?\n");
+ ret = r;
+ continue;
+ }
+ v9ses->dfltuid = make_kuid(current_user_ns(), option);
+ if (!uid_valid(v9ses->dfltuid)) {
+ p9_debug(P9_DEBUG_ERROR,
+ "uid field, but not a uid?\n");
+ ret = -EINVAL;
+ }
+ break;
+ case Opt_dfltgid:
+ r = match_int(&args[0], &option);
+ if (r < 0) {
+ p9_debug(P9_DEBUG_ERROR,
+ "integer field, but no integer?\n");
+ ret = r;
+ continue;
+ }
+ v9ses->dfltgid = make_kgid(current_user_ns(), option);
+ if (!gid_valid(v9ses->dfltgid)) {
+ p9_debug(P9_DEBUG_ERROR,
+ "gid field, but not a gid?\n");
+ ret = -EINVAL;
+ }
+ break;
+ case Opt_afid:
+ r = match_int(&args[0], &option);
+ if (r < 0) {
+ p9_debug(P9_DEBUG_ERROR,
+ "integer field, but no integer?\n");
+ ret = r;
+ } else {
+ v9ses->afid = option;
+ }
+ break;
+ case Opt_uname:
+ kfree(v9ses->uname);
+ v9ses->uname = match_strdup(&args[0]);
+ if (!v9ses->uname) {
+ ret = -ENOMEM;
+ goto free_and_return;
+ }
+ break;
+ case Opt_remotename:
+ kfree(v9ses->aname);
+ v9ses->aname = match_strdup(&args[0]);
+ if (!v9ses->aname) {
+ ret = -ENOMEM;
+ goto free_and_return;
+ }
+ break;
+ case Opt_nodevmap:
+ v9ses->nodev = 1;
+ break;
+ case Opt_cache_loose:
+ v9ses->cache = CACHE_LOOSE;
+ break;
+ case Opt_fscache:
+ v9ses->cache = CACHE_FSCACHE;
+ break;
+ case Opt_mmap:
+ v9ses->cache = CACHE_MMAP;
+ break;
+ case Opt_cachetag:
+#ifdef CONFIG_9P_FSCACHE
+ kfree(v9ses->cachetag);
+ v9ses->cachetag = match_strdup(&args[0]);
+ if (!v9ses->cachetag) {
+ ret = -ENOMEM;
+ goto free_and_return;
+ }
+#endif
+ break;
+ case Opt_cache:
+ s = match_strdup(&args[0]);
+ if (!s) {
+ ret = -ENOMEM;
+ p9_debug(P9_DEBUG_ERROR,
+ "problem allocating copy of cache arg\n");
+ goto free_and_return;
+ }
+ r = get_cache_mode(s);
+ if (r < 0)
+ ret = r;
+ else
+ v9ses->cache = r;
+
+ kfree(s);
+ break;
+
+ case Opt_access:
+ s = match_strdup(&args[0]);
+ if (!s) {
+ ret = -ENOMEM;
+ p9_debug(P9_DEBUG_ERROR,
+ "problem allocating copy of access arg\n");
+ goto free_and_return;
+ }
+
+ v9ses->flags &= ~V9FS_ACCESS_MASK;
+ if (strcmp(s, "user") == 0)
+ v9ses->flags |= V9FS_ACCESS_USER;
+ else if (strcmp(s, "any") == 0)
+ v9ses->flags |= V9FS_ACCESS_ANY;
+ else if (strcmp(s, "client") == 0) {
+ v9ses->flags |= V9FS_ACCESS_CLIENT;
+ } else {
+ uid_t uid;
+
+ v9ses->flags |= V9FS_ACCESS_SINGLE;
+ r = kstrtouint(s, 10, &uid);
+ if (r) {
+ ret = r;
+ pr_info("Unknown access argument %s: %d\n",
+ s, r);
+ kfree(s);
+ continue;
+ }
+ v9ses->uid = make_kuid(current_user_ns(), uid);
+ if (!uid_valid(v9ses->uid)) {
+ ret = -EINVAL;
+ pr_info("Unknown uid %s\n", s);
+ }
+ }
+
+ kfree(s);
+ break;
+
+ case Opt_posixacl:
+#ifdef CONFIG_9P_FS_POSIX_ACL
+ v9ses->flags |= V9FS_POSIX_ACL;
+#else
+ p9_debug(P9_DEBUG_ERROR,
+ "Not defined CONFIG_9P_FS_POSIX_ACL. Ignoring posixacl option\n");
+#endif
+ break;
+
+ case Opt_locktimeout:
+ r = match_int(&args[0], &option);
+ if (r < 0) {
+ p9_debug(P9_DEBUG_ERROR,
+ "integer field, but no integer?\n");
+ ret = r;
+ continue;
+ }
+ if (option < 1) {
+ p9_debug(P9_DEBUG_ERROR,
+ "locktimeout must be a greater than zero integer.\n");
+ ret = -EINVAL;
+ continue;
+ }
+ v9ses->session_lock_timeout = (long)option * HZ;
+ break;
+
+ default:
+ continue;
+ }
+ }
+
+free_and_return:
+ kfree(tmp_options);
+fail_option_alloc:
+ return ret;
+}
+
+/**
+ * v9fs_session_init - initialize session
+ * @v9ses: session information structure
+ * @dev_name: device being mounted
+ * @data: options
+ *
+ */
+
+struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
+ const char *dev_name, char *data)
+{
+ struct p9_fid *fid;
+ int rc = -ENOMEM;
+
+ v9ses->uname = kstrdup(V9FS_DEFUSER, GFP_KERNEL);
+ if (!v9ses->uname)
+ goto err_names;
+
+ v9ses->aname = kstrdup(V9FS_DEFANAME, GFP_KERNEL);
+ if (!v9ses->aname)
+ goto err_names;
+ init_rwsem(&v9ses->rename_sem);
+
+ v9ses->uid = INVALID_UID;
+ v9ses->dfltuid = V9FS_DEFUID;
+ v9ses->dfltgid = V9FS_DEFGID;
+
+ v9ses->clnt = p9_client_create(dev_name, data);
+ if (IS_ERR(v9ses->clnt)) {
+ rc = PTR_ERR(v9ses->clnt);
+ p9_debug(P9_DEBUG_ERROR, "problem initializing 9p client\n");
+ goto err_names;
+ }
+
+ v9ses->flags = V9FS_ACCESS_USER;
+
+ if (p9_is_proto_dotl(v9ses->clnt)) {
+ v9ses->flags = V9FS_ACCESS_CLIENT;
+ v9ses->flags |= V9FS_PROTO_2000L;
+ } else if (p9_is_proto_dotu(v9ses->clnt)) {
+ v9ses->flags |= V9FS_PROTO_2000U;
+ }
+
+ rc = v9fs_parse_options(v9ses, data);
+ if (rc < 0)
+ goto err_clnt;
+
+ v9ses->maxdata = v9ses->clnt->msize - P9_IOHDRSZ;
+
+ if (!v9fs_proto_dotl(v9ses) &&
+ ((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_CLIENT)) {
+ /*
+ * We support ACCESS_CLIENT only for dotl.
+ * Fall back to ACCESS_USER
+ */
+ v9ses->flags &= ~V9FS_ACCESS_MASK;
+ v9ses->flags |= V9FS_ACCESS_USER;
+ }
+ /*FIXME !! */
+ /* for legacy mode, fall back to V9FS_ACCESS_ANY */
+ if (!(v9fs_proto_dotu(v9ses) || v9fs_proto_dotl(v9ses)) &&
+ ((v9ses->flags&V9FS_ACCESS_MASK) == V9FS_ACCESS_USER)) {
+
+ v9ses->flags &= ~V9FS_ACCESS_MASK;
+ v9ses->flags |= V9FS_ACCESS_ANY;
+ v9ses->uid = INVALID_UID;
+ }
+ if (!v9fs_proto_dotl(v9ses) ||
+ !((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_CLIENT)) {
+ /*
+ * We support ACL checks on clinet only if the protocol is
+ * 9P2000.L and access is V9FS_ACCESS_CLIENT.
+ */
+ v9ses->flags &= ~V9FS_ACL_MASK;
+ }
+
+ fid = p9_client_attach(v9ses->clnt, NULL, v9ses->uname, INVALID_UID,
+ v9ses->aname);
+ if (IS_ERR(fid)) {
+ rc = PTR_ERR(fid);
+ p9_debug(P9_DEBUG_ERROR, "cannot attach\n");
+ goto err_clnt;
+ }
+
+ if ((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_SINGLE)
+ fid->uid = v9ses->uid;
+ else
+ fid->uid = INVALID_UID;
+
+#ifdef CONFIG_9P_FSCACHE
+ /* register the session for caching */
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
+ rc = v9fs_cache_session_get_cookie(v9ses, dev_name);
+ if (rc < 0)
+ goto err_clnt;
+ }
+#endif
+ spin_lock(&v9fs_sessionlist_lock);
+ list_add(&v9ses->slist, &v9fs_sessionlist);
+ spin_unlock(&v9fs_sessionlist_lock);
+
+ return fid;
+
+err_clnt:
+#ifdef CONFIG_9P_FSCACHE
+ kfree(v9ses->cachetag);
+#endif
+ p9_client_destroy(v9ses->clnt);
+err_names:
+ kfree(v9ses->uname);
+ kfree(v9ses->aname);
+ return ERR_PTR(rc);
+}
+
+/**
+ * v9fs_session_close - shutdown a session
+ * @v9ses: session information structure
+ *
+ */
+
+void v9fs_session_close(struct v9fs_session_info *v9ses)
+{
+ if (v9ses->clnt) {
+ p9_client_destroy(v9ses->clnt);
+ v9ses->clnt = NULL;
+ }
+
+#ifdef CONFIG_9P_FSCACHE
+ fscache_relinquish_volume(v9fs_session_cache(v9ses), NULL, false);
+ kfree(v9ses->cachetag);
+#endif
+ kfree(v9ses->uname);
+ kfree(v9ses->aname);
+
+ spin_lock(&v9fs_sessionlist_lock);
+ list_del(&v9ses->slist);
+ spin_unlock(&v9fs_sessionlist_lock);
+}
+
+/**
+ * v9fs_session_cancel - terminate a session
+ * @v9ses: session to terminate
+ *
+ * mark transport as disconnected and cancel all pending requests.
+ */
+
+void v9fs_session_cancel(struct v9fs_session_info *v9ses)
+{
+ p9_debug(P9_DEBUG_ERROR, "cancel session %p\n", v9ses);
+ p9_client_disconnect(v9ses->clnt);
+}
+
+/**
+ * v9fs_session_begin_cancel - Begin terminate of a session
+ * @v9ses: session to terminate
+ *
+ * After this call we don't allow any request other than clunk.
+ */
+
+void v9fs_session_begin_cancel(struct v9fs_session_info *v9ses)
+{
+ p9_debug(P9_DEBUG_ERROR, "begin cancel session %p\n", v9ses);
+ p9_client_begin_disconnect(v9ses->clnt);
+}
+
+extern int v9fs_error_init(void);
+
+static struct kobject *v9fs_kobj;
+
+#ifdef CONFIG_9P_FSCACHE
+/*
+ * List caches associated with a session
+ */
+static ssize_t caches_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ ssize_t n = 0, count = 0, limit = PAGE_SIZE;
+ struct v9fs_session_info *v9ses;
+
+ spin_lock(&v9fs_sessionlist_lock);
+ list_for_each_entry(v9ses, &v9fs_sessionlist, slist) {
+ if (v9ses->cachetag) {
+ n = snprintf(buf, limit, "%s\n", v9ses->cachetag);
+ if (n < 0) {
+ count = n;
+ break;
+ }
+
+ count += n;
+ limit -= n;
+ }
+ }
+
+ spin_unlock(&v9fs_sessionlist_lock);
+ return count;
+}
+
+static struct kobj_attribute v9fs_attr_cache = __ATTR_RO(caches);
+#endif /* CONFIG_9P_FSCACHE */
+
+static struct attribute *v9fs_attrs[] = {
+#ifdef CONFIG_9P_FSCACHE
+ &v9fs_attr_cache.attr,
+#endif
+ NULL,
+};
+
+static const struct attribute_group v9fs_attr_group = {
+ .attrs = v9fs_attrs,
+};
+
+/**
+ * v9fs_sysfs_init - Initialize the v9fs sysfs interface
+ *
+ */
+
+static int __init v9fs_sysfs_init(void)
+{
+ v9fs_kobj = kobject_create_and_add("9p", fs_kobj);
+ if (!v9fs_kobj)
+ return -ENOMEM;
+
+ if (sysfs_create_group(v9fs_kobj, &v9fs_attr_group)) {
+ kobject_put(v9fs_kobj);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+/**
+ * v9fs_sysfs_cleanup - Unregister the v9fs sysfs interface
+ *
+ */
+
+static void v9fs_sysfs_cleanup(void)
+{
+ sysfs_remove_group(v9fs_kobj, &v9fs_attr_group);
+ kobject_put(v9fs_kobj);
+}
+
+static void v9fs_inode_init_once(void *foo)
+{
+ struct v9fs_inode *v9inode = (struct v9fs_inode *)foo;
+
+ memset(&v9inode->qid, 0, sizeof(v9inode->qid));
+ inode_init_once(&v9inode->netfs.inode);
+}
+
+/**
+ * v9fs_init_inode_cache - initialize a cache for 9P
+ * Returns 0 on success.
+ */
+static int v9fs_init_inode_cache(void)
+{
+ v9fs_inode_cache = kmem_cache_create("v9fs_inode_cache",
+ sizeof(struct v9fs_inode),
+ 0, (SLAB_RECLAIM_ACCOUNT|
+ SLAB_MEM_SPREAD|SLAB_ACCOUNT),
+ v9fs_inode_init_once);
+ if (!v9fs_inode_cache)
+ return -ENOMEM;
+
+ return 0;
+}
+
+/**
+ * v9fs_destroy_inode_cache - destroy the cache of 9P inode
+ *
+ */
+static void v9fs_destroy_inode_cache(void)
+{
+ /*
+ * Make sure all delayed rcu free inodes are flushed before we
+ * destroy cache.
+ */
+ rcu_barrier();
+ kmem_cache_destroy(v9fs_inode_cache);
+}
+
+static int v9fs_cache_register(void)
+{
+ int ret;
+
+ ret = v9fs_init_inode_cache();
+ if (ret < 0)
+ return ret;
+ return ret;
+}
+
+static void v9fs_cache_unregister(void)
+{
+ v9fs_destroy_inode_cache();
+}
+
+/**
+ * init_v9fs - Initialize module
+ *
+ */
+
+static int __init init_v9fs(void)
+{
+ int err;
+
+ pr_info("Installing v9fs 9p2000 file system support\n");
+ /* TODO: Setup list of registered trasnport modules */
+
+ err = v9fs_cache_register();
+ if (err < 0) {
+ pr_err("Failed to register v9fs for caching\n");
+ return err;
+ }
+
+ err = v9fs_sysfs_init();
+ if (err < 0) {
+ pr_err("Failed to register with sysfs\n");
+ goto out_cache;
+ }
+ err = register_filesystem(&v9fs_fs_type);
+ if (err < 0) {
+ pr_err("Failed to register filesystem\n");
+ goto out_sysfs_cleanup;
+ }
+
+ return 0;
+
+out_sysfs_cleanup:
+ v9fs_sysfs_cleanup();
+
+out_cache:
+ v9fs_cache_unregister();
+
+ return err;
+}
+
+/**
+ * exit_v9fs - shutdown module
+ *
+ */
+
+static void __exit exit_v9fs(void)
+{
+ v9fs_sysfs_cleanup();
+ v9fs_cache_unregister();
+ unregister_filesystem(&v9fs_fs_type);
+}
+
+module_init(init_v9fs)
+module_exit(exit_v9fs)
+
+MODULE_AUTHOR("Latchesar Ionkov <lucho@ionkov.net>");
+MODULE_AUTHOR("Eric Van Hensbergen <ericvh@gmail.com>");
+MODULE_AUTHOR("Ron Minnich <rminnich@lanl.gov>");
+MODULE_LICENSE("GPL");
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
new file mode 100644
index 000000000..6acabc2e7
--- /dev/null
+++ b/fs/9p/v9fs.h
@@ -0,0 +1,232 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * V9FS definitions.
+ *
+ * Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com>
+ * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ */
+#ifndef FS_9P_V9FS_H
+#define FS_9P_V9FS_H
+
+#include <linux/backing-dev.h>
+#include <linux/netfs.h>
+
+/**
+ * enum p9_session_flags - option flags for each 9P session
+ * @V9FS_PROTO_2000U: whether or not to use 9P2000.u extensions
+ * @V9FS_PROTO_2000L: whether or not to use 9P2000.l extensions
+ * @V9FS_ACCESS_SINGLE: only the mounting user can access the hierarchy
+ * @V9FS_ACCESS_USER: a new attach will be issued for every user (default)
+ * @V9FS_ACCESS_CLIENT: Just like user, but access check is performed on client.
+ * @V9FS_ACCESS_ANY: use a single attach for all users
+ * @V9FS_ACCESS_MASK: bit mask of different ACCESS options
+ * @V9FS_POSIX_ACL: POSIX ACLs are enforced
+ *
+ * Session flags reflect options selected by users at mount time
+ */
+#define V9FS_ACCESS_ANY (V9FS_ACCESS_SINGLE | \
+ V9FS_ACCESS_USER | \
+ V9FS_ACCESS_CLIENT)
+#define V9FS_ACCESS_MASK V9FS_ACCESS_ANY
+#define V9FS_ACL_MASK V9FS_POSIX_ACL
+
+enum p9_session_flags {
+ V9FS_PROTO_2000U = 0x01,
+ V9FS_PROTO_2000L = 0x02,
+ V9FS_ACCESS_SINGLE = 0x04,
+ V9FS_ACCESS_USER = 0x08,
+ V9FS_ACCESS_CLIENT = 0x10,
+ V9FS_POSIX_ACL = 0x20
+};
+
+/* possible values of ->cache */
+/**
+ * enum p9_cache_modes - user specified cache preferences
+ * @CACHE_NONE: do not cache data, dentries, or directory contents (default)
+ * @CACHE_LOOSE: cache data, dentries, and directory contents w/no consistency
+ *
+ * eventually support loose, tight, time, session, default always none
+ */
+
+enum p9_cache_modes {
+ CACHE_NONE,
+ CACHE_MMAP,
+ CACHE_LOOSE,
+ CACHE_FSCACHE,
+ nr__p9_cache_modes
+};
+
+/**
+ * struct v9fs_session_info - per-instance session information
+ * @flags: session options of type &p9_session_flags
+ * @nodev: set to 1 to disable device mapping
+ * @debug: debug level
+ * @afid: authentication handle
+ * @cache: cache mode of type &p9_cache_modes
+ * @cachetag: the tag of the cache associated with this session
+ * @fscache: session cookie associated with FS-Cache
+ * @uname: string user name to mount hierarchy as
+ * @aname: mount specifier for remote hierarchy
+ * @maxdata: maximum data to be sent/recvd per protocol message
+ * @dfltuid: default numeric userid to mount hierarchy as
+ * @dfltgid: default numeric groupid to mount hierarchy as
+ * @uid: if %V9FS_ACCESS_SINGLE, the numeric uid which mounted the hierarchy
+ * @clnt: reference to 9P network client instantiated for this session
+ * @slist: reference to list of registered 9p sessions
+ *
+ * This structure holds state for each session instance established during
+ * a sys_mount() .
+ *
+ * Bugs: there seems to be a lot of state which could be condensed and/or
+ * removed.
+ */
+
+struct v9fs_session_info {
+ /* options */
+ unsigned char flags;
+ unsigned char nodev;
+ unsigned short debug;
+ unsigned int afid;
+ unsigned int cache;
+#ifdef CONFIG_9P_FSCACHE
+ char *cachetag;
+ struct fscache_volume *fscache;
+#endif
+
+ char *uname; /* user name to mount as */
+ char *aname; /* name of remote hierarchy being mounted */
+ unsigned int maxdata; /* max data for client interface */
+ kuid_t dfltuid; /* default uid/muid for legacy support */
+ kgid_t dfltgid; /* default gid for legacy support */
+ kuid_t uid; /* if ACCESS_SINGLE, the uid that has access */
+ struct p9_client *clnt; /* 9p client */
+ struct list_head slist; /* list of sessions registered with v9fs */
+ struct rw_semaphore rename_sem;
+ long session_lock_timeout; /* retry interval for blocking locks */
+};
+
+/* cache_validity flags */
+#define V9FS_INO_INVALID_ATTR 0x01
+
+struct v9fs_inode {
+ struct netfs_inode netfs; /* Netfslib context and vfs inode */
+ struct p9_qid qid;
+ unsigned int cache_validity;
+ struct p9_fid *writeback_fid;
+ struct mutex v_mutex;
+};
+
+static inline struct v9fs_inode *V9FS_I(const struct inode *inode)
+{
+ return container_of(inode, struct v9fs_inode, netfs.inode);
+}
+
+static inline struct fscache_cookie *v9fs_inode_cookie(struct v9fs_inode *v9inode)
+{
+#ifdef CONFIG_9P_FSCACHE
+ return netfs_i_cookie(&v9inode->netfs);
+#else
+ return NULL;
+#endif
+}
+
+static inline struct fscache_volume *v9fs_session_cache(struct v9fs_session_info *v9ses)
+{
+#ifdef CONFIG_9P_FSCACHE
+ return v9ses->fscache;
+#else
+ return NULL;
+#endif
+}
+
+
+extern int v9fs_show_options(struct seq_file *m, struct dentry *root);
+
+struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
+ const char *dev_name, char *data);
+extern void v9fs_session_close(struct v9fs_session_info *v9ses);
+extern void v9fs_session_cancel(struct v9fs_session_info *v9ses);
+extern void v9fs_session_begin_cancel(struct v9fs_session_info *v9ses);
+extern struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
+ unsigned int flags);
+extern int v9fs_vfs_unlink(struct inode *i, struct dentry *d);
+extern int v9fs_vfs_rmdir(struct inode *i, struct dentry *d);
+extern int v9fs_vfs_rename(struct user_namespace *mnt_userns,
+ struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry,
+ unsigned int flags);
+extern struct inode *v9fs_inode_from_fid(struct v9fs_session_info *v9ses,
+ struct p9_fid *fid,
+ struct super_block *sb, int new);
+extern const struct inode_operations v9fs_dir_inode_operations_dotl;
+extern const struct inode_operations v9fs_file_inode_operations_dotl;
+extern const struct inode_operations v9fs_symlink_inode_operations_dotl;
+extern const struct netfs_request_ops v9fs_req_ops;
+extern struct inode *v9fs_inode_from_fid_dotl(struct v9fs_session_info *v9ses,
+ struct p9_fid *fid,
+ struct super_block *sb, int new);
+
+/* other default globals */
+#define V9FS_PORT 564
+#define V9FS_DEFUSER "nobody"
+#define V9FS_DEFANAME ""
+#define V9FS_DEFUID KUIDT_INIT(-2)
+#define V9FS_DEFGID KGIDT_INIT(-2)
+
+static inline struct v9fs_session_info *v9fs_inode2v9ses(struct inode *inode)
+{
+ return inode->i_sb->s_fs_info;
+}
+
+static inline struct v9fs_session_info *v9fs_dentry2v9ses(struct dentry *dentry)
+{
+ return dentry->d_sb->s_fs_info;
+}
+
+static inline int v9fs_proto_dotu(struct v9fs_session_info *v9ses)
+{
+ return v9ses->flags & V9FS_PROTO_2000U;
+}
+
+static inline int v9fs_proto_dotl(struct v9fs_session_info *v9ses)
+{
+ return v9ses->flags & V9FS_PROTO_2000L;
+}
+
+/**
+ * v9fs_get_inode_from_fid - Helper routine to populate an inode by
+ * issuing a attribute request
+ * @v9ses: session information
+ * @fid: fid to issue attribute request for
+ * @sb: superblock on which to create inode
+ *
+ */
+static inline struct inode *
+v9fs_get_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
+ struct super_block *sb)
+{
+ if (v9fs_proto_dotl(v9ses))
+ return v9fs_inode_from_fid_dotl(v9ses, fid, sb, 0);
+ else
+ return v9fs_inode_from_fid(v9ses, fid, sb, 0);
+}
+
+/**
+ * v9fs_get_new_inode_from_fid - Helper routine to populate an inode by
+ * issuing a attribute request
+ * @v9ses: session information
+ * @fid: fid to issue attribute request for
+ * @sb: superblock on which to create inode
+ *
+ */
+static inline struct inode *
+v9fs_get_new_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
+ struct super_block *sb)
+{
+ if (v9fs_proto_dotl(v9ses))
+ return v9fs_inode_from_fid_dotl(v9ses, fid, sb, 1);
+ else
+ return v9fs_inode_from_fid(v9ses, fid, sb, 1);
+}
+
+#endif
diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h
new file mode 100644
index 000000000..bc417da7e
--- /dev/null
+++ b/fs/9p/v9fs_vfs.h
@@ -0,0 +1,92 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * V9FS VFS extensions.
+ *
+ * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ */
+#ifndef FS_9P_V9FS_VFS_H
+#define FS_9P_V9FS_VFS_H
+
+/* plan9 semantics are that created files are implicitly opened.
+ * But linux semantics are that you call create, then open.
+ * the plan9 approach is superior as it provides an atomic
+ * open.
+ * we track the create fid here. When the file is opened, if fidopen is
+ * non-zero, we use the fid and can skip some steps.
+ * there may be a better way to do this, but I don't know it.
+ * one BAD way is to clunk the fid on create, then open it again:
+ * you lose the atomicity of file open
+ */
+
+/* special case:
+ * unlink calls remove, which is an implicit clunk. So we have to track
+ * that kind of thing so that we don't try to clunk a dead fid.
+ */
+#define P9_LOCK_TIMEOUT (30*HZ)
+
+/* flags for v9fs_stat2inode() & v9fs_stat2inode_dotl() */
+#define V9FS_STAT2INODE_KEEP_ISIZE 1
+
+extern struct file_system_type v9fs_fs_type;
+extern const struct address_space_operations v9fs_addr_operations;
+extern const struct file_operations v9fs_file_operations;
+extern const struct file_operations v9fs_file_operations_dotl;
+extern const struct file_operations v9fs_dir_operations;
+extern const struct file_operations v9fs_dir_operations_dotl;
+extern const struct dentry_operations v9fs_dentry_operations;
+extern const struct dentry_operations v9fs_cached_dentry_operations;
+extern const struct file_operations v9fs_cached_file_operations;
+extern const struct file_operations v9fs_cached_file_operations_dotl;
+extern const struct file_operations v9fs_mmap_file_operations;
+extern const struct file_operations v9fs_mmap_file_operations_dotl;
+extern struct kmem_cache *v9fs_inode_cache;
+
+struct inode *v9fs_alloc_inode(struct super_block *sb);
+void v9fs_free_inode(struct inode *inode);
+struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode,
+ dev_t rdev);
+int v9fs_init_inode(struct v9fs_session_info *v9ses,
+ struct inode *inode, umode_t mode, dev_t rdev);
+void v9fs_evict_inode(struct inode *inode);
+ino_t v9fs_qid2ino(struct p9_qid *qid);
+void v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode,
+ struct super_block *sb, unsigned int flags);
+void v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode,
+ unsigned int flags);
+int v9fs_dir_release(struct inode *inode, struct file *filp);
+int v9fs_file_open(struct inode *inode, struct file *file);
+void v9fs_inode2stat(struct inode *inode, struct p9_wstat *stat);
+int v9fs_uflags2omode(int uflags, int extended);
+
+void v9fs_blank_wstat(struct p9_wstat *wstat);
+int v9fs_vfs_setattr_dotl(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *iattr);
+int v9fs_file_fsync_dotl(struct file *filp, loff_t start, loff_t end,
+ int datasync);
+int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode);
+int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode);
+static inline void v9fs_invalidate_inode_attr(struct inode *inode)
+{
+ struct v9fs_inode *v9inode;
+
+ v9inode = V9FS_I(inode);
+ v9inode->cache_validity |= V9FS_INO_INVALID_ATTR;
+}
+
+int v9fs_open_to_dotl_flags(int flags);
+
+static inline void v9fs_i_size_write(struct inode *inode, loff_t i_size)
+{
+ /*
+ * 32-bit need the lock, concurrent updates could break the
+ * sequences and make i_size_read() loop forever.
+ * 64-bit updates are atomic and can skip the locking.
+ */
+ if (sizeof(i_size) > sizeof(long))
+ spin_lock(&inode->i_lock);
+ i_size_write(inode, i_size);
+ if (sizeof(i_size) > sizeof(long))
+ spin_unlock(&inode->i_lock);
+}
+#endif
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
new file mode 100644
index 000000000..a19891015
--- /dev/null
+++ b/fs/9p/vfs_addr.c
@@ -0,0 +1,360 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * This file contians vfs address (mmap) ops for 9P2000.
+ *
+ * Copyright (C) 2005 by Eric Van Hensbergen <ericvh@gmail.com>
+ * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/inet.h>
+#include <linux/pagemap.h>
+#include <linux/idr.h>
+#include <linux/sched.h>
+#include <linux/swap.h>
+#include <linux/uio.h>
+#include <linux/netfs.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "cache.h"
+#include "fid.h"
+
+/**
+ * v9fs_issue_read - Issue a read from 9P
+ * @subreq: The read to make
+ */
+static void v9fs_issue_read(struct netfs_io_subrequest *subreq)
+{
+ struct netfs_io_request *rreq = subreq->rreq;
+ struct p9_fid *fid = rreq->netfs_priv;
+ struct iov_iter to;
+ loff_t pos = subreq->start + subreq->transferred;
+ size_t len = subreq->len - subreq->transferred;
+ int total, err;
+
+ iov_iter_xarray(&to, ITER_DEST, &rreq->mapping->i_pages, pos, len);
+
+ total = p9_client_read(fid, pos, &to, &err);
+
+ /* if we just extended the file size, any portion not in
+ * cache won't be on server and is zeroes */
+ __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+
+ netfs_subreq_terminated(subreq, err ?: total, false);
+}
+
+/**
+ * v9fs_init_request - Initialise a read request
+ * @rreq: The read request
+ * @file: The file being read from
+ */
+static int v9fs_init_request(struct netfs_io_request *rreq, struct file *file)
+{
+ struct inode *inode = file_inode(file);
+ struct v9fs_inode *v9inode = V9FS_I(inode);
+ struct p9_fid *fid = file->private_data;
+
+ BUG_ON(!fid);
+
+ /* we might need to read from a fid that was opened write-only
+ * for read-modify-write of page cache, use the writeback fid
+ * for that */
+ if (rreq->origin == NETFS_READ_FOR_WRITE &&
+ (fid->mode & O_ACCMODE) == O_WRONLY) {
+ fid = v9inode->writeback_fid;
+ BUG_ON(!fid);
+ }
+
+ p9_fid_get(fid);
+ rreq->netfs_priv = fid;
+ return 0;
+}
+
+/**
+ * v9fs_free_request - Cleanup request initialized by v9fs_init_rreq
+ * @rreq: The I/O request to clean up
+ */
+static void v9fs_free_request(struct netfs_io_request *rreq)
+{
+ struct p9_fid *fid = rreq->netfs_priv;
+
+ p9_fid_put(fid);
+}
+
+/**
+ * v9fs_begin_cache_operation - Begin a cache operation for a read
+ * @rreq: The read request
+ */
+static int v9fs_begin_cache_operation(struct netfs_io_request *rreq)
+{
+#ifdef CONFIG_9P_FSCACHE
+ struct fscache_cookie *cookie = v9fs_inode_cookie(V9FS_I(rreq->inode));
+
+ return fscache_begin_read_operation(&rreq->cache_resources, cookie);
+#else
+ return -ENOBUFS;
+#endif
+}
+
+const struct netfs_request_ops v9fs_req_ops = {
+ .init_request = v9fs_init_request,
+ .free_request = v9fs_free_request,
+ .begin_cache_operation = v9fs_begin_cache_operation,
+ .issue_read = v9fs_issue_read,
+};
+
+/**
+ * v9fs_release_folio - release the private state associated with a folio
+ * @folio: The folio to be released
+ * @gfp: The caller's allocation restrictions
+ *
+ * Returns true if the page can be released, false otherwise.
+ */
+
+static bool v9fs_release_folio(struct folio *folio, gfp_t gfp)
+{
+ struct inode *inode = folio_inode(folio);
+
+ if (folio_test_private(folio))
+ return false;
+#ifdef CONFIG_9P_FSCACHE
+ if (folio_test_fscache(folio)) {
+ if (current_is_kswapd() || !(gfp & __GFP_FS))
+ return false;
+ folio_wait_fscache(folio);
+ }
+#endif
+ fscache_note_page_release(v9fs_inode_cookie(V9FS_I(inode)));
+ return true;
+}
+
+static void v9fs_invalidate_folio(struct folio *folio, size_t offset,
+ size_t length)
+{
+ folio_wait_fscache(folio);
+}
+
+static void v9fs_write_to_cache_done(void *priv, ssize_t transferred_or_error,
+ bool was_async)
+{
+ struct v9fs_inode *v9inode = priv;
+ __le32 version;
+
+ if (IS_ERR_VALUE(transferred_or_error) &&
+ transferred_or_error != -ENOBUFS) {
+ version = cpu_to_le32(v9inode->qid.version);
+ fscache_invalidate(v9fs_inode_cookie(v9inode), &version,
+ i_size_read(&v9inode->netfs.inode), 0);
+ }
+}
+
+static int v9fs_vfs_write_folio_locked(struct folio *folio)
+{
+ struct inode *inode = folio_inode(folio);
+ struct v9fs_inode *v9inode = V9FS_I(inode);
+ struct fscache_cookie *cookie = v9fs_inode_cookie(v9inode);
+ loff_t start = folio_pos(folio);
+ loff_t i_size = i_size_read(inode);
+ struct iov_iter from;
+ size_t len = folio_size(folio);
+ int err;
+
+ if (start >= i_size)
+ return 0; /* Simultaneous truncation occurred */
+
+ len = min_t(loff_t, i_size - start, len);
+
+ iov_iter_xarray(&from, ITER_SOURCE, &folio_mapping(folio)->i_pages, start, len);
+
+ /* We should have writeback_fid always set */
+ BUG_ON(!v9inode->writeback_fid);
+
+ folio_wait_fscache(folio);
+ folio_start_writeback(folio);
+
+ p9_client_write(v9inode->writeback_fid, start, &from, &err);
+
+ if (err == 0 &&
+ fscache_cookie_enabled(cookie) &&
+ test_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags)) {
+ folio_start_fscache(folio);
+ fscache_write_to_cache(v9fs_inode_cookie(v9inode),
+ folio_mapping(folio), start, len, i_size,
+ v9fs_write_to_cache_done, v9inode,
+ true);
+ }
+
+ folio_end_writeback(folio);
+ return err;
+}
+
+static int v9fs_vfs_writepage(struct page *page, struct writeback_control *wbc)
+{
+ struct folio *folio = page_folio(page);
+ int retval;
+
+ p9_debug(P9_DEBUG_VFS, "folio %p\n", folio);
+
+ retval = v9fs_vfs_write_folio_locked(folio);
+ if (retval < 0) {
+ if (retval == -EAGAIN) {
+ folio_redirty_for_writepage(wbc, folio);
+ retval = 0;
+ } else {
+ mapping_set_error(folio_mapping(folio), retval);
+ }
+ } else
+ retval = 0;
+
+ folio_unlock(folio);
+ return retval;
+}
+
+static int v9fs_launder_folio(struct folio *folio)
+{
+ int retval;
+
+ if (folio_clear_dirty_for_io(folio)) {
+ retval = v9fs_vfs_write_folio_locked(folio);
+ if (retval)
+ return retval;
+ }
+ folio_wait_fscache(folio);
+ return 0;
+}
+
+/**
+ * v9fs_direct_IO - 9P address space operation for direct I/O
+ * @iocb: target I/O control block
+ * @iter: The data/buffer to use
+ *
+ * The presence of v9fs_direct_IO() in the address space ops vector
+ * allowes open() O_DIRECT flags which would have failed otherwise.
+ *
+ * In the non-cached mode, we shunt off direct read and write requests before
+ * the VFS gets them, so this method should never be called.
+ *
+ * Direct IO is not 'yet' supported in the cached mode. Hence when
+ * this routine is called through generic_file_aio_read(), the read/write fails
+ * with an error.
+ *
+ */
+static ssize_t
+v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
+{
+ struct file *file = iocb->ki_filp;
+ loff_t pos = iocb->ki_pos;
+ ssize_t n;
+ int err = 0;
+
+ if (iov_iter_rw(iter) == WRITE) {
+ n = p9_client_write(file->private_data, pos, iter, &err);
+ if (n) {
+ struct inode *inode = file_inode(file);
+ loff_t i_size = i_size_read(inode);
+
+ if (pos + n > i_size)
+ inode_add_bytes(inode, pos + n - i_size);
+ }
+ } else {
+ n = p9_client_read(file->private_data, pos, iter, &err);
+ }
+ return n ? n : err;
+}
+
+static int v9fs_write_begin(struct file *filp, struct address_space *mapping,
+ loff_t pos, unsigned int len,
+ struct page **subpagep, void **fsdata)
+{
+ int retval;
+ struct folio *folio;
+ struct v9fs_inode *v9inode = V9FS_I(mapping->host);
+
+ p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping);
+
+ BUG_ON(!v9inode->writeback_fid);
+
+ /* Prefetch area to be written into the cache if we're caching this
+ * file. We need to do this before we get a lock on the page in case
+ * there's more than one writer competing for the same cache block.
+ */
+ retval = netfs_write_begin(&v9inode->netfs, filp, mapping, pos, len, &folio, fsdata);
+ if (retval < 0)
+ return retval;
+
+ *subpagep = &folio->page;
+ return retval;
+}
+
+static int v9fs_write_end(struct file *filp, struct address_space *mapping,
+ loff_t pos, unsigned int len, unsigned int copied,
+ struct page *subpage, void *fsdata)
+{
+ loff_t last_pos = pos + copied;
+ struct folio *folio = page_folio(subpage);
+ struct inode *inode = mapping->host;
+ struct v9fs_inode *v9inode = V9FS_I(inode);
+
+ p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping);
+
+ if (!folio_test_uptodate(folio)) {
+ if (unlikely(copied < len)) {
+ copied = 0;
+ goto out;
+ }
+
+ folio_mark_uptodate(folio);
+ }
+
+ /*
+ * No need to use i_size_read() here, the i_size
+ * cannot change under us because we hold the i_mutex.
+ */
+ if (last_pos > inode->i_size) {
+ inode_add_bytes(inode, last_pos - inode->i_size);
+ i_size_write(inode, last_pos);
+ fscache_update_cookie(v9fs_inode_cookie(v9inode), NULL, &last_pos);
+ }
+ folio_mark_dirty(folio);
+out:
+ folio_unlock(folio);
+ folio_put(folio);
+
+ return copied;
+}
+
+#ifdef CONFIG_9P_FSCACHE
+/*
+ * Mark a page as having been made dirty and thus needing writeback. We also
+ * need to pin the cache object to write back to.
+ */
+static bool v9fs_dirty_folio(struct address_space *mapping, struct folio *folio)
+{
+ struct v9fs_inode *v9inode = V9FS_I(mapping->host);
+
+ return fscache_dirty_folio(mapping, folio, v9fs_inode_cookie(v9inode));
+}
+#else
+#define v9fs_dirty_folio filemap_dirty_folio
+#endif
+
+const struct address_space_operations v9fs_addr_operations = {
+ .read_folio = netfs_read_folio,
+ .readahead = netfs_readahead,
+ .dirty_folio = v9fs_dirty_folio,
+ .writepage = v9fs_vfs_writepage,
+ .write_begin = v9fs_write_begin,
+ .write_end = v9fs_write_end,
+ .release_folio = v9fs_release_folio,
+ .invalidate_folio = v9fs_invalidate_folio,
+ .launder_folio = v9fs_launder_folio,
+ .direct_IO = v9fs_direct_IO,
+};
diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
new file mode 100644
index 000000000..f89f01734
--- /dev/null
+++ b/fs/9p/vfs_dentry.c
@@ -0,0 +1,109 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * This file contians vfs dentry ops for the 9P2000 protocol.
+ *
+ * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/pagemap.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/inet.h>
+#include <linux/namei.h>
+#include <linux/idr.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+
+/**
+ * v9fs_cached_dentry_delete - called when dentry refcount equals 0
+ * @dentry: dentry in question
+ *
+ */
+static int v9fs_cached_dentry_delete(const struct dentry *dentry)
+{
+ p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p)\n",
+ dentry, dentry);
+
+ /* Don't cache negative dentries */
+ if (d_really_is_negative(dentry))
+ return 1;
+ return 0;
+}
+
+/**
+ * v9fs_dentry_release - called when dentry is going to be freed
+ * @dentry: dentry that is being release
+ *
+ */
+
+static void v9fs_dentry_release(struct dentry *dentry)
+{
+ struct hlist_node *p, *n;
+
+ p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p)\n",
+ dentry, dentry);
+ hlist_for_each_safe(p, n, (struct hlist_head *)&dentry->d_fsdata)
+ p9_fid_put(hlist_entry(p, struct p9_fid, dlist));
+ dentry->d_fsdata = NULL;
+}
+
+static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
+{
+ struct p9_fid *fid;
+ struct inode *inode;
+ struct v9fs_inode *v9inode;
+
+ if (flags & LOOKUP_RCU)
+ return -ECHILD;
+
+ inode = d_inode(dentry);
+ if (!inode)
+ goto out_valid;
+
+ v9inode = V9FS_I(inode);
+ if (v9inode->cache_validity & V9FS_INO_INVALID_ATTR) {
+ int retval;
+ struct v9fs_session_info *v9ses;
+
+ fid = v9fs_fid_lookup(dentry);
+ if (IS_ERR(fid))
+ return PTR_ERR(fid);
+
+ v9ses = v9fs_inode2v9ses(inode);
+ if (v9fs_proto_dotl(v9ses))
+ retval = v9fs_refresh_inode_dotl(fid, inode);
+ else
+ retval = v9fs_refresh_inode(fid, inode);
+ p9_fid_put(fid);
+
+ if (retval == -ENOENT)
+ return 0;
+ if (retval < 0)
+ return retval;
+ }
+out_valid:
+ return 1;
+}
+
+const struct dentry_operations v9fs_cached_dentry_operations = {
+ .d_revalidate = v9fs_lookup_revalidate,
+ .d_weak_revalidate = v9fs_lookup_revalidate,
+ .d_delete = v9fs_cached_dentry_delete,
+ .d_release = v9fs_dentry_release,
+};
+
+const struct dentry_operations v9fs_dentry_operations = {
+ .d_delete = always_delete_dentry,
+ .d_release = v9fs_dentry_release,
+};
diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c
new file mode 100644
index 000000000..3bb95adc9
--- /dev/null
+++ b/fs/9p/vfs_dir.c
@@ -0,0 +1,250 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * This file contains vfs directory ops for the 9P2000 protocol.
+ *
+ * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/inet.h>
+#include <linux/idr.h>
+#include <linux/slab.h>
+#include <linux/uio.h>
+#include <linux/fscache.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+
+/**
+ * struct p9_rdir - readdir accounting
+ * @head: start offset of current dirread buffer
+ * @tail: end offset of current dirread buffer
+ * @buf: dirread buffer
+ *
+ * private structure for keeping track of readdir
+ * allocated on demand
+ */
+
+struct p9_rdir {
+ int head;
+ int tail;
+ uint8_t buf[];
+};
+
+/**
+ * dt_type - return file type
+ * @mistat: mistat structure
+ *
+ */
+
+static inline int dt_type(struct p9_wstat *mistat)
+{
+ unsigned long perm = mistat->mode;
+ int rettype = DT_REG;
+
+ if (perm & P9_DMDIR)
+ rettype = DT_DIR;
+ if (perm & P9_DMSYMLINK)
+ rettype = DT_LNK;
+
+ return rettype;
+}
+
+/**
+ * v9fs_alloc_rdir_buf - Allocate buffer used for read and readdir
+ * @filp: opened file structure
+ * @buflen: Length in bytes of buffer to allocate
+ *
+ */
+
+static struct p9_rdir *v9fs_alloc_rdir_buf(struct file *filp, int buflen)
+{
+ struct p9_fid *fid = filp->private_data;
+
+ if (!fid->rdir)
+ fid->rdir = kzalloc(sizeof(struct p9_rdir) + buflen, GFP_KERNEL);
+ return fid->rdir;
+}
+
+/**
+ * v9fs_dir_readdir - iterate through a directory
+ * @file: opened file structure
+ * @ctx: actor we feed the entries to
+ *
+ */
+
+static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx)
+{
+ bool over;
+ struct p9_wstat st;
+ int err = 0;
+ struct p9_fid *fid;
+ int buflen;
+ struct p9_rdir *rdir;
+ struct kvec kvec;
+
+ p9_debug(P9_DEBUG_VFS, "name %pD\n", file);
+ fid = file->private_data;
+
+ buflen = fid->clnt->msize - P9_IOHDRSZ;
+
+ rdir = v9fs_alloc_rdir_buf(file, buflen);
+ if (!rdir)
+ return -ENOMEM;
+ kvec.iov_base = rdir->buf;
+ kvec.iov_len = buflen;
+
+ while (1) {
+ if (rdir->tail == rdir->head) {
+ struct iov_iter to;
+ int n;
+
+ iov_iter_kvec(&to, ITER_DEST, &kvec, 1, buflen);
+ n = p9_client_read(file->private_data, ctx->pos, &to,
+ &err);
+ if (err)
+ return err;
+ if (n == 0)
+ return 0;
+
+ rdir->head = 0;
+ rdir->tail = n;
+ }
+ while (rdir->head < rdir->tail) {
+ err = p9stat_read(fid->clnt, rdir->buf + rdir->head,
+ rdir->tail - rdir->head, &st);
+ if (err <= 0) {
+ p9_debug(P9_DEBUG_VFS, "returned %d\n", err);
+ return -EIO;
+ }
+
+ over = !dir_emit(ctx, st.name, strlen(st.name),
+ v9fs_qid2ino(&st.qid), dt_type(&st));
+ p9stat_free(&st);
+ if (over)
+ return 0;
+
+ rdir->head += err;
+ ctx->pos += err;
+ }
+ }
+}
+
+/**
+ * v9fs_dir_readdir_dotl - iterate through a directory
+ * @file: opened file structure
+ * @ctx: actor we feed the entries to
+ *
+ */
+static int v9fs_dir_readdir_dotl(struct file *file, struct dir_context *ctx)
+{
+ int err = 0;
+ struct p9_fid *fid;
+ int buflen;
+ struct p9_rdir *rdir;
+ struct p9_dirent curdirent;
+
+ p9_debug(P9_DEBUG_VFS, "name %pD\n", file);
+ fid = file->private_data;
+
+ buflen = fid->clnt->msize - P9_READDIRHDRSZ;
+
+ rdir = v9fs_alloc_rdir_buf(file, buflen);
+ if (!rdir)
+ return -ENOMEM;
+
+ while (1) {
+ if (rdir->tail == rdir->head) {
+ err = p9_client_readdir(fid, rdir->buf, buflen,
+ ctx->pos);
+ if (err <= 0)
+ return err;
+
+ rdir->head = 0;
+ rdir->tail = err;
+ }
+
+ while (rdir->head < rdir->tail) {
+
+ err = p9dirent_read(fid->clnt, rdir->buf + rdir->head,
+ rdir->tail - rdir->head,
+ &curdirent);
+ if (err < 0) {
+ p9_debug(P9_DEBUG_VFS, "returned %d\n", err);
+ return -EIO;
+ }
+
+ if (!dir_emit(ctx, curdirent.d_name,
+ strlen(curdirent.d_name),
+ v9fs_qid2ino(&curdirent.qid),
+ curdirent.d_type))
+ return 0;
+
+ ctx->pos = curdirent.d_off;
+ rdir->head += err;
+ }
+ }
+}
+
+
+/**
+ * v9fs_dir_release - close a directory
+ * @inode: inode of the directory
+ * @filp: file pointer to a directory
+ *
+ */
+
+int v9fs_dir_release(struct inode *inode, struct file *filp)
+{
+ struct v9fs_inode *v9inode = V9FS_I(inode);
+ struct p9_fid *fid;
+ __le32 version;
+ loff_t i_size;
+
+ fid = filp->private_data;
+ p9_debug(P9_DEBUG_VFS, "inode: %p filp: %p fid: %d\n",
+ inode, filp, fid ? fid->fid : -1);
+ if (fid) {
+ spin_lock(&inode->i_lock);
+ hlist_del(&fid->ilist);
+ spin_unlock(&inode->i_lock);
+ p9_fid_put(fid);
+ }
+
+ if ((filp->f_mode & FMODE_WRITE)) {
+ version = cpu_to_le32(v9inode->qid.version);
+ i_size = i_size_read(inode);
+ fscache_unuse_cookie(v9fs_inode_cookie(v9inode),
+ &version, &i_size);
+ } else {
+ fscache_unuse_cookie(v9fs_inode_cookie(v9inode), NULL, NULL);
+ }
+ return 0;
+}
+
+const struct file_operations v9fs_dir_operations = {
+ .read = generic_read_dir,
+ .llseek = generic_file_llseek,
+ .iterate_shared = v9fs_dir_readdir,
+ .open = v9fs_file_open,
+ .release = v9fs_dir_release,
+};
+
+const struct file_operations v9fs_dir_operations_dotl = {
+ .read = generic_read_dir,
+ .llseek = generic_file_llseek,
+ .iterate_shared = v9fs_dir_readdir_dotl,
+ .open = v9fs_file_open,
+ .release = v9fs_dir_release,
+ .fsync = v9fs_file_fsync_dotl,
+};
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
new file mode 100644
index 000000000..aec43ba83
--- /dev/null
+++ b/fs/9p/vfs_file.c
@@ -0,0 +1,711 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * This file contians vfs file ops for 9P2000.
+ *
+ * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/file.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/inet.h>
+#include <linux/list.h>
+#include <linux/pagemap.h>
+#include <linux/utsname.h>
+#include <linux/uaccess.h>
+#include <linux/idr.h>
+#include <linux/uio.h>
+#include <linux/slab.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+#include "cache.h"
+
+static const struct vm_operations_struct v9fs_file_vm_ops;
+static const struct vm_operations_struct v9fs_mmap_file_vm_ops;
+
+/**
+ * v9fs_file_open - open a file (or directory)
+ * @inode: inode to be opened
+ * @file: file being opened
+ *
+ */
+
+int v9fs_file_open(struct inode *inode, struct file *file)
+{
+ int err;
+ struct v9fs_inode *v9inode;
+ struct v9fs_session_info *v9ses;
+ struct p9_fid *fid, *writeback_fid;
+ int omode;
+
+ p9_debug(P9_DEBUG_VFS, "inode: %p file: %p\n", inode, file);
+ v9inode = V9FS_I(inode);
+ v9ses = v9fs_inode2v9ses(inode);
+ if (v9fs_proto_dotl(v9ses))
+ omode = v9fs_open_to_dotl_flags(file->f_flags);
+ else
+ omode = v9fs_uflags2omode(file->f_flags,
+ v9fs_proto_dotu(v9ses));
+ fid = file->private_data;
+ if (!fid) {
+ fid = v9fs_fid_clone(file_dentry(file));
+ if (IS_ERR(fid))
+ return PTR_ERR(fid);
+
+ err = p9_client_open(fid, omode);
+ if (err < 0) {
+ p9_fid_put(fid);
+ return err;
+ }
+ if ((file->f_flags & O_APPEND) &&
+ (!v9fs_proto_dotu(v9ses) && !v9fs_proto_dotl(v9ses)))
+ generic_file_llseek(file, 0, SEEK_END);
+
+ file->private_data = fid;
+ }
+
+ mutex_lock(&v9inode->v_mutex);
+ if ((v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) &&
+ !v9inode->writeback_fid &&
+ ((file->f_flags & O_ACCMODE) != O_RDONLY)) {
+ /*
+ * clone a fid and add it to writeback_fid
+ * we do it during open time instead of
+ * page dirty time via write_begin/page_mkwrite
+ * because we want write after unlink usecase
+ * to work.
+ */
+ writeback_fid = v9fs_writeback_fid(file_dentry(file));
+ if (IS_ERR(writeback_fid)) {
+ err = PTR_ERR(writeback_fid);
+ mutex_unlock(&v9inode->v_mutex);
+ goto out_error;
+ }
+ v9inode->writeback_fid = (void *) writeback_fid;
+ }
+ mutex_unlock(&v9inode->v_mutex);
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
+ fscache_use_cookie(v9fs_inode_cookie(v9inode),
+ file->f_mode & FMODE_WRITE);
+ v9fs_open_fid_add(inode, &fid);
+ return 0;
+out_error:
+ p9_fid_put(file->private_data);
+ file->private_data = NULL;
+ return err;
+}
+
+/**
+ * v9fs_file_lock - lock a file (or directory)
+ * @filp: file to be locked
+ * @cmd: lock command
+ * @fl: file lock structure
+ *
+ * Bugs: this looks like a local only lock, we should extend into 9P
+ * by using open exclusive
+ */
+
+static int v9fs_file_lock(struct file *filp, int cmd, struct file_lock *fl)
+{
+ struct inode *inode = file_inode(filp);
+
+ p9_debug(P9_DEBUG_VFS, "filp: %p lock: %p\n", filp, fl);
+
+ if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
+ filemap_write_and_wait(inode->i_mapping);
+ invalidate_mapping_pages(&inode->i_data, 0, -1);
+ }
+
+ return 0;
+}
+
+static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
+{
+ struct p9_flock flock;
+ struct p9_fid *fid;
+ uint8_t status = P9_LOCK_ERROR;
+ int res = 0;
+ unsigned char fl_type;
+ struct v9fs_session_info *v9ses;
+
+ fid = filp->private_data;
+ BUG_ON(fid == NULL);
+
+ BUG_ON((fl->fl_flags & FL_POSIX) != FL_POSIX);
+
+ res = locks_lock_file_wait(filp, fl);
+ if (res < 0)
+ goto out;
+
+ /* convert posix lock to p9 tlock args */
+ memset(&flock, 0, sizeof(flock));
+ /* map the lock type */
+ switch (fl->fl_type) {
+ case F_RDLCK:
+ flock.type = P9_LOCK_TYPE_RDLCK;
+ break;
+ case F_WRLCK:
+ flock.type = P9_LOCK_TYPE_WRLCK;
+ break;
+ case F_UNLCK:
+ flock.type = P9_LOCK_TYPE_UNLCK;
+ break;
+ }
+ flock.start = fl->fl_start;
+ if (fl->fl_end == OFFSET_MAX)
+ flock.length = 0;
+ else
+ flock.length = fl->fl_end - fl->fl_start + 1;
+ flock.proc_id = fl->fl_pid;
+ flock.client_id = fid->clnt->name;
+ if (IS_SETLKW(cmd))
+ flock.flags = P9_LOCK_FLAGS_BLOCK;
+
+ v9ses = v9fs_inode2v9ses(file_inode(filp));
+
+ /*
+ * if its a blocked request and we get P9_LOCK_BLOCKED as the status
+ * for lock request, keep on trying
+ */
+ for (;;) {
+ res = p9_client_lock_dotl(fid, &flock, &status);
+ if (res < 0)
+ goto out_unlock;
+
+ if (status != P9_LOCK_BLOCKED)
+ break;
+ if (status == P9_LOCK_BLOCKED && !IS_SETLKW(cmd))
+ break;
+ if (schedule_timeout_interruptible(v9ses->session_lock_timeout)
+ != 0)
+ break;
+ /*
+ * p9_client_lock_dotl overwrites flock.client_id with the
+ * server message, free and reuse the client name
+ */
+ if (flock.client_id != fid->clnt->name) {
+ kfree(flock.client_id);
+ flock.client_id = fid->clnt->name;
+ }
+ }
+
+ /* map 9p status to VFS status */
+ switch (status) {
+ case P9_LOCK_SUCCESS:
+ res = 0;
+ break;
+ case P9_LOCK_BLOCKED:
+ res = -EAGAIN;
+ break;
+ default:
+ WARN_ONCE(1, "unknown lock status code: %d\n", status);
+ fallthrough;
+ case P9_LOCK_ERROR:
+ case P9_LOCK_GRACE:
+ res = -ENOLCK;
+ break;
+ }
+
+out_unlock:
+ /*
+ * incase server returned error for lock request, revert
+ * it locally
+ */
+ if (res < 0 && fl->fl_type != F_UNLCK) {
+ fl_type = fl->fl_type;
+ fl->fl_type = F_UNLCK;
+ /* Even if this fails we want to return the remote error */
+ locks_lock_file_wait(filp, fl);
+ fl->fl_type = fl_type;
+ }
+ if (flock.client_id != fid->clnt->name)
+ kfree(flock.client_id);
+out:
+ return res;
+}
+
+static int v9fs_file_getlock(struct file *filp, struct file_lock *fl)
+{
+ struct p9_getlock glock;
+ struct p9_fid *fid;
+ int res = 0;
+
+ fid = filp->private_data;
+ BUG_ON(fid == NULL);
+
+ posix_test_lock(filp, fl);
+ /*
+ * if we have a conflicting lock locally, no need to validate
+ * with server
+ */
+ if (fl->fl_type != F_UNLCK)
+ return res;
+
+ /* convert posix lock to p9 tgetlock args */
+ memset(&glock, 0, sizeof(glock));
+ glock.type = P9_LOCK_TYPE_UNLCK;
+ glock.start = fl->fl_start;
+ if (fl->fl_end == OFFSET_MAX)
+ glock.length = 0;
+ else
+ glock.length = fl->fl_end - fl->fl_start + 1;
+ glock.proc_id = fl->fl_pid;
+ glock.client_id = fid->clnt->name;
+
+ res = p9_client_getlock_dotl(fid, &glock);
+ if (res < 0)
+ goto out;
+ /* map 9p lock type to os lock type */
+ switch (glock.type) {
+ case P9_LOCK_TYPE_RDLCK:
+ fl->fl_type = F_RDLCK;
+ break;
+ case P9_LOCK_TYPE_WRLCK:
+ fl->fl_type = F_WRLCK;
+ break;
+ case P9_LOCK_TYPE_UNLCK:
+ fl->fl_type = F_UNLCK;
+ break;
+ }
+ if (glock.type != P9_LOCK_TYPE_UNLCK) {
+ fl->fl_start = glock.start;
+ if (glock.length == 0)
+ fl->fl_end = OFFSET_MAX;
+ else
+ fl->fl_end = glock.start + glock.length - 1;
+ fl->fl_pid = -glock.proc_id;
+ }
+out:
+ if (glock.client_id != fid->clnt->name)
+ kfree(glock.client_id);
+ return res;
+}
+
+/**
+ * v9fs_file_lock_dotl - lock a file (or directory)
+ * @filp: file to be locked
+ * @cmd: lock command
+ * @fl: file lock structure
+ *
+ */
+
+static int v9fs_file_lock_dotl(struct file *filp, int cmd, struct file_lock *fl)
+{
+ struct inode *inode = file_inode(filp);
+ int ret = -ENOLCK;
+
+ p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %pD\n",
+ filp, cmd, fl, filp);
+
+ if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
+ filemap_write_and_wait(inode->i_mapping);
+ invalidate_mapping_pages(&inode->i_data, 0, -1);
+ }
+
+ if (IS_SETLK(cmd) || IS_SETLKW(cmd))
+ ret = v9fs_file_do_lock(filp, cmd, fl);
+ else if (IS_GETLK(cmd))
+ ret = v9fs_file_getlock(filp, fl);
+ else
+ ret = -EINVAL;
+ return ret;
+}
+
+/**
+ * v9fs_file_flock_dotl - lock a file
+ * @filp: file to be locked
+ * @cmd: lock command
+ * @fl: file lock structure
+ *
+ */
+
+static int v9fs_file_flock_dotl(struct file *filp, int cmd,
+ struct file_lock *fl)
+{
+ struct inode *inode = file_inode(filp);
+ int ret = -ENOLCK;
+
+ p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %pD\n",
+ filp, cmd, fl, filp);
+
+ if (!(fl->fl_flags & FL_FLOCK))
+ goto out_err;
+
+ if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
+ filemap_write_and_wait(inode->i_mapping);
+ invalidate_mapping_pages(&inode->i_data, 0, -1);
+ }
+ /* Convert flock to posix lock */
+ fl->fl_flags |= FL_POSIX;
+ fl->fl_flags ^= FL_FLOCK;
+
+ if (IS_SETLK(cmd) | IS_SETLKW(cmd))
+ ret = v9fs_file_do_lock(filp, cmd, fl);
+ else
+ ret = -EINVAL;
+out_err:
+ return ret;
+}
+
+/**
+ * v9fs_file_read_iter - read from a file
+ * @iocb: The operation parameters
+ * @to: The buffer to read into
+ *
+ */
+static ssize_t
+v9fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+ struct p9_fid *fid = iocb->ki_filp->private_data;
+ int ret, err = 0;
+
+ p9_debug(P9_DEBUG_VFS, "count %zu offset %lld\n",
+ iov_iter_count(to), iocb->ki_pos);
+
+ if (iocb->ki_filp->f_flags & O_NONBLOCK)
+ ret = p9_client_read_once(fid, iocb->ki_pos, to, &err);
+ else
+ ret = p9_client_read(fid, iocb->ki_pos, to, &err);
+ if (!ret)
+ return err;
+
+ iocb->ki_pos += ret;
+ return ret;
+}
+
+/**
+ * v9fs_file_write_iter - write to a file
+ * @iocb: The operation parameters
+ * @from: The data to write
+ *
+ */
+static ssize_t
+v9fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+ struct file *file = iocb->ki_filp;
+ ssize_t retval;
+ loff_t origin;
+ int err = 0;
+
+ retval = generic_write_checks(iocb, from);
+ if (retval <= 0)
+ return retval;
+
+ origin = iocb->ki_pos;
+ retval = p9_client_write(file->private_data, iocb->ki_pos, from, &err);
+ if (retval > 0) {
+ struct inode *inode = file_inode(file);
+ loff_t i_size;
+ unsigned long pg_start, pg_end;
+
+ pg_start = origin >> PAGE_SHIFT;
+ pg_end = (origin + retval - 1) >> PAGE_SHIFT;
+ if (inode->i_mapping && inode->i_mapping->nrpages)
+ invalidate_inode_pages2_range(inode->i_mapping,
+ pg_start, pg_end);
+ iocb->ki_pos += retval;
+ i_size = i_size_read(inode);
+ if (iocb->ki_pos > i_size) {
+ inode_add_bytes(inode, iocb->ki_pos - i_size);
+ /*
+ * Need to serialize against i_size_write() in
+ * v9fs_stat2inode()
+ */
+ v9fs_i_size_write(inode, iocb->ki_pos);
+ }
+ return retval;
+ }
+ return err;
+}
+
+static int v9fs_file_fsync(struct file *filp, loff_t start, loff_t end,
+ int datasync)
+{
+ struct p9_fid *fid;
+ struct inode *inode = filp->f_mapping->host;
+ struct p9_wstat wstat;
+ int retval;
+
+ retval = file_write_and_wait_range(filp, start, end);
+ if (retval)
+ return retval;
+
+ inode_lock(inode);
+ p9_debug(P9_DEBUG_VFS, "filp %p datasync %x\n", filp, datasync);
+
+ fid = filp->private_data;
+ v9fs_blank_wstat(&wstat);
+
+ retval = p9_client_wstat(fid, &wstat);
+ inode_unlock(inode);
+
+ return retval;
+}
+
+int v9fs_file_fsync_dotl(struct file *filp, loff_t start, loff_t end,
+ int datasync)
+{
+ struct p9_fid *fid;
+ struct inode *inode = filp->f_mapping->host;
+ int retval;
+
+ retval = file_write_and_wait_range(filp, start, end);
+ if (retval)
+ return retval;
+
+ inode_lock(inode);
+ p9_debug(P9_DEBUG_VFS, "filp %p datasync %x\n", filp, datasync);
+
+ fid = filp->private_data;
+
+ retval = p9_client_fsync(fid, datasync);
+ inode_unlock(inode);
+
+ return retval;
+}
+
+static int
+v9fs_file_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+ int retval;
+
+
+ retval = generic_file_mmap(filp, vma);
+ if (!retval)
+ vma->vm_ops = &v9fs_file_vm_ops;
+
+ return retval;
+}
+
+static int
+v9fs_mmap_file_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+ int retval;
+ struct inode *inode;
+ struct v9fs_inode *v9inode;
+ struct p9_fid *fid;
+
+ inode = file_inode(filp);
+ v9inode = V9FS_I(inode);
+ mutex_lock(&v9inode->v_mutex);
+ if (!v9inode->writeback_fid &&
+ (vma->vm_flags & VM_SHARED) &&
+ (vma->vm_flags & VM_WRITE)) {
+ /*
+ * clone a fid and add it to writeback_fid
+ * we do it during mmap instead of
+ * page dirty time via write_begin/page_mkwrite
+ * because we want write after unlink usecase
+ * to work.
+ */
+ fid = v9fs_writeback_fid(file_dentry(filp));
+ if (IS_ERR(fid)) {
+ retval = PTR_ERR(fid);
+ mutex_unlock(&v9inode->v_mutex);
+ return retval;
+ }
+ v9inode->writeback_fid = (void *) fid;
+ }
+ mutex_unlock(&v9inode->v_mutex);
+
+ retval = generic_file_mmap(filp, vma);
+ if (!retval)
+ vma->vm_ops = &v9fs_mmap_file_vm_ops;
+
+ return retval;
+}
+
+static vm_fault_t
+v9fs_vm_page_mkwrite(struct vm_fault *vmf)
+{
+ struct v9fs_inode *v9inode;
+ struct folio *folio = page_folio(vmf->page);
+ struct file *filp = vmf->vma->vm_file;
+ struct inode *inode = file_inode(filp);
+
+
+ p9_debug(P9_DEBUG_VFS, "folio %p fid %lx\n",
+ folio, (unsigned long)filp->private_data);
+
+ v9inode = V9FS_I(inode);
+
+ /* Wait for the page to be written to the cache before we allow it to
+ * be modified. We then assume the entire page will need writing back.
+ */
+#ifdef CONFIG_9P_FSCACHE
+ if (folio_test_fscache(folio) &&
+ folio_wait_fscache_killable(folio) < 0)
+ return VM_FAULT_NOPAGE;
+#endif
+
+ /* Update file times before taking page lock */
+ file_update_time(filp);
+
+ BUG_ON(!v9inode->writeback_fid);
+ if (folio_lock_killable(folio) < 0)
+ return VM_FAULT_RETRY;
+ if (folio_mapping(folio) != inode->i_mapping)
+ goto out_unlock;
+ folio_wait_stable(folio);
+
+ return VM_FAULT_LOCKED;
+out_unlock:
+ folio_unlock(folio);
+ return VM_FAULT_NOPAGE;
+}
+
+/**
+ * v9fs_mmap_file_read_iter - read from a file
+ * @iocb: The operation parameters
+ * @to: The buffer to read into
+ *
+ */
+static ssize_t
+v9fs_mmap_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+ /* TODO: Check if there are dirty pages */
+ return v9fs_file_read_iter(iocb, to);
+}
+
+/**
+ * v9fs_mmap_file_write_iter - write to a file
+ * @iocb: The operation parameters
+ * @from: The data to write
+ *
+ */
+static ssize_t
+v9fs_mmap_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+ /*
+ * TODO: invalidate mmaps on filp's inode between
+ * offset and offset+count
+ */
+ return v9fs_file_write_iter(iocb, from);
+}
+
+static void v9fs_mmap_vm_close(struct vm_area_struct *vma)
+{
+ struct inode *inode;
+
+ struct writeback_control wbc = {
+ .nr_to_write = LONG_MAX,
+ .sync_mode = WB_SYNC_ALL,
+ .range_start = (loff_t)vma->vm_pgoff * PAGE_SIZE,
+ /* absolute end, byte at end included */
+ .range_end = (loff_t)vma->vm_pgoff * PAGE_SIZE +
+ (vma->vm_end - vma->vm_start - 1),
+ };
+
+ if (!(vma->vm_flags & VM_SHARED))
+ return;
+
+ p9_debug(P9_DEBUG_VFS, "9p VMA close, %p, flushing", vma);
+
+ inode = file_inode(vma->vm_file);
+ filemap_fdatawrite_wbc(inode->i_mapping, &wbc);
+}
+
+
+static const struct vm_operations_struct v9fs_file_vm_ops = {
+ .fault = filemap_fault,
+ .map_pages = filemap_map_pages,
+ .page_mkwrite = v9fs_vm_page_mkwrite,
+};
+
+static const struct vm_operations_struct v9fs_mmap_file_vm_ops = {
+ .close = v9fs_mmap_vm_close,
+ .fault = filemap_fault,
+ .map_pages = filemap_map_pages,
+ .page_mkwrite = v9fs_vm_page_mkwrite,
+};
+
+
+const struct file_operations v9fs_cached_file_operations = {
+ .llseek = generic_file_llseek,
+ .read_iter = generic_file_read_iter,
+ .write_iter = generic_file_write_iter,
+ .open = v9fs_file_open,
+ .release = v9fs_dir_release,
+ .lock = v9fs_file_lock,
+ .mmap = v9fs_file_mmap,
+ .splice_read = generic_file_splice_read,
+ .splice_write = iter_file_splice_write,
+ .fsync = v9fs_file_fsync,
+};
+
+const struct file_operations v9fs_cached_file_operations_dotl = {
+ .llseek = generic_file_llseek,
+ .read_iter = generic_file_read_iter,
+ .write_iter = generic_file_write_iter,
+ .open = v9fs_file_open,
+ .release = v9fs_dir_release,
+ .lock = v9fs_file_lock_dotl,
+ .flock = v9fs_file_flock_dotl,
+ .mmap = v9fs_file_mmap,
+ .splice_read = generic_file_splice_read,
+ .splice_write = iter_file_splice_write,
+ .fsync = v9fs_file_fsync_dotl,
+};
+
+const struct file_operations v9fs_file_operations = {
+ .llseek = generic_file_llseek,
+ .read_iter = v9fs_file_read_iter,
+ .write_iter = v9fs_file_write_iter,
+ .open = v9fs_file_open,
+ .release = v9fs_dir_release,
+ .lock = v9fs_file_lock,
+ .mmap = generic_file_readonly_mmap,
+ .splice_read = generic_file_splice_read,
+ .splice_write = iter_file_splice_write,
+ .fsync = v9fs_file_fsync,
+};
+
+const struct file_operations v9fs_file_operations_dotl = {
+ .llseek = generic_file_llseek,
+ .read_iter = v9fs_file_read_iter,
+ .write_iter = v9fs_file_write_iter,
+ .open = v9fs_file_open,
+ .release = v9fs_dir_release,
+ .lock = v9fs_file_lock_dotl,
+ .flock = v9fs_file_flock_dotl,
+ .mmap = generic_file_readonly_mmap,
+ .splice_read = generic_file_splice_read,
+ .splice_write = iter_file_splice_write,
+ .fsync = v9fs_file_fsync_dotl,
+};
+
+const struct file_operations v9fs_mmap_file_operations = {
+ .llseek = generic_file_llseek,
+ .read_iter = v9fs_mmap_file_read_iter,
+ .write_iter = v9fs_mmap_file_write_iter,
+ .open = v9fs_file_open,
+ .release = v9fs_dir_release,
+ .lock = v9fs_file_lock,
+ .mmap = v9fs_mmap_file_mmap,
+ .splice_read = generic_file_splice_read,
+ .splice_write = iter_file_splice_write,
+ .fsync = v9fs_file_fsync,
+};
+
+const struct file_operations v9fs_mmap_file_operations_dotl = {
+ .llseek = generic_file_llseek,
+ .read_iter = v9fs_mmap_file_read_iter,
+ .write_iter = v9fs_mmap_file_write_iter,
+ .open = v9fs_file_open,
+ .release = v9fs_dir_release,
+ .lock = v9fs_file_lock_dotl,
+ .flock = v9fs_file_flock_dotl,
+ .mmap = v9fs_mmap_file_mmap,
+ .splice_read = generic_file_splice_read,
+ .splice_write = iter_file_splice_write,
+ .fsync = v9fs_file_fsync_dotl,
+};
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
new file mode 100644
index 000000000..4d1a4a8d9
--- /dev/null
+++ b/fs/9p/vfs_inode.c
@@ -0,0 +1,1465 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * This file contains vfs inode ops for the 9P2000 protocol.
+ *
+ * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/pagemap.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/inet.h>
+#include <linux/namei.h>
+#include <linux/idr.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/xattr.h>
+#include <linux/posix_acl.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+#include "cache.h"
+#include "xattr.h"
+#include "acl.h"
+
+static const struct inode_operations v9fs_dir_inode_operations;
+static const struct inode_operations v9fs_dir_inode_operations_dotu;
+static const struct inode_operations v9fs_file_inode_operations;
+static const struct inode_operations v9fs_symlink_inode_operations;
+
+/**
+ * unixmode2p9mode - convert unix mode bits to plan 9
+ * @v9ses: v9fs session information
+ * @mode: mode to convert
+ *
+ */
+
+static u32 unixmode2p9mode(struct v9fs_session_info *v9ses, umode_t mode)
+{
+ int res;
+
+ res = mode & 0777;
+ if (S_ISDIR(mode))
+ res |= P9_DMDIR;
+ if (v9fs_proto_dotu(v9ses)) {
+ if (v9ses->nodev == 0) {
+ if (S_ISSOCK(mode))
+ res |= P9_DMSOCKET;
+ if (S_ISFIFO(mode))
+ res |= P9_DMNAMEDPIPE;
+ if (S_ISBLK(mode))
+ res |= P9_DMDEVICE;
+ if (S_ISCHR(mode))
+ res |= P9_DMDEVICE;
+ }
+
+ if ((mode & S_ISUID) == S_ISUID)
+ res |= P9_DMSETUID;
+ if ((mode & S_ISGID) == S_ISGID)
+ res |= P9_DMSETGID;
+ if ((mode & S_ISVTX) == S_ISVTX)
+ res |= P9_DMSETVTX;
+ }
+ return res;
+}
+
+/**
+ * p9mode2perm- convert plan9 mode bits to unix permission bits
+ * @v9ses: v9fs session information
+ * @stat: p9_wstat from which mode need to be derived
+ *
+ */
+static int p9mode2perm(struct v9fs_session_info *v9ses,
+ struct p9_wstat *stat)
+{
+ int res;
+ int mode = stat->mode;
+
+ res = mode & S_IALLUGO;
+ if (v9fs_proto_dotu(v9ses)) {
+ if ((mode & P9_DMSETUID) == P9_DMSETUID)
+ res |= S_ISUID;
+
+ if ((mode & P9_DMSETGID) == P9_DMSETGID)
+ res |= S_ISGID;
+
+ if ((mode & P9_DMSETVTX) == P9_DMSETVTX)
+ res |= S_ISVTX;
+ }
+ return res;
+}
+
+/**
+ * p9mode2unixmode- convert plan9 mode bits to unix mode bits
+ * @v9ses: v9fs session information
+ * @stat: p9_wstat from which mode need to be derived
+ * @rdev: major number, minor number in case of device files.
+ *
+ */
+static umode_t p9mode2unixmode(struct v9fs_session_info *v9ses,
+ struct p9_wstat *stat, dev_t *rdev)
+{
+ int res, r;
+ u32 mode = stat->mode;
+
+ *rdev = 0;
+ res = p9mode2perm(v9ses, stat);
+
+ if ((mode & P9_DMDIR) == P9_DMDIR)
+ res |= S_IFDIR;
+ else if ((mode & P9_DMSYMLINK) && (v9fs_proto_dotu(v9ses)))
+ res |= S_IFLNK;
+ else if ((mode & P9_DMSOCKET) && (v9fs_proto_dotu(v9ses))
+ && (v9ses->nodev == 0))
+ res |= S_IFSOCK;
+ else if ((mode & P9_DMNAMEDPIPE) && (v9fs_proto_dotu(v9ses))
+ && (v9ses->nodev == 0))
+ res |= S_IFIFO;
+ else if ((mode & P9_DMDEVICE) && (v9fs_proto_dotu(v9ses))
+ && (v9ses->nodev == 0)) {
+ char type = 0;
+ int major = -1, minor = -1;
+
+ r = sscanf(stat->extension, "%c %i %i", &type, &major, &minor);
+ if (r != 3) {
+ p9_debug(P9_DEBUG_ERROR,
+ "invalid device string, umode will be bogus: %s\n",
+ stat->extension);
+ return res;
+ }
+ switch (type) {
+ case 'c':
+ res |= S_IFCHR;
+ break;
+ case 'b':
+ res |= S_IFBLK;
+ break;
+ default:
+ p9_debug(P9_DEBUG_ERROR, "Unknown special type %c %s\n",
+ type, stat->extension);
+ }
+ *rdev = MKDEV(major, minor);
+ } else
+ res |= S_IFREG;
+
+ return res;
+}
+
+/**
+ * v9fs_uflags2omode- convert posix open flags to plan 9 mode bits
+ * @uflags: flags to convert
+ * @extended: if .u extensions are active
+ */
+
+int v9fs_uflags2omode(int uflags, int extended)
+{
+ int ret;
+
+ ret = 0;
+ switch (uflags&3) {
+ default:
+ case O_RDONLY:
+ ret = P9_OREAD;
+ break;
+
+ case O_WRONLY:
+ ret = P9_OWRITE;
+ break;
+
+ case O_RDWR:
+ ret = P9_ORDWR;
+ break;
+ }
+
+ if (extended) {
+ if (uflags & O_EXCL)
+ ret |= P9_OEXCL;
+
+ if (uflags & O_APPEND)
+ ret |= P9_OAPPEND;
+ }
+
+ return ret;
+}
+
+/**
+ * v9fs_blank_wstat - helper function to setup a 9P stat structure
+ * @wstat: structure to initialize
+ *
+ */
+
+void
+v9fs_blank_wstat(struct p9_wstat *wstat)
+{
+ wstat->type = ~0;
+ wstat->dev = ~0;
+ wstat->qid.type = ~0;
+ wstat->qid.version = ~0;
+ *((long long *)&wstat->qid.path) = ~0;
+ wstat->mode = ~0;
+ wstat->atime = ~0;
+ wstat->mtime = ~0;
+ wstat->length = ~0;
+ wstat->name = NULL;
+ wstat->uid = NULL;
+ wstat->gid = NULL;
+ wstat->muid = NULL;
+ wstat->n_uid = INVALID_UID;
+ wstat->n_gid = INVALID_GID;
+ wstat->n_muid = INVALID_UID;
+ wstat->extension = NULL;
+}
+
+/**
+ * v9fs_alloc_inode - helper function to allocate an inode
+ * @sb: The superblock to allocate the inode from
+ */
+struct inode *v9fs_alloc_inode(struct super_block *sb)
+{
+ struct v9fs_inode *v9inode;
+
+ v9inode = alloc_inode_sb(sb, v9fs_inode_cache, GFP_KERNEL);
+ if (!v9inode)
+ return NULL;
+ v9inode->writeback_fid = NULL;
+ v9inode->cache_validity = 0;
+ mutex_init(&v9inode->v_mutex);
+ return &v9inode->netfs.inode;
+}
+
+/**
+ * v9fs_free_inode - destroy an inode
+ * @inode: The inode to be freed
+ */
+
+void v9fs_free_inode(struct inode *inode)
+{
+ kmem_cache_free(v9fs_inode_cache, V9FS_I(inode));
+}
+
+/*
+ * Set parameters for the netfs library
+ */
+static void v9fs_set_netfs_context(struct inode *inode)
+{
+ struct v9fs_inode *v9inode = V9FS_I(inode);
+ netfs_inode_init(&v9inode->netfs, &v9fs_req_ops);
+}
+
+int v9fs_init_inode(struct v9fs_session_info *v9ses,
+ struct inode *inode, umode_t mode, dev_t rdev)
+{
+ int err = 0;
+
+ inode_init_owner(&init_user_ns, inode, NULL, mode);
+ inode->i_blocks = 0;
+ inode->i_rdev = rdev;
+ inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
+ inode->i_mapping->a_ops = &v9fs_addr_operations;
+ inode->i_private = NULL;
+
+ switch (mode & S_IFMT) {
+ case S_IFIFO:
+ case S_IFBLK:
+ case S_IFCHR:
+ case S_IFSOCK:
+ if (v9fs_proto_dotl(v9ses)) {
+ inode->i_op = &v9fs_file_inode_operations_dotl;
+ } else if (v9fs_proto_dotu(v9ses)) {
+ inode->i_op = &v9fs_file_inode_operations;
+ } else {
+ p9_debug(P9_DEBUG_ERROR,
+ "special files without extended mode\n");
+ err = -EINVAL;
+ goto error;
+ }
+ init_special_inode(inode, inode->i_mode, inode->i_rdev);
+ break;
+ case S_IFREG:
+ if (v9fs_proto_dotl(v9ses)) {
+ inode->i_op = &v9fs_file_inode_operations_dotl;
+ if (v9ses->cache == CACHE_LOOSE ||
+ v9ses->cache == CACHE_FSCACHE)
+ inode->i_fop =
+ &v9fs_cached_file_operations_dotl;
+ else if (v9ses->cache == CACHE_MMAP)
+ inode->i_fop = &v9fs_mmap_file_operations_dotl;
+ else
+ inode->i_fop = &v9fs_file_operations_dotl;
+ } else {
+ inode->i_op = &v9fs_file_inode_operations;
+ if (v9ses->cache == CACHE_LOOSE ||
+ v9ses->cache == CACHE_FSCACHE)
+ inode->i_fop =
+ &v9fs_cached_file_operations;
+ else if (v9ses->cache == CACHE_MMAP)
+ inode->i_fop = &v9fs_mmap_file_operations;
+ else
+ inode->i_fop = &v9fs_file_operations;
+ }
+
+ break;
+ case S_IFLNK:
+ if (!v9fs_proto_dotu(v9ses) && !v9fs_proto_dotl(v9ses)) {
+ p9_debug(P9_DEBUG_ERROR,
+ "extended modes used with legacy protocol\n");
+ err = -EINVAL;
+ goto error;
+ }
+
+ if (v9fs_proto_dotl(v9ses))
+ inode->i_op = &v9fs_symlink_inode_operations_dotl;
+ else
+ inode->i_op = &v9fs_symlink_inode_operations;
+
+ break;
+ case S_IFDIR:
+ inc_nlink(inode);
+ if (v9fs_proto_dotl(v9ses))
+ inode->i_op = &v9fs_dir_inode_operations_dotl;
+ else if (v9fs_proto_dotu(v9ses))
+ inode->i_op = &v9fs_dir_inode_operations_dotu;
+ else
+ inode->i_op = &v9fs_dir_inode_operations;
+
+ if (v9fs_proto_dotl(v9ses))
+ inode->i_fop = &v9fs_dir_operations_dotl;
+ else
+ inode->i_fop = &v9fs_dir_operations;
+
+ break;
+ default:
+ p9_debug(P9_DEBUG_ERROR, "BAD mode 0x%hx S_IFMT 0x%x\n",
+ mode, mode & S_IFMT);
+ err = -EINVAL;
+ goto error;
+ }
+
+ v9fs_set_netfs_context(inode);
+error:
+ return err;
+
+}
+
+/**
+ * v9fs_get_inode - helper function to setup an inode
+ * @sb: superblock
+ * @mode: mode to setup inode with
+ * @rdev: The device numbers to set
+ */
+
+struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t rdev)
+{
+ int err;
+ struct inode *inode;
+ struct v9fs_session_info *v9ses = sb->s_fs_info;
+
+ p9_debug(P9_DEBUG_VFS, "super block: %p mode: %ho\n", sb, mode);
+
+ inode = new_inode(sb);
+ if (!inode) {
+ pr_warn("%s (%d): Problem allocating inode\n",
+ __func__, task_pid_nr(current));
+ return ERR_PTR(-ENOMEM);
+ }
+ err = v9fs_init_inode(v9ses, inode, mode, rdev);
+ if (err) {
+ iput(inode);
+ return ERR_PTR(err);
+ }
+ return inode;
+}
+
+/**
+ * v9fs_evict_inode - Remove an inode from the inode cache
+ * @inode: inode to release
+ *
+ */
+void v9fs_evict_inode(struct inode *inode)
+{
+ struct v9fs_inode *v9inode = V9FS_I(inode);
+ __le32 version;
+
+ truncate_inode_pages_final(&inode->i_data);
+ version = cpu_to_le32(v9inode->qid.version);
+ fscache_clear_inode_writeback(v9fs_inode_cookie(v9inode), inode,
+ &version);
+ clear_inode(inode);
+ filemap_fdatawrite(&inode->i_data);
+
+ fscache_relinquish_cookie(v9fs_inode_cookie(v9inode), false);
+ /* clunk the fid stashed in writeback_fid */
+ p9_fid_put(v9inode->writeback_fid);
+ v9inode->writeback_fid = NULL;
+}
+
+static int v9fs_test_inode(struct inode *inode, void *data)
+{
+ int umode;
+ dev_t rdev;
+ struct v9fs_inode *v9inode = V9FS_I(inode);
+ struct p9_wstat *st = (struct p9_wstat *)data;
+ struct v9fs_session_info *v9ses = v9fs_inode2v9ses(inode);
+
+ umode = p9mode2unixmode(v9ses, st, &rdev);
+ /* don't match inode of different type */
+ if (inode_wrong_type(inode, umode))
+ return 0;
+
+ /* compare qid details */
+ if (memcmp(&v9inode->qid.version,
+ &st->qid.version, sizeof(v9inode->qid.version)))
+ return 0;
+
+ if (v9inode->qid.type != st->qid.type)
+ return 0;
+
+ if (v9inode->qid.path != st->qid.path)
+ return 0;
+ return 1;
+}
+
+static int v9fs_test_new_inode(struct inode *inode, void *data)
+{
+ return 0;
+}
+
+static int v9fs_set_inode(struct inode *inode, void *data)
+{
+ struct v9fs_inode *v9inode = V9FS_I(inode);
+ struct p9_wstat *st = (struct p9_wstat *)data;
+
+ memcpy(&v9inode->qid, &st->qid, sizeof(st->qid));
+ return 0;
+}
+
+static struct inode *v9fs_qid_iget(struct super_block *sb,
+ struct p9_qid *qid,
+ struct p9_wstat *st,
+ int new)
+{
+ dev_t rdev;
+ int retval;
+ umode_t umode;
+ unsigned long i_ino;
+ struct inode *inode;
+ struct v9fs_session_info *v9ses = sb->s_fs_info;
+ int (*test)(struct inode *inode, void *data);
+
+ if (new)
+ test = v9fs_test_new_inode;
+ else
+ test = v9fs_test_inode;
+
+ i_ino = v9fs_qid2ino(qid);
+ inode = iget5_locked(sb, i_ino, test, v9fs_set_inode, st);
+ if (!inode)
+ return ERR_PTR(-ENOMEM);
+ if (!(inode->i_state & I_NEW))
+ return inode;
+ /*
+ * initialize the inode with the stat info
+ * FIXME!! we may need support for stale inodes
+ * later.
+ */
+ inode->i_ino = i_ino;
+ umode = p9mode2unixmode(v9ses, st, &rdev);
+ retval = v9fs_init_inode(v9ses, inode, umode, rdev);
+ if (retval)
+ goto error;
+
+ v9fs_stat2inode(st, inode, sb, 0);
+ v9fs_cache_inode_get_cookie(inode);
+ unlock_new_inode(inode);
+ return inode;
+error:
+ iget_failed(inode);
+ return ERR_PTR(retval);
+
+}
+
+struct inode *
+v9fs_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
+ struct super_block *sb, int new)
+{
+ struct p9_wstat *st;
+ struct inode *inode = NULL;
+
+ st = p9_client_stat(fid);
+ if (IS_ERR(st))
+ return ERR_CAST(st);
+
+ inode = v9fs_qid_iget(sb, &st->qid, st, new);
+ p9stat_free(st);
+ kfree(st);
+ return inode;
+}
+
+/**
+ * v9fs_at_to_dotl_flags- convert Linux specific AT flags to
+ * plan 9 AT flag.
+ * @flags: flags to convert
+ */
+static int v9fs_at_to_dotl_flags(int flags)
+{
+ int rflags = 0;
+
+ if (flags & AT_REMOVEDIR)
+ rflags |= P9_DOTL_AT_REMOVEDIR;
+
+ return rflags;
+}
+
+/**
+ * v9fs_dec_count - helper functon to drop i_nlink.
+ *
+ * If a directory had nlink <= 2 (including . and ..), then we should not drop
+ * the link count, which indicates the underlying exported fs doesn't maintain
+ * nlink accurately. e.g.
+ * - overlayfs sets nlink to 1 for merged dir
+ * - ext4 (with dir_nlink feature enabled) sets nlink to 1 if a dir has more
+ * than EXT4_LINK_MAX (65000) links.
+ *
+ * @inode: inode whose nlink is being dropped
+ */
+static void v9fs_dec_count(struct inode *inode)
+{
+ if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2)
+ drop_nlink(inode);
+}
+
+/**
+ * v9fs_remove - helper function to remove files and directories
+ * @dir: directory inode that is being deleted
+ * @dentry: dentry that is being deleted
+ * @flags: removing a directory
+ *
+ */
+
+static int v9fs_remove(struct inode *dir, struct dentry *dentry, int flags)
+{
+ struct inode *inode;
+ int retval = -EOPNOTSUPP;
+ struct p9_fid *v9fid, *dfid;
+ struct v9fs_session_info *v9ses;
+
+ p9_debug(P9_DEBUG_VFS, "inode: %p dentry: %p rmdir: %x\n",
+ dir, dentry, flags);
+
+ v9ses = v9fs_inode2v9ses(dir);
+ inode = d_inode(dentry);
+ dfid = v9fs_parent_fid(dentry);
+ if (IS_ERR(dfid)) {
+ retval = PTR_ERR(dfid);
+ p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", retval);
+ return retval;
+ }
+ if (v9fs_proto_dotl(v9ses))
+ retval = p9_client_unlinkat(dfid, dentry->d_name.name,
+ v9fs_at_to_dotl_flags(flags));
+ p9_fid_put(dfid);
+ if (retval == -EOPNOTSUPP) {
+ /* Try the one based on path */
+ v9fid = v9fs_fid_clone(dentry);
+ if (IS_ERR(v9fid))
+ return PTR_ERR(v9fid);
+ retval = p9_client_remove(v9fid);
+ }
+ if (!retval) {
+ /*
+ * directories on unlink should have zero
+ * link count
+ */
+ if (flags & AT_REMOVEDIR) {
+ clear_nlink(inode);
+ v9fs_dec_count(dir);
+ } else
+ v9fs_dec_count(inode);
+
+ v9fs_invalidate_inode_attr(inode);
+ v9fs_invalidate_inode_attr(dir);
+
+ /* invalidate all fids associated with dentry */
+ /* NOTE: This will not include open fids */
+ dentry->d_op->d_release(dentry);
+ }
+ return retval;
+}
+
+/**
+ * v9fs_create - Create a file
+ * @v9ses: session information
+ * @dir: directory that dentry is being created in
+ * @dentry: dentry that is being created
+ * @extension: 9p2000.u extension string to support devices, etc.
+ * @perm: create permissions
+ * @mode: open mode
+ *
+ */
+static struct p9_fid *
+v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
+ struct dentry *dentry, char *extension, u32 perm, u8 mode)
+{
+ int err;
+ const unsigned char *name;
+ struct p9_fid *dfid, *ofid = NULL, *fid = NULL;
+ struct inode *inode;
+
+ p9_debug(P9_DEBUG_VFS, "name %pd\n", dentry);
+
+ err = 0;
+ name = dentry->d_name.name;
+ dfid = v9fs_parent_fid(dentry);
+ if (IS_ERR(dfid)) {
+ err = PTR_ERR(dfid);
+ p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", err);
+ return ERR_PTR(err);
+ }
+
+ /* clone a fid to use for creation */
+ ofid = clone_fid(dfid);
+ if (IS_ERR(ofid)) {
+ err = PTR_ERR(ofid);
+ p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err);
+ goto error;
+ }
+
+ err = p9_client_fcreate(ofid, name, perm, mode, extension);
+ if (err < 0) {
+ p9_debug(P9_DEBUG_VFS, "p9_client_fcreate failed %d\n", err);
+ goto error;
+ }
+
+ if (!(perm & P9_DMLINK)) {
+ /* now walk from the parent so we can get unopened fid */
+ fid = p9_client_walk(dfid, 1, &name, 1);
+ if (IS_ERR(fid)) {
+ err = PTR_ERR(fid);
+ p9_debug(P9_DEBUG_VFS,
+ "p9_client_walk failed %d\n", err);
+ goto error;
+ }
+ /*
+ * instantiate inode and assign the unopened fid to the dentry
+ */
+ inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ p9_debug(P9_DEBUG_VFS,
+ "inode creation failed %d\n", err);
+ goto error;
+ }
+ v9fs_fid_add(dentry, &fid);
+ d_instantiate(dentry, inode);
+ }
+ p9_fid_put(dfid);
+ return ofid;
+error:
+ p9_fid_put(dfid);
+ p9_fid_put(ofid);
+ p9_fid_put(fid);
+ return ERR_PTR(err);
+}
+
+/**
+ * v9fs_vfs_create - VFS hook to create a regular file
+ * @mnt_userns: The user namespace of the mount
+ * @dir: The parent directory
+ * @dentry: The name of file to be created
+ * @mode: The UNIX file mode to set
+ * @excl: True if the file must not yet exist
+ *
+ * open(.., O_CREAT) is handled in v9fs_vfs_atomic_open(). This is only called
+ * for mknod(2).
+ *
+ */
+
+static int
+v9fs_vfs_create(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
+{
+ struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir);
+ u32 perm = unixmode2p9mode(v9ses, mode);
+ struct p9_fid *fid;
+
+ /* P9_OEXCL? */
+ fid = v9fs_create(v9ses, dir, dentry, NULL, perm, P9_ORDWR);
+ if (IS_ERR(fid))
+ return PTR_ERR(fid);
+
+ v9fs_invalidate_inode_attr(dir);
+ p9_fid_put(fid);
+
+ return 0;
+}
+
+/**
+ * v9fs_vfs_mkdir - VFS mkdir hook to create a directory
+ * @mnt_userns: The user namespace of the mount
+ * @dir: inode that is being unlinked
+ * @dentry: dentry that is being unlinked
+ * @mode: mode for new directory
+ *
+ */
+
+static int v9fs_vfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
+{
+ int err;
+ u32 perm;
+ struct p9_fid *fid;
+ struct v9fs_session_info *v9ses;
+
+ p9_debug(P9_DEBUG_VFS, "name %pd\n", dentry);
+ err = 0;
+ v9ses = v9fs_inode2v9ses(dir);
+ perm = unixmode2p9mode(v9ses, mode | S_IFDIR);
+ fid = v9fs_create(v9ses, dir, dentry, NULL, perm, P9_OREAD);
+ if (IS_ERR(fid)) {
+ err = PTR_ERR(fid);
+ fid = NULL;
+ } else {
+ inc_nlink(dir);
+ v9fs_invalidate_inode_attr(dir);
+ }
+
+ if (fid)
+ p9_fid_put(fid);
+
+ return err;
+}
+
+/**
+ * v9fs_vfs_lookup - VFS lookup hook to "walk" to a new inode
+ * @dir: inode that is being walked from
+ * @dentry: dentry that is being walked to?
+ * @flags: lookup flags (unused)
+ *
+ */
+
+struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
+ unsigned int flags)
+{
+ struct dentry *res;
+ struct v9fs_session_info *v9ses;
+ struct p9_fid *dfid, *fid;
+ struct inode *inode;
+ const unsigned char *name;
+
+ p9_debug(P9_DEBUG_VFS, "dir: %p dentry: (%pd) %p flags: %x\n",
+ dir, dentry, dentry, flags);
+
+ if (dentry->d_name.len > NAME_MAX)
+ return ERR_PTR(-ENAMETOOLONG);
+
+ v9ses = v9fs_inode2v9ses(dir);
+ /* We can walk d_parent because we hold the dir->i_mutex */
+ dfid = v9fs_parent_fid(dentry);
+ if (IS_ERR(dfid))
+ return ERR_CAST(dfid);
+
+ /*
+ * Make sure we don't use a wrong inode due to parallel
+ * unlink. For cached mode create calls request for new
+ * inode. But with cache disabled, lookup should do this.
+ */
+ name = dentry->d_name.name;
+ fid = p9_client_walk(dfid, 1, &name, 1);
+ p9_fid_put(dfid);
+ if (fid == ERR_PTR(-ENOENT))
+ inode = NULL;
+ else if (IS_ERR(fid))
+ inode = ERR_CAST(fid);
+ else if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
+ inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb);
+ else
+ inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
+ /*
+ * If we had a rename on the server and a parallel lookup
+ * for the new name, then make sure we instantiate with
+ * the new name. ie look up for a/b, while on server somebody
+ * moved b under k and client parallely did a lookup for
+ * k/b.
+ */
+ res = d_splice_alias(inode, dentry);
+ if (!IS_ERR(fid)) {
+ if (!res)
+ v9fs_fid_add(dentry, &fid);
+ else if (!IS_ERR(res))
+ v9fs_fid_add(res, &fid);
+ else
+ p9_fid_put(fid);
+ }
+ return res;
+}
+
+static int
+v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
+ struct file *file, unsigned int flags, umode_t mode)
+{
+ int err;
+ u32 perm;
+ struct v9fs_inode *v9inode;
+ struct v9fs_session_info *v9ses;
+ struct p9_fid *fid, *inode_fid;
+ struct dentry *res = NULL;
+ struct inode *inode;
+
+ if (d_in_lookup(dentry)) {
+ res = v9fs_vfs_lookup(dir, dentry, 0);
+ if (IS_ERR(res))
+ return PTR_ERR(res);
+
+ if (res)
+ dentry = res;
+ }
+
+ /* Only creates */
+ if (!(flags & O_CREAT) || d_really_is_positive(dentry))
+ return finish_no_open(file, res);
+
+ err = 0;
+
+ v9ses = v9fs_inode2v9ses(dir);
+ perm = unixmode2p9mode(v9ses, mode);
+ fid = v9fs_create(v9ses, dir, dentry, NULL, perm,
+ v9fs_uflags2omode(flags,
+ v9fs_proto_dotu(v9ses)));
+ if (IS_ERR(fid)) {
+ err = PTR_ERR(fid);
+ goto error;
+ }
+
+ v9fs_invalidate_inode_attr(dir);
+ inode = d_inode(dentry);
+ v9inode = V9FS_I(inode);
+ mutex_lock(&v9inode->v_mutex);
+ if ((v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) &&
+ !v9inode->writeback_fid &&
+ ((flags & O_ACCMODE) != O_RDONLY)) {
+ /*
+ * clone a fid and add it to writeback_fid
+ * we do it during open time instead of
+ * page dirty time via write_begin/page_mkwrite
+ * because we want write after unlink usecase
+ * to work.
+ */
+ inode_fid = v9fs_writeback_fid(dentry);
+ if (IS_ERR(inode_fid)) {
+ err = PTR_ERR(inode_fid);
+ mutex_unlock(&v9inode->v_mutex);
+ goto error;
+ }
+ v9inode->writeback_fid = (void *) inode_fid;
+ }
+ mutex_unlock(&v9inode->v_mutex);
+ err = finish_open(file, dentry, generic_file_open);
+ if (err)
+ goto error;
+
+ file->private_data = fid;
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
+ fscache_use_cookie(v9fs_inode_cookie(v9inode),
+ file->f_mode & FMODE_WRITE);
+ v9fs_open_fid_add(inode, &fid);
+
+ file->f_mode |= FMODE_CREATED;
+out:
+ dput(res);
+ return err;
+
+error:
+ p9_fid_put(fid);
+ goto out;
+}
+
+/**
+ * v9fs_vfs_unlink - VFS unlink hook to delete an inode
+ * @i: inode that is being unlinked
+ * @d: dentry that is being unlinked
+ *
+ */
+
+int v9fs_vfs_unlink(struct inode *i, struct dentry *d)
+{
+ return v9fs_remove(i, d, 0);
+}
+
+/**
+ * v9fs_vfs_rmdir - VFS unlink hook to delete a directory
+ * @i: inode that is being unlinked
+ * @d: dentry that is being unlinked
+ *
+ */
+
+int v9fs_vfs_rmdir(struct inode *i, struct dentry *d)
+{
+ return v9fs_remove(i, d, AT_REMOVEDIR);
+}
+
+/**
+ * v9fs_vfs_rename - VFS hook to rename an inode
+ * @mnt_userns: The user namespace of the mount
+ * @old_dir: old dir inode
+ * @old_dentry: old dentry
+ * @new_dir: new dir inode
+ * @new_dentry: new dentry
+ * @flags: RENAME_* flags
+ *
+ */
+
+int
+v9fs_vfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+ struct dentry *old_dentry, struct inode *new_dir,
+ struct dentry *new_dentry, unsigned int flags)
+{
+ int retval;
+ struct inode *old_inode;
+ struct inode *new_inode;
+ struct v9fs_session_info *v9ses;
+ struct p9_fid *oldfid = NULL, *dfid = NULL;
+ struct p9_fid *olddirfid = NULL;
+ struct p9_fid *newdirfid = NULL;
+ struct p9_wstat wstat;
+
+ if (flags)
+ return -EINVAL;
+
+ p9_debug(P9_DEBUG_VFS, "\n");
+ retval = 0;
+ old_inode = d_inode(old_dentry);
+ new_inode = d_inode(new_dentry);
+ v9ses = v9fs_inode2v9ses(old_inode);
+ oldfid = v9fs_fid_lookup(old_dentry);
+ if (IS_ERR(oldfid))
+ return PTR_ERR(oldfid);
+
+ dfid = v9fs_parent_fid(old_dentry);
+ olddirfid = clone_fid(dfid);
+ p9_fid_put(dfid);
+ dfid = NULL;
+
+ if (IS_ERR(olddirfid)) {
+ retval = PTR_ERR(olddirfid);
+ goto error;
+ }
+
+ dfid = v9fs_parent_fid(new_dentry);
+ newdirfid = clone_fid(dfid);
+ p9_fid_put(dfid);
+ dfid = NULL;
+
+ if (IS_ERR(newdirfid)) {
+ retval = PTR_ERR(newdirfid);
+ goto error;
+ }
+
+ down_write(&v9ses->rename_sem);
+ if (v9fs_proto_dotl(v9ses)) {
+ retval = p9_client_renameat(olddirfid, old_dentry->d_name.name,
+ newdirfid, new_dentry->d_name.name);
+ if (retval == -EOPNOTSUPP)
+ retval = p9_client_rename(oldfid, newdirfid,
+ new_dentry->d_name.name);
+ if (retval != -EOPNOTSUPP)
+ goto error_locked;
+ }
+ if (old_dentry->d_parent != new_dentry->d_parent) {
+ /*
+ * 9P .u can only handle file rename in the same directory
+ */
+
+ p9_debug(P9_DEBUG_ERROR, "old dir and new dir are different\n");
+ retval = -EXDEV;
+ goto error_locked;
+ }
+ v9fs_blank_wstat(&wstat);
+ wstat.muid = v9ses->uname;
+ wstat.name = new_dentry->d_name.name;
+ retval = p9_client_wstat(oldfid, &wstat);
+
+error_locked:
+ if (!retval) {
+ if (new_inode) {
+ if (S_ISDIR(new_inode->i_mode))
+ clear_nlink(new_inode);
+ else
+ v9fs_dec_count(new_inode);
+ }
+ if (S_ISDIR(old_inode->i_mode)) {
+ if (!new_inode)
+ inc_nlink(new_dir);
+ v9fs_dec_count(old_dir);
+ }
+ v9fs_invalidate_inode_attr(old_inode);
+ v9fs_invalidate_inode_attr(old_dir);
+ v9fs_invalidate_inode_attr(new_dir);
+
+ /* successful rename */
+ d_move(old_dentry, new_dentry);
+ }
+ up_write(&v9ses->rename_sem);
+
+error:
+ p9_fid_put(newdirfid);
+ p9_fid_put(olddirfid);
+ p9_fid_put(oldfid);
+ return retval;
+}
+
+/**
+ * v9fs_vfs_getattr - retrieve file metadata
+ * @mnt_userns: The user namespace of the mount
+ * @path: Object to query
+ * @stat: metadata structure to populate
+ * @request_mask: Mask of STATX_xxx flags indicating the caller's interests
+ * @flags: AT_STATX_xxx setting
+ *
+ */
+
+static int
+v9fs_vfs_getattr(struct user_namespace *mnt_userns, const struct path *path,
+ struct kstat *stat, u32 request_mask, unsigned int flags)
+{
+ struct dentry *dentry = path->dentry;
+ struct v9fs_session_info *v9ses;
+ struct p9_fid *fid;
+ struct p9_wstat *st;
+
+ p9_debug(P9_DEBUG_VFS, "dentry: %p\n", dentry);
+ v9ses = v9fs_dentry2v9ses(dentry);
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
+ generic_fillattr(&init_user_ns, d_inode(dentry), stat);
+ return 0;
+ }
+ fid = v9fs_fid_lookup(dentry);
+ if (IS_ERR(fid))
+ return PTR_ERR(fid);
+
+ st = p9_client_stat(fid);
+ p9_fid_put(fid);
+ if (IS_ERR(st))
+ return PTR_ERR(st);
+
+ v9fs_stat2inode(st, d_inode(dentry), dentry->d_sb, 0);
+ generic_fillattr(&init_user_ns, d_inode(dentry), stat);
+
+ p9stat_free(st);
+ kfree(st);
+ return 0;
+}
+
+/**
+ * v9fs_vfs_setattr - set file metadata
+ * @mnt_userns: The user namespace of the mount
+ * @dentry: file whose metadata to set
+ * @iattr: metadata assignment structure
+ *
+ */
+
+static int v9fs_vfs_setattr(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *iattr)
+{
+ int retval, use_dentry = 0;
+ struct inode *inode = d_inode(dentry);
+ struct v9fs_inode *v9inode = V9FS_I(inode);
+ struct v9fs_session_info *v9ses;
+ struct p9_fid *fid = NULL;
+ struct p9_wstat wstat;
+
+ p9_debug(P9_DEBUG_VFS, "\n");
+ retval = setattr_prepare(&init_user_ns, dentry, iattr);
+ if (retval)
+ return retval;
+
+ retval = -EPERM;
+ v9ses = v9fs_dentry2v9ses(dentry);
+ if (iattr->ia_valid & ATTR_FILE) {
+ fid = iattr->ia_file->private_data;
+ WARN_ON(!fid);
+ }
+ if (!fid) {
+ fid = v9fs_fid_lookup(dentry);
+ use_dentry = 1;
+ }
+ if (IS_ERR(fid))
+ return PTR_ERR(fid);
+
+ v9fs_blank_wstat(&wstat);
+ if (iattr->ia_valid & ATTR_MODE)
+ wstat.mode = unixmode2p9mode(v9ses, iattr->ia_mode);
+
+ if (iattr->ia_valid & ATTR_MTIME)
+ wstat.mtime = iattr->ia_mtime.tv_sec;
+
+ if (iattr->ia_valid & ATTR_ATIME)
+ wstat.atime = iattr->ia_atime.tv_sec;
+
+ if (iattr->ia_valid & ATTR_SIZE)
+ wstat.length = iattr->ia_size;
+
+ if (v9fs_proto_dotu(v9ses)) {
+ if (iattr->ia_valid & ATTR_UID)
+ wstat.n_uid = iattr->ia_uid;
+
+ if (iattr->ia_valid & ATTR_GID)
+ wstat.n_gid = iattr->ia_gid;
+ }
+
+ /* Write all dirty data */
+ if (d_is_reg(dentry))
+ filemap_write_and_wait(inode->i_mapping);
+
+ retval = p9_client_wstat(fid, &wstat);
+
+ if (use_dentry)
+ p9_fid_put(fid);
+
+ if (retval < 0)
+ return retval;
+
+ if ((iattr->ia_valid & ATTR_SIZE) &&
+ iattr->ia_size != i_size_read(inode)) {
+ truncate_setsize(inode, iattr->ia_size);
+ fscache_resize_cookie(v9fs_inode_cookie(v9inode), iattr->ia_size);
+ }
+
+ v9fs_invalidate_inode_attr(inode);
+
+ setattr_copy(&init_user_ns, inode, iattr);
+ mark_inode_dirty(inode);
+ return 0;
+}
+
+/**
+ * v9fs_stat2inode - populate an inode structure with mistat info
+ * @stat: Plan 9 metadata (mistat) structure
+ * @inode: inode to populate
+ * @sb: superblock of filesystem
+ * @flags: control flags (e.g. V9FS_STAT2INODE_KEEP_ISIZE)
+ *
+ */
+
+void
+v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode,
+ struct super_block *sb, unsigned int flags)
+{
+ umode_t mode;
+ struct v9fs_session_info *v9ses = sb->s_fs_info;
+ struct v9fs_inode *v9inode = V9FS_I(inode);
+
+ set_nlink(inode, 1);
+
+ inode->i_atime.tv_sec = stat->atime;
+ inode->i_mtime.tv_sec = stat->mtime;
+ inode->i_ctime.tv_sec = stat->mtime;
+
+ inode->i_uid = v9ses->dfltuid;
+ inode->i_gid = v9ses->dfltgid;
+
+ if (v9fs_proto_dotu(v9ses)) {
+ inode->i_uid = stat->n_uid;
+ inode->i_gid = stat->n_gid;
+ }
+ if ((S_ISREG(inode->i_mode)) || (S_ISDIR(inode->i_mode))) {
+ if (v9fs_proto_dotu(v9ses)) {
+ unsigned int i_nlink;
+ /*
+ * Hadlink support got added later to the .u extension.
+ * So there can be a server out there that doesn't
+ * support this even with .u extension. That would
+ * just leave us with stat->extension being an empty
+ * string, though.
+ */
+ /* HARDLINKCOUNT %u */
+ if (sscanf(stat->extension,
+ " HARDLINKCOUNT %u", &i_nlink) == 1)
+ set_nlink(inode, i_nlink);
+ }
+ }
+ mode = p9mode2perm(v9ses, stat);
+ mode |= inode->i_mode & ~S_IALLUGO;
+ inode->i_mode = mode;
+
+ if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE))
+ v9fs_i_size_write(inode, stat->length);
+ /* not real number of blocks, but 512 byte ones ... */
+ inode->i_blocks = (stat->length + 512 - 1) >> 9;
+ v9inode->cache_validity &= ~V9FS_INO_INVALID_ATTR;
+}
+
+/**
+ * v9fs_qid2ino - convert qid into inode number
+ * @qid: qid to hash
+ *
+ * BUG: potential for inode number collisions?
+ */
+
+ino_t v9fs_qid2ino(struct p9_qid *qid)
+{
+ u64 path = qid->path + 2;
+ ino_t i = 0;
+
+ if (sizeof(ino_t) == sizeof(path))
+ memcpy(&i, &path, sizeof(ino_t));
+ else
+ i = (ino_t) (path ^ (path >> 32));
+
+ return i;
+}
+
+/**
+ * v9fs_vfs_get_link - follow a symlink path
+ * @dentry: dentry for symlink
+ * @inode: inode for symlink
+ * @done: delayed call for when we are done with the return value
+ */
+
+static const char *v9fs_vfs_get_link(struct dentry *dentry,
+ struct inode *inode,
+ struct delayed_call *done)
+{
+ struct v9fs_session_info *v9ses;
+ struct p9_fid *fid;
+ struct p9_wstat *st;
+ char *res;
+
+ if (!dentry)
+ return ERR_PTR(-ECHILD);
+
+ v9ses = v9fs_dentry2v9ses(dentry);
+ if (!v9fs_proto_dotu(v9ses))
+ return ERR_PTR(-EBADF);
+
+ p9_debug(P9_DEBUG_VFS, "%pd\n", dentry);
+ fid = v9fs_fid_lookup(dentry);
+
+ if (IS_ERR(fid))
+ return ERR_CAST(fid);
+
+ st = p9_client_stat(fid);
+ p9_fid_put(fid);
+ if (IS_ERR(st))
+ return ERR_CAST(st);
+
+ if (!(st->mode & P9_DMSYMLINK)) {
+ p9stat_free(st);
+ kfree(st);
+ return ERR_PTR(-EINVAL);
+ }
+ res = st->extension;
+ st->extension = NULL;
+ if (strlen(res) >= PATH_MAX)
+ res[PATH_MAX - 1] = '\0';
+
+ p9stat_free(st);
+ kfree(st);
+ set_delayed_call(done, kfree_link, res);
+ return res;
+}
+
+/**
+ * v9fs_vfs_mkspecial - create a special file
+ * @dir: inode to create special file in
+ * @dentry: dentry to create
+ * @perm: mode to create special file
+ * @extension: 9p2000.u format extension string representing special file
+ *
+ */
+
+static int v9fs_vfs_mkspecial(struct inode *dir, struct dentry *dentry,
+ u32 perm, const char *extension)
+{
+ struct p9_fid *fid;
+ struct v9fs_session_info *v9ses;
+
+ v9ses = v9fs_inode2v9ses(dir);
+ if (!v9fs_proto_dotu(v9ses)) {
+ p9_debug(P9_DEBUG_ERROR, "not extended\n");
+ return -EPERM;
+ }
+
+ fid = v9fs_create(v9ses, dir, dentry, (char *) extension, perm,
+ P9_OREAD);
+ if (IS_ERR(fid))
+ return PTR_ERR(fid);
+
+ v9fs_invalidate_inode_attr(dir);
+ p9_fid_put(fid);
+ return 0;
+}
+
+/**
+ * v9fs_vfs_symlink - helper function to create symlinks
+ * @mnt_userns: The user namespace of the mount
+ * @dir: directory inode containing symlink
+ * @dentry: dentry for symlink
+ * @symname: symlink data
+ *
+ * See Also: 9P2000.u RFC for more information
+ *
+ */
+
+static int
+v9fs_vfs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *symname)
+{
+ p9_debug(P9_DEBUG_VFS, " %lu,%pd,%s\n",
+ dir->i_ino, dentry, symname);
+
+ return v9fs_vfs_mkspecial(dir, dentry, P9_DMSYMLINK, symname);
+}
+
+#define U32_MAX_DIGITS 10
+
+/**
+ * v9fs_vfs_link - create a hardlink
+ * @old_dentry: dentry for file to link to
+ * @dir: inode destination for new link
+ * @dentry: dentry for link
+ *
+ */
+
+static int
+v9fs_vfs_link(struct dentry *old_dentry, struct inode *dir,
+ struct dentry *dentry)
+{
+ int retval;
+ char name[1 + U32_MAX_DIGITS + 2]; /* sign + number + \n + \0 */
+ struct p9_fid *oldfid;
+
+ p9_debug(P9_DEBUG_VFS, " %lu,%pd,%pd\n",
+ dir->i_ino, dentry, old_dentry);
+
+ oldfid = v9fs_fid_clone(old_dentry);
+ if (IS_ERR(oldfid))
+ return PTR_ERR(oldfid);
+
+ sprintf(name, "%d\n", oldfid->fid);
+ retval = v9fs_vfs_mkspecial(dir, dentry, P9_DMLINK, name);
+ if (!retval) {
+ v9fs_refresh_inode(oldfid, d_inode(old_dentry));
+ v9fs_invalidate_inode_attr(dir);
+ }
+ p9_fid_put(oldfid);
+ return retval;
+}
+
+/**
+ * v9fs_vfs_mknod - create a special file
+ * @mnt_userns: The user namespace of the mount
+ * @dir: inode destination for new link
+ * @dentry: dentry for file
+ * @mode: mode for creation
+ * @rdev: device associated with special file
+ *
+ */
+
+static int
+v9fs_vfs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t mode, dev_t rdev)
+{
+ struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir);
+ int retval;
+ char name[2 + U32_MAX_DIGITS + 1 + U32_MAX_DIGITS + 1];
+ u32 perm;
+
+ p9_debug(P9_DEBUG_VFS, " %lu,%pd mode: %x MAJOR: %u MINOR: %u\n",
+ dir->i_ino, dentry, mode,
+ MAJOR(rdev), MINOR(rdev));
+
+ /* build extension */
+ if (S_ISBLK(mode))
+ sprintf(name, "b %u %u", MAJOR(rdev), MINOR(rdev));
+ else if (S_ISCHR(mode))
+ sprintf(name, "c %u %u", MAJOR(rdev), MINOR(rdev));
+ else
+ *name = 0;
+
+ perm = unixmode2p9mode(v9ses, mode);
+ retval = v9fs_vfs_mkspecial(dir, dentry, perm, name);
+
+ return retval;
+}
+
+int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode)
+{
+ int umode;
+ dev_t rdev;
+ struct p9_wstat *st;
+ struct v9fs_session_info *v9ses;
+ unsigned int flags;
+
+ v9ses = v9fs_inode2v9ses(inode);
+ st = p9_client_stat(fid);
+ if (IS_ERR(st))
+ return PTR_ERR(st);
+ /*
+ * Don't update inode if the file type is different
+ */
+ umode = p9mode2unixmode(v9ses, st, &rdev);
+ if (inode_wrong_type(inode, umode))
+ goto out;
+
+ /*
+ * We don't want to refresh inode->i_size,
+ * because we may have cached data
+ */
+ flags = (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) ?
+ V9FS_STAT2INODE_KEEP_ISIZE : 0;
+ v9fs_stat2inode(st, inode, inode->i_sb, flags);
+out:
+ p9stat_free(st);
+ kfree(st);
+ return 0;
+}
+
+static const struct inode_operations v9fs_dir_inode_operations_dotu = {
+ .create = v9fs_vfs_create,
+ .lookup = v9fs_vfs_lookup,
+ .atomic_open = v9fs_vfs_atomic_open,
+ .symlink = v9fs_vfs_symlink,
+ .link = v9fs_vfs_link,
+ .unlink = v9fs_vfs_unlink,
+ .mkdir = v9fs_vfs_mkdir,
+ .rmdir = v9fs_vfs_rmdir,
+ .mknod = v9fs_vfs_mknod,
+ .rename = v9fs_vfs_rename,
+ .getattr = v9fs_vfs_getattr,
+ .setattr = v9fs_vfs_setattr,
+};
+
+static const struct inode_operations v9fs_dir_inode_operations = {
+ .create = v9fs_vfs_create,
+ .lookup = v9fs_vfs_lookup,
+ .atomic_open = v9fs_vfs_atomic_open,
+ .unlink = v9fs_vfs_unlink,
+ .mkdir = v9fs_vfs_mkdir,
+ .rmdir = v9fs_vfs_rmdir,
+ .mknod = v9fs_vfs_mknod,
+ .rename = v9fs_vfs_rename,
+ .getattr = v9fs_vfs_getattr,
+ .setattr = v9fs_vfs_setattr,
+};
+
+static const struct inode_operations v9fs_file_inode_operations = {
+ .getattr = v9fs_vfs_getattr,
+ .setattr = v9fs_vfs_setattr,
+};
+
+static const struct inode_operations v9fs_symlink_inode_operations = {
+ .get_link = v9fs_vfs_get_link,
+ .getattr = v9fs_vfs_getattr,
+ .setattr = v9fs_vfs_setattr,
+};
+
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
new file mode 100644
index 000000000..5cfa4b4f0
--- /dev/null
+++ b/fs/9p/vfs_inode_dotl.c
@@ -0,0 +1,1001 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * This file contains vfs inode ops for the 9P2000.L protocol.
+ *
+ * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/pagemap.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/inet.h>
+#include <linux/namei.h>
+#include <linux/idr.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/xattr.h>
+#include <linux/posix_acl.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+#include "cache.h"
+#include "xattr.h"
+#include "acl.h"
+
+static int
+v9fs_vfs_mknod_dotl(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t omode, dev_t rdev);
+
+/**
+ * v9fs_get_fsgid_for_create - Helper function to get the gid for a new object
+ * @dir_inode: The directory inode
+ *
+ * Helper function to get the gid for creating a
+ * new file system object. This checks the S_ISGID to determine the owning
+ * group of the new file system object.
+ */
+
+static kgid_t v9fs_get_fsgid_for_create(struct inode *dir_inode)
+{
+ BUG_ON(dir_inode == NULL);
+
+ if (dir_inode->i_mode & S_ISGID) {
+ /* set_gid bit is set.*/
+ return dir_inode->i_gid;
+ }
+ return current_fsgid();
+}
+
+static int v9fs_test_inode_dotl(struct inode *inode, void *data)
+{
+ struct v9fs_inode *v9inode = V9FS_I(inode);
+ struct p9_stat_dotl *st = (struct p9_stat_dotl *)data;
+
+ /* don't match inode of different type */
+ if (inode_wrong_type(inode, st->st_mode))
+ return 0;
+
+ if (inode->i_generation != st->st_gen)
+ return 0;
+
+ /* compare qid details */
+ if (memcmp(&v9inode->qid.version,
+ &st->qid.version, sizeof(v9inode->qid.version)))
+ return 0;
+
+ if (v9inode->qid.type != st->qid.type)
+ return 0;
+
+ if (v9inode->qid.path != st->qid.path)
+ return 0;
+ return 1;
+}
+
+/* Always get a new inode */
+static int v9fs_test_new_inode_dotl(struct inode *inode, void *data)
+{
+ return 0;
+}
+
+static int v9fs_set_inode_dotl(struct inode *inode, void *data)
+{
+ struct v9fs_inode *v9inode = V9FS_I(inode);
+ struct p9_stat_dotl *st = (struct p9_stat_dotl *)data;
+
+ memcpy(&v9inode->qid, &st->qid, sizeof(st->qid));
+ inode->i_generation = st->st_gen;
+ return 0;
+}
+
+static struct inode *v9fs_qid_iget_dotl(struct super_block *sb,
+ struct p9_qid *qid,
+ struct p9_fid *fid,
+ struct p9_stat_dotl *st,
+ int new)
+{
+ int retval;
+ unsigned long i_ino;
+ struct inode *inode;
+ struct v9fs_session_info *v9ses = sb->s_fs_info;
+ int (*test)(struct inode *inode, void *data);
+
+ if (new)
+ test = v9fs_test_new_inode_dotl;
+ else
+ test = v9fs_test_inode_dotl;
+
+ i_ino = v9fs_qid2ino(qid);
+ inode = iget5_locked(sb, i_ino, test, v9fs_set_inode_dotl, st);
+ if (!inode)
+ return ERR_PTR(-ENOMEM);
+ if (!(inode->i_state & I_NEW))
+ return inode;
+ /*
+ * initialize the inode with the stat info
+ * FIXME!! we may need support for stale inodes
+ * later.
+ */
+ inode->i_ino = i_ino;
+ retval = v9fs_init_inode(v9ses, inode,
+ st->st_mode, new_decode_dev(st->st_rdev));
+ if (retval)
+ goto error;
+
+ v9fs_stat2inode_dotl(st, inode, 0);
+ v9fs_cache_inode_get_cookie(inode);
+ retval = v9fs_get_acl(inode, fid);
+ if (retval)
+ goto error;
+
+ unlock_new_inode(inode);
+ return inode;
+error:
+ iget_failed(inode);
+ return ERR_PTR(retval);
+
+}
+
+struct inode *
+v9fs_inode_from_fid_dotl(struct v9fs_session_info *v9ses, struct p9_fid *fid,
+ struct super_block *sb, int new)
+{
+ struct p9_stat_dotl *st;
+ struct inode *inode = NULL;
+
+ st = p9_client_getattr_dotl(fid, P9_STATS_BASIC | P9_STATS_GEN);
+ if (IS_ERR(st))
+ return ERR_CAST(st);
+
+ inode = v9fs_qid_iget_dotl(sb, &st->qid, fid, st, new);
+ kfree(st);
+ return inode;
+}
+
+struct dotl_openflag_map {
+ int open_flag;
+ int dotl_flag;
+};
+
+static int v9fs_mapped_dotl_flags(int flags)
+{
+ int i;
+ int rflags = 0;
+ struct dotl_openflag_map dotl_oflag_map[] = {
+ { O_CREAT, P9_DOTL_CREATE },
+ { O_EXCL, P9_DOTL_EXCL },
+ { O_NOCTTY, P9_DOTL_NOCTTY },
+ { O_APPEND, P9_DOTL_APPEND },
+ { O_NONBLOCK, P9_DOTL_NONBLOCK },
+ { O_DSYNC, P9_DOTL_DSYNC },
+ { FASYNC, P9_DOTL_FASYNC },
+ { O_DIRECT, P9_DOTL_DIRECT },
+ { O_LARGEFILE, P9_DOTL_LARGEFILE },
+ { O_DIRECTORY, P9_DOTL_DIRECTORY },
+ { O_NOFOLLOW, P9_DOTL_NOFOLLOW },
+ { O_NOATIME, P9_DOTL_NOATIME },
+ { O_CLOEXEC, P9_DOTL_CLOEXEC },
+ { O_SYNC, P9_DOTL_SYNC},
+ };
+ for (i = 0; i < ARRAY_SIZE(dotl_oflag_map); i++) {
+ if (flags & dotl_oflag_map[i].open_flag)
+ rflags |= dotl_oflag_map[i].dotl_flag;
+ }
+ return rflags;
+}
+
+/**
+ * v9fs_open_to_dotl_flags- convert Linux specific open flags to
+ * plan 9 open flag.
+ * @flags: flags to convert
+ */
+int v9fs_open_to_dotl_flags(int flags)
+{
+ int rflags = 0;
+
+ /*
+ * We have same bits for P9_DOTL_READONLY, P9_DOTL_WRONLY
+ * and P9_DOTL_NOACCESS
+ */
+ rflags |= flags & O_ACCMODE;
+ rflags |= v9fs_mapped_dotl_flags(flags);
+
+ return rflags;
+}
+
+/**
+ * v9fs_vfs_create_dotl - VFS hook to create files for 9P2000.L protocol.
+ * @mnt_userns: The user namespace of the mount
+ * @dir: directory inode that is being created
+ * @dentry: dentry that is being deleted
+ * @omode: create permissions
+ * @excl: True if the file must not yet exist
+ *
+ */
+static int
+v9fs_vfs_create_dotl(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t omode, bool excl)
+{
+ return v9fs_vfs_mknod_dotl(mnt_userns, dir, dentry, omode, 0);
+}
+
+static int
+v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
+ struct file *file, unsigned int flags, umode_t omode)
+{
+ int err = 0;
+ kgid_t gid;
+ umode_t mode;
+ const unsigned char *name = NULL;
+ struct p9_qid qid;
+ struct inode *inode;
+ struct p9_fid *fid = NULL;
+ struct v9fs_inode *v9inode;
+ struct p9_fid *dfid = NULL, *ofid = NULL, *inode_fid = NULL;
+ struct v9fs_session_info *v9ses;
+ struct posix_acl *pacl = NULL, *dacl = NULL;
+ struct dentry *res = NULL;
+
+ if (d_in_lookup(dentry)) {
+ res = v9fs_vfs_lookup(dir, dentry, 0);
+ if (IS_ERR(res))
+ return PTR_ERR(res);
+
+ if (res)
+ dentry = res;
+ }
+
+ /* Only creates */
+ if (!(flags & O_CREAT) || d_really_is_positive(dentry))
+ return finish_no_open(file, res);
+
+ v9ses = v9fs_inode2v9ses(dir);
+
+ name = dentry->d_name.name;
+ p9_debug(P9_DEBUG_VFS, "name:%s flags:0x%x mode:0x%x\n",
+ name, flags, omode);
+
+ dfid = v9fs_parent_fid(dentry);
+ if (IS_ERR(dfid)) {
+ err = PTR_ERR(dfid);
+ p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", err);
+ goto out;
+ }
+
+ /* clone a fid to use for creation */
+ ofid = clone_fid(dfid);
+ if (IS_ERR(ofid)) {
+ err = PTR_ERR(ofid);
+ p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err);
+ goto out;
+ }
+
+ gid = v9fs_get_fsgid_for_create(dir);
+
+ mode = omode;
+ /* Update mode based on ACL value */
+ err = v9fs_acl_mode(dir, &mode, &dacl, &pacl);
+ if (err) {
+ p9_debug(P9_DEBUG_VFS, "Failed to get acl values in creat %d\n",
+ err);
+ goto out;
+ }
+ err = p9_client_create_dotl(ofid, name, v9fs_open_to_dotl_flags(flags),
+ mode, gid, &qid);
+ if (err < 0) {
+ p9_debug(P9_DEBUG_VFS, "p9_client_open_dotl failed in creat %d\n",
+ err);
+ goto out;
+ }
+ v9fs_invalidate_inode_attr(dir);
+
+ /* instantiate inode and assign the unopened fid to the dentry */
+ fid = p9_client_walk(dfid, 1, &name, 1);
+ if (IS_ERR(fid)) {
+ err = PTR_ERR(fid);
+ p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err);
+ goto out;
+ }
+ inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n", err);
+ goto out;
+ }
+ /* Now set the ACL based on the default value */
+ v9fs_set_create_acl(inode, fid, dacl, pacl);
+
+ v9fs_fid_add(dentry, &fid);
+ d_instantiate(dentry, inode);
+
+ v9inode = V9FS_I(inode);
+ mutex_lock(&v9inode->v_mutex);
+ if ((v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) &&
+ !v9inode->writeback_fid &&
+ ((flags & O_ACCMODE) != O_RDONLY)) {
+ /*
+ * clone a fid and add it to writeback_fid
+ * we do it during open time instead of
+ * page dirty time via write_begin/page_mkwrite
+ * because we want write after unlink usecase
+ * to work.
+ */
+ inode_fid = v9fs_writeback_fid(dentry);
+ if (IS_ERR(inode_fid)) {
+ err = PTR_ERR(inode_fid);
+ mutex_unlock(&v9inode->v_mutex);
+ goto out;
+ }
+ v9inode->writeback_fid = (void *) inode_fid;
+ }
+ mutex_unlock(&v9inode->v_mutex);
+ /* Since we are opening a file, assign the open fid to the file */
+ err = finish_open(file, dentry, generic_file_open);
+ if (err)
+ goto out;
+ file->private_data = ofid;
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
+ fscache_use_cookie(v9fs_inode_cookie(v9inode),
+ file->f_mode & FMODE_WRITE);
+ v9fs_open_fid_add(inode, &ofid);
+ file->f_mode |= FMODE_CREATED;
+out:
+ p9_fid_put(dfid);
+ p9_fid_put(ofid);
+ p9_fid_put(fid);
+ v9fs_put_acl(dacl, pacl);
+ dput(res);
+ return err;
+}
+
+/**
+ * v9fs_vfs_mkdir_dotl - VFS mkdir hook to create a directory
+ * @mnt_userns: The user namespace of the mount
+ * @dir: inode that is being unlinked
+ * @dentry: dentry that is being unlinked
+ * @omode: mode for new directory
+ *
+ */
+
+static int v9fs_vfs_mkdir_dotl(struct user_namespace *mnt_userns,
+ struct inode *dir, struct dentry *dentry,
+ umode_t omode)
+{
+ int err;
+ struct v9fs_session_info *v9ses;
+ struct p9_fid *fid = NULL, *dfid = NULL;
+ kgid_t gid;
+ const unsigned char *name;
+ umode_t mode;
+ struct inode *inode;
+ struct p9_qid qid;
+ struct posix_acl *dacl = NULL, *pacl = NULL;
+
+ p9_debug(P9_DEBUG_VFS, "name %pd\n", dentry);
+ err = 0;
+ v9ses = v9fs_inode2v9ses(dir);
+
+ omode |= S_IFDIR;
+ if (dir->i_mode & S_ISGID)
+ omode |= S_ISGID;
+
+ dfid = v9fs_parent_fid(dentry);
+ if (IS_ERR(dfid)) {
+ err = PTR_ERR(dfid);
+ p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", err);
+ goto error;
+ }
+
+ gid = v9fs_get_fsgid_for_create(dir);
+ mode = omode;
+ /* Update mode based on ACL value */
+ err = v9fs_acl_mode(dir, &mode, &dacl, &pacl);
+ if (err) {
+ p9_debug(P9_DEBUG_VFS, "Failed to get acl values in mkdir %d\n",
+ err);
+ goto error;
+ }
+ name = dentry->d_name.name;
+ err = p9_client_mkdir_dotl(dfid, name, mode, gid, &qid);
+ if (err < 0)
+ goto error;
+ fid = p9_client_walk(dfid, 1, &name, 1);
+ if (IS_ERR(fid)) {
+ err = PTR_ERR(fid);
+ p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n",
+ err);
+ goto error;
+ }
+
+ /* instantiate inode and assign the unopened fid to the dentry */
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
+ inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n",
+ err);
+ goto error;
+ }
+ v9fs_fid_add(dentry, &fid);
+ v9fs_set_create_acl(inode, fid, dacl, pacl);
+ d_instantiate(dentry, inode);
+ err = 0;
+ } else {
+ /*
+ * Not in cached mode. No need to populate
+ * inode with stat. We need to get an inode
+ * so that we can set the acl with dentry
+ */
+ inode = v9fs_get_inode(dir->i_sb, mode, 0);
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ goto error;
+ }
+ v9fs_set_create_acl(inode, fid, dacl, pacl);
+ d_instantiate(dentry, inode);
+ }
+ inc_nlink(dir);
+ v9fs_invalidate_inode_attr(dir);
+error:
+ p9_fid_put(fid);
+ v9fs_put_acl(dacl, pacl);
+ p9_fid_put(dfid);
+ return err;
+}
+
+static int
+v9fs_vfs_getattr_dotl(struct user_namespace *mnt_userns,
+ const struct path *path, struct kstat *stat,
+ u32 request_mask, unsigned int flags)
+{
+ struct dentry *dentry = path->dentry;
+ struct v9fs_session_info *v9ses;
+ struct p9_fid *fid;
+ struct p9_stat_dotl *st;
+
+ p9_debug(P9_DEBUG_VFS, "dentry: %p\n", dentry);
+ v9ses = v9fs_dentry2v9ses(dentry);
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
+ generic_fillattr(&init_user_ns, d_inode(dentry), stat);
+ return 0;
+ }
+ fid = v9fs_fid_lookup(dentry);
+ if (IS_ERR(fid))
+ return PTR_ERR(fid);
+
+ /* Ask for all the fields in stat structure. Server will return
+ * whatever it supports
+ */
+
+ st = p9_client_getattr_dotl(fid, P9_STATS_ALL);
+ p9_fid_put(fid);
+ if (IS_ERR(st))
+ return PTR_ERR(st);
+
+ v9fs_stat2inode_dotl(st, d_inode(dentry), 0);
+ generic_fillattr(&init_user_ns, d_inode(dentry), stat);
+ /* Change block size to what the server returned */
+ stat->blksize = st->st_blksize;
+
+ kfree(st);
+ return 0;
+}
+
+/*
+ * Attribute flags.
+ */
+#define P9_ATTR_MODE (1 << 0)
+#define P9_ATTR_UID (1 << 1)
+#define P9_ATTR_GID (1 << 2)
+#define P9_ATTR_SIZE (1 << 3)
+#define P9_ATTR_ATIME (1 << 4)
+#define P9_ATTR_MTIME (1 << 5)
+#define P9_ATTR_CTIME (1 << 6)
+#define P9_ATTR_ATIME_SET (1 << 7)
+#define P9_ATTR_MTIME_SET (1 << 8)
+
+struct dotl_iattr_map {
+ int iattr_valid;
+ int p9_iattr_valid;
+};
+
+static int v9fs_mapped_iattr_valid(int iattr_valid)
+{
+ int i;
+ int p9_iattr_valid = 0;
+ struct dotl_iattr_map dotl_iattr_map[] = {
+ { ATTR_MODE, P9_ATTR_MODE },
+ { ATTR_UID, P9_ATTR_UID },
+ { ATTR_GID, P9_ATTR_GID },
+ { ATTR_SIZE, P9_ATTR_SIZE },
+ { ATTR_ATIME, P9_ATTR_ATIME },
+ { ATTR_MTIME, P9_ATTR_MTIME },
+ { ATTR_CTIME, P9_ATTR_CTIME },
+ { ATTR_ATIME_SET, P9_ATTR_ATIME_SET },
+ { ATTR_MTIME_SET, P9_ATTR_MTIME_SET },
+ };
+ for (i = 0; i < ARRAY_SIZE(dotl_iattr_map); i++) {
+ if (iattr_valid & dotl_iattr_map[i].iattr_valid)
+ p9_iattr_valid |= dotl_iattr_map[i].p9_iattr_valid;
+ }
+ return p9_iattr_valid;
+}
+
+/**
+ * v9fs_vfs_setattr_dotl - set file metadata
+ * @mnt_userns: The user namespace of the mount
+ * @dentry: file whose metadata to set
+ * @iattr: metadata assignment structure
+ *
+ */
+
+int v9fs_vfs_setattr_dotl(struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct iattr *iattr)
+{
+ int retval, use_dentry = 0;
+ struct p9_fid *fid = NULL;
+ struct p9_iattr_dotl p9attr = {
+ .uid = INVALID_UID,
+ .gid = INVALID_GID,
+ };
+ struct inode *inode = d_inode(dentry);
+
+ p9_debug(P9_DEBUG_VFS, "\n");
+
+ retval = setattr_prepare(&init_user_ns, dentry, iattr);
+ if (retval)
+ return retval;
+
+ p9attr.valid = v9fs_mapped_iattr_valid(iattr->ia_valid);
+ if (iattr->ia_valid & ATTR_MODE)
+ p9attr.mode = iattr->ia_mode;
+ if (iattr->ia_valid & ATTR_UID)
+ p9attr.uid = iattr->ia_uid;
+ if (iattr->ia_valid & ATTR_GID)
+ p9attr.gid = iattr->ia_gid;
+ if (iattr->ia_valid & ATTR_SIZE)
+ p9attr.size = iattr->ia_size;
+ if (iattr->ia_valid & ATTR_ATIME_SET) {
+ p9attr.atime_sec = iattr->ia_atime.tv_sec;
+ p9attr.atime_nsec = iattr->ia_atime.tv_nsec;
+ }
+ if (iattr->ia_valid & ATTR_MTIME_SET) {
+ p9attr.mtime_sec = iattr->ia_mtime.tv_sec;
+ p9attr.mtime_nsec = iattr->ia_mtime.tv_nsec;
+ }
+
+ if (iattr->ia_valid & ATTR_FILE) {
+ fid = iattr->ia_file->private_data;
+ WARN_ON(!fid);
+ }
+ if (!fid) {
+ fid = v9fs_fid_lookup(dentry);
+ use_dentry = 1;
+ }
+ if (IS_ERR(fid))
+ return PTR_ERR(fid);
+
+ /* Write all dirty data */
+ if (S_ISREG(inode->i_mode))
+ filemap_write_and_wait(inode->i_mapping);
+
+ retval = p9_client_setattr(fid, &p9attr);
+ if (retval < 0) {
+ if (use_dentry)
+ p9_fid_put(fid);
+ return retval;
+ }
+
+ if ((iattr->ia_valid & ATTR_SIZE) &&
+ iattr->ia_size != i_size_read(inode))
+ truncate_setsize(inode, iattr->ia_size);
+
+ v9fs_invalidate_inode_attr(inode);
+ setattr_copy(&init_user_ns, inode, iattr);
+ mark_inode_dirty(inode);
+ if (iattr->ia_valid & ATTR_MODE) {
+ /* We also want to update ACL when we update mode bits */
+ retval = v9fs_acl_chmod(inode, fid);
+ if (retval < 0) {
+ if (use_dentry)
+ p9_fid_put(fid);
+ return retval;
+ }
+ }
+ if (use_dentry)
+ p9_fid_put(fid);
+
+ return 0;
+}
+
+/**
+ * v9fs_stat2inode_dotl - populate an inode structure with stat info
+ * @stat: stat structure
+ * @inode: inode to populate
+ * @flags: ctrl flags (e.g. V9FS_STAT2INODE_KEEP_ISIZE)
+ *
+ */
+
+void
+v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode,
+ unsigned int flags)
+{
+ umode_t mode;
+ struct v9fs_inode *v9inode = V9FS_I(inode);
+
+ if ((stat->st_result_mask & P9_STATS_BASIC) == P9_STATS_BASIC) {
+ inode->i_atime.tv_sec = stat->st_atime_sec;
+ inode->i_atime.tv_nsec = stat->st_atime_nsec;
+ inode->i_mtime.tv_sec = stat->st_mtime_sec;
+ inode->i_mtime.tv_nsec = stat->st_mtime_nsec;
+ inode->i_ctime.tv_sec = stat->st_ctime_sec;
+ inode->i_ctime.tv_nsec = stat->st_ctime_nsec;
+ inode->i_uid = stat->st_uid;
+ inode->i_gid = stat->st_gid;
+ set_nlink(inode, stat->st_nlink);
+
+ mode = stat->st_mode & S_IALLUGO;
+ mode |= inode->i_mode & ~S_IALLUGO;
+ inode->i_mode = mode;
+
+ if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE))
+ v9fs_i_size_write(inode, stat->st_size);
+ inode->i_blocks = stat->st_blocks;
+ } else {
+ if (stat->st_result_mask & P9_STATS_ATIME) {
+ inode->i_atime.tv_sec = stat->st_atime_sec;
+ inode->i_atime.tv_nsec = stat->st_atime_nsec;
+ }
+ if (stat->st_result_mask & P9_STATS_MTIME) {
+ inode->i_mtime.tv_sec = stat->st_mtime_sec;
+ inode->i_mtime.tv_nsec = stat->st_mtime_nsec;
+ }
+ if (stat->st_result_mask & P9_STATS_CTIME) {
+ inode->i_ctime.tv_sec = stat->st_ctime_sec;
+ inode->i_ctime.tv_nsec = stat->st_ctime_nsec;
+ }
+ if (stat->st_result_mask & P9_STATS_UID)
+ inode->i_uid = stat->st_uid;
+ if (stat->st_result_mask & P9_STATS_GID)
+ inode->i_gid = stat->st_gid;
+ if (stat->st_result_mask & P9_STATS_NLINK)
+ set_nlink(inode, stat->st_nlink);
+ if (stat->st_result_mask & P9_STATS_MODE) {
+ mode = stat->st_mode & S_IALLUGO;
+ mode |= inode->i_mode & ~S_IALLUGO;
+ inode->i_mode = mode;
+ }
+ if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE) &&
+ stat->st_result_mask & P9_STATS_SIZE)
+ v9fs_i_size_write(inode, stat->st_size);
+ if (stat->st_result_mask & P9_STATS_BLOCKS)
+ inode->i_blocks = stat->st_blocks;
+ }
+ if (stat->st_result_mask & P9_STATS_GEN)
+ inode->i_generation = stat->st_gen;
+
+ /* Currently we don't support P9_STATS_BTIME and P9_STATS_DATA_VERSION
+ * because the inode structure does not have fields for them.
+ */
+ v9inode->cache_validity &= ~V9FS_INO_INVALID_ATTR;
+}
+
+static int
+v9fs_vfs_symlink_dotl(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, const char *symname)
+{
+ int err;
+ kgid_t gid;
+ const unsigned char *name;
+ struct p9_qid qid;
+ struct inode *inode;
+ struct p9_fid *dfid;
+ struct p9_fid *fid = NULL;
+ struct v9fs_session_info *v9ses;
+
+ name = dentry->d_name.name;
+ p9_debug(P9_DEBUG_VFS, "%lu,%s,%s\n", dir->i_ino, name, symname);
+ v9ses = v9fs_inode2v9ses(dir);
+
+ dfid = v9fs_parent_fid(dentry);
+ if (IS_ERR(dfid)) {
+ err = PTR_ERR(dfid);
+ p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", err);
+ return err;
+ }
+
+ gid = v9fs_get_fsgid_for_create(dir);
+
+ /* Server doesn't alter fid on TSYMLINK. Hence no need to clone it. */
+ err = p9_client_symlink(dfid, name, symname, gid, &qid);
+
+ if (err < 0) {
+ p9_debug(P9_DEBUG_VFS, "p9_client_symlink failed %d\n", err);
+ goto error;
+ }
+
+ v9fs_invalidate_inode_attr(dir);
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
+ /* Now walk from the parent so we can get an unopened fid. */
+ fid = p9_client_walk(dfid, 1, &name, 1);
+ if (IS_ERR(fid)) {
+ err = PTR_ERR(fid);
+ p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n",
+ err);
+ goto error;
+ }
+
+ /* instantiate inode and assign the unopened fid to dentry */
+ inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n",
+ err);
+ goto error;
+ }
+ v9fs_fid_add(dentry, &fid);
+ d_instantiate(dentry, inode);
+ err = 0;
+ } else {
+ /* Not in cached mode. No need to populate inode with stat */
+ inode = v9fs_get_inode(dir->i_sb, S_IFLNK, 0);
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ goto error;
+ }
+ d_instantiate(dentry, inode);
+ }
+
+error:
+ p9_fid_put(fid);
+ p9_fid_put(dfid);
+ return err;
+}
+
+/**
+ * v9fs_vfs_link_dotl - create a hardlink for dotl
+ * @old_dentry: dentry for file to link to
+ * @dir: inode destination for new link
+ * @dentry: dentry for link
+ *
+ */
+
+static int
+v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir,
+ struct dentry *dentry)
+{
+ int err;
+ struct p9_fid *dfid, *oldfid;
+ struct v9fs_session_info *v9ses;
+
+ p9_debug(P9_DEBUG_VFS, "dir ino: %lu, old_name: %pd, new_name: %pd\n",
+ dir->i_ino, old_dentry, dentry);
+
+ v9ses = v9fs_inode2v9ses(dir);
+ dfid = v9fs_parent_fid(dentry);
+ if (IS_ERR(dfid))
+ return PTR_ERR(dfid);
+
+ oldfid = v9fs_fid_lookup(old_dentry);
+ if (IS_ERR(oldfid)) {
+ p9_fid_put(dfid);
+ return PTR_ERR(oldfid);
+ }
+
+ err = p9_client_link(dfid, oldfid, dentry->d_name.name);
+
+ p9_fid_put(dfid);
+ p9_fid_put(oldfid);
+ if (err < 0) {
+ p9_debug(P9_DEBUG_VFS, "p9_client_link failed %d\n", err);
+ return err;
+ }
+
+ v9fs_invalidate_inode_attr(dir);
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
+ /* Get the latest stat info from server. */
+ struct p9_fid *fid;
+
+ fid = v9fs_fid_lookup(old_dentry);
+ if (IS_ERR(fid))
+ return PTR_ERR(fid);
+
+ v9fs_refresh_inode_dotl(fid, d_inode(old_dentry));
+ p9_fid_put(fid);
+ }
+ ihold(d_inode(old_dentry));
+ d_instantiate(dentry, d_inode(old_dentry));
+
+ return err;
+}
+
+/**
+ * v9fs_vfs_mknod_dotl - create a special file
+ * @mnt_userns: The user namespace of the mount
+ * @dir: inode destination for new link
+ * @dentry: dentry for file
+ * @omode: mode for creation
+ * @rdev: device associated with special file
+ *
+ */
+static int
+v9fs_vfs_mknod_dotl(struct user_namespace *mnt_userns, struct inode *dir,
+ struct dentry *dentry, umode_t omode, dev_t rdev)
+{
+ int err;
+ kgid_t gid;
+ const unsigned char *name;
+ umode_t mode;
+ struct v9fs_session_info *v9ses;
+ struct p9_fid *fid = NULL, *dfid = NULL;
+ struct inode *inode;
+ struct p9_qid qid;
+ struct posix_acl *dacl = NULL, *pacl = NULL;
+
+ p9_debug(P9_DEBUG_VFS, " %lu,%pd mode: %x MAJOR: %u MINOR: %u\n",
+ dir->i_ino, dentry, omode,
+ MAJOR(rdev), MINOR(rdev));
+
+ v9ses = v9fs_inode2v9ses(dir);
+ dfid = v9fs_parent_fid(dentry);
+ if (IS_ERR(dfid)) {
+ err = PTR_ERR(dfid);
+ p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", err);
+ goto error;
+ }
+
+ gid = v9fs_get_fsgid_for_create(dir);
+ mode = omode;
+ /* Update mode based on ACL value */
+ err = v9fs_acl_mode(dir, &mode, &dacl, &pacl);
+ if (err) {
+ p9_debug(P9_DEBUG_VFS, "Failed to get acl values in mknod %d\n",
+ err);
+ goto error;
+ }
+ name = dentry->d_name.name;
+
+ err = p9_client_mknod_dotl(dfid, name, mode, rdev, gid, &qid);
+ if (err < 0)
+ goto error;
+
+ v9fs_invalidate_inode_attr(dir);
+ fid = p9_client_walk(dfid, 1, &name, 1);
+ if (IS_ERR(fid)) {
+ err = PTR_ERR(fid);
+ p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n",
+ err);
+ goto error;
+ }
+
+ /* instantiate inode and assign the unopened fid to the dentry */
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
+ inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n",
+ err);
+ goto error;
+ }
+ v9fs_set_create_acl(inode, fid, dacl, pacl);
+ v9fs_fid_add(dentry, &fid);
+ d_instantiate(dentry, inode);
+ err = 0;
+ } else {
+ /*
+ * Not in cached mode. No need to populate inode with stat.
+ * socket syscall returns a fd, so we need instantiate
+ */
+ inode = v9fs_get_inode(dir->i_sb, mode, rdev);
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ goto error;
+ }
+ v9fs_set_create_acl(inode, fid, dacl, pacl);
+ d_instantiate(dentry, inode);
+ }
+error:
+ p9_fid_put(fid);
+ v9fs_put_acl(dacl, pacl);
+ p9_fid_put(dfid);
+
+ return err;
+}
+
+/**
+ * v9fs_vfs_get_link_dotl - follow a symlink path
+ * @dentry: dentry for symlink
+ * @inode: inode for symlink
+ * @done: destructor for return value
+ */
+
+static const char *
+v9fs_vfs_get_link_dotl(struct dentry *dentry,
+ struct inode *inode,
+ struct delayed_call *done)
+{
+ struct p9_fid *fid;
+ char *target;
+ int retval;
+
+ if (!dentry)
+ return ERR_PTR(-ECHILD);
+
+ p9_debug(P9_DEBUG_VFS, "%pd\n", dentry);
+
+ fid = v9fs_fid_lookup(dentry);
+ if (IS_ERR(fid))
+ return ERR_CAST(fid);
+ retval = p9_client_readlink(fid, &target);
+ p9_fid_put(fid);
+ if (retval)
+ return ERR_PTR(retval);
+ set_delayed_call(done, kfree_link, target);
+ return target;
+}
+
+int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode)
+{
+ struct p9_stat_dotl *st;
+ struct v9fs_session_info *v9ses;
+ unsigned int flags;
+
+ v9ses = v9fs_inode2v9ses(inode);
+ st = p9_client_getattr_dotl(fid, P9_STATS_ALL);
+ if (IS_ERR(st))
+ return PTR_ERR(st);
+ /*
+ * Don't update inode if the file type is different
+ */
+ if (inode_wrong_type(inode, st->st_mode))
+ goto out;
+
+ /*
+ * We don't want to refresh inode->i_size,
+ * because we may have cached data
+ */
+ flags = (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) ?
+ V9FS_STAT2INODE_KEEP_ISIZE : 0;
+ v9fs_stat2inode_dotl(st, inode, flags);
+out:
+ kfree(st);
+ return 0;
+}
+
+const struct inode_operations v9fs_dir_inode_operations_dotl = {
+ .create = v9fs_vfs_create_dotl,
+ .atomic_open = v9fs_vfs_atomic_open_dotl,
+ .lookup = v9fs_vfs_lookup,
+ .link = v9fs_vfs_link_dotl,
+ .symlink = v9fs_vfs_symlink_dotl,
+ .unlink = v9fs_vfs_unlink,
+ .mkdir = v9fs_vfs_mkdir_dotl,
+ .rmdir = v9fs_vfs_rmdir,
+ .mknod = v9fs_vfs_mknod_dotl,
+ .rename = v9fs_vfs_rename,
+ .getattr = v9fs_vfs_getattr_dotl,
+ .setattr = v9fs_vfs_setattr_dotl,
+ .listxattr = v9fs_listxattr,
+ .get_acl = v9fs_iop_get_acl,
+};
+
+const struct inode_operations v9fs_file_inode_operations_dotl = {
+ .getattr = v9fs_vfs_getattr_dotl,
+ .setattr = v9fs_vfs_setattr_dotl,
+ .listxattr = v9fs_listxattr,
+ .get_acl = v9fs_iop_get_acl,
+};
+
+const struct inode_operations v9fs_symlink_inode_operations_dotl = {
+ .get_link = v9fs_vfs_get_link_dotl,
+ .getattr = v9fs_vfs_getattr_dotl,
+ .setattr = v9fs_vfs_setattr_dotl,
+ .listxattr = v9fs_listxattr,
+};
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
new file mode 100644
index 000000000..2d9ee073d
--- /dev/null
+++ b/fs/9p/vfs_super.c
@@ -0,0 +1,369 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *
+ * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/inet.h>
+#include <linux/pagemap.h>
+#include <linux/mount.h>
+#include <linux/idr.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/statfs.h>
+#include <linux/magic.h>
+#include <linux/fscache.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+#include "xattr.h"
+#include "acl.h"
+
+static const struct super_operations v9fs_super_ops, v9fs_super_ops_dotl;
+
+/**
+ * v9fs_set_super - set the superblock
+ * @s: super block
+ * @data: file system specific data
+ *
+ */
+
+static int v9fs_set_super(struct super_block *s, void *data)
+{
+ s->s_fs_info = data;
+ return set_anon_super(s, data);
+}
+
+/**
+ * v9fs_fill_super - populate superblock with info
+ * @sb: superblock
+ * @v9ses: session information
+ * @flags: flags propagated from v9fs_mount()
+ *
+ */
+
+static int
+v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
+ int flags)
+{
+ int ret;
+
+ sb->s_maxbytes = MAX_LFS_FILESIZE;
+ sb->s_blocksize_bits = fls(v9ses->maxdata - 1);
+ sb->s_blocksize = 1 << sb->s_blocksize_bits;
+ sb->s_magic = V9FS_MAGIC;
+ if (v9fs_proto_dotl(v9ses)) {
+ sb->s_op = &v9fs_super_ops_dotl;
+ sb->s_xattr = v9fs_xattr_handlers;
+ } else {
+ sb->s_op = &v9fs_super_ops;
+ sb->s_time_max = U32_MAX;
+ }
+
+ sb->s_time_min = 0;
+
+ ret = super_setup_bdi(sb);
+ if (ret)
+ return ret;
+
+ if (!v9ses->cache) {
+ sb->s_bdi->ra_pages = 0;
+ sb->s_bdi->io_pages = 0;
+ } else {
+ sb->s_bdi->ra_pages = v9ses->maxdata >> PAGE_SHIFT;
+ sb->s_bdi->io_pages = v9ses->maxdata >> PAGE_SHIFT;
+ }
+
+ sb->s_flags |= SB_ACTIVE | SB_DIRSYNC;
+ if (!v9ses->cache)
+ sb->s_flags |= SB_SYNCHRONOUS;
+
+#ifdef CONFIG_9P_FS_POSIX_ACL
+ if ((v9ses->flags & V9FS_ACL_MASK) == V9FS_POSIX_ACL)
+ sb->s_flags |= SB_POSIXACL;
+#endif
+
+ return 0;
+}
+
+/**
+ * v9fs_mount - mount a superblock
+ * @fs_type: file system type
+ * @flags: mount flags
+ * @dev_name: device name that was mounted
+ * @data: mount options
+ *
+ */
+
+static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
+ const char *dev_name, void *data)
+{
+ struct super_block *sb = NULL;
+ struct inode *inode = NULL;
+ struct dentry *root = NULL;
+ struct v9fs_session_info *v9ses = NULL;
+ umode_t mode = 0777 | S_ISVTX;
+ struct p9_fid *fid;
+ int retval = 0;
+
+ p9_debug(P9_DEBUG_VFS, "\n");
+
+ v9ses = kzalloc(sizeof(struct v9fs_session_info), GFP_KERNEL);
+ if (!v9ses)
+ return ERR_PTR(-ENOMEM);
+
+ fid = v9fs_session_init(v9ses, dev_name, data);
+ if (IS_ERR(fid)) {
+ retval = PTR_ERR(fid);
+ goto free_session;
+ }
+
+ sb = sget(fs_type, NULL, v9fs_set_super, flags, v9ses);
+ if (IS_ERR(sb)) {
+ retval = PTR_ERR(sb);
+ goto clunk_fid;
+ }
+ retval = v9fs_fill_super(sb, v9ses, flags);
+ if (retval)
+ goto release_sb;
+
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
+ sb->s_d_op = &v9fs_cached_dentry_operations;
+ else
+ sb->s_d_op = &v9fs_dentry_operations;
+
+ inode = v9fs_get_inode(sb, S_IFDIR | mode, 0);
+ if (IS_ERR(inode)) {
+ retval = PTR_ERR(inode);
+ goto release_sb;
+ }
+
+ root = d_make_root(inode);
+ if (!root) {
+ retval = -ENOMEM;
+ goto release_sb;
+ }
+ sb->s_root = root;
+ if (v9fs_proto_dotl(v9ses)) {
+ struct p9_stat_dotl *st = NULL;
+
+ st = p9_client_getattr_dotl(fid, P9_STATS_BASIC);
+ if (IS_ERR(st)) {
+ retval = PTR_ERR(st);
+ goto release_sb;
+ }
+ d_inode(root)->i_ino = v9fs_qid2ino(&st->qid);
+ v9fs_stat2inode_dotl(st, d_inode(root), 0);
+ kfree(st);
+ } else {
+ struct p9_wstat *st = NULL;
+
+ st = p9_client_stat(fid);
+ if (IS_ERR(st)) {
+ retval = PTR_ERR(st);
+ goto release_sb;
+ }
+
+ d_inode(root)->i_ino = v9fs_qid2ino(&st->qid);
+ v9fs_stat2inode(st, d_inode(root), sb, 0);
+
+ p9stat_free(st);
+ kfree(st);
+ }
+ retval = v9fs_get_acl(inode, fid);
+ if (retval)
+ goto release_sb;
+ v9fs_fid_add(root, &fid);
+
+ p9_debug(P9_DEBUG_VFS, " simple set mount, return 0\n");
+ return dget(sb->s_root);
+
+clunk_fid:
+ p9_fid_put(fid);
+ v9fs_session_close(v9ses);
+free_session:
+ kfree(v9ses);
+ return ERR_PTR(retval);
+
+release_sb:
+ /*
+ * we will do the session_close and root dentry release
+ * in the below call. But we need to clunk fid, because we haven't
+ * attached the fid to dentry so it won't get clunked
+ * automatically.
+ */
+ p9_fid_put(fid);
+ deactivate_locked_super(sb);
+ return ERR_PTR(retval);
+}
+
+/**
+ * v9fs_kill_super - Kill Superblock
+ * @s: superblock
+ *
+ */
+
+static void v9fs_kill_super(struct super_block *s)
+{
+ struct v9fs_session_info *v9ses = s->s_fs_info;
+
+ p9_debug(P9_DEBUG_VFS, " %p\n", s);
+
+ kill_anon_super(s);
+
+ v9fs_session_cancel(v9ses);
+ v9fs_session_close(v9ses);
+ kfree(v9ses);
+ s->s_fs_info = NULL;
+ p9_debug(P9_DEBUG_VFS, "exiting kill_super\n");
+}
+
+static void
+v9fs_umount_begin(struct super_block *sb)
+{
+ struct v9fs_session_info *v9ses;
+
+ v9ses = sb->s_fs_info;
+ v9fs_session_begin_cancel(v9ses);
+}
+
+static int v9fs_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+ struct v9fs_session_info *v9ses;
+ struct p9_fid *fid;
+ struct p9_rstatfs rs;
+ int res;
+
+ fid = v9fs_fid_lookup(dentry);
+ if (IS_ERR(fid)) {
+ res = PTR_ERR(fid);
+ goto done;
+ }
+
+ v9ses = v9fs_dentry2v9ses(dentry);
+ if (v9fs_proto_dotl(v9ses)) {
+ res = p9_client_statfs(fid, &rs);
+ if (res == 0) {
+ buf->f_type = rs.type;
+ buf->f_bsize = rs.bsize;
+ buf->f_blocks = rs.blocks;
+ buf->f_bfree = rs.bfree;
+ buf->f_bavail = rs.bavail;
+ buf->f_files = rs.files;
+ buf->f_ffree = rs.ffree;
+ buf->f_fsid = u64_to_fsid(rs.fsid);
+ buf->f_namelen = rs.namelen;
+ }
+ if (res != -ENOSYS)
+ goto done;
+ }
+ res = simple_statfs(dentry, buf);
+done:
+ p9_fid_put(fid);
+ return res;
+}
+
+static int v9fs_drop_inode(struct inode *inode)
+{
+ struct v9fs_session_info *v9ses;
+
+ v9ses = v9fs_inode2v9ses(inode);
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
+ return generic_drop_inode(inode);
+ /*
+ * in case of non cached mode always drop the
+ * inode because we want the inode attribute
+ * to always match that on the server.
+ */
+ return 1;
+}
+
+static int v9fs_write_inode(struct inode *inode,
+ struct writeback_control *wbc)
+{
+ int ret;
+ struct p9_wstat wstat;
+ struct v9fs_inode *v9inode;
+ /*
+ * send an fsync request to server irrespective of
+ * wbc->sync_mode.
+ */
+ p9_debug(P9_DEBUG_VFS, "%s: inode %p\n", __func__, inode);
+ v9inode = V9FS_I(inode);
+ if (!v9inode->writeback_fid)
+ return 0;
+ v9fs_blank_wstat(&wstat);
+
+ ret = p9_client_wstat(v9inode->writeback_fid, &wstat);
+ if (ret < 0) {
+ __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+ return ret;
+ }
+ fscache_unpin_writeback(wbc, v9fs_inode_cookie(v9inode));
+ return 0;
+}
+
+static int v9fs_write_inode_dotl(struct inode *inode,
+ struct writeback_control *wbc)
+{
+ int ret;
+ struct v9fs_inode *v9inode;
+ /*
+ * send an fsync request to server irrespective of
+ * wbc->sync_mode.
+ */
+ v9inode = V9FS_I(inode);
+ p9_debug(P9_DEBUG_VFS, "%s: inode %p, writeback_fid %p\n",
+ __func__, inode, v9inode->writeback_fid);
+ if (!v9inode->writeback_fid)
+ return 0;
+
+ ret = p9_client_fsync(v9inode->writeback_fid, 0);
+ if (ret < 0) {
+ __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+ return ret;
+ }
+ fscache_unpin_writeback(wbc, v9fs_inode_cookie(v9inode));
+ return 0;
+}
+
+static const struct super_operations v9fs_super_ops = {
+ .alloc_inode = v9fs_alloc_inode,
+ .free_inode = v9fs_free_inode,
+ .statfs = simple_statfs,
+ .evict_inode = v9fs_evict_inode,
+ .show_options = v9fs_show_options,
+ .umount_begin = v9fs_umount_begin,
+ .write_inode = v9fs_write_inode,
+};
+
+static const struct super_operations v9fs_super_ops_dotl = {
+ .alloc_inode = v9fs_alloc_inode,
+ .free_inode = v9fs_free_inode,
+ .statfs = v9fs_statfs,
+ .drop_inode = v9fs_drop_inode,
+ .evict_inode = v9fs_evict_inode,
+ .show_options = v9fs_show_options,
+ .umount_begin = v9fs_umount_begin,
+ .write_inode = v9fs_write_inode_dotl,
+};
+
+struct file_system_type v9fs_fs_type = {
+ .name = "9p",
+ .mount = v9fs_mount,
+ .kill_sb = v9fs_kill_super,
+ .owner = THIS_MODULE,
+ .fs_flags = FS_RENAME_DOES_D_MOVE,
+};
+MODULE_ALIAS_FS("9p");
diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c
new file mode 100644
index 000000000..3b9aa61de
--- /dev/null
+++ b/fs/9p/xattr.c
@@ -0,0 +1,194 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/uio.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "fid.h"
+#include "xattr.h"
+
+ssize_t v9fs_fid_xattr_get(struct p9_fid *fid, const char *name,
+ void *buffer, size_t buffer_size)
+{
+ ssize_t retval;
+ u64 attr_size;
+ struct p9_fid *attr_fid;
+ struct kvec kvec = {.iov_base = buffer, .iov_len = buffer_size};
+ struct iov_iter to;
+ int err;
+
+ iov_iter_kvec(&to, ITER_DEST, &kvec, 1, buffer_size);
+
+ attr_fid = p9_client_xattrwalk(fid, name, &attr_size);
+ if (IS_ERR(attr_fid)) {
+ retval = PTR_ERR(attr_fid);
+ p9_debug(P9_DEBUG_VFS, "p9_client_attrwalk failed %zd\n",
+ retval);
+ return retval;
+ }
+ if (attr_size > buffer_size) {
+ if (!buffer_size) /* request to get the attr_size */
+ retval = attr_size;
+ else
+ retval = -ERANGE;
+ } else {
+ iov_iter_truncate(&to, attr_size);
+ retval = p9_client_read(attr_fid, 0, &to, &err);
+ if (err)
+ retval = err;
+ }
+ p9_fid_put(attr_fid);
+ return retval;
+}
+
+
+/*
+ * v9fs_xattr_get()
+ *
+ * Copy an extended attribute into the buffer
+ * provided, or compute the buffer size required.
+ * Buffer is NULL to compute the size of the buffer required.
+ *
+ * Returns a negative error number on failure, or the number of bytes
+ * used / required on success.
+ */
+ssize_t v9fs_xattr_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t buffer_size)
+{
+ struct p9_fid *fid;
+ int ret;
+
+ p9_debug(P9_DEBUG_VFS, "name = '%s' value_len = %zu\n",
+ name, buffer_size);
+ fid = v9fs_fid_lookup(dentry);
+ if (IS_ERR(fid))
+ return PTR_ERR(fid);
+ ret = v9fs_fid_xattr_get(fid, name, buffer, buffer_size);
+ p9_fid_put(fid);
+
+ return ret;
+}
+
+/*
+ * v9fs_xattr_set()
+ *
+ * Create, replace or remove an extended attribute for this inode. Buffer
+ * is NULL to remove an existing extended attribute, and non-NULL to
+ * either replace an existing extended attribute, or create a new extended
+ * attribute. The flags XATTR_REPLACE and XATTR_CREATE
+ * specify that an extended attribute must exist and must not exist
+ * previous to the call, respectively.
+ *
+ * Returns 0, or a negative error number on failure.
+ */
+int v9fs_xattr_set(struct dentry *dentry, const char *name,
+ const void *value, size_t value_len, int flags)
+{
+ int ret;
+ struct p9_fid *fid;
+
+ fid = v9fs_fid_lookup(dentry);
+ if (IS_ERR(fid))
+ return PTR_ERR(fid);
+ ret = v9fs_fid_xattr_set(fid, name, value, value_len, flags);
+ p9_fid_put(fid);
+ return ret;
+}
+
+int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name,
+ const void *value, size_t value_len, int flags)
+{
+ struct kvec kvec = {.iov_base = (void *)value, .iov_len = value_len};
+ struct iov_iter from;
+ int retval, err;
+
+ iov_iter_kvec(&from, ITER_SOURCE, &kvec, 1, value_len);
+
+ p9_debug(P9_DEBUG_VFS, "name = %s value_len = %zu flags = %d\n",
+ name, value_len, flags);
+
+ /* Clone it */
+ fid = clone_fid(fid);
+ if (IS_ERR(fid))
+ return PTR_ERR(fid);
+
+ /*
+ * On success fid points to xattr
+ */
+ retval = p9_client_xattrcreate(fid, name, value_len, flags);
+ if (retval < 0)
+ p9_debug(P9_DEBUG_VFS, "p9_client_xattrcreate failed %d\n",
+ retval);
+ else
+ p9_client_write(fid, 0, &from, &retval);
+ err = p9_fid_put(fid);
+ if (!retval && err)
+ retval = err;
+ return retval;
+}
+
+ssize_t v9fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
+{
+ /* Txattrwalk with an empty string lists xattrs instead */
+ return v9fs_xattr_get(dentry, "", buffer, buffer_size);
+}
+
+static int v9fs_xattr_handler_get(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, void *buffer, size_t size)
+{
+ const char *full_name = xattr_full_name(handler, name);
+
+ return v9fs_xattr_get(dentry, full_name, buffer, size);
+}
+
+static int v9fs_xattr_handler_set(const struct xattr_handler *handler,
+ struct user_namespace *mnt_userns,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
+{
+ const char *full_name = xattr_full_name(handler, name);
+
+ return v9fs_xattr_set(dentry, full_name, value, size, flags);
+}
+
+static struct xattr_handler v9fs_xattr_user_handler = {
+ .prefix = XATTR_USER_PREFIX,
+ .get = v9fs_xattr_handler_get,
+ .set = v9fs_xattr_handler_set,
+};
+
+static struct xattr_handler v9fs_xattr_trusted_handler = {
+ .prefix = XATTR_TRUSTED_PREFIX,
+ .get = v9fs_xattr_handler_get,
+ .set = v9fs_xattr_handler_set,
+};
+
+#ifdef CONFIG_9P_FS_SECURITY
+static struct xattr_handler v9fs_xattr_security_handler = {
+ .prefix = XATTR_SECURITY_PREFIX,
+ .get = v9fs_xattr_handler_get,
+ .set = v9fs_xattr_handler_set,
+};
+#endif
+
+const struct xattr_handler *v9fs_xattr_handlers[] = {
+ &v9fs_xattr_user_handler,
+ &v9fs_xattr_trusted_handler,
+#ifdef CONFIG_9P_FS_POSIX_ACL
+ &v9fs_xattr_acl_access_handler,
+ &v9fs_xattr_acl_default_handler,
+#endif
+#ifdef CONFIG_9P_FS_SECURITY
+ &v9fs_xattr_security_handler,
+#endif
+ NULL
+};
diff --git a/fs/9p/xattr.h b/fs/9p/xattr.h
new file mode 100644
index 000000000..3e11fc333
--- /dev/null
+++ b/fs/9p/xattr.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ */
+#ifndef FS_9P_XATTR_H
+#define FS_9P_XATTR_H
+
+#include <linux/xattr.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+
+extern const struct xattr_handler *v9fs_xattr_handlers[];
+extern const struct xattr_handler v9fs_xattr_acl_access_handler;
+extern const struct xattr_handler v9fs_xattr_acl_default_handler;
+
+ssize_t v9fs_fid_xattr_get(struct p9_fid *fid, const char *name,
+ void *buffer, size_t buffer_size);
+ssize_t v9fs_xattr_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t buffer_size);
+int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name,
+ const void *value, size_t value_len, int flags);
+int v9fs_xattr_set(struct dentry *dentry, const char *name,
+ const void *value, size_t value_len, int flags);
+ssize_t v9fs_listxattr(struct dentry *dentry, char *buffer,
+ size_t buffer_size);
+#endif /* FS_9P_XATTR_H */