Initial commit; kernel source import

fs/9p/Kconfig

@@ -0,0 +1,33 @@
+config 9P_FS
+	tristate "Plan 9 Resource Sharing Support (9P2000)"
+	depends on INET && NET_9P
+	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.
+
+	  To learn more about Access Control Lists, visit the POSIX ACLs for
+	  Linux website <http://acl.bestbits.at/>.
+
+	  If you don't know what Access Control Lists are, say N
+
+endif

fs/9p/Makefile

@@ -0,0 +1,17 @@
+obj-$(CONFIG_9P_FS) := 9p.o
+
+9p-objs := \
+	vfs_super.o \
+	vfs_inode.o \
+	vfs_inode_dotl.o \
+	vfs_addr.o \
+	vfs_file.o \
+	vfs_dir.o \
+	vfs_dentry.o \
+	v9fs.o \
+	fid.o  \
+	xattr.o \
+	xattr_user.o
+
+9p-$(CONFIG_9P_FSCACHE) += cache.o
+9p-$(CONFIG_9P_FS_POSIX_ACL) += acl.o

fs/9p/acl.c

@@ -0,0 +1,375 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+#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, POSIX_ACL_XATTR_DEFAULT);
+	pacl = __v9fs_get_acl(fid, POSIX_ACL_XATTR_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(acl == ACL_NOT_CACHED);
+	return acl;
+}
+
+struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type)
+{
+	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)) {
+		/*
+		 * 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 = POSIX_ACL_XATTR_ACCESS;
+		break;
+	case ACL_TYPE_DEFAULT:
+		name = POSIX_ACL_XATTR_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_remote_get_acl(struct dentry *dentry, const char *name,
+			       void *buffer, size_t size, int type)
+{
+	char *full_name;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		full_name =  POSIX_ACL_XATTR_ACCESS;
+		break;
+	case ACL_TYPE_DEFAULT:
+		full_name = POSIX_ACL_XATTR_DEFAULT;
+		break;
+	default:
+		BUG();
+	}
+	return v9fs_xattr_get(dentry, full_name, buffer, size);
+}
+
+static int v9fs_xattr_get_acl(struct dentry *dentry, const char *name,
+			      void *buffer, size_t size, int type)
+{
+	struct v9fs_session_info *v9ses;
+	struct posix_acl *acl;
+	int error;
+
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+
+	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_remote_get_acl(dentry, name, buffer, size, type);
+
+	acl = v9fs_get_cached_acl(dentry->d_inode, type);
+	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_remote_set_acl(struct dentry *dentry, const char *name,
+			      const void *value, size_t size,
+			      int flags, int type)
+{
+	char *full_name;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		full_name =  POSIX_ACL_XATTR_ACCESS;
+		break;
+	case ACL_TYPE_DEFAULT:
+		full_name = POSIX_ACL_XATTR_DEFAULT;
+		break;
+	default:
+		BUG();
+	}
+	return v9fs_xattr_set(dentry, full_name, value, size, flags);
+}
+
+
+static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name,
+			      const void *value, size_t size,
+			      int flags, int type)
+{
+	int retval;
+	struct posix_acl *acl;
+	struct v9fs_session_info *v9ses;
+	struct inode *inode = dentry->d_inode;
+
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+
+	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_remote_set_acl(dentry, name,
+					   value, size, flags, type);
+
+	if (S_ISLNK(inode->i_mode))
+		return -EOPNOTSUPP;
+	if (!inode_owner_or_capable(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(acl);
+			if (retval)
+				goto err_out;
+		}
+	} else
+		acl = NULL;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name = POSIX_ACL_XATTR_ACCESS;
+		if (acl) {
+			struct iattr iattr;
+
+			retval = posix_acl_update_mode(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.
+				 */
+				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(dentry, &iattr);
+		}
+		break;
+	case ACL_TYPE_DEFAULT:
+		name = POSIX_ACL_XATTR_DEFAULT;
+		if (!S_ISDIR(inode->i_mode)) {
+			retval = acl ? -EINVAL : 0;
+			goto err_out;
+		}
+		break;
+	default:
+		BUG();
+	}
+	retval = v9fs_xattr_set(dentry, name, value, size, flags);
+	if (!retval)
+		set_cached_acl(inode, type, acl);
+err_out:
+	posix_acl_release(acl);
+	return retval;
+}
+
+const struct xattr_handler v9fs_xattr_acl_access_handler = {
+	.prefix	= POSIX_ACL_XATTR_ACCESS,
+	.flags	= ACL_TYPE_ACCESS,
+	.get	= v9fs_xattr_get_acl,
+	.set	= v9fs_xattr_set_acl,
+};
+
+const struct xattr_handler v9fs_xattr_acl_default_handler = {
+	.prefix	= POSIX_ACL_XATTR_DEFAULT,
+	.flags	= ACL_TYPE_DEFAULT,
+	.get	= v9fs_xattr_get_acl,
+	.set	= v9fs_xattr_set_acl,
+};

fs/9p/acl.h

@@ -0,0 +1,55 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+#ifndef FS_9P_ACL_H
+#define FS_9P_ACL_H
+
+#ifdef CONFIG_9P_FS_POSIX_ACL
+extern int v9fs_get_acl(struct inode *, struct p9_fid *);
+extern struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type);
+extern int v9fs_acl_chmod(struct inode *, struct p9_fid *);
+extern int v9fs_set_create_acl(struct inode *, struct p9_fid *,
+			       struct posix_acl *, struct posix_acl *);
+extern int v9fs_acl_mode(struct inode *dir, umode_t *modep,
+			 struct posix_acl **dpacl, struct posix_acl **pacl);
+extern 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 */

fs/9p/cache.c

@@ -0,0 +1,415 @@
+/*
+ * V9FS cache definitions.
+ *
+ *  Copyright (C) 2009 by Abhishek Kulkarni <adkulkar@umail.iu.edu>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#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"
+
+#define CACHETAG_LEN  11
+
+struct fscache_netfs v9fs_cache_netfs = {
+	.name 		= "9p",
+	.version 	= 0,
+};
+
+/**
+ * v9fs_random_cachetag - Generate a random tag to be associated
+ *			  with a new cache session.
+ *
+ * The value of jiffies is used for a fairly randomly cache tag.
+ */
+
+static
+int v9fs_random_cachetag(struct v9fs_session_info *v9ses)
+{
+	v9ses->cachetag = kmalloc(CACHETAG_LEN, GFP_KERNEL);
+	if (!v9ses->cachetag)
+		return -ENOMEM;
+
+	return scnprintf(v9ses->cachetag, CACHETAG_LEN, "%lu", jiffies);
+}
+
+static uint16_t v9fs_cache_session_get_key(const void *cookie_netfs_data,
+					   void *buffer, uint16_t bufmax)
+{
+	struct v9fs_session_info *v9ses;
+	uint16_t klen = 0;
+
+	v9ses = (struct v9fs_session_info *)cookie_netfs_data;
+	p9_debug(P9_DEBUG_FSC, "session %p buf %p size %u\n",
+		 v9ses, buffer, bufmax);
+
+	if (v9ses->cachetag)
+		klen = strlen(v9ses->cachetag);
+
+	if (klen > bufmax)
+		return 0;
+
+	memcpy(buffer, v9ses->cachetag, klen);
+	p9_debug(P9_DEBUG_FSC, "cache session tag %s\n", v9ses->cachetag);
+	return klen;
+}
+
+const struct fscache_cookie_def v9fs_cache_session_index_def = {
+	.name		= "9P.session",
+	.type		= FSCACHE_COOKIE_TYPE_INDEX,
+	.get_key	= v9fs_cache_session_get_key,
+};
+
+void v9fs_cache_session_get_cookie(struct v9fs_session_info *v9ses)
+{
+	/* If no cache session tag was specified, we generate a random one. */
+	if (!v9ses->cachetag)
+		v9fs_random_cachetag(v9ses);
+
+	v9ses->fscache = fscache_acquire_cookie(v9fs_cache_netfs.primary_index,
+						&v9fs_cache_session_index_def,
+						v9ses);
+	p9_debug(P9_DEBUG_FSC, "session %p get cookie %p\n",
+		 v9ses, v9ses->fscache);
+}
+
+void v9fs_cache_session_put_cookie(struct v9fs_session_info *v9ses)
+{
+	p9_debug(P9_DEBUG_FSC, "session %p put cookie %p\n",
+		 v9ses, v9ses->fscache);
+	fscache_relinquish_cookie(v9ses->fscache, 0);
+	v9ses->fscache = NULL;
+}
+
+
+static uint16_t v9fs_cache_inode_get_key(const void *cookie_netfs_data,
+					 void *buffer, uint16_t bufmax)
+{
+	const struct v9fs_inode *v9inode = cookie_netfs_data;
+	memcpy(buffer, &v9inode->qid.path, sizeof(v9inode->qid.path));
+	p9_debug(P9_DEBUG_FSC, "inode %p get key %llu\n",
+		 &v9inode->vfs_inode, v9inode->qid.path);
+	return sizeof(v9inode->qid.path);
+}
+
+static void v9fs_cache_inode_get_attr(const void *cookie_netfs_data,
+				      uint64_t *size)
+{
+	const struct v9fs_inode *v9inode = cookie_netfs_data;
+	*size = i_size_read(&v9inode->vfs_inode);
+
+	p9_debug(P9_DEBUG_FSC, "inode %p get attr %llu\n",
+		 &v9inode->vfs_inode, *size);
+}
+
+static uint16_t v9fs_cache_inode_get_aux(const void *cookie_netfs_data,
+					 void *buffer, uint16_t buflen)
+{
+	const struct v9fs_inode *v9inode = cookie_netfs_data;
+	memcpy(buffer, &v9inode->qid.version, sizeof(v9inode->qid.version));
+	p9_debug(P9_DEBUG_FSC, "inode %p get aux %u\n",
+		 &v9inode->vfs_inode, v9inode->qid.version);
+	return sizeof(v9inode->qid.version);
+}
+
+static enum
+fscache_checkaux v9fs_cache_inode_check_aux(void *cookie_netfs_data,
+					    const void *buffer,
+					    uint16_t buflen)
+{
+	const struct v9fs_inode *v9inode = cookie_netfs_data;
+
+	if (buflen != sizeof(v9inode->qid.version))
+		return FSCACHE_CHECKAUX_OBSOLETE;
+
+	if (memcmp(buffer, &v9inode->qid.version,
+		   sizeof(v9inode->qid.version)))
+		return FSCACHE_CHECKAUX_OBSOLETE;
+
+	return FSCACHE_CHECKAUX_OKAY;
+}
+
+static void v9fs_cache_inode_now_uncached(void *cookie_netfs_data)
+{
+	struct v9fs_inode *v9inode = cookie_netfs_data;
+	struct pagevec pvec;
+	pgoff_t first;
+	int loop, nr_pages;
+
+	pagevec_init(&pvec, 0);
+	first = 0;
+
+	for (;;) {
+		nr_pages = pagevec_lookup(&pvec, v9inode->vfs_inode.i_mapping,
+					  first,
+					  PAGEVEC_SIZE - pagevec_count(&pvec));
+		if (!nr_pages)
+			break;
+
+		for (loop = 0; loop < nr_pages; loop++)
+			ClearPageFsCache(pvec.pages[loop]);
+
+		first = pvec.pages[nr_pages - 1]->index + 1;
+
+		pvec.nr = nr_pages;
+		pagevec_release(&pvec);
+		cond_resched();
+	}
+}
+
+const struct fscache_cookie_def v9fs_cache_inode_index_def = {
+	.name		= "9p.inode",
+	.type		= FSCACHE_COOKIE_TYPE_DATAFILE,
+	.get_key	= v9fs_cache_inode_get_key,
+	.get_attr	= v9fs_cache_inode_get_attr,
+	.get_aux	= v9fs_cache_inode_get_aux,
+	.check_aux	= v9fs_cache_inode_check_aux,
+	.now_uncached	= v9fs_cache_inode_now_uncached,
+};
+
+void v9fs_cache_inode_get_cookie(struct inode *inode)
+{
+	struct v9fs_inode *v9inode;
+	struct v9fs_session_info *v9ses;
+
+	if (!S_ISREG(inode->i_mode))
+		return;
+
+	v9inode = V9FS_I(inode);
+	if (v9inode->fscache)
+		return;
+
+	v9ses = v9fs_inode2v9ses(inode);
+	v9inode->fscache = fscache_acquire_cookie(v9ses->fscache,
+						  &v9fs_cache_inode_index_def,
+						  v9inode);
+
+	p9_debug(P9_DEBUG_FSC, "inode %p get cookie %p\n",
+		 inode, v9inode->fscache);
+}
+
+void v9fs_cache_inode_put_cookie(struct inode *inode)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	if (!v9inode->fscache)
+		return;
+	p9_debug(P9_DEBUG_FSC, "inode %p put cookie %p\n",
+		 inode, v9inode->fscache);
+
+	fscache_relinquish_cookie(v9inode->fscache, 0);
+	v9inode->fscache = NULL;
+}
+
+void v9fs_cache_inode_flush_cookie(struct inode *inode)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	if (!v9inode->fscache)
+		return;
+	p9_debug(P9_DEBUG_FSC, "inode %p flush cookie %p\n",
+		 inode, v9inode->fscache);
+
+	fscache_relinquish_cookie(v9inode->fscache, 1);
+	v9inode->fscache = NULL;
+}
+
+void v9fs_cache_inode_set_cookie(struct inode *inode, struct file *filp)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+	struct p9_fid *fid;
+
+	if (!v9inode->fscache)
+		return;
+
+	spin_lock(&v9inode->fscache_lock);
+	fid = filp->private_data;
+	if ((filp->f_flags & O_ACCMODE) != O_RDONLY)
+		v9fs_cache_inode_flush_cookie(inode);
+	else
+		v9fs_cache_inode_get_cookie(inode);
+
+	spin_unlock(&v9inode->fscache_lock);
+}
+
+void v9fs_cache_inode_reset_cookie(struct inode *inode)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+	struct v9fs_session_info *v9ses;
+	struct fscache_cookie *old;
+
+	if (!v9inode->fscache)
+		return;
+
+	old = v9inode->fscache;
+
+	spin_lock(&v9inode->fscache_lock);
+	fscache_relinquish_cookie(v9inode->fscache, 1);
+
+	v9ses = v9fs_inode2v9ses(inode);
+	v9inode->fscache = fscache_acquire_cookie(v9ses->fscache,
+						  &v9fs_cache_inode_index_def,
+						  v9inode);
+	p9_debug(P9_DEBUG_FSC, "inode %p revalidating cookie old %p new %p\n",
+		 inode, old, v9inode->fscache);
+
+	spin_unlock(&v9inode->fscache_lock);
+}
+
+int __v9fs_fscache_release_page(struct page *page, gfp_t gfp)
+{
+	struct inode *inode = page->mapping->host;
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	BUG_ON(!v9inode->fscache);
+
+	return fscache_maybe_release_page(v9inode->fscache, page, gfp);
+}
+
+void __v9fs_fscache_invalidate_page(struct page *page)
+{
+	struct inode *inode = page->mapping->host;
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	BUG_ON(!v9inode->fscache);
+
+	if (PageFsCache(page)) {
+		fscache_wait_on_page_write(v9inode->fscache, page);
+		BUG_ON(!PageLocked(page));
+		fscache_uncache_page(v9inode->fscache, page);
+	}
+}
+
+static void v9fs_vfs_readpage_complete(struct page *page, void *data,
+				       int error)
+{
+	if (!error)
+		SetPageUptodate(page);
+
+	unlock_page(page);
+}
+
+/**
+ * __v9fs_readpage_from_fscache - read a page from cache
+ *
+ * Returns 0 if the pages are in cache and a BIO is submitted,
+ * 1 if the pages are not in cache and -error otherwise.
+ */
+
+int __v9fs_readpage_from_fscache(struct inode *inode, struct page *page)
+{
+	int ret;
+	const struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	p9_debug(P9_DEBUG_FSC, "inode %p page %p\n", inode, page);
+	if (!v9inode->fscache)
+		return -ENOBUFS;
+
+	ret = fscache_read_or_alloc_page(v9inode->fscache,
+					 page,
+					 v9fs_vfs_readpage_complete,
+					 NULL,
+					 GFP_KERNEL);
+	switch (ret) {
+	case -ENOBUFS:
+	case -ENODATA:
+		p9_debug(P9_DEBUG_FSC, "page/inode not in cache %d\n", ret);
+		return 1;
+	case 0:
+		p9_debug(P9_DEBUG_FSC, "BIO submitted\n");
+		return ret;
+	default:
+		p9_debug(P9_DEBUG_FSC, "ret %d\n", ret);
+		return ret;
+	}
+}
+
+/**
+ * __v9fs_readpages_from_fscache - read multiple pages from cache
+ *
+ * Returns 0 if the pages are in cache and a BIO is submitted,
+ * 1 if the pages are not in cache and -error otherwise.
+ */
+
+int __v9fs_readpages_from_fscache(struct inode *inode,
+				  struct address_space *mapping,
+				  struct list_head *pages,
+				  unsigned *nr_pages)
+{
+	int ret;
+	const struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	p9_debug(P9_DEBUG_FSC, "inode %p pages %u\n", inode, *nr_pages);
+	if (!v9inode->fscache)
+		return -ENOBUFS;
+
+	ret = fscache_read_or_alloc_pages(v9inode->fscache,
+					  mapping, pages, nr_pages,
+					  v9fs_vfs_readpage_complete,
+					  NULL,
+					  mapping_gfp_mask(mapping));
+	switch (ret) {
+	case -ENOBUFS:
+	case -ENODATA:
+		p9_debug(P9_DEBUG_FSC, "pages/inodes not in cache %d\n", ret);
+		return 1;
+	case 0:
+		BUG_ON(!list_empty(pages));
+		BUG_ON(*nr_pages != 0);
+		p9_debug(P9_DEBUG_FSC, "BIO submitted\n");
+		return ret;
+	default:
+		p9_debug(P9_DEBUG_FSC, "ret %d\n", ret);
+		return ret;
+	}
+}
+
+/**
+ * __v9fs_readpage_to_fscache - write a page to the cache
+ *
+ */
+
+void __v9fs_readpage_to_fscache(struct inode *inode, struct page *page)
+{
+	int ret;
+	const struct v9fs_inode *v9inode = V9FS_I(inode);
+
+	p9_debug(P9_DEBUG_FSC, "inode %p page %p\n", inode, page);
+	ret = fscache_write_page(v9inode->fscache, page, GFP_KERNEL);
+	p9_debug(P9_DEBUG_FSC, "ret =  %d\n", ret);
+	if (ret != 0)
+		v9fs_uncache_page(inode, page);
+}
+
+/*
+ * wait for a page to complete writing to the cache
+ */
+void __v9fs_fscache_wait_on_page_write(struct inode *inode, struct page *page)
+{
+	const struct v9fs_inode *v9inode = V9FS_I(inode);
+	p9_debug(P9_DEBUG_FSC, "inode %p page %p\n", inode, page);
+	if (PageFsCache(page))
+		fscache_wait_on_page_write(v9inode->fscache, page);
+}

fs/9p/cache.h

@@ -0,0 +1,139 @@
+/*
+ * V9FS cache definitions.
+ *
+ *  Copyright (C) 2009 by Abhishek Kulkarni <adkulkar@umail.iu.edu>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#ifndef _9P_CACHE_H
+#ifdef CONFIG_9P_FSCACHE
+#include <linux/fscache.h>
+#include <linux/spinlock.h>
+
+extern struct fscache_netfs v9fs_cache_netfs;
+extern const struct fscache_cookie_def v9fs_cache_session_index_def;
+extern const struct fscache_cookie_def v9fs_cache_inode_index_def;
+
+extern void v9fs_cache_session_get_cookie(struct v9fs_session_info *v9ses);
+extern void v9fs_cache_session_put_cookie(struct v9fs_session_info *v9ses);
+
+extern void v9fs_cache_inode_get_cookie(struct inode *inode);
+extern void v9fs_cache_inode_put_cookie(struct inode *inode);
+extern void v9fs_cache_inode_flush_cookie(struct inode *inode);
+extern void v9fs_cache_inode_set_cookie(struct inode *inode, struct file *filp);
+extern void v9fs_cache_inode_reset_cookie(struct inode *inode);
+
+extern int __v9fs_cache_register(void);
+extern void __v9fs_cache_unregister(void);
+
+extern int __v9fs_fscache_release_page(struct page *page, gfp_t gfp);
+extern void __v9fs_fscache_invalidate_page(struct page *page);
+extern int __v9fs_readpage_from_fscache(struct inode *inode,
+					struct page *page);
+extern int __v9fs_readpages_from_fscache(struct inode *inode,
+					 struct address_space *mapping,
+					 struct list_head *pages,
+					 unsigned *nr_pages);
+extern void __v9fs_readpage_to_fscache(struct inode *inode, struct page *page);
+extern void __v9fs_fscache_wait_on_page_write(struct inode *inode,
+					      struct page *page);
+
+static inline int v9fs_fscache_release_page(struct page *page,
+					    gfp_t gfp)
+{
+	return __v9fs_fscache_release_page(page, gfp);
+}
+
+static inline void v9fs_fscache_invalidate_page(struct page *page)
+{
+	__v9fs_fscache_invalidate_page(page);
+}
+
+static inline int v9fs_readpage_from_fscache(struct inode *inode,
+					     struct page *page)
+{
+	return __v9fs_readpage_from_fscache(inode, page);
+}
+
+static inline int v9fs_readpages_from_fscache(struct inode *inode,
+					      struct address_space *mapping,
+					      struct list_head *pages,
+					      unsigned *nr_pages)
+{
+	return __v9fs_readpages_from_fscache(inode, mapping, pages,
+					     nr_pages);
+}
+
+static inline void v9fs_readpage_to_fscache(struct inode *inode,
+					    struct page *page)
+{
+	if (PageFsCache(page))
+		__v9fs_readpage_to_fscache(inode, page);
+}
+
+static inline void v9fs_uncache_page(struct inode *inode, struct page *page)
+{
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+	fscache_uncache_page(v9inode->fscache, page);
+	BUG_ON(PageFsCache(page));
+}
+
+static inline void v9fs_fscache_wait_on_page_write(struct inode *inode,
+						   struct page *page)
+{
+	return __v9fs_fscache_wait_on_page_write(inode, page);
+}
+
+#else /* CONFIG_9P_FSCACHE */
+
+static inline int v9fs_fscache_release_page(struct page *page,
+					    gfp_t gfp) {
+	return 1;
+}
+
+static inline void v9fs_fscache_invalidate_page(struct page *page) {}
+
+static inline int v9fs_readpage_from_fscache(struct inode *inode,
+					     struct page *page)
+{
+	return -ENOBUFS;
+}
+
+static inline int v9fs_readpages_from_fscache(struct inode *inode,
+					      struct address_space *mapping,
+					      struct list_head *pages,
+					      unsigned *nr_pages)
+{
+	return -ENOBUFS;
+}
+
+static inline void v9fs_readpage_to_fscache(struct inode *inode,
+					    struct page *page)
+{}
+
+static inline void v9fs_uncache_page(struct inode *inode, struct page *page)
+{}
+
+static inline void v9fs_fscache_wait_on_page_write(struct inode *inode,
+						   struct page *page)
+{
+	return;
+}
+
+#endif /* CONFIG_9P_FSCACHE */
+#endif /* _9P_CACHE_H */

fs/9p/fid.c

@@ -0,0 +1,306 @@
+/*
+ * V9FS FID Management
+ *
+ *  Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net>
+ *  Copyright (C) 2005, 2006 by Eric Van Hensbergen <ericvh@gmail.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#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"
+
+/**
+ * v9fs_fid_add - add a fid to a dentry
+ * @dentry: dentry that the fid is being added to
+ * @fid: fid to add
+ *
+ */
+
+static inline void __add_fid(struct dentry *dentry, struct p9_fid *fid)
+{
+	hlist_add_head(&fid->dlist, (struct hlist_head *)&dentry->d_fsdata);
+}
+
+void v9fs_fid_add(struct dentry *dentry, struct p9_fid *fid)
+{
+	spin_lock(&dentry->d_lock);
+	__add_fid(dentry, fid);
+	spin_unlock(&dentry->d_lock);
+}
+
+/**
+ * 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: %s (%p) uid %d any %d\n",
+		 dentry->d_name.name, 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;
+				break;
+			}
+		}
+		spin_unlock(&dentry->d_lock);
+	}
+
+	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, char ***names)
+{
+	int n = 0, i;
+	char **wnames;
+	struct dentry *ds;
+
+	for (ds = dentry; !IS_ROOT(ds); ds = ds->d_parent)
+		n++;
+
+	wnames = kmalloc(sizeof(char *) * n, GFP_KERNEL);
+	if (!wnames)
+		goto err_out;
+
+	for (ds = dentry, i = (n-1); i >= 0; i--, ds = ds->d_parent)
+		wnames[i] = (char  *)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;
+	char **wnames, *uname;
+	int i, n, l, clone, access;
+	struct v9fs_session_info *v9ses;
+	struct p9_fid *fid, *old_fid = NULL;
+
+	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 */
+		fid = p9_client_walk(fid, 1, (char **)&dentry->d_name.name, 1);
+		goto fid_out;
+	}
+	up_read(&v9ses->rename_sem);
+
+	/* start from the root and try to do a lookup */
+	fid = v9fs_fid_find(dentry->d_sb->s_root, uid, any);
+	if (!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;
+
+		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 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;
+	}
+	clone = 1;
+	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 patch component change
+		 */
+		fid = p9_client_walk(fid, l, &wnames[i], clone);
+		if (IS_ERR(fid)) {
+			if (old_fid) {
+				/*
+				 * If we fail, clunk fid which are mapping
+				 * to path component and not the last component
+				 * of the path.
+				 */
+				p9_client_clunk(old_fid);
+			}
+			kfree(wnames);
+			goto err_out;
+		}
+		old_fid = fid;
+		i += l;
+		clone = 0;
+	}
+	kfree(wnames);
+fid_out:
+	if (!IS_ERR(fid)) {
+		spin_lock(&dentry->d_lock);
+		if (d_unhashed(dentry)) {
+			spin_unlock(&dentry->d_lock);
+			p9_client_clunk(fid);
+			fid = ERR_PTR(-ENOENT);
+		} else {
+			__add_fid(dentry, 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_fid_clone(struct dentry *dentry)
+{
+	struct p9_fid *fid, *ret;
+
+	fid = v9fs_fid_lookup(dentry);
+	if (IS_ERR(fid))
+		return fid;
+
+	ret = p9_client_walk(fid, 0, NULL, 1);
+	return ret;
+}
+
+static struct p9_fid *v9fs_fid_clone_with_uid(struct dentry *dentry, kuid_t uid)
+{
+	struct p9_fid *fid, *ret;
+
+	fid = v9fs_fid_lookup_with_uid(dentry, uid, 0);
+	if (IS_ERR(fid))
+		return fid;
+
+	ret = p9_client_walk(fid, 0, NULL, 1);
+	return ret;
+}
+
+struct p9_fid *v9fs_writeback_fid(struct dentry *dentry)
+{
+	int err;
+	struct p9_fid *fid;
+
+	fid = v9fs_fid_clone_with_uid(dentry, GLOBAL_ROOT_UID);
+	if (IS_ERR(fid))
+		goto error_out;
+	/*
+	 * 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_client_clunk(fid);
+		fid = ERR_PTR(err);
+		goto error_out;
+	}
+error_out:
+	return fid;
+}

fs/9p/fid.h

@@ -0,0 +1,30 @@
+/*
+ * V9FS FID Management
+ *
+ *  Copyright (C) 2005 by Eric Van Hensbergen <ericvh@gmail.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+#ifndef FS_9P_FID_H
+#define FS_9P_FID_H
+#include <linux/list.h>
+
+struct p9_fid *v9fs_fid_lookup(struct dentry *dentry);
+struct p9_fid *v9fs_fid_clone(struct dentry *dentry);
+void v9fs_fid_add(struct dentry *dentry, struct p9_fid *fid);
+struct p9_fid *v9fs_writeback_fid(struct dentry *dentry);
+#endif

fs/9p/v9fs.c

@@ -0,0 +1,677 @@
+/*
+ *  linux/fs/9p/v9fs.c
+ *
+ *  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>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#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/parser.h>
+#include <linux/idr.h>
+#include <linux/slab.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_trans, Opt_cache, Opt_cachetag,
+	/* Options that take no arguments */
+	Opt_nodevmap,
+	/* Cache options */
+	Opt_cache_loose, Opt_fscache,
+	/* Access options */
+	Opt_access, Opt_posixacl,
+	/* 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_cachetag, "cachetag=%s"},
+	{Opt_access, "access=%s"},
+	{Opt_posixacl, "posixacl"},
+	{Opt_err, NULL}
+};
+
+/* 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, "none")) {
+		version = CACHE_NONE;
+		p9_debug(P9_DEBUG_9P, "Cache mode: none\n");
+	} else
+		pr_info("Unknown Cache mode %s\n", s);
+	return version;
+}
+
+/**
+ * v9fs_parse_options - parse mount options into session structure
+ * @v9ses: existing v9fs session information
+ *
+ * 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, *e;
+	int ret = 0;
+
+	/* setup defaults */
+	v9ses->afid = ~0;
+	v9ses->debug = 0;
+	v9ses->cache = CACHE_NONE;
+#ifdef CONFIG_9P_FSCACHE
+	v9ses->cachetag = NULL;
+#endif
+
+	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;
+				continue;
+			}
+			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;
+				continue;
+			}
+			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;
+				continue;
+			}
+			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;
+				continue;
+			}
+			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_cachetag:
+#ifdef CONFIG_9P_FSCACHE
+			v9ses->cachetag = match_strdup(&args[0]);
+#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;
+			}
+			ret = get_cache_mode(s);
+			if (ret == -EINVAL) {
+				kfree(s);
+				goto free_and_return;
+			}
+
+			v9ses->cache = ret;
+			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;
+				uid = simple_strtoul(s, &e, 10);
+				if (*e != '\0') {
+					ret = -EINVAL;
+					pr_info("Unknown access argument %s\n",
+						s);
+					kfree(s);
+					goto free_and_return;
+				}
+				v9ses->uid = make_kuid(current_user_ns(), uid);
+				if (!uid_valid(v9ses->uid)) {
+					ret = -EINVAL;
+					pr_info("Uknown uid %s\n", s);
+					kfree(s);
+					goto free_and_return;
+				}
+			}
+
+			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;
+
+		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)
+{
+	int retval = -EINVAL;
+	struct p9_fid *fid;
+	int rc;
+
+	v9ses->uname = kstrdup(V9FS_DEFUSER, GFP_KERNEL);
+	if (!v9ses->uname)
+		return ERR_PTR(-ENOMEM);
+
+	v9ses->aname = kstrdup(V9FS_DEFANAME, GFP_KERNEL);
+	if (!v9ses->aname) {
+		kfree(v9ses->uname);
+		return ERR_PTR(-ENOMEM);
+	}
+	init_rwsem(&v9ses->rename_sem);
+
+	rc = bdi_setup_and_register(&v9ses->bdi, "9p", BDI_CAP_MAP_COPY);
+	if (rc) {
+		kfree(v9ses->aname);
+		kfree(v9ses->uname);
+		return ERR_PTR(rc);
+	}
+
+	spin_lock(&v9fs_sessionlist_lock);
+	list_add(&v9ses->slist, &v9fs_sessionlist);
+	spin_unlock(&v9fs_sessionlist_lock);
+
+	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)) {
+		retval = PTR_ERR(v9ses->clnt);
+		v9ses->clnt = NULL;
+		p9_debug(P9_DEBUG_ERROR, "problem initializing 9p client\n");
+		goto error;
+	}
+
+	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) {
+		retval = rc;
+		goto error;
+	}
+
+	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)) {
+		retval = PTR_ERR(fid);
+		fid = NULL;
+		p9_debug(P9_DEBUG_ERROR, "cannot attach\n");
+		goto error;
+	}
+
+	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 */
+	v9fs_cache_session_get_cookie(v9ses);
+#endif
+
+	return fid;
+
+error:
+	bdi_destroy(&v9ses->bdi);
+	return ERR_PTR(retval);
+}
+
+/**
+ * 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
+	if (v9ses->fscache) {
+		v9fs_cache_session_put_cookie(v9ses);
+		kfree(v9ses->cachetag);
+	}
+#endif
+	kfree(v9ses->uname);
+	kfree(v9ses->aname);
+
+	bdi_destroy(&v9ses->bdi);
+
+	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
+/**
+ * caches_show - list caches associated with a session
+ *
+ * Returns the size of buffer written.
+ */
+
+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 struct attribute_group v9fs_attr_group = {
+	.attrs = v9fs_attrs,
+};
+
+/**
+ * v9fs_sysfs_init - Initialize the v9fs sysfs interface
+ *
+ */
+
+static int 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;
+#ifdef CONFIG_9P_FSCACHE
+	v9inode->fscache = NULL;
+#endif
+	memset(&v9inode->qid, 0, sizeof(v9inode->qid));
+	inode_init_once(&v9inode->vfs_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),
+					  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;
+#ifdef CONFIG_9P_FSCACHE
+	return fscache_register_netfs(&v9fs_cache_netfs);
+#else
+	return ret;
+#endif
+}
+
+static void v9fs_cache_unregister(void)
+{
+	v9fs_destroy_inode_cache();
+#ifdef CONFIG_9P_FSCACHE
+	fscache_unregister_netfs(&v9fs_cache_netfs);
+#endif
+}
+
+/**
+ * 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");

fs/9p/v9fs.h

@@ -0,0 +1,227 @@
+/*
+ * V9FS definitions.
+ *
+ *  Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+#ifndef FS_9P_V9FS_H
+#define FS_9P_V9FS_H
+
+#include <linux/backing-dev.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_LOOSE,
+	CACHE_FSCACHE,
+};
+
+/**
+ * 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
+ * @options: copy of options string given by user
+ * @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_cookie *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 backing_dev_info bdi;
+	struct rw_semaphore rename_sem;
+};
+
+/* cache_validity flags */
+#define V9FS_INO_INVALID_ATTR 0x01
+
+struct v9fs_inode {
+#ifdef CONFIG_9P_FSCACHE
+	spinlock_t fscache_lock;
+	struct fscache_cookie *fscache;
+#endif
+	struct p9_qid qid;
+	unsigned int cache_validity;
+	struct p9_fid *writeback_fid;
+	struct mutex v_mutex;
+	struct inode vfs_inode;
+};
+
+static inline struct v9fs_inode *V9FS_I(const struct inode *inode)
+{
+	return container_of(inode, struct v9fs_inode, vfs_inode);
+}
+
+struct p9_fid *v9fs_session_init(struct v9fs_session_info *, const char *,
+									char *);
+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 inode *old_dir, struct dentry *old_dentry,
+			struct inode *new_dir, struct dentry *new_dentry);
+extern void v9fs_vfs_put_link(struct dentry *dentry, struct nameidata *nd,
+			void *p);
+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 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

fs/9p/v9fs_vfs.h

@@ -0,0 +1,88 @@
+/*
+ * V9FS VFS extensions.
+ *
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+#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)
+
+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 struct kmem_cache *v9fs_inode_cache;
+
+struct inode *v9fs_alloc_inode(struct super_block *sb);
+void v9fs_destroy_inode(struct inode *inode);
+struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t);
+int v9fs_init_inode(struct v9fs_session_info *v9ses,
+		    struct inode *inode, umode_t mode, dev_t);
+void v9fs_evict_inode(struct inode *inode);
+ino_t v9fs_qid2ino(struct p9_qid *qid);
+void v9fs_stat2inode(struct p9_wstat *, struct inode *, struct super_block *);
+void v9fs_stat2inode_dotl(struct p9_stat_dotl *, struct inode *);
+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);
+
+ssize_t v9fs_file_readn(struct file *, char *, char __user *, u32, u64);
+ssize_t v9fs_fid_readn(struct p9_fid *, char *, char __user *, u32, u64);
+void v9fs_blank_wstat(struct p9_wstat *wstat);
+int v9fs_vfs_setattr_dotl(struct dentry *, struct iattr *);
+int v9fs_file_fsync_dotl(struct file *filp, loff_t start, loff_t end,
+			 int datasync);
+ssize_t v9fs_file_write_internal(struct inode *, struct p9_fid *,
+				 const char __user *, size_t, loff_t *, int);
+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;
+	return;
+}
+
+int v9fs_open_to_dotl_flags(int flags);
+#endif

fs/9p/vfs_addr.c

@@ -0,0 +1,353 @@
+/*
+ *  linux/fs/9p/vfs_addr.c
+ *
+ * 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>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#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/aio.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_fid_readpage - read an entire page in from 9P
+ *
+ * @fid: fid being read
+ * @page: structure to page
+ *
+ */
+static int v9fs_fid_readpage(struct p9_fid *fid, struct page *page)
+{
+	int retval;
+	loff_t offset;
+	char *buffer;
+	struct inode *inode;
+
+	inode = page->mapping->host;
+	p9_debug(P9_DEBUG_VFS, "\n");
+
+	BUG_ON(!PageLocked(page));
+
+	retval = v9fs_readpage_from_fscache(inode, page);
+	if (retval == 0)
+		return retval;
+
+	buffer = kmap(page);
+	offset = page_offset(page);
+
+	retval = v9fs_fid_readn(fid, buffer, NULL, PAGE_CACHE_SIZE, offset);
+	if (retval < 0) {
+		v9fs_uncache_page(inode, page);
+		goto done;
+	}
+
+	memset(buffer + retval, 0, PAGE_CACHE_SIZE - retval);
+	flush_dcache_page(page);
+	SetPageUptodate(page);
+
+	v9fs_readpage_to_fscache(inode, page);
+	retval = 0;
+
+done:
+	kunmap(page);
+	unlock_page(page);
+	return retval;
+}
+
+/**
+ * v9fs_vfs_readpage - read an entire page in from 9P
+ *
+ * @filp: file being read
+ * @page: structure to page
+ *
+ */
+
+static int v9fs_vfs_readpage(struct file *filp, struct page *page)
+{
+	return v9fs_fid_readpage(filp->private_data, page);
+}
+
+/**
+ * v9fs_vfs_readpages - read a set of pages from 9P
+ *
+ * @filp: file being read
+ * @mapping: the address space
+ * @pages: list of pages to read
+ * @nr_pages: count of pages to read
+ *
+ */
+
+static int v9fs_vfs_readpages(struct file *filp, struct address_space *mapping,
+			     struct list_head *pages, unsigned nr_pages)
+{
+	int ret = 0;
+	struct inode *inode;
+
+	inode = mapping->host;
+	p9_debug(P9_DEBUG_VFS, "inode: %p file: %p\n", inode, filp);
+
+	ret = v9fs_readpages_from_fscache(inode, mapping, pages, &nr_pages);
+	if (ret == 0)
+		return ret;
+
+	ret = read_cache_pages(mapping, pages, (void *)v9fs_vfs_readpage, filp);
+	p9_debug(P9_DEBUG_VFS, "  = %d\n", ret);
+	return ret;
+}
+
+/**
+ * v9fs_release_page - release the private state associated with a page
+ *
+ * Returns 1 if the page can be released, false otherwise.
+ */
+
+static int v9fs_release_page(struct page *page, gfp_t gfp)
+{
+	if (PagePrivate(page))
+		return 0;
+	return v9fs_fscache_release_page(page, gfp);
+}
+
+/**
+ * v9fs_invalidate_page - Invalidate a page completely or partially
+ *
+ * @page: structure to page
+ * @offset: offset in the page
+ */
+
+static void v9fs_invalidate_page(struct page *page, unsigned long offset)
+{
+	/*
+	 * If called with zero offset, we should release
+	 * the private state assocated with the page
+	 */
+	if (offset == 0)
+		v9fs_fscache_invalidate_page(page);
+}
+
+static int v9fs_vfs_writepage_locked(struct page *page)
+{
+	char *buffer;
+	int retval, len;
+	loff_t offset, size;
+	mm_segment_t old_fs;
+	struct v9fs_inode *v9inode;
+	struct inode *inode = page->mapping->host;
+
+	v9inode = V9FS_I(inode);
+	size = i_size_read(inode);
+	if (page->index == size >> PAGE_CACHE_SHIFT)
+		len = size & ~PAGE_CACHE_MASK;
+	else
+		len = PAGE_CACHE_SIZE;
+
+	set_page_writeback(page);
+
+	buffer = kmap(page);
+	offset = page_offset(page);
+
+	old_fs = get_fs();
+	set_fs(get_ds());
+	/* We should have writeback_fid always set */
+	BUG_ON(!v9inode->writeback_fid);
+
+	retval = v9fs_file_write_internal(inode,
+					  v9inode->writeback_fid,
+					  (__force const char __user *)buffer,
+					  len, &offset, 0);
+	if (retval > 0)
+		retval = 0;
+
+	set_fs(old_fs);
+	kunmap(page);
+	end_page_writeback(page);
+	return retval;
+}
+
+static int v9fs_vfs_writepage(struct page *page, struct writeback_control *wbc)
+{
+	int retval;
+
+	retval = v9fs_vfs_writepage_locked(page);
+	if (retval < 0) {
+		if (retval == -EAGAIN) {
+			redirty_page_for_writepage(wbc, page);
+			retval = 0;
+		} else {
+			SetPageError(page);
+			mapping_set_error(page->mapping, retval);
+		}
+	} else
+		retval = 0;
+
+	unlock_page(page);
+	return retval;
+}
+
+/**
+ * v9fs_launder_page - Writeback a dirty page
+ * Returns 0 on success.
+ */
+
+static int v9fs_launder_page(struct page *page)
+{
+	int retval;
+	struct inode *inode = page->mapping->host;
+
+	v9fs_fscache_wait_on_page_write(inode, page);
+	if (clear_page_dirty_for_io(page)) {
+		retval = v9fs_vfs_writepage_locked(page);
+		if (retval)
+			return retval;
+	}
+	return 0;
+}
+
+/**
+ * v9fs_direct_IO - 9P address space operation for direct I/O
+ * @rw: direction (read or write)
+ * @iocb: target I/O control block
+ * @iov: array of vectors that define I/O buffer
+ * @pos: offset in file to begin the operation
+ * @nr_segs: size of iovec array
+ *
+ * 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(int rw, struct kiocb *iocb, const struct iovec *iov,
+	       loff_t pos, unsigned long nr_segs)
+{
+	/*
+	 * FIXME
+	 * Now that we do caching with cache mode enabled, We need
+	 * to support direct IO
+	 */
+	p9_debug(P9_DEBUG_VFS, "v9fs_direct_IO: v9fs_direct_IO (%s) off/no(%lld/%lu) EINVAL\n",
+		 iocb->ki_filp->f_path.dentry->d_name.name,
+		 (long long)pos, nr_segs);
+
+	return -EINVAL;
+}
+
+static int v9fs_write_begin(struct file *filp, struct address_space *mapping,
+			    loff_t pos, unsigned len, unsigned flags,
+			    struct page **pagep, void **fsdata)
+{
+	int retval = 0;
+	struct page *page;
+	struct v9fs_inode *v9inode;
+	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+	struct inode *inode = mapping->host;
+
+	v9inode = V9FS_I(inode);
+start:
+	page = grab_cache_page_write_begin(mapping, index, flags);
+	if (!page) {
+		retval = -ENOMEM;
+		goto out;
+	}
+	BUG_ON(!v9inode->writeback_fid);
+	if (PageUptodate(page))
+		goto out;
+
+	if (len == PAGE_CACHE_SIZE)
+		goto out;
+
+	retval = v9fs_fid_readpage(v9inode->writeback_fid, page);
+	page_cache_release(page);
+	if (!retval)
+		goto start;
+out:
+	*pagep = page;
+	return retval;
+}
+
+static int v9fs_write_end(struct file *filp, struct address_space *mapping,
+			  loff_t pos, unsigned len, unsigned copied,
+			  struct page *page, void *fsdata)
+{
+	loff_t last_pos = pos + copied;
+	struct inode *inode = page->mapping->host;
+
+	if (unlikely(copied < len)) {
+		/*
+		 * zero out the rest of the area
+		 */
+		unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+
+		zero_user(page, from + copied, len - copied);
+		flush_dcache_page(page);
+	}
+
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
+	/*
+	 * 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);
+	}
+	set_page_dirty(page);
+	unlock_page(page);
+	page_cache_release(page);
+
+	return copied;
+}
+
+
+const struct address_space_operations v9fs_addr_operations = {
+	.readpage = v9fs_vfs_readpage,
+	.readpages = v9fs_vfs_readpages,
+	.set_page_dirty = __set_page_dirty_nobuffers,
+	.writepage = v9fs_vfs_writepage,
+	.write_begin = v9fs_write_begin,
+	.write_end = v9fs_write_end,
+	.releasepage = v9fs_release_page,
+	.invalidatepage = v9fs_invalidate_page,
+	.launder_page = v9fs_launder_page,
+	.direct_IO = v9fs_direct_IO,
+};

fs/9p/vfs_dentry.c

@@ -0,0 +1,139 @@
+/*
+ *  linux/fs/9p/vfs_dentry.c
+ *
+ * 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>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#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_dentry_delete - called when dentry refcount equals 0
+ * @dentry:  dentry in question
+ *
+ * By returning 1 here we should remove cacheing of unused
+ * dentry components.
+ *
+ */
+
+static int v9fs_dentry_delete(const struct dentry *dentry)
+{
+	p9_debug(P9_DEBUG_VFS, " dentry: %s (%p)\n",
+		 dentry->d_name.name, dentry);
+
+	return 1;
+}
+
+/**
+ * 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: %s (%p)\n",
+		 dentry->d_name.name, dentry);
+
+	/* Don't cache negative dentries */
+	if (!dentry->d_inode)
+		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: %s (%p)\n",
+		 dentry->d_name.name, dentry);
+	hlist_for_each_safe(p, n, (struct hlist_head *)&dentry->d_fsdata)
+		p9_client_clunk(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 = dentry->d_inode;
+	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);
+		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 = v9fs_dentry_delete,
+	.d_release = v9fs_dentry_release,
+};

fs/9p/vfs_dir.c

@@ -0,0 +1,269 @@
+/*
+ * linux/fs/9p/vfs_dir.c
+ *
+ * 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>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#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 <net/9p/9p.h>
+#include <net/9p/client.h>
+
+#include "v9fs.h"
+#include "v9fs_vfs.h"
+#include "fid.h"
+
+/**
+ * struct p9_rdir - readdir accounting
+ * @mutex: mutex protecting readdir
+ * @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;
+}
+
+static void p9stat_init(struct p9_wstat *stbuf)
+{
+	stbuf->name  = NULL;
+	stbuf->uid   = NULL;
+	stbuf->gid   = NULL;
+	stbuf->muid  = NULL;
+	stbuf->extension = NULL;
+}
+
+/**
+ * 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 - read a directory
+ * @filp: opened file structure
+ * @dirent: directory structure ???
+ * @filldir: function to populate directory structure ???
+ *
+ */
+
+static int v9fs_dir_readdir(struct file *filp, void *dirent, filldir_t filldir)
+{
+	int over;
+	struct p9_wstat st;
+	int err = 0;
+	struct p9_fid *fid;
+	int buflen;
+	int reclen = 0;
+	struct p9_rdir *rdir;
+
+	p9_debug(P9_DEBUG_VFS, "name %s\n", filp->f_path.dentry->d_name.name);
+	fid = filp->private_data;
+
+	buflen = fid->clnt->msize - P9_IOHDRSZ;
+
+	rdir = v9fs_alloc_rdir_buf(filp, buflen);
+	if (!rdir)
+		return -ENOMEM;
+
+	while (1) {
+		if (rdir->tail == rdir->head) {
+			err = v9fs_file_readn(filp, rdir->buf, NULL,
+							buflen, filp->f_pos);
+			if (err <= 0)
+				return err;
+
+			rdir->head = 0;
+			rdir->tail = err;
+		}
+		while (rdir->head < rdir->tail) {
+			p9stat_init(&st);
+			err = p9stat_read(fid->clnt, rdir->buf + rdir->head,
+					  rdir->tail - rdir->head, &st);
+			if (err) {
+				p9_debug(P9_DEBUG_VFS, "returned %d\n", err);
+				p9stat_free(&st);
+				return -EIO;
+			}
+			reclen = st.size+2;
+
+			over = filldir(dirent, st.name, strlen(st.name),
+			    filp->f_pos, v9fs_qid2ino(&st.qid), dt_type(&st));
+
+			p9stat_free(&st);
+
+			if (over)
+				return 0;
+
+			rdir->head += reclen;
+			filp->f_pos += reclen;
+		}
+	}
+}
+
+/**
+ * v9fs_dir_readdir_dotl - read a directory
+ * @filp: opened file structure
+ * @dirent: buffer to fill dirent structures
+ * @filldir: function to populate dirent structures
+ *
+ */
+static int v9fs_dir_readdir_dotl(struct file *filp, void *dirent,
+						filldir_t filldir)
+{
+	int over;
+	int err = 0;
+	struct p9_fid *fid;
+	int buflen;
+	struct p9_rdir *rdir;
+	struct p9_dirent curdirent;
+	u64 oldoffset = 0;
+
+	p9_debug(P9_DEBUG_VFS, "name %s\n", filp->f_path.dentry->d_name.name);
+	fid = filp->private_data;
+
+	buflen = fid->clnt->msize - P9_READDIRHDRSZ;
+
+	rdir = v9fs_alloc_rdir_buf(filp, buflen);
+	if (!rdir)
+		return -ENOMEM;
+
+	while (1) {
+		if (rdir->tail == rdir->head) {
+			err = p9_client_readdir(fid, rdir->buf, buflen,
+						filp->f_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;
+			}
+
+			/* d_off in dirent structure tracks the offset into
+			 * the next dirent in the dir. However, filldir()
+			 * expects offset into the current dirent. Hence
+			 * while calling filldir send the offset from the
+			 * previous dirent structure.
+			 */
+			over = filldir(dirent, curdirent.d_name,
+					strlen(curdirent.d_name),
+					oldoffset, v9fs_qid2ino(&curdirent.qid),
+					curdirent.d_type);
+			oldoffset = curdirent.d_off;
+
+			if (over)
+				return 0;
+
+			filp->f_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 p9_fid *fid;
+
+	fid = filp->private_data;
+	p9_debug(P9_DEBUG_VFS, "inode: %p filp: %p fid: %d\n",
+		 inode, filp, fid ? fid->fid : -1);
+	if (fid)
+		p9_client_clunk(fid);
+	return 0;
+}
+
+const struct file_operations v9fs_dir_operations = {
+	.read = generic_read_dir,
+	.llseek = generic_file_llseek,
+	.readdir = 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,
+	.readdir = v9fs_dir_readdir_dotl,
+	.open = v9fs_file_open,
+	.release = v9fs_dir_release,
+        .fsync = v9fs_file_fsync_dotl,
+};

fs/9p/vfs_file.c

@@ -0,0 +1,790 @@
+/*
+ *  linux/fs/9p/vfs_file.c
+ *
+ * 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>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#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 <asm/uaccess.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"
+#include "cache.h"
+
+static const struct vm_operations_struct v9fs_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;
+	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->f_path.dentry);
+		if (IS_ERR(fid))
+			return PTR_ERR(fid);
+
+		err = p9_client_open(fid, omode);
+		if (err < 0) {
+			p9_client_clunk(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 && !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.
+		 */
+		fid = v9fs_writeback_fid(file->f_path.dentry);
+		if (IS_ERR(fid)) {
+			err = PTR_ERR(fid);
+			mutex_unlock(&v9inode->v_mutex);
+			goto out_error;
+		}
+		v9inode->writeback_fid = (void *) fid;
+	}
+	mutex_unlock(&v9inode->v_mutex);
+#ifdef CONFIG_9P_FSCACHE
+	if (v9ses->cache)
+		v9fs_cache_inode_set_cookie(inode, file);
+#endif
+	return 0;
+out_error:
+	p9_client_clunk(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)
+{
+	int res = 0;
+	struct inode *inode = file_inode(filp);
+
+	p9_debug(P9_DEBUG_VFS, "filp: %p lock: %p\n", filp, fl);
+
+	/* No mandatory locks */
+	if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
+		return -ENOLCK;
+
+	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 res;
+}
+
+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;
+	int res = 0;
+	unsigned char fl_type;
+
+	fid = filp->private_data;
+	BUG_ON(fid == NULL);
+
+	if ((fl->fl_flags & FL_POSIX) != FL_POSIX)
+		BUG();
+
+	res = posix_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 = utsname()->nodename;
+	if (IS_SETLKW(cmd))
+		flock.flags = P9_LOCK_FLAGS_BLOCK;
+
+	/*
+	 * 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)
+			break;
+
+		if (status != P9_LOCK_BLOCKED)
+			break;
+		if (status == P9_LOCK_BLOCKED && !IS_SETLKW(cmd))
+			break;
+		if (schedule_timeout_interruptible(P9_LOCK_TIMEOUT) != 0)
+			break;
+	}
+
+	/* map 9p status to VFS status */
+	switch (status) {
+	case P9_LOCK_SUCCESS:
+		res = 0;
+		break;
+	case P9_LOCK_BLOCKED:
+		res = -EAGAIN;
+		break;
+	case P9_LOCK_ERROR:
+	case P9_LOCK_GRACE:
+		res = -ENOLCK;
+		break;
+	default:
+		BUG();
+	}
+
+	/*
+	 * 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;
+		res = posix_lock_file_wait(filp, fl);
+		fl->fl_type = fl_type;
+	}
+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 = utsname()->nodename;
+
+	res = p9_client_getlock_dotl(fid, &glock);
+	if (res < 0)
+		return res;
+	/* 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;
+	}
+	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: %s\n",
+		 filp, cmd, fl, filp->f_path.dentry->d_name.name);
+
+	/* No mandatory locks */
+	if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
+		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);
+	}
+
+	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;
+out_err:
+	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: %s\n",
+		 filp, cmd, fl, filp->f_path.dentry->d_name.name);
+
+	/* No mandatory locks */
+	if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
+		goto out_err;
+
+	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_owner = (fl_owner_t)filp;
+	fl->fl_start = 0;
+	fl->fl_end = OFFSET_MAX;
+	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_fid_readn - read from a fid
+ * @fid: fid to read
+ * @data: data buffer to read data into
+ * @udata: user data buffer to read data into
+ * @count: size of buffer
+ * @offset: offset at which to read data
+ *
+ */
+ssize_t
+v9fs_fid_readn(struct p9_fid *fid, char *data, char __user *udata, u32 count,
+	       u64 offset)
+{
+	int n, total, size;
+
+	p9_debug(P9_DEBUG_VFS, "fid %d offset %llu count %d\n",
+		 fid->fid, (long long unsigned)offset, count);
+	n = 0;
+	total = 0;
+	size = fid->iounit ? fid->iounit : fid->clnt->msize - P9_IOHDRSZ;
+	do {
+		n = p9_client_read(fid, data, udata, offset, count);
+		if (n <= 0)
+			break;
+
+		if (data)
+			data += n;
+		if (udata)
+			udata += n;
+
+		offset += n;
+		count -= n;
+		total += n;
+	} while (count > 0 && n == size);
+
+	if (n < 0)
+		total = n;
+
+	return total;
+}
+
+/**
+ * v9fs_file_readn - read from a file
+ * @filp: file pointer to read
+ * @data: data buffer to read data into
+ * @udata: user data buffer to read data into
+ * @count: size of buffer
+ * @offset: offset at which to read data
+ *
+ */
+ssize_t
+v9fs_file_readn(struct file *filp, char *data, char __user *udata, u32 count,
+	       u64 offset)
+{
+	return v9fs_fid_readn(filp->private_data, data, udata, count, offset);
+}
+
+/**
+ * v9fs_file_read - read from a file
+ * @filp: file pointer to read
+ * @udata: user data buffer to read data into
+ * @count: size of buffer
+ * @offset: offset at which to read data
+ *
+ */
+
+static ssize_t
+v9fs_file_read(struct file *filp, char __user *udata, size_t count,
+	       loff_t * offset)
+{
+	int ret;
+	struct p9_fid *fid;
+	size_t size;
+
+	p9_debug(P9_DEBUG_VFS, "count %zu offset %lld\n", count, *offset);
+	fid = filp->private_data;
+
+	size = fid->iounit ? fid->iounit : fid->clnt->msize - P9_IOHDRSZ;
+	if (count > size)
+		ret = v9fs_file_readn(filp, NULL, udata, count, *offset);
+	else
+		ret = p9_client_read(fid, NULL, udata, *offset, count);
+
+	if (ret > 0)
+		*offset += ret;
+
+	return ret;
+}
+
+ssize_t
+v9fs_file_write_internal(struct inode *inode, struct p9_fid *fid,
+			 const char __user *data, size_t count,
+			 loff_t *offset, int invalidate)
+{
+	int n;
+	loff_t i_size;
+	size_t total = 0;
+	struct p9_client *clnt;
+	loff_t origin = *offset;
+	unsigned long pg_start, pg_end;
+
+	p9_debug(P9_DEBUG_VFS, "data %p count %d offset %x\n",
+		 data, (int)count, (int)*offset);
+
+	clnt = fid->clnt;
+	do {
+		n = p9_client_write(fid, NULL, data+total, origin+total, count);
+		if (n <= 0)
+			break;
+		count -= n;
+		total += n;
+	} while (count > 0);
+
+	if (invalidate && (total > 0)) {
+		pg_start = origin >> PAGE_CACHE_SHIFT;
+		pg_end = (origin + total - 1) >> PAGE_CACHE_SHIFT;
+		if (inode->i_mapping && inode->i_mapping->nrpages)
+			invalidate_inode_pages2_range(inode->i_mapping,
+						      pg_start, pg_end);
+		*offset += total;
+		i_size = i_size_read(inode);
+		if (*offset > i_size) {
+			inode_add_bytes(inode, *offset - i_size);
+			i_size_write(inode, *offset);
+		}
+	}
+	if (n < 0)
+		return n;
+
+	return total;
+}
+
+/**
+ * v9fs_file_write - write to a file
+ * @filp: file pointer to write
+ * @data: data buffer to write data from
+ * @count: size of buffer
+ * @offset: offset at which to write data
+ *
+ */
+static ssize_t
+v9fs_file_write(struct file *filp, const char __user * data,
+		size_t count, loff_t *offset)
+{
+	ssize_t retval = 0;
+	loff_t origin = *offset;
+
+
+	retval = generic_write_checks(filp, &origin, &count, 0);
+	if (retval)
+		goto out;
+
+	retval = -EINVAL;
+	if ((ssize_t) count < 0)
+		goto out;
+	retval = 0;
+	if (!count)
+		goto out;
+
+	retval = v9fs_file_write_internal(file_inode(filp),
+					filp->private_data,
+					data, count, &origin, 1);
+	/* update offset on successful write */
+	if (retval > 0)
+		*offset = origin;
+out:
+	return retval;
+}
+
+
+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 = filemap_write_and_wait_range(inode->i_mapping, start, end);
+	if (retval)
+		return retval;
+
+	mutex_lock(&inode->i_mutex);
+	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);
+	mutex_unlock(&inode->i_mutex);
+
+	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 = filemap_write_and_wait_range(inode->i_mapping, start, end);
+	if (retval)
+		return retval;
+
+	mutex_lock(&inode->i_mutex);
+	p9_debug(P9_DEBUG_VFS, "filp %p datasync %x\n", filp, datasync);
+
+	fid = filp->private_data;
+
+	retval = p9_client_fsync(fid, datasync);
+	mutex_unlock(&inode->i_mutex);
+
+	return retval;
+}
+
+static int
+v9fs_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	int retval;
+
+	retval = generic_file_mmap(file, vma);
+	if (!retval)
+		vma->vm_ops = &v9fs_file_vm_ops;
+
+	return retval;
+}
+
+static int
+v9fs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct v9fs_inode *v9inode;
+	struct page *page = vmf->page;
+	struct file *filp = vma->vm_file;
+	struct inode *inode = file_inode(filp);
+
+
+	p9_debug(P9_DEBUG_VFS, "page %p fid %lx\n",
+		 page, (unsigned long)filp->private_data);
+
+	/* Update file times before taking page lock */
+	file_update_time(filp);
+
+	v9inode = V9FS_I(inode);
+	/* make sure the cache has finished storing the page */
+	v9fs_fscache_wait_on_page_write(inode, page);
+	BUG_ON(!v9inode->writeback_fid);
+	lock_page(page);
+	if (page->mapping != inode->i_mapping)
+		goto out_unlock;
+	wait_for_stable_page(page);
+
+	return VM_FAULT_LOCKED;
+out_unlock:
+	unlock_page(page);
+	return VM_FAULT_NOPAGE;
+}
+
+static ssize_t
+v9fs_direct_read(struct file *filp, char __user *udata, size_t count,
+		 loff_t *offsetp)
+{
+	loff_t size, offset;
+	struct inode *inode;
+	struct address_space *mapping;
+
+	offset = *offsetp;
+	mapping = filp->f_mapping;
+	inode = mapping->host;
+	if (!count)
+		return 0;
+	size = i_size_read(inode);
+	if (offset < size)
+		filemap_write_and_wait_range(mapping, offset,
+					     offset + count - 1);
+
+	return v9fs_file_read(filp, udata, count, offsetp);
+}
+
+/**
+ * v9fs_cached_file_read - read from a file
+ * @filp: file pointer to read
+ * @udata: user data buffer to read data into
+ * @count: size of buffer
+ * @offset: offset at which to read data
+ *
+ */
+static ssize_t
+v9fs_cached_file_read(struct file *filp, char __user *data, size_t count,
+		      loff_t *offset)
+{
+	if (filp->f_flags & O_DIRECT)
+		return v9fs_direct_read(filp, data, count, offset);
+	return do_sync_read(filp, data, count, offset);
+}
+
+static ssize_t
+v9fs_direct_write(struct file *filp, const char __user * data,
+		  size_t count, loff_t *offsetp)
+{
+	loff_t offset;
+	ssize_t retval;
+	struct inode *inode;
+	struct address_space *mapping;
+
+	offset = *offsetp;
+	mapping = filp->f_mapping;
+	inode = mapping->host;
+	if (!count)
+		return 0;
+
+	mutex_lock(&inode->i_mutex);
+	retval = filemap_write_and_wait_range(mapping, offset,
+					      offset + count - 1);
+	if (retval)
+		goto err_out;
+	/*
+	 * After a write we want buffered reads to be sure to go to disk to get
+	 * the new data.  We invalidate clean cached page from the region we're
+	 * about to write.  We do this *before* the write so that if we fail
+	 * here we fall back to buffered write
+	 */
+	if (mapping->nrpages) {
+		pgoff_t pg_start = offset >> PAGE_CACHE_SHIFT;
+		pgoff_t pg_end   = (offset + count - 1) >> PAGE_CACHE_SHIFT;
+
+		retval = invalidate_inode_pages2_range(mapping,
+							pg_start, pg_end);
+		/*
+		 * If a page can not be invalidated, fall back
+		 * to buffered write.
+		 */
+		if (retval) {
+			if (retval == -EBUSY)
+				goto buff_write;
+			goto err_out;
+		}
+	}
+	retval = v9fs_file_write(filp, data, count, offsetp);
+err_out:
+	mutex_unlock(&inode->i_mutex);
+	return retval;
+
+buff_write:
+	mutex_unlock(&inode->i_mutex);
+	return do_sync_write(filp, data, count, offsetp);
+}
+
+/**
+ * v9fs_cached_file_write - write to a file
+ * @filp: file pointer to write
+ * @data: data buffer to write data from
+ * @count: size of buffer
+ * @offset: offset at which to write data
+ *
+ */
+static ssize_t
+v9fs_cached_file_write(struct file *filp, const char __user * data,
+		       size_t count, loff_t *offset)
+{
+
+	if (filp->f_flags & O_DIRECT)
+		return v9fs_direct_write(filp, data, count, offset);
+	return do_sync_write(filp, data, count, offset);
+}
+
+static const struct vm_operations_struct v9fs_file_vm_ops = {
+	.fault = filemap_fault,
+	.page_mkwrite = v9fs_vm_page_mkwrite,
+	.remap_pages = generic_file_remap_pages,
+};
+
+
+const struct file_operations v9fs_cached_file_operations = {
+	.llseek = generic_file_llseek,
+	.read = v9fs_cached_file_read,
+	.write = v9fs_cached_file_write,
+	.aio_read = generic_file_aio_read,
+	.aio_write = generic_file_aio_write,
+	.open = v9fs_file_open,
+	.release = v9fs_dir_release,
+	.lock = v9fs_file_lock,
+	.mmap = v9fs_file_mmap,
+	.fsync = v9fs_file_fsync,
+};
+
+const struct file_operations v9fs_cached_file_operations_dotl = {
+	.llseek = generic_file_llseek,
+	.read = v9fs_cached_file_read,
+	.write = v9fs_cached_file_write,
+	.aio_read = generic_file_aio_read,
+	.aio_write = generic_file_aio_write,
+	.open = v9fs_file_open,
+	.release = v9fs_dir_release,
+	.lock = v9fs_file_lock_dotl,
+	.flock = v9fs_file_flock_dotl,
+	.mmap = v9fs_file_mmap,
+	.fsync = v9fs_file_fsync_dotl,
+};
+
+const struct file_operations v9fs_file_operations = {
+	.llseek = generic_file_llseek,
+	.read = v9fs_file_read,
+	.write = v9fs_file_write,
+	.open = v9fs_file_open,
+	.release = v9fs_dir_release,
+	.lock = v9fs_file_lock,
+	.mmap = generic_file_readonly_mmap,
+	.fsync = v9fs_file_fsync,
+};
+
+const struct file_operations v9fs_file_operations_dotl = {
+	.llseek = generic_file_llseek,
+	.read = v9fs_file_read,
+	.write = v9fs_file_write,
+	.open = v9fs_file_open,
+	.release = v9fs_dir_release,
+	.lock = v9fs_file_lock_dotl,
+	.flock = v9fs_file_flock_dotl,
+	.mmap = generic_file_readonly_mmap,
+	.fsync = v9fs_file_fsync_dotl,
+};

fs/9p/vfs_super.c

@@ -0,0 +1,368 @@
+/*
+ *  linux/fs/9p/vfs_super.c
+ *
+ * This file contians superblock ops for 9P2000. It is intended that
+ * you mount this file system on directories.
+ *
+ *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#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/seq_file.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 <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 void
+v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
+		int flags, void *data)
+{
+	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_bdi = &v9ses->bdi;
+	if (v9ses->cache)
+		sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024)/PAGE_CACHE_SIZE;
+
+	sb->s_flags |= MS_ACTIVE | MS_DIRSYNC | MS_NOATIME;
+	if (!v9ses->cache)
+		sb->s_flags |= MS_SYNCHRONOUS;
+
+#ifdef CONFIG_9P_FS_POSIX_ACL
+	if ((v9ses->flags & V9FS_ACL_MASK) == V9FS_POSIX_ACL)
+		sb->s_flags |= MS_POSIXACL;
+#endif
+
+	save_mount_options(sb, data);
+}
+
+/**
+ * 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 = S_IRWXUGO | 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);
+		/*
+		 * we need to call session_close to tear down some
+		 * of the data structure setup by session_init
+		 */
+		goto close_session;
+	}
+
+	sb = sget(fs_type, NULL, v9fs_set_super, flags, v9ses);
+	if (IS_ERR(sb)) {
+		retval = PTR_ERR(sb);
+		goto clunk_fid;
+	}
+	v9fs_fill_super(sb, v9ses, flags, data);
+
+	if (v9ses->cache)
+		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;
+		}
+		root->d_inode->i_ino = v9fs_qid2ino(&st->qid);
+		v9fs_stat2inode_dotl(st, root->d_inode);
+		kfree(st);
+	} else {
+		struct p9_wstat *st = NULL;
+		st = p9_client_stat(fid);
+		if (IS_ERR(st)) {
+			retval = PTR_ERR(st);
+			goto release_sb;
+		}
+
+		root->d_inode->i_ino = v9fs_qid2ino(&st->qid);
+		v9fs_stat2inode(st, root->d_inode, sb);
+
+		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_client_clunk(fid);
+close_session:
+	v9fs_session_close(v9ses);
+	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_client_clunk(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.val[0] = rs.fsid & 0xFFFFFFFFUL;
+			buf->f_fsid.val[1] = (rs.fsid >> 32) & 0xFFFFFFFFUL;
+			buf->f_namelen = rs.namelen;
+		}
+		if (res != -ENOSYS)
+			goto done;
+	}
+	res = simple_statfs(dentry, buf);
+done:
+	return res;
+}
+
+static int v9fs_drop_inode(struct inode *inode)
+{
+	struct v9fs_session_info *v9ses;
+	v9ses = v9fs_inode2v9ses(inode);
+	if (v9ses->cache)
+		return generic_drop_inode(inode);
+	/*
+	 * in case of non cached mode always drop the
+	 * 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;
+	}
+	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.
+	 */
+	p9_debug(P9_DEBUG_VFS, "%s: inode %p\n", __func__, inode);
+	v9inode = V9FS_I(inode);
+	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;
+	}
+	return 0;
+}
+
+static const struct super_operations v9fs_super_ops = {
+	.alloc_inode = v9fs_alloc_inode,
+	.destroy_inode = v9fs_destroy_inode,
+	.statfs = simple_statfs,
+	.evict_inode = v9fs_evict_inode,
+	.show_options = generic_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,
+	.destroy_inode = v9fs_destroy_inode,
+	.statfs = v9fs_statfs,
+	.drop_inode = v9fs_drop_inode,
+	.evict_inode = v9fs_evict_inode,
+	.show_options = generic_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");

fs/9p/xattr.c

@@ -0,0 +1,175 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/sched.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;
+	int msize, read_count;
+	u64 offset = 0, attr_size;
+	struct p9_fid *attr_fid;
+
+	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);
+		attr_fid = NULL;
+		goto error;
+	}
+	if (!buffer_size) {
+		/* request to get the attr_size */
+		retval = attr_size;
+		goto error;
+	}
+	if (attr_size > buffer_size) {
+		retval = -ERANGE;
+		goto error;
+	}
+	msize = attr_fid->clnt->msize;
+	while (attr_size) {
+		if (attr_size > (msize - P9_IOHDRSZ))
+			read_count = msize - P9_IOHDRSZ;
+		else
+			read_count = attr_size;
+		read_count = p9_client_read(attr_fid, ((char *)buffer)+offset,
+					NULL, offset, read_count);
+		if (read_count < 0) {
+			/* error in xattr read */
+			retval = read_count;
+			goto error;
+		}
+		offset += read_count;
+		attr_size -= read_count;
+	}
+	/* Total read xattr bytes */
+	retval = offset;
+error:
+	if (attr_fid)
+		p9_client_clunk(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;
+
+	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);
+
+	return v9fs_fid_xattr_get(fid, name, buffer, buffer_size);
+}
+
+/*
+ * 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)
+{
+	struct p9_fid *fid = v9fs_fid_lookup(dentry);
+	if (IS_ERR(fid))
+		return PTR_ERR(fid);
+	return v9fs_fid_xattr_set(fid, name, value, value_len, flags);
+}
+
+int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name,
+		   const void *value, size_t value_len, int flags)
+{
+	u64 offset = 0;
+	int retval, msize, write_count;
+
+	p9_debug(P9_DEBUG_VFS, "name = %s value_len = %zu flags = %d\n",
+		 name, value_len, flags);
+
+	/* Clone it */
+	fid = p9_client_walk(fid, 0, NULL, 1);
+	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);
+		p9_client_clunk(fid);
+		return retval;
+	}
+	msize = fid->clnt->msize;
+	while (value_len) {
+		if (value_len > (msize - P9_IOHDRSZ))
+			write_count = msize - P9_IOHDRSZ;
+		else
+			write_count = value_len;
+		write_count = p9_client_write(fid, ((char *)value)+offset,
+					NULL, offset, write_count);
+		if (write_count < 0) {
+			/* error in xattr write */
+			retval = write_count;
+			break;
+		}
+		offset += write_count;
+		value_len -= write_count;
+	}
+	return p9_client_clunk(fid);
+}
+
+ssize_t v9fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
+{
+	return v9fs_xattr_get(dentry, NULL, buffer, buffer_size);
+}
+
+const struct xattr_handler *v9fs_xattr_handlers[] = {
+	&v9fs_xattr_user_handler,
+#ifdef CONFIG_9P_FS_POSIX_ACL
+	&v9fs_xattr_acl_access_handler,
+	&v9fs_xattr_acl_default_handler,
+#endif
+	NULL
+};

fs/9p/xattr.h

@@ -0,0 +1,35 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+#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 struct xattr_handler v9fs_xattr_user_handler;
+extern const struct xattr_handler v9fs_xattr_acl_access_handler;
+extern const struct xattr_handler v9fs_xattr_acl_default_handler;
+
+extern ssize_t v9fs_fid_xattr_get(struct p9_fid *, const char *,
+				  void *, size_t);
+extern ssize_t v9fs_xattr_get(struct dentry *, const char *,
+			      void *, size_t);
+extern int v9fs_fid_xattr_set(struct p9_fid *, const char *,
+			  const void *, size_t, int);
+extern int v9fs_xattr_set(struct dentry *, const char *,
+			  const void *, size_t, int);
+extern ssize_t v9fs_listxattr(struct dentry *, char *, size_t);
+#endif /* FS_9P_XATTR_H */

fs/9p/xattr_user.c

@@ -0,0 +1,80 @@
+/*
+ * Copyright IBM Corporation, 2010
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ *
+ */
+
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include "xattr.h"
+
+static int v9fs_xattr_user_get(struct dentry *dentry, const char *name,
+			void *buffer, size_t size, int type)
+{
+	int retval;
+	char *full_name;
+	size_t name_len;
+	size_t prefix_len = XATTR_USER_PREFIX_LEN;
+
+	if (name == NULL)
+		return -EINVAL;
+
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+
+	name_len = strlen(name);
+	full_name = kmalloc(prefix_len + name_len + 1 , GFP_KERNEL);
+	if (!full_name)
+		return -ENOMEM;
+	memcpy(full_name, XATTR_USER_PREFIX, prefix_len);
+	memcpy(full_name+prefix_len, name, name_len);
+	full_name[prefix_len + name_len] = '\0';
+
+	retval = v9fs_xattr_get(dentry, full_name, buffer, size);
+	kfree(full_name);
+	return retval;
+}
+
+static int v9fs_xattr_user_set(struct dentry *dentry, const char *name,
+			const void *value, size_t size, int flags, int type)
+{
+	int retval;
+	char *full_name;
+	size_t name_len;
+	size_t prefix_len = XATTR_USER_PREFIX_LEN;
+
+	if (name == NULL)
+		return -EINVAL;
+
+	if (strcmp(name, "") == 0)
+		return -EINVAL;
+
+	name_len = strlen(name);
+	full_name = kmalloc(prefix_len + name_len + 1 , GFP_KERNEL);
+	if (!full_name)
+		return -ENOMEM;
+	memcpy(full_name, XATTR_USER_PREFIX, prefix_len);
+	memcpy(full_name + prefix_len, name, name_len);
+	full_name[prefix_len + name_len] = '\0';
+
+	retval = v9fs_xattr_set(dentry, full_name, value, size, flags);
+	kfree(full_name);
+	return retval;
+}
+
+struct xattr_handler v9fs_xattr_user_handler = {
+	.prefix	= XATTR_USER_PREFIX,
+	.get	= v9fs_xattr_user_get,
+	.set	= v9fs_xattr_user_set,
+};