Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ericvh/v9fs

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ericvh/v9fs: (46 commits)
  fs/9p: Make the writeback_fid owned by root
  fs/9p: Writeback dirty data before setattr
  fs/9p: call vmtruncate before setattr 9p opeation
  fs/9p: Properly update inode attributes on link
  fs/9p: Prevent multiple inclusion of same header
  fs/9p: Workaround vfs rename rehash bug
  fs/9p: Mark directory inode invalid for many directory inode operations
  fs/9p: Add . and .. dentry revalidation flag
  fs/9p: mark inode attribute invalid on rename, unlink and setattr
  fs/9p: Add support for marking inode attribute invalid
  fs/9p: Initialize root inode number for dotl
  fs/9p: Update link count correctly on different file system operations
  fs/9p: Add drop_inode 9p callback
  fs/9p: Add direct IO support in cached mode
  fs/9p: Fix inode i_size update in file_write
  fs/9p: set default readahead pages in cached mode
  fs/9p: Move writeback fid to v9fs_inode
  fs/9p: Add v9fs_inode
  fs/9p: Don't set stat.st_blocks based on nrpages
  fs/9p: Add inode hashing
  ...

fs/9p/acl.c

@@ -21,8 +21,8 @@
 #include <linux/posix_acl_xattr.h>
 #include "xattr.h"
 #include "acl.h"
-#include "v9fs_vfs.h"
 #include "v9fs.h"
+#include "v9fs_vfs.h"
 
 static struct posix_acl *__v9fs_get_acl(struct p9_fid *fid, char *name)
 {
@@ -59,7 +59,8 @@ int v9fs_get_acl(struct inode *inode, struct p9_fid *fid)
 	struct v9fs_session_info *v9ses;
 
 	v9ses = v9fs_inode2v9ses(inode);
-	if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) {
+	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;
@@ -71,11 +72,15 @@ int v9fs_get_acl(struct inode *inode, struct p9_fid *fid)
 	if (!IS_ERR(dacl) && !IS_ERR(pacl)) {
 		set_cached_acl(inode, ACL_TYPE_DEFAULT, dacl);
 		set_cached_acl(inode, ACL_TYPE_ACCESS, pacl);
-		posix_acl_release(dacl);
-		posix_acl_release(pacl);
 	} else
 		retval = -EIO;
 
+	if (!IS_ERR(dacl))
+		posix_acl_release(dacl);
+
+	if (!IS_ERR(pacl))
+		posix_acl_release(pacl);
+
 	return retval;
 }
 
@@ -100,9 +105,10 @@ int v9fs_check_acl(struct inode *inode, int mask, unsigned int flags)
 		return -ECHILD;
 
 	v9ses = v9fs_inode2v9ses(inode);
-	if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) {
+	if (((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) ||
+			((v9ses->flags & V9FS_ACL_MASK) != V9FS_POSIX_ACL)) {
 		/*
-		 * On access = client mode get the acl
+		 * On access = client  and acl = on mode get the acl
 		 * values from the server
 		 */
 		return 0;
@@ -128,6 +134,10 @@ static int v9fs_set_acl(struct dentry *dentry, int type, struct posix_acl *acl)
 	struct inode *inode = dentry->d_inode;
 
 	set_cached_acl(inode, type, acl);
+
+	if (!acl)
+		return 0;
+
 	/* Set a setxattr request to server */
 	size = posix_acl_xattr_size(acl->a_count);
 	buffer = kmalloc(size, GFP_KERNEL);
@@ -177,9 +187,7 @@ int v9fs_acl_chmod(struct dentry *dentry)
 int v9fs_set_create_acl(struct dentry *dentry,
 			struct posix_acl *dpacl, struct posix_acl *pacl)
 {
-	if (dpacl)
 	v9fs_set_acl(dentry, ACL_TYPE_DEFAULT, dpacl);
-	if (pacl)
 	v9fs_set_acl(dentry, ACL_TYPE_ACCESS, pacl);
 	posix_acl_release(dpacl);
 	posix_acl_release(pacl);

fs/9p/cache.h

@@ -25,20 +25,6 @@
 #include <linux/fscache.h>
 #include <linux/spinlock.h>
 
-extern struct kmem_cache *vcookie_cache;
-
-struct v9fs_cookie {
-	spinlock_t lock;
-	struct inode inode;
-	struct fscache_cookie *fscache;
-	struct p9_qid *qid;
-};
-
-static inline struct v9fs_cookie *v9fs_inode2cookie(const struct inode *inode)
-{
-	return container_of(inode, struct v9fs_cookie, inode);
-}
-
 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;
@@ -64,23 +50,8 @@ extern int __v9fs_readpages_from_fscache(struct inode *inode,
 					 struct list_head *pages,
 					 unsigned *nr_pages);
 extern void __v9fs_readpage_to_fscache(struct inode *inode, struct page *page);
-
-
-/**
- * v9fs_cache_register - Register v9fs file system with the cache
- */
-static inline int v9fs_cache_register(void)
-{
-	return __v9fs_cache_register();
-}
-
-/**
- * v9fs_cache_unregister - Unregister v9fs from the cache
- */
-static inline void v9fs_cache_unregister(void)
-{
-	__v9fs_cache_unregister();
-}
+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)
@@ -117,28 +88,27 @@ static inline void v9fs_readpage_to_fscache(struct inode *inode,
 
 static inline void v9fs_uncache_page(struct inode *inode, struct page *page)
 {
-	struct v9fs_cookie *vcookie = v9fs_inode2cookie(inode);
-	fscache_uncache_page(vcookie->fscache, page);
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+	fscache_uncache_page(v9inode->fscache, page);
 	BUG_ON(PageFsCache(page));
 }
 
-static inline void v9fs_vcookie_set_qid(struct inode *inode,
+static inline void v9fs_fscache_set_key(struct inode *inode,
 					struct p9_qid *qid)
 {
-	struct v9fs_cookie *vcookie = v9fs_inode2cookie(inode);
-	spin_lock(&vcookie->lock);
-	vcookie->qid = qid;
-	spin_unlock(&vcookie->lock);
+	struct v9fs_inode *v9inode = V9FS_I(inode);
+	spin_lock(&v9inode->fscache_lock);
+	v9inode->fscache_key = qid;
+	spin_unlock(&v9inode->fscache_lock);
 }
 
-#else /* CONFIG_9P_FSCACHE */
-
-static inline int v9fs_cache_register(void)
+static inline void v9fs_fscache_wait_on_page_write(struct inode *inode,
+						   struct page *page)
 {
-	return 1;
+	return __v9fs_fscache_wait_on_page_write(inode, page);
 }
 
-static inline void v9fs_cache_unregister(void) {}
+#else /* CONFIG_9P_FSCACHE */
 
 static inline int v9fs_fscache_release_page(struct page *page,
 					    gfp_t gfp) {
@@ -168,9 +138,11 @@ static inline void v9fs_readpage_to_fscache(struct inode *inode,
 static inline void v9fs_uncache_page(struct inode *inode, struct page *page)
 {}
 
-static inline void v9fs_vcookie_set_qid(struct inode *inode,
-					struct p9_qid *qid)
-{}
+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

@@ -125,46 +125,17 @@ static int build_path_from_dentry(struct v9fs_session_info *v9ses,
 	return -ENOMEM;
 }
 
-/**
- * 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)
+static struct p9_fid *v9fs_fid_lookup_with_uid(struct dentry *dentry,
+					       uid_t uid, int any)
 {
-	int i, n, l, clone, any, access;
-	u32 uid;
-	struct p9_fid *fid, *old_fid = NULL;
 	struct dentry *ds;
-	struct v9fs_session_info *v9ses;
 	char **wnames, *uname;
+	int i, n, l, clone, access;
+	struct v9fs_session_info *v9ses;
+	struct p9_fid *fid, *old_fid = NULL;
 
 	v9ses = v9fs_inode2v9ses(dentry->d_inode);
 	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 = ~0;
-		any = 0;
-		break;
-	}
-
 	fid = v9fs_fid_find(dentry, uid, any);
 	if (fid)
 		return fid;
@@ -250,6 +221,45 @@ struct p9_fid *v9fs_fid_lookup(struct dentry *dentry)
 	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)
+{
+	uid_t uid;
+	int  any, access;
+	struct v9fs_session_info *v9ses;
+
+	v9ses = v9fs_inode2v9ses(dentry->d_inode);
+	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 = ~0;
+		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;
@@ -261,3 +271,39 @@ struct p9_fid *v9fs_fid_clone(struct dentry *dentry)
 	ret = p9_client_walk(fid, 0, NULL, 1);
 	return ret;
 }
+
+static struct p9_fid *v9fs_fid_clone_with_uid(struct dentry *dentry, uid_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, 0);
+	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

@@ -19,7 +19,8 @@
  *  Boston, MA  02111-1301  USA
  *
  */
-
+#ifndef FS_9P_FID_H
+#define FS_9P_FID_H
 #include <linux/list.h>
 
 /**
@@ -45,3 +46,5 @@ struct v9fs_dentry {
 struct p9_fid *v9fs_fid_lookup(struct dentry *dentry);
 struct p9_fid *v9fs_fid_clone(struct dentry *dentry);
 int v9fs_fid_add(struct dentry *dentry, struct p9_fid *fid);
+struct p9_fid *v9fs_writeback_fid(struct dentry *dentry);
+#endif

fs/9p/v9fs.c

@@ -39,6 +39,7 @@
 
 static DEFINE_SPINLOCK(v9fs_sessionlist_lock);
 static LIST_HEAD(v9fs_sessionlist);
+struct kmem_cache *v9fs_inode_cache;
 
 /*
  * Option Parsing (code inspired by NFS code)
@@ -55,7 +56,7 @@ enum {
 	/* Cache options */
 	Opt_cache_loose, Opt_fscache,
 	/* Access options */
-	Opt_access,
+	Opt_access, Opt_posixacl,
 	/* Error token */
 	Opt_err
 };
@@ -73,6 +74,7 @@ static const match_table_t tokens = {
 	{Opt_fscache, "fscache"},
 	{Opt_cachetag, "cachetag=%s"},
 	{Opt_access, "access=%s"},
+	{Opt_posixacl, "posixacl"},
 	{Opt_err, NULL}
 };
 
@@ -194,15 +196,7 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
 			else if (strcmp(s, "any") == 0)
 				v9ses->flags |= V9FS_ACCESS_ANY;
 			else if (strcmp(s, "client") == 0) {
-#ifdef CONFIG_9P_FS_POSIX_ACL
 				v9ses->flags |= V9FS_ACCESS_CLIENT;
-#else
-				P9_DPRINTK(P9_DEBUG_ERROR,
-					"access=client option not supported\n");
-				kfree(s);
-				ret = -EINVAL;
-				goto free_and_return;
-#endif
 			} else {
 				v9ses->flags |= V9FS_ACCESS_SINGLE;
 				v9ses->uid = simple_strtoul(s, &e, 10);
@@ -212,6 +206,16 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
 			kfree(s);
 			break;
 
+		case Opt_posixacl:
+#ifdef CONFIG_9P_FS_POSIX_ACL
+			v9ses->flags |= V9FS_POSIX_ACL;
+#else
+			P9_DPRINTK(P9_DEBUG_ERROR,
+					"Not defined CONFIG_9P_FS_POSIX_ACL. "
+					"Ignoring posixacl option\n");
+#endif
+			break;
+
 		default:
 			continue;
 		}
@@ -260,19 +264,12 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 	list_add(&v9ses->slist, &v9fs_sessionlist);
 	spin_unlock(&v9fs_sessionlist_lock);
 
-	v9ses->flags = V9FS_ACCESS_USER;
 	strcpy(v9ses->uname, V9FS_DEFUSER);
 	strcpy(v9ses->aname, V9FS_DEFANAME);
 	v9ses->uid = ~0;
 	v9ses->dfltuid = V9FS_DEFUID;
 	v9ses->dfltgid = V9FS_DEFGID;
 
-	rc = v9fs_parse_options(v9ses, data);
-	if (rc < 0) {
-		retval = rc;
-		goto error;
-	}
-
 	v9ses->clnt = p9_client_create(dev_name, data);
 	if (IS_ERR(v9ses->clnt)) {
 		retval = PTR_ERR(v9ses->clnt);
@@ -281,10 +278,20 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 		goto error;
 	}
 
-	if (p9_is_proto_dotl(v9ses->clnt))
+	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))
+	} 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;
 
@@ -306,6 +313,14 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 		v9ses->flags |= V9FS_ACCESS_ANY;
 		v9ses->uid = ~0;
 	}
+	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, ~0,
 							v9ses->aname);
@@ -467,6 +482,63 @@ static void v9fs_sysfs_cleanup(void)
 	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;
+	v9inode->fscache_key = NULL;
+#endif
+	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)
+{
+	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
  *

fs/9p/v9fs.h

@@ -20,6 +20,9 @@
  *  Boston, MA  02111-1301  USA
  *
  */
+#ifndef FS_9P_V9FS_H
+#define FS_9P_V9FS_H
+
 #include <linux/backing-dev.h>
 
 /**
@@ -28,8 +31,10 @@
  * @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
  */
@@ -37,13 +42,15 @@
 			 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_ACCESS_CLIENT	= 0x10,
+	V9FS_POSIX_ACL		= 0x20
 };
 
 /* possible values of ->cache */
@@ -109,8 +116,28 @@ struct v9fs_session_info {
 	struct list_head slist; /* list of sessions registered with v9fs */
 	struct backing_dev_info bdi;
 	struct rw_semaphore rename_sem;
+	struct p9_fid *root_fid; /* Used for file system sync */
+};
+
+/* cache_validity flags */
+#define V9FS_INO_INVALID_ATTR 0x01
+
+struct v9fs_inode {
+#ifdef CONFIG_9P_FSCACHE
+	spinlock_t fscache_lock;
+	struct fscache_cookie *fscache;
+	struct p9_qid *fscache_key;
+#endif
+	unsigned int cache_validity;
+	struct p9_fid *writeback_fid;
+	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);
@@ -124,14 +151,13 @@ 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(struct v9fs_session_info *v9ses,
+extern struct inode *v9fs_inode_from_fid(struct v9fs_session_info *v9ses,
 					 struct p9_fid *fid,
 					 struct super_block *sb);
-
 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_dotl(struct v9fs_session_info *v9ses,
+extern struct inode *v9fs_inode_from_fid_dotl(struct v9fs_session_info *v9ses,
 					      struct p9_fid *fid,
 					      struct super_block *sb);
 
@@ -158,7 +184,7 @@ static inline int v9fs_proto_dotl(struct v9fs_session_info *v9ses)
 }
 
 /**
- * v9fs_inode_from_fid - Helper routine to populate an inode by
+ * 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
@@ -166,11 +192,12 @@ static inline int v9fs_proto_dotl(struct v9fs_session_info *v9ses)
  *
  */
 static inline struct inode *
-v9fs_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
+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_dotl(v9ses, fid, sb);
+		return v9fs_inode_from_fid_dotl(v9ses, fid, sb);
 	else
-		return v9fs_inode(v9ses, fid, sb);
+		return v9fs_inode_from_fid(v9ses, fid, sb);
 }
+#endif

fs/9p/v9fs_vfs.h

@@ -20,6 +20,8 @@
  *  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.
@@ -36,6 +38,7 @@
  * 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;
@@ -45,13 +48,15 @@ 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;
 
-#ifdef CONFIG_9P_FSCACHE
 struct inode *v9fs_alloc_inode(struct super_block *sb);
 void v9fs_destroy_inode(struct inode *inode);
-#endif
-
 struct inode *v9fs_get_inode(struct super_block *sb, int mode);
+int v9fs_init_inode(struct v9fs_session_info *v9ses,
+		    struct inode *inode, int mode);
 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 *);
@@ -62,8 +67,19 @@ 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, int datasync);
-
-#define P9_LOCK_TIMEOUT (30*HZ)
+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;
+}
+#endif

fs/9p/vfs_addr.c

@@ -39,16 +39,16 @@
 #include "v9fs.h"
 #include "v9fs_vfs.h"
 #include "cache.h"
+#include "fid.h"
 
 /**
- * v9fs_vfs_readpage - read an entire page in from 9P
+ * v9fs_fid_readpage - read an entire page in from 9P
  *
- * @filp: file being read
+ * @fid: fid being read
  * @page: structure to page
  *
  */
-
-static int v9fs_vfs_readpage(struct file *filp, struct page *page)
+static int v9fs_fid_readpage(struct p9_fid *fid, struct page *page)
 {
 	int retval;
 	loff_t offset;
@@ -67,7 +67,7 @@ static int v9fs_vfs_readpage(struct file *filp, struct page *page)
 	buffer = kmap(page);
 	offset = page_offset(page);
 
-	retval = v9fs_file_readn(filp, buffer, NULL, PAGE_CACHE_SIZE, offset);
+	retval = v9fs_fid_readn(fid, buffer, NULL, PAGE_CACHE_SIZE, offset);
 	if (retval < 0) {
 		v9fs_uncache_page(inode, page);
 		goto done;
@@ -86,6 +86,19 @@ static int v9fs_vfs_readpage(struct file *filp, struct 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
  *
@@ -124,7 +137,6 @@ static int v9fs_release_page(struct page *page, gfp_t gfp)
 {
 	if (PagePrivate(page))
 		return 0;
-
 	return v9fs_fscache_release_page(page, gfp);
 }
 
@@ -137,20 +149,89 @@ static int v9fs_release_page(struct page *page, gfp_t gfp)
 
 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
- * Since the writes go directly to the server, we simply return a 0
- * here to indicate success.
- *
  * 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;
 }
 
@@ -173,9 +254,15 @@ static int v9fs_launder_page(struct page *page)
  * with an error.
  *
  */
-ssize_t v9fs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
+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_DPRINTK(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,
@@ -183,9 +270,82 @@ ssize_t v9fs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 
 	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,

fs/9p/vfs_dentry.c

@@ -63,20 +63,15 @@ static int v9fs_dentry_delete(const struct dentry *dentry)
  * v9fs_cached_dentry_delete - called when dentry refcount equals 0
  * @dentry:  dentry in question
  *
- * Only return 1 if our inode is invalid.  Only non-synthetic files
- * (ones without mtime == 0) should be calling this function.
- *
  */
-
 static int v9fs_cached_dentry_delete(const struct dentry *dentry)
 {
-	struct inode *inode = dentry->d_inode;
-	P9_DPRINTK(P9_DEBUG_VFS, " dentry: %s (%p)\n", dentry->d_name.name,
-									dentry);
+	P9_DPRINTK(P9_DEBUG_VFS, " dentry: %s (%p)\n",
+		   dentry->d_name.name, dentry);
 
-	if(!inode)
+	/* Don't cache negative dentries */
+	if (!dentry->d_inode)
 		return 1;
-
 	return 0;
 }
 
@@ -105,7 +100,41 @@ static void v9fs_dentry_release(struct dentry *dentry)
 	}
 }
 
+static int v9fs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
+{
+	struct p9_fid *fid;
+	struct inode *inode;
+	struct v9fs_inode *v9inode;
+
+	if (nd->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 <= 0)
+			return retval;
+	}
+out_valid:
+	return 1;
+}
+
 const struct dentry_operations v9fs_cached_dentry_operations = {
+	.d_revalidate = v9fs_lookup_revalidate,
 	.d_delete = v9fs_cached_dentry_delete,
 	.d_release = v9fs_dentry_release,
 };

fs/9p/vfs_dir.c

@@ -295,7 +295,6 @@ int v9fs_dir_release(struct inode *inode, struct file *filp)
 	P9_DPRINTK(P9_DEBUG_VFS,
 			"v9fs_dir_release: inode: %p filp: %p fid: %d\n",
 			inode, filp, fid ? fid->fid : -1);
-	filemap_write_and_wait(inode->i_mapping);
 	if (fid)
 		p9_client_clunk(fid);
 	return 0;

fs/9p/vfs_super.c

@@ -86,12 +86,15 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
 	} 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 = flags | MS_ACTIVE | MS_SYNCHRONOUS | MS_DIRSYNC |
-	    MS_NOATIME;
+	sb->s_flags = 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_ACCESS_MASK) == V9FS_ACCESS_CLIENT)
+	if ((v9ses->flags & V9FS_ACL_MASK) == V9FS_POSIX_ACL)
 		sb->s_flags |= MS_POSIXACL;
 #endif
 
@@ -151,7 +154,6 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
 		retval = PTR_ERR(inode);
 		goto release_sb;
 	}
-
 	root = d_alloc_root(inode);
 	if (!root) {
 		iput(inode);
@@ -166,7 +168,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
 			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 {
@@ -183,10 +185,21 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
 		p9stat_free(st);
 		kfree(st);
 	}
+	v9fs_fid_add(root, fid);
 	retval = v9fs_get_acl(inode, fid);
 	if (retval)
 		goto release_sb;
-	v9fs_fid_add(root, fid);
+	/*
+	 * Add the root fid to session info. This is used
+	 * for file system sync. We want a cloned fid here
+	 * so that we can do a sync_filesystem after a
+	 * shrink_dcache_for_umount
+	 */
+	v9ses->root_fid = v9fs_fid_clone(root);
+	if (IS_ERR(v9ses->root_fid)) {
+		retval = PTR_ERR(v9ses->root_fid);
+		goto release_sb;
+	}
 
 	P9_DPRINTK(P9_DEBUG_VFS, " simple set mount, return 0\n");
 	return dget(sb->s_root);
@@ -197,15 +210,11 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
 	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.
+	 * we will do the session_close and root dentry
+	 * release in the below call.
 	 */
-	p9_client_clunk(fid);
 	deactivate_locked_super(sb);
 	return ERR_PTR(retval);
 }
@@ -223,7 +232,7 @@ static void v9fs_kill_super(struct super_block *s)
 	P9_DPRINTK(P9_DEBUG_VFS, " %p\n", s);
 
 	kill_anon_super(s);
-
+	p9_client_clunk(v9ses->root_fid);
 	v9fs_session_cancel(v9ses);
 	v9fs_session_close(v9ses);
 	kfree(v9ses);
@@ -276,11 +285,31 @@ static int v9fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	return res;
 }
 
+static int v9fs_sync_fs(struct super_block *sb, int wait)
+{
+	struct v9fs_session_info *v9ses = sb->s_fs_info;
+
+	P9_DPRINTK(P9_DEBUG_VFS, "v9fs_sync_fs: super_block %p\n", sb);
+	return p9_client_sync_fs(v9ses->root_fid);
+}
+
+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 const struct super_operations v9fs_super_ops = {
-#ifdef CONFIG_9P_FSCACHE
 	.alloc_inode = v9fs_alloc_inode,
 	.destroy_inode = v9fs_destroy_inode,
-#endif
 	.statfs = simple_statfs,
 	.evict_inode = v9fs_evict_inode,
 	.show_options = generic_show_options,
@@ -288,11 +317,11 @@ static const struct super_operations v9fs_super_ops = {
 };
 
 static const struct super_operations v9fs_super_ops_dotl = {
-#ifdef CONFIG_9P_FSCACHE
 	.alloc_inode = v9fs_alloc_inode,
 	.destroy_inode = v9fs_destroy_inode,
-#endif
+	.sync_fs = v9fs_sync_fs,
 	.statfs = v9fs_statfs,
+	.drop_inode = v9fs_drop_inode,
 	.evict_inode = v9fs_evict_inode,
 	.show_options = generic_show_options,
 	.umount_begin = v9fs_umount_begin,
@@ -303,5 +332,5 @@ struct file_system_type v9fs_fs_type = {
 	.mount = v9fs_mount,
 	.kill_sb = v9fs_kill_super,
 	.owner = THIS_MODULE,
-	.fs_flags = FS_RENAME_DOES_D_MOVE,
+	.fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT,
 };

include/net/9p/9p.h

@@ -139,6 +139,8 @@ do { \
  */
 
 enum p9_msg_t {
+	P9_TSYNCFS = 0,
+	P9_RSYNCFS,
 	P9_TLERROR = 6,
 	P9_RLERROR,
 	P9_TSTATFS = 8,
@@ -688,7 +690,11 @@ struct p9_rwstat {
  * @id: protocol operating identifier of type &p9_msg_t
  * @tag: transaction id of the request
  * @offset: used by marshalling routines to track currentposition in buffer
- * @capacity: used by marshalling routines to track total capacity
+ * @capacity: used by marshalling routines to track total malloc'd capacity
+ * @pubuf: Payload user buffer given by the caller
+ * @pubuf: Payload kernel buffer given by the caller
+ * @pbuf_size: pubuf/pkbuf(only one will be !NULL) size to be read/write.
+ * @private: For transport layer's use.
  * @sdata: payload
  *
  * &p9_fcall represents the structure for all 9P RPC
@@ -705,6 +711,10 @@ struct p9_fcall {
 
 	size_t offset;
 	size_t capacity;
+	char __user *pubuf;
+	char *pkbuf;
+	size_t pbuf_size;
+	void *private;
 
 	uint8_t *sdata;
 };

include/net/9p/client.h

@@ -230,6 +230,7 @@ int p9_client_create_dotl(struct p9_fid *ofid, char *name, u32 flags, u32 mode,
 		gid_t gid, struct p9_qid *qid);
 int p9_client_clunk(struct p9_fid *fid);
 int p9_client_fsync(struct p9_fid *fid, int datasync);
+int p9_client_sync_fs(struct p9_fid *fid);
 int p9_client_remove(struct p9_fid *fid);
 int p9_client_read(struct p9_fid *fid, char *data, char __user *udata,
 							u64 offset, u32 count);

include/net/9p/transport.h

@@ -26,11 +26,19 @@
 #ifndef NET_9P_TRANSPORT_H
 #define NET_9P_TRANSPORT_H
 
+#define P9_TRANS_PREF_PAYLOAD_MASK 0x1
+
+/* Default. Add Payload to PDU before sending it down to transport layer */
+#define P9_TRANS_PREF_PAYLOAD_DEF  0x0
+/* Send pay load seperately to transport layer along with PDU.*/
+#define P9_TRANS_PREF_PAYLOAD_SEP  0x1
+
 /**
  * struct p9_trans_module - transport module interface
  * @list: used to maintain a list of currently available transports
  * @name: the human-readable name of the transport
  * @maxsize: transport provided maximum packet size
+ * @pref: Preferences of this transport
  * @def: set if this transport should be considered the default
  * @create: member function to create a new connection on this transport
  * @request: member function to issue a request to the transport
@@ -47,6 +55,7 @@ struct p9_trans_module {
 	struct list_head list;
 	char *name;		/* name of transport */
 	int maxsize;		/* max message size of transport */
+	int pref;               /* Preferences of this transport */
 	int def;		/* this transport should be default */
 	struct module *owner;
 	int (*create)(struct p9_client *, const char *, char *);

net/9p/Makefile

@@ -9,6 +9,7 @@ obj-$(CONFIG_NET_9P_RDMA) += 9pnet_rdma.o
 	util.o \
 	protocol.o \
 	trans_fd.o \
+	trans_common.o \
 
 9pnet_virtio-objs := \
 	trans_virtio.o \

net/9p/client.c

@@ -229,10 +229,23 @@ static struct p9_req_t *p9_tag_alloc(struct p9_client *c, u16 tag)
 			return ERR_PTR(-ENOMEM);
 		}
 		init_waitqueue_head(req->wq);
+		if ((c->trans_mod->pref & P9_TRANS_PREF_PAYLOAD_MASK) ==
+				P9_TRANS_PREF_PAYLOAD_SEP) {
+			int alloc_msize = min(c->msize, 4096);
+			req->tc = kmalloc(sizeof(struct p9_fcall)+alloc_msize,
+					GFP_KERNEL);
+			req->tc->capacity = alloc_msize;
+			req->rc = kmalloc(sizeof(struct p9_fcall)+alloc_msize,
+					GFP_KERNEL);
+			req->rc->capacity = alloc_msize;
+		} else {
 			req->tc = kmalloc(sizeof(struct p9_fcall)+c->msize,
 					GFP_KERNEL);
+			req->tc->capacity = c->msize;
 			req->rc = kmalloc(sizeof(struct p9_fcall)+c->msize,
 					GFP_KERNEL);
+			req->rc->capacity = c->msize;
+		}
 		if ((!req->tc) || (!req->rc)) {
 			printk(KERN_ERR "Couldn't grow tag array\n");
 			kfree(req->tc);
@@ -243,9 +256,7 @@ static struct p9_req_t *p9_tag_alloc(struct p9_client *c, u16 tag)
 			return ERR_PTR(-ENOMEM);
 		}
 		req->tc->sdata = (char *) req->tc + sizeof(struct p9_fcall);
-		req->tc->capacity = c->msize;
 		req->rc->sdata = (char *) req->rc + sizeof(struct p9_fcall);
-		req->rc->capacity = c->msize;
 	}
 
 	p9pdu_reset(req->tc);
@@ -443,6 +454,7 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
 {
 	int8_t type;
 	int err;
+	int ecode;
 
 	err = p9_parse_header(req->rc, NULL, &type, NULL, 0);
 	if (err) {
@@ -450,12 +462,30 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
 		return err;
 	}
 
-	if (type == P9_RERROR || type == P9_RLERROR) {
-		int ecode;
+	if (type != P9_RERROR && type != P9_RLERROR)
+		return 0;
 
 	if (!p9_is_proto_dotl(c)) {
 		char *ename;
 
+		if (req->tc->pbuf_size) {
+			/* Handle user buffers */
+			size_t len = req->rc->size - req->rc->offset;
+			if (req->tc->pubuf) {
+				/* User Buffer */
+				err = copy_from_user(
+					&req->rc->sdata[req->rc->offset],
+					req->tc->pubuf, len);
+				if (err) {
+					err = -EFAULT;
+					goto out_err;
+				}
+			} else {
+				/* Kernel Buffer */
+				memmove(&req->rc->sdata[req->rc->offset],
+						req->tc->pkbuf, len);
+			}
+		}
 		err = p9pdu_readf(req->rc, c->proto_version, "s?d",
 				&ename, &ecode);
 		if (err)
@@ -467,7 +497,8 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
 		if (!err || !IS_ERR_VALUE(err)) {
 			err = p9_errstr2errno(ename, strlen(ename));
 
-				P9_DPRINTK(P9_DEBUG_9P, "<<< RERROR (%d) %s\n", -ecode, ename);
+			P9_DPRINTK(P9_DEBUG_9P, "<<< RERROR (%d) %s\n", -ecode,
+					ename);
 
 			kfree(ename);
 		}
@@ -478,8 +509,6 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
 		P9_DPRINTK(P9_DEBUG_9P, "<<< RLERROR (%d)\n", -ecode);
 	}
 
-	} else
-		err = 0;
 
 	return err;
 
@@ -1191,6 +1220,27 @@ int p9_client_fsync(struct p9_fid *fid, int datasync)
 }
 EXPORT_SYMBOL(p9_client_fsync);
 
+int p9_client_sync_fs(struct p9_fid *fid)
+{
+	int err = 0;
+	struct p9_req_t *req;
+	struct p9_client *clnt;
+
+	P9_DPRINTK(P9_DEBUG_9P, ">>> TSYNC_FS fid %d\n", fid->fid);
+
+	clnt = fid->clnt;
+	req = p9_client_rpc(clnt, P9_TSYNCFS, "d", fid->fid);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
+	P9_DPRINTK(P9_DEBUG_9P, "<<< RSYNCFS fid %d\n", fid->fid);
+	p9_free_req(clnt, req);
+error:
+	return err;
+}
+EXPORT_SYMBOL(p9_client_sync_fs);
+
 int p9_client_clunk(struct p9_fid *fid)
 {
 	int err;
@@ -1270,7 +1320,15 @@ p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset,
 	if (count < rsize)
 		rsize = count;
 
-	req = p9_client_rpc(clnt, P9_TREAD, "dqd", fid->fid, offset, rsize);
+	/* Don't bother zerocopy form small IO (< 1024) */
+	if (((clnt->trans_mod->pref & P9_TRANS_PREF_PAYLOAD_MASK) ==
+			P9_TRANS_PREF_PAYLOAD_SEP) && (rsize > 1024)) {
+		req = p9_client_rpc(clnt, P9_TREAD, "dqE", fid->fid, offset,
+				rsize, data, udata);
+	} else {
+		req = p9_client_rpc(clnt, P9_TREAD, "dqd", fid->fid, offset,
+				rsize);
+	}
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto error;
@@ -1284,6 +1342,7 @@ p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset,
 
 	P9_DPRINTK(P9_DEBUG_9P, "<<< RREAD count %d\n", count);
 
+	if (!req->tc->pbuf_size) {
 		if (data) {
 			memmove(data, dataptr, count);
 		} else {
@@ -1293,6 +1352,7 @@ p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset,
 				goto free_and_error;
 			}
 		}
+	}
 	p9_free_req(clnt, req);
 	return count;
 
@@ -1323,12 +1383,21 @@ p9_client_write(struct p9_fid *fid, char *data, const char __user *udata,
 
 	if (count < rsize)
 		rsize = count;
+
+	/* Don't bother zerocopy form small IO (< 1024) */
+	if (((clnt->trans_mod->pref & P9_TRANS_PREF_PAYLOAD_MASK) ==
+				P9_TRANS_PREF_PAYLOAD_SEP) && (rsize > 1024)) {
+		req = p9_client_rpc(clnt, P9_TWRITE, "dqE", fid->fid, offset,
+				rsize, data, udata);
+	} else {
+
 		if (data)
-		req = p9_client_rpc(clnt, P9_TWRITE, "dqD", fid->fid, offset,
-								rsize, data);
+			req = p9_client_rpc(clnt, P9_TWRITE, "dqD", fid->fid,
+					offset, rsize, data);
 		else
-		req = p9_client_rpc(clnt, P9_TWRITE, "dqU", fid->fid, offset,
-								rsize, udata);
+			req = p9_client_rpc(clnt, P9_TWRITE, "dqU", fid->fid,
+					offset, rsize, udata);
+	}
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto error;
@@ -1716,7 +1785,14 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset)
 	if (count < rsize)
 		rsize = count;
 
-	req = p9_client_rpc(clnt, P9_TREADDIR, "dqd", fid->fid, offset, rsize);
+	if ((clnt->trans_mod->pref & P9_TRANS_PREF_PAYLOAD_MASK) ==
+			P9_TRANS_PREF_PAYLOAD_SEP) {
+		req = p9_client_rpc(clnt, P9_TREADDIR, "dqF", fid->fid,
+				offset, rsize, data);
+	} else {
+		req = p9_client_rpc(clnt, P9_TREADDIR, "dqd", fid->fid,
+				offset, rsize);
+	}
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto error;
@@ -1730,7 +1806,7 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset)
 
 	P9_DPRINTK(P9_DEBUG_9P, "<<< RREADDIR count %d\n", count);
 
-	if (data)
+	if (!req->tc->pbuf_size && data)
 		memmove(data, dataptr, count);
 
 	p9_free_req(clnt, req);

net/9p/protocol.c

@@ -114,6 +114,26 @@ pdu_write_u(struct p9_fcall *pdu, const char __user *udata, size_t size)
 	return size - len;
 }
 
+static size_t
+pdu_write_urw(struct p9_fcall *pdu, const char *kdata, const char __user *udata,
+		size_t size)
+{
+	BUG_ON(pdu->size > P9_IOHDRSZ);
+	pdu->pubuf = (char __user *)udata;
+	pdu->pkbuf = (char *)kdata;
+	pdu->pbuf_size = size;
+	return 0;
+}
+
+static size_t
+pdu_write_readdir(struct p9_fcall *pdu, const char *kdata, size_t size)
+{
+	BUG_ON(pdu->size > P9_READDIRHDRSZ);
+	pdu->pkbuf = (char *)kdata;
+	pdu->pbuf_size = size;
+	return 0;
+}
+
 /*
 	b - int8_t
 	w - int16_t
@@ -445,6 +465,25 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt,
 					errcode = -EFAULT;
 			}
 			break;
+		case 'E':{
+				 int32_t cnt = va_arg(ap, int32_t);
+				 const char *k = va_arg(ap, const void *);
+				 const char *u = va_arg(ap, const void *);
+				 errcode = p9pdu_writef(pdu, proto_version, "d",
+						 cnt);
+				 if (!errcode && pdu_write_urw(pdu, k, u, cnt))
+					errcode = -EFAULT;
+			 }
+			 break;
+		case 'F':{
+				 int32_t cnt = va_arg(ap, int32_t);
+				 const char *k = va_arg(ap, const void *);
+				 errcode = p9pdu_writef(pdu, proto_version, "d",
+						 cnt);
+				 if (!errcode && pdu_write_readdir(pdu, k, cnt))
+					errcode = -EFAULT;
+			 }
+			 break;
 		case 'U':{
 				int32_t count = va_arg(ap, int32_t);
 				const char __user *udata =
@@ -579,6 +618,7 @@ EXPORT_SYMBOL(p9stat_read);
 
 int p9pdu_prepare(struct p9_fcall *pdu, int16_t tag, int8_t type)
 {
+	pdu->id = type;
 	return p9pdu_writef(pdu, 0, "dbw", 0, type, tag);
 }
 
@@ -606,6 +646,10 @@ void p9pdu_reset(struct p9_fcall *pdu)
 {
 	pdu->offset = 0;
 	pdu->size = 0;
+	pdu->private = NULL;
+	pdu->pubuf = NULL;
+	pdu->pkbuf = NULL;
+	pdu->pbuf_size = 0;
 }
 
 int p9dirent_read(char *buf, int len, struct p9_dirent *dirent,

net/9p/trans_common.c

+/*
+ * Copyright IBM Corporation, 2010
+ * Author Venkateswararao Jujjuri <jvrao@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/slab.h>
+#include <linux/module.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+#include <linux/scatterlist.h>
+#include "trans_common.h"
+
+/**
+ *  p9_release_req_pages - Release pages after the transaction.
+ *  @*private: PDU's private page of struct trans_rpage_info
+ */
+void
+p9_release_req_pages(struct trans_rpage_info *rpinfo)
+{
+	int i = 0;
+
+	while (rpinfo->rp_data[i] && rpinfo->rp_nr_pages--) {
+		put_page(rpinfo->rp_data[i]);
+		i++;
+	}
+}
+EXPORT_SYMBOL(p9_release_req_pages);
+
+/**
+ * p9_nr_pages - Return number of pages needed to accomodate the payload.
+ */
+int
+p9_nr_pages(struct p9_req_t *req)
+{
+	int start_page, end_page;
+	start_page =  (unsigned long long)req->tc->pubuf >> PAGE_SHIFT;
+	end_page = ((unsigned long long)req->tc->pubuf + req->tc->pbuf_size +
+			PAGE_SIZE - 1) >> PAGE_SHIFT;
+	return end_page - start_page;
+}
+EXPORT_SYMBOL(p9_nr_pages);
+
+/**
+ * payload_gup - Translates user buffer into kernel pages and
+ * pins them either for read/write through get_user_pages_fast().
+ * @req: Request to be sent to server.
+ * @pdata_off: data offset into the first page after translation (gup).
+ * @pdata_len: Total length of the IO. gup may not return requested # of pages.
+ * @nr_pages: number of pages to accomodate the payload
+ * @rw: Indicates if the pages are for read or write.
+ */
+int
+p9_payload_gup(struct p9_req_t *req, size_t *pdata_off, int *pdata_len,
+		int nr_pages, u8 rw)
+{
+	uint32_t first_page_bytes = 0;
+	uint32_t pdata_mapped_pages;
+	struct trans_rpage_info  *rpinfo;
+
+	*pdata_off = (size_t)req->tc->pubuf & (PAGE_SIZE-1);
+
+	if (*pdata_off)
+		first_page_bytes = min((PAGE_SIZE - *pdata_off),
+				req->tc->pbuf_size);
+
+	rpinfo = req->tc->private;
+	pdata_mapped_pages = get_user_pages_fast((unsigned long)req->tc->pubuf,
+			nr_pages, rw, &rpinfo->rp_data[0]);
+
+	if (pdata_mapped_pages < 0) {
+		printk(KERN_ERR "get_user_pages_fast failed:%d udata:%p"
+				"nr_pages:%d\n", pdata_mapped_pages,
+				req->tc->pubuf, nr_pages);
+		pdata_mapped_pages = 0;
+		return -EIO;
+	}
+	rpinfo->rp_nr_pages = pdata_mapped_pages;
+	if (*pdata_off) {
+		*pdata_len = first_page_bytes;
+		*pdata_len += min((req->tc->pbuf_size - *pdata_len),
+				((size_t)pdata_mapped_pages - 1) << PAGE_SHIFT);
+	} else {
+		*pdata_len = min(req->tc->pbuf_size,
+				(size_t)pdata_mapped_pages << PAGE_SHIFT);
+	}
+	return 0;
+}
+EXPORT_SYMBOL(p9_payload_gup);

net/9p/trans_common.h

+/*
+ * Copyright IBM Corporation, 2010
+ * Author Venkateswararao Jujjuri <jvrao@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.
+ *
+ */
+
+/* TRUE if it is user context */
+#define P9_IS_USER_CONTEXT (!segment_eq(get_fs(), KERNEL_DS))
+
+/**
+ * struct trans_rpage_info - To store mapped page information in PDU.
+ * @rp_alloc:Set if this structure is allocd, not a reuse unused space in pdu.
+ * @rp_nr_pages: Number of mapped pages
+ * @rp_data: Array of page pointers
+ */
+struct trans_rpage_info {
+	u8 rp_alloc;
+	int rp_nr_pages;
+	struct page *rp_data[0];
+};
+
+void p9_release_req_pages(struct trans_rpage_info *);
+int p9_payload_gup(struct p9_req_t *, size_t *, int *, int, u8);
+int p9_nr_pages(struct p9_req_t *);

net/9p/trans_virtio.c

@@ -45,6 +45,7 @@
 #include <linux/scatterlist.h>
 #include <linux/virtio.h>
 #include <linux/virtio_9p.h>
+#include "trans_common.h"
 
 #define VIRTQUEUE_NUM	128
 
@@ -155,6 +156,14 @@ static void req_done(struct virtqueue *vq)
 					rc->tag);
 			req = p9_tag_lookup(chan->client, rc->tag);
 			req->status = REQ_STATUS_RCVD;
+			if (req->tc->private) {
+				struct trans_rpage_info *rp = req->tc->private;
+				/*Release pages */
+				p9_release_req_pages(rp);
+				if (rp->rp_alloc)
+					kfree(rp);
+				req->tc->private = NULL;
+			}
 			p9_client_cb(chan->client, req);
 		} else {
 			spin_unlock_irqrestore(&chan->lock, flags);
@@ -202,6 +211,38 @@ static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req)
 	return 1;
 }
 
+/**
+ * pack_sg_list_p - Just like pack_sg_list. Instead of taking a buffer,
+ * this takes a list of pages.
+ * @sg: scatter/gather list to pack into
+ * @start: which segment of the sg_list to start at
+ * @pdata_off: Offset into the first page
+ * @**pdata: a list of pages to add into sg.
+ * @count: amount of data to pack into the scatter/gather list
+ */
+static int
+pack_sg_list_p(struct scatterlist *sg, int start, int limit, size_t pdata_off,
+		struct page **pdata, int count)
+{
+	int s;
+	int i = 0;
+	int index = start;
+
+	if (pdata_off) {
+		s = min((int)(PAGE_SIZE - pdata_off), count);
+		sg_set_page(&sg[index++], pdata[i++], s, pdata_off);
+		count -= s;
+	}
+
+	while (count) {
+		BUG_ON(index > limit);
+		s = min((int)PAGE_SIZE, count);
+		sg_set_page(&sg[index++], pdata[i++], s, 0);
+		count -= s;
+	}
+	return index-start;
+}
+
 /**
  * p9_virtio_request - issue a request
  * @client: client instance issuing the request
@@ -212,22 +253,97 @@ static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req)
 static int
 p9_virtio_request(struct p9_client *client, struct p9_req_t *req)
 {
-	int in, out;
+	int in, out, inp, outp;
 	struct virtio_chan *chan = client->trans;
 	char *rdata = (char *)req->rc+sizeof(struct p9_fcall);
 	unsigned long flags;
-	int err;
+	size_t pdata_off = 0;
+	struct trans_rpage_info *rpinfo = NULL;
+	int err, pdata_len = 0;
 
 	P9_DPRINTK(P9_DEBUG_TRANS, "9p debug: virtio request\n");
 
 req_retry:
 	req->status = REQ_STATUS_SENT;
 
+	if (req->tc->pbuf_size && (req->tc->pubuf && P9_IS_USER_CONTEXT)) {
+		int nr_pages = p9_nr_pages(req);
+		int rpinfo_size = sizeof(struct trans_rpage_info) +
+			sizeof(struct page *) * nr_pages;
+
+		if (rpinfo_size <= (req->tc->capacity - req->tc->size)) {
+			/* We can use sdata */
+			req->tc->private = req->tc->sdata + req->tc->size;
+			rpinfo = (struct trans_rpage_info *)req->tc->private;
+			rpinfo->rp_alloc = 0;
+		} else {
+			req->tc->private = kmalloc(rpinfo_size, GFP_NOFS);
+			if (!req->tc->private) {
+				P9_DPRINTK(P9_DEBUG_TRANS, "9p debug: "
+					"private kmalloc returned NULL");
+				return -ENOMEM;
+			}
+			rpinfo = (struct trans_rpage_info *)req->tc->private;
+			rpinfo->rp_alloc = 1;
+		}
+
+		err = p9_payload_gup(req, &pdata_off, &pdata_len, nr_pages,
+				req->tc->id == P9_TREAD ? 1 : 0);
+		if (err < 0) {
+			if (rpinfo->rp_alloc)
+				kfree(rpinfo);
+			return err;
+		}
+	}
+
 	spin_lock_irqsave(&chan->lock, flags);
+
+	/* Handle out VirtIO ring buffers */
 	out = pack_sg_list(chan->sg, 0, VIRTQUEUE_NUM, req->tc->sdata,
 			req->tc->size);
-	in = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM-out, rdata,
+
+	if (req->tc->pbuf_size && (req->tc->id == P9_TWRITE)) {
+		/* We have additional write payload buffer to take care */
+		if (req->tc->pubuf && P9_IS_USER_CONTEXT) {
+			outp = pack_sg_list_p(chan->sg, out, VIRTQUEUE_NUM,
+					pdata_off, rpinfo->rp_data, pdata_len);
+		} else {
+			char *pbuf = req->tc->pubuf ? req->tc->pubuf :
+								req->tc->pkbuf;
+			outp = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM, pbuf,
+					req->tc->pbuf_size);
+		}
+		out += outp;
+	}
+
+	/* Handle in VirtIO ring buffers */
+	if (req->tc->pbuf_size &&
+		((req->tc->id == P9_TREAD) || (req->tc->id == P9_TREADDIR))) {
+		/*
+		 * Take care of additional Read payload.
+		 * 11 is the read/write header = PDU Header(7) + IO Size (4).
+		 * Arrange in such a way that server places header in the
+		 * alloced memory and payload onto the user buffer.
+		 */
+		inp = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM, rdata, 11);
+		/*
+		 * Running executables in the filesystem may result in
+		 * a read request with kernel buffer as opposed to user buffer.
+		 */
+		if (req->tc->pubuf && P9_IS_USER_CONTEXT) {
+			in = pack_sg_list_p(chan->sg, out+inp, VIRTQUEUE_NUM,
+					pdata_off, rpinfo->rp_data, pdata_len);
+		} else {
+			char *pbuf = req->tc->pubuf ? req->tc->pubuf :
+								req->tc->pkbuf;
+			in = pack_sg_list(chan->sg, out+inp, VIRTQUEUE_NUM,
+					pbuf, req->tc->pbuf_size);
+		}
+		in += inp;
+	} else {
+		in = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM, rdata,
 				client->msize);
+	}
 
 	err = virtqueue_add_buf(chan->vq, chan->sg, out, in, req->tc);
 	if (err < 0) {
@@ -246,6 +362,8 @@ p9_virtio_request(struct p9_client *client, struct p9_req_t *req)
 			P9_DPRINTK(P9_DEBUG_TRANS,
 					"9p debug: "
 					"virtio rpc add_buf returned failure");
+			if (rpinfo && rpinfo->rp_alloc)
+				kfree(rpinfo);
 			return -EIO;
 		}
 	}
@@ -448,6 +566,7 @@ static struct p9_trans_module p9_virtio_trans = {
 	.request = p9_virtio_request,
 	.cancel = p9_virtio_cancel,
 	.maxsize = PAGE_SIZE*16,
+	.pref = P9_TRANS_PREF_PAYLOAD_SEP,
 	.def = 0,
 	.owner = THIS_MODULE,
 };