270 files changed, 6343 insertions, 3229 deletions

diff --git a/fs/9p/acl.c b/fs/9p/acl.c
index 12d602351dbe..6e58c4ca1e6e 100644
--- a/fs/9p/acl.c
+++ b/fs/9p/acl.c
@@ -91,11 +91,14 @@ static struct posix_acl *v9fs_get_cached_acl(struct inode *inode, int type)
         return acl;
 }
 
-int v9fs_check_acl(struct inode *inode, int mask)
+int v9fs_check_acl(struct inode *inode, int mask, unsigned int flags)
 {
         struct posix_acl *acl;
         struct v9fs_session_info *v9ses;
 
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
         v9ses = v9fs_inode2v9ses(inode);
         if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) {
                 /*
diff --git a/fs/9p/acl.h b/fs/9p/acl.h
index 59e18c2e8c7e..7ef3ac9f6d95 100644
--- a/fs/9p/acl.h
+++ b/fs/9p/acl.h
@@ -16,7 +16,7 @@
 
 #ifdef CONFIG_9P_FS_POSIX_ACL
 extern int v9fs_get_acl(struct inode *, struct p9_fid *);
-extern int v9fs_check_acl(struct inode *inode, int mask);
+extern int v9fs_check_acl(struct inode *inode, int mask, unsigned int flags);
 extern int v9fs_acl_chmod(struct dentry *);
 extern int v9fs_set_create_acl(struct dentry *,
                                struct posix_acl *, struct posix_acl *);
diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index cbf4e50f3933..466d2a4fc5cb 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -51,7 +51,7 @@
  *
  */
 
-static int v9fs_dentry_delete(struct dentry *dentry)
+static int v9fs_dentry_delete(const struct dentry *dentry)
 {
         P9_DPRINTK(P9_DEBUG_VFS, " dentry: %s (%p)\n", dentry->d_name.name,
                                                                         dentry);
@@ -68,7 +68,7 @@ static int v9fs_dentry_delete(struct dentry *dentry)
  *
  */
 
-static int v9fs_cached_dentry_delete(struct dentry *dentry)
+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,
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 34bf71b56542..59782981b225 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -237,10 +237,17 @@ struct inode *v9fs_alloc_inode(struct super_block *sb)
  *
  */
 
-void v9fs_destroy_inode(struct inode *inode)
+static void v9fs_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(vcookie_cache, v9fs_inode2cookie(inode));
 }
+
+void v9fs_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, v9fs_i_callback);
+}
 #endif
 
 /**
@@ -270,11 +277,11 @@ static struct dentry *v9fs_dentry_from_dir_inode(struct inode *inode)
 {
         struct dentry *dentry;
 
-        spin_lock(&dcache_lock);
+        spin_lock(&inode->i_lock);
         /* Directory should have only one entry. */
         BUG_ON(S_ISDIR(inode->i_mode) && !list_is_singular(&inode->i_dentry));
         dentry = list_entry(inode->i_dentry.next, struct dentry, d_alias);
-        spin_unlock(&dcache_lock);
+        spin_unlock(&inode->i_lock);
         return dentry;
 }
 
@@ -628,9 +635,9 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
         }
 
         if (v9ses->cache)
-                dentry->d_op = &v9fs_cached_dentry_operations;
+                d_set_d_op(dentry, &v9fs_cached_dentry_operations);
         else
-                dentry->d_op = &v9fs_dentry_operations;
+                d_set_d_op(dentry, &v9fs_dentry_operations);
 
         d_instantiate(dentry, inode);
         err = v9fs_fid_add(dentry, fid);
@@ -742,7 +749,7 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, int omode,
                                 err);
                         goto error;
                 }
-                dentry->d_op = &v9fs_cached_dentry_operations;
+                d_set_d_op(dentry, &v9fs_cached_dentry_operations);
                 d_instantiate(dentry, inode);
                 err = v9fs_fid_add(dentry, fid);
                 if (err < 0)
@@ -760,7 +767,7 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, int omode,
                         err = PTR_ERR(inode);
                         goto error;
                 }
-                dentry->d_op = &v9fs_dentry_operations;
+                d_set_d_op(dentry, &v9fs_dentry_operations);
                 d_instantiate(dentry, inode);
         }
         /* Now set the ACL based on the default value */
@@ -949,7 +956,7 @@ static int v9fs_vfs_mkdir_dotl(struct inode *dir,
                                 err);
                         goto error;
                 }
-                dentry->d_op = &v9fs_cached_dentry_operations;
+                d_set_d_op(dentry, &v9fs_cached_dentry_operations);
                 d_instantiate(dentry, inode);
                 err = v9fs_fid_add(dentry, fid);
                 if (err < 0)
@@ -966,7 +973,7 @@ static int v9fs_vfs_mkdir_dotl(struct inode *dir,
                         err = PTR_ERR(inode);
                         goto error;
                 }
-                dentry->d_op = &v9fs_dentry_operations;
+                d_set_d_op(dentry, &v9fs_dentry_operations);
                 d_instantiate(dentry, inode);
         }
         /* Now set the ACL based on the default value */
@@ -1034,9 +1041,9 @@ static struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 
 inst_out:
         if (v9ses->cache)
-                dentry->d_op = &v9fs_cached_dentry_operations;
+                d_set_d_op(dentry, &v9fs_cached_dentry_operations);
         else
-                dentry->d_op = &v9fs_dentry_operations;
+                d_set_d_op(dentry, &v9fs_dentry_operations);
 
         d_add(dentry, inode);
         return NULL;
@@ -1702,7 +1709,7 @@ v9fs_vfs_symlink_dotl(struct inode *dir, struct dentry *dentry,
                                         err);
                         goto error;
                 }
-                dentry->d_op = &v9fs_cached_dentry_operations;
+                d_set_d_op(dentry, &v9fs_cached_dentry_operations);
                 d_instantiate(dentry, inode);
                 err = v9fs_fid_add(dentry, fid);
                 if (err < 0)
@@ -1715,7 +1722,7 @@ v9fs_vfs_symlink_dotl(struct inode *dir, struct dentry *dentry,
                         err = PTR_ERR(inode);
                         goto error;
                 }
-                dentry->d_op = &v9fs_dentry_operations;
+                d_set_d_op(dentry, &v9fs_dentry_operations);
                 d_instantiate(dentry, inode);
         }
 
@@ -1849,7 +1856,7 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir,
                 ihold(old_dentry->d_inode);
         }
 
-        dentry->d_op = old_dentry->d_op;
+        d_set_d_op(dentry, old_dentry->d_op);
         d_instantiate(dentry, old_dentry->d_inode);
 
         return err;
@@ -1973,7 +1980,7 @@ v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, int omode,
                                 err);
                         goto error;
                 }
-                dentry->d_op = &v9fs_cached_dentry_operations;
+                d_set_d_op(dentry, &v9fs_cached_dentry_operations);
                 d_instantiate(dentry, inode);
                 err = v9fs_fid_add(dentry, fid);
                 if (err < 0)
@@ -1989,7 +1996,7 @@ v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, int omode,
                         err = PTR_ERR(inode);
                         goto error;
                 }
-                dentry->d_op = &v9fs_dentry_operations;
+                d_set_d_op(dentry, &v9fs_dentry_operations);
                 d_instantiate(dentry, inode);
         }
         /* Now set the ACL based on the default value */
diff --git a/fs/adfs/dir.c b/fs/adfs/dir.c
index f4287e4de744..bf7693c384f9 100644
--- a/fs/adfs/dir.c
+++ b/fs/adfs/dir.c
@@ -201,7 +201,8 @@ const struct file_operations adfs_dir_operations = {
 };
 
 static int
-adfs_hash(struct dentry *parent, struct qstr *qstr)
+adfs_hash(const struct dentry *parent, const struct inode *inode,
+                struct qstr *qstr)
 {
         const unsigned int name_len = ADFS_SB(parent->d_sb)->s_namelen;
         const unsigned char *name;
@@ -237,17 +238,19 @@ adfs_hash(struct dentry *parent, struct qstr *qstr)
  * requirements of the underlying filesystem.
  */
 static int
-adfs_compare(struct dentry *parent, struct qstr *entry, struct qstr *name)
+adfs_compare(const struct dentry *parent, const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name)
 {
         int i;
 
-        if (entry->len != name->len)
+        if (len != name->len)
                 return 1;
 
         for (i = 0; i < name->len; i++) {
                 char a, b;
 
-                a = entry->name[i];
+                a = str[i];
                 b = name->name[i];
 
                 if (a >= 'A' && a <= 'Z')
@@ -273,7 +276,7 @@ adfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
         struct object_info obj;
         int error;
 
-        dentry->d_op = &adfs_dentry_operations; 
+        d_set_d_op(dentry, &adfs_dentry_operations);
         lock_kernel();
         error = adfs_dir_lookup_byname(dir, &dentry->d_name, &obj);
         if (error == 0) {
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index 959dbff2d42d..a4041b52fbca 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -240,11 +240,18 @@ static struct inode *adfs_alloc_inode(struct super_block *sb)
         return &ei->vfs_inode;
 }
 
-static void adfs_destroy_inode(struct inode *inode)
+static void adfs_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(adfs_inode_cachep, ADFS_I(inode));
 }
 
+static void adfs_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, adfs_i_callback);
+}
+
 static void init_once(void *foo)
 {
         struct adfs_inode_info *ei = (struct adfs_inode_info *) foo;
@@ -477,7 +484,7 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent)
                 adfs_error(sb, "get root inode failed\n");
                 goto error;
         } else
-                sb->s_root->d_op = &adfs_dentry_operations;
+                d_set_d_op(sb->s_root, &adfs_dentry_operations);
         unlock_kernel();
         return 0;
 
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index 7d0f0a30f7a3..3a4557e8325c 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -128,7 +128,7 @@ affs_fix_dcache(struct dentry *dentry, u32 entry_ino)
         void *data = dentry->d_fsdata;
         struct list_head *head, *next;
 
-        spin_lock(&dcache_lock);
+        spin_lock(&inode->i_lock);
         head = &inode->i_dentry;
         next = head->next;
         while (next != head) {
@@ -139,7 +139,7 @@ affs_fix_dcache(struct dentry *dentry, u32 entry_ino)
                 }
                 next = next->next;
         }
-        spin_unlock(&dcache_lock);
+        spin_unlock(&inode->i_lock);
 }
 
 
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index 914d1c0bc07a..944a4042fb65 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -13,11 +13,19 @@
 typedef int (*toupper_t)(int);
 
 static int       affs_toupper(int ch);
-static int       affs_hash_dentry(struct dentry *, struct qstr *);
-static int       affs_compare_dentry(struct dentry *, struct qstr *, struct qstr *);
+static int       affs_hash_dentry(const struct dentry *,
+                const struct inode *, struct qstr *);
+static int       affs_compare_dentry(const struct dentry *parent,
+                const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name);
 static int       affs_intl_toupper(int ch);
-static int       affs_intl_hash_dentry(struct dentry *, struct qstr *);
-static int       affs_intl_compare_dentry(struct dentry *, struct qstr *, struct qstr *);
+static int       affs_intl_hash_dentry(const struct dentry *,
+                const struct inode *, struct qstr *);
+static int       affs_intl_compare_dentry(const struct dentry *parent,
+                const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name);
 
 const struct dentry_operations affs_dentry_operations = {
         .d_hash         = affs_hash_dentry,
@@ -58,13 +66,13 @@ affs_get_toupper(struct super_block *sb)
  * Note: the dentry argument is the parent dentry.
  */
 static inline int
-__affs_hash_dentry(struct dentry *dentry, struct qstr *qstr, toupper_t toupper)
+__affs_hash_dentry(struct qstr *qstr, toupper_t toupper)
 {
         const u8 *name = qstr->name;
         unsigned long hash;
         int i;
 
-        i = affs_check_name(qstr->name,qstr->len);
+        i = affs_check_name(qstr->name, qstr->len);
         if (i)
                 return i;
 
@@ -78,39 +86,41 @@ __affs_hash_dentry(struct dentry *dentry, struct qstr *qstr, toupper_t toupper)
 }
 
 static int
-affs_hash_dentry(struct dentry *dentry, struct qstr *qstr)
+affs_hash_dentry(const struct dentry *dentry, const struct inode *inode,
+                struct qstr *qstr)
 {
-        return __affs_hash_dentry(dentry, qstr, affs_toupper);
+        return __affs_hash_dentry(qstr, affs_toupper);
 }
 static int
-affs_intl_hash_dentry(struct dentry *dentry, struct qstr *qstr)
+affs_intl_hash_dentry(const struct dentry *dentry, const struct inode *inode,
+                struct qstr *qstr)
 {
-        return __affs_hash_dentry(dentry, qstr, affs_intl_toupper);
+        return __affs_hash_dentry(qstr, affs_intl_toupper);
 }
 
-static inline int
-__affs_compare_dentry(struct dentry *dentry, struct qstr *a, struct qstr *b, toupper_t toupper)
+static inline int __affs_compare_dentry(unsigned int len,
+                const char *str, const struct qstr *name, toupper_t toupper)
 {
-        const u8 *aname = a->name;
-        const u8 *bname = b->name;
-        int len;
+        const u8 *aname = str;
+        const u8 *bname = name->name;
 
-        /* 'a' is the qstr of an already existing dentry, so the name
-         * must be valid. 'b' must be validated first.
+        /*
+         * 'str' is the name of an already existing dentry, so the name
+         * must be valid. 'name' must be validated first.
          */
 
-        if (affs_check_name(b->name,b->len))
+        if (affs_check_name(name->name, name->len))
                 return 1;
 
-        /* If the names are longer than the allowed 30 chars,
+        /*
+         * If the names are longer than the allowed 30 chars,
          * the excess is ignored, so their length may differ.
          */
-        len = a->len;
         if (len >= 30) {
-                if (b->len < 30)
+                if (name->len < 30)
                         return 1;
                 len = 30;
-        } else if (len != b->len)
+        } else if (len != name->len)
                 return 1;
 
         for (; len > 0; len--)
@@ -121,14 +131,18 @@ __affs_compare_dentry(struct dentry *dentry, struct qstr *a, struct qstr *b, tou
 }
 
 static int
-affs_compare_dentry(struct dentry *dentry, struct qstr *a, struct qstr *b)
+affs_compare_dentry(const struct dentry *parent, const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name)
 {
-        return __affs_compare_dentry(dentry, a, b, affs_toupper);
+        return __affs_compare_dentry(len, str, name, affs_toupper);
 }
 static int
-affs_intl_compare_dentry(struct dentry *dentry, struct qstr *a, struct qstr *b)
+affs_intl_compare_dentry(const struct dentry *parent,const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name)
 {
-        return __affs_compare_dentry(dentry, a, b, affs_intl_toupper);
+        return __affs_compare_dentry(len, str, name, affs_intl_toupper);
 }
 
 /*
@@ -226,7 +240,7 @@ affs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
                 if (IS_ERR(inode))
                         return ERR_CAST(inode);
         }
-        dentry->d_op = AFFS_SB(sb)->s_flags & SF_INTL ? &affs_intl_dentry_operations : &affs_dentry_operations;
+        d_set_d_op(dentry, AFFS_SB(sb)->s_flags & SF_INTL ? &affs_intl_dentry_operations : &affs_dentry_operations);
         d_add(dentry, inode);
         return NULL;
 }
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 0cf7f4384cbd..d39081bbe7ce 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -95,11 +95,18 @@ static struct inode *affs_alloc_inode(struct super_block *sb)
         return &i->vfs_inode;
 }
 
-static void affs_destroy_inode(struct inode *inode)
+static void affs_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(affs_inode_cachep, AFFS_I(inode));
 }
 
+static void affs_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, affs_i_callback);
+}
+
 static void init_once(void *foo)
 {
         struct affs_inode_info *ei = (struct affs_inode_info *) foo;
@@ -475,7 +482,7 @@ got_root:
                 printk(KERN_ERR "AFFS: Get root inode failed\n");
                 goto out_error;
         }
-        sb->s_root->d_op = &affs_dentry_operations;
+        d_set_d_op(sb->s_root, &affs_dentry_operations);
 
         pr_debug("AFFS: s_flags=%lX\n",sb->s_flags);
         return 0;
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 5439e1bc9a86..34a3263d60a4 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/fs.h>
+#include <linux/namei.h>
 #include <linux/pagemap.h>
 #include <linux/ctype.h>
 #include <linux/sched.h>
@@ -23,7 +24,7 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
 static int afs_dir_open(struct inode *inode, struct file *file);
 static int afs_readdir(struct file *file, void *dirent, filldir_t filldir);
 static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd);
-static int afs_d_delete(struct dentry *dentry);
+static int afs_d_delete(const struct dentry *dentry);
 static void afs_d_release(struct dentry *dentry);
 static int afs_lookup_filldir(void *_cookie, const char *name, int nlen,
                                   loff_t fpos, u64 ino, unsigned dtype);
@@ -581,7 +582,7 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
         }
 
 success:
-        dentry->d_op = &afs_fs_dentry_operations;
+        d_set_d_op(dentry, &afs_fs_dentry_operations);
 
         d_add(dentry, inode);
         _leave(" = 0 { vn=%u u=%u } -> { ino=%lu v=%llu }",
@@ -607,6 +608,9 @@ static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd)
         void *dir_version;
         int ret;
 
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
+
         vnode = AFS_FS_I(dentry->d_inode);
 
         if (dentry->d_inode)
@@ -730,7 +734,7 @@ out_bad:
  * - called from dput() when d_count is going to 0.
  * - return 1 to request dentry be unhashed, 0 otherwise
  */
-static int afs_d_delete(struct dentry *dentry)
+static int afs_d_delete(const struct dentry *dentry)
 {
         _enter("%s", dentry->d_name.name);
 
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index cca8eef736fc..6d4bc1c8ff60 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -624,7 +624,7 @@ extern void afs_clear_permits(struct afs_vnode *);
 extern void afs_cache_permit(struct afs_vnode *, struct key *, long);
 extern void afs_zap_permits(struct rcu_head *);
 extern struct key *afs_request_key(struct afs_cell *);
-extern int afs_permission(struct inode *, int);
+extern int afs_permission(struct inode *, int, unsigned int);
 
 /*
  * server.c
diff --git a/fs/afs/security.c b/fs/afs/security.c
index bb4ed144d0e4..f44b9d355377 100644
--- a/fs/afs/security.c
+++ b/fs/afs/security.c
@@ -285,13 +285,16 @@ static int afs_check_permit(struct afs_vnode *vnode, struct key *key,
  * - AFS ACLs are attached to directories only, and a file is controlled by its
  *   parent directory's ACL
  */
-int afs_permission(struct inode *inode, int mask)
+int afs_permission(struct inode *inode, int mask, unsigned int flags)
 {
         struct afs_vnode *vnode = AFS_FS_I(inode);
         afs_access_t uninitialized_var(access);
         struct key *key;
         int ret;
 
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
         _enter("{{%x:%u},%lx},%x,",
                vnode->fid.vid, vnode->fid.vnode, vnode->flags, mask);
 
@@ -347,7 +350,7 @@ int afs_permission(struct inode *inode, int mask)
         }
 
         key_put(key);
-        ret = generic_permission(inode, mask, NULL);
+        ret = generic_permission(inode, mask, flags, NULL);
         _leave(" = %d", ret);
         return ret;
 
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 27201cffece4..f901a9d7c111 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -498,6 +498,14 @@ static struct inode *afs_alloc_inode(struct super_block *sb)
         return &vnode->vfs_inode;
 }
 
+static void afs_i_callback(struct rcu_head *head)
+{
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        struct afs_vnode *vnode = AFS_FS_I(inode);
+        INIT_LIST_HEAD(&inode->i_dentry);
+        kmem_cache_free(afs_inode_cachep, vnode);
+}
+
 /*
  * destroy an AFS inode struct
  */
@@ -511,7 +519,7 @@ static void afs_destroy_inode(struct inode *inode)
 
         ASSERTCMP(vnode->server, ==, NULL);
 
-        kmem_cache_free(afs_inode_cachep, vnode);
+        call_rcu(&inode->i_rcu, afs_i_callback);
         atomic_dec(&afs_count_active_inodes);
 }
 
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 57ce55b2564c..5fd38112a6ca 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -102,7 +102,7 @@ struct file *anon_inode_getfile(const char *name,
         this.name = name;
         this.len = strlen(name);
         this.hash = 0;
-        path.dentry = d_alloc(anon_inode_mnt->mnt_sb->s_root, &this);
+        path.dentry = d_alloc_pseudo(anon_inode_mnt->mnt_sb, &this);
         if (!path.dentry)
                 goto err_module;
 
@@ -113,7 +113,7 @@ struct file *anon_inode_getfile(const char *name,
          */
         ihold(anon_inode_inode);
 
-        path.dentry->d_op = &anon_inodefs_dentry_operations;
+        d_set_d_op(path.dentry, &anon_inodefs_dentry_operations);
         d_instantiate(path.dentry, anon_inode_inode);
 
         error = -ENFILE;
@@ -232,7 +232,7 @@ static int __init anon_inode_init(void)
         return 0;
 
 err_mntput:
-        mntput(anon_inode_mnt);
+        mntput_long(anon_inode_mnt);
 err_unregister_filesystem:
         unregister_filesystem(&anon_inode_fs_type);
 err_exit:
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index 3d283abf67d7..0fffe1c24cec 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -16,6 +16,7 @@
 #include <linux/auto_fs4.h>
 #include <linux/auto_dev-ioctl.h>
 #include <linux/mutex.h>
+#include <linux/spinlock.h>
 #include <linux/list.h>
 
 /* This is the range of ioctl() numbers we claim as ours */
@@ -60,6 +61,8 @@ do {							\
                 current->pid, __func__, ##args);        \
 } while (0)
 
+extern spinlock_t autofs4_lock;
+
 /* Unified info structure.  This is pointed to by both the dentry and
    inode structures.  Each file in the filesystem has an instance of this
    structure.  It holds a reference to the dentry, so dentries are never
@@ -254,17 +257,15 @@ static inline int simple_positive(struct dentry *dentry)
         return dentry->d_inode && !d_unhashed(dentry);
 }
 
-static inline int __simple_empty(struct dentry *dentry)
+static inline void __autofs4_add_expiring(struct dentry *dentry)
 {
-        struct dentry *child;
-        int ret = 0;
-
-        list_for_each_entry(child, &dentry->d_subdirs, d_u.d_child)
-                if (simple_positive(child))
-                        goto out;
-        ret = 1;
-out:
-        return ret;
+        struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
+        struct autofs_info *ino = autofs4_dentry_ino(dentry);
+        if (ino) {
+                if (list_empty(&ino->expiring))
+                        list_add(&ino->expiring, &sbi->expiring_list);
+        }
+        return;
 }
 
 static inline void autofs4_add_expiring(struct dentry *dentry)
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index a796c9417fb1..cc1d01365905 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -91,24 +91,64 @@ done:
 }
 
 /*
- * Calculate next entry in top down tree traversal.
- * From next_mnt in namespace.c - elegant.
+ * Calculate and dget next entry in top down tree traversal.
  */
-static struct dentry *next_dentry(struct dentry *p, struct dentry *root)
+static struct dentry *get_next_positive_dentry(struct dentry *prev,
+                                                struct dentry *root)
 {
-        struct list_head *next = p->d_subdirs.next;
+        struct list_head *next;
+        struct dentry *p, *ret;
+
+        if (prev == NULL)
+                return dget(prev);
 
+        spin_lock(&autofs4_lock);
+relock:
+        p = prev;
+        spin_lock(&p->d_lock);
+again:
+        next = p->d_subdirs.next;
         if (next == &p->d_subdirs) {
                 while (1) {
-                        if (p == root)
+                        struct dentry *parent;
+
+                        if (p == root) {
+                                spin_unlock(&p->d_lock);
+                                spin_unlock(&autofs4_lock);
+                                dput(prev);
                                 return NULL;
+                        }
+
+                        parent = p->d_parent;
+                        if (!spin_trylock(&parent->d_lock)) {
+                                spin_unlock(&p->d_lock);
+                                cpu_relax();
+                                goto relock;
+                        }
+                        spin_unlock(&p->d_lock);
                         next = p->d_u.d_child.next;
-                        if (next != &p->d_parent->d_subdirs)
+                        p = parent;
+                        if (next != &parent->d_subdirs)
                                 break;
-                        p = p->d_parent;
                 }
         }
-        return list_entry(next, struct dentry, d_u.d_child);
+        ret = list_entry(next, struct dentry, d_u.d_child);
+
+        spin_lock_nested(&ret->d_lock, DENTRY_D_LOCK_NESTED);
+        /* Negative dentry - try next */
+        if (!simple_positive(ret)) {
+                spin_unlock(&ret->d_lock);
+                p = ret;
+                goto again;
+        }
+        dget_dlock(ret);
+        spin_unlock(&ret->d_lock);
+        spin_unlock(&p->d_lock);
+        spin_unlock(&autofs4_lock);
+
+        dput(prev);
+
+        return ret;
 }
 
 /*
@@ -158,18 +198,11 @@ static int autofs4_tree_busy(struct vfsmount *mnt,
         if (!simple_positive(top))
                 return 1;
 
-        spin_lock(&dcache_lock);
-        for (p = top; p; p = next_dentry(p, top)) {
-                /* Negative dentry - give up */
-                if (!simple_positive(p))
-                        continue;
-
+        p = NULL;
+        while ((p = get_next_positive_dentry(p, top))) {
                 DPRINTK("dentry %p %.*s",
                         p, (int) p->d_name.len, p->d_name.name);
 
-                p = dget(p);
-                spin_unlock(&dcache_lock);
-
                 /*
                  * Is someone visiting anywhere in the subtree ?
                  * If there's no mount we need to check the usage
@@ -198,16 +231,13 @@ static int autofs4_tree_busy(struct vfsmount *mnt,
                         else
                                 ino_count++;
 
-                        if (atomic_read(&p->d_count) > ino_count) {
+                        if (p->d_count > ino_count) {
                                 top_ino->last_used = jiffies;
                                 dput(p);
                                 return 1;
                         }
                 }
-                dput(p);
-                spin_lock(&dcache_lock);
         }
-        spin_unlock(&dcache_lock);
 
         /* Timeout of a tree mount is ultimately determined by its top dentry */
         if (!autofs4_can_expire(top, timeout, do_now))
@@ -226,32 +256,21 @@ static struct dentry *autofs4_check_leaves(struct vfsmount *mnt,
         DPRINTK("parent %p %.*s",
                 parent, (int)parent->d_name.len, parent->d_name.name);
 
-        spin_lock(&dcache_lock);
-        for (p = parent; p; p = next_dentry(p, parent)) {
-                /* Negative dentry - give up */
-                if (!simple_positive(p))
-                        continue;
-
+        p = NULL;
+        while ((p = get_next_positive_dentry(p, parent))) {
                 DPRINTK("dentry %p %.*s",
                         p, (int) p->d_name.len, p->d_name.name);
 
-                p = dget(p);
-                spin_unlock(&dcache_lock);
-
                 if (d_mountpoint(p)) {
                         /* Can we umount this guy */
                         if (autofs4_mount_busy(mnt, p))
-                                goto cont;
+                                continue;
 
                         /* Can we expire this guy */
                         if (autofs4_can_expire(p, timeout, do_now))
                                 return p;
                 }
-cont:
-                dput(p);
-                spin_lock(&dcache_lock);
         }
-        spin_unlock(&dcache_lock);
         return NULL;
 }
 
@@ -276,7 +295,9 @@ struct dentry *autofs4_expire_direct(struct super_block *sb,
                 struct autofs_info *ino = autofs4_dentry_ino(root);
                 if (d_mountpoint(root)) {
                         ino->flags |= AUTOFS_INF_MOUNTPOINT;
-                        root->d_mounted--;
+                        spin_lock(&root->d_lock);
+                        root->d_flags &= ~DCACHE_MOUNTED;
+                        spin_unlock(&root->d_lock);
                 }
                 ino->flags |= AUTOFS_INF_EXPIRING;
                 init_completion(&ino->expire_complete);
@@ -302,8 +323,8 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 {
         unsigned long timeout;
         struct dentry *root = sb->s_root;
+        struct dentry *dentry;
         struct dentry *expired = NULL;
-        struct list_head *next;
         int do_now = how & AUTOFS_EXP_IMMEDIATE;
         int exp_leaves = how & AUTOFS_EXP_LEAVES;
         struct autofs_info *ino;
@@ -315,23 +336,8 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
         now = jiffies;
         timeout = sbi->exp_timeout;
 
-        spin_lock(&dcache_lock);
-        next = root->d_subdirs.next;
-
-        /* On exit from the loop expire is set to a dgot dentry
-         * to expire or it's NULL */
-        while ( next != &root->d_subdirs ) {
-                struct dentry *dentry = list_entry(next, struct dentry, d_u.d_child);
-
-                /* Negative dentry - give up */
-                if (!simple_positive(dentry)) {
-                        next = next->next;
-                        continue;
-                }
-
-                dentry = dget(dentry);
-                spin_unlock(&dcache_lock);
-
+        dentry = NULL;
+        while ((dentry = get_next_positive_dentry(dentry, root))) {
                 spin_lock(&sbi->fs_lock);
                 ino = autofs4_dentry_ino(dentry);
 
@@ -347,7 +353,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 
                         /* Path walk currently on this dentry? */
                         ino_count = atomic_read(&ino->count) + 2;
-                        if (atomic_read(&dentry->d_count) > ino_count)
+                        if (dentry->d_count > ino_count)
                                 goto next;
 
                         /* Can we umount this guy */
@@ -369,7 +375,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
                 if (!exp_leaves) {
                         /* Path walk currently on this dentry? */
                         ino_count = atomic_read(&ino->count) + 1;
-                        if (atomic_read(&dentry->d_count) > ino_count)
+                        if (dentry->d_count > ino_count)
                                 goto next;
 
                         if (!autofs4_tree_busy(mnt, dentry, timeout, do_now)) {
@@ -383,7 +389,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
                 } else {
                         /* Path walk currently on this dentry? */
                         ino_count = atomic_read(&ino->count) + 1;
-                        if (atomic_read(&dentry->d_count) > ino_count)
+                        if (dentry->d_count > ino_count)
                                 goto next;
 
                         expired = autofs4_check_leaves(mnt, dentry, timeout, do_now);
@@ -394,11 +400,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
                 }
 next:
                 spin_unlock(&sbi->fs_lock);
-                dput(dentry);
-                spin_lock(&dcache_lock);
-                next = next->next;
         }
-        spin_unlock(&dcache_lock);
         return NULL;
 
 found:
@@ -408,9 +410,13 @@ found:
         ino->flags |= AUTOFS_INF_EXPIRING;
         init_completion(&ino->expire_complete);
         spin_unlock(&sbi->fs_lock);
-        spin_lock(&dcache_lock);
+        spin_lock(&autofs4_lock);
+        spin_lock(&expired->d_parent->d_lock);
+        spin_lock_nested(&expired->d_lock, DENTRY_D_LOCK_NESTED);
         list_move(&expired->d_parent->d_subdirs, &expired->d_u.d_child);
-        spin_unlock(&dcache_lock);
+        spin_unlock(&expired->d_lock);
+        spin_unlock(&expired->d_parent->d_lock);
+        spin_unlock(&autofs4_lock);
         return expired;
 }
 
@@ -499,7 +505,14 @@ int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 
                 spin_lock(&sbi->fs_lock);
                 if (ino->flags & AUTOFS_INF_MOUNTPOINT) {
-                        sb->s_root->d_mounted++;
+                        spin_lock(&sb->s_root->d_lock);
+                        /*
+                         * If we haven't been expired away, then reset
+                         * mounted status.
+                         */
+                        if (mnt->mnt_parent != mnt)
+                                sb->s_root->d_flags |= DCACHE_MOUNTED;
+                        spin_unlock(&sb->s_root->d_lock);
                         ino->flags &= ~AUTOFS_INF_MOUNTPOINT;
                 }
                 ino->flags &= ~AUTOFS_INF_EXPIRING;
diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c
index ac87e49fa706..a7bdb9dcac84 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -309,7 +309,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
                 goto fail_iput;
         pipe = NULL;
 
-        root->d_op = &autofs4_sb_dentry_operations;
+        d_set_d_op(root, &autofs4_sb_dentry_operations);
         root->d_fsdata = ino;
 
         /* Can this call block? */
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index d5c1401f0031..651e4ef563b1 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -23,6 +23,8 @@
 
 #include "autofs_i.h"
 
+DEFINE_SPINLOCK(autofs4_lock);
+
 static int autofs4_dir_symlink(struct inode *,struct dentry *,const char *);
 static int autofs4_dir_unlink(struct inode *,struct dentry *);
 static int autofs4_dir_rmdir(struct inode *,struct dentry *);
@@ -142,12 +144,15 @@ static int autofs4_dir_open(struct inode *inode, struct file *file)
          * autofs file system so just let the libfs routines handle
          * it.
          */
-        spin_lock(&dcache_lock);
+        spin_lock(&autofs4_lock);
+        spin_lock(&dentry->d_lock);
         if (!d_mountpoint(dentry) && list_empty(&dentry->d_subdirs)) {
-                spin_unlock(&dcache_lock);
+                spin_unlock(&dentry->d_lock);
+                spin_unlock(&autofs4_lock);
                 return -ENOENT;
         }
-        spin_unlock(&dcache_lock);
+        spin_unlock(&dentry->d_lock);
+        spin_unlock(&autofs4_lock);
 
 out:
         return dcache_dir_open(inode, file);
@@ -252,9 +257,11 @@ static void *autofs4_follow_link(struct dentry *dentry, struct nameidata *nd)
         /* We trigger a mount for almost all flags */
         lookup_type = autofs4_need_mount(nd->flags);
         spin_lock(&sbi->fs_lock);
-        spin_lock(&dcache_lock);
+        spin_lock(&autofs4_lock);
+        spin_lock(&dentry->d_lock);
         if (!(lookup_type || ino->flags & AUTOFS_INF_PENDING)) {
-                spin_unlock(&dcache_lock);
+                spin_unlock(&dentry->d_lock);
+                spin_unlock(&autofs4_lock);
                 spin_unlock(&sbi->fs_lock);
                 goto follow;
         }
@@ -266,7 +273,8 @@ static void *autofs4_follow_link(struct dentry *dentry, struct nameidata *nd)
          */
         if (ino->flags & AUTOFS_INF_PENDING ||
             (!d_mountpoint(dentry) && list_empty(&dentry->d_subdirs))) {
-                spin_unlock(&dcache_lock);
+                spin_unlock(&dentry->d_lock);
+                spin_unlock(&autofs4_lock);
                 spin_unlock(&sbi->fs_lock);
 
                 status = try_to_fill_dentry(dentry, nd->flags);
@@ -275,7 +283,8 @@ static void *autofs4_follow_link(struct dentry *dentry, struct nameidata *nd)
 
                 goto follow;
         }
-        spin_unlock(&dcache_lock);
+        spin_unlock(&dentry->d_lock);
+        spin_unlock(&autofs4_lock);
         spin_unlock(&sbi->fs_lock);
 follow:
         /*
@@ -306,12 +315,19 @@ out_error:
  */
 static int autofs4_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
-        struct inode *dir = dentry->d_parent->d_inode;
-        struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb);
-        int oz_mode = autofs4_oz_mode(sbi);
+        struct inode *dir;
+        struct autofs_sb_info *sbi;
+        int oz_mode;
         int flags = nd ? nd->flags : 0;
         int status = 1;
 
+        if (flags & LOOKUP_RCU)
+                return -ECHILD;
+
+        dir = dentry->d_parent->d_inode;
+        sbi = autofs4_sbi(dir->i_sb);
+        oz_mode = autofs4_oz_mode(sbi);
+
         /* Pending dentry */
         spin_lock(&sbi->fs_lock);
         if (autofs4_ispending(dentry)) {
@@ -346,12 +362,14 @@ static int autofs4_revalidate(struct dentry *dentry, struct nameidata *nd)
                 return 0;
 
         /* Check for a non-mountpoint directory with no contents */
-        spin_lock(&dcache_lock);
+        spin_lock(&autofs4_lock);
+        spin_lock(&dentry->d_lock);
         if (S_ISDIR(dentry->d_inode->i_mode) &&
             !d_mountpoint(dentry) && list_empty(&dentry->d_subdirs)) {
                 DPRINTK("dentry=%p %.*s, emptydir",
                          dentry, dentry->d_name.len, dentry->d_name.name);
-                spin_unlock(&dcache_lock);
+                spin_unlock(&dentry->d_lock);
+                spin_unlock(&autofs4_lock);
 
                 /* The daemon never causes a mount to trigger */
                 if (oz_mode)
@@ -367,7 +385,8 @@ static int autofs4_revalidate(struct dentry *dentry, struct nameidata *nd)
 
                 return status;
         }
-        spin_unlock(&dcache_lock);
+        spin_unlock(&dentry->d_lock);
+        spin_unlock(&autofs4_lock);
 
         return 1;
 }
@@ -422,7 +441,7 @@ static struct dentry *autofs4_lookup_active(struct dentry *dentry)
         const unsigned char *str = name->name;
         struct list_head *p, *head;
 
-        spin_lock(&dcache_lock);
+        spin_lock(&autofs4_lock);
         spin_lock(&sbi->lookup_lock);
         head = &sbi->active_list;
         list_for_each(p, head) {
@@ -436,7 +455,7 @@ static struct dentry *autofs4_lookup_active(struct dentry *dentry)
                 spin_lock(&active->d_lock);
 
                 /* Already gone? */
-                if (atomic_read(&active->d_count) == 0)
+                if (active->d_count == 0)
                         goto next;
 
                 qstr = &active->d_name;
@@ -452,17 +471,17 @@ static struct dentry *autofs4_lookup_active(struct dentry *dentry)
                         goto next;
 
                 if (d_unhashed(active)) {
-                        dget(active);
+                        dget_dlock(active);
                         spin_unlock(&active->d_lock);
                         spin_unlock(&sbi->lookup_lock);
-                        spin_unlock(&dcache_lock);
+                        spin_unlock(&autofs4_lock);
                         return active;
                 }
 next:
                 spin_unlock(&active->d_lock);
         }
         spin_unlock(&sbi->lookup_lock);
-        spin_unlock(&dcache_lock);
+        spin_unlock(&autofs4_lock);
 
         return NULL;
 }
@@ -477,7 +496,7 @@ static struct dentry *autofs4_lookup_expiring(struct dentry *dentry)
         const unsigned char *str = name->name;
         struct list_head *p, *head;
 
-        spin_lock(&dcache_lock);
+        spin_lock(&autofs4_lock);
         spin_lock(&sbi->lookup_lock);
         head = &sbi->expiring_list;
         list_for_each(p, head) {
@@ -507,17 +526,17 @@ static struct dentry *autofs4_lookup_expiring(struct dentry *dentry)
                         goto next;
 
                 if (d_unhashed(expiring)) {
-                        dget(expiring);
+                        dget_dlock(expiring);
                         spin_unlock(&expiring->d_lock);
                         spin_unlock(&sbi->lookup_lock);
-                        spin_unlock(&dcache_lock);
+                        spin_unlock(&autofs4_lock);
                         return expiring;
                 }
 next:
                 spin_unlock(&expiring->d_lock);
         }
         spin_unlock(&sbi->lookup_lock);
-        spin_unlock(&dcache_lock);
+        spin_unlock(&autofs4_lock);
 
         return NULL;
 }
@@ -559,7 +578,7 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, s
                  * we check for the hashed dentry and return the newly
                  * hashed dentry.
                  */
-                dentry->d_op = &autofs4_root_dentry_operations;
+                d_set_d_op(dentry, &autofs4_root_dentry_operations);
 
                 /*
                  * And we need to ensure that the same dentry is used for
@@ -698,9 +717,9 @@ static int autofs4_dir_symlink(struct inode *dir,
         d_add(dentry, inode);
 
         if (dir == dir->i_sb->s_root->d_inode)
-                dentry->d_op = &autofs4_root_dentry_operations;
+                d_set_d_op(dentry, &autofs4_root_dentry_operations);
         else
-                dentry->d_op = &autofs4_dentry_operations;
+                d_set_d_op(dentry, &autofs4_dentry_operations);
 
         dentry->d_fsdata = ino;
         ino->dentry = dget(dentry);
@@ -753,12 +772,12 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry)
 
         dir->i_mtime = CURRENT_TIME;
 
-        spin_lock(&dcache_lock);
+        spin_lock(&autofs4_lock);
         autofs4_add_expiring(dentry);
         spin_lock(&dentry->d_lock);
         __d_drop(dentry);
         spin_unlock(&dentry->d_lock);
-        spin_unlock(&dcache_lock);
+        spin_unlock(&autofs4_lock);
 
         return 0;
 }
@@ -775,16 +794,20 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry)
         if (!autofs4_oz_mode(sbi))
                 return -EACCES;
 
-        spin_lock(&dcache_lock);
+        spin_lock(&autofs4_lock);
+        spin_lock(&sbi->lookup_lock);
+        spin_lock(&dentry->d_lock);
         if (!list_empty(&dentry->d_subdirs)) {
-                spin_unlock(&dcache_lock);
+                spin_unlock(&dentry->d_lock);
+                spin_unlock(&sbi->lookup_lock);
+                spin_unlock(&autofs4_lock);
                 return -ENOTEMPTY;
         }
-        autofs4_add_expiring(dentry);
-        spin_lock(&dentry->d_lock);
+        __autofs4_add_expiring(dentry);
+        spin_unlock(&sbi->lookup_lock);
         __d_drop(dentry);
         spin_unlock(&dentry->d_lock);
-        spin_unlock(&dcache_lock);
+        spin_unlock(&autofs4_lock);
 
         if (atomic_dec_and_test(&ino->count)) {
                 p_ino = autofs4_dentry_ino(dentry->d_parent);
@@ -829,9 +852,9 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, int mode)
         d_add(dentry, inode);
 
         if (dir == dir->i_sb->s_root->d_inode)
-                dentry->d_op = &autofs4_root_dentry_operations;
+                d_set_d_op(dentry, &autofs4_root_dentry_operations);
         else
-                dentry->d_op = &autofs4_dentry_operations;
+                d_set_d_op(dentry, &autofs4_dentry_operations);
 
         dentry->d_fsdata = ino;
         ino->dentry = dget(dentry);
@@ -980,19 +1003,11 @@ static int autofs4_root_ioctl_unlocked(struct inode *inode, struct file *filp,
         }
 }
 
-static DEFINE_MUTEX(autofs4_ioctl_mutex);
-
 static long autofs4_root_ioctl(struct file *filp,
                                unsigned int cmd, unsigned long arg)
 {
-        long ret;
         struct inode *inode = filp->f_dentry->d_inode;
-
-        mutex_lock(&autofs4_ioctl_mutex);
-        ret = autofs4_root_ioctl_unlocked(inode, filp, cmd, arg);
-        mutex_unlock(&autofs4_ioctl_mutex);
-
-        return ret;
+        return autofs4_root_ioctl_unlocked(inode, filp, cmd, arg);
 }
 
 #ifdef CONFIG_COMPAT
@@ -1002,13 +1017,11 @@ static long autofs4_root_compat_ioctl(struct file *filp,
         struct inode *inode = filp->f_path.dentry->d_inode;
         int ret;
 
-        mutex_lock(&autofs4_ioctl_mutex);
         if (cmd == AUTOFS_IOC_READY || cmd == AUTOFS_IOC_FAIL)
                 ret = autofs4_root_ioctl_unlocked(inode, filp, cmd, arg);
         else
                 ret = autofs4_root_ioctl_unlocked(inode, filp, cmd,
                         (unsigned long)compat_ptr(arg));
-        mutex_unlock(&autofs4_ioctl_mutex);
 
         return ret;
 }
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 2341375386f8..c5f8459c905e 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -186,16 +186,26 @@ static int autofs4_getpath(struct autofs_sb_info *sbi,
 {
         struct dentry *root = sbi->sb->s_root;
         struct dentry *tmp;
-        char *buf = *name;
+        char *buf;
         char *p;
-        int len = 0;
+        int len;
+        unsigned seq;
 
-        spin_lock(&dcache_lock);
+rename_retry:
+        buf = *name;
+        len = 0;
+
+        seq = read_seqbegin(&rename_lock);
+        rcu_read_lock();
+        spin_lock(&autofs4_lock);
         for (tmp = dentry ; tmp != root ; tmp = tmp->d_parent)
                 len += tmp->d_name.len + 1;
 
         if (!len || --len > NAME_MAX) {
-                spin_unlock(&dcache_lock);
+                spin_unlock(&autofs4_lock);
+                rcu_read_unlock();
+                if (read_seqretry(&rename_lock, seq))
+                        goto rename_retry;
                 return 0;
         }
 
@@ -208,7 +218,10 @@ static int autofs4_getpath(struct autofs_sb_info *sbi,
                 p -= tmp->d_name.len;
                 strncpy(p, tmp->d_name.name, tmp->d_name.len);
         }
-        spin_unlock(&dcache_lock);
+        spin_unlock(&autofs4_lock);
+        rcu_read_unlock();
+        if (read_seqretry(&rename_lock, seq))
+                goto rename_retry;
 
         return len;
 }
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index f024d8aaddef..9ad2369d9e35 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -229,8 +229,11 @@ static int bad_inode_readlink(struct dentry *dentry, char __user *buffer,
         return -EIO;
 }
 
-static int bad_inode_permission(struct inode *inode, int mask)
+static int bad_inode_permission(struct inode *inode, int mask, unsigned int flags)
 {
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
         return -EIO;
 }
 
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index aa4e7c7ae3c6..de93581b79a2 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -284,12 +284,18 @@ befs_alloc_inode(struct super_block *sb)
         return &bi->vfs_inode;
 }
 
-static void
-befs_destroy_inode(struct inode *inode)
+static void befs_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(befs_inode_cachep, BEFS_I(inode));
 }
 
+static void befs_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, befs_i_callback);
+}
+
 static void init_once(void *foo)
 {
         struct befs_inode_info *bi = (struct befs_inode_info *) foo;
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index 76db6d7d49bb..a8e37f81d097 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -248,11 +248,18 @@ static struct inode *bfs_alloc_inode(struct super_block *sb)
         return &bi->vfs_inode;
 }
 
-static void bfs_destroy_inode(struct inode *inode)
+static void bfs_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(bfs_inode_cachep, BFS_I(inode));
 }
 
+static void bfs_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, bfs_i_callback);
+}
+
 static void init_once(void *foo)
 {
         struct bfs_inode_info *bi = foo;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 4230252fd689..771f23527010 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -409,13 +409,20 @@ static struct inode *bdev_alloc_inode(struct super_block *sb)
         return &ei->vfs_inode;
 }
 
-static void bdev_destroy_inode(struct inode *inode)
+static void bdev_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
         struct bdev_inode *bdi = BDEV_I(inode);
 
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(bdev_cachep, bdi);
 }
 
+static void bdev_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, bdev_i_callback);
+}
+
 static void init_once(void *foo)
 {
         struct bdev_inode *ei = (struct bdev_inode *) foo;
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 2222d161c7b6..6ae2c8cac9d5 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -185,18 +185,23 @@ static int btrfs_xattr_acl_set(struct dentry *dentry, const char *name,
         return ret;
 }
 
-int btrfs_check_acl(struct inode *inode, int mask)
+int btrfs_check_acl(struct inode *inode, int mask, unsigned int flags)
 {
-        struct posix_acl *acl;
         int error = -EAGAIN;
 
-        acl = btrfs_get_acl(inode, ACL_TYPE_ACCESS);
+        if (flags & IPERM_FLAG_RCU) {
+                if (!negative_cached_acl(inode, ACL_TYPE_ACCESS))
+                        error = -ECHILD;
 
-        if (IS_ERR(acl))
-                return PTR_ERR(acl);
-        if (acl) {
-                error = posix_acl_permission(inode, acl, mask);
-                posix_acl_release(acl);
+        } else {
+                struct posix_acl *acl;
+                acl = btrfs_get_acl(inode, ACL_TYPE_ACCESS);
+                if (IS_ERR(acl))
+                        return PTR_ERR(acl);
+                if (acl) {
+                        error = posix_acl_permission(inode, acl, mask);
+                        posix_acl_release(acl);
+                }
         }
 
         return error;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index af52f6d7a4d8..a142d204b526 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2544,7 +2544,7 @@ int btrfs_sync_fs(struct super_block *sb, int wait);
 
 /* acl.c */
 #ifdef CONFIG_BTRFS_FS_POSIX_ACL
-int btrfs_check_acl(struct inode *inode, int mask);
+int btrfs_check_acl(struct inode *inode, int mask, unsigned int flags);
 #else
 #define btrfs_check_acl NULL
 #endif
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index c547cca26a26..51d2e4de34eb 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -696,6 +696,7 @@ static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
                                    __btree_submit_bio_done);
 }
 
+#ifdef CONFIG_MIGRATION
 static int btree_migratepage(struct address_space *mapping,
                         struct page *newpage, struct page *page)
 {
@@ -712,12 +713,9 @@ static int btree_migratepage(struct address_space *mapping,
         if (page_has_private(page) &&
             !try_to_release_page(page, GFP_KERNEL))
                 return -EAGAIN;
-#ifdef CONFIG_MIGRATION
         return migrate_page(mapping, newpage, page);
-#else
-        return -ENOSYS;
-#endif
 }
+#endif
 
 static int btree_writepage(struct page *page, struct writeback_control *wbc)
 {
@@ -1009,7 +1007,10 @@ static int find_and_setup_root(struct btrfs_root *tree_root,
         blocksize = btrfs_level_size(root, btrfs_root_level(&root->root_item));
         root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item),
                                      blocksize, generation);
-        BUG_ON(!root->node);
+        if (!root->node || !btrfs_buffer_uptodate(root->node, generation)) {
+                free_extent_buffer(root->node);
+                return -EIO;
+        }
         root->commit_root = btrfs_root_node(root);
         return 0;
 }
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index 6f0444473594..0ccf9a8afcdf 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -110,7 +110,7 @@ static struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid,
 
         dentry = d_obtain_alias(inode);
         if (!IS_ERR(dentry))
-                dentry->d_op = &btrfs_dentry_operations;
+                d_set_d_op(dentry, &btrfs_dentry_operations);
         return dentry;
 fail:
         srcu_read_unlock(&fs_info->subvol_srcu, index);
@@ -166,7 +166,7 @@ static struct dentry *btrfs_fh_to_dentry(struct super_block *sb, struct fid *fh,
 static struct dentry *btrfs_get_parent(struct dentry *child)
 {
         struct inode *dir = child->d_inode;
-        static struct dentry *dentry;
+        struct dentry *dentry;
         struct btrfs_root *root = BTRFS_I(dir)->root;
         struct btrfs_path *path;
         struct extent_buffer *leaf;
@@ -225,7 +225,7 @@ static struct dentry *btrfs_get_parent(struct dentry *child)
         key.offset = 0;
         dentry = d_obtain_alias(btrfs_iget(root->fs_info->sb, &key, root, NULL));
         if (!IS_ERR(dentry))
-                dentry->d_op = &btrfs_dentry_operations;
+                d_set_d_op(dentry, &btrfs_dentry_operations);
         return dentry;
 fail:
         btrfs_free_path(path);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index bcd59c7dfb57..227e5815d838 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -429,6 +429,7 @@ err:
 
 static int cache_block_group(struct btrfs_block_group_cache *cache,
                              struct btrfs_trans_handle *trans,
+                             struct btrfs_root *root,
                              int load_cache_only)
 {
         struct btrfs_fs_info *fs_info = cache->fs_info;
@@ -442,9 +443,12 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
 
         /*
          * We can't do the read from on-disk cache during a commit since we need
-         * to have the normal tree locking.
+         * to have the normal tree locking.  Also if we are currently trying to
+         * allocate blocks for the tree root we can't do the fast caching since
+         * we likely hold important locks.
          */
-        if (!trans->transaction->in_commit) {
+        if (!trans->transaction->in_commit &&
+            (root && root != root->fs_info->tree_root)) {
                 spin_lock(&cache->lock);
                 if (cache->cached != BTRFS_CACHE_NO) {
                         spin_unlock(&cache->lock);
@@ -2741,6 +2745,7 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group,
         struct btrfs_root *root = block_group->fs_info->tree_root;
         struct inode *inode = NULL;
         u64 alloc_hint = 0;
+        int dcs = BTRFS_DC_ERROR;
         int num_pages = 0;
         int retries = 0;
         int ret = 0;
@@ -2795,6 +2800,8 @@ again:
 
         spin_lock(&block_group->lock);
         if (block_group->cached != BTRFS_CACHE_FINISHED) {
+                /* We're not cached, don't bother trying to write stuff out */
+                dcs = BTRFS_DC_WRITTEN;
                 spin_unlock(&block_group->lock);
                 goto out_put;
         }
@@ -2821,6 +2828,8 @@ again:
         ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, num_pages,
                                               num_pages, num_pages,
                                               &alloc_hint);
+        if (!ret)
+                dcs = BTRFS_DC_SETUP;
         btrfs_free_reserved_data_space(inode, num_pages);
 out_put:
         iput(inode);
@@ -2828,10 +2837,7 @@ out_free:
         btrfs_release_path(root, path);
 out:
         spin_lock(&block_group->lock);
-        if (ret)
-                block_group->disk_cache_state = BTRFS_DC_ERROR;
-        else
-                block_group->disk_cache_state = BTRFS_DC_SETUP;
+        block_group->disk_cache_state = dcs;
         spin_unlock(&block_group->lock);
 
         return ret;
@@ -3037,7 +3043,13 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
 
 u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags)
 {
-        u64 num_devices = root->fs_info->fs_devices->rw_devices;
+        /*
+         * we add in the count of missing devices because we want
+         * to make sure that any RAID levels on a degraded FS
+         * continue to be honored.
+         */
+        u64 num_devices = root->fs_info->fs_devices->rw_devices +
+                root->fs_info->fs_devices->missing_devices;
 
         if (num_devices == 1)
                 flags &= ~(BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID0);
@@ -4080,7 +4092,7 @@ static int update_block_group(struct btrfs_trans_handle *trans,
                  * space back to the block group, otherwise we will leak space.
                  */
                 if (!alloc && cache->cached == BTRFS_CACHE_NO)
-                        cache_block_group(cache, trans, 1);
+                        cache_block_group(cache, trans, NULL, 1);
 
                 byte_in_group = bytenr - cache->key.objectid;
                 WARN_ON(byte_in_group > cache->key.offset);
@@ -4930,11 +4942,31 @@ search:
                 btrfs_get_block_group(block_group);
                 search_start = block_group->key.objectid;
 
+                /*
+                 * this can happen if we end up cycling through all the
+                 * raid types, but we want to make sure we only allocate
+                 * for the proper type.
+                 */
+                if (!block_group_bits(block_group, data)) {
+                    u64 extra = BTRFS_BLOCK_GROUP_DUP |
+                                BTRFS_BLOCK_GROUP_RAID1 |
+                                BTRFS_BLOCK_GROUP_RAID10;
+
+                        /*
+                         * if they asked for extra copies and this block group
+                         * doesn't provide them, bail.  This does allow us to
+                         * fill raid0 from raid1.
+                         */
+                        if ((data & extra) && !(block_group->flags & extra))
+                                goto loop;
+                }
+
 have_block_group:
                 if (unlikely(block_group->cached == BTRFS_CACHE_NO)) {
                         u64 free_percent;
 
-                        ret = cache_block_group(block_group, trans, 1);
+                        ret = cache_block_group(block_group, trans,
+                                                orig_root, 1);
                         if (block_group->cached == BTRFS_CACHE_FINISHED)
                                 goto have_block_group;
 
@@ -4958,7 +4990,8 @@ have_block_group:
                         if (loop > LOOP_CACHING_NOWAIT ||
                             (loop > LOOP_FIND_IDEAL &&
                              atomic_read(&space_info->caching_threads) < 2)) {
-                                ret = cache_block_group(block_group, trans, 0);
+                                ret = cache_block_group(block_group, trans,
+                                                        orig_root, 0);
                                 BUG_ON(ret);
                         }
                         found_uncached_bg = true;
@@ -5515,7 +5548,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
         u64 num_bytes = ins->offset;
 
         block_group = btrfs_lookup_block_group(root->fs_info, ins->objectid);
-        cache_block_group(block_group, trans, 0);
+        cache_block_group(block_group, trans, NULL, 0);
         caching_ctl = get_caching_control(block_group);
 
         if (!caching_ctl) {
@@ -6300,9 +6333,13 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
                                            NULL, NULL);
                 BUG_ON(ret < 0);
                 if (ret > 0) {
-                        ret = btrfs_del_orphan_item(trans, tree_root,
-                                                    root->root_key.objectid);
-                        BUG_ON(ret);
+                        /* if we fail to delete the orphan item this time
+                         * around, it'll get picked up the next time.
+                         *
+                         * The most common failure here is just -ENOENT.
+                         */
+                        btrfs_del_orphan_item(trans, tree_root,
+                                              root->root_key.objectid);
                 }
         }
 
@@ -7878,7 +7915,14 @@ static u64 update_block_group_flags(struct btrfs_root *root, u64 flags)
         u64 stripped = BTRFS_BLOCK_GROUP_RAID0 |
                 BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10;
 
-        num_devices = root->fs_info->fs_devices->rw_devices;
+        /*
+         * we add in the count of missing devices because we want
+         * to make sure that any RAID levels on a degraded FS
+         * continue to be honored.
+         */
+        num_devices = root->fs_info->fs_devices->rw_devices +
+                root->fs_info->fs_devices->missing_devices;
+
         if (num_devices == 1) {
                 stripped |= BTRFS_BLOCK_GROUP_DUP;
                 stripped = flags & ~stripped;
@@ -8247,7 +8291,6 @@ int btrfs_read_block_groups(struct btrfs_root *root)
                         break;
                 if (ret != 0)
                         goto error;
-
                 leaf = path->nodes[0];
                 btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
                 cache = kzalloc(sizeof(*cache), GFP_NOFS);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index c1faded5fca0..66836d85763b 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -48,30 +48,34 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages,
                                          struct page **prepared_pages,
                                          struct iov_iter *i)
 {
-        size_t copied;
+        size_t copied = 0;
         int pg = 0;
         int offset = pos & (PAGE_CACHE_SIZE - 1);
+        int total_copied = 0;
 
         while (write_bytes > 0) {
                 size_t count = min_t(size_t,
                                      PAGE_CACHE_SIZE - offset, write_bytes);
                 struct page *page = prepared_pages[pg];
-again:
-                if (unlikely(iov_iter_fault_in_readable(i, count)))
-                        return -EFAULT;
-
-                /* Copy data from userspace to the current page */
-                copied = iov_iter_copy_from_user(page, i, offset, count);
+                /*
+                 * Copy data from userspace to the current page
+                 *
+                 * Disable pagefault to avoid recursive lock since
+                 * the pages are already locked
+                 */
+                pagefault_disable();
+                copied = iov_iter_copy_from_user_atomic(page, i, offset, count);
+                pagefault_enable();
 
                 /* Flush processor's dcache for this page */
                 flush_dcache_page(page);
                 iov_iter_advance(i, copied);
                 write_bytes -= copied;
+                total_copied += copied;
 
+                /* Return to btrfs_file_aio_write to fault page */
                 if (unlikely(copied == 0)) {
-                        count = min_t(size_t, PAGE_CACHE_SIZE - offset,
-                                      iov_iter_single_seg_count(i));
-                        goto again;
+                        break;
                 }
 
                 if (unlikely(copied < PAGE_CACHE_SIZE - offset)) {
@@ -81,7 +85,7 @@ again:
                         offset = 0;
                 }
         }
-        return 0;
+        return total_copied;
 }
 
 /*
@@ -854,6 +858,8 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
         unsigned long last_index;
         int will_write;
         int buffered = 0;
+        int copied = 0;
+        int dirty_pages = 0;
 
         will_write = ((file->f_flags & O_DSYNC) || IS_SYNC(inode) ||
                       (file->f_flags & O_DIRECT));
@@ -970,7 +976,17 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
                 WARN_ON(num_pages > nrptrs);
                 memset(pages, 0, sizeof(struct page *) * nrptrs);
 
-                ret = btrfs_delalloc_reserve_space(inode, write_bytes);
+                /*
+                 * Fault pages before locking them in prepare_pages
+                 * to avoid recursive lock
+                 */
+                if (unlikely(iov_iter_fault_in_readable(&i, write_bytes))) {
+                        ret = -EFAULT;
+                        goto out;
+                }
+
+                ret = btrfs_delalloc_reserve_space(inode,
+                                        num_pages << PAGE_CACHE_SHIFT);
                 if (ret)
                         goto out;
 
@@ -978,37 +994,49 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
                                     pos, first_index, last_index,
                                     write_bytes);
                 if (ret) {
-                        btrfs_delalloc_release_space(inode, write_bytes);
+                        btrfs_delalloc_release_space(inode,
+                                        num_pages << PAGE_CACHE_SHIFT);
                         goto out;
                 }
 
-                ret = btrfs_copy_from_user(pos, num_pages,
+                copied = btrfs_copy_from_user(pos, num_pages,
                                            write_bytes, pages, &i);
-                if (ret == 0) {
+                dirty_pages = (copied + PAGE_CACHE_SIZE - 1) >>
+                                        PAGE_CACHE_SHIFT;
+
+                if (num_pages > dirty_pages) {
+                        if (copied > 0)
+                                atomic_inc(
+                                        &BTRFS_I(inode)->outstanding_extents);
+                        btrfs_delalloc_release_space(inode,
+                                        (num_pages - dirty_pages) <<
+                                        PAGE_CACHE_SHIFT);
+                }
+
+                if (copied > 0) {
                         dirty_and_release_pages(NULL, root, file, pages,
-                                                num_pages, pos, write_bytes);
+                                                dirty_pages, pos, copied);
                 }
 
                 btrfs_drop_pages(pages, num_pages);
-                if (ret) {
-                        btrfs_delalloc_release_space(inode, write_bytes);
-                        goto out;
-                }
 
-                if (will_write) {
-                        filemap_fdatawrite_range(inode->i_mapping, pos,
-                                                 pos + write_bytes - 1);
-                } else {
-                        balance_dirty_pages_ratelimited_nr(inode->i_mapping,
-                                                           num_pages);
-                        if (num_pages <
-                            (root->leafsize >> PAGE_CACHE_SHIFT) + 1)
-                                btrfs_btree_balance_dirty(root, 1);
-                        btrfs_throttle(root);
+                if (copied > 0) {
+                        if (will_write) {
+                                filemap_fdatawrite_range(inode->i_mapping, pos,
+                                                         pos + copied - 1);
+                        } else {
+                                balance_dirty_pages_ratelimited_nr(
+                                                        inode->i_mapping,
+                                                        dirty_pages);
+                                if (dirty_pages <
+                                (root->leafsize >> PAGE_CACHE_SHIFT) + 1)
+                                        btrfs_btree_balance_dirty(root, 1);
+                                btrfs_throttle(root);
+                        }
                 }
 
-                pos += write_bytes;
-                num_written += write_bytes;
+                pos += copied;
+                num_written += copied;
 
                 cond_resched();
         }
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 22ee0dc2e6b8..60d684266959 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -290,7 +290,7 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
                        (unsigned long long)BTRFS_I(inode)->generation,
                        (unsigned long long)generation,
                        (unsigned long long)block_group->key.objectid);
-                goto out;
+                goto free_cache;
         }
 
         if (!num_entries)
@@ -524,6 +524,12 @@ int btrfs_write_out_cache(struct btrfs_root *root,
                 return 0;
         }
 
+        node = rb_first(&block_group->free_space_offset);
+        if (!node) {
+                iput(inode);
+                return 0;
+        }
+
         last_index = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT;
         filemap_write_and_wait(inode->i_mapping);
         btrfs_wait_ordered_range(inode, inode->i_size &
@@ -543,10 +549,6 @@ int btrfs_write_out_cache(struct btrfs_root *root,
          */
         first_page_offset = (sizeof(u32) * num_checksums) + sizeof(u64);
 
-        node = rb_first(&block_group->free_space_offset);
-        if (!node)
-                goto out_free;
-
         /*
          * Lock all pages first so we can lock the extent safely.
          *
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 8039390bd6a6..a0ff46a47895 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -495,7 +495,7 @@ again:
                 add_async_extent(async_cow, start, num_bytes,
                                  total_compressed, pages, nr_pages_ret);
 
-                if (start + num_bytes < end && start + num_bytes < actual_end) {
+                if (start + num_bytes < end) {
                         start += num_bytes;
                         pages = NULL;
                         cond_resched();
@@ -4084,7 +4084,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
         int index;
         int ret;
 
-        dentry->d_op = &btrfs_dentry_operations;
+        d_set_d_op(dentry, &btrfs_dentry_operations);
 
         if (dentry->d_name.len > BTRFS_NAME_LEN)
                 return ERR_PTR(-ENAMETOOLONG);
@@ -4127,7 +4127,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
         return inode;
 }
 
-static int btrfs_dentry_delete(struct dentry *dentry)
+static int btrfs_dentry_delete(const struct dentry *dentry)
 {
         struct btrfs_root *root;
 
@@ -5712,9 +5712,9 @@ static void btrfs_end_dio_bio(struct bio *bio, int err)
 
         if (err) {
                 printk(KERN_ERR "btrfs direct IO failed ino %lu rw %lu "
-                      "disk_bytenr %lu len %u err no %d\n",
-                      dip->inode->i_ino, bio->bi_rw, bio->bi_sector,
-                      bio->bi_size, err);
+                      "sector %#Lx len %u err no %d\n",
+                      dip->inode->i_ino, bio->bi_rw,
+                      (unsigned long long)bio->bi_sector, bio->bi_size, err);
                 dip->errors = 1;
 
                 /*
@@ -5934,8 +5934,7 @@ free_ordered:
          */
         if (write) {
                 struct btrfs_ordered_extent *ordered;
-                ordered = btrfs_lookup_ordered_extent(inode,
-                                                      dip->logical_offset);
+                ordered = btrfs_lookup_ordered_extent(inode, file_offset);
                 if (!test_bit(BTRFS_ORDERED_PREALLOC, &ordered->flags) &&
                     !test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags))
                         btrfs_free_reserved_extent(root, ordered->start,
@@ -6496,6 +6495,13 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
         return inode;
 }
 
+static void btrfs_i_callback(struct rcu_head *head)
+{
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
+        kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode));
+}
+
 void btrfs_destroy_inode(struct inode *inode)
 {
         struct btrfs_ordered_extent *ordered;
@@ -6565,7 +6571,7 @@ void btrfs_destroy_inode(struct inode *inode)
         inode_tree_del(inode);
         btrfs_drop_extent_cache(inode, 0, (u64)-1, 0);
 free:
-        kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode));
+        call_rcu(&inode->i_rcu, btrfs_i_callback);
 }
 
 int btrfs_drop_inode(struct inode *inode)
@@ -7205,11 +7211,11 @@ static int btrfs_set_page_dirty(struct page *page)
         return __set_page_dirty_nobuffers(page);
 }
 
-static int btrfs_permission(struct inode *inode, int mask)
+static int btrfs_permission(struct inode *inode, int mask, unsigned int flags)
 {
         if ((BTRFS_I(inode)->flags & BTRFS_INODE_READONLY) && (mask & MAY_WRITE))
                 return -EACCES;
-        return generic_permission(inode, mask, btrfs_check_acl);
+        return generic_permission(inode, mask, flags, btrfs_check_acl);
 }
 
 static const struct inode_operations btrfs_dir_inode_operations = {
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index f1c9bb4079ed..f87552a1d7ea 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -947,23 +947,42 @@ out:
 
 static noinline int btrfs_ioctl_snap_create(struct file *file,
                                             void __user *arg, int subvol,
-                                            int async)
+                                            int v2)
 {
         struct btrfs_ioctl_vol_args *vol_args = NULL;
-        struct btrfs_ioctl_async_vol_args *async_vol_args = NULL;
+        struct btrfs_ioctl_vol_args_v2 *vol_args_v2 = NULL;
         char *name;
         u64 fd;
-        u64 transid = 0;
         int ret;
 
-        if (async) {
-                async_vol_args = memdup_user(arg, sizeof(*async_vol_args));
-                if (IS_ERR(async_vol_args))
-                        return PTR_ERR(async_vol_args);
+        if (v2) {
+                u64 transid = 0;
+                u64 *ptr = NULL;
 
-                name = async_vol_args->name;
-                fd = async_vol_args->fd;
-                async_vol_args->name[BTRFS_SNAPSHOT_NAME_MAX] = '\0';
+                vol_args_v2 = memdup_user(arg, sizeof(*vol_args_v2));
+                if (IS_ERR(vol_args_v2))
+                        return PTR_ERR(vol_args_v2);
+
+                if (vol_args_v2->flags & ~BTRFS_SUBVOL_CREATE_ASYNC) {
+                        ret = -EINVAL;
+                        goto out;
+                }
+
+                name = vol_args_v2->name;
+                fd = vol_args_v2->fd;
+                vol_args_v2->name[BTRFS_SUBVOL_NAME_MAX] = '\0';
+
+                if (vol_args_v2->flags & BTRFS_SUBVOL_CREATE_ASYNC)
+                        ptr = &transid;
+
+                ret = btrfs_ioctl_snap_create_transid(file, name, fd,
+                                                      subvol, ptr);
+
+                if (ret == 0 && ptr &&
+                    copy_to_user(arg +
+                                 offsetof(struct btrfs_ioctl_vol_args_v2,
+                                          transid), ptr, sizeof(*ptr)))
+                        ret = -EFAULT;
         } else {
                 vol_args = memdup_user(arg, sizeof(*vol_args));
                 if (IS_ERR(vol_args))
@@ -971,20 +990,13 @@ static noinline int btrfs_ioctl_snap_create(struct file *file,
                 name = vol_args->name;
                 fd = vol_args->fd;
                 vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
-        }
-
-        ret = btrfs_ioctl_snap_create_transid(file, name, fd,
-                                              subvol, &transid);
 
-        if (!ret && async) {
-                if (copy_to_user(arg +
-                                offsetof(struct btrfs_ioctl_async_vol_args,
-                                transid), &transid, sizeof(transid)))
-                        return -EFAULT;
+                ret = btrfs_ioctl_snap_create_transid(file, name, fd,
+                                                      subvol, NULL);
         }
-
+out:
         kfree(vol_args);
-        kfree(async_vol_args);
+        kfree(vol_args_v2);
 
         return ret;
 }
@@ -2246,7 +2258,7 @@ long btrfs_ioctl(struct file *file, unsigned int
                 return btrfs_ioctl_getversion(file, argp);
         case BTRFS_IOC_SNAP_CREATE:
                 return btrfs_ioctl_snap_create(file, argp, 0, 0);
-        case BTRFS_IOC_SNAP_CREATE_ASYNC:
+        case BTRFS_IOC_SNAP_CREATE_V2:
                 return btrfs_ioctl_snap_create(file, argp, 0, 1);
         case BTRFS_IOC_SUBVOL_CREATE:
                 return btrfs_ioctl_snap_create(file, argp, 1, 0);
diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h
index 17c99ebdf960..c344d12c646b 100644
--- a/fs/btrfs/ioctl.h
+++ b/fs/btrfs/ioctl.h
@@ -30,11 +30,15 @@ struct btrfs_ioctl_vol_args {
         char name[BTRFS_PATH_NAME_MAX + 1];
 };
 
-#define BTRFS_SNAPSHOT_NAME_MAX 4079
-struct btrfs_ioctl_async_vol_args {
+#define BTRFS_SUBVOL_CREATE_ASYNC       (1ULL << 0)
+
+#define BTRFS_SUBVOL_NAME_MAX 4039
+struct btrfs_ioctl_vol_args_v2 {
         __s64 fd;
         __u64 transid;
-        char name[BTRFS_SNAPSHOT_NAME_MAX + 1];
+        __u64 flags;
+        __u64 unused[4];
+        char name[BTRFS_SUBVOL_NAME_MAX + 1];
 };
 
 #define BTRFS_INO_LOOKUP_PATH_MAX 4080
@@ -187,6 +191,6 @@ struct btrfs_ioctl_space_args {
                                     struct btrfs_ioctl_space_args)
 #define BTRFS_IOC_START_SYNC _IOR(BTRFS_IOCTL_MAGIC, 24, __u64)
 #define BTRFS_IOC_WAIT_SYNC  _IOW(BTRFS_IOCTL_MAGIC, 22, __u64)
-#define BTRFS_IOC_SNAP_CREATE_ASYNC _IOW(BTRFS_IOCTL_MAGIC, 23, \
-                                   struct btrfs_ioctl_async_vol_args)
+#define BTRFS_IOC_SNAP_CREATE_V2 _IOW(BTRFS_IOCTL_MAGIC, 23, \
+                                   struct btrfs_ioctl_vol_args_v2)
 #endif
diff --git a/fs/btrfs/orphan.c b/fs/btrfs/orphan.c
index 79cba5fbc28e..f8be250963a0 100644
--- a/fs/btrfs/orphan.c
+++ b/fs/btrfs/orphan.c
@@ -56,8 +56,12 @@ int btrfs_del_orphan_item(struct btrfs_trans_handle *trans,
                 return -ENOMEM;
 
         ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
-        if (ret)
+        if (ret < 0)
                 goto out;
+        if (ret) {
+                ret = -ENOENT;
+                goto out;
+        }
 
         ret = btrfs_del_item(trans, root, path);
 
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index dbb51ea7a13c..883c6fa1367e 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -685,9 +685,9 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
                 mutex_unlock(&root->d_inode->i_mutex);
 
                 if (IS_ERR(new_root)) {
+                        dput(root);
                         deactivate_locked_super(s);
                         error = PTR_ERR(new_root);
-                        dput(root);
                         goto error_free_subvol_name;
                 }
                 if (!new_root->d_inode) {
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index cc04dc1445d6..6b9884507837 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -412,12 +412,16 @@ static noinline int device_list_add(const char *path,
 
                 device->fs_devices = fs_devices;
                 fs_devices->num_devices++;
-        } else if (strcmp(device->name, path)) {
+        } else if (!device->name || strcmp(device->name, path)) {
                 name = kstrdup(path, GFP_NOFS);
                 if (!name)
                         return -ENOMEM;
                 kfree(device->name);
                 device->name = name;
+                if (device->missing) {
+                        fs_devices->missing_devices--;
+                        device->missing = 0;
+                }
         }
 
         if (found_transid > fs_devices->latest_trans) {
@@ -1236,6 +1240,9 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 
         device->fs_devices->num_devices--;
 
+        if (device->missing)
+                root->fs_info->fs_devices->missing_devices--;
+
         next_device = list_entry(root->fs_info->fs_devices->devices.next,
                                  struct btrfs_device, dev_list);
         if (device->bdev == root->fs_info->sb->s_bdev)
@@ -3080,7 +3087,9 @@ static struct btrfs_device *add_missing_dev(struct btrfs_root *root,
         device->devid = devid;
         device->work.func = pending_bios_fn;
         device->fs_devices = fs_devices;
+        device->missing = 1;
         fs_devices->num_devices++;
+        fs_devices->missing_devices++;
         spin_lock_init(&device->io_lock);
         INIT_LIST_HEAD(&device->dev_alloc_list);
         memcpy(device->uuid, dev_uuid, BTRFS_UUID_SIZE);
@@ -3278,6 +3287,15 @@ static int read_one_dev(struct btrfs_root *root,
                         device = add_missing_dev(root, devid, dev_uuid);
                         if (!device)
                                 return -ENOMEM;
+                } else if (!device->missing) {
+                        /*
+                         * this happens when a device that was properly setup
+                         * in the device info lists suddenly goes bad.
+                         * device->bdev is NULL, and so we have to set
+                         * device->missing to one here
+                         */
+                        root->fs_info->fs_devices->missing_devices++;
+                        device->missing = 1;
                 }
         }
 
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 2b638b6e4eea..2740db49eb04 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -44,6 +44,7 @@ struct btrfs_device {
 
         int writeable;
         int in_fs_metadata;
+        int missing;
 
         spinlock_t io_lock;
 
@@ -93,6 +94,7 @@ struct btrfs_fs_devices {
         u64 num_devices;
         u64 open_devices;
         u64 rw_devices;
+        u64 missing_devices;
         u64 total_rw_bytes;
         struct block_device *latest_bdev;
 
diff --git a/fs/buffer.c b/fs/buffer.c
index 5930e382959b..2219a76e2caf 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1270,12 +1270,10 @@ static inline void check_irqs_on(void)
 static void bh_lru_install(struct buffer_head *bh)
 {
         struct buffer_head *evictee = NULL;
-        struct bh_lru *lru;
 
         check_irqs_on();
         bh_lru_lock();
-        lru = &__get_cpu_var(bh_lrus);
-        if (lru->bhs[0] != bh) {
+        if (__this_cpu_read(bh_lrus.bhs[0]) != bh) {
                 struct buffer_head *bhs[BH_LRU_SIZE];
                 int in;
                 int out = 0;
@@ -1283,7 +1281,8 @@ static void bh_lru_install(struct buffer_head *bh)
                 get_bh(bh);
                 bhs[out++] = bh;
                 for (in = 0; in < BH_LRU_SIZE; in++) {
-                        struct buffer_head *bh2 = lru->bhs[in];
+                        struct buffer_head *bh2 =
+                                __this_cpu_read(bh_lrus.bhs[in]);
 
                         if (bh2 == bh) {
                                 __brelse(bh2);
@@ -1298,7 +1297,7 @@ static void bh_lru_install(struct buffer_head *bh)
                 }
                 while (out < BH_LRU_SIZE)
                         bhs[out++] = NULL;
-                memcpy(lru->bhs, bhs, sizeof(bhs));
+                memcpy(__this_cpu_ptr(&bh_lrus.bhs), bhs, sizeof(bhs));
         }
         bh_lru_unlock();
 
@@ -1313,23 +1312,22 @@ static struct buffer_head *
 lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size)
 {
         struct buffer_head *ret = NULL;
-        struct bh_lru *lru;
         unsigned int i;
 
         check_irqs_on();
         bh_lru_lock();
-        lru = &__get_cpu_var(bh_lrus);
         for (i = 0; i < BH_LRU_SIZE; i++) {
-                struct buffer_head *bh = lru->bhs[i];
+                struct buffer_head *bh = __this_cpu_read(bh_lrus.bhs[i]);
 
                 if (bh && bh->b_bdev == bdev &&
                                 bh->b_blocknr == block && bh->b_size == size) {
                         if (i) {
                                 while (i) {
-                                        lru->bhs[i] = lru->bhs[i - 1];
+                                        __this_cpu_write(bh_lrus.bhs[i],
+                                                __this_cpu_read(bh_lrus.bhs[i - 1]));
                                         i--;
                                 }
-                                lru->bhs[0] = bh;
+                                __this_cpu_write(bh_lrus.bhs[0], bh);
                         }
                         get_bh(bh);
                         ret = bh;
@@ -3203,22 +3201,23 @@ static void recalc_bh_state(void)
         int i;
         int tot = 0;
 
-        if (__get_cpu_var(bh_accounting).ratelimit++ < 4096)
+        if (__this_cpu_inc_return(bh_accounting.ratelimit) - 1 < 4096)
                 return;
-        __get_cpu_var(bh_accounting).ratelimit = 0;
+        __this_cpu_write(bh_accounting.ratelimit, 0);
         for_each_online_cpu(i)
                 tot += per_cpu(bh_accounting, i).nr;
         buffer_heads_over_limit = (tot > max_buffer_heads);
 }
-        
+
 struct buffer_head *alloc_buffer_head(gfp_t gfp_flags)
 {
         struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags);
         if (ret) {
                 INIT_LIST_HEAD(&ret->b_assoc_buffers);
-                get_cpu_var(bh_accounting).nr++;
+                preempt_disable();
+                __this_cpu_inc(bh_accounting.nr);
                 recalc_bh_state();
-                put_cpu_var(bh_accounting);
+                preempt_enable();
         }
         return ret;
 }
@@ -3228,9 +3227,10 @@ void free_buffer_head(struct buffer_head *bh)
 {
         BUG_ON(!list_empty(&bh->b_assoc_buffers));
         kmem_cache_free(bh_cachep, bh);
-        get_cpu_var(bh_accounting).nr--;
+        preempt_disable();
+        __this_cpu_dec(bh_accounting.nr);
         recalc_bh_state();
-        put_cpu_var(bh_accounting);
+        preempt_enable();
 }
 EXPORT_SYMBOL(free_buffer_head);
 
@@ -3243,9 +3243,8 @@ static void buffer_exit_cpu(int cpu)
                 brelse(b->bhs[i]);
                 b->bhs[i] = NULL;
         }
-        get_cpu_var(bh_accounting).nr += per_cpu(bh_accounting, cpu).nr;
+        this_cpu_add(bh_accounting.nr, per_cpu(bh_accounting, cpu).nr);
         per_cpu(bh_accounting, cpu).nr = 0;
-        put_cpu_var(bh_accounting);
 }
 
 static int buffer_cpu_notify(struct notifier_block *self,
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 7d447af84ec4..fa7ca04ee816 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -40,12 +40,13 @@ int ceph_init_dentry(struct dentry *dentry)
         if (dentry->d_fsdata)
                 return 0;
 
-        if (ceph_snap(dentry->d_parent->d_inode) == CEPH_NOSNAP)
-                dentry->d_op = &ceph_dentry_ops;
+        if (dentry->d_parent == NULL ||   /* nfs fh_to_dentry */
+            ceph_snap(dentry->d_parent->d_inode) == CEPH_NOSNAP)
+                d_set_d_op(dentry, &ceph_dentry_ops);
         else if (ceph_snap(dentry->d_parent->d_inode) == CEPH_SNAPDIR)
-                dentry->d_op = &ceph_snapdir_dentry_ops;
+                d_set_d_op(dentry, &ceph_snapdir_dentry_ops);
         else
-                dentry->d_op = &ceph_snap_dentry_ops;
+                d_set_d_op(dentry, &ceph_snap_dentry_ops);
 
         di = kmem_cache_alloc(ceph_dentry_cachep, GFP_NOFS | __GFP_ZERO);
         if (!di)
@@ -111,11 +112,11 @@ static int __dcache_readdir(struct file *filp,
         dout("__dcache_readdir %p at %llu (last %p)\n", dir, filp->f_pos,
              last);
 
-        spin_lock(&dcache_lock);
+        spin_lock(&parent->d_lock);
 
         /* start at beginning? */
-        if (filp->f_pos == 2 || (last &&
-                                 filp->f_pos < ceph_dentry(last)->offset)) {
+        if (filp->f_pos == 2 || last == NULL ||
+            filp->f_pos < ceph_dentry(last)->offset) {
                 if (list_empty(&parent->d_subdirs))
                         goto out_unlock;
                 p = parent->d_subdirs.prev;
@@ -135,6 +136,7 @@ more:
                         fi->at_end = 1;
                         goto out_unlock;
                 }
+                spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
                 if (!d_unhashed(dentry) && dentry->d_inode &&
                     ceph_snap(dentry->d_inode) != CEPH_SNAPDIR &&
                     ceph_ino(dentry->d_inode) != CEPH_INO_CEPH &&
@@ -144,13 +146,15 @@ more:
                      dentry->d_name.len, dentry->d_name.name, di->offset,
                      filp->f_pos, d_unhashed(dentry) ? " unhashed" : "",
                      !dentry->d_inode ? " null" : "");
+                spin_unlock(&dentry->d_lock);
                 p = p->prev;
                 dentry = list_entry(p, struct dentry, d_u.d_child);
                 di = ceph_dentry(dentry);
         }
 
-        atomic_inc(&dentry->d_count);
-        spin_unlock(&dcache_lock);
+        dget_dlock(dentry);
+        spin_unlock(&dentry->d_lock);
+        spin_unlock(&parent->d_lock);
 
         dout(" %llu (%llu) dentry %p %.*s %p\n", di->offset, filp->f_pos,
              dentry, dentry->d_name.len, dentry->d_name.name, dentry->d_inode);
@@ -176,19 +180,19 @@ more:
 
         filp->f_pos++;
 
-        /* make sure a dentry wasn't dropped while we didn't have dcache_lock */
+        /* make sure a dentry wasn't dropped while we didn't have parent lock */
         if (!ceph_i_test(dir, CEPH_I_COMPLETE)) {
                 dout(" lost I_COMPLETE on %p; falling back to mds\n", dir);
                 err = -EAGAIN;
                 goto out;
         }
 
-        spin_lock(&dcache_lock);
+        spin_lock(&parent->d_lock);
         p = p->prev;    /* advance to next dentry */
         goto more;
 
 out_unlock:
-        spin_unlock(&dcache_lock);
+        spin_unlock(&parent->d_lock);
 out:
         if (last)
                 dput(last);
@@ -986,7 +990,12 @@ static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry)
  */
 static int ceph_d_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
-        struct inode *dir = dentry->d_parent->d_inode;
+        struct inode *dir;
+
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
+
+        dir = dentry->d_parent->d_inode;
 
         dout("d_revalidate %p '%.*s' inode %p offset %lld\n", dentry,
              dentry->d_name.len, dentry->d_name.name, dentry->d_inode,
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 8d79b8912e31..7d0e4a82d898 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -282,7 +282,8 @@ int ceph_release(struct inode *inode, struct file *file)
 static int striped_read(struct inode *inode,
                         u64 off, u64 len,
                         struct page **pages, int num_pages,
-                        int *checkeof, bool align_to_pages)
+                        int *checkeof, bool align_to_pages,
+                        unsigned long buf_align)
 {
         struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
         struct ceph_inode_info *ci = ceph_inode(inode);
@@ -307,7 +308,7 @@ static int striped_read(struct inode *inode,
 
 more:
         if (align_to_pages)
-                page_align = (pos - io_align) & ~PAGE_MASK;
+                page_align = (pos - io_align + buf_align) & ~PAGE_MASK;
         else
                 page_align = pos & ~PAGE_MASK;
         this_len = left;
@@ -376,16 +377,18 @@ static ssize_t ceph_sync_read(struct file *file, char __user *data,
         struct inode *inode = file->f_dentry->d_inode;
         struct page **pages;
         u64 off = *poff;
-        int num_pages = calc_pages_for(off, len);
-        int ret;
+        int num_pages, ret;
 
         dout("sync_read on file %p %llu~%u %s\n", file, off, len,
              (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
 
-        if (file->f_flags & O_DIRECT)
-                pages = ceph_get_direct_page_vector(data, num_pages);
-        else
+        if (file->f_flags & O_DIRECT) {
+                num_pages = calc_pages_for((unsigned long)data, len);
+                pages = ceph_get_direct_page_vector(data, num_pages, true);
+        } else {
+                num_pages = calc_pages_for(off, len);
                 pages = ceph_alloc_page_vector(num_pages, GFP_NOFS);
+        }
         if (IS_ERR(pages))
                 return PTR_ERR(pages);
 
@@ -400,7 +403,8 @@ static ssize_t ceph_sync_read(struct file *file, char __user *data,
                 goto done;
 
         ret = striped_read(inode, off, len, pages, num_pages, checkeof,
-                           file->f_flags & O_DIRECT);
+                           file->f_flags & O_DIRECT,
+                           (unsigned long)data & ~PAGE_MASK);
 
         if (ret >= 0 && (file->f_flags & O_DIRECT) == 0)
                 ret = ceph_copy_page_vector_to_user(pages, data, off, ret);
@@ -409,7 +413,7 @@ static ssize_t ceph_sync_read(struct file *file, char __user *data,
 
 done:
         if (file->f_flags & O_DIRECT)
-                ceph_put_page_vector(pages, num_pages);
+                ceph_put_page_vector(pages, num_pages, true);
         else
                 ceph_release_page_vector(pages, num_pages);
         dout("sync_read result %d\n", ret);
@@ -456,6 +460,7 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data,
         int do_sync = 0;
         int check_caps = 0;
         int page_align, io_align;
+        unsigned long buf_align;
         int ret;
         struct timespec mtime = CURRENT_TIME;
 
@@ -471,6 +476,7 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data,
                 pos = *offset;
 
         io_align = pos & ~PAGE_MASK;
+        buf_align = (unsigned long)data & ~PAGE_MASK;
 
         ret = filemap_write_and_wait_range(inode->i_mapping, pos, pos + left);
         if (ret < 0)
@@ -496,12 +502,15 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data,
          */
 more:
         len = left;
-        if (file->f_flags & O_DIRECT)
+        if (file->f_flags & O_DIRECT) {
                 /* write from beginning of first page, regardless of
                    io alignment */
-                page_align = (pos - io_align) & ~PAGE_MASK;
-        else
+                page_align = (pos - io_align + buf_align) & ~PAGE_MASK;
+                num_pages = calc_pages_for((unsigned long)data, len);
+        } else {
                 page_align = pos & ~PAGE_MASK;
+                num_pages = calc_pages_for(pos, len);
+        }
         req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
                                     ceph_vino(inode), pos, &len,
                                     CEPH_OSD_OP_WRITE, flags,
@@ -512,10 +521,8 @@ more:
         if (!req)
                 return -ENOMEM;
 
-        num_pages = calc_pages_for(pos, len);
-
         if (file->f_flags & O_DIRECT) {
-                pages = ceph_get_direct_page_vector(data, num_pages);
+                pages = ceph_get_direct_page_vector(data, num_pages, false);
                 if (IS_ERR(pages)) {
                         ret = PTR_ERR(pages);
                         goto out;
@@ -565,7 +572,7 @@ more:
         }
 
         if (file->f_flags & O_DIRECT)
-                ceph_put_page_vector(pages, num_pages);
+                ceph_put_page_vector(pages, num_pages, false);
         else if (file->f_flags & O_SYNC)
                 ceph_release_page_vector(pages, num_pages);
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index bf1286588f26..e61de4f7b99d 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -368,6 +368,15 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
         return &ci->vfs_inode;
 }
 
+static void ceph_i_callback(struct rcu_head *head)
+{
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        struct ceph_inode_info *ci = ceph_inode(inode);
+
+        INIT_LIST_HEAD(&inode->i_dentry);
+        kmem_cache_free(ceph_inode_cachep, ci);
+}
+
 void ceph_destroy_inode(struct inode *inode)
 {
         struct ceph_inode_info *ci = ceph_inode(inode);
@@ -407,7 +416,7 @@ void ceph_destroy_inode(struct inode *inode)
         if (ci->i_xattrs.prealloc_blob)
                 ceph_buffer_put(ci->i_xattrs.prealloc_blob);
 
-        kmem_cache_free(ceph_inode_cachep, ci);
+        call_rcu(&inode->i_rcu, ceph_i_callback);
 }
 
 
@@ -841,13 +850,13 @@ static void ceph_set_dentry_offset(struct dentry *dn)
         di->offset = ceph_inode(inode)->i_max_offset++;
         spin_unlock(&inode->i_lock);
 
-        spin_lock(&dcache_lock);
-        spin_lock(&dn->d_lock);
+        spin_lock(&dir->d_lock);
+        spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED);
         list_move(&dn->d_u.d_child, &dir->d_subdirs);
         dout("set_dentry_offset %p %lld (%p %p)\n", dn, di->offset,
              dn->d_u.d_child.prev, dn->d_u.d_child.next);
         spin_unlock(&dn->d_lock);
-        spin_unlock(&dcache_lock);
+        spin_unlock(&dir->d_lock);
 }
 
 /*
@@ -879,8 +888,8 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
         } else if (realdn) {
                 dout("dn %p (%d) spliced with %p (%d) "
                      "inode %p ino %llx.%llx\n",
-                     dn, atomic_read(&dn->d_count),
-                     realdn, atomic_read(&realdn->d_count),
+                     dn, dn->d_count,
+                     realdn, realdn->d_count,
                      realdn->d_inode, ceph_vinop(realdn->d_inode));
                 dput(dn);
                 dn = realdn;
@@ -1231,11 +1240,11 @@ retry_lookup:
                         goto retry_lookup;
                 } else {
                         /* reorder parent's d_subdirs */
-                        spin_lock(&dcache_lock);
-                        spin_lock(&dn->d_lock);
+                        spin_lock(&parent->d_lock);
+                        spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED);
                         list_move(&dn->d_u.d_child, &parent->d_subdirs);
                         spin_unlock(&dn->d_lock);
-                        spin_unlock(&dcache_lock);
+                        spin_unlock(&parent->d_lock);
                 }
 
                 di = dn->d_fsdata;
@@ -1772,12 +1781,17 @@ int ceph_do_getattr(struct inode *inode, int mask)
  * Check inode permissions.  We verify we have a valid value for
  * the AUTH cap, then call the generic handler.
  */
-int ceph_permission(struct inode *inode, int mask)
+int ceph_permission(struct inode *inode, int mask, unsigned int flags)
 {
-        int err = ceph_do_getattr(inode, CEPH_CAP_AUTH_SHARED);
+        int err;
+
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
+        err = ceph_do_getattr(inode, CEPH_CAP_AUTH_SHARED);
 
         if (!err)
-                err = generic_permission(inode, mask, NULL);
+                err = generic_permission(inode, mask, flags, NULL);
         return err;
 }
 
diff --git a/fs/ceph/ioctl.h b/fs/ceph/ioctl.h
index a6ce54e94eb5..52e8fd74d450 100644
--- a/fs/ceph/ioctl.h
+++ b/fs/ceph/ioctl.h
@@ -4,7 +4,7 @@
 #include <linux/ioctl.h>
 #include <linux/types.h>
 
-#define CEPH_IOCTL_MAGIC 0x98
+#define CEPH_IOCTL_MAGIC 0x97
 
 /* just use u64 to align sanely on all archs */
 struct ceph_ioctl_layout {
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index 40abde93c345..476b329867d4 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -11,40 +11,68 @@
  * Implement fcntl and flock locking functions.
  */
 static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
-                             u64 pid, u64 pid_ns,
-                             int cmd, u64 start, u64 length, u8 wait)
+                             int cmd, u8 wait, struct file_lock *fl)
 {
         struct inode *inode = file->f_dentry->d_inode;
         struct ceph_mds_client *mdsc =
                 ceph_sb_to_client(inode->i_sb)->mdsc;
         struct ceph_mds_request *req;
         int err;
+        u64 length = 0;
 
         req = ceph_mdsc_create_request(mdsc, operation, USE_AUTH_MDS);
         if (IS_ERR(req))
                 return PTR_ERR(req);
         req->r_inode = igrab(inode);
 
+        /* mds requires start and length rather than start and end */
+        if (LLONG_MAX == fl->fl_end)
+                length = 0;
+        else
+                length = fl->fl_end - fl->fl_start + 1;
+
         dout("ceph_lock_message: rule: %d, op: %d, pid: %llu, start: %llu, "
              "length: %llu, wait: %d, type`: %d", (int)lock_type,
-             (int)operation, pid, start, length, wait, cmd);
+             (int)operation, (u64)fl->fl_pid, fl->fl_start,
+             length, wait, fl->fl_type);
+
 
         req->r_args.filelock_change.rule = lock_type;
         req->r_args.filelock_change.type = cmd;
-        req->r_args.filelock_change.pid = cpu_to_le64(pid);
+        req->r_args.filelock_change.pid = cpu_to_le64((u64)fl->fl_pid);
         /* This should be adjusted, but I'm not sure if
            namespaces actually get id numbers*/
         req->r_args.filelock_change.pid_namespace =
-                cpu_to_le64((u64)pid_ns);
-        req->r_args.filelock_change.start = cpu_to_le64(start);
+                cpu_to_le64((u64)(unsigned long)fl->fl_nspid);
+        req->r_args.filelock_change.start = cpu_to_le64(fl->fl_start);
         req->r_args.filelock_change.length = cpu_to_le64(length);
         req->r_args.filelock_change.wait = wait;
 
         err = ceph_mdsc_do_request(mdsc, inode, req);
+
+        if ( operation == CEPH_MDS_OP_GETFILELOCK){
+                fl->fl_pid = le64_to_cpu(req->r_reply_info.filelock_reply->pid);
+                if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type)
+                        fl->fl_type = F_RDLCK;
+                else if (CEPH_LOCK_EXCL == req->r_reply_info.filelock_reply->type)
+                        fl->fl_type = F_WRLCK;
+                else
+                        fl->fl_type = F_UNLCK;
+
+                fl->fl_start = le64_to_cpu(req->r_reply_info.filelock_reply->start);
+                length = le64_to_cpu(req->r_reply_info.filelock_reply->start) +
+                                                 le64_to_cpu(req->r_reply_info.filelock_reply->length);
+                if (length >= 1)
+                        fl->fl_end = length -1;
+                else
+                        fl->fl_end = 0;
+
+        }
         ceph_mdsc_put_request(req);
         dout("ceph_lock_message: rule: %d, op: %d, pid: %llu, start: %llu, "
-             "length: %llu, wait: %d, type`: %d err code %d", (int)lock_type,
-             (int)operation, pid, start, length, wait, cmd, err);
+             "length: %llu, wait: %d, type`: %d, err code %d", (int)lock_type,
+             (int)operation, (u64)fl->fl_pid, fl->fl_start,
+             length, wait, fl->fl_type, err);
         return err;
 }
 
@@ -54,7 +82,6 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
  */
 int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
 {
-        u64 length;
         u8 lock_cmd;
         int err;
         u8 wait = 0;
@@ -76,29 +103,20 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
         else
                 lock_cmd = CEPH_LOCK_UNLOCK;
 
-        if (LLONG_MAX == fl->fl_end)
-                length = 0;
-        else
-                length = fl->fl_end - fl->fl_start + 1;
-
-        err = ceph_lock_message(CEPH_LOCK_FCNTL, op, file,
-                                (u64)fl->fl_pid,
-                                (u64)(unsigned long)fl->fl_nspid,
-                                lock_cmd, fl->fl_start,
-                                length, wait);
+        err = ceph_lock_message(CEPH_LOCK_FCNTL, op, file, lock_cmd, wait, fl);
         if (!err) {
-                dout("mds locked, locking locally");
-                err = posix_lock_file(file, fl, NULL);
-                if (err && (CEPH_MDS_OP_SETFILELOCK == op)) {
-                        /* undo! This should only happen if the kernel detects
-                         * local deadlock. */
-                        ceph_lock_message(CEPH_LOCK_FCNTL, op, file,
-                                          (u64)fl->fl_pid,
-                                          (u64)(unsigned long)fl->fl_nspid,
-                                          CEPH_LOCK_UNLOCK, fl->fl_start,
-                                          length, 0);
-                        dout("got %d on posix_lock_file, undid lock", err);
+                if ( op != CEPH_MDS_OP_GETFILELOCK ){
+                        dout("mds locked, locking locally");
+                        err = posix_lock_file(file, fl, NULL);
+                        if (err && (CEPH_MDS_OP_SETFILELOCK == op)) {
+                                /* undo! This should only happen if the kernel detects
+                                 * local deadlock. */
+                                ceph_lock_message(CEPH_LOCK_FCNTL, op, file,
+                                                  CEPH_LOCK_UNLOCK, 0, fl);
+                                dout("got %d on posix_lock_file, undid lock", err);
+                        }
                 }
+
         } else {
                 dout("mds returned error code %d", err);
         }
@@ -107,7 +125,6 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
 
 int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 {
-        u64 length;
         u8 lock_cmd;
         int err;
         u8 wait = 1;
@@ -127,26 +144,15 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
                 lock_cmd = CEPH_LOCK_EXCL;
         else
                 lock_cmd = CEPH_LOCK_UNLOCK;
-        /* mds requires start and length rather than start and end */
-        if (LLONG_MAX == fl->fl_end)
-                length = 0;
-        else
-                length = fl->fl_end - fl->fl_start + 1;
 
         err = ceph_lock_message(CEPH_LOCK_FLOCK, CEPH_MDS_OP_SETFILELOCK,
-                                file, (u64)fl->fl_pid,
-                                (u64)(unsigned long)fl->fl_nspid,
-                                lock_cmd, fl->fl_start,
-                                length, wait);
+                                file, lock_cmd, wait, fl);
         if (!err) {
                 err = flock_lock_file_wait(file, fl);
                 if (err) {
                         ceph_lock_message(CEPH_LOCK_FLOCK,
                                           CEPH_MDS_OP_SETFILELOCK,
-                                          file, (u64)fl->fl_pid,
-                                          (u64)(unsigned long)fl->fl_nspid,
-                                          CEPH_LOCK_UNLOCK, fl->fl_start,
-                                          length, 0);
+                                          file, CEPH_LOCK_UNLOCK, 0, fl);
                         dout("got %d on flock_lock_file_wait, undid lock", err);
                 }
         } else {
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 098b18508479..a50fca1e03be 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -202,6 +202,38 @@ out_bad:
 }
 
 /*
+ * parse fcntl F_GETLK results
+ */
+static int parse_reply_info_filelock(void **p, void *end,
+                struct ceph_mds_reply_info_parsed *info)
+{
+        if (*p + sizeof(*info->filelock_reply) > end)
+                goto bad;
+
+        info->filelock_reply = *p;
+        *p += sizeof(*info->filelock_reply);
+
+        if (unlikely(*p != end))
+                goto bad;
+        return 0;
+
+bad:
+        return -EIO;
+}
+
+/*
+ * parse extra results
+ */
+static int parse_reply_info_extra(void **p, void *end,
+                struct ceph_mds_reply_info_parsed *info)
+{
+        if (info->head->op == CEPH_MDS_OP_GETFILELOCK)
+                return parse_reply_info_filelock(p, end, info);
+        else
+                return parse_reply_info_dir(p, end, info);
+}
+
+/*
  * parse entire mds reply
  */
 static int parse_reply_info(struct ceph_msg *msg,
@@ -223,10 +255,10 @@ static int parse_reply_info(struct ceph_msg *msg,
                         goto out_bad;
         }
 
-        /* dir content */
+        /* extra */
         ceph_decode_32_safe(&p, end, len, bad);
         if (len > 0) {
-                err = parse_reply_info_dir(&p, p+len, info);
+                err = parse_reply_info_extra(&p, p+len, info);
                 if (err < 0)
                         goto out_bad;
         }
@@ -1454,7 +1486,7 @@ retry:
         *base = ceph_ino(temp->d_inode);
         *plen = len;
         dout("build_path on %p %d built %llx '%.*s'\n",
-             dentry, atomic_read(&dentry->d_count), *base, len, path);
+             dentry, dentry->d_count, *base, len, path);
         return path;
 }
 
@@ -2074,7 +2106,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 
         mutex_lock(&session->s_mutex);
         if (err < 0) {
-                pr_err("mdsc_handle_reply got corrupt reply mds%d\n", mds);
+                pr_err("mdsc_handle_reply got corrupt reply mds%d(tid:%lld)\n", mds, tid);
                 ceph_msg_dump(msg);
                 goto out_err;
         }
@@ -2094,7 +2126,8 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
         mutex_lock(&req->r_fill_mutex);
         err = ceph_fill_trace(mdsc->fsc->sb, req, req->r_session);
         if (err == 0) {
-                if (result == 0 && rinfo->dir_nr)
+                if (result == 0 && req->r_op != CEPH_MDS_OP_GETFILELOCK &&
+                    rinfo->dir_nr)
                         ceph_readdir_prepopulate(req, req->r_session);
                 ceph_unreserve_caps(mdsc, &req->r_caps_reservation);
         }
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 9341fd4f1432..aabe563b54db 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -42,26 +42,37 @@ struct ceph_mds_reply_info_in {
 };
 
 /*
- * parsed info about an mds reply, including information about the
- * target inode and/or its parent directory and dentry, and directory
- * contents (for readdir results).
+ * parsed info about an mds reply, including information about
+ * either: 1) the target inode and/or its parent directory and dentry,
+ * and directory contents (for readdir results), or
+ * 2) the file range lock info (for fcntl F_GETLK results).
  */
 struct ceph_mds_reply_info_parsed {
         struct ceph_mds_reply_head    *head;
 
+        /* trace */
         struct ceph_mds_reply_info_in diri, targeti;
         struct ceph_mds_reply_dirfrag *dirfrag;
         char                          *dname;
         u32                           dname_len;
         struct ceph_mds_reply_lease   *dlease;
 
-        struct ceph_mds_reply_dirfrag *dir_dir;
-        int                           dir_nr;
-        char                          **dir_dname;
-        u32                           *dir_dname_len;
-        struct ceph_mds_reply_lease   **dir_dlease;
-        struct ceph_mds_reply_info_in *dir_in;
-        u8                            dir_complete, dir_end;
+        /* extra */
+        union {
+                /* for fcntl F_GETLK results */
+                struct ceph_filelock *filelock_reply;
+
+                /* for readdir results */
+                struct {
+                        struct ceph_mds_reply_dirfrag *dir_dir;
+                        int                           dir_nr;
+                        char                          **dir_dname;
+                        u32                           *dir_dname_len;
+                        struct ceph_mds_reply_lease   **dir_dlease;
+                        struct ceph_mds_reply_info_in *dir_in;
+                        u8                            dir_complete, dir_end;
+                };
+        };
 
         /* encoded blob describing snapshot contexts for certain
            operations (e.g., open) */
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 7f01728a4657..4553d8829edb 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -665,7 +665,7 @@ extern void ceph_queue_invalidate(struct inode *inode);
 extern void ceph_queue_writeback(struct inode *inode);
 
 extern int ceph_do_getattr(struct inode *inode, int mask);
-extern int ceph_permission(struct inode *inode, int mask);
+extern int ceph_permission(struct inode *inode, int mask, unsigned int flags);
 extern int ceph_setattr(struct dentry *dentry, struct iattr *attr);
 extern int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
                         struct kstat *stat);
diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile
index adefa60a9bdc..43b19dd39191 100644
--- a/fs/cifs/Makefile
+++ b/fs/cifs/Makefile
@@ -6,7 +6,9 @@ obj-$(CONFIG_CIFS) += cifs.o
 cifs-y := cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o inode.o \
           link.o misc.o netmisc.o smbdes.o smbencrypt.o transport.o asn1.o \
           md4.o md5.o cifs_unicode.o nterr.o xattr.o cifsencrypt.o \
-          readdir.o ioctl.o sess.o export.o cifsacl.o
+          readdir.o ioctl.o sess.o export.o
+
+cifs-$(CONFIG_CIFS_ACL) += cifsacl.o
 
 cifs-$(CONFIG_CIFS_UPCALL) += cifs_spnego.o
 
diff --git a/fs/cifs/README b/fs/cifs/README
index ee68d1036544..46af99ab3614 100644
--- a/fs/cifs/README
+++ b/fs/cifs/README
@@ -337,6 +337,15 @@ A partial list of the supported mount options follows:
   wsize         default write size (default 57344)
                 maximum wsize currently allowed by CIFS is 57344 (fourteen
                 4096 byte pages)
+  actimeo=n     attribute cache timeout in seconds (default 1 second).
+                After this timeout, the cifs client requests fresh attribute
+                information from the server. This option allows to tune the
+                attribute cache timeout to suit the workload needs. Shorter
+                timeouts mean better the cache coherency, but increased number
+                of calls to the server. Longer timeouts mean reduced number
+                of calls to the server at the expense of less stricter cache
+                coherency checks (i.e. incorrect attribute cache for a short
+                period of time).
   rw            mount the network share read-write (note that the
                 server may still consider the share read-only)
   ro            mount network share read-only
diff --git a/fs/cifs/cache.c b/fs/cifs/cache.c
index 224d7bbd1fcc..e654dfd092c3 100644
--- a/fs/cifs/cache.c
+++ b/fs/cifs/cache.c
@@ -64,7 +64,9 @@ static uint16_t cifs_server_get_key(const void *cookie_netfs_data,
                                    void *buffer, uint16_t maxbuf)
 {
         const struct TCP_Server_Info *server = cookie_netfs_data;
-        const struct sockaddr *sa = (struct sockaddr *) &server->addr.sockAddr;
+        const struct sockaddr *sa = (struct sockaddr *) &server->dstaddr;
+        const struct sockaddr_in *addr = (struct sockaddr_in *) sa;
+        const struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *) sa;
         struct cifs_server_key *key = buffer;
         uint16_t key_len = sizeof(struct cifs_server_key);
 
@@ -76,16 +78,16 @@ static uint16_t cifs_server_get_key(const void *cookie_netfs_data,
          */
         switch (sa->sa_family) {
         case AF_INET:
-                key->family = server->addr.sockAddr.sin_family;
-                key->port = server->addr.sockAddr.sin_port;
-                key->addr[0].ipv4_addr = server->addr.sockAddr.sin_addr;
+                key->family = sa->sa_family;
+                key->port = addr->sin_port;
+                key->addr[0].ipv4_addr = addr->sin_addr;
                 key_len += sizeof(key->addr[0].ipv4_addr);
                 break;
 
         case AF_INET6:
-                key->family = server->addr.sockAddr6.sin6_family;
-                key->port = server->addr.sockAddr6.sin6_port;
-                key->addr[0].ipv6_addr = server->addr.sockAddr6.sin6_addr;
+                key->family = sa->sa_family;
+                key->port = addr6->sin6_port;
+                key->addr[0].ipv6_addr = addr6->sin6_addr;
                 key_len += sizeof(key->addr[0].ipv6_addr);
                 break;
 
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 103ab8b605b0..ede98300a8cd 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -119,29 +119,27 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
                     "Display Internal CIFS Data Structures for Debugging\n"
                     "---------------------------------------------------\n");
         seq_printf(m, "CIFS Version %s\n", CIFS_VERSION);
-        seq_printf(m, "Features: ");
+        seq_printf(m, "Features:");
 #ifdef CONFIG_CIFS_DFS_UPCALL
-        seq_printf(m, "dfs");
-        seq_putc(m, ' ');
+        seq_printf(m, " dfs");
 #endif
 #ifdef CONFIG_CIFS_FSCACHE
-        seq_printf(m, "fscache");
-        seq_putc(m, ' ');
+        seq_printf(m, " fscache");
 #endif
 #ifdef CONFIG_CIFS_WEAK_PW_HASH
-        seq_printf(m, "lanman");
-        seq_putc(m, ' ');
+        seq_printf(m, " lanman");
 #endif
 #ifdef CONFIG_CIFS_POSIX
-        seq_printf(m, "posix");
-        seq_putc(m, ' ');
+        seq_printf(m, " posix");
 #endif
 #ifdef CONFIG_CIFS_UPCALL
-        seq_printf(m, "spnego");
-        seq_putc(m, ' ');
+        seq_printf(m, " spnego");
 #endif
 #ifdef CONFIG_CIFS_XATTR
-        seq_printf(m, "xattr");
+        seq_printf(m, " xattr");
+#endif
+#ifdef CONFIG_CIFS_ACL
+        seq_printf(m, " acl");
 #endif
         seq_putc(m, '\n');
         seq_printf(m, "Active VFS Requests: %d\n", GlobalTotalActiveXid);
diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h
index e9a393c9c2ca..7852cd677051 100644
--- a/fs/cifs/cifs_fs_sb.h
+++ b/fs/cifs/cifs_fs_sb.h
@@ -48,6 +48,7 @@ struct cifs_sb_info {
         struct nls_table *local_nls;
         unsigned int rsize;
         unsigned int wsize;
+        unsigned long actimeo; /* attribute cache timeout (jiffies) */
         atomic_t active;
         uid_t   mnt_uid;
         gid_t   mnt_gid;
diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c
index 87044906cd1f..4dfba8283165 100644
--- a/fs/cifs/cifs_spnego.c
+++ b/fs/cifs/cifs_spnego.c
@@ -98,6 +98,8 @@ struct key *
 cifs_get_spnego_key(struct cifsSesInfo *sesInfo)
 {
         struct TCP_Server_Info *server = sesInfo->server;
+        struct sockaddr_in *sa = (struct sockaddr_in *) &server->dstaddr;
+        struct sockaddr_in6 *sa6 = (struct sockaddr_in6 *) &server->dstaddr;
         char *description, *dp;
         size_t desc_len;
         struct key *spnego_key;
@@ -127,10 +129,10 @@ cifs_get_spnego_key(struct cifsSesInfo *sesInfo)
         dp = description + strlen(description);
 
         /* add the server address */
-        if (server->addr.sockAddr.sin_family == AF_INET)
-                sprintf(dp, "ip4=%pI4", &server->addr.sockAddr.sin_addr);
-        else if (server->addr.sockAddr.sin_family == AF_INET6)
-                sprintf(dp, "ip6=%pI6", &server->addr.sockAddr6.sin6_addr);
+        if (server->dstaddr.ss_family == AF_INET)
+                sprintf(dp, "ip4=%pI4", &sa->sin_addr);
+        else if (server->dstaddr.ss_family == AF_INET6)
+                sprintf(dp, "ip6=%pI6", &sa6->sin6_addr);
         else
                 goto out;
 
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index c6ebea088ac7..a437ec391a01 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -30,8 +30,6 @@
 #include "cifs_debug.h"
 
 
-#ifdef CONFIG_CIFS_EXPERIMENTAL
-
 static struct cifs_wksid wksidarr[NUM_WK_SIDS] = {
         {{1, 0, {0, 0, 0, 0, 0, 0}, {0, 0, 0, 0, 0} }, "null user"},
         {{1, 1, {0, 0, 0, 0, 0, 1}, {0, 0, 0, 0, 0} }, "nobody"},
@@ -774,4 +772,3 @@ int mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode)
 
         return rc;
 }
-#endif /* CONFIG_CIFS_EXPERIMENTAL */
diff --git a/fs/cifs/cifsacl.h b/fs/cifs/cifsacl.h
index 6c8096cf5155..c4ae7d036563 100644
--- a/fs/cifs/cifsacl.h
+++ b/fs/cifs/cifsacl.h
@@ -74,11 +74,7 @@ struct cifs_wksid {
         char sidname[SIDNAMELENGTH];
 } __attribute__((packed));
 
-#ifdef CONFIG_CIFS_EXPERIMENTAL
-
 extern int match_sid(struct cifs_sid *);
 extern int compare_sids(const struct cifs_sid *, const struct cifs_sid *);
 
-#endif /*  CONFIG_CIFS_EXPERIMENTAL */
-
 #endif /* _CIFSACL_H */
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index f856732161ab..66f3d50d0676 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -72,6 +72,7 @@ static int cifs_calculate_signature(const struct smb_hdr *cifs_pdu,
         return 0;
 }
 
+/* must be called with server->srv_mutex held */
 int cifs_sign_smb(struct smb_hdr *cifs_pdu, struct TCP_Server_Info *server,
                   __u32 *pexpected_response_sequence_number)
 {
@@ -84,14 +85,12 @@ int cifs_sign_smb(struct smb_hdr *cifs_pdu, struct TCP_Server_Info *server,
         if ((cifs_pdu->Flags2 & SMBFLG2_SECURITY_SIGNATURE) == 0)
                 return rc;
 
-        spin_lock(&GlobalMid_Lock);
         cifs_pdu->Signature.Sequence.SequenceNumber =
                         cpu_to_le32(server->sequence_number);
         cifs_pdu->Signature.Sequence.Reserved = 0;
 
         *pexpected_response_sequence_number = server->sequence_number++;
         server->sequence_number++;
-        spin_unlock(&GlobalMid_Lock);
 
         rc = cifs_calculate_signature(cifs_pdu, server, smb_signature);
         if (rc)
@@ -149,6 +148,7 @@ static int cifs_calc_signature2(const struct kvec *iov, int n_vec,
         return rc;
 }
 
+/* must be called with server->srv_mutex held */
 int cifs_sign_smb2(struct kvec *iov, int n_vec, struct TCP_Server_Info *server,
                    __u32 *pexpected_response_sequence_number)
 {
@@ -162,14 +162,12 @@ int cifs_sign_smb2(struct kvec *iov, int n_vec, struct TCP_Server_Info *server,
         if ((cifs_pdu->Flags2 & SMBFLG2_SECURITY_SIGNATURE) == 0)
                 return rc;
 
-        spin_lock(&GlobalMid_Lock);
         cifs_pdu->Signature.Sequence.SequenceNumber =
                                 cpu_to_le32(server->sequence_number);
         cifs_pdu->Signature.Sequence.Reserved = 0;
 
         *pexpected_response_sequence_number = server->sequence_number++;
         server->sequence_number++;
-        spin_unlock(&GlobalMid_Lock);
 
         rc = cifs_calc_signature2(iov, n_vec, server, smb_signature);
         if (rc)
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 76c8a906a63e..5e7075d5f139 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -283,10 +283,13 @@ cifs_statfs(struct dentry *dentry, struct kstatfs *buf)
         return 0;
 }
 
-static int cifs_permission(struct inode *inode, int mask)
+static int cifs_permission(struct inode *inode, int mask, unsigned int flags)
 {
         struct cifs_sb_info *cifs_sb;
 
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
         cifs_sb = CIFS_SB(inode->i_sb);
 
         if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) {
@@ -298,7 +301,7 @@ static int cifs_permission(struct inode *inode, int mask)
                 on the client (above and beyond ACL on servers) for
                 servers which do not support setting and viewing mode bits,
                 so allowing client to check permissions is useful */
-                return generic_permission(inode, mask, NULL);
+                return generic_permission(inode, mask, flags, NULL);
 }
 
 static struct kmem_cache *cifs_inode_cachep;
@@ -326,6 +329,8 @@ cifs_alloc_inode(struct super_block *sb)
         cifs_inode->invalid_mapping = false;
         cifs_inode->vfs_inode.i_blkbits = 14;  /* 2**14 = CIFS_MAX_MSGSIZE */
         cifs_inode->server_eof = 0;
+        cifs_inode->uniqueid = 0;
+        cifs_inode->createtime = 0;
 
         /* Can not set i_flags here - they get immediately overwritten
            to zero by the VFS */
@@ -334,10 +339,17 @@ cifs_alloc_inode(struct super_block *sb)
         return &cifs_inode->vfs_inode;
 }
 
+static void cifs_i_callback(struct rcu_head *head)
+{
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
+        kmem_cache_free(cifs_inode_cachep, CIFS_I(inode));
+}
+
 static void
 cifs_destroy_inode(struct inode *inode)
 {
-        kmem_cache_free(cifs_inode_cachep, CIFS_I(inode));
+        call_rcu(&inode->i_rcu, cifs_i_callback);
 }
 
 static void
@@ -351,18 +363,19 @@ cifs_evict_inode(struct inode *inode)
 static void
 cifs_show_address(struct seq_file *s, struct TCP_Server_Info *server)
 {
+        struct sockaddr_in *sa = (struct sockaddr_in *) &server->dstaddr;
+        struct sockaddr_in6 *sa6 = (struct sockaddr_in6 *) &server->dstaddr;
+
         seq_printf(s, ",addr=");
 
-        switch (server->addr.sockAddr.sin_family) {
+        switch (server->dstaddr.ss_family) {
         case AF_INET:
-                seq_printf(s, "%pI4", &server->addr.sockAddr.sin_addr.s_addr);
+                seq_printf(s, "%pI4", &sa->sin_addr.s_addr);
                 break;
         case AF_INET6:
-                seq_printf(s, "%pI6",
-                           &server->addr.sockAddr6.sin6_addr.s6_addr);
-                if (server->addr.sockAddr6.sin6_scope_id)
-                        seq_printf(s, "%%%u",
-                                   server->addr.sockAddr6.sin6_scope_id);
+                seq_printf(s, "%pI6", &sa6->sin6_addr.s6_addr);
+                if (sa6->sin6_scope_id)
+                        seq_printf(s, "%%%u", sa6->sin6_scope_id);
                 break;
         default:
                 seq_printf(s, "(unknown)");
@@ -463,6 +476,8 @@ cifs_show_options(struct seq_file *s, struct vfsmount *m)
 
         seq_printf(s, ",rsize=%d", cifs_sb->rsize);
         seq_printf(s, ",wsize=%d", cifs_sb->wsize);
+        /* convert actimeo and display it in seconds */
+                seq_printf(s, ",actimeo=%lu", cifs_sb->actimeo / HZ);
 
         return 0;
 }
@@ -935,7 +950,6 @@ init_cifs(void)
         GlobalCurrentXid = 0;
         GlobalTotalActiveXid = 0;
         GlobalMaxActiveXid = 0;
-        memset(Local_System_Name, 0, 15);
         spin_lock_init(&cifs_tcp_ses_lock);
         spin_lock_init(&cifs_file_list_lock);
         spin_lock_init(&GlobalMid_Lock);
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index b577bf0a1bb3..606ca8bb7102 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -45,6 +45,16 @@
 #define CIFS_MIN_RCV_POOL 4
 
 /*
+ * default attribute cache timeout (jiffies)
+ */
+#define CIFS_DEF_ACTIMEO (1 * HZ)
+
+/*
+ * max attribute cache timeout (jiffies) - 2^30
+ */
+#define CIFS_MAX_ACTIMEO (1 << 30)
+
+/*
  * MAX_REQ is the maximum number of requests that WE will send
  * on one socket concurrently. It also matches the most common
  * value of max multiplex returned by servers.  We may
@@ -153,10 +163,7 @@ struct TCP_Server_Info {
         char server_RFC1001_name[RFC1001_NAME_LEN_WITH_NULL];
         char *hostname; /* hostname portion of UNC string */
         struct socket *ssocket;
-        union {
-                struct sockaddr_in sockAddr;
-                struct sockaddr_in6 sockAddr6;
-        } addr;
+        struct sockaddr_storage dstaddr;
         struct sockaddr_storage srcaddr; /* locally bind to this IP */
         wait_queue_head_t response_q;
         wait_queue_head_t request_q; /* if more than maxmpx to srvr must block*/
@@ -200,7 +207,7 @@ struct TCP_Server_Info {
         char cryptkey[CIFS_CRYPTO_KEY_SIZE]; /* used by ntlm, ntlmv2 etc */
         /* 16th byte of RFC1001 workstation name is always null */
         char workstation_RFC1001_name[RFC1001_NAME_LEN_WITH_NULL];
-        __u32 sequence_number; /* needed for CIFS PDU signature */
+        __u32 sequence_number; /* for signing, protected by srv_mutex */
         struct session_key session_key;
         unsigned long lstrp; /* when we got last response from this server */
         u16 dialect; /* dialect index that server chose */
@@ -446,6 +453,7 @@ struct cifsInodeInfo {
         bool invalid_mapping:1;         /* pagecache is invalid */
         u64  server_eof;                /* current file size on server */
         u64  uniqueid;                  /* server inode number */
+        u64  createtime;                /* creation time on server */
 #ifdef CONFIG_CIFS_FSCACHE
         struct fscache_cookie *fscache;
 #endif
@@ -566,6 +574,7 @@ struct cifs_fattr {
         u64             cf_uniqueid;
         u64             cf_eof;
         u64             cf_bytes;
+        u64             cf_createtime;
         uid_t           cf_uid;
         gid_t           cf_gid;
         umode_t         cf_mode;
@@ -746,8 +755,6 @@ GLOBAL_EXTERN unsigned int GlobalTotalActiveXid; /* prot by GlobalMid_Sem */
 GLOBAL_EXTERN unsigned int GlobalMaxActiveXid;  /* prot by GlobalMid_Sem */
 GLOBAL_EXTERN spinlock_t GlobalMid_Lock;  /* protects above & list operations */
                                           /* on midQ entries */
-GLOBAL_EXTERN char Local_System_Name[15];
-
 /*
  *  Global counters, updated atomically
  */
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index db961dc4fd3d..e6d1481b16c1 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -54,7 +54,8 @@ do {								\
              __func__, curr_xid, (int)rc);                      \
 } while (0)
 extern char *build_path_from_dentry(struct dentry *);
-extern char *cifs_build_path_to_root(struct cifs_sb_info *cifs_sb);
+extern char *cifs_build_path_to_root(struct cifs_sb_info *cifs_sb,
+                                        struct cifsTconInfo *tcon);
 extern char *build_wildcard_path_from_dentry(struct dentry *direntry);
 extern char *cifs_compose_mount_options(const char *sb_mountdata,
                 const char *fullpath, const struct dfs_info3_param *ref,
@@ -79,9 +80,7 @@ extern bool is_valid_oplock_break(struct smb_hdr *smb,
                                   struct TCP_Server_Info *);
 extern bool is_size_safe_to_change(struct cifsInodeInfo *, __u64 eof);
 extern struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *, bool);
-#ifdef CONFIG_CIFS_EXPERIMENTAL
 extern struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *, bool);
-#endif
 extern unsigned int smbCalcSize(struct smb_hdr *ptr);
 extern unsigned int smbCalcSize_LE(struct smb_hdr *ptr);
 extern int decode_negTokenInit(unsigned char *security_blob, int length,
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 2f2632b6df5a..2f6795e524d3 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -401,15 +401,12 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses)
         else if ((secFlags & CIFSSEC_AUTH_MASK) == CIFSSEC_MAY_KRB5) {
                 cFYI(1, "Kerberos only mechanism, enable extended security");
                 pSMB->hdr.Flags2 |= SMBFLG2_EXT_SEC;
-        }
-#ifdef CONFIG_CIFS_EXPERIMENTAL
-        else if ((secFlags & CIFSSEC_MUST_NTLMSSP) == CIFSSEC_MUST_NTLMSSP)
+        } else if ((secFlags & CIFSSEC_MUST_NTLMSSP) == CIFSSEC_MUST_NTLMSSP)
                 pSMB->hdr.Flags2 |= SMBFLG2_EXT_SEC;
         else if ((secFlags & CIFSSEC_AUTH_MASK) == CIFSSEC_MAY_NTLMSSP) {
                 cFYI(1, "NTLMSSP only mechanism, enable extended security");
                 pSMB->hdr.Flags2 |= SMBFLG2_EXT_SEC;
         }
-#endif
 
         count = 0;
         for (i = 0; i < CIFS_NUM_PROT; i++) {
@@ -2478,95 +2475,6 @@ querySymLinkRetry:
 }
 
 #ifdef CONFIG_CIFS_EXPERIMENTAL
-/* Initialize NT TRANSACT SMB into small smb request buffer.
-   This assumes that all NT TRANSACTS that we init here have
-   total parm and data under about 400 bytes (to fit in small cifs
-   buffer size), which is the case so far, it easily fits. NB:
-        Setup words themselves and ByteCount
-        MaxSetupCount (size of returned setup area) and
-        MaxParameterCount (returned parms size) must be set by caller */
-static int
-smb_init_nttransact(const __u16 sub_command, const int setup_count,
-                   const int parm_len, struct cifsTconInfo *tcon,
-                   void **ret_buf)
-{
-        int rc;
-        __u32 temp_offset;
-        struct smb_com_ntransact_req *pSMB;
-
-        rc = small_smb_init(SMB_COM_NT_TRANSACT, 19 + setup_count, tcon,
-                                (void **)&pSMB);
-        if (rc)
-                return rc;
-        *ret_buf = (void *)pSMB;
-        pSMB->Reserved = 0;
-        pSMB->TotalParameterCount = cpu_to_le32(parm_len);
-        pSMB->TotalDataCount  = 0;
-        pSMB->MaxDataCount = cpu_to_le32((tcon->ses->server->maxBuf -
-                                          MAX_CIFS_HDR_SIZE) & 0xFFFFFF00);
-        pSMB->ParameterCount = pSMB->TotalParameterCount;
-        pSMB->DataCount  = pSMB->TotalDataCount;
-        temp_offset = offsetof(struct smb_com_ntransact_req, Parms) +
-                        (setup_count * 2) - 4 /* for rfc1001 length itself */;
-        pSMB->ParameterOffset = cpu_to_le32(temp_offset);
-        pSMB->DataOffset = cpu_to_le32(temp_offset + parm_len);
-        pSMB->SetupCount = setup_count; /* no need to le convert byte fields */
-        pSMB->SubCommand = cpu_to_le16(sub_command);
-        return 0;
-}
-
-static int
-validate_ntransact(char *buf, char **ppparm, char **ppdata,
-                   __u32 *pparmlen, __u32 *pdatalen)
-{
-        char *end_of_smb;
-        __u32 data_count, data_offset, parm_count, parm_offset;
-        struct smb_com_ntransact_rsp *pSMBr;
-
-        *pdatalen = 0;
-        *pparmlen = 0;
-
-        if (buf == NULL)
-                return -EINVAL;
-
-        pSMBr = (struct smb_com_ntransact_rsp *)buf;
-
-        /* ByteCount was converted from little endian in SendReceive */
-        end_of_smb = 2 /* sizeof byte count */ + pSMBr->ByteCount +
-                        (char *)&pSMBr->ByteCount;
-
-        data_offset = le32_to_cpu(pSMBr->DataOffset);
-        data_count = le32_to_cpu(pSMBr->DataCount);
-        parm_offset = le32_to_cpu(pSMBr->ParameterOffset);
-        parm_count = le32_to_cpu(pSMBr->ParameterCount);
-
-        *ppparm = (char *)&pSMBr->hdr.Protocol + parm_offset;
-        *ppdata = (char *)&pSMBr->hdr.Protocol + data_offset;
-
-        /* should we also check that parm and data areas do not overlap? */
-        if (*ppparm > end_of_smb) {
-                cFYI(1, "parms start after end of smb");
-                return -EINVAL;
-        } else if (parm_count + *ppparm > end_of_smb) {
-                cFYI(1, "parm end after end of smb");
-                return -EINVAL;
-        } else if (*ppdata > end_of_smb) {
-                cFYI(1, "data starts after end of smb");
-                return -EINVAL;
-        } else if (data_count + *ppdata > end_of_smb) {
-                cFYI(1, "data %p + count %d (%p) past smb end %p start %p",
-                        *ppdata, data_count, (data_count + *ppdata),
-                        end_of_smb, pSMBr);
-                return -EINVAL;
-        } else if (parm_count + data_count > pSMBr->ByteCount) {
-                cFYI(1, "parm count and data count larger than SMB");
-                return -EINVAL;
-        }
-        *pdatalen = data_count;
-        *pparmlen = parm_count;
-        return 0;
-}
-
 int
 CIFSSMBQueryReparseLinkInfo(const int xid, struct cifsTconInfo *tcon,
                         const unsigned char *searchName,
@@ -3056,7 +2964,97 @@ GetExtAttrOut:
 
 #endif /* CONFIG_POSIX */
 
-#ifdef CONFIG_CIFS_EXPERIMENTAL
+#ifdef CONFIG_CIFS_ACL
+/*
+ * Initialize NT TRANSACT SMB into small smb request buffer.  This assumes that
+ * all NT TRANSACTS that we init here have total parm and data under about 400
+ * bytes (to fit in small cifs buffer size), which is the case so far, it
+ * easily fits. NB: Setup words themselves and ByteCount MaxSetupCount (size of
+ * returned setup area) and MaxParameterCount (returned parms size) must be set
+ * by caller
+ */
+static int
+smb_init_nttransact(const __u16 sub_command, const int setup_count,
+                   const int parm_len, struct cifsTconInfo *tcon,
+                   void **ret_buf)
+{
+        int rc;
+        __u32 temp_offset;
+        struct smb_com_ntransact_req *pSMB;
+
+        rc = small_smb_init(SMB_COM_NT_TRANSACT, 19 + setup_count, tcon,
+                                (void **)&pSMB);
+        if (rc)
+                return rc;
+        *ret_buf = (void *)pSMB;
+        pSMB->Reserved = 0;
+        pSMB->TotalParameterCount = cpu_to_le32(parm_len);
+        pSMB->TotalDataCount  = 0;
+        pSMB->MaxDataCount = cpu_to_le32((tcon->ses->server->maxBuf -
+                                          MAX_CIFS_HDR_SIZE) & 0xFFFFFF00);
+        pSMB->ParameterCount = pSMB->TotalParameterCount;
+        pSMB->DataCount  = pSMB->TotalDataCount;
+        temp_offset = offsetof(struct smb_com_ntransact_req, Parms) +
+                        (setup_count * 2) - 4 /* for rfc1001 length itself */;
+        pSMB->ParameterOffset = cpu_to_le32(temp_offset);
+        pSMB->DataOffset = cpu_to_le32(temp_offset + parm_len);
+        pSMB->SetupCount = setup_count; /* no need to le convert byte fields */
+        pSMB->SubCommand = cpu_to_le16(sub_command);
+        return 0;
+}
+
+static int
+validate_ntransact(char *buf, char **ppparm, char **ppdata,
+                   __u32 *pparmlen, __u32 *pdatalen)
+{
+        char *end_of_smb;
+        __u32 data_count, data_offset, parm_count, parm_offset;
+        struct smb_com_ntransact_rsp *pSMBr;
+
+        *pdatalen = 0;
+        *pparmlen = 0;
+
+        if (buf == NULL)
+                return -EINVAL;
+
+        pSMBr = (struct smb_com_ntransact_rsp *)buf;
+
+        /* ByteCount was converted from little endian in SendReceive */
+        end_of_smb = 2 /* sizeof byte count */ + pSMBr->ByteCount +
+                        (char *)&pSMBr->ByteCount;
+
+        data_offset = le32_to_cpu(pSMBr->DataOffset);
+        data_count = le32_to_cpu(pSMBr->DataCount);
+        parm_offset = le32_to_cpu(pSMBr->ParameterOffset);
+        parm_count = le32_to_cpu(pSMBr->ParameterCount);
+
+        *ppparm = (char *)&pSMBr->hdr.Protocol + parm_offset;
+        *ppdata = (char *)&pSMBr->hdr.Protocol + data_offset;
+
+        /* should we also check that parm and data areas do not overlap? */
+        if (*ppparm > end_of_smb) {
+                cFYI(1, "parms start after end of smb");
+                return -EINVAL;
+        } else if (parm_count + *ppparm > end_of_smb) {
+                cFYI(1, "parm end after end of smb");
+                return -EINVAL;
+        } else if (*ppdata > end_of_smb) {
+                cFYI(1, "data starts after end of smb");
+                return -EINVAL;
+        } else if (data_count + *ppdata > end_of_smb) {
+                cFYI(1, "data %p + count %d (%p) past smb end %p start %p",
+                        *ppdata, data_count, (data_count + *ppdata),
+                        end_of_smb, pSMBr);
+                return -EINVAL;
+        } else if (parm_count + data_count > pSMBr->ByteCount) {
+                cFYI(1, "parm count and data count larger than SMB");
+                return -EINVAL;
+        }
+        *pdatalen = data_count;
+        *pparmlen = parm_count;
+        return 0;
+}
+
 /* Get Security Descriptor (by handle) from remote server for a file or dir */
 int
 CIFSSMBGetCIFSACL(const int xid, struct cifsTconInfo *tcon, __u16 fid,
@@ -3214,7 +3212,7 @@ setCifsAclRetry:
         return (rc);
 }
 
-#endif /* CONFIG_CIFS_EXPERIMENTAL */
+#endif /* CONFIG_CIFS_ACL */
 
 /* Legacy Query Path Information call for lookup to old servers such
    as Win9x/WinME */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 32fa4d9b5dbc..a65d311d163a 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -64,8 +64,8 @@ struct smb_vol {
         char *UNC;
         char *UNCip;
         char *iocharset;  /* local code page for mapping to and from Unicode */
-        char source_rfc1001_name[16]; /* netbios name of client */
-        char target_rfc1001_name[16]; /* netbios name of server for Win9x/ME */
+        char source_rfc1001_name[RFC1001_NAME_LEN_WITH_NULL]; /* clnt nb name */
+        char target_rfc1001_name[RFC1001_NAME_LEN_WITH_NULL]; /* srvr nb name */
         uid_t cred_uid;
         uid_t linux_uid;
         gid_t linux_gid;
@@ -105,6 +105,7 @@ struct smb_vol {
         unsigned int wsize;
         bool sockopt_tcp_nodelay:1;
         unsigned short int port;
+        unsigned long actimeo; /* attribute cache timeout (jiffies) */
         char *prepath;
         struct sockaddr_storage srcaddr; /* allow binding to a local IP */
         struct nls_table *local_nls;
@@ -114,8 +115,8 @@ struct smb_vol {
 #define TLINK_ERROR_EXPIRE      (1 * HZ)
 #define TLINK_IDLE_EXPIRE       (600 * HZ)
 
-static int ipv4_connect(struct TCP_Server_Info *server);
-static int ipv6_connect(struct TCP_Server_Info *server);
+static int ip_connect(struct TCP_Server_Info *server);
+static int generic_ip_connect(struct TCP_Server_Info *server);
 static void tlink_rb_insert(struct rb_root *root, struct tcon_link *new_tlink);
 static void cifs_prune_tlinks(struct work_struct *work);
 
@@ -199,10 +200,9 @@ cifs_reconnect(struct TCP_Server_Info *server)
         while ((server->tcpStatus != CifsExiting) &&
                (server->tcpStatus != CifsGood)) {
                 try_to_freeze();
-                if (server->addr.sockAddr6.sin6_family == AF_INET6)
-                        rc = ipv6_connect(server);
-                else
-                        rc = ipv4_connect(server);
+
+                /* we should try only the port we connected to before */
+                rc = generic_ip_connect(server);
                 if (rc) {
                         cFYI(1, "reconnect error %d", rc);
                         msleep(3000);
@@ -476,7 +476,7 @@ incomplete_rcv:
                          * initialize frame)
                          */
                         cifs_set_port((struct sockaddr *)
-                                        &server->addr.sockAddr, CIFS_PORT);
+                                        &server->dstaddr, CIFS_PORT);
                         cifs_reconnect(server);
                         csocket = server->ssocket;
                         wake_up(&server->response_q);
@@ -806,24 +806,21 @@ cifs_parse_mount_options(char *options, const char *devname,
         short int override_gid = -1;
         bool uid_specified = false;
         bool gid_specified = false;
+        char *nodename = utsname()->nodename;
 
         separator[0] = ',';
         separator[1] = 0;
 
-        if (Local_System_Name[0] != 0)
-                memcpy(vol->source_rfc1001_name, Local_System_Name, 15);
-        else {
-                char *nodename = utsname()->nodename;
-                int n = strnlen(nodename, 15);
-                memset(vol->source_rfc1001_name, 0x20, 15);
-                for (i = 0; i < n; i++) {
-                        /* does not have to be perfect mapping since field is
-                        informational, only used for servers that do not support
-                        port 445 and it can be overridden at mount time */
-                        vol->source_rfc1001_name[i] = toupper(nodename[i]);
-                }
-        }
-        vol->source_rfc1001_name[15] = 0;
+        /*
+         * does not have to be perfect mapping since field is
+         * informational, only used for servers that do not support
+         * port 445 and it can be overridden at mount time
+         */
+        memset(vol->source_rfc1001_name, 0x20, RFC1001_NAME_LEN);
+        for (i = 0; i < strnlen(nodename, RFC1001_NAME_LEN); i++)
+                vol->source_rfc1001_name[i] = toupper(nodename[i]);
+
+        vol->source_rfc1001_name[RFC1001_NAME_LEN] = 0;
         /* null target name indicates to use *SMBSERVR default called name
            if we end up sending RFC1001 session initialize */
         vol->target_rfc1001_name[0] = 0;
@@ -840,6 +837,8 @@ cifs_parse_mount_options(char *options, const char *devname,
         /* default to using server inode numbers where available */
         vol->server_ino = 1;
 
+        vol->actimeo = CIFS_DEF_ACTIMEO;
+
         if (!options)
                 return 1;
 
@@ -985,13 +984,11 @@ cifs_parse_mount_options(char *options, const char *devname,
                                 return 1;
                         } else if (strnicmp(value, "krb5", 4) == 0) {
                                 vol->secFlg |= CIFSSEC_MAY_KRB5;
-#ifdef CONFIG_CIFS_EXPERIMENTAL
                         } else if (strnicmp(value, "ntlmsspi", 8) == 0) {
                                 vol->secFlg |= CIFSSEC_MAY_NTLMSSP |
                                         CIFSSEC_MUST_SIGN;
                         } else if (strnicmp(value, "ntlmssp", 7) == 0) {
                                 vol->secFlg |= CIFSSEC_MAY_NTLMSSP;
-#endif
                         } else if (strnicmp(value, "ntlmv2i", 7) == 0) {
                                 vol->secFlg |= CIFSSEC_MAY_NTLMV2 |
                                         CIFSSEC_MUST_SIGN;
@@ -1168,22 +1165,22 @@ cifs_parse_mount_options(char *options, const char *devname,
                         if (!value || !*value || (*value == ' ')) {
                                 cFYI(1, "invalid (empty) netbiosname");
                         } else {
-                                memset(vol->source_rfc1001_name, 0x20, 15);
-                                for (i = 0; i < 15; i++) {
-                                /* BB are there cases in which a comma can be
-                                valid in this workstation netbios name (and need
-                                special handling)? */
-
-                                /* We do not uppercase netbiosname for user */
+                                memset(vol->source_rfc1001_name, 0x20,
+                                        RFC1001_NAME_LEN);
+                                /*
+                                 * FIXME: are there cases in which a comma can
+                                 * be valid in workstation netbios name (and
+                                 * need special handling)?
+                                 */
+                                for (i = 0; i < RFC1001_NAME_LEN; i++) {
+                                        /* don't ucase netbiosname for user */
                                         if (value[i] == 0)
                                                 break;
-                                        else
-                                                vol->source_rfc1001_name[i] =
-                                                                value[i];
+                                        vol->source_rfc1001_name[i] = value[i];
                                 }
                                 /* The string has 16th byte zero still from
                                 set at top of the function  */
-                                if ((i == 15) && (value[i] != 0))
+                                if (i == RFC1001_NAME_LEN && value[i] != 0)
                                         printk(KERN_WARNING "CIFS: netbiosname"
                                                 " longer than 15 truncated.\n");
                         }
@@ -1193,7 +1190,8 @@ cifs_parse_mount_options(char *options, const char *devname,
                                 cFYI(1, "empty server netbiosname specified");
                         } else {
                                 /* last byte, type, is 0x20 for servr type */
-                                memset(vol->target_rfc1001_name, 0x20, 16);
+                                memset(vol->target_rfc1001_name, 0x20,
+                                        RFC1001_NAME_LEN_WITH_NULL);
 
                                 for (i = 0; i < 15; i++) {
                                 /* BB are there cases in which a comma can be
@@ -1210,10 +1208,20 @@ cifs_parse_mount_options(char *options, const char *devname,
                                 }
                                 /* The string has 16th byte zero still from
                                    set at top of the function  */
-                                if ((i == 15) && (value[i] != 0))
+                                if (i == RFC1001_NAME_LEN && value[i] != 0)
                                         printk(KERN_WARNING "CIFS: server net"
                                         "biosname longer than 15 truncated.\n");
                         }
+                } else if (strnicmp(data, "actimeo", 7) == 0) {
+                        if (value && *value) {
+                                vol->actimeo = HZ * simple_strtoul(value,
+                                                                   &value, 0);
+                                if (vol->actimeo > CIFS_MAX_ACTIMEO) {
+                                        cERROR(1, "CIFS: attribute cache"
+                                                        "timeout too large");
+                                        return 1;
+                                }
+                        }
                 } else if (strnicmp(data, "credentials", 4) == 0) {
                         /* ignore */
                 } else if (strnicmp(data, "version", 3) == 0) {
@@ -1331,10 +1339,8 @@ cifs_parse_mount_options(char *options, const char *devname,
                         vol->no_psx_acl = 0;
                 } else if (strnicmp(data, "noacl", 5) == 0) {
                         vol->no_psx_acl = 1;
-#ifdef CONFIG_CIFS_EXPERIMENTAL
                 } else if (strnicmp(data, "locallease", 6) == 0) {
                         vol->local_lease = 1;
-#endif
                 } else if (strnicmp(data, "sign", 4) == 0) {
                         vol->secFlg |= CIFSSEC_MUST_SIGN;
                 } else if (strnicmp(data, "seal", 4) == 0) {
@@ -1444,35 +1450,71 @@ srcip_matches(struct sockaddr *srcaddr, struct sockaddr *rhs)
         }
 }
 
+/*
+ * If no port is specified in addr structure, we try to match with 445 port
+ * and if it fails - with 139 ports. It should be called only if address
+ * families of server and addr are equal.
+ */
+static bool
+match_port(struct TCP_Server_Info *server, struct sockaddr *addr)
+{
+        unsigned short int port, *sport;
+
+        switch (addr->sa_family) {
+        case AF_INET:
+                sport = &((struct sockaddr_in *) &server->dstaddr)->sin_port;
+                port = ((struct sockaddr_in *) addr)->sin_port;
+                break;
+        case AF_INET6:
+                sport = &((struct sockaddr_in6 *) &server->dstaddr)->sin6_port;
+                port = ((struct sockaddr_in6 *) addr)->sin6_port;
+                break;
+        default:
+                WARN_ON(1);
+                return false;
+        }
+
+        if (!port) {
+                port = htons(CIFS_PORT);
+                if (port == *sport)
+                        return true;
+
+                port = htons(RFC1001_PORT);
+        }
+
+        return port == *sport;
+}
 
 static bool
 match_address(struct TCP_Server_Info *server, struct sockaddr *addr,
               struct sockaddr *srcaddr)
 {
-        struct sockaddr_in *addr4 = (struct sockaddr_in *)addr;
-        struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *)addr;
-
         switch (addr->sa_family) {
-        case AF_INET:
-                if (addr4->sin_addr.s_addr !=
-                    server->addr.sockAddr.sin_addr.s_addr)
-                        return false;
-                if (addr4->sin_port &&
-                    addr4->sin_port != server->addr.sockAddr.sin_port)
+        case AF_INET: {
+                struct sockaddr_in *addr4 = (struct sockaddr_in *)addr;
+                struct sockaddr_in *srv_addr4 =
+                                        (struct sockaddr_in *)&server->dstaddr;
+
+                if (addr4->sin_addr.s_addr != srv_addr4->sin_addr.s_addr)
                         return false;
                 break;
-        case AF_INET6:
+        }
+        case AF_INET6: {
+                struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *)addr;
+                struct sockaddr_in6 *srv_addr6 =
+                                        (struct sockaddr_in6 *)&server->dstaddr;
+
                 if (!ipv6_addr_equal(&addr6->sin6_addr,
-                                     &server->addr.sockAddr6.sin6_addr))
+                                     &srv_addr6->sin6_addr))
                         return false;
-                if (addr6->sin6_scope_id !=
-                    server->addr.sockAddr6.sin6_scope_id)
-                        return false;
-                if (addr6->sin6_port &&
-                    addr6->sin6_port != server->addr.sockAddr6.sin6_port)
+                if (addr6->sin6_scope_id != srv_addr6->sin6_scope_id)
                         return false;
                 break;
         }
+        default:
+                WARN_ON(1);
+                return false; /* don't expect to be here */
+        }
 
         if (!srcip_matches(srcaddr, (struct sockaddr *)&server->srcaddr))
                 return false;
@@ -1539,6 +1581,9 @@ cifs_find_tcp_session(struct sockaddr *addr, struct smb_vol *vol)
                                    (struct sockaddr *)&vol->srcaddr))
                         continue;
 
+                if (!match_port(server, addr))
+                        continue;
+
                 if (!match_security(server, vol))
                         continue;
 
@@ -1671,14 +1716,13 @@ cifs_get_tcp_session(struct smb_vol *volume_info)
                 cFYI(1, "attempting ipv6 connect");
                 /* BB should we allow ipv6 on port 139? */
                 /* other OS never observed in Wild doing 139 with v6 */
-                memcpy(&tcp_ses->addr.sockAddr6, sin_server6,
-                        sizeof(struct sockaddr_in6));
-                rc = ipv6_connect(tcp_ses);
-        } else {
-                memcpy(&tcp_ses->addr.sockAddr, sin_server,
-                        sizeof(struct sockaddr_in));
-                rc = ipv4_connect(tcp_ses);
-        }
+                memcpy(&tcp_ses->dstaddr, sin_server6,
+                       sizeof(struct sockaddr_in6));
+        } else
+                memcpy(&tcp_ses->dstaddr, sin_server,
+                       sizeof(struct sockaddr_in));
+
+        rc = ip_connect(tcp_ses);
         if (rc < 0) {
                 cERROR(1, "Error connecting to socket. Aborting operation");
                 goto out_err_crypto_release;
@@ -1783,6 +1827,8 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info)
 {
         int rc = -ENOMEM, xid;
         struct cifsSesInfo *ses;
+        struct sockaddr_in *addr = (struct sockaddr_in *)&server->dstaddr;
+        struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *)&server->dstaddr;
 
         xid = GetXid();
 
@@ -1826,12 +1872,10 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info)
 
         /* new SMB session uses our server ref */
         ses->server = server;
-        if (server->addr.sockAddr6.sin6_family == AF_INET6)
-                sprintf(ses->serverName, "%pI6",
-                        &server->addr.sockAddr6.sin6_addr);
+        if (server->dstaddr.ss_family == AF_INET6)
+                sprintf(ses->serverName, "%pI6", &addr6->sin6_addr);
         else
-                sprintf(ses->serverName, "%pI4",
-                        &server->addr.sockAddr.sin_addr.s_addr);
+                sprintf(ses->serverName, "%pI4", &addr->sin_addr);
 
         if (volume_info->username)
                 strncpy(ses->userName, volume_info->username,
@@ -2126,19 +2170,106 @@ bind_socket(struct TCP_Server_Info *server)
 }
 
 static int
-ipv4_connect(struct TCP_Server_Info *server)
+ip_rfc1001_connect(struct TCP_Server_Info *server)
 {
         int rc = 0;
-        int val;
-        bool connected = false;
-        __be16 orig_port = 0;
+        /*
+         * some servers require RFC1001 sessinit before sending
+         * negprot - BB check reconnection in case where second
+         * sessinit is sent but no second negprot
+         */
+        struct rfc1002_session_packet *ses_init_buf;
+        struct smb_hdr *smb_buf;
+        ses_init_buf = kzalloc(sizeof(struct rfc1002_session_packet),
+                               GFP_KERNEL);
+        if (ses_init_buf) {
+                ses_init_buf->trailer.session_req.called_len = 32;
+
+                if (server->server_RFC1001_name &&
+                    server->server_RFC1001_name[0] != 0)
+                        rfc1002mangle(ses_init_buf->trailer.
+                                      session_req.called_name,
+                                      server->server_RFC1001_name,
+                                      RFC1001_NAME_LEN_WITH_NULL);
+                else
+                        rfc1002mangle(ses_init_buf->trailer.
+                                      session_req.called_name,
+                                      DEFAULT_CIFS_CALLED_NAME,
+                                      RFC1001_NAME_LEN_WITH_NULL);
+
+                ses_init_buf->trailer.session_req.calling_len = 32;
+
+                /*
+                 * calling name ends in null (byte 16) from old smb
+                 * convention.
+                 */
+                if (server->workstation_RFC1001_name &&
+                    server->workstation_RFC1001_name[0] != 0)
+                        rfc1002mangle(ses_init_buf->trailer.
+                                      session_req.calling_name,
+                                      server->workstation_RFC1001_name,
+                                      RFC1001_NAME_LEN_WITH_NULL);
+                else
+                        rfc1002mangle(ses_init_buf->trailer.
+                                      session_req.calling_name,
+                                      "LINUX_CIFS_CLNT",
+                                      RFC1001_NAME_LEN_WITH_NULL);
+
+                ses_init_buf->trailer.session_req.scope1 = 0;
+                ses_init_buf->trailer.session_req.scope2 = 0;
+                smb_buf = (struct smb_hdr *)ses_init_buf;
+
+                /* sizeof RFC1002_SESSION_REQUEST with no scope */
+                smb_buf->smb_buf_length = 0x81000044;
+                rc = smb_send(server, smb_buf, 0x44);
+                kfree(ses_init_buf);
+                /*
+                 * RFC1001 layer in at least one server
+                 * requires very short break before negprot
+                 * presumably because not expecting negprot
+                 * to follow so fast.  This is a simple
+                 * solution that works without
+                 * complicating the code and causes no
+                 * significant slowing down on mount
+                 * for everyone else
+                 */
+                usleep_range(1000, 2000);
+        }
+        /*
+         * else the negprot may still work without this
+         * even though malloc failed
+         */
+
+        return rc;
+}
+
+static int
+generic_ip_connect(struct TCP_Server_Info *server)
+{
+        int rc = 0;
+        unsigned short int sport;
+        int slen, sfamily;
         struct socket *socket = server->ssocket;
+        struct sockaddr *saddr;
+
+        saddr = (struct sockaddr *) &server->dstaddr;
+
+        if (server->dstaddr.ss_family == AF_INET6) {
+                sport = ((struct sockaddr_in6 *) saddr)->sin6_port;
+                slen = sizeof(struct sockaddr_in6);
+                sfamily = AF_INET6;
+        } else {
+                sport = ((struct sockaddr_in *) saddr)->sin_port;
+                slen = sizeof(struct sockaddr_in);
+                sfamily = AF_INET;
+        }
 
         if (socket == NULL) {
-                rc = sock_create_kern(PF_INET, SOCK_STREAM,
+                rc = sock_create_kern(sfamily, SOCK_STREAM,
                                       IPPROTO_TCP, &socket);
                 if (rc < 0) {
                         cERROR(1, "Error %d creating socket", rc);
+                        server->ssocket = NULL;
                         return rc;
                 }
 
@@ -2146,63 +2277,28 @@ ipv4_connect(struct TCP_Server_Info *server)
                 cFYI(1, "Socket created");
                 server->ssocket = socket;
                 socket->sk->sk_allocation = GFP_NOFS;
-                cifs_reclassify_socket4(socket);
+                if (sfamily == AF_INET6)
+                        cifs_reclassify_socket6(socket);
+                else
+                        cifs_reclassify_socket4(socket);
         }
 
         rc = bind_socket(server);
         if (rc < 0)
                 return rc;
 
-        /* user overrode default port */
-        if (server->addr.sockAddr.sin_port) {
-                rc = socket->ops->connect(socket, (struct sockaddr *)
-                                          &server->addr.sockAddr,
-                                          sizeof(struct sockaddr_in), 0);
-                if (rc >= 0)
-                        connected = true;
-        }
-
-        if (!connected) {
-                /* save original port so we can retry user specified port
-                        later if fall back ports fail this time  */
-                orig_port = server->addr.sockAddr.sin_port;
-
-                /* do not retry on the same port we just failed on */
-                if (server->addr.sockAddr.sin_port != htons(CIFS_PORT)) {
-                        server->addr.sockAddr.sin_port = htons(CIFS_PORT);
-                        rc = socket->ops->connect(socket,
-                                                (struct sockaddr *)
-                                                &server->addr.sockAddr,
-                                                sizeof(struct sockaddr_in), 0);
-                        if (rc >= 0)
-                                connected = true;
-                }
-        }
-        if (!connected) {
-                server->addr.sockAddr.sin_port = htons(RFC1001_PORT);
-                rc = socket->ops->connect(socket, (struct sockaddr *)
-                                              &server->addr.sockAddr,
-                                              sizeof(struct sockaddr_in), 0);
-                if (rc >= 0)
-                        connected = true;
-        }
-
-        /* give up here - unless we want to retry on different
-                protocol families some day */
-        if (!connected) {
-                if (orig_port)
-                        server->addr.sockAddr.sin_port = orig_port;
-                cFYI(1, "Error %d connecting to server via ipv4", rc);
+        rc = socket->ops->connect(socket, saddr, slen, 0);
+        if (rc < 0) {
+                cFYI(1, "Error %d connecting to server", rc);
                 sock_release(socket);
                 server->ssocket = NULL;
                 return rc;
         }
 
-
         /*
          * Eventually check for other socket options to change from
-         *  the default. sock_setsockopt not used because it expects
-         *  user space buffer
+         * the default. sock_setsockopt not used because it expects
+         * user space buffer
          */
         socket->sk->sk_rcvtimeo = 7 * HZ;
         socket->sk->sk_sndtimeo = 5 * HZ;
@@ -2216,7 +2312,7 @@ ipv4_connect(struct TCP_Server_Info *server)
         }
 
         if (server->tcp_nodelay) {
-                val = 1;
+                int val = 1;
                 rc = kernel_setsockopt(socket, SOL_TCP, TCP_NODELAY,
                                 (char *)&val, sizeof(val));
                 if (rc)
@@ -2227,161 +2323,39 @@ ipv4_connect(struct TCP_Server_Info *server)
                  socket->sk->sk_sndbuf,
                  socket->sk->sk_rcvbuf, socket->sk->sk_rcvtimeo);
 
-        /* send RFC1001 sessinit */
-        if (server->addr.sockAddr.sin_port == htons(RFC1001_PORT)) {
-                /* some servers require RFC1001 sessinit before sending
-                negprot - BB check reconnection in case where second
-                sessinit is sent but no second negprot */
-                struct rfc1002_session_packet *ses_init_buf;
-                struct smb_hdr *smb_buf;
-                ses_init_buf = kzalloc(sizeof(struct rfc1002_session_packet),
-                                       GFP_KERNEL);
-                if (ses_init_buf) {
-                        ses_init_buf->trailer.session_req.called_len = 32;
-                        if (server->server_RFC1001_name &&
-                            server->server_RFC1001_name[0] != 0)
-                                rfc1002mangle(ses_init_buf->trailer.
-                                                session_req.called_name,
-                                              server->server_RFC1001_name,
-                                              RFC1001_NAME_LEN_WITH_NULL);
-                        else
-                                rfc1002mangle(ses_init_buf->trailer.
-                                                session_req.called_name,
-                                              DEFAULT_CIFS_CALLED_NAME,
-                                              RFC1001_NAME_LEN_WITH_NULL);
-
-                        ses_init_buf->trailer.session_req.calling_len = 32;
-
-                        /* calling name ends in null (byte 16) from old smb
-                        convention. */
-                        if (server->workstation_RFC1001_name &&
-                            server->workstation_RFC1001_name[0] != 0)
-                                rfc1002mangle(ses_init_buf->trailer.
-                                                session_req.calling_name,
-                                              server->workstation_RFC1001_name,
-                                              RFC1001_NAME_LEN_WITH_NULL);
-                        else
-                                rfc1002mangle(ses_init_buf->trailer.
-                                                session_req.calling_name,
-                                              "LINUX_CIFS_CLNT",
-                                              RFC1001_NAME_LEN_WITH_NULL);
-
-                        ses_init_buf->trailer.session_req.scope1 = 0;
-                        ses_init_buf->trailer.session_req.scope2 = 0;
-                        smb_buf = (struct smb_hdr *)ses_init_buf;
-                        /* sizeof RFC1002_SESSION_REQUEST with no scope */
-                        smb_buf->smb_buf_length = 0x81000044;
-                        rc = smb_send(server, smb_buf, 0x44);
-                        kfree(ses_init_buf);
-                        msleep(1); /* RFC1001 layer in at least one server
-                                      requires very short break before negprot
-                                      presumably because not expecting negprot
-                                      to follow so fast.  This is a simple
-                                      solution that works without
-                                      complicating the code and causes no
-                                      significant slowing down on mount
-                                      for everyone else */
-                }
-                /* else the negprot may still work without this
-                even though malloc failed */
-
-        }
+        if (sport == htons(RFC1001_PORT))
+                rc = ip_rfc1001_connect(server);
 
         return rc;
 }
 
 static int
-ipv6_connect(struct TCP_Server_Info *server)
+ip_connect(struct TCP_Server_Info *server)
 {
-        int rc = 0;
-        int val;
-        bool connected = false;
-        __be16 orig_port = 0;
-        struct socket *socket = server->ssocket;
+        unsigned short int *sport;
+        struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *)&server->dstaddr;
+        struct sockaddr_in *addr = (struct sockaddr_in *)&server->dstaddr;
 
-        if (socket == NULL) {
-                rc = sock_create_kern(PF_INET6, SOCK_STREAM,
-                                      IPPROTO_TCP, &socket);
-                if (rc < 0) {
-                        cERROR(1, "Error %d creating ipv6 socket", rc);
-                        socket = NULL;
-                        return rc;
-                }
+        if (server->dstaddr.ss_family == AF_INET6)
+                sport = &addr6->sin6_port;
+        else
+                sport = &addr->sin_port;
 
-                /* BB other socket options to set KEEPALIVE, NODELAY? */
-                cFYI(1, "ipv6 Socket created");
-                server->ssocket = socket;
-                socket->sk->sk_allocation = GFP_NOFS;
-                cifs_reclassify_socket6(socket);
-        }
+        if (*sport == 0) {
+                int rc;
 
-        rc = bind_socket(server);
-        if (rc < 0)
-                return rc;
+                /* try with 445 port at first */
+                *sport = htons(CIFS_PORT);
 
-        /* user overrode default port */
-        if (server->addr.sockAddr6.sin6_port) {
-                rc = socket->ops->connect(socket,
-                                (struct sockaddr *) &server->addr.sockAddr6,
-                                sizeof(struct sockaddr_in6), 0);
+                rc = generic_ip_connect(server);
                 if (rc >= 0)
-                        connected = true;
-        }
-
-        if (!connected) {
-                /* save original port so we can retry user specified port
-                        later if fall back ports fail this time  */
-
-                orig_port = server->addr.sockAddr6.sin6_port;
-                /* do not retry on the same port we just failed on */
-                if (server->addr.sockAddr6.sin6_port != htons(CIFS_PORT)) {
-                        server->addr.sockAddr6.sin6_port = htons(CIFS_PORT);
-                        rc = socket->ops->connect(socket, (struct sockaddr *)
-                                        &server->addr.sockAddr6,
-                                        sizeof(struct sockaddr_in6), 0);
-                        if (rc >= 0)
-                                connected = true;
-                }
-        }
-        if (!connected) {
-                server->addr.sockAddr6.sin6_port = htons(RFC1001_PORT);
-                rc = socket->ops->connect(socket, (struct sockaddr *)
-                                &server->addr.sockAddr6,
-                                sizeof(struct sockaddr_in6), 0);
-                if (rc >= 0)
-                        connected = true;
-        }
-
-        /* give up here - unless we want to retry on different
-                protocol families some day */
-        if (!connected) {
-                if (orig_port)
-                        server->addr.sockAddr6.sin6_port = orig_port;
-                cFYI(1, "Error %d connecting to server via ipv6", rc);
-                sock_release(socket);
-                server->ssocket = NULL;
-                return rc;
-        }
-
-        /*
-         * Eventually check for other socket options to change from
-         * the default. sock_setsockopt not used because it expects
-         * user space buffer
-         */
-        socket->sk->sk_rcvtimeo = 7 * HZ;
-        socket->sk->sk_sndtimeo = 5 * HZ;
+                        return rc;
 
-        if (server->tcp_nodelay) {
-                val = 1;
-                rc = kernel_setsockopt(socket, SOL_TCP, TCP_NODELAY,
-                                (char *)&val, sizeof(val));
-                if (rc)
-                        cFYI(1, "set TCP_NODELAY socket option error %d", rc);
+                /* if it failed, try with 139 port */
+                *sport = htons(RFC1001_PORT);
         }
 
-        server->ssocket = socket;
-
-        return rc;
+        return generic_ip_connect(server);
 }
 
 void reset_cifs_unix_caps(int xid, struct cifsTconInfo *tcon,
@@ -2571,6 +2545,8 @@ static void setup_cifs_sb(struct smb_vol *pvolume_info,
         cFYI(1, "file mode: 0x%x  dir mode: 0x%x",
                 cifs_sb->mnt_file_mode, cifs_sb->mnt_dir_mode);
 
+        cifs_sb->actimeo = pvolume_info->actimeo;
+
         if (pvolume_info->noperm)
                 cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_PERM;
         if (pvolume_info->setuids)
@@ -2821,13 +2797,13 @@ remote_path_check:
         /* check if a whole path (including prepath) is not remote */
         if (!rc && cifs_sb->prepathlen && tcon) {
                 /* build_path_to_root works only when we have a valid tcon */
-                full_path = cifs_build_path_to_root(cifs_sb);
+                full_path = cifs_build_path_to_root(cifs_sb, tcon);
                 if (full_path == NULL) {
                         rc = -ENOMEM;
                         goto mount_fail_check;
                 }
                 rc = is_path_accessible(xid, tcon, cifs_sb, full_path);
-                if (rc != -EREMOTE) {
+                if (rc != 0 && rc != -EREMOTE) {
                         kfree(full_path);
                         goto mount_fail_check;
                 }
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 3840eddbfb7a..2e773825835e 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -135,9 +135,9 @@ static void setup_cifs_dentry(struct cifsTconInfo *tcon,
                               struct inode *newinode)
 {
         if (tcon->nocase)
-                direntry->d_op = &cifs_ci_dentry_ops;
+                d_set_d_op(direntry, &cifs_ci_dentry_ops);
         else
-                direntry->d_op = &cifs_dentry_ops;
+                d_set_d_op(direntry, &cifs_dentry_ops);
         d_instantiate(direntry, newinode);
 }
 
@@ -293,10 +293,8 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode,
                         args.uid = NO_CHANGE_64;
                         args.gid = NO_CHANGE_64;
                 }
-                CIFSSMBUnixSetPathInfo(xid, tcon, full_path, &args,
-                                        cifs_sb->local_nls,
-                                        cifs_sb->mnt_cifs_flags &
-                                                CIFS_MOUNT_MAP_SPECIAL_CHR);
+                CIFSSMBUnixSetFileInfo(xid, tcon, &args, fileHandle,
+                                        current->tgid);
         } else {
                 /* BB implement mode setting via Windows security
                    descriptors e.g. */
@@ -421,9 +419,9 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, int mode,
                 rc = cifs_get_inode_info_unix(&newinode, full_path,
                                                 inode->i_sb, xid);
                 if (pTcon->nocase)
-                        direntry->d_op = &cifs_ci_dentry_ops;
+                        d_set_d_op(direntry, &cifs_ci_dentry_ops);
                 else
-                        direntry->d_op = &cifs_dentry_ops;
+                        d_set_d_op(direntry, &cifs_dentry_ops);
 
                 if (rc == 0)
                         d_instantiate(direntry, newinode);
@@ -604,9 +602,9 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
 
         if ((rc == 0) && (newInode != NULL)) {
                 if (pTcon->nocase)
-                        direntry->d_op = &cifs_ci_dentry_ops;
+                        d_set_d_op(direntry, &cifs_ci_dentry_ops);
                 else
-                        direntry->d_op = &cifs_dentry_ops;
+                        d_set_d_op(direntry, &cifs_dentry_ops);
                 d_add(direntry, newInode);
                 if (posix_open) {
                         filp = lookup_instantiate_filp(nd, direntry,
@@ -634,9 +632,9 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
                 rc = 0;
                 direntry->d_time = jiffies;
                 if (pTcon->nocase)
-                        direntry->d_op = &cifs_ci_dentry_ops;
+                        d_set_d_op(direntry, &cifs_ci_dentry_ops);
                 else
-                        direntry->d_op = &cifs_dentry_ops;
+                        d_set_d_op(direntry, &cifs_dentry_ops);
                 d_add(direntry, NULL);
         /*      if it was once a directory (but how can we tell?) we could do
                 shrink_dcache_parent(direntry); */
@@ -656,22 +654,37 @@ lookup_out:
 static int
 cifs_d_revalidate(struct dentry *direntry, struct nameidata *nd)
 {
-        int isValid = 1;
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
 
         if (direntry->d_inode) {
                 if (cifs_revalidate_dentry(direntry))
                         return 0;
-        } else {
-                cFYI(1, "neg dentry 0x%p name = %s",
-                         direntry, direntry->d_name.name);
-                if (time_after(jiffies, direntry->d_time + HZ) ||
-                        !lookupCacheEnabled) {
-                        d_drop(direntry);
-                        isValid = 0;
-                }
+                else
+                        return 1;
+        }
+
+        /*
+         * This may be nfsd (or something), anyway, we can't see the
+         * intent of this. So, since this can be for creation, drop it.
+         */
+        if (!nd)
+                return 0;
+
+        /*
+         * Drop the negative dentry, in order to make sure to use the
+         * case sensitive name which is specified by user if this is
+         * for creation.
+         */
+        if (!(nd->flags & (LOOKUP_CONTINUE | LOOKUP_PARENT))) {
+                if (nd->flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
+                        return 0;
         }
 
-        return isValid;
+        if (time_after(jiffies, direntry->d_time + HZ) || !lookupCacheEnabled)
+                return 0;
+
+        return 1;
 }
 
 /* static int cifs_d_delete(struct dentry *direntry)
@@ -688,9 +701,10 @@ const struct dentry_operations cifs_dentry_ops = {
 /* d_delete:       cifs_d_delete,      */ /* not needed except for debugging */
 };
 
-static int cifs_ci_hash(struct dentry *dentry, struct qstr *q)
+static int cifs_ci_hash(const struct dentry *dentry, const struct inode *inode,
+                struct qstr *q)
 {
-        struct nls_table *codepage = CIFS_SB(dentry->d_inode->i_sb)->local_nls;
+        struct nls_table *codepage = CIFS_SB(dentry->d_sb)->local_nls;
         unsigned long hash;
         int i;
 
@@ -703,21 +717,16 @@ static int cifs_ci_hash(struct dentry *dentry, struct qstr *q)
         return 0;
 }
 
-static int cifs_ci_compare(struct dentry *dentry, struct qstr *a,
-                           struct qstr *b)
+static int cifs_ci_compare(const struct dentry *parent,
+                const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name)
 {
-        struct nls_table *codepage = CIFS_SB(dentry->d_inode->i_sb)->local_nls;
-
-        if ((a->len == b->len) &&
-            (nls_strnicmp(codepage, a->name, b->name, a->len) == 0)) {
-                /*
-                 * To preserve case, don't let an existing negative dentry's
-                 * case take precedence.  If a is not a negative dentry, this
-                 * should have no side effects
-                 */
-                memcpy((void *)a->name, b->name, a->len);
+        struct nls_table *codepage = CIFS_SB(pinode->i_sb)->local_nls;
+
+        if ((name->len == len) &&
+            (nls_strnicmp(codepage, name->name, str, len) == 0))
                 return 0;
-        }
         return 1;
 }
 
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index b857ce5db775..d843631c028d 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -104,53 +104,6 @@ static inline int cifs_get_disposition(unsigned int flags)
                 return FILE_OPEN;
 }
 
-static inline int cifs_open_inode_helper(struct inode *inode,
-        struct cifsTconInfo *pTcon, __u32 oplock, FILE_ALL_INFO *buf,
-        char *full_path, int xid)
-{
-        struct cifsInodeInfo *pCifsInode = CIFS_I(inode);
-        struct timespec temp;
-        int rc;
-
-        if (pCifsInode->clientCanCacheRead) {
-                /* we have the inode open somewhere else
-                   no need to discard cache data */
-                goto client_can_cache;
-        }
-
-        /* BB need same check in cifs_create too? */
-        /* if not oplocked, invalidate inode pages if mtime or file
-           size changed */
-        temp = cifs_NTtimeToUnix(buf->LastWriteTime);
-        if (timespec_equal(&inode->i_mtime, &temp) &&
-                           (inode->i_size ==
-                            (loff_t)le64_to_cpu(buf->EndOfFile))) {
-                cFYI(1, "inode unchanged on server");
-        } else {
-                if (inode->i_mapping) {
-                        /* BB no need to lock inode until after invalidate
-                        since namei code should already have it locked? */
-                        rc = filemap_write_and_wait(inode->i_mapping);
-                        mapping_set_error(inode->i_mapping, rc);
-                }
-                cFYI(1, "invalidating remote inode since open detected it "
-                         "changed");
-                invalidate_remote_inode(inode);
-        }
-
-client_can_cache:
-        if (pTcon->unix_ext)
-                rc = cifs_get_inode_info_unix(&inode, full_path, inode->i_sb,
-                                              xid);
-        else
-                rc = cifs_get_inode_info(&inode, full_path, buf, inode->i_sb,
-                                         xid, NULL);
-
-        cifs_set_oplock_level(pCifsInode, oplock);
-
-        return rc;
-}
-
 int cifs_posix_open(char *full_path, struct inode **pinode,
                         struct super_block *sb, int mode, unsigned int f_flags,
                         __u32 *poplock, __u16 *pnetfid, int xid)
@@ -213,6 +166,76 @@ posix_open_ret:
         return rc;
 }
 
+static int
+cifs_nt_open(char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb,
+             struct cifsTconInfo *tcon, unsigned int f_flags, __u32 *poplock,
+             __u16 *pnetfid, int xid)
+{
+        int rc;
+        int desiredAccess;
+        int disposition;
+        FILE_ALL_INFO *buf;
+
+        desiredAccess = cifs_convert_flags(f_flags);
+
+/*********************************************************************
+ *  open flag mapping table:
+ *
+ *      POSIX Flag            CIFS Disposition
+ *      ----------            ----------------
+ *      O_CREAT               FILE_OPEN_IF
+ *      O_CREAT | O_EXCL      FILE_CREATE
+ *      O_CREAT | O_TRUNC     FILE_OVERWRITE_IF
+ *      O_TRUNC               FILE_OVERWRITE
+ *      none of the above     FILE_OPEN
+ *
+ *      Note that there is not a direct match between disposition
+ *      FILE_SUPERSEDE (ie create whether or not file exists although
+ *      O_CREAT | O_TRUNC is similar but truncates the existing
+ *      file rather than creating a new file as FILE_SUPERSEDE does
+ *      (which uses the attributes / metadata passed in on open call)
+ *?
+ *?  O_SYNC is a reasonable match to CIFS writethrough flag
+ *?  and the read write flags match reasonably.  O_LARGEFILE
+ *?  is irrelevant because largefile support is always used
+ *?  by this client. Flags O_APPEND, O_DIRECT, O_DIRECTORY,
+ *       O_FASYNC, O_NOFOLLOW, O_NONBLOCK need further investigation
+ *********************************************************************/
+
+        disposition = cifs_get_disposition(f_flags);
+
+        /* BB pass O_SYNC flag through on file attributes .. BB */
+
+        buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
+        if (!buf)
+                return -ENOMEM;
+
+        if (tcon->ses->capabilities & CAP_NT_SMBS)
+                rc = CIFSSMBOpen(xid, tcon, full_path, disposition,
+                         desiredAccess, CREATE_NOT_DIR, pnetfid, poplock, buf,
+                         cifs_sb->local_nls, cifs_sb->mnt_cifs_flags
+                                 & CIFS_MOUNT_MAP_SPECIAL_CHR);
+        else
+                rc = SMBLegacyOpen(xid, tcon, full_path, disposition,
+                        desiredAccess, CREATE_NOT_DIR, pnetfid, poplock, buf,
+                        cifs_sb->local_nls, cifs_sb->mnt_cifs_flags
+                                & CIFS_MOUNT_MAP_SPECIAL_CHR);
+
+        if (rc)
+                goto out;
+
+        if (tcon->unix_ext)
+                rc = cifs_get_inode_info_unix(&inode, full_path, inode->i_sb,
+                                              xid);
+        else
+                rc = cifs_get_inode_info(&inode, full_path, buf, inode->i_sb,
+                                         xid, pnetfid);
+
+out:
+        kfree(buf);
+        return rc;
+}
+
 struct cifsFileInfo *
 cifs_new_fileinfo(__u16 fileHandle, struct file *file,
                   struct tcon_link *tlink, __u32 oplock)
@@ -317,10 +340,8 @@ int cifs_open(struct inode *inode, struct file *file)
         struct cifsFileInfo *pCifsFile = NULL;
         struct cifsInodeInfo *pCifsInode;
         char *full_path = NULL;
-        int desiredAccess;
-        int disposition;
+        bool posix_open_ok = false;
         __u16 netfid;
-        FILE_ALL_INFO *buf = NULL;
 
         xid = GetXid();
 
@@ -358,17 +379,7 @@ int cifs_open(struct inode *inode, struct file *file)
                                 file->f_flags, &oplock, &netfid, xid);
                 if (rc == 0) {
                         cFYI(1, "posix open succeeded");
-
-                        pCifsFile = cifs_new_fileinfo(netfid, file, tlink,
-                                                      oplock);
-                        if (pCifsFile == NULL) {
-                                CIFSSMBClose(xid, tcon, netfid);
-                                rc = -ENOMEM;
-                        }
-
-                        cifs_fscache_set_inode_cookie(inode, file);
-
-                        goto out;
+                        posix_open_ok = true;
                 } else if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) {
                         if (tcon->ses->serverNOS)
                                 cERROR(1, "server %s of type %s returned"
@@ -385,103 +396,39 @@ int cifs_open(struct inode *inode, struct file *file)
                    or DFS errors */
         }
 
-        desiredAccess = cifs_convert_flags(file->f_flags);
-
-/*********************************************************************
- *  open flag mapping table:
- *
- *      POSIX Flag            CIFS Disposition
- *      ----------            ----------------
- *      O_CREAT               FILE_OPEN_IF
- *      O_CREAT | O_EXCL      FILE_CREATE
- *      O_CREAT | O_TRUNC     FILE_OVERWRITE_IF
- *      O_TRUNC               FILE_OVERWRITE
- *      none of the above     FILE_OPEN
- *
- *      Note that there is not a direct match between disposition
- *      FILE_SUPERSEDE (ie create whether or not file exists although
- *      O_CREAT | O_TRUNC is similar but truncates the existing
- *      file rather than creating a new file as FILE_SUPERSEDE does
- *      (which uses the attributes / metadata passed in on open call)
- *?
- *?  O_SYNC is a reasonable match to CIFS writethrough flag
- *?  and the read write flags match reasonably.  O_LARGEFILE
- *?  is irrelevant because largefile support is always used
- *?  by this client. Flags O_APPEND, O_DIRECT, O_DIRECTORY,
- *       O_FASYNC, O_NOFOLLOW, O_NONBLOCK need further investigation
- *********************************************************************/
-
-        disposition = cifs_get_disposition(file->f_flags);
-
-        /* BB pass O_SYNC flag through on file attributes .. BB */
-
-        /* Also refresh inode by passing in file_info buf returned by SMBOpen
-           and calling get_inode_info with returned buf (at least helps
-           non-Unix server case) */
-
-        /* BB we can not do this if this is the second open of a file
-           and the first handle has writebehind data, we might be
-           able to simply do a filemap_fdatawrite/filemap_fdatawait first */
-        buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
-        if (!buf) {
-                rc = -ENOMEM;
-                goto out;
-        }
-
-        if (tcon->ses->capabilities & CAP_NT_SMBS)
-                rc = CIFSSMBOpen(xid, tcon, full_path, disposition,
-                         desiredAccess, CREATE_NOT_DIR, &netfid, &oplock, buf,
-                         cifs_sb->local_nls, cifs_sb->mnt_cifs_flags
-                                 & CIFS_MOUNT_MAP_SPECIAL_CHR);
-        else
-                rc = -EIO; /* no NT SMB support fall into legacy open below */
-
-        if (rc == -EIO) {
-                /* Old server, try legacy style OpenX */
-                rc = SMBLegacyOpen(xid, tcon, full_path, disposition,
-                        desiredAccess, CREATE_NOT_DIR, &netfid, &oplock, buf,
-                        cifs_sb->local_nls, cifs_sb->mnt_cifs_flags
-                                & CIFS_MOUNT_MAP_SPECIAL_CHR);
-        }
-        if (rc) {
-                cFYI(1, "cifs_open returned 0x%x", rc);
-                goto out;
+        if (!posix_open_ok) {
+                rc = cifs_nt_open(full_path, inode, cifs_sb, tcon,
+                                  file->f_flags, &oplock, &netfid, xid);
+                if (rc)
+                        goto out;
         }
 
-        rc = cifs_open_inode_helper(inode, tcon, oplock, buf, full_path, xid);
-        if (rc != 0)
-                goto out;
-
         pCifsFile = cifs_new_fileinfo(netfid, file, tlink, oplock);
         if (pCifsFile == NULL) {
+                CIFSSMBClose(xid, tcon, netfid);
                 rc = -ENOMEM;
                 goto out;
         }
 
         cifs_fscache_set_inode_cookie(inode, file);
 
-        if (oplock & CIFS_CREATE_ACTION) {
+        if ((oplock & CIFS_CREATE_ACTION) && !posix_open_ok && tcon->unix_ext) {
                 /* time to set mode which we can not set earlier due to
                    problems creating new read-only files */
-                if (tcon->unix_ext) {
-                        struct cifs_unix_set_info_args args = {
-                                .mode   = inode->i_mode,
-                                .uid    = NO_CHANGE_64,
-                                .gid    = NO_CHANGE_64,
-                                .ctime  = NO_CHANGE_64,
-                                .atime  = NO_CHANGE_64,
-                                .mtime  = NO_CHANGE_64,
-                                .device = 0,
-                        };
-                        CIFSSMBUnixSetPathInfo(xid, tcon, full_path, &args,
-                                               cifs_sb->local_nls,
-                                               cifs_sb->mnt_cifs_flags &
-                                                CIFS_MOUNT_MAP_SPECIAL_CHR);
-                }
+                struct cifs_unix_set_info_args args = {
+                        .mode   = inode->i_mode,
+                        .uid    = NO_CHANGE_64,
+                        .gid    = NO_CHANGE_64,
+                        .ctime  = NO_CHANGE_64,
+                        .atime  = NO_CHANGE_64,
+                        .mtime  = NO_CHANGE_64,
+                        .device = 0,
+                };
+                CIFSSMBUnixSetFileInfo(xid, tcon, &args, netfid,
+                                        pCifsFile->pid);
         }
 
 out:
-        kfree(buf);
         kfree(full_path);
         FreeXid(xid);
         cifs_put_tlink(tlink);
@@ -1108,7 +1055,6 @@ static ssize_t cifs_write(struct cifsFileInfo *open_file,
         return total_written;
 }
 
-#ifdef CONFIG_CIFS_EXPERIMENTAL
 struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
                                         bool fsuid_only)
 {
@@ -1142,7 +1088,6 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
         spin_unlock(&cifs_file_list_lock);
         return NULL;
 }
-#endif
 
 struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode,
                                         bool fsuid_only)
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 28cb6e735943..0c7e36910e31 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -518,6 +518,7 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info,
 
         fattr->cf_eof = le64_to_cpu(info->EndOfFile);
         fattr->cf_bytes = le64_to_cpu(info->AllocationSize);
+        fattr->cf_createtime = le64_to_cpu(info->CreationTime);
 
         if (fattr->cf_cifsattrs & ATTR_DIRECTORY) {
                 fattr->cf_mode = S_IFDIR | cifs_sb->mnt_dir_mode;
@@ -686,7 +687,7 @@ int cifs_get_inode_info(struct inode **pinode,
                         cFYI(1, "cifs_sfu_type failed: %d", tmprc);
         }
 
-#ifdef CONFIG_CIFS_EXPERIMENTAL
+#ifdef CONFIG_CIFS_ACL
         /* fill in 0777 bits from ACL */
         if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) {
                 rc = cifs_acl_to_fattr(cifs_sb, &fattr, *pinode, full_path,
@@ -697,7 +698,7 @@ int cifs_get_inode_info(struct inode **pinode,
                         goto cgii_exit;
                 }
         }
-#endif
+#endif /* CONFIG_CIFS_ACL */
 
         /* fill in remaining high mode bits e.g. SUID, VTX */
         if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)
@@ -728,12 +729,12 @@ static const struct inode_operations cifs_ipc_inode_ops = {
         .lookup = cifs_lookup,
 };
 
-char *cifs_build_path_to_root(struct cifs_sb_info *cifs_sb)
+char *cifs_build_path_to_root(struct cifs_sb_info *cifs_sb,
+                                struct cifsTconInfo *tcon)
 {
         int pplen = cifs_sb->prepathlen;
         int dfsplen;
         char *full_path = NULL;
-        struct cifsTconInfo *tcon = cifs_sb_master_tcon(cifs_sb);
 
         /* if no prefix path, simply set path to the root of share to "" */
         if (pplen == 0) {
@@ -779,6 +780,10 @@ cifs_find_inode(struct inode *inode, void *opaque)
         if (CIFS_I(inode)->uniqueid != fattr->cf_uniqueid)
                 return 0;
 
+        /* use createtime like an i_generation field */
+        if (CIFS_I(inode)->createtime != fattr->cf_createtime)
+                return 0;
+
         /* don't match inode of different type */
         if ((inode->i_mode & S_IFMT) != (fattr->cf_mode & S_IFMT))
                 return 0;
@@ -796,6 +801,7 @@ cifs_init_inode(struct inode *inode, void *opaque)
         struct cifs_fattr *fattr = (struct cifs_fattr *) opaque;
 
         CIFS_I(inode)->uniqueid = fattr->cf_uniqueid;
+        CIFS_I(inode)->createtime = fattr->cf_createtime;
         return 0;
 }
 
@@ -809,14 +815,14 @@ inode_has_hashed_dentries(struct inode *inode)
 {
         struct dentry *dentry;
 
-        spin_lock(&dcache_lock);
+        spin_lock(&inode->i_lock);
         list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
                 if (!d_unhashed(dentry) || IS_ROOT(dentry)) {
-                        spin_unlock(&dcache_lock);
+                        spin_unlock(&inode->i_lock);
                         return true;
                 }
         }
-        spin_unlock(&dcache_lock);
+        spin_unlock(&inode->i_lock);
         return false;
 }
 
@@ -875,7 +881,7 @@ struct inode *cifs_root_iget(struct super_block *sb, unsigned long ino)
         char *full_path;
         struct cifsTconInfo *tcon = cifs_sb_master_tcon(cifs_sb);
 
-        full_path = cifs_build_path_to_root(cifs_sb);
+        full_path = cifs_build_path_to_root(cifs_sb, tcon);
         if (full_path == NULL)
                 return ERR_PTR(-ENOMEM);
 
@@ -1319,9 +1325,9 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode)
         to set uid/gid */
                         inc_nlink(inode);
                         if (pTcon->nocase)
-                                direntry->d_op = &cifs_ci_dentry_ops;
+                                d_set_d_op(direntry, &cifs_ci_dentry_ops);
                         else
-                                direntry->d_op = &cifs_dentry_ops;
+                                d_set_d_op(direntry, &cifs_dentry_ops);
 
                         cifs_unix_basic_to_fattr(&fattr, pInfo, cifs_sb);
                         cifs_fill_uniqueid(inode->i_sb, &fattr);
@@ -1363,9 +1369,9 @@ mkdir_get_info:
                                                  inode->i_sb, xid, NULL);
 
                 if (pTcon->nocase)
-                        direntry->d_op = &cifs_ci_dentry_ops;
+                        d_set_d_op(direntry, &cifs_ci_dentry_ops);
                 else
-                        direntry->d_op = &cifs_dentry_ops;
+                        d_set_d_op(direntry, &cifs_dentry_ops);
                 d_instantiate(direntry, newinode);
                  /* setting nlink not necessary except in cases where we
                   * failed to get it from the server or was set bogus */
@@ -1653,6 +1659,7 @@ static bool
 cifs_inode_needs_reval(struct inode *inode)
 {
         struct cifsInodeInfo *cifs_i = CIFS_I(inode);
+        struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 
         if (cifs_i->clientCanCacheRead)
                 return false;
@@ -1663,12 +1670,12 @@ cifs_inode_needs_reval(struct inode *inode)
         if (cifs_i->time == 0)
                 return true;
 
-        /* FIXME: the actimeo should be tunable */
-        if (time_after_eq(jiffies, cifs_i->time + HZ))
+        if (!time_in_range(jiffies, cifs_i->time,
+                                cifs_i->time + cifs_sb->actimeo))
                 return true;
 
         /* hardlinked files w/ noserverino get "special" treatment */
-        if (!(CIFS_SB(inode->i_sb)->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) &&
+        if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) &&
             S_ISREG(inode->i_mode) && inode->i_nlink != 1)
                 return true;
 
@@ -2121,7 +2128,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 
         if (attrs->ia_valid & ATTR_MODE) {
                 rc = 0;
-#ifdef CONFIG_CIFS_EXPERIMENTAL
+#ifdef CONFIG_CIFS_ACL
                 if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) {
                         rc = mode_to_cifs_acl(inode, full_path, mode);
                         if (rc) {
@@ -2130,7 +2137,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
                                 goto cifs_setattr_exit;
                         }
                 } else
-#endif
+#endif /* CONFIG_CIFS_ACL */
                 if (((mode & S_IWUGO) == 0) &&
                     (cifsInode->cifsAttrs & ATTR_READONLY) == 0) {
 
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index 85cdbf831e7b..fe2f6a93c49e 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -525,9 +525,9 @@ cifs_symlink(struct inode *inode, struct dentry *direntry, const char *symname)
                               rc);
                 } else {
                         if (pTcon->nocase)
-                                direntry->d_op = &cifs_ci_dentry_ops;
+                                d_set_d_op(direntry, &cifs_ci_dentry_ops);
                         else
-                                direntry->d_op = &cifs_dentry_ops;
+                                d_set_d_op(direntry, &cifs_dentry_ops);
                         d_instantiate(direntry, newinode);
                 }
         }
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 32d300e8f20e..76b1b37c9e6b 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -79,7 +79,7 @@ cifs_readdir_lookup(struct dentry *parent, struct qstr *name,
         cFYI(1, "For %s", name->name);
 
         if (parent->d_op && parent->d_op->d_hash)
-                parent->d_op->d_hash(parent, name);
+                parent->d_op->d_hash(parent, parent->d_inode, name);
         else
                 name->hash = full_name_hash(name->name, name->len);
 
@@ -103,9 +103,9 @@ cifs_readdir_lookup(struct dentry *parent, struct qstr *name,
         }
 
         if (cifs_sb_master_tcon(CIFS_SB(sb))->nocase)
-                dentry->d_op = &cifs_ci_dentry_ops;
+                d_set_d_op(dentry, &cifs_ci_dentry_ops);
         else
-                dentry->d_op = &cifs_dentry_ops;
+                d_set_d_op(dentry, &cifs_dentry_ops);
 
         alias = d_materialise_unique(dentry, inode);
         if (alias != NULL) {
@@ -160,6 +160,7 @@ cifs_dir_info_to_fattr(struct cifs_fattr *fattr, FILE_DIRECTORY_INFO *info,
         fattr->cf_cifsattrs = le32_to_cpu(info->ExtFileAttributes);
         fattr->cf_eof = le64_to_cpu(info->EndOfFile);
         fattr->cf_bytes = le64_to_cpu(info->AllocationSize);
+        fattr->cf_createtime = le64_to_cpu(info->CreationTime);
         fattr->cf_atime = cifs_NTtimeToUnix(info->LastAccessTime);
         fattr->cf_ctime = cifs_NTtimeToUnix(info->ChangeTime);
         fattr->cf_mtime = cifs_NTtimeToUnix(info->LastWriteTime);
@@ -759,18 +760,6 @@ static int cifs_filldir(char *pfindEntry, struct file *file, filldir_t filldir,
         rc = filldir(direntry, qstring.name, qstring.len, file->f_pos,
                      ino, fattr.cf_dtype);
 
-        /*
-         * we can not return filldir errors to the caller since they are
-         * "normal" when the stat blocksize is too small - we return remapped
-         * error instead
-         *
-         * FIXME: This looks bogus. filldir returns -EOVERFLOW in the above
-         * case already. Why should we be clobbering other errors from it?
-         */
-        if (rc) {
-                cFYI(1, "filldir rc = %d", rc);
-                rc = -EOVERFLOW;
-        }
         dput(tmp_dentry);
         return rc;
 }
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 7b01d3f6eed6..eb746486e49e 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -420,7 +420,6 @@ static int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len,
         return 0;
 }
 
-#ifdef CONFIG_CIFS_EXPERIMENTAL
 /* BB Move to ntlmssp.c eventually */
 
 /* We do not malloc the blob, it is passed in pbuffer, because
@@ -431,13 +430,14 @@ static void build_ntlmssp_negotiate_blob(unsigned char *pbuffer,
         NEGOTIATE_MESSAGE *sec_blob = (NEGOTIATE_MESSAGE *)pbuffer;
         __u32 flags;
 
+        memset(pbuffer, 0, sizeof(NEGOTIATE_MESSAGE));
         memcpy(sec_blob->Signature, NTLMSSP_SIGNATURE, 8);
         sec_blob->MessageType = NtLmNegotiate;
 
         /* BB is NTLMV2 session security format easier to use here? */
         flags = NTLMSSP_NEGOTIATE_56 |  NTLMSSP_REQUEST_TARGET |
                 NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE |
-                NTLMSSP_NEGOTIATE_NTLM;
+                NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC;
         if (ses->server->secMode &
                         (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) {
                 flags |= NTLMSSP_NEGOTIATE_SIGN;
@@ -446,7 +446,7 @@ static void build_ntlmssp_negotiate_blob(unsigned char *pbuffer,
                                 NTLMSSP_NEGOTIATE_EXTENDED_SEC;
         }
 
-        sec_blob->NegotiateFlags |= cpu_to_le32(flags);
+        sec_blob->NegotiateFlags = cpu_to_le32(flags);
 
         sec_blob->WorkstationName.BufferOffset = 0;
         sec_blob->WorkstationName.Length = 0;
@@ -477,7 +477,7 @@ static int build_ntlmssp_auth_blob(unsigned char *pbuffer,
         flags = NTLMSSP_NEGOTIATE_56 |
                 NTLMSSP_REQUEST_TARGET | NTLMSSP_NEGOTIATE_TARGET_INFO |
                 NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE |
-                NTLMSSP_NEGOTIATE_NTLM;
+                NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC;
         if (ses->server->secMode &
            (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
                 flags |= NTLMSSP_NEGOTIATE_SIGN;
@@ -485,7 +485,7 @@ static int build_ntlmssp_auth_blob(unsigned char *pbuffer,
                 flags |= NTLMSSP_NEGOTIATE_ALWAYS_SIGN;
 
         tmp = pbuffer + sizeof(AUTHENTICATE_MESSAGE);
-        sec_blob->NegotiateFlags |= cpu_to_le32(flags);
+        sec_blob->NegotiateFlags = cpu_to_le32(flags);
 
         sec_blob->LmChallengeResponse.BufferOffset =
                                 cpu_to_le32(sizeof(AUTHENTICATE_MESSAGE));
@@ -544,8 +544,9 @@ static int build_ntlmssp_auth_blob(unsigned char *pbuffer,
         sec_blob->WorkstationName.MaximumLength = 0;
         tmp += 2;
 
-        if ((ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_KEY_XCH) &&
-                        !calc_seckey(ses)) {
+        if (((ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_KEY_XCH) ||
+                (ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_EXTENDED_SEC))
+                        && !calc_seckey(ses)) {
                 memcpy(tmp, ses->ntlmssp->ciphertext, CIFS_CPHTXT_SIZE);
                 sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - pbuffer);
                 sec_blob->SessionKey.Length = cpu_to_le16(CIFS_CPHTXT_SIZE);
@@ -563,17 +564,6 @@ setup_ntlmv2_ret:
         return rc;
 }
 
-
-static void setup_ntlmssp_neg_req(SESSION_SETUP_ANDX *pSMB,
-                                 struct cifsSesInfo *ses)
-{
-        build_ntlmssp_negotiate_blob(&pSMB->req.SecurityBlob[0], ses);
-        pSMB->req.SecurityBlobLength = cpu_to_le16(sizeof(NEGOTIATE_MESSAGE));
-
-        return;
-}
-#endif
-
 int
 CIFS_SessSetup(unsigned int xid, struct cifsSesInfo *ses,
                const struct nls_table *nls_cp)
@@ -814,71 +804,70 @@ ssetup_ntlmssp_authenticate:
                 rc = -ENOSYS;
                 goto ssetup_exit;
 #endif /* CONFIG_CIFS_UPCALL */
-        } else {
-#ifdef CONFIG_CIFS_EXPERIMENTAL
-                if (type == RawNTLMSSP) {
-                        if ((pSMB->req.hdr.Flags2 & SMBFLG2_UNICODE) == 0) {
-                                cERROR(1, "NTLMSSP requires Unicode support");
-                                rc = -ENOSYS;
+        } else if (type == RawNTLMSSP) {
+                if ((pSMB->req.hdr.Flags2 & SMBFLG2_UNICODE) == 0) {
+                        cERROR(1, "NTLMSSP requires Unicode support");
+                        rc = -ENOSYS;
+                        goto ssetup_exit;
+                }
+
+                cFYI(1, "ntlmssp session setup phase %d", phase);
+                pSMB->req.hdr.Flags2 |= SMBFLG2_EXT_SEC;
+                capabilities |= CAP_EXTENDED_SECURITY;
+                pSMB->req.Capabilities |= cpu_to_le32(capabilities);
+                switch(phase) {
+                case NtLmNegotiate:
+                        build_ntlmssp_negotiate_blob(
+                                pSMB->req.SecurityBlob, ses);
+                        iov[1].iov_len = sizeof(NEGOTIATE_MESSAGE);
+                        iov[1].iov_base = pSMB->req.SecurityBlob;
+                        pSMB->req.SecurityBlobLength =
+                                cpu_to_le16(sizeof(NEGOTIATE_MESSAGE));
+                        break;
+                case NtLmAuthenticate:
+                        /*
+                         * 5 is an empirical value, large enough to hold
+                         * authenticate message plus max 10 of av paris,
+                         * domain, user, workstation names, flags, etc.
+                         */
+                        ntlmsspblob = kzalloc(
+                                5*sizeof(struct _AUTHENTICATE_MESSAGE),
+                                GFP_KERNEL);
+                        if (!ntlmsspblob) {
+                                cERROR(1, "Can't allocate NTLMSSP blob");
+                                rc = -ENOMEM;
                                 goto ssetup_exit;
                         }
 
-                        cFYI(1, "ntlmssp session setup phase %d", phase);
-                        pSMB->req.hdr.Flags2 |= SMBFLG2_EXT_SEC;
-                        capabilities |= CAP_EXTENDED_SECURITY;
-                        pSMB->req.Capabilities |= cpu_to_le32(capabilities);
-                        if (phase == NtLmNegotiate) {
-                                setup_ntlmssp_neg_req(pSMB, ses);
-                                iov[1].iov_len = sizeof(NEGOTIATE_MESSAGE);
-                                iov[1].iov_base = &pSMB->req.SecurityBlob[0];
-                        } else if (phase == NtLmAuthenticate) {
-                                /* 5 is an empirical value, large enought to
-                                 * hold authenticate message, max 10 of
-                                 * av paris, doamin,user,workstation mames,
-                                 * flags etc..
-                                 */
-                                ntlmsspblob = kmalloc(
-                                        5*sizeof(struct _AUTHENTICATE_MESSAGE),
-                                        GFP_KERNEL);
-                                if (!ntlmsspblob) {
-                                        cERROR(1, "Can't allocate NTLMSSP");
-                                        rc = -ENOMEM;
-                                        goto ssetup_exit;
-                                }
-
-                                rc = build_ntlmssp_auth_blob(ntlmsspblob,
-                                                        &blob_len, ses, nls_cp);
-                                if (rc)
-                                        goto ssetup_exit;
-                                iov[1].iov_len = blob_len;
-                                iov[1].iov_base = ntlmsspblob;
-                                pSMB->req.SecurityBlobLength =
-                                        cpu_to_le16(blob_len);
-                                /* Make sure that we tell the server that we
-                                   are using the uid that it just gave us back
-                                   on the response (challenge) */
-                                smb_buf->Uid = ses->Suid;
-                        } else {
-                                cERROR(1, "invalid phase %d", phase);
-                                rc = -ENOSYS;
+                        rc = build_ntlmssp_auth_blob(ntlmsspblob,
+                                                &blob_len, ses, nls_cp);
+                        if (rc)
                                 goto ssetup_exit;
-                        }
-                        /* unicode strings must be word aligned */
-                        if ((iov[0].iov_len + iov[1].iov_len) % 2) {
-                                *bcc_ptr = 0;
-                                bcc_ptr++;
-                        }
-                        unicode_oslm_strings(&bcc_ptr, nls_cp);
-                } else {
-                        cERROR(1, "secType %d not supported!", type);
+                        iov[1].iov_len = blob_len;
+                        iov[1].iov_base = ntlmsspblob;
+                        pSMB->req.SecurityBlobLength = cpu_to_le16(blob_len);
+                        /*
+                         * Make sure that we tell the server that we are using
+                         * the uid that it just gave us back on the response
+                         * (challenge)
+                         */
+                        smb_buf->Uid = ses->Suid;
+                        break;
+                default:
+                        cERROR(1, "invalid phase %d", phase);
                         rc = -ENOSYS;
                         goto ssetup_exit;
                 }
-#else
+                /* unicode strings must be word aligned */
+                if ((iov[0].iov_len + iov[1].iov_len) % 2) {
+                        *bcc_ptr = 0;
+                        bcc_ptr++;
+                }
+                unicode_oslm_strings(&bcc_ptr, nls_cp);
+        } else {
                 cERROR(1, "secType %d not supported!", type);
                 rc = -ENOSYS;
                 goto ssetup_exit;
-#endif
         }
 
         iov[2].iov_base = str_area;
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index e0588cdf4cc5..59ca81b16919 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -119,7 +119,7 @@ smb_sendv(struct TCP_Server_Info *server, struct kvec *iov, int n_vec)
         if (ssocket == NULL)
                 return -ENOTSOCK; /* BB eventually add reconnect code here */
 
-        smb_msg.msg_name = (struct sockaddr *) &server->addr.sockAddr;
+        smb_msg.msg_name = (struct sockaddr *) &server->dstaddr;
         smb_msg.msg_namelen = sizeof(struct sockaddr);
         smb_msg.msg_control = NULL;
         smb_msg.msg_controllen = 0;
diff --git a/fs/coda/cache.c b/fs/coda/cache.c
index 9060f08e70cf..5525e1c660fd 100644
--- a/fs/coda/cache.c
+++ b/fs/coda/cache.c
@@ -93,7 +93,7 @@ static void coda_flag_children(struct dentry *parent, int flag)
         struct list_head *child;
         struct dentry *de;
 
-        spin_lock(&dcache_lock);
+        spin_lock(&parent->d_lock);
         list_for_each(child, &parent->d_subdirs)
         {
                 de = list_entry(child, struct dentry, d_u.d_child);
@@ -102,7 +102,7 @@ static void coda_flag_children(struct dentry *parent, int flag)
                         continue;
                 coda_flag_inode(de->d_inode, flag);
         }
-        spin_unlock(&dcache_lock);
+        spin_unlock(&parent->d_lock);
         return; 
 }
 
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index 5d8b35539601..29badd91360f 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -18,6 +18,7 @@
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/spinlock.h>
+#include <linux/namei.h>
 
 #include <asm/uaccess.h>
 
@@ -47,7 +48,7 @@ static int coda_readdir(struct file *file, void *buf, filldir_t filldir);
 
 /* dentry ops */
 static int coda_dentry_revalidate(struct dentry *de, struct nameidata *nd);
-static int coda_dentry_delete(struct dentry *);
+static int coda_dentry_delete(const struct dentry *);
 
 /* support routines */
 static int coda_venus_readdir(struct file *coda_file, void *buf,
@@ -125,7 +126,7 @@ static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, struc
                 return ERR_PTR(error);
 
 exit:
-        entry->d_op = &coda_dentry_operations;
+        d_set_d_op(entry, &coda_dentry_operations);
 
         if (inode && (type & CODA_NOCACHE))
                 coda_flag_inode(inode, C_VATTR | C_PURGE);
@@ -134,10 +135,13 @@ exit:
 }
 
 
-int coda_permission(struct inode *inode, int mask)
+int coda_permission(struct inode *inode, int mask, unsigned int flags)
 {
         int error;
 
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
         mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
  
         if (!mask)
@@ -541,9 +545,13 @@ out:
 /* called when a cache lookup succeeds */
 static int coda_dentry_revalidate(struct dentry *de, struct nameidata *nd)
 {
-        struct inode *inode = de->d_inode;
+        struct inode *inode;
         struct coda_inode_info *cii;
 
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
+
+        inode = de->d_inode;
         if (!inode || coda_isroot(inode))
                 goto out;
         if (is_bad_inode(inode))
@@ -559,7 +567,7 @@ static int coda_dentry_revalidate(struct dentry *de, struct nameidata *nd)
         if (cii->c_flags & C_FLUSH) 
                 coda_flag_inode_children(inode, C_FLUSH);
 
-        if (atomic_read(&de->d_count) > 1)
+        if (de->d_count > 1)
                 /* pretend it's valid, but don't change the flags */
                 goto out;
 
@@ -577,7 +585,7 @@ out:
  * This is the callback from dput() when d_count is going to 0.
  * We use this to unhash dentries with bad inodes.
  */
-static int coda_dentry_delete(struct dentry * dentry)
+static int coda_dentry_delete(const struct dentry * dentry)
 {
         int flags;
 
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index 5ea57c8c7f97..50dc7d189f56 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -56,11 +56,18 @@ static struct inode *coda_alloc_inode(struct super_block *sb)
         return &ei->vfs_inode;
 }
 
-static void coda_destroy_inode(struct inode *inode)
+static void coda_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(coda_inode_cachep, ITOC(inode));
 }
 
+static void coda_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, coda_i_callback);
+}
+
 static void init_once(void *foo)
 {
         struct coda_inode_info *ei = (struct coda_inode_info *) foo;
diff --git a/fs/coda/pioctl.c b/fs/coda/pioctl.c
index 2fd89b5c5c7b..741f0bd03918 100644
--- a/fs/coda/pioctl.c
+++ b/fs/coda/pioctl.c
@@ -24,7 +24,7 @@
 #include <linux/coda_psdev.h>
 
 /* pioctl ops */
-static int coda_ioctl_permission(struct inode *inode, int mask);
+static int coda_ioctl_permission(struct inode *inode, int mask, unsigned int flags);
 static long coda_pioctl(struct file *filp, unsigned int cmd,
                         unsigned long user_data);
 
@@ -41,8 +41,10 @@ const struct file_operations coda_ioctl_operations = {
 };
 
 /* the coda pioctl inode ops */
-static int coda_ioctl_permission(struct inode *inode, int mask)
+static int coda_ioctl_permission(struct inode *inode, int mask, unsigned int flags)
 {
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
         return (mask & MAY_EXEC) ? -EACCES : 0;
 }
 
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index a60579b007b0..61abb638b4bf 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -42,7 +42,7 @@
 #include <linux/tty.h>
 #include <linux/vt_kern.h>
 #include <linux/fb.h>
-#include <linux/videodev.h>
+#include <linux/videodev2.h>
 #include <linux/netdevice.h>
 #include <linux/raw.h>
 #include <linux/blkdev.h>
@@ -836,6 +836,7 @@ COMPATIBLE_IOCTL(TCSETSW)
 COMPATIBLE_IOCTL(TCSETSF)
 COMPATIBLE_IOCTL(TIOCLINUX)
 COMPATIBLE_IOCTL(TIOCSBRK)
+COMPATIBLE_IOCTL(TIOCGDEV)
 COMPATIBLE_IOCTL(TIOCCBRK)
 COMPATIBLE_IOCTL(TIOCGSID)
 COMPATIBLE_IOCTL(TIOCGICOUNT)
diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h
index da6061a6df40..026cf68553a4 100644
--- a/fs/configfs/configfs_internal.h
+++ b/fs/configfs/configfs_internal.h
@@ -120,7 +120,7 @@ static inline struct config_item *configfs_get_config_item(struct dentry *dentry
 {
         struct config_item * item = NULL;
 
-        spin_lock(&dcache_lock);
+        spin_lock(&dentry->d_lock);
         if (!d_unhashed(dentry)) {
                 struct configfs_dirent * sd = dentry->d_fsdata;
                 if (sd->s_type & CONFIGFS_ITEM_LINK) {
@@ -129,7 +129,7 @@ static inline struct config_item *configfs_get_config_item(struct dentry *dentry
                 } else
                         item = config_item_get(sd->s_element);
         }
-        spin_unlock(&dcache_lock);
+        spin_unlock(&dentry->d_lock);
 
         return item;
 }
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 0b502f80c691..36637a8c1ed3 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -67,7 +67,7 @@ static void configfs_d_iput(struct dentry * dentry,
  * We _must_ delete our dentries on last dput, as the chain-to-parent
  * behavior is required to clear the parents of default_groups.
  */
-static int configfs_d_delete(struct dentry *dentry)
+static int configfs_d_delete(const struct dentry *dentry)
 {
         return 1;
 }
@@ -232,10 +232,8 @@ int configfs_make_dirent(struct configfs_dirent * parent_sd,
 
         sd->s_mode = mode;
         sd->s_dentry = dentry;
-        if (dentry) {
+        if (dentry)
                 dentry->d_fsdata = configfs_get(sd);
-                dentry->d_op = &configfs_dentry_ops;
-        }
 
         return 0;
 }
@@ -278,7 +276,6 @@ static int create_dir(struct config_item * k, struct dentry * p,
                 error = configfs_create(d, mode, init_dir);
                 if (!error) {
                         inc_nlink(p->d_inode);
-                        (d)->d_op = &configfs_dentry_ops;
                 } else {
                         struct configfs_dirent *sd = d->d_fsdata;
                         if (sd) {
@@ -371,9 +368,7 @@ int configfs_create_link(struct configfs_symlink *sl,
                                    CONFIGFS_ITEM_LINK);
         if (!err) {
                 err = configfs_create(dentry, mode, init_symlink);
-                if (!err)
-                        dentry->d_op = &configfs_dentry_ops;
-                else {
+                if (err) {
                         struct configfs_dirent *sd = dentry->d_fsdata;
                         if (sd) {
                                 spin_lock(&configfs_dirent_lock);
@@ -399,8 +394,7 @@ static void remove_dir(struct dentry * d)
         if (d->d_inode)
                 simple_rmdir(parent->d_inode,d);
 
-        pr_debug(" o %s removing done (%d)\n",d->d_name.name,
-                 atomic_read(&d->d_count));
+        pr_debug(" o %s removing done (%d)\n",d->d_name.name, d->d_count);
 
         dput(parent);
 }
@@ -448,7 +442,7 @@ static int configfs_attach_attr(struct configfs_dirent * sd, struct dentry * den
                 return error;
         }
 
-        dentry->d_op = &configfs_dentry_ops;
+        d_set_d_op(dentry, &configfs_dentry_ops);
         d_rehash(dentry);
 
         return 0;
@@ -493,7 +487,11 @@ static struct dentry * configfs_lookup(struct inode *dir,
                  * If it doesn't exist and it isn't a NOT_PINNED item,
                  * it must be negative.
                  */
-                return simple_lookup(dir, dentry, nd);
+                if (dentry->d_name.len > NAME_MAX)
+                        return ERR_PTR(-ENAMETOOLONG);
+                d_set_d_op(dentry, &configfs_dentry_ops);
+                d_add(dentry, NULL);
+                return NULL;
         }
 
 out:
@@ -685,6 +683,7 @@ static int create_default_group(struct config_group *parent_group,
         ret = -ENOMEM;
         child = d_alloc(parent, &name);
         if (child) {
+                d_set_d_op(child, &configfs_dentry_ops);
                 d_add(child, NULL);
 
                 ret = configfs_attach_group(&parent_group->cg_item,
@@ -1682,6 +1681,7 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys)
         err = -ENOMEM;
         dentry = d_alloc(configfs_sb->s_root, &name);
         if (dentry) {
+                d_set_d_op(dentry, &configfs_dentry_ops);
                 d_add(dentry, NULL);
 
                 err = configfs_attach_group(sd->s_element, &group->cg_item,
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 253476d78ed8..c83f4768eeaa 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -250,18 +250,14 @@ void configfs_drop_dentry(struct configfs_dirent * sd, struct dentry * parent)
         struct dentry * dentry = sd->s_dentry;
 
         if (dentry) {
-                spin_lock(&dcache_lock);
                 spin_lock(&dentry->d_lock);
                 if (!(d_unhashed(dentry) && dentry->d_inode)) {
-                        dget_locked(dentry);
+                        dget_dlock(dentry);
                         __d_drop(dentry);
                         spin_unlock(&dentry->d_lock);
-                        spin_unlock(&dcache_lock);
                         simple_unlink(parent->d_inode, dentry);
-                } else {
+                } else
                         spin_unlock(&dentry->d_lock);
-                        spin_unlock(&dcache_lock);
-                }
         }
 }
 
diff --git a/fs/dcache.c b/fs/dcache.c
index 23702a9d4e6d..5699d4c027cb 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -33,20 +33,58 @@
 #include <linux/bootmem.h>
 #include <linux/fs_struct.h>
 #include <linux/hardirq.h>
+#include <linux/bit_spinlock.h>
+#include <linux/rculist_bl.h>
 #include "internal.h"
 
+/*
+ * Usage:
+ * dcache->d_inode->i_lock protects:
+ *   - i_dentry, d_alias, d_inode of aliases
+ * dcache_hash_bucket lock protects:
+ *   - the dcache hash table
+ * s_anon bl list spinlock protects:
+ *   - the s_anon list (see __d_drop)
+ * dcache_lru_lock protects:
+ *   - the dcache lru lists and counters
+ * d_lock protects:
+ *   - d_flags
+ *   - d_name
+ *   - d_lru
+ *   - d_count
+ *   - d_unhashed()
+ *   - d_parent and d_subdirs
+ *   - childrens' d_child and d_parent
+ *   - d_alias, d_inode
+ *
+ * Ordering:
+ * dentry->d_inode->i_lock
+ *   dentry->d_lock
+ *     dcache_lru_lock
+ *     dcache_hash_bucket lock
+ *     s_anon lock
+ *
+ * If there is an ancestor relationship:
+ * dentry->d_parent->...->d_parent->d_lock
+ *   ...
+ *     dentry->d_parent->d_lock
+ *       dentry->d_lock
+ *
+ * If no ancestor relationship:
+ * if (dentry1 < dentry2)
+ *   dentry1->d_lock
+ *     dentry2->d_lock
+ */
 int sysctl_vfs_cache_pressure __read_mostly = 100;
 EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure);
 
- __cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_lock);
+static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_lru_lock);
 __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock);
 
-EXPORT_SYMBOL(dcache_lock);
+EXPORT_SYMBOL(rename_lock);
 
 static struct kmem_cache *dentry_cache __read_mostly;
 
-#define DNAME_INLINE_LEN (sizeof(struct dentry)-offsetof(struct dentry,d_iname))
-
 /*
  * This is the single most critical data structure when it comes
  * to the dcache: the hashtable for lookups. Somebody should try
@@ -60,22 +98,51 @@ static struct kmem_cache *dentry_cache __read_mostly;
 
 static unsigned int d_hash_mask __read_mostly;
 static unsigned int d_hash_shift __read_mostly;
-static struct hlist_head *dentry_hashtable __read_mostly;
+
+struct dcache_hash_bucket {
+        struct hlist_bl_head head;
+};
+static struct dcache_hash_bucket *dentry_hashtable __read_mostly;
+
+static inline struct dcache_hash_bucket *d_hash(struct dentry *parent,
+                                        unsigned long hash)
+{
+        hash += ((unsigned long) parent ^ GOLDEN_RATIO_PRIME) / L1_CACHE_BYTES;
+        hash = hash ^ ((hash ^ GOLDEN_RATIO_PRIME) >> D_HASHBITS);
+        return dentry_hashtable + (hash & D_HASHMASK);
+}
+
+static inline void spin_lock_bucket(struct dcache_hash_bucket *b)
+{
+        bit_spin_lock(0, (unsigned long *)&b->head.first);
+}
+
+static inline void spin_unlock_bucket(struct dcache_hash_bucket *b)
+{
+        __bit_spin_unlock(0, (unsigned long *)&b->head.first);
+}
 
 /* Statistics gathering. */
 struct dentry_stat_t dentry_stat = {
         .age_limit = 45,
 };
 
-static struct percpu_counter nr_dentry __cacheline_aligned_in_smp;
-static struct percpu_counter nr_dentry_unused __cacheline_aligned_in_smp;
+static DEFINE_PER_CPU(unsigned int, nr_dentry);
 
 #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
+static int get_nr_dentry(void)
+{
+        int i;
+        int sum = 0;
+        for_each_possible_cpu(i)
+                sum += per_cpu(nr_dentry, i);
+        return sum < 0 ? 0 : sum;
+}
+
 int proc_nr_dentry(ctl_table *table, int write, void __user *buffer,
                    size_t *lenp, loff_t *ppos)
 {
-        dentry_stat.nr_dentry = percpu_counter_sum_positive(&nr_dentry);
-        dentry_stat.nr_unused = percpu_counter_sum_positive(&nr_dentry_unused);
+        dentry_stat.nr_dentry = get_nr_dentry();
         return proc_dointvec(table, write, buffer, lenp, ppos);
 }
 #endif
@@ -91,35 +158,50 @@ static void __d_free(struct rcu_head *head)
 }
 
 /*
- * no dcache_lock, please.
+ * no locks, please.
  */
 static void d_free(struct dentry *dentry)
 {
-        percpu_counter_dec(&nr_dentry);
+        BUG_ON(dentry->d_count);
+        this_cpu_dec(nr_dentry);
         if (dentry->d_op && dentry->d_op->d_release)
                 dentry->d_op->d_release(dentry);
 
         /* if dentry was never inserted into hash, immediate free is OK */
-        if (hlist_unhashed(&dentry->d_hash))
+        if (hlist_bl_unhashed(&dentry->d_hash))
                 __d_free(&dentry->d_u.d_rcu);
         else
                 call_rcu(&dentry->d_u.d_rcu, __d_free);
 }
 
+/**
+ * dentry_rcuwalk_barrier - invalidate in-progress rcu-walk lookups
+ * After this call, in-progress rcu-walk path lookup will fail. This
+ * should be called after unhashing, and after changing d_inode (if
+ * the dentry has not already been unhashed).
+ */
+static inline void dentry_rcuwalk_barrier(struct dentry *dentry)
+{
+        assert_spin_locked(&dentry->d_lock);
+        /* Go through a barrier */
+        write_seqcount_barrier(&dentry->d_seq);
+}
+
 /*
  * Release the dentry's inode, using the filesystem
- * d_iput() operation if defined.
+ * d_iput() operation if defined. Dentry has no refcount
+ * and is unhashed.
  */
 static void dentry_iput(struct dentry * dentry)
         __releases(dentry->d_lock)
-        __releases(dcache_lock)
+        __releases(dentry->d_inode->i_lock)
 {
         struct inode *inode = dentry->d_inode;
         if (inode) {
                 dentry->d_inode = NULL;
                 list_del_init(&dentry->d_alias);
                 spin_unlock(&dentry->d_lock);
-                spin_unlock(&dcache_lock);
+                spin_unlock(&inode->i_lock);
                 if (!inode->i_nlink)
                         fsnotify_inoderemove(inode);
                 if (dentry->d_op && dentry->d_op->d_iput)
@@ -128,40 +210,72 @@ static void dentry_iput(struct dentry * dentry)
                         iput(inode);
         } else {
                 spin_unlock(&dentry->d_lock);
-                spin_unlock(&dcache_lock);
         }
 }
 
 /*
- * dentry_lru_(add|del|move_tail) must be called with dcache_lock held.
+ * Release the dentry's inode, using the filesystem
+ * d_iput() operation if defined. dentry remains in-use.
+ */
+static void dentry_unlink_inode(struct dentry * dentry)
+        __releases(dentry->d_lock)
+        __releases(dentry->d_inode->i_lock)
+{
+        struct inode *inode = dentry->d_inode;
+        dentry->d_inode = NULL;
+        list_del_init(&dentry->d_alias);
+        dentry_rcuwalk_barrier(dentry);
+        spin_unlock(&dentry->d_lock);
+        spin_unlock(&inode->i_lock);
+        if (!inode->i_nlink)
+                fsnotify_inoderemove(inode);
+        if (dentry->d_op && dentry->d_op->d_iput)
+                dentry->d_op->d_iput(dentry, inode);
+        else
+                iput(inode);
+}
+
+/*
+ * dentry_lru_(add|del|move_tail) must be called with d_lock held.
  */
 static void dentry_lru_add(struct dentry *dentry)
 {
         if (list_empty(&dentry->d_lru)) {
+                spin_lock(&dcache_lru_lock);
                 list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
                 dentry->d_sb->s_nr_dentry_unused++;
-                percpu_counter_inc(&nr_dentry_unused);
+                dentry_stat.nr_unused++;
+                spin_unlock(&dcache_lru_lock);
         }
 }
 
+static void __dentry_lru_del(struct dentry *dentry)
+{
+        list_del_init(&dentry->d_lru);
+        dentry->d_sb->s_nr_dentry_unused--;
+        dentry_stat.nr_unused--;
+}
+
 static void dentry_lru_del(struct dentry *dentry)
 {
         if (!list_empty(&dentry->d_lru)) {
-                list_del_init(&dentry->d_lru);
-                dentry->d_sb->s_nr_dentry_unused--;
-                percpu_counter_dec(&nr_dentry_unused);
+                spin_lock(&dcache_lru_lock);
+                __dentry_lru_del(dentry);
+                spin_unlock(&dcache_lru_lock);
         }
 }
 
 static void dentry_lru_move_tail(struct dentry *dentry)
 {
+        spin_lock(&dcache_lru_lock);
         if (list_empty(&dentry->d_lru)) {
                 list_add_tail(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
                 dentry->d_sb->s_nr_dentry_unused++;
-                percpu_counter_inc(&nr_dentry_unused);
+                dentry_stat.nr_unused++;
         } else {
                 list_move_tail(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
         }
+        spin_unlock(&dcache_lru_lock);
 }
 
 /**
@@ -171,22 +285,115 @@ static void dentry_lru_move_tail(struct dentry *dentry)
  * The dentry must already be unhashed and removed from the LRU.
  *
  * If this is the root of the dentry tree, return NULL.
+ *
+ * dentry->d_lock and parent->d_lock must be held by caller, and are dropped by
+ * d_kill.
  */
-static struct dentry *d_kill(struct dentry *dentry)
+static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent)
         __releases(dentry->d_lock)
-        __releases(dcache_lock)
+        __releases(parent->d_lock)
+        __releases(dentry->d_inode->i_lock)
 {
-        struct dentry *parent;
-
+        dentry->d_parent = NULL;
         list_del(&dentry->d_u.d_child);
-        /*drops the locks, at that point nobody can reach this dentry */
+        if (parent)
+                spin_unlock(&parent->d_lock);
         dentry_iput(dentry);
+        /*
+         * dentry_iput drops the locks, at which point nobody (except
+         * transient RCU lookups) can reach this dentry.
+         */
+        d_free(dentry);
+        return parent;
+}
+
+/**
+ * d_drop - drop a dentry
+ * @dentry: dentry to drop
+ *
+ * d_drop() unhashes the entry from the parent dentry hashes, so that it won't
+ * be found through a VFS lookup any more. Note that this is different from
+ * deleting the dentry - d_delete will try to mark the dentry negative if
+ * possible, giving a successful _negative_ lookup, while d_drop will
+ * just make the cache lookup fail.
+ *
+ * d_drop() is used mainly for stuff that wants to invalidate a dentry for some
+ * reason (NFS timeouts or autofs deletes).
+ *
+ * __d_drop requires dentry->d_lock.
+ */
+void __d_drop(struct dentry *dentry)
+{
+        if (!(dentry->d_flags & DCACHE_UNHASHED)) {
+                if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED)) {
+                        bit_spin_lock(0,
+                                (unsigned long *)&dentry->d_sb->s_anon.first);
+                        dentry->d_flags |= DCACHE_UNHASHED;
+                        hlist_bl_del_init(&dentry->d_hash);
+                        __bit_spin_unlock(0,
+                                (unsigned long *)&dentry->d_sb->s_anon.first);
+                } else {
+                        struct dcache_hash_bucket *b;
+                        b = d_hash(dentry->d_parent, dentry->d_name.hash);
+                        spin_lock_bucket(b);
+                        /*
+                         * We may not actually need to put DCACHE_UNHASHED
+                         * manipulations under the hash lock, but follow
+                         * the principle of least surprise.
+                         */
+                        dentry->d_flags |= DCACHE_UNHASHED;
+                        hlist_bl_del_rcu(&dentry->d_hash);
+                        spin_unlock_bucket(b);
+                        dentry_rcuwalk_barrier(dentry);
+                }
+        }
+}
+EXPORT_SYMBOL(__d_drop);
+
+void d_drop(struct dentry *dentry)
+{
+        spin_lock(&dentry->d_lock);
+        __d_drop(dentry);
+        spin_unlock(&dentry->d_lock);
+}
+EXPORT_SYMBOL(d_drop);
+
+/*
+ * Finish off a dentry we've decided to kill.
+ * dentry->d_lock must be held, returns with it unlocked.
+ * If ref is non-zero, then decrement the refcount too.
+ * Returns dentry requiring refcount drop, or NULL if we're done.
+ */
+static inline struct dentry *dentry_kill(struct dentry *dentry, int ref)
+        __releases(dentry->d_lock)
+{
+        struct inode *inode;
+        struct dentry *parent;
+
+        inode = dentry->d_inode;
+        if (inode && !spin_trylock(&inode->i_lock)) {
+relock:
+                spin_unlock(&dentry->d_lock);
+                cpu_relax();
+                return dentry; /* try again with same dentry */
+        }
         if (IS_ROOT(dentry))
                 parent = NULL;
         else
                 parent = dentry->d_parent;
-        d_free(dentry);
-        return parent;
+        if (parent && !spin_trylock(&parent->d_lock)) {
+                if (inode)
+                        spin_unlock(&inode->i_lock);
+                goto relock;
+        }
+
+        if (ref)
+                dentry->d_count--;
+        /* if dentry was on the d_lru list delete it from there */
+        dentry_lru_del(dentry);
+        /* if it was on the hash then remove it */
+        __d_drop(dentry);
+        return d_kill(dentry, parent);
 }
 
 /* 
@@ -214,34 +421,26 @@ static struct dentry *d_kill(struct dentry *dentry)
  * call the dentry unlink method as well as removing it from the queues and
  * releasing its resources. If the parent dentries were scheduled for release
  * they too may now get deleted.
- *
- * no dcache lock, please.
  */
-
 void dput(struct dentry *dentry)
 {
         if (!dentry)
                 return;
 
 repeat:
-        if (atomic_read(&dentry->d_count) == 1)
+        if (dentry->d_count == 1)
                 might_sleep();
-        if (!atomic_dec_and_lock(&dentry->d_count, &dcache_lock))
-                return;
-
         spin_lock(&dentry->d_lock);
-        if (atomic_read(&dentry->d_count)) {
+        BUG_ON(!dentry->d_count);
+        if (dentry->d_count > 1) {
+                dentry->d_count--;
                 spin_unlock(&dentry->d_lock);
-                spin_unlock(&dcache_lock);
                 return;
         }
 
-        /*
-         * AV: ->d_delete() is _NOT_ allowed to block now.
-         */
-        if (dentry->d_op && dentry->d_op->d_delete) {
+        if (dentry->d_flags & DCACHE_OP_DELETE) {
                 if (dentry->d_op->d_delete(dentry))
-                        goto unhash_it;
+                        goto kill_it;
         }
 
         /* Unreachable? Get rid of it */
@@ -252,16 +451,12 @@ repeat:
         dentry->d_flags |= DCACHE_REFERENCED;
         dentry_lru_add(dentry);
 
-        spin_unlock(&dentry->d_lock);
-        spin_unlock(&dcache_lock);
+        dentry->d_count--;
+        spin_unlock(&dentry->d_lock);
         return;
 
-unhash_it:
-        __d_drop(dentry);
 kill_it:
-        /* if dentry was on the d_lru list delete it from there */
-        dentry_lru_del(dentry);
-        dentry = d_kill(dentry);
+        dentry = dentry_kill(dentry, 1);
         if (dentry)
                 goto repeat;
 }
@@ -284,9 +479,9 @@ int d_invalidate(struct dentry * dentry)
         /*
          * If it's already been dropped, return OK.
          */
-        spin_lock(&dcache_lock);
+        spin_lock(&dentry->d_lock);
         if (d_unhashed(dentry)) {
-                spin_unlock(&dcache_lock);
+                spin_unlock(&dentry->d_lock);
                 return 0;
         }
         /*
@@ -294,9 +489,9 @@ int d_invalidate(struct dentry * dentry)
          * to get rid of unused child entries.
          */
         if (!list_empty(&dentry->d_subdirs)) {
-                spin_unlock(&dcache_lock);
+                spin_unlock(&dentry->d_lock);
                 shrink_dcache_parent(dentry);
-                spin_lock(&dcache_lock);
+                spin_lock(&dentry->d_lock);
         }
 
         /*
@@ -309,35 +504,61 @@ int d_invalidate(struct dentry * dentry)
          * we might still populate it if it was a
          * working directory or similar).
          */
-        spin_lock(&dentry->d_lock);
-        if (atomic_read(&dentry->d_count) > 1) {
+        if (dentry->d_count > 1) {
                 if (dentry->d_inode && S_ISDIR(dentry->d_inode->i_mode)) {
                         spin_unlock(&dentry->d_lock);
-                        spin_unlock(&dcache_lock);
                         return -EBUSY;
                 }
         }
 
         __d_drop(dentry);
         spin_unlock(&dentry->d_lock);
-        spin_unlock(&dcache_lock);
         return 0;
 }
 EXPORT_SYMBOL(d_invalidate);
 
-/* This should be called _only_ with dcache_lock held */
-static inline struct dentry * __dget_locked(struct dentry *dentry)
+/* This must be called with d_lock held */
+static inline void __dget_dlock(struct dentry *dentry)
 {
-        atomic_inc(&dentry->d_count);
-        dentry_lru_del(dentry);
-        return dentry;
+        dentry->d_count++;
 }
 
-struct dentry * dget_locked(struct dentry *dentry)
+static inline void __dget(struct dentry *dentry)
 {
-        return __dget_locked(dentry);
+        spin_lock(&dentry->d_lock);
+        __dget_dlock(dentry);
+        spin_unlock(&dentry->d_lock);
+}
+
+struct dentry *dget_parent(struct dentry *dentry)
+{
+        struct dentry *ret;
+
+repeat:
+        /*
+         * Don't need rcu_dereference because we re-check it was correct under
+         * the lock.
+         */
+        rcu_read_lock();
+        ret = dentry->d_parent;
+        if (!ret) {
+                rcu_read_unlock();
+                goto out;
+        }
+        spin_lock(&ret->d_lock);
+        if (unlikely(ret != dentry->d_parent)) {
+                spin_unlock(&ret->d_lock);
+                rcu_read_unlock();
+                goto repeat;
+        }
+        rcu_read_unlock();
+        BUG_ON(!ret->d_count);
+        ret->d_count++;
+        spin_unlock(&ret->d_lock);
+out:
+        return ret;
 }
-EXPORT_SYMBOL(dget_locked);
+EXPORT_SYMBOL(dget_parent);
 
 /**
  * d_find_alias - grab a hashed alias of inode
@@ -355,42 +576,51 @@ EXPORT_SYMBOL(dget_locked);
  * any other hashed alias over that one unless @want_discon is set,
  * in which case only return an IS_ROOT, DCACHE_DISCONNECTED alias.
  */
-
-static struct dentry * __d_find_alias(struct inode *inode, int want_discon)
+static struct dentry *__d_find_alias(struct inode *inode, int want_discon)
 {
-        struct list_head *head, *next, *tmp;
-        struct dentry *alias, *discon_alias=NULL;
+        struct dentry *alias, *discon_alias;
 
-        head = &inode->i_dentry;
-        next = inode->i_dentry.next;
-        while (next != head) {
-                tmp = next;
-                next = tmp->next;
-                prefetch(next);
-                alias = list_entry(tmp, struct dentry, d_alias);
+again:
+        discon_alias = NULL;
+        list_for_each_entry(alias, &inode->i_dentry, d_alias) {
+                spin_lock(&alias->d_lock);
                 if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
                         if (IS_ROOT(alias) &&
-                            (alias->d_flags & DCACHE_DISCONNECTED))
+                            (alias->d_flags & DCACHE_DISCONNECTED)) {
                                 discon_alias = alias;
-                        else if (!want_discon) {
-                                __dget_locked(alias);
+                        } else if (!want_discon) {
+                                __dget_dlock(alias);
+                                spin_unlock(&alias->d_lock);
+                                return alias;
+                        }
+                }
+                spin_unlock(&alias->d_lock);
+        }
+        if (discon_alias) {
+                alias = discon_alias;
+                spin_lock(&alias->d_lock);
+                if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
+                        if (IS_ROOT(alias) &&
+                            (alias->d_flags & DCACHE_DISCONNECTED)) {
+                                __dget_dlock(alias);
+                                spin_unlock(&alias->d_lock);
                                 return alias;
                         }
                 }
+                spin_unlock(&alias->d_lock);
+                goto again;
         }
-        if (discon_alias)
-                __dget_locked(discon_alias);
-        return discon_alias;
+        return NULL;
 }
 
-struct dentry * d_find_alias(struct inode *inode)
+struct dentry *d_find_alias(struct inode *inode)
 {
         struct dentry *de = NULL;
 
         if (!list_empty(&inode->i_dentry)) {
-                spin_lock(&dcache_lock);
+                spin_lock(&inode->i_lock);
                 de = __d_find_alias(inode, 0);
-                spin_unlock(&dcache_lock);
+                spin_unlock(&inode->i_lock);
         }
         return de;
 }
@@ -404,54 +634,61 @@ void d_prune_aliases(struct inode *inode)
 {
         struct dentry *dentry;
 restart:
-        spin_lock(&dcache_lock);
+        spin_lock(&inode->i_lock);
         list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
                 spin_lock(&dentry->d_lock);
-                if (!atomic_read(&dentry->d_count)) {
-                        __dget_locked(dentry);
+                if (!dentry->d_count) {
+                        __dget_dlock(dentry);
                         __d_drop(dentry);
                         spin_unlock(&dentry->d_lock);
-                        spin_unlock(&dcache_lock);
+                        spin_unlock(&inode->i_lock);
                         dput(dentry);
                         goto restart;
                 }
                 spin_unlock(&dentry->d_lock);
         }
-        spin_unlock(&dcache_lock);
+        spin_unlock(&inode->i_lock);
 }
 EXPORT_SYMBOL(d_prune_aliases);
 
 /*
- * Throw away a dentry - free the inode, dput the parent.  This requires that
- * the LRU list has already been removed.
+ * Try to throw away a dentry - free the inode, dput the parent.
+ * Requires dentry->d_lock is held, and dentry->d_count == 0.
+ * Releases dentry->d_lock.
  *
- * Try to prune ancestors as well.  This is necessary to prevent
- * quadratic behavior of shrink_dcache_parent(), but is also expected
- * to be beneficial in reducing dentry cache fragmentation.
+ * This may fail if locks cannot be acquired no problem, just try again.
  */
-static void prune_one_dentry(struct dentry * dentry)
+static void try_prune_one_dentry(struct dentry *dentry)
         __releases(dentry->d_lock)
-        __releases(dcache_lock)
-        __acquires(dcache_lock)
 {
-        __d_drop(dentry);
-        dentry = d_kill(dentry);
+        struct dentry *parent;
 
+        parent = dentry_kill(dentry, 0);
         /*
-         * Prune ancestors.  Locking is simpler than in dput(),
-         * because dcache_lock needs to be taken anyway.
+         * If dentry_kill returns NULL, we have nothing more to do.
+         * if it returns the same dentry, trylocks failed. In either
+         * case, just loop again.
+         *
+         * Otherwise, we need to prune ancestors too. This is necessary
+         * to prevent quadratic behavior of shrink_dcache_parent(), but
+         * is also expected to be beneficial in reducing dentry cache
+         * fragmentation.
          */
-        spin_lock(&dcache_lock);
+        if (!parent)
+                return;
+        if (parent == dentry)
+                return;
+
+        /* Prune ancestors. */
+        dentry = parent;
         while (dentry) {
-                if (!atomic_dec_and_lock(&dentry->d_count, &dentry->d_lock))
+                spin_lock(&dentry->d_lock);
+                if (dentry->d_count > 1) {
+                        dentry->d_count--;
+                        spin_unlock(&dentry->d_lock);
                         return;
-
-                if (dentry->d_op && dentry->d_op->d_delete)
-                        dentry->d_op->d_delete(dentry);
-                dentry_lru_del(dentry);
-                __d_drop(dentry);
-                dentry = d_kill(dentry);
-                spin_lock(&dcache_lock);
+                }
+                dentry = dentry_kill(dentry, 1);
         }
 }
 
@@ -459,24 +696,35 @@ static void shrink_dentry_list(struct list_head *list)
 {
         struct dentry *dentry;
 
-        while (!list_empty(list)) {
-                dentry = list_entry(list->prev, struct dentry, d_lru);
-                dentry_lru_del(dentry);
+        rcu_read_lock();
+        for (;;) {
+                dentry = list_entry_rcu(list->prev, struct dentry, d_lru);
+                if (&dentry->d_lru == list)
+                        break; /* empty */
+                spin_lock(&dentry->d_lock);
+                if (dentry != list_entry(list->prev, struct dentry, d_lru)) {
+                        spin_unlock(&dentry->d_lock);
+                        continue;
+                }
 
                 /*
                  * We found an inuse dentry which was not removed from
                  * the LRU because of laziness during lookup.  Do not free
                  * it - just keep it off the LRU list.
                  */
-                spin_lock(&dentry->d_lock);
-                if (atomic_read(&dentry->d_count)) {
+                if (dentry->d_count) {
+                        dentry_lru_del(dentry);
                         spin_unlock(&dentry->d_lock);
                         continue;
                 }
-                prune_one_dentry(dentry);
-                /* dentry->d_lock was dropped in prune_one_dentry() */
-                cond_resched_lock(&dcache_lock);
+
+                rcu_read_unlock();
+
+                try_prune_one_dentry(dentry);
+
+                rcu_read_lock();
         }
+        rcu_read_unlock();
 }
 
 /**
@@ -495,42 +743,44 @@ static void __shrink_dcache_sb(struct super_block *sb, int *count, int flags)
         LIST_HEAD(tmp);
         int cnt = *count;
 
-        spin_lock(&dcache_lock);
+relock:
+        spin_lock(&dcache_lru_lock);
         while (!list_empty(&sb->s_dentry_lru)) {
                 dentry = list_entry(sb->s_dentry_lru.prev,
                                 struct dentry, d_lru);
                 BUG_ON(dentry->d_sb != sb);
 
+                if (!spin_trylock(&dentry->d_lock)) {
+                        spin_unlock(&dcache_lru_lock);
+                        cpu_relax();
+                        goto relock;
+                }
+
                 /*
                  * If we are honouring the DCACHE_REFERENCED flag and the
                  * dentry has this flag set, don't free it.  Clear the flag
                  * and put it back on the LRU.
                  */
-                if (flags & DCACHE_REFERENCED) {
-                        spin_lock(&dentry->d_lock);
-                        if (dentry->d_flags & DCACHE_REFERENCED) {
-                                dentry->d_flags &= ~DCACHE_REFERENCED;
-                                list_move(&dentry->d_lru, &referenced);
-                                spin_unlock(&dentry->d_lock);
-                                cond_resched_lock(&dcache_lock);
-                                continue;
-                        }
+                if (flags & DCACHE_REFERENCED &&
+                                dentry->d_flags & DCACHE_REFERENCED) {
+                        dentry->d_flags &= ~DCACHE_REFERENCED;
+                        list_move(&dentry->d_lru, &referenced);
                         spin_unlock(&dentry->d_lock);
+                } else {
+                        list_move_tail(&dentry->d_lru, &tmp);
+                        spin_unlock(&dentry->d_lock);
+                        if (!--cnt)
+                                break;
                 }
-
-                list_move_tail(&dentry->d_lru, &tmp);
-                if (!--cnt)
-                        break;
-                cond_resched_lock(&dcache_lock);
+                cond_resched_lock(&dcache_lru_lock);
         }
-
-        *count = cnt;
-        shrink_dentry_list(&tmp);
-
         if (!list_empty(&referenced))
                 list_splice(&referenced, &sb->s_dentry_lru);
-        spin_unlock(&dcache_lock);
+        spin_unlock(&dcache_lru_lock);
 
+        shrink_dentry_list(&tmp);
+
+        *count = cnt;
 }
 
 /**
@@ -546,13 +796,12 @@ static void prune_dcache(int count)
 {
         struct super_block *sb, *p = NULL;
         int w_count;
-        int unused = percpu_counter_sum_positive(&nr_dentry_unused);
+        int unused = dentry_stat.nr_unused;
         int prune_ratio;
         int pruned;
 
         if (unused == 0 || count == 0)
                 return;
-        spin_lock(&dcache_lock);
         if (count >= unused)
                 prune_ratio = 1;
         else
@@ -589,11 +838,9 @@ static void prune_dcache(int count)
                 if (down_read_trylock(&sb->s_umount)) {
                         if ((sb->s_root != NULL) &&
                             (!list_empty(&sb->s_dentry_lru))) {
-                                spin_unlock(&dcache_lock);
                                 __shrink_dcache_sb(sb, &w_count,
                                                 DCACHE_REFERENCED);
                                 pruned -= w_count;
-                                spin_lock(&dcache_lock);
                         }
                         up_read(&sb->s_umount);
                 }
@@ -609,7 +856,6 @@ static void prune_dcache(int count)
         if (p)
                 __put_super(p);
         spin_unlock(&sb_lock);
-        spin_unlock(&dcache_lock);
 }
 
 /**
@@ -623,12 +869,14 @@ void shrink_dcache_sb(struct super_block *sb)
 {
         LIST_HEAD(tmp);
 
-        spin_lock(&dcache_lock);
+        spin_lock(&dcache_lru_lock);
         while (!list_empty(&sb->s_dentry_lru)) {
                 list_splice_init(&sb->s_dentry_lru, &tmp);
+                spin_unlock(&dcache_lru_lock);
                 shrink_dentry_list(&tmp);
+                spin_lock(&dcache_lru_lock);
         }
-        spin_unlock(&dcache_lock);
+        spin_unlock(&dcache_lru_lock);
 }
 EXPORT_SYMBOL(shrink_dcache_sb);
 
@@ -645,10 +893,10 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
         BUG_ON(!IS_ROOT(dentry));
 
         /* detach this root from the system */
-        spin_lock(&dcache_lock);
+        spin_lock(&dentry->d_lock);
         dentry_lru_del(dentry);
         __d_drop(dentry);
-        spin_unlock(&dcache_lock);
+        spin_unlock(&dentry->d_lock);
 
         for (;;) {
                 /* descend to the first leaf in the current subtree */
@@ -657,14 +905,16 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
 
                         /* this is a branch with children - detach all of them
                          * from the system in one go */
-                        spin_lock(&dcache_lock);
+                        spin_lock(&dentry->d_lock);
                         list_for_each_entry(loop, &dentry->d_subdirs,
                                             d_u.d_child) {
+                                spin_lock_nested(&loop->d_lock,
+                                                DENTRY_D_LOCK_NESTED);
                                 dentry_lru_del(loop);
                                 __d_drop(loop);
-                                cond_resched_lock(&dcache_lock);
+                                spin_unlock(&loop->d_lock);
                         }
-                        spin_unlock(&dcache_lock);
+                        spin_unlock(&dentry->d_lock);
 
                         /* move to the first child */
                         dentry = list_entry(dentry->d_subdirs.next,
@@ -676,7 +926,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
                 do {
                         struct inode *inode;
 
-                        if (atomic_read(&dentry->d_count) != 0) {
+                        if (dentry->d_count != 0) {
                                 printk(KERN_ERR
                                        "BUG: Dentry %p{i=%lx,n=%s}"
                                        " still in use (%d)"
@@ -685,20 +935,23 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
                                        dentry->d_inode ?
                                        dentry->d_inode->i_ino : 0UL,
                                        dentry->d_name.name,
-                                       atomic_read(&dentry->d_count),
+                                       dentry->d_count,
                                        dentry->d_sb->s_type->name,
                                        dentry->d_sb->s_id);
                                 BUG();
                         }
 
-                        if (IS_ROOT(dentry))
+                        if (IS_ROOT(dentry)) {
                                 parent = NULL;
-                        else {
+                                list_del(&dentry->d_u.d_child);
+                        } else {
                                 parent = dentry->d_parent;
-                                atomic_dec(&parent->d_count);
+                                spin_lock(&parent->d_lock);
+                                parent->d_count--;
+                                list_del(&dentry->d_u.d_child);
+                                spin_unlock(&parent->d_lock);
                         }
 
-                        list_del(&dentry->d_u.d_child);
                         detached++;
 
                         inode = dentry->d_inode;
@@ -728,8 +981,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
 
 /*
  * destroy the dentries attached to a superblock on unmounting
- * - we don't need to use dentry->d_lock, and only need dcache_lock when
- *   removing the dentry from the system lists and hashes because:
+ * - we don't need to use dentry->d_lock because:
  *   - the superblock is detached from all mountings and open files, so the
  *     dentry trees will not be rearranged by the VFS
  *   - s_umount is write-locked, so the memory pressure shrinker will ignore
@@ -746,11 +998,13 @@ void shrink_dcache_for_umount(struct super_block *sb)
 
         dentry = sb->s_root;
         sb->s_root = NULL;
-        atomic_dec(&dentry->d_count);
+        spin_lock(&dentry->d_lock);
+        dentry->d_count--;
+        spin_unlock(&dentry->d_lock);
         shrink_dcache_for_umount_subtree(dentry);
 
-        while (!hlist_empty(&sb->s_anon)) {
-                dentry = hlist_entry(sb->s_anon.first, struct dentry, d_hash);
+        while (!hlist_bl_empty(&sb->s_anon)) {
+                dentry = hlist_bl_entry(hlist_bl_first(&sb->s_anon), struct dentry, d_hash);
                 shrink_dcache_for_umount_subtree(dentry);
         }
 }
@@ -768,15 +1022,20 @@ void shrink_dcache_for_umount(struct super_block *sb)
  * Return true if the parent or its subdirectories contain
  * a mount point
  */
- 
 int have_submounts(struct dentry *parent)
 {
-        struct dentry *this_parent = parent;
+        struct dentry *this_parent;
         struct list_head *next;
+        unsigned seq;
+        int locked = 0;
+
+        seq = read_seqbegin(&rename_lock);
+again:
+        this_parent = parent;
 
-        spin_lock(&dcache_lock);
         if (d_mountpoint(parent))
                 goto positive;
+        spin_lock(&this_parent->d_lock);
 repeat:
         next = this_parent->d_subdirs.next;
 resume:
@@ -784,27 +1043,65 @@ resume:
                 struct list_head *tmp = next;
                 struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
                 next = tmp->next;
+
+                spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
                 /* Have we found a mount point ? */
-                if (d_mountpoint(dentry))
+                if (d_mountpoint(dentry)) {
+                        spin_unlock(&dentry->d_lock);
+                        spin_unlock(&this_parent->d_lock);
                         goto positive;
+                }
                 if (!list_empty(&dentry->d_subdirs)) {
+                        spin_unlock(&this_parent->d_lock);
+                        spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_);
                         this_parent = dentry;
+                        spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_);
                         goto repeat;
                 }
+                spin_unlock(&dentry->d_lock);
         }
         /*
          * All done at this level ... ascend and resume the search.
          */
         if (this_parent != parent) {
-                next = this_parent->d_u.d_child.next;
-                this_parent = this_parent->d_parent;
+                struct dentry *tmp;
+                struct dentry *child;
+
+                tmp = this_parent->d_parent;
+                rcu_read_lock();
+                spin_unlock(&this_parent->d_lock);
+                child = this_parent;
+                this_parent = tmp;
+                spin_lock(&this_parent->d_lock);
+                /* might go back up the wrong parent if we have had a rename
+                 * or deletion */
+                if (this_parent != child->d_parent ||
+                         (!locked && read_seqretry(&rename_lock, seq))) {
+                        spin_unlock(&this_parent->d_lock);
+                        rcu_read_unlock();
+                        goto rename_retry;
+                }
+                rcu_read_unlock();
+                next = child->d_u.d_child.next;
                 goto resume;
         }
-        spin_unlock(&dcache_lock);
+        spin_unlock(&this_parent->d_lock);
+        if (!locked && read_seqretry(&rename_lock, seq))
+                goto rename_retry;
+        if (locked)
+                write_sequnlock(&rename_lock);
         return 0; /* No mount points found in tree */
 positive:
-        spin_unlock(&dcache_lock);
+        if (!locked && read_seqretry(&rename_lock, seq))
+                goto rename_retry;
+        if (locked)
+                write_sequnlock(&rename_lock);
         return 1;
+
+rename_retry:
+        locked = 1;
+        write_seqlock(&rename_lock);
+        goto again;
 }
 EXPORT_SYMBOL(have_submounts);
 
@@ -824,11 +1121,16 @@ EXPORT_SYMBOL(have_submounts);
  */
 static int select_parent(struct dentry * parent)
 {
-        struct dentry *this_parent = parent;
+        struct dentry *this_parent;
         struct list_head *next;
+        unsigned seq;
         int found = 0;
+        int locked = 0;
 
-        spin_lock(&dcache_lock);
+        seq = read_seqbegin(&rename_lock);
+again:
+        this_parent = parent;
+        spin_lock(&this_parent->d_lock);
 repeat:
         next = this_parent->d_subdirs.next;
 resume:
@@ -837,11 +1139,13 @@ resume:
                 struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
                 next = tmp->next;
 
+                spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
+
                 /* 
                  * move only zero ref count dentries to the end 
                  * of the unused list for prune_dcache
                  */
-                if (!atomic_read(&dentry->d_count)) {
+                if (!dentry->d_count) {
                         dentry_lru_move_tail(dentry);
                         found++;
                 } else {
@@ -853,28 +1157,63 @@ resume:
                  * ensures forward progress). We'll be coming back to find
                  * the rest.
                  */
-                if (found && need_resched())
+                if (found && need_resched()) {
+                        spin_unlock(&dentry->d_lock);
                         goto out;
+                }
 
                 /*
                  * Descend a level if the d_subdirs list is non-empty.
                  */
                 if (!list_empty(&dentry->d_subdirs)) {
+                        spin_unlock(&this_parent->d_lock);
+                        spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_);
                         this_parent = dentry;
+                        spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_);
                         goto repeat;
                 }
+
+                spin_unlock(&dentry->d_lock);
         }
         /*
          * All done at this level ... ascend and resume the search.
          */
         if (this_parent != parent) {
-                next = this_parent->d_u.d_child.next;
-                this_parent = this_parent->d_parent;
+                struct dentry *tmp;
+                struct dentry *child;
+
+                tmp = this_parent->d_parent;
+                rcu_read_lock();
+                spin_unlock(&this_parent->d_lock);
+                child = this_parent;
+                this_parent = tmp;
+                spin_lock(&this_parent->d_lock);
+                /* might go back up the wrong parent if we have had a rename
+                 * or deletion */
+                if (this_parent != child->d_parent ||
+                        (!locked && read_seqretry(&rename_lock, seq))) {
+                        spin_unlock(&this_parent->d_lock);
+                        rcu_read_unlock();
+                        goto rename_retry;
+                }
+                rcu_read_unlock();
+                next = child->d_u.d_child.next;
                 goto resume;
         }
 out:
-        spin_unlock(&dcache_lock);
+        spin_unlock(&this_parent->d_lock);
+        if (!locked && read_seqretry(&rename_lock, seq))
+                goto rename_retry;
+        if (locked)
+                write_sequnlock(&rename_lock);
         return found;
+
+rename_retry:
+        if (found)
+                return found;
+        locked = 1;
+        write_seqlock(&rename_lock);
+        goto again;
 }
 
 /**
@@ -908,16 +1247,13 @@ EXPORT_SYMBOL(shrink_dcache_parent);
  */
 static int shrink_dcache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
 {
-        int nr_unused;
-
         if (nr) {
                 if (!(gfp_mask & __GFP_FS))
                         return -1;
                 prune_dcache(nr);
         }
 
-        nr_unused = percpu_counter_sum_positive(&nr_dentry_unused);
-        return (nr_unused / 100) * sysctl_vfs_cache_pressure;
+        return (dentry_stat.nr_unused / 100) * sysctl_vfs_cache_pressure;
 }
 
 static struct shrinker dcache_shrinker = {
@@ -960,38 +1296,52 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
         memcpy(dname, name->name, name->len);
         dname[name->len] = 0;
 
-        atomic_set(&dentry->d_count, 1);
+        dentry->d_count = 1;
         dentry->d_flags = DCACHE_UNHASHED;
         spin_lock_init(&dentry->d_lock);
+        seqcount_init(&dentry->d_seq);
         dentry->d_inode = NULL;
         dentry->d_parent = NULL;
         dentry->d_sb = NULL;
         dentry->d_op = NULL;
         dentry->d_fsdata = NULL;
-        dentry->d_mounted = 0;
-        INIT_HLIST_NODE(&dentry->d_hash);
+        INIT_HLIST_BL_NODE(&dentry->d_hash);
         INIT_LIST_HEAD(&dentry->d_lru);
         INIT_LIST_HEAD(&dentry->d_subdirs);
         INIT_LIST_HEAD(&dentry->d_alias);
+        INIT_LIST_HEAD(&dentry->d_u.d_child);
 
         if (parent) {
-                dentry->d_parent = dget(parent);
+                spin_lock(&parent->d_lock);
+                /*
+                 * don't need child lock because it is not subject
+                 * to concurrency here
+                 */
+                __dget_dlock(parent);
+                dentry->d_parent = parent;
                 dentry->d_sb = parent->d_sb;
-        } else {
-                INIT_LIST_HEAD(&dentry->d_u.d_child);
-        }
-
-        spin_lock(&dcache_lock);
-        if (parent)
                 list_add(&dentry->d_u.d_child, &parent->d_subdirs);
-        spin_unlock(&dcache_lock);
+                spin_unlock(&parent->d_lock);
+        }
 
-        percpu_counter_inc(&nr_dentry);
+        this_cpu_inc(nr_dentry);
 
         return dentry;
 }
 EXPORT_SYMBOL(d_alloc);
 
+struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name)
+{
+        struct dentry *dentry = d_alloc(NULL, name);
+        if (dentry) {
+                dentry->d_sb = sb;
+                dentry->d_parent = dentry;
+                dentry->d_flags |= DCACHE_DISCONNECTED;
+        }
+        return dentry;
+}
+EXPORT_SYMBOL(d_alloc_pseudo);
+
 struct dentry *d_alloc_name(struct dentry *parent, const char *name)
 {
         struct qstr q;
@@ -1003,12 +1353,36 @@ struct dentry *d_alloc_name(struct dentry *parent, const char *name)
 }
 EXPORT_SYMBOL(d_alloc_name);
 
-/* the caller must hold dcache_lock */
+void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
+{
+        BUG_ON(dentry->d_op);
+        BUG_ON(dentry->d_flags & (DCACHE_OP_HASH        |
+                                DCACHE_OP_COMPARE       |
+                                DCACHE_OP_REVALIDATE    |
+                                DCACHE_OP_DELETE ));
+        dentry->d_op = op;
+        if (!op)
+                return;
+        if (op->d_hash)
+                dentry->d_flags |= DCACHE_OP_HASH;
+        if (op->d_compare)
+                dentry->d_flags |= DCACHE_OP_COMPARE;
+        if (op->d_revalidate)
+                dentry->d_flags |= DCACHE_OP_REVALIDATE;
+        if (op->d_delete)
+                dentry->d_flags |= DCACHE_OP_DELETE;
+
+}
+EXPORT_SYMBOL(d_set_d_op);
+
 static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 {
+        spin_lock(&dentry->d_lock);
         if (inode)
                 list_add(&dentry->d_alias, &inode->i_dentry);
         dentry->d_inode = inode;
+        dentry_rcuwalk_barrier(dentry);
+        spin_unlock(&dentry->d_lock);
         fsnotify_d_instantiate(dentry, inode);
 }
 
@@ -1030,9 +1404,11 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode)
 void d_instantiate(struct dentry *entry, struct inode * inode)
 {
         BUG_ON(!list_empty(&entry->d_alias));
-        spin_lock(&dcache_lock);
+        if (inode)
+                spin_lock(&inode->i_lock);
         __d_instantiate(entry, inode);
-        spin_unlock(&dcache_lock);
+        if (inode)
+                spin_unlock(&inode->i_lock);
         security_d_instantiate(entry, inode);
 }
 EXPORT_SYMBOL(d_instantiate);
@@ -1069,15 +1445,18 @@ static struct dentry *__d_instantiate_unique(struct dentry *entry,
         list_for_each_entry(alias, &inode->i_dentry, d_alias) {
                 struct qstr *qstr = &alias->d_name;
 
+                /*
+                 * Don't need alias->d_lock here, because aliases with
+                 * d_parent == entry->d_parent are not subject to name or
+                 * parent changes, because the parent inode i_mutex is held.
+                 */
                 if (qstr->hash != hash)
                         continue;
                 if (alias->d_parent != entry->d_parent)
                         continue;
-                if (qstr->len != len)
+                if (dentry_cmp(qstr->name, qstr->len, name, len))
                         continue;
-                if (memcmp(qstr->name, name, len))
-                        continue;
-                dget_locked(alias);
+                __dget(alias);
                 return alias;
         }
 
@@ -1091,9 +1470,11 @@ struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode)
 
         BUG_ON(!list_empty(&entry->d_alias));
 
-        spin_lock(&dcache_lock);
+        if (inode)
+                spin_lock(&inode->i_lock);
         result = __d_instantiate_unique(entry, inode);
-        spin_unlock(&dcache_lock);
+        if (inode)
+                spin_unlock(&inode->i_lock);
 
         if (!result) {
                 security_d_instantiate(entry, inode);
@@ -1134,14 +1515,6 @@ struct dentry * d_alloc_root(struct inode * root_inode)
 }
 EXPORT_SYMBOL(d_alloc_root);
 
-static inline struct hlist_head *d_hash(struct dentry *parent,
-                                        unsigned long hash)
-{
-        hash += ((unsigned long) parent ^ GOLDEN_RATIO_PRIME) / L1_CACHE_BYTES;
-        hash = hash ^ ((hash ^ GOLDEN_RATIO_PRIME) >> D_HASHBITS);
-        return dentry_hashtable + (hash & D_HASHMASK);
-}
-
 /**
  * d_obtain_alias - find or allocate a dentry for a given inode
  * @inode: inode to allocate the dentry for
@@ -1182,10 +1555,11 @@ struct dentry *d_obtain_alias(struct inode *inode)
         }
         tmp->d_parent = tmp; /* make sure dput doesn't croak */
 
-        spin_lock(&dcache_lock);
+
+        spin_lock(&inode->i_lock);
         res = __d_find_alias(inode, 0);
         if (res) {
-                spin_unlock(&dcache_lock);
+                spin_unlock(&inode->i_lock);
                 dput(tmp);
                 goto out_iput;
         }
@@ -1195,12 +1569,14 @@ struct dentry *d_obtain_alias(struct inode *inode)
         tmp->d_sb = inode->i_sb;
         tmp->d_inode = inode;
         tmp->d_flags |= DCACHE_DISCONNECTED;
-        tmp->d_flags &= ~DCACHE_UNHASHED;
         list_add(&tmp->d_alias, &inode->i_dentry);
-        hlist_add_head(&tmp->d_hash, &inode->i_sb->s_anon);
+        bit_spin_lock(0, (unsigned long *)&tmp->d_sb->s_anon.first);
+        tmp->d_flags &= ~DCACHE_UNHASHED;
+        hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon);
+        __bit_spin_unlock(0, (unsigned long *)&tmp->d_sb->s_anon.first);
         spin_unlock(&tmp->d_lock);
+        spin_unlock(&inode->i_lock);
 
-        spin_unlock(&dcache_lock);
         return tmp;
 
  out_iput:
@@ -1230,18 +1606,18 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
         struct dentry *new = NULL;
 
         if (inode && S_ISDIR(inode->i_mode)) {
-                spin_lock(&dcache_lock);
+                spin_lock(&inode->i_lock);
                 new = __d_find_alias(inode, 1);
                 if (new) {
                         BUG_ON(!(new->d_flags & DCACHE_DISCONNECTED));
-                        spin_unlock(&dcache_lock);
+                        spin_unlock(&inode->i_lock);
                         security_d_instantiate(new, inode);
                         d_move(new, dentry);
                         iput(inode);
                 } else {
-                        /* already taking dcache_lock, so d_add() by hand */
+                        /* already taking inode->i_lock, so d_add() by hand */
                         __d_instantiate(dentry, inode);
-                        spin_unlock(&dcache_lock);
+                        spin_unlock(&inode->i_lock);
                         security_d_instantiate(dentry, inode);
                         d_rehash(dentry);
                 }
@@ -1314,10 +1690,10 @@ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
          * Negative dentry: instantiate it unless the inode is a directory and
          * already has a dentry.
          */
-        spin_lock(&dcache_lock);
+        spin_lock(&inode->i_lock);
         if (!S_ISDIR(inode->i_mode) || list_empty(&inode->i_dentry)) {
                 __d_instantiate(found, inode);
-                spin_unlock(&dcache_lock);
+                spin_unlock(&inode->i_lock);
                 security_d_instantiate(found, inode);
                 return found;
         }
@@ -1327,8 +1703,8 @@ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
          * reference to it, move it in place and use it.
          */
         new = list_entry(inode->i_dentry.next, struct dentry, d_alias);
-        dget_locked(new);
-        spin_unlock(&dcache_lock);
+        __dget(new);
+        spin_unlock(&inode->i_lock);
         security_d_instantiate(found, inode);
         d_move(new, found);
         iput(inode);
@@ -1342,6 +1718,112 @@ err_out:
 EXPORT_SYMBOL(d_add_ci);
 
 /**
+ * __d_lookup_rcu - search for a dentry (racy, store-free)
+ * @parent: parent dentry
+ * @name: qstr of name we wish to find
+ * @seq: returns d_seq value at the point where the dentry was found
+ * @inode: returns dentry->d_inode when the inode was found valid.
+ * Returns: dentry, or NULL
+ *
+ * __d_lookup_rcu is the dcache lookup function for rcu-walk name
+ * resolution (store-free path walking) design described in
+ * Documentation/filesystems/path-lookup.txt.
+ *
+ * This is not to be used outside core vfs.
+ *
+ * __d_lookup_rcu must only be used in rcu-walk mode, ie. with vfsmount lock
+ * held, and rcu_read_lock held. The returned dentry must not be stored into
+ * without taking d_lock and checking d_seq sequence count against @seq
+ * returned here.
+ *
+ * A refcount may be taken on the found dentry with the __d_rcu_to_refcount
+ * function.
+ *
+ * Alternatively, __d_lookup_rcu may be called again to look up the child of
+ * the returned dentry, so long as its parent's seqlock is checked after the
+ * child is looked up. Thus, an interlocking stepping of sequence lock checks
+ * is formed, giving integrity down the path walk.
+ */
+struct dentry *__d_lookup_rcu(struct dentry *parent, struct qstr *name,
+                                unsigned *seq, struct inode **inode)
+{
+        unsigned int len = name->len;
+        unsigned int hash = name->hash;
+        const unsigned char *str = name->name;
+        struct dcache_hash_bucket *b = d_hash(parent, hash);
+        struct hlist_bl_node *node;
+        struct dentry *dentry;
+
+        /*
+         * Note: There is significant duplication with __d_lookup_rcu which is
+         * required to prevent single threaded performance regressions
+         * especially on architectures where smp_rmb (in seqcounts) are costly.
+         * Keep the two functions in sync.
+         */
+
+        /*
+         * The hash list is protected using RCU.
+         *
+         * Carefully use d_seq when comparing a candidate dentry, to avoid
+         * races with d_move().
+         *
+         * It is possible that concurrent renames can mess up our list
+         * walk here and result in missing our dentry, resulting in the
+         * false-negative result. d_lookup() protects against concurrent
+         * renames using rename_lock seqlock.
+         *
+         * See Documentation/vfs/dcache-locking.txt for more details.
+         */
+        hlist_bl_for_each_entry_rcu(dentry, node, &b->head, d_hash) {
+                struct inode *i;
+                const char *tname;
+                int tlen;
+
+                if (dentry->d_name.hash != hash)
+                        continue;
+
+seqretry:
+                *seq = read_seqcount_begin(&dentry->d_seq);
+                if (dentry->d_parent != parent)
+                        continue;
+                if (d_unhashed(dentry))
+                        continue;
+                tlen = dentry->d_name.len;
+                tname = dentry->d_name.name;
+                i = dentry->d_inode;
+                prefetch(tname);
+                if (i)
+                        prefetch(i);
+                /*
+                 * This seqcount check is required to ensure name and
+                 * len are loaded atomically, so as not to walk off the
+                 * edge of memory when walking. If we could load this
+                 * atomically some other way, we could drop this check.
+                 */
+                if (read_seqcount_retry(&dentry->d_seq, *seq))
+                        goto seqretry;
+                if (parent->d_flags & DCACHE_OP_COMPARE) {
+                        if (parent->d_op->d_compare(parent, *inode,
+                                                dentry, i,
+                                                tlen, tname, name))
+                                continue;
+                } else {
+                        if (dentry_cmp(tname, tlen, str, len))
+                                continue;
+                }
+                /*
+                 * No extra seqcount check is required after the name
+                 * compare. The caller must perform a seqcount check in
+                 * order to do anything useful with the returned dentry
+                 * anyway.
+                 */
+                *inode = i;
+                return dentry;
+        }
+        return NULL;
+}
+
+/**
  * d_lookup - search for a dentry
  * @parent: parent dentry
  * @name: qstr of name we wish to find
@@ -1352,10 +1834,10 @@ EXPORT_SYMBOL(d_add_ci);
  * dentry is returned. The caller must use dput to free the entry when it has
  * finished using it. %NULL is returned if the dentry does not exist.
  */
-struct dentry * d_lookup(struct dentry * parent, struct qstr * name)
+struct dentry *d_lookup(struct dentry *parent, struct qstr *name)
 {
-        struct dentry * dentry = NULL;
-        unsigned long seq;
+        struct dentry *dentry;
+        unsigned seq;
 
         do {
                 seq = read_seqbegin(&rename_lock);
@@ -1367,7 +1849,7 @@ struct dentry * d_lookup(struct dentry * parent, struct qstr * name)
 }
 EXPORT_SYMBOL(d_lookup);
 
-/*
+/**
  * __d_lookup - search for a dentry (racy)
  * @parent: parent dentry
  * @name: qstr of name we wish to find
@@ -1382,17 +1864,24 @@ EXPORT_SYMBOL(d_lookup);
  *
  * __d_lookup callers must be commented.
  */
-struct dentry * __d_lookup(struct dentry * parent, struct qstr * name)
+struct dentry *__d_lookup(struct dentry *parent, struct qstr *name)
 {
         unsigned int len = name->len;
         unsigned int hash = name->hash;
         const unsigned char *str = name->name;
-        struct hlist_head *head = d_hash(parent,hash);
+        struct dcache_hash_bucket *b = d_hash(parent, hash);
+        struct hlist_bl_node *node;
         struct dentry *found = NULL;
-        struct hlist_node *node;
         struct dentry *dentry;
 
         /*
+         * Note: There is significant duplication with __d_lookup_rcu which is
+         * required to prevent single threaded performance regressions
+         * especially on architectures where smp_rmb (in seqcounts) are costly.
+         * Keep the two functions in sync.
+         */
+
+        /*
          * The hash list is protected using RCU.
          *
          * Take d_lock when comparing a candidate dentry, to avoid races
@@ -1407,25 +1896,16 @@ struct dentry * __d_lookup(struct dentry * parent, struct qstr * name)
          */
         rcu_read_lock();
         
-        hlist_for_each_entry_rcu(dentry, node, head, d_hash) {
-                struct qstr *qstr;
+        hlist_bl_for_each_entry_rcu(dentry, node, &b->head, d_hash) {
+                const char *tname;
+                int tlen;
 
                 if (dentry->d_name.hash != hash)
                         continue;
-                if (dentry->d_parent != parent)
-                        continue;
 
                 spin_lock(&dentry->d_lock);
-
-                /*
-                 * Recheck the dentry after taking the lock - d_move may have
-                 * changed things. Don't bother checking the hash because
-                 * we're about to compare the whole name anyway.
-                 */
                 if (dentry->d_parent != parent)
                         goto next;
-
-                /* non-existing due to RCU? */
                 if (d_unhashed(dentry))
                         goto next;
 
@@ -1433,18 +1913,19 @@ struct dentry * __d_lookup(struct dentry * parent, struct qstr * name)
                  * It is safe to compare names since d_move() cannot
                  * change the qstr (protected by d_lock).
                  */
-                qstr = &dentry->d_name;
-                if (parent->d_op && parent->d_op->d_compare) {
-                        if (parent->d_op->d_compare(parent, qstr, name))
+                tlen = dentry->d_name.len;
+                tname = dentry->d_name.name;
+                if (parent->d_flags & DCACHE_OP_COMPARE) {
+                        if (parent->d_op->d_compare(parent, parent->d_inode,
+                                                dentry, dentry->d_inode,
+                                                tlen, tname, name))
                                 goto next;
                 } else {
-                        if (qstr->len != len)
-                                goto next;
-                        if (memcmp(qstr->name, str, len))
+                        if (dentry_cmp(tname, tlen, str, len))
                                 goto next;
                 }
 
-                atomic_inc(&dentry->d_count);
+                dentry->d_count++;
                 found = dentry;
                 spin_unlock(&dentry->d_lock);
                 break;
@@ -1473,8 +1954,8 @@ struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name)
          * routine may choose to leave the hash value unchanged.
          */
         name->hash = full_name_hash(name->name, name->len);
-        if (dir->d_op && dir->d_op->d_hash) {
-                if (dir->d_op->d_hash(dir, name) < 0)
+        if (dir->d_flags & DCACHE_OP_HASH) {
+                if (dir->d_op->d_hash(dir, dir->d_inode, name) < 0)
                         goto out;
         }
         dentry = d_lookup(dir, name);
@@ -1483,34 +1964,32 @@ out:
 }
 
 /**
- * d_validate - verify dentry provided from insecure source
+ * d_validate - verify dentry provided from insecure source (deprecated)
  * @dentry: The dentry alleged to be valid child of @dparent
  * @dparent: The parent dentry (known to be valid)
  *
  * An insecure source has sent us a dentry, here we verify it and dget() it.
  * This is used by ncpfs in its readdir implementation.
  * Zero is returned in the dentry is invalid.
+ *
+ * This function is slow for big directories, and deprecated, do not use it.
  */
-int d_validate(struct dentry *dentry, struct dentry *parent)
+int d_validate(struct dentry *dentry, struct dentry *dparent)
 {
-        struct hlist_head *head = d_hash(parent, dentry->d_name.hash);
-        struct hlist_node *node;
-        struct dentry *d;
-
-        /* Check whether the ptr might be valid at all.. */
-        if (!kmem_ptr_validate(dentry_cache, dentry))
-                return 0;
-        if (dentry->d_parent != parent)
-                return 0;
+        struct dentry *child;
 
-        rcu_read_lock();
-        hlist_for_each_entry_rcu(d, node, head, d_hash) {
-                if (d == dentry) {
-                        dget(dentry);
+        spin_lock(&dparent->d_lock);
+        list_for_each_entry(child, &dparent->d_subdirs, d_u.d_child) {
+                if (dentry == child) {
+                        spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
+                        __dget_dlock(dentry);
+                        spin_unlock(&dentry->d_lock);
+                        spin_unlock(&dparent->d_lock);
                         return 1;
                 }
         }
-        rcu_read_unlock();
+        spin_unlock(&dparent->d_lock);
+
         return 0;
 }
 EXPORT_SYMBOL(d_validate);
@@ -1538,16 +2017,23 @@ EXPORT_SYMBOL(d_validate);
  
 void d_delete(struct dentry * dentry)
 {
+        struct inode *inode;
         int isdir = 0;
         /*
          * Are we the only user?
          */
-        spin_lock(&dcache_lock);
+again:
         spin_lock(&dentry->d_lock);
-        isdir = S_ISDIR(dentry->d_inode->i_mode);
-        if (atomic_read(&dentry->d_count) == 1) {
+        inode = dentry->d_inode;
+        isdir = S_ISDIR(inode->i_mode);
+        if (dentry->d_count == 1) {
+                if (inode && !spin_trylock(&inode->i_lock)) {
+                        spin_unlock(&dentry->d_lock);
+                        cpu_relax();
+                        goto again;
+                }
                 dentry->d_flags &= ~DCACHE_CANT_MOUNT;
-                dentry_iput(dentry);
+                dentry_unlink_inode(dentry);
                 fsnotify_nameremove(dentry, isdir);
                 return;
         }
@@ -1556,17 +2042,18 @@ void d_delete(struct dentry * dentry)
                 __d_drop(dentry);
 
         spin_unlock(&dentry->d_lock);
-        spin_unlock(&dcache_lock);
 
         fsnotify_nameremove(dentry, isdir);
 }
 EXPORT_SYMBOL(d_delete);
 
-static void __d_rehash(struct dentry * entry, struct hlist_head *list)
+static void __d_rehash(struct dentry * entry, struct dcache_hash_bucket *b)
 {
-
+        BUG_ON(!d_unhashed(entry));
+        spin_lock_bucket(b);
         entry->d_flags &= ~DCACHE_UNHASHED;
-        hlist_add_head_rcu(&entry->d_hash, list);
+        hlist_bl_add_head_rcu(&entry->d_hash, &b->head);
+        spin_unlock_bucket(b);
 }
 
 static void _d_rehash(struct dentry * entry)
@@ -1583,25 +2070,39 @@ static void _d_rehash(struct dentry * entry)
  
 void d_rehash(struct dentry * entry)
 {
-        spin_lock(&dcache_lock);
         spin_lock(&entry->d_lock);
         _d_rehash(entry);
         spin_unlock(&entry->d_lock);
-        spin_unlock(&dcache_lock);
 }
 EXPORT_SYMBOL(d_rehash);
 
-/*
- * When switching names, the actual string doesn't strictly have to
- * be preserved in the target - because we're dropping the target
- * anyway. As such, we can just do a simple memcpy() to copy over
- * the new name before we switch.
+/**
+ * dentry_update_name_case - update case insensitive dentry with a new name
+ * @dentry: dentry to be updated
+ * @name: new name
  *
- * Note that we have to be a lot more careful about getting the hash
- * switched - we have to switch the hash value properly even if it
- * then no longer matches the actual (corrupted) string of the target.
- * The hash value has to match the hash queue that the dentry is on..
+ * Update a case insensitive dentry with new case of name.
+ *
+ * dentry must have been returned by d_lookup with name @name. Old and new
+ * name lengths must match (ie. no d_compare which allows mismatched name
+ * lengths).
+ *
+ * Parent inode i_mutex must be held over d_lookup and into this call (to
+ * keep renames and concurrent inserts, and readdir(2) away).
  */
+void dentry_update_name_case(struct dentry *dentry, struct qstr *name)
+{
+        BUG_ON(!mutex_is_locked(&dentry->d_inode->i_mutex));
+        BUG_ON(dentry->d_name.len != name->len); /* d_lookup gives this */
+
+        spin_lock(&dentry->d_lock);
+        write_seqcount_begin(&dentry->d_seq);
+        memcpy((unsigned char *)dentry->d_name.name, name->name, name->len);
+        write_seqcount_end(&dentry->d_seq);
+        spin_unlock(&dentry->d_lock);
+}
+EXPORT_SYMBOL(dentry_update_name_case);
+
 static void switch_names(struct dentry *dentry, struct dentry *target)
 {
         if (dname_external(target)) {
@@ -1643,54 +2144,84 @@ static void switch_names(struct dentry *dentry, struct dentry *target)
         swap(dentry->d_name.len, target->d_name.len);
 }
 
+static void dentry_lock_for_move(struct dentry *dentry, struct dentry *target)
+{
+        /*
+         * XXXX: do we really need to take target->d_lock?
+         */
+        if (IS_ROOT(dentry) || dentry->d_parent == target->d_parent)
+                spin_lock(&target->d_parent->d_lock);
+        else {
+                if (d_ancestor(dentry->d_parent, target->d_parent)) {
+                        spin_lock(&dentry->d_parent->d_lock);
+                        spin_lock_nested(&target->d_parent->d_lock,
+                                                DENTRY_D_LOCK_NESTED);
+                } else {
+                        spin_lock(&target->d_parent->d_lock);
+                        spin_lock_nested(&dentry->d_parent->d_lock,
+                                                DENTRY_D_LOCK_NESTED);
+                }
+        }
+        if (target < dentry) {
+                spin_lock_nested(&target->d_lock, 2);
+                spin_lock_nested(&dentry->d_lock, 3);
+        } else {
+                spin_lock_nested(&dentry->d_lock, 2);
+                spin_lock_nested(&target->d_lock, 3);
+        }
+}
+
+static void dentry_unlock_parents_for_move(struct dentry *dentry,
+                                        struct dentry *target)
+{
+        if (target->d_parent != dentry->d_parent)
+                spin_unlock(&dentry->d_parent->d_lock);
+        if (target->d_parent != target)
+                spin_unlock(&target->d_parent->d_lock);
+}
+
 /*
- * We cannibalize "target" when moving dentry on top of it,
- * because it's going to be thrown away anyway. We could be more
- * polite about it, though.
- *
- * This forceful removal will result in ugly /proc output if
- * somebody holds a file open that got deleted due to a rename.
- * We could be nicer about the deleted file, and let it show
- * up under the name it had before it was deleted rather than
- * under the original name of the file that was moved on top of it.
+ * When switching names, the actual string doesn't strictly have to
+ * be preserved in the target - because we're dropping the target
+ * anyway. As such, we can just do a simple memcpy() to copy over
+ * the new name before we switch.
+ *
+ * Note that we have to be a lot more careful about getting the hash
+ * switched - we have to switch the hash value properly even if it
+ * then no longer matches the actual (corrupted) string of the target.
+ * The hash value has to match the hash queue that the dentry is on..
  */
- 
 /*
- * d_move_locked - move a dentry
+ * d_move - move a dentry
  * @dentry: entry to move
  * @target: new dentry
  *
  * Update the dcache to reflect the move of a file name. Negative
  * dcache entries should not be moved in this way.
  */
-static void d_move_locked(struct dentry * dentry, struct dentry * target)
+void d_move(struct dentry * dentry, struct dentry * target)
 {
-        struct hlist_head *list;
-
         if (!dentry->d_inode)
                 printk(KERN_WARNING "VFS: moving negative dcache entry\n");
 
+        BUG_ON(d_ancestor(dentry, target));
+        BUG_ON(d_ancestor(target, dentry));
+
         write_seqlock(&rename_lock);
-        /*
-         * XXXX: do we really need to take target->d_lock?
-         */
-        if (target < dentry) {
-                spin_lock(&target->d_lock);
-                spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
-        } else {
-                spin_lock(&dentry->d_lock);
-                spin_lock_nested(&target->d_lock, DENTRY_D_LOCK_NESTED);
-        }
 
-        /* Move the dentry to the target hash queue, if on different bucket */
-        if (d_unhashed(dentry))
-                goto already_unhashed;
+        dentry_lock_for_move(dentry, target);
 
-        hlist_del_rcu(&dentry->d_hash);
+        write_seqcount_begin(&dentry->d_seq);
+        write_seqcount_begin(&target->d_seq);
 
-already_unhashed:
-        list = d_hash(target->d_parent, target->d_name.hash);
-        __d_rehash(dentry, list);
+        /* __d_drop does write_seqcount_barrier, but they're OK to nest. */
+
+        /*
+         * Move the dentry to the target hash queue. Don't bother checking
+         * for the same hash queue because of how unlikely it is.
+         */
+        __d_drop(dentry);
+        __d_rehash(dentry, d_hash(target->d_parent, target->d_name.hash));
 
         /* Unhash the target: dput() will then get rid of it */
         __d_drop(target);
@@ -1715,27 +2246,16 @@ already_unhashed:
         }
 
         list_add(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs);
+
+        write_seqcount_end(&target->d_seq);
+        write_seqcount_end(&dentry->d_seq);
+
+        dentry_unlock_parents_for_move(dentry, target);
         spin_unlock(&target->d_lock);
         fsnotify_d_move(dentry);
         spin_unlock(&dentry->d_lock);
         write_sequnlock(&rename_lock);
 }
-
-/**
- * d_move - move a dentry
- * @dentry: entry to move
- * @target: new dentry
- *
- * Update the dcache to reflect the move of a file name. Negative
- * dcache entries should not be moved in this way.
- */
-
-void d_move(struct dentry * dentry, struct dentry * target)
-{
-        spin_lock(&dcache_lock);
-        d_move_locked(dentry, target);
-        spin_unlock(&dcache_lock);
-}
 EXPORT_SYMBOL(d_move);
 
 /**
@@ -1761,13 +2281,13 @@ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2)
  * This helper attempts to cope with remotely renamed directories
  *
  * It assumes that the caller is already holding
- * dentry->d_parent->d_inode->i_mutex and the dcache_lock
+ * dentry->d_parent->d_inode->i_mutex and the inode->i_lock
  *
  * Note: If ever the locking in lock_rename() changes, then please
  * remember to update this too...
  */
-static struct dentry *__d_unalias(struct dentry *dentry, struct dentry *alias)
-        __releases(dcache_lock)
+static struct dentry *__d_unalias(struct inode *inode,
+                struct dentry *dentry, struct dentry *alias)
 {
         struct mutex *m1 = NULL, *m2 = NULL;
         struct dentry *ret;
@@ -1790,10 +2310,10 @@ static struct dentry *__d_unalias(struct dentry *dentry, struct dentry *alias)
                 goto out_err;
         m2 = &alias->d_parent->d_inode->i_mutex;
 out_unalias:
-        d_move_locked(alias, dentry);
+        d_move(alias, dentry);
         ret = alias;
 out_err:
-        spin_unlock(&dcache_lock);
+        spin_unlock(&inode->i_lock);
         if (m2)
                 mutex_unlock(m2);
         if (m1)
@@ -1804,17 +2324,23 @@ out_err:
 /*
  * Prepare an anonymous dentry for life in the superblock's dentry tree as a
  * named dentry in place of the dentry to be replaced.
+ * returns with anon->d_lock held!
  */
 static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon)
 {
         struct dentry *dparent, *aparent;
 
-        switch_names(dentry, anon);
-        swap(dentry->d_name.hash, anon->d_name.hash);
+        dentry_lock_for_move(anon, dentry);
+
+        write_seqcount_begin(&dentry->d_seq);
+        write_seqcount_begin(&anon->d_seq);
 
         dparent = dentry->d_parent;
         aparent = anon->d_parent;
 
+        switch_names(dentry, anon);
+        swap(dentry->d_name.hash, anon->d_name.hash);
+
         dentry->d_parent = (aparent == anon) ? dentry : aparent;
         list_del(&dentry->d_u.d_child);
         if (!IS_ROOT(dentry))
@@ -1829,6 +2355,13 @@ static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon)
         else
                 INIT_LIST_HEAD(&anon->d_u.d_child);
 
+        write_seqcount_end(&dentry->d_seq);
+        write_seqcount_end(&anon->d_seq);
+
+        dentry_unlock_parents_for_move(anon, dentry);
+        spin_unlock(&dentry->d_lock);
+
+        /* anon->d_lock still locked, returns locked */
         anon->d_flags &= ~DCACHE_DISCONNECTED;
 }
 
@@ -1846,14 +2379,15 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
 
         BUG_ON(!d_unhashed(dentry));
 
-        spin_lock(&dcache_lock);
-
         if (!inode) {
                 actual = dentry;
                 __d_instantiate(dentry, NULL);
-                goto found_lock;
+                d_rehash(actual);
+                goto out_nolock;
         }
 
+        spin_lock(&inode->i_lock);
+
         if (S_ISDIR(inode->i_mode)) {
                 struct dentry *alias;
 
@@ -1864,13 +2398,12 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
                         /* Is this an anonymous mountpoint that we could splice
                          * into our tree? */
                         if (IS_ROOT(alias)) {
-                                spin_lock(&alias->d_lock);
                                 __d_materialise_dentry(dentry, alias);
                                 __d_drop(alias);
                                 goto found;
                         }
                         /* Nope, but we must(!) avoid directory aliasing */
-                        actual = __d_unalias(dentry, alias);
+                        actual = __d_unalias(inode, dentry, alias);
                         if (IS_ERR(actual))
                                 dput(alias);
                         goto out_nolock;
@@ -1881,15 +2414,14 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
         actual = __d_instantiate_unique(dentry, inode);
         if (!actual)
                 actual = dentry;
-        else if (unlikely(!d_unhashed(actual)))
-                goto shouldnt_be_hashed;
+        else
+                BUG_ON(!d_unhashed(actual));
 
-found_lock:
         spin_lock(&actual->d_lock);
 found:
         _d_rehash(actual);
         spin_unlock(&actual->d_lock);
-        spin_unlock(&dcache_lock);
+        spin_unlock(&inode->i_lock);
 out_nolock:
         if (actual == dentry) {
                 security_d_instantiate(dentry, inode);
@@ -1898,10 +2430,6 @@ out_nolock:
 
         iput(inode);
         return actual;
-
-shouldnt_be_hashed:
-        spin_unlock(&dcache_lock);
-        BUG();
 }
 EXPORT_SYMBOL_GPL(d_materialise_unique);
 
@@ -1928,7 +2456,7 @@ static int prepend_name(char **buffer, int *buflen, struct qstr *name)
  * @buffer: pointer to the end of the buffer
  * @buflen: pointer to buffer length
  *
- * Caller holds the dcache_lock.
+ * Caller holds the rename_lock.
  *
  * If path is not reachable from the supplied root, then the value of
  * root is changed (without modifying refcounts).
@@ -1956,7 +2484,9 @@ static int prepend_path(const struct path *path, struct path *root,
                 }
                 parent = dentry->d_parent;
                 prefetch(parent);
+                spin_lock(&dentry->d_lock);
                 error = prepend_name(buffer, buflen, &dentry->d_name);
+                spin_unlock(&dentry->d_lock);
                 if (!error)
                         error = prepend(buffer, buflen, "/", 1);
                 if (error)
@@ -2012,9 +2542,9 @@ char *__d_path(const struct path *path, struct path *root,
         int error;
 
         prepend(&res, &buflen, "\0", 1);
-        spin_lock(&dcache_lock);
+        write_seqlock(&rename_lock);
         error = prepend_path(path, root, &res, &buflen);
-        spin_unlock(&dcache_lock);
+        write_sequnlock(&rename_lock);
 
         if (error)
                 return ERR_PTR(error);
@@ -2076,12 +2606,12 @@ char *d_path(const struct path *path, char *buf, int buflen)
                 return path->dentry->d_op->d_dname(path->dentry, buf, buflen);
 
         get_fs_root(current->fs, &root);
-        spin_lock(&dcache_lock);
+        write_seqlock(&rename_lock);
         tmp = root;
         error = path_with_deleted(path, &tmp, &res, &buflen);
         if (error)
                 res = ERR_PTR(error);
-        spin_unlock(&dcache_lock);
+        write_sequnlock(&rename_lock);
         path_put(&root);
         return res;
 }
@@ -2107,12 +2637,12 @@ char *d_path_with_unreachable(const struct path *path, char *buf, int buflen)
                 return path->dentry->d_op->d_dname(path->dentry, buf, buflen);
 
         get_fs_root(current->fs, &root);
-        spin_lock(&dcache_lock);
+        write_seqlock(&rename_lock);
         tmp = root;
         error = path_with_deleted(path, &tmp, &res, &buflen);
         if (!error && !path_equal(&tmp, &root))
                 error = prepend_unreachable(&res, &buflen);
-        spin_unlock(&dcache_lock);
+        write_sequnlock(&rename_lock);
         path_put(&root);
         if (error)
                 res =  ERR_PTR(error);
@@ -2144,7 +2674,7 @@ char *dynamic_dname(struct dentry *dentry, char *buffer, int buflen,
 /*
  * Write full pathname from the root of the filesystem into the buffer.
  */
-char *__dentry_path(struct dentry *dentry, char *buf, int buflen)
+static char *__dentry_path(struct dentry *dentry, char *buf, int buflen)
 {
         char *end = buf + buflen;
         char *retval;
@@ -2158,10 +2688,13 @@ char *__dentry_path(struct dentry *dentry, char *buf, int buflen)
 
         while (!IS_ROOT(dentry)) {
                 struct dentry *parent = dentry->d_parent;
+                int error;
 
                 prefetch(parent);
-                if ((prepend_name(&end, &buflen, &dentry->d_name) != 0) ||
-                    (prepend(&end, &buflen, "/", 1) != 0))
+                spin_lock(&dentry->d_lock);
+                error = prepend_name(&end, &buflen, &dentry->d_name);
+                spin_unlock(&dentry->d_lock);
+                if (error != 0 || prepend(&end, &buflen, "/", 1) != 0)
                         goto Elong;
 
                 retval = end;
@@ -2171,14 +2704,25 @@ char *__dentry_path(struct dentry *dentry, char *buf, int buflen)
 Elong:
         return ERR_PTR(-ENAMETOOLONG);
 }
-EXPORT_SYMBOL(__dentry_path);
+
+char *dentry_path_raw(struct dentry *dentry, char *buf, int buflen)
+{
+        char *retval;
+
+        write_seqlock(&rename_lock);
+        retval = __dentry_path(dentry, buf, buflen);
+        write_sequnlock(&rename_lock);
+
+        return retval;
+}
+EXPORT_SYMBOL(dentry_path_raw);
 
 char *dentry_path(struct dentry *dentry, char *buf, int buflen)
 {
         char *p = NULL;
         char *retval;
 
-        spin_lock(&dcache_lock);
+        write_seqlock(&rename_lock);
         if (d_unlinked(dentry)) {
                 p = buf + buflen;
                 if (prepend(&p, &buflen, "//deleted", 10) != 0)
@@ -2186,12 +2730,11 @@ char *dentry_path(struct dentry *dentry, char *buf, int buflen)
                 buflen++;
         }
         retval = __dentry_path(dentry, buf, buflen);
-        spin_unlock(&dcache_lock);
+        write_sequnlock(&rename_lock);
         if (!IS_ERR(retval) && p)
                 *p = '/';       /* restore '/' overriden with '\0' */
         return retval;
 Elong:
-        spin_unlock(&dcache_lock);
         return ERR_PTR(-ENAMETOOLONG);
 }
 
@@ -2225,7 +2768,7 @@ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
         get_fs_root_and_pwd(current->fs, &root, &pwd);
 
         error = -ENOENT;
-        spin_lock(&dcache_lock);
+        write_seqlock(&rename_lock);
         if (!d_unlinked(pwd.dentry)) {
                 unsigned long len;
                 struct path tmp = root;
@@ -2234,7 +2777,7 @@ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
 
                 prepend(&cwd, &buflen, "\0", 1);
                 error = prepend_path(&pwd, &tmp, &cwd, &buflen);
-                spin_unlock(&dcache_lock);
+                write_sequnlock(&rename_lock);
 
                 if (error)
                         goto out;
@@ -2253,8 +2796,9 @@ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
                         if (copy_to_user(buf, cwd, len))
                                 error = -EFAULT;
                 }
-        } else
-                spin_unlock(&dcache_lock);
+        } else {
+                write_sequnlock(&rename_lock);
+        }
 
 out:
         path_put(&pwd);
@@ -2282,25 +2826,25 @@ out:
 int is_subdir(struct dentry *new_dentry, struct dentry *old_dentry)
 {
         int result;
-        unsigned long seq;
+        unsigned seq;
 
         if (new_dentry == old_dentry)
                 return 1;
 
-        /*
-         * Need rcu_readlock to protect against the d_parent trashing
-         * due to d_move
-         */
-        rcu_read_lock();
         do {
                 /* for restarting inner loop in case of seq retry */
                 seq = read_seqbegin(&rename_lock);
+                /*
+                 * Need rcu_readlock to protect against the d_parent trashing
+                 * due to d_move
+                 */
+                rcu_read_lock();
                 if (d_ancestor(old_dentry, new_dentry))
                         result = 1;
                 else
                         result = 0;
+                rcu_read_unlock();
         } while (read_seqretry(&rename_lock, seq));
-        rcu_read_unlock();
 
         return result;
 }
@@ -2332,10 +2876,15 @@ EXPORT_SYMBOL(path_is_under);
 
 void d_genocide(struct dentry *root)
 {
-        struct dentry *this_parent = root;
+        struct dentry *this_parent;
         struct list_head *next;
+        unsigned seq;
+        int locked = 0;
 
-        spin_lock(&dcache_lock);
+        seq = read_seqbegin(&rename_lock);
+again:
+        this_parent = root;
+        spin_lock(&this_parent->d_lock);
 repeat:
         next = this_parent->d_subdirs.next;
 resume:
@@ -2343,21 +2892,62 @@ resume:
                 struct list_head *tmp = next;
                 struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
                 next = tmp->next;
-                if (d_unhashed(dentry)||!dentry->d_inode)
+
+                spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
+                if (d_unhashed(dentry) || !dentry->d_inode) {
+                        spin_unlock(&dentry->d_lock);
                         continue;
+                }
                 if (!list_empty(&dentry->d_subdirs)) {
+                        spin_unlock(&this_parent->d_lock);
+                        spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_);
                         this_parent = dentry;
+                        spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_);
                         goto repeat;
                 }
-                atomic_dec(&dentry->d_count);
+                if (!(dentry->d_flags & DCACHE_GENOCIDE)) {
+                        dentry->d_flags |= DCACHE_GENOCIDE;
+                        dentry->d_count--;
+                }
+                spin_unlock(&dentry->d_lock);
         }
         if (this_parent != root) {
-                next = this_parent->d_u.d_child.next;
-                atomic_dec(&this_parent->d_count);
-                this_parent = this_parent->d_parent;
+                struct dentry *tmp;
+                struct dentry *child;
+
+                tmp = this_parent->d_parent;
+                if (!(this_parent->d_flags & DCACHE_GENOCIDE)) {
+                        this_parent->d_flags |= DCACHE_GENOCIDE;
+                        this_parent->d_count--;
+                }
+                rcu_read_lock();
+                spin_unlock(&this_parent->d_lock);
+                child = this_parent;
+                this_parent = tmp;
+                spin_lock(&this_parent->d_lock);
+                /* might go back up the wrong parent if we have had a rename
+                 * or deletion */
+                if (this_parent != child->d_parent ||
+                         (!locked && read_seqretry(&rename_lock, seq))) {
+                        spin_unlock(&this_parent->d_lock);
+                        rcu_read_unlock();
+                        goto rename_retry;
+                }
+                rcu_read_unlock();
+                next = child->d_u.d_child.next;
                 goto resume;
         }
-        spin_unlock(&dcache_lock);
+        spin_unlock(&this_parent->d_lock);
+        if (!locked && read_seqretry(&rename_lock, seq))
+                goto rename_retry;
+        if (locked)
+                write_sequnlock(&rename_lock);
+        return;
+
+rename_retry:
+        locked = 1;
+        write_seqlock(&rename_lock);
+        goto again;
 }
 
 /**
@@ -2411,7 +3001,7 @@ static void __init dcache_init_early(void)
 
         dentry_hashtable =
                 alloc_large_system_hash("Dentry cache",
-                                        sizeof(struct hlist_head),
+                                        sizeof(struct dcache_hash_bucket),
                                         dhash_entries,
                                         13,
                                         HASH_EARLY,
@@ -2420,16 +3010,13 @@ static void __init dcache_init_early(void)
                                         0);
 
         for (loop = 0; loop < (1 << d_hash_shift); loop++)
-                INIT_HLIST_HEAD(&dentry_hashtable[loop]);
+                INIT_HLIST_BL_HEAD(&dentry_hashtable[loop].head);
 }
 
 static void __init dcache_init(void)
 {
         int loop;
 
-        percpu_counter_init(&nr_dentry, 0);
-        percpu_counter_init(&nr_dentry_unused, 0);
-
         /* 
          * A constructor could be added for stable state like the lists,
          * but it is probably not worth it because of the cache nature
@@ -2446,7 +3033,7 @@ static void __init dcache_init(void)
 
         dentry_hashtable =
                 alloc_large_system_hash("Dentry cache",
-                                        sizeof(struct hlist_head),
+                                        sizeof(struct dcache_hash_bucket),
                                         dhash_entries,
                                         13,
                                         0,
@@ -2455,7 +3042,7 @@ static void __init dcache_init(void)
                                         0);
 
         for (loop = 0; loop < (1 << d_hash_shift); loop++)
-                INIT_HLIST_HEAD(&dentry_hashtable[loop]);
+                INIT_HLIST_BL_HEAD(&dentry_hashtable[loop].head);
 }
 
 /* SLAB cache for __getname() consumers */
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 37a34c2c622a..9c64ae9e4c1a 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -63,6 +63,9 @@
 #define NEEDED_RMEM (4*1024*1024)
 #define CONN_HASH_SIZE 32
 
+/* Number of messages to send before rescheduling */
+#define MAX_SEND_MSG_COUNT 25
+
 struct cbuf {
         unsigned int base;
         unsigned int len;
@@ -108,6 +111,7 @@ struct connection {
 #define CF_INIT_PENDING 4
 #define CF_IS_OTHERCON 5
 #define CF_CLOSE 6
+#define CF_APP_LIMITED 7
         struct list_head writequeue;  /* List of outgoing writequeue_entries */
         spinlock_t writequeue_lock;
         int (*rx_action) (struct connection *); /* What to do when active */
@@ -295,7 +299,17 @@ static void lowcomms_write_space(struct sock *sk)
 {
         struct connection *con = sock2con(sk);
 
-        if (con && !test_and_set_bit(CF_WRITE_PENDING, &con->flags))
+        if (!con)
+                return;
+
+        clear_bit(SOCK_NOSPACE, &con->sock->flags);
+
+        if (test_and_clear_bit(CF_APP_LIMITED, &con->flags)) {
+                con->sock->sk->sk_write_pending--;
+                clear_bit(SOCK_ASYNC_NOSPACE, &con->sock->flags);
+        }
+
+        if (!test_and_set_bit(CF_WRITE_PENDING, &con->flags))
                 queue_work(send_workqueue, &con->swork);
 }
 
@@ -915,6 +929,7 @@ static void tcp_connect_to_sock(struct connection *con)
         struct sockaddr_storage saddr, src_addr;
         int addr_len;
         struct socket *sock = NULL;
+        int one = 1;
 
         if (con->nodeid == 0) {
                 log_print("attempt to connect sock 0 foiled");
@@ -960,6 +975,11 @@ static void tcp_connect_to_sock(struct connection *con)
         make_sockaddr(&saddr, dlm_config.ci_tcp_port, &addr_len);
 
         log_print("connecting to %d", con->nodeid);
+
+        /* Turn off Nagle's algorithm */
+        kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (char *)&one,
+                          sizeof(one));
+
         result =
                 sock->ops->connect(sock, (struct sockaddr *)&saddr, addr_len,
                                    O_NONBLOCK);
@@ -1011,6 +1031,10 @@ static struct socket *tcp_create_listen_sock(struct connection *con,
                 goto create_out;
         }
 
+        /* Turn off Nagle's algorithm */
+        kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (char *)&one,
+                          sizeof(one));
+
         result = kernel_setsockopt(sock, SOL_SOCKET, SO_REUSEADDR,
                                    (char *)&one, sizeof(one));
 
@@ -1297,6 +1321,7 @@ static void send_to_sock(struct connection *con)
         const int msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL;
         struct writequeue_entry *e;
         int len, offset;
+        int count = 0;
 
         mutex_lock(&con->sock_mutex);
         if (con->sock == NULL)
@@ -1319,14 +1344,27 @@ static void send_to_sock(struct connection *con)
                         ret = kernel_sendpage(con->sock, e->page, offset, len,
                                               msg_flags);
                         if (ret == -EAGAIN || ret == 0) {
+                                if (ret == -EAGAIN &&
+                                    test_bit(SOCK_ASYNC_NOSPACE, &con->sock->flags) &&
+                                    !test_and_set_bit(CF_APP_LIMITED, &con->flags)) {
+                                        /* Notify TCP that we're limited by the
+                                         * application window size.
+                                         */
+                                        set_bit(SOCK_NOSPACE, &con->sock->flags);
+                                        con->sock->sk->sk_write_pending++;
+                                }
                                 cond_resched();
                                 goto out;
                         }
                         if (ret <= 0)
                                 goto send_error;
                 }
-                        /* Don't starve people filling buffers */
+
+                /* Don't starve people filling buffers */
+                if (++count >= MAX_SEND_MSG_COUNT) {
                         cond_resched();
+                        count = 0;
+                }
 
                 spin_lock(&con->writequeue_lock);
                 e->offset += ret;
@@ -1430,20 +1468,19 @@ static void work_stop(void)
 
 static int work_start(void)
 {
-        int error;
-        recv_workqueue = create_workqueue("dlm_recv");
-        error = IS_ERR(recv_workqueue);
-        if (error) {
-                log_print("can't start dlm_recv %d", error);
-                return error;
+        recv_workqueue = alloc_workqueue("dlm_recv", WQ_MEM_RECLAIM |
+                                         WQ_HIGHPRI | WQ_FREEZEABLE, 0);
+        if (!recv_workqueue) {
+                log_print("can't start dlm_recv");
+                return -ENOMEM;
         }
 
-        send_workqueue = create_singlethread_workqueue("dlm_send");
-        error = IS_ERR(send_workqueue);
-        if (error) {
-                log_print("can't start dlm_send %d", error);
+        send_workqueue = alloc_workqueue("dlm_send", WQ_MEM_RECLAIM |
+                                         WQ_HIGHPRI | WQ_FREEZEABLE, 0);
+        if (!send_workqueue) {
+                log_print("can't start dlm_send");
                 destroy_workqueue(recv_workqueue);
-                return error;
+                return -ENOMEM;
         }
 
         return 0;
diff --git a/fs/ecryptfs/dentry.c b/fs/ecryptfs/dentry.c
index 906e803f7f79..6fc4f319b550 100644
--- a/fs/ecryptfs/dentry.c
+++ b/fs/ecryptfs/dentry.c
@@ -44,12 +44,17 @@
  */
 static int ecryptfs_d_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
-        struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
-        struct vfsmount *lower_mnt = ecryptfs_dentry_to_lower_mnt(dentry);
+        struct dentry *lower_dentry;
+        struct vfsmount *lower_mnt;
         struct dentry *dentry_save;
         struct vfsmount *vfsmount_save;
         int rc = 1;
 
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
+
+        lower_dentry = ecryptfs_dentry_to_lower(dentry);
+        lower_mnt = ecryptfs_dentry_to_lower_mnt(dentry);
         if (!lower_dentry->d_op || !lower_dentry->d_op->d_revalidate)
                 goto out;
         dentry_save = nd->path.dentry;
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 9d1a22d62765..337352a94751 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -260,7 +260,7 @@ int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
                                    ecryptfs_dentry->d_parent));
         lower_inode = lower_dentry->d_inode;
         fsstack_copy_attr_atime(ecryptfs_dir_inode, lower_dir_dentry->d_inode);
-        BUG_ON(!atomic_read(&lower_dentry->d_count));
+        BUG_ON(!lower_dentry->d_count);
         ecryptfs_set_dentry_private(ecryptfs_dentry,
                                     kmem_cache_alloc(ecryptfs_dentry_info_cache,
                                                      GFP_KERNEL));
@@ -441,7 +441,7 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
         struct qstr lower_name;
         int rc = 0;
 
-        ecryptfs_dentry->d_op = &ecryptfs_dops;
+        d_set_d_op(ecryptfs_dentry, &ecryptfs_dops);
         if ((ecryptfs_dentry->d_name.len == 1
              && !strcmp(ecryptfs_dentry->d_name.name, "."))
             || (ecryptfs_dentry->d_name.len == 2
@@ -454,7 +454,7 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
         lower_name.hash = ecryptfs_dentry->d_name.hash;
         if (lower_dir_dentry->d_op && lower_dir_dentry->d_op->d_hash) {
                 rc = lower_dir_dentry->d_op->d_hash(lower_dir_dentry,
-                                                    &lower_name);
+                                lower_dir_dentry->d_inode, &lower_name);
                 if (rc < 0)
                         goto out_d_drop;
         }
@@ -489,7 +489,7 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
         lower_name.hash = full_name_hash(lower_name.name, lower_name.len);
         if (lower_dir_dentry->d_op && lower_dir_dentry->d_op->d_hash) {
                 rc = lower_dir_dentry->d_op->d_hash(lower_dir_dentry,
-                                                    &lower_name);
+                                lower_dir_dentry->d_inode, &lower_name);
                 if (rc < 0)
                         goto out_d_drop;
         }
@@ -980,8 +980,10 @@ int ecryptfs_truncate(struct dentry *dentry, loff_t new_length)
 }
 
 static int
-ecryptfs_permission(struct inode *inode, int mask)
+ecryptfs_permission(struct inode *inode, int mask, unsigned int flags)
 {
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
         return inode_permission(ecryptfs_inode_to_lower(inode), mask);
 }
 
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index a9dbd62518e6..351038675376 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -189,7 +189,7 @@ int ecryptfs_interpose(struct dentry *lower_dentry, struct dentry *dentry,
         if (special_file(lower_inode->i_mode))
                 init_special_inode(inode, lower_inode->i_mode,
                                    lower_inode->i_rdev);
-        dentry->d_op = &ecryptfs_dops;
+        d_set_d_op(dentry, &ecryptfs_dops);
         fsstack_copy_attr_all(inode, lower_inode);
         /* This size will be overwritten for real files w/ headers and
          * other metadata */
@@ -594,7 +594,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
                 deactivate_locked_super(s);
                 goto out;
         }
-        s->s_root->d_op = &ecryptfs_dops;
+        d_set_d_op(s->s_root, &ecryptfs_dops);
         s->s_root->d_sb = s;
         s->s_root->d_parent = s->s_root;
 
diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c
index 2720178b7718..3042fe123a34 100644
--- a/fs/ecryptfs/super.c
+++ b/fs/ecryptfs/super.c
@@ -62,6 +62,16 @@ out:
         return inode;
 }
 
+static void ecryptfs_i_callback(struct rcu_head *head)
+{
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        struct ecryptfs_inode_info *inode_info;
+        inode_info = ecryptfs_inode_to_private(inode);
+
+        INIT_LIST_HEAD(&inode->i_dentry);
+        kmem_cache_free(ecryptfs_inode_info_cache, inode_info);
+}
+
 /**
  * ecryptfs_destroy_inode
  * @inode: The ecryptfs inode
@@ -88,7 +98,7 @@ static void ecryptfs_destroy_inode(struct inode *inode)
                 }
         }
         ecryptfs_destroy_crypt_stat(&inode_info->crypt_stat);
-        kmem_cache_free(ecryptfs_inode_info_cache, inode_info);
+        call_rcu(&inode->i_rcu, ecryptfs_i_callback);
 }
 
 /**
diff --git a/fs/efs/super.c b/fs/efs/super.c
index 5073a07652cc..0f31acb0131c 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -65,11 +65,18 @@ static struct inode *efs_alloc_inode(struct super_block *sb)
         return &ei->vfs_inode;
 }
 
-static void efs_destroy_inode(struct inode *inode)
+static void efs_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(efs_inode_cachep, INODE_INFO(inode));
 }
 
+static void efs_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, efs_i_callback);
+}
+
 static void init_once(void *foo)
 {
         struct efs_inode_info *ei = (struct efs_inode_info *) foo;
diff --git a/fs/exec.c b/fs/exec.c
index d68c378a3137..c62efcb959c7 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -275,6 +275,11 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
         vma->vm_flags = VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP;
         vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
         INIT_LIST_HEAD(&vma->anon_vma_chain);
+
+        err = security_file_mmap(NULL, 0, 0, 0, vma->vm_start, 1);
+        if (err)
+                goto err;
+
         err = insert_vm_struct(mm, vma);
         if (err)
                 goto err;
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 79c3ae6e0456..8c6c4669b381 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -150,12 +150,19 @@ static struct inode *exofs_alloc_inode(struct super_block *sb)
         return &oi->vfs_inode;
 }
 
+static void exofs_i_callback(struct rcu_head *head)
+{
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
+        kmem_cache_free(exofs_inode_cachep, exofs_i(inode));
+}
+
 /*
  * Remove an inode from the cache
  */
 static void exofs_destroy_inode(struct inode *inode)
 {
-        kmem_cache_free(exofs_inode_cachep, exofs_i(inode));
+        call_rcu(&inode->i_rcu, exofs_i_callback);
 }
 
 /*
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 51b304056f10..4b6825740dd5 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -43,24 +43,26 @@ find_acceptable_alias(struct dentry *result,
                 void *context)
 {
         struct dentry *dentry, *toput = NULL;
+        struct inode *inode;
 
         if (acceptable(context, result))
                 return result;
 
-        spin_lock(&dcache_lock);
-        list_for_each_entry(dentry, &result->d_inode->i_dentry, d_alias) {
-                dget_locked(dentry);
-                spin_unlock(&dcache_lock);
+        inode = result->d_inode;
+        spin_lock(&inode->i_lock);
+        list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+                dget(dentry);
+                spin_unlock(&inode->i_lock);
                 if (toput)
                         dput(toput);
                 if (dentry != result && acceptable(context, dentry)) {
                         dput(result);
                         return dentry;
                 }
-                spin_lock(&dcache_lock);
+                spin_lock(&inode->i_lock);
                 toput = dentry;
         }
-        spin_unlock(&dcache_lock);
+        spin_unlock(&inode->i_lock);
 
         if (toput)
                 dput(toput);
diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c
index 2bcc0431bada..7b4180554a62 100644
--- a/fs/ext2/acl.c
+++ b/fs/ext2/acl.c
@@ -232,10 +232,17 @@ ext2_set_acl(struct inode *inode, int type, struct posix_acl *acl)
 }
 
 int
-ext2_check_acl(struct inode *inode, int mask)
+ext2_check_acl(struct inode *inode, int mask, unsigned int flags)
 {
-        struct posix_acl *acl = ext2_get_acl(inode, ACL_TYPE_ACCESS);
+        struct posix_acl *acl;
+
+        if (flags & IPERM_FLAG_RCU) {
+                if (!negative_cached_acl(inode, ACL_TYPE_ACCESS))
+                        return -ECHILD;
+                return -EAGAIN;
+        }
 
+        acl = ext2_get_acl(inode, ACL_TYPE_ACCESS);
         if (IS_ERR(acl))
                 return PTR_ERR(acl);
         if (acl) {
diff --git a/fs/ext2/acl.h b/fs/ext2/acl.h
index 3ff6cbb9ac44..c939b7b12099 100644
--- a/fs/ext2/acl.h
+++ b/fs/ext2/acl.h
@@ -54,7 +54,7 @@ static inline int ext2_acl_count(size_t size)
 #ifdef CONFIG_EXT2_FS_POSIX_ACL
 
 /* acl.c */
-extern int ext2_check_acl (struct inode *, int);
+extern int ext2_check_acl (struct inode *, int, unsigned int);
 extern int ext2_acl_chmod (struct inode *);
 extern int ext2_init_acl (struct inode *, struct inode *);
 
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index d89e0b6a2d78..e0c6380ff992 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -161,11 +161,18 @@ static struct inode *ext2_alloc_inode(struct super_block *sb)
         return &ei->vfs_inode;
 }
 
-static void ext2_destroy_inode(struct inode *inode)
+static void ext2_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(ext2_inode_cachep, EXT2_I(inode));
 }
 
+static void ext2_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, ext2_i_callback);
+}
+
 static void init_once(void *foo)
 {
         struct ext2_inode_info *ei = (struct ext2_inode_info *) foo;
diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c
index 8a11fe212183..e4fa49e6c539 100644
--- a/fs/ext3/acl.c
+++ b/fs/ext3/acl.c
@@ -240,10 +240,17 @@ ext3_set_acl(handle_t *handle, struct inode *inode, int type,
 }
 
 int
-ext3_check_acl(struct inode *inode, int mask)
+ext3_check_acl(struct inode *inode, int mask, unsigned int flags)
 {
-        struct posix_acl *acl = ext3_get_acl(inode, ACL_TYPE_ACCESS);
+        struct posix_acl *acl;
+
+        if (flags & IPERM_FLAG_RCU) {
+                if (!negative_cached_acl(inode, ACL_TYPE_ACCESS))
+                        return -ECHILD;
+                return -EAGAIN;
+        }
 
+        acl = ext3_get_acl(inode, ACL_TYPE_ACCESS);
         if (IS_ERR(acl))
                 return PTR_ERR(acl);
         if (acl) {
diff --git a/fs/ext3/acl.h b/fs/ext3/acl.h
index 597334626de9..5faf8048e906 100644
--- a/fs/ext3/acl.h
+++ b/fs/ext3/acl.h
@@ -54,7 +54,7 @@ static inline int ext3_acl_count(size_t size)
 #ifdef CONFIG_EXT3_FS_POSIX_ACL
 
 /* acl.c */
-extern int ext3_check_acl (struct inode *, int);
+extern int ext3_check_acl (struct inode *, int, unsigned int);
 extern int ext3_acl_chmod (struct inode *);
 extern int ext3_init_acl (handle_t *, struct inode *, struct inode *);
 
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index acf8695fa8f0..77ce1616f725 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -479,6 +479,13 @@ static struct inode *ext3_alloc_inode(struct super_block *sb)
         return &ei->vfs_inode;
 }
 
+static void ext3_i_callback(struct rcu_head *head)
+{
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
+        kmem_cache_free(ext3_inode_cachep, EXT3_I(inode));
+}
+
 static void ext3_destroy_inode(struct inode *inode)
 {
         if (!list_empty(&(EXT3_I(inode)->i_orphan))) {
@@ -489,7 +496,7 @@ static void ext3_destroy_inode(struct inode *inode)
                                 false);
                 dump_stack();
         }
-        kmem_cache_free(ext3_inode_cachep, EXT3_I(inode));
+        call_rcu(&inode->i_rcu, ext3_i_callback);
 }
 
 static void init_once(void *foo)
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index 5e2ed4504ead..e0270d1f8d82 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -238,10 +238,17 @@ ext4_set_acl(handle_t *handle, struct inode *inode, int type,
 }
 
 int
-ext4_check_acl(struct inode *inode, int mask)
+ext4_check_acl(struct inode *inode, int mask, unsigned int flags)
 {
-        struct posix_acl *acl = ext4_get_acl(inode, ACL_TYPE_ACCESS);
+        struct posix_acl *acl;
+
+        if (flags & IPERM_FLAG_RCU) {
+                if (!negative_cached_acl(inode, ACL_TYPE_ACCESS))
+                        return -ECHILD;
+                return -EAGAIN;
+        }
 
+        acl = ext4_get_acl(inode, ACL_TYPE_ACCESS);
         if (IS_ERR(acl))
                 return PTR_ERR(acl);
         if (acl) {
diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h
index 9d843d5deac4..dec821168fd4 100644
--- a/fs/ext4/acl.h
+++ b/fs/ext4/acl.h
@@ -54,7 +54,7 @@ static inline int ext4_acl_count(size_t size)
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
 
 /* acl.c */
-extern int ext4_check_acl(struct inode *, int);
+extern int ext4_check_acl(struct inode *, int, unsigned int);
 extern int ext4_acl_chmod(struct inode *);
 extern int ext4_init_acl(handle_t *, struct inode *, struct inode *);
 
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 6a5edea2d70b..94ce3d7a1c4b 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -910,6 +910,7 @@ struct ext4_inode_info {
 #define EXT4_MOUNT_JOURNAL_CHECKSUM     0x800000 /* Journal checksums */
 #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */
 #define EXT4_MOUNT_I_VERSION            0x2000000 /* i_version support */
+#define EXT4_MOUNT_MBLK_IO_SUBMIT       0x4000000 /* multi-block io submits */
 #define EXT4_MOUNT_DELALLOC             0x8000000 /* Delalloc support */
 #define EXT4_MOUNT_DATA_ERR_ABORT       0x10000000 /* Abort on file data write */
 #define EXT4_MOUNT_BLOCK_VALIDITY       0x20000000 /* Block validity checking */
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index bdbe69902207..e659597b690b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2125,9 +2125,12 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
                          */
                         if (unlikely(journal_data && PageChecked(page)))
                                 err = __ext4_journalled_writepage(page, len);
-                        else
+                        else if (test_opt(inode->i_sb, MBLK_IO_SUBMIT))
                                 err = ext4_bio_write_page(&io_submit, page,
                                                           len, mpd->wbc);
+                        else
+                                err = block_write_full_page(page,
+                                        noalloc_get_block_write, mpd->wbc);
 
                         if (!err)
                                 mpd->pages_written++;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 92203b8a099f..dc40e75cba88 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -872,7 +872,7 @@ static struct buffer_head * ext4_find_entry (struct inode *dir,
         if (namelen > EXT4_NAME_LEN)
                 return NULL;
         if ((namelen <= 2) && (name[0] == '.') &&
-            (name[1] == '.' || name[1] == '0')) {
+            (name[1] == '.' || name[1] == '\0')) {
                 /*
                  * "." or ".." will only be in the first block
                  * NFS may look up ".."; "." should be handled by the VFS
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index dc963929de65..981c8477adab 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -232,6 +232,8 @@ static int setup_new_group_blocks(struct super_block *sb,
                                GFP_NOFS);
         if (err)
                 goto exit_bh;
+        for (i = 0, bit = gdblocks + 1; i < reserved_gdb; i++, bit++)
+                ext4_set_bit(bit, bh->b_data);
 
         ext4_debug("mark block bitmap %#04llx (+%llu)\n", input->block_bitmap,
                    input->block_bitmap - start);
@@ -247,6 +249,9 @@ static int setup_new_group_blocks(struct super_block *sb,
         err = sb_issue_zeroout(sb, block, sbi->s_itb_per_group, GFP_NOFS);
         if (err)
                 goto exit_bh;
+        for (i = 0, bit = input->inode_table - start;
+             i < sbi->s_itb_per_group; i++, bit++)
+                ext4_set_bit(bit, bh->b_data);
 
         if ((err = extend_or_restart_transaction(handle, 2, bh)))
                 goto exit_bh;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index e32195d6aac3..cd37f9d5e447 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -841,6 +841,13 @@ static int ext4_drop_inode(struct inode *inode)
         return drop;
 }
 
+static void ext4_i_callback(struct rcu_head *head)
+{
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
+        kmem_cache_free(ext4_inode_cachep, EXT4_I(inode));
+}
+
 static void ext4_destroy_inode(struct inode *inode)
 {
         ext4_ioend_wait(inode);
@@ -853,7 +860,7 @@ static void ext4_destroy_inode(struct inode *inode)
                                 true);
                 dump_stack();
         }
-        kmem_cache_free(ext4_inode_cachep, EXT4_I(inode));
+        call_rcu(&inode->i_rcu, ext4_i_callback);
 }
 
 static void init_once(void *foo)
@@ -1026,6 +1033,8 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
             !(def_mount_opts & EXT4_DEFM_NODELALLOC))
                 seq_puts(seq, ",nodelalloc");
 
+        if (test_opt(sb, MBLK_IO_SUBMIT))
+                seq_puts(seq, ",mblk_io_submit");
         if (sbi->s_stripe)
                 seq_printf(seq, ",stripe=%lu", sbi->s_stripe);
         /*
@@ -1239,8 +1248,8 @@ enum {
         Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
         Opt_noquota, Opt_ignore, Opt_barrier, Opt_nobarrier, Opt_err,
         Opt_resize, Opt_usrquota, Opt_grpquota, Opt_i_version,
-        Opt_stripe, Opt_delalloc, Opt_nodelalloc,
-        Opt_block_validity, Opt_noblock_validity,
+        Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
+        Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
         Opt_inode_readahead_blks, Opt_journal_ioprio,
         Opt_dioread_nolock, Opt_dioread_lock,
         Opt_discard, Opt_nodiscard,
@@ -1304,6 +1313,8 @@ static const match_table_t tokens = {
         {Opt_resize, "resize"},
         {Opt_delalloc, "delalloc"},
         {Opt_nodelalloc, "nodelalloc"},
+        {Opt_mblk_io_submit, "mblk_io_submit"},
+        {Opt_nomblk_io_submit, "nomblk_io_submit"},
         {Opt_block_validity, "block_validity"},
         {Opt_noblock_validity, "noblock_validity"},
         {Opt_inode_readahead_blks, "inode_readahead_blks=%u"},
@@ -1725,6 +1736,12 @@ set_qf_format:
                 case Opt_nodelalloc:
                         clear_opt(sbi->s_mount_opt, DELALLOC);
                         break;
+                case Opt_mblk_io_submit:
+                        set_opt(sbi->s_mount_opt, MBLK_IO_SUBMIT);
+                        break;
+                case Opt_nomblk_io_submit:
+                        clear_opt(sbi->s_mount_opt, MBLK_IO_SUBMIT);
+                        break;
                 case Opt_stripe:
                         if (match_int(&args[0], &option))
                                 return 0;
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index ad6998a92c30..206351af7c58 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -514,11 +514,18 @@ static struct inode *fat_alloc_inode(struct super_block *sb)
         return &ei->vfs_inode;
 }
 
-static void fat_destroy_inode(struct inode *inode)
+static void fat_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(fat_inode_cachep, MSDOS_I(inode));
 }
 
+static void fat_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, fat_i_callback);
+}
+
 static void init_once(void *foo)
 {
         struct msdos_inode_info *ei = (struct msdos_inode_info *)foo;
@@ -743,7 +750,7 @@ static struct dentry *fat_fh_to_dentry(struct super_block *sb,
          */
         result = d_obtain_alias(inode);
         if (!IS_ERR(result))
-                result->d_op = sb->s_root->d_op;
+                d_set_d_op(result, sb->s_root->d_op);
         return result;
 }
 
@@ -793,7 +800,7 @@ static struct dentry *fat_get_parent(struct dentry *child)
 
         parent = d_obtain_alias(inode);
         if (!IS_ERR(parent))
-                parent->d_op = sb->s_root->d_op;
+                d_set_d_op(parent, sb->s_root->d_op);
 out:
         unlock_super(sb);
 
diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c
index 3345aabd1dd7..35ffe43afa4b 100644
--- a/fs/fat/namei_msdos.c
+++ b/fs/fat/namei_msdos.c
@@ -148,7 +148,8 @@ static int msdos_find(struct inode *dir, const unsigned char *name, int len,
  * that the existing dentry can be used. The msdos fs routines will
  * return ENOENT or EINVAL as appropriate.
  */
-static int msdos_hash(struct dentry *dentry, struct qstr *qstr)
+static int msdos_hash(const struct dentry *dentry, const struct inode *inode,
+               struct qstr *qstr)
 {
         struct fat_mount_options *options = &MSDOS_SB(dentry->d_sb)->options;
         unsigned char msdos_name[MSDOS_NAME];
@@ -164,16 +165,18 @@ static int msdos_hash(struct dentry *dentry, struct qstr *qstr)
  * Compare two msdos names. If either of the names are invalid,
  * we fall back to doing the standard name comparison.
  */
-static int msdos_cmp(struct dentry *dentry, struct qstr *a, struct qstr *b)
+static int msdos_cmp(const struct dentry *parent, const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name)
 {
-        struct fat_mount_options *options = &MSDOS_SB(dentry->d_sb)->options;
+        struct fat_mount_options *options = &MSDOS_SB(parent->d_sb)->options;
         unsigned char a_msdos_name[MSDOS_NAME], b_msdos_name[MSDOS_NAME];
         int error;
 
-        error = msdos_format_name(a->name, a->len, a_msdos_name, options);
+        error = msdos_format_name(name->name, name->len, a_msdos_name, options);
         if (error)
                 goto old_compare;
-        error = msdos_format_name(b->name, b->len, b_msdos_name, options);
+        error = msdos_format_name(str, len, b_msdos_name, options);
         if (error)
                 goto old_compare;
         error = memcmp(a_msdos_name, b_msdos_name, MSDOS_NAME);
@@ -182,8 +185,8 @@ out:
 
 old_compare:
         error = 1;
-        if (a->len == b->len)
-                error = memcmp(a->name, b->name, a->len);
+        if (name->len == len)
+                error = memcmp(name->name, str, len);
         goto out;
 }
 
@@ -224,10 +227,10 @@ static struct dentry *msdos_lookup(struct inode *dir, struct dentry *dentry,
         }
 out:
         unlock_super(sb);
-        dentry->d_op = &msdos_dentry_operations;
+        d_set_d_op(dentry, &msdos_dentry_operations);
         dentry = d_splice_alias(inode, dentry);
         if (dentry)
-                dentry->d_op = &msdos_dentry_operations;
+                d_set_d_op(dentry, &msdos_dentry_operations);
         return dentry;
 
 error:
@@ -670,7 +673,7 @@ static int msdos_fill_super(struct super_block *sb, void *data, int silent)
         }
 
         sb->s_flags |= MS_NOATIME;
-        sb->s_root->d_op = &msdos_dentry_operations;
+        d_set_d_op(sb->s_root, &msdos_dentry_operations);
         unlock_super(sb);
         return 0;
 }
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index b936703b8924..e3ffc5e12332 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -43,6 +43,9 @@ static int vfat_revalidate_shortname(struct dentry *dentry)
 
 static int vfat_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
+
         /* This is not negative dentry. Always valid. */
         if (dentry->d_inode)
                 return 1;
@@ -51,6 +54,9 @@ static int vfat_revalidate(struct dentry *dentry, struct nameidata *nd)
 
 static int vfat_revalidate_ci(struct dentry *dentry, struct nameidata *nd)
 {
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
+
         /*
          * This is not negative dentry. Always valid.
          *
@@ -85,22 +91,26 @@ static int vfat_revalidate_ci(struct dentry *dentry, struct nameidata *nd)
 }
 
 /* returns the length of a struct qstr, ignoring trailing dots */
-static unsigned int vfat_striptail_len(struct qstr *qstr)
+static unsigned int __vfat_striptail_len(unsigned int len, const char *name)
 {
-        unsigned int len = qstr->len;
-
-        while (len && qstr->name[len - 1] == '.')
+        while (len && name[len - 1] == '.')
                 len--;
         return len;
 }
 
+static unsigned int vfat_striptail_len(const struct qstr *qstr)
+{
+        return __vfat_striptail_len(qstr->len, qstr->name);
+}
+
 /*
  * Compute the hash for the vfat name corresponding to the dentry.
  * Note: if the name is invalid, we leave the hash code unchanged so
  * that the existing dentry can be used. The vfat fs routines will
  * return ENOENT or EINVAL as appropriate.
  */
-static int vfat_hash(struct dentry *dentry, struct qstr *qstr)
+static int vfat_hash(const struct dentry *dentry, const struct inode *inode,
+                struct qstr *qstr)
 {
         qstr->hash = full_name_hash(qstr->name, vfat_striptail_len(qstr));
         return 0;
@@ -112,9 +122,10 @@ static int vfat_hash(struct dentry *dentry, struct qstr *qstr)
  * that the existing dentry can be used. The vfat fs routines will
  * return ENOENT or EINVAL as appropriate.
  */
-static int vfat_hashi(struct dentry *dentry, struct qstr *qstr)
+static int vfat_hashi(const struct dentry *dentry, const struct inode *inode,
+                struct qstr *qstr)
 {
-        struct nls_table *t = MSDOS_SB(dentry->d_inode->i_sb)->nls_io;
+        struct nls_table *t = MSDOS_SB(dentry->d_sb)->nls_io;
         const unsigned char *name;
         unsigned int len;
         unsigned long hash;
@@ -133,16 +144,18 @@ static int vfat_hashi(struct dentry *dentry, struct qstr *qstr)
 /*
  * Case insensitive compare of two vfat names.
  */
-static int vfat_cmpi(struct dentry *dentry, struct qstr *a, struct qstr *b)
+static int vfat_cmpi(const struct dentry *parent, const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name)
 {
-        struct nls_table *t = MSDOS_SB(dentry->d_inode->i_sb)->nls_io;
+        struct nls_table *t = MSDOS_SB(parent->d_sb)->nls_io;
         unsigned int alen, blen;
 
         /* A filename cannot end in '.' or we treat it like it has none */
-        alen = vfat_striptail_len(a);
-        blen = vfat_striptail_len(b);
+        alen = vfat_striptail_len(name);
+        blen = __vfat_striptail_len(len, str);
         if (alen == blen) {
-                if (nls_strnicmp(t, a->name, b->name, alen) == 0)
+                if (nls_strnicmp(t, name->name, str, alen) == 0)
                         return 0;
         }
         return 1;
@@ -151,15 +164,17 @@ static int vfat_cmpi(struct dentry *dentry, struct qstr *a, struct qstr *b)
 /*
  * Case sensitive compare of two vfat names.
  */
-static int vfat_cmp(struct dentry *dentry, struct qstr *a, struct qstr *b)
+static int vfat_cmp(const struct dentry *parent, const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name)
 {
         unsigned int alen, blen;
 
         /* A filename cannot end in '.' or we treat it like it has none */
-        alen = vfat_striptail_len(a);
-        blen = vfat_striptail_len(b);
+        alen = vfat_striptail_len(name);
+        blen = __vfat_striptail_len(len, str);
         if (alen == blen) {
-                if (strncmp(a->name, b->name, alen) == 0)
+                if (strncmp(name->name, str, alen) == 0)
                         return 0;
         }
         return 1;
@@ -757,11 +772,11 @@ static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
 
 out:
         unlock_super(sb);
-        dentry->d_op = sb->s_root->d_op;
+        d_set_d_op(dentry, sb->s_root->d_op);
         dentry->d_time = dentry->d_parent->d_inode->i_version;
         dentry = d_splice_alias(inode, dentry);
         if (dentry) {
-                dentry->d_op = sb->s_root->d_op;
+                d_set_d_op(dentry, sb->s_root->d_op);
                 dentry->d_time = dentry->d_parent->d_inode->i_version;
         }
         return dentry;
@@ -1063,9 +1078,9 @@ static int vfat_fill_super(struct super_block *sb, void *data, int silent)
         }
 
         if (MSDOS_SB(sb)->options.name_check != 's')
-                sb->s_root->d_op = &vfat_ci_dentry_ops;
+                d_set_d_op(sb->s_root, &vfat_ci_dentry_ops);
         else
-                sb->s_root->d_op = &vfat_dentry_ops;
+                d_set_d_op(sb->s_root, &vfat_dentry_ops);
 
         unlock_super(sb);
         return 0;
diff --git a/fs/filesystems.c b/fs/filesystems.c
index 68ba492d8eef..751d6b255a12 100644
--- a/fs/filesystems.c
+++ b/fs/filesystems.c
@@ -115,6 +115,9 @@ int unregister_filesystem(struct file_system_type * fs)
                 tmp = &(*tmp)->next;
         }
         write_unlock(&file_systems_lock);
+
+        synchronize_rcu();
+
         return -EINVAL;
 }
 
diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c
index 8c04eac5079d..2ba6719ac612 100644
--- a/fs/freevxfs/vxfs_inode.c
+++ b/fs/freevxfs/vxfs_inode.c
@@ -337,6 +337,13 @@ vxfs_iget(struct super_block *sbp, ino_t ino)
         return ip;
 }
 
+static void vxfs_i_callback(struct rcu_head *head)
+{
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
+        kmem_cache_free(vxfs_inode_cachep, inode->i_private);
+}
+
 /**
  * vxfs_evict_inode - remove inode from main memory
  * @ip:         inode to discard.
@@ -350,5 +357,5 @@ vxfs_evict_inode(struct inode *ip)
 {
         truncate_inode_pages(&ip->i_data, 0);
         end_writeback(ip);
-        kmem_cache_free(vxfs_inode_cachep, ip->i_private);
+        call_rcu(&ip->i_rcu, vxfs_i_callback);
 }
diff --git a/fs/fs_struct.c b/fs/fs_struct.c
index ed45a9cf5f3d..68ca487bedb1 100644
--- a/fs/fs_struct.c
+++ b/fs/fs_struct.c
@@ -14,12 +14,14 @@ void set_fs_root(struct fs_struct *fs, struct path *path)
         struct path old_root;
 
         spin_lock(&fs->lock);
+        write_seqcount_begin(&fs->seq);
         old_root = fs->root;
         fs->root = *path;
-        path_get(path);
+        path_get_long(path);
+        write_seqcount_end(&fs->seq);
         spin_unlock(&fs->lock);
         if (old_root.dentry)
-                path_put(&old_root);
+                path_put_long(&old_root);
 }
 
 /*
@@ -31,13 +33,15 @@ void set_fs_pwd(struct fs_struct *fs, struct path *path)
         struct path old_pwd;
 
         spin_lock(&fs->lock);
+        write_seqcount_begin(&fs->seq);
         old_pwd = fs->pwd;
         fs->pwd = *path;
-        path_get(path);
+        path_get_long(path);
+        write_seqcount_end(&fs->seq);
         spin_unlock(&fs->lock);
 
         if (old_pwd.dentry)
-                path_put(&old_pwd);
+                path_put_long(&old_pwd);
 }
 
 void chroot_fs_refs(struct path *old_root, struct path *new_root)
@@ -52,31 +56,33 @@ void chroot_fs_refs(struct path *old_root, struct path *new_root)
                 fs = p->fs;
                 if (fs) {
                         spin_lock(&fs->lock);
+                        write_seqcount_begin(&fs->seq);
                         if (fs->root.dentry == old_root->dentry
                             && fs->root.mnt == old_root->mnt) {
-                                path_get(new_root);
+                                path_get_long(new_root);
                                 fs->root = *new_root;
                                 count++;
                         }
                         if (fs->pwd.dentry == old_root->dentry
                             && fs->pwd.mnt == old_root->mnt) {
-                                path_get(new_root);
+                                path_get_long(new_root);
                                 fs->pwd = *new_root;
                                 count++;
                         }
+                        write_seqcount_end(&fs->seq);
                         spin_unlock(&fs->lock);
                 }
                 task_unlock(p);
         } while_each_thread(g, p);
         read_unlock(&tasklist_lock);
         while (count--)
-                path_put(old_root);
+                path_put_long(old_root);
 }
 
 void free_fs_struct(struct fs_struct *fs)
 {
-        path_put(&fs->root);
-        path_put(&fs->pwd);
+        path_put_long(&fs->root);
+        path_put_long(&fs->pwd);
         kmem_cache_free(fs_cachep, fs);
 }
 
@@ -88,8 +94,10 @@ void exit_fs(struct task_struct *tsk)
                 int kill;
                 task_lock(tsk);
                 spin_lock(&fs->lock);
+                write_seqcount_begin(&fs->seq);
                 tsk->fs = NULL;
                 kill = !--fs->users;
+                write_seqcount_end(&fs->seq);
                 spin_unlock(&fs->lock);
                 task_unlock(tsk);
                 if (kill)
@@ -105,8 +113,15 @@ struct fs_struct *copy_fs_struct(struct fs_struct *old)
                 fs->users = 1;
                 fs->in_exec = 0;
                 spin_lock_init(&fs->lock);
+                seqcount_init(&fs->seq);
                 fs->umask = old->umask;
-                get_fs_root_and_pwd(old, &fs->root, &fs->pwd);
+
+                spin_lock(&old->lock);
+                fs->root = old->root;
+                path_get_long(&fs->root);
+                fs->pwd = old->pwd;
+                path_get_long(&fs->pwd);
+                spin_unlock(&old->lock);
         }
         return fs;
 }
@@ -144,6 +159,7 @@ EXPORT_SYMBOL(current_umask);
 struct fs_struct init_fs = {
         .users          = 1,
         .lock           = __SPIN_LOCK_UNLOCKED(init_fs.lock),
+        .seq            = SEQCNT_ZERO,
         .umask          = 0022,
 };
 
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 6e07696308dc..cf8d28d1fbad 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -251,6 +251,20 @@ static void queue_request(struct fuse_conn *fc, struct fuse_req *req)
         kill_fasync(&fc->fasync, SIGIO, POLL_IN);
 }
 
+void fuse_queue_forget(struct fuse_conn *fc, struct fuse_forget_link *forget,
+                       u64 nodeid, u64 nlookup)
+{
+        forget->forget_one.nodeid = nodeid;
+        forget->forget_one.nlookup = nlookup;
+
+        spin_lock(&fc->lock);
+        fc->forget_list_tail->next = forget;
+        fc->forget_list_tail = forget;
+        wake_up(&fc->waitq);
+        kill_fasync(&fc->fasync, SIGIO, POLL_IN);
+        spin_unlock(&fc->lock);
+}
+
 static void flush_bg_queue(struct fuse_conn *fc)
 {
         while (fc->active_background < fc->max_background &&
@@ -438,12 +452,6 @@ static void fuse_request_send_nowait(struct fuse_conn *fc, struct fuse_req *req)
         }
 }
 
-void fuse_request_send_noreply(struct fuse_conn *fc, struct fuse_req *req)
-{
-        req->isreply = 0;
-        fuse_request_send_nowait(fc, req);
-}
-
 void fuse_request_send_background(struct fuse_conn *fc, struct fuse_req *req)
 {
         req->isreply = 1;
@@ -896,9 +904,15 @@ static int fuse_copy_args(struct fuse_copy_state *cs, unsigned numargs,
         return err;
 }
 
+static int forget_pending(struct fuse_conn *fc)
+{
+        return fc->forget_list_head.next != NULL;
+}
+
 static int request_pending(struct fuse_conn *fc)
 {
-        return !list_empty(&fc->pending) || !list_empty(&fc->interrupts);
+        return !list_empty(&fc->pending) || !list_empty(&fc->interrupts) ||
+                forget_pending(fc);
 }
 
 /* Wait until a request is available on the pending list */
@@ -960,6 +974,120 @@ __releases(fc->lock)
         return err ? err : reqsize;
 }
 
+static struct fuse_forget_link *dequeue_forget(struct fuse_conn *fc,
+                                               unsigned max,
+                                               unsigned *countp)
+{
+        struct fuse_forget_link *head = fc->forget_list_head.next;
+        struct fuse_forget_link **newhead = &head;
+        unsigned count;
+
+        for (count = 0; *newhead != NULL && count < max; count++)
+                newhead = &(*newhead)->next;
+
+        fc->forget_list_head.next = *newhead;
+        *newhead = NULL;
+        if (fc->forget_list_head.next == NULL)
+                fc->forget_list_tail = &fc->forget_list_head;
+
+        if (countp != NULL)
+                *countp = count;
+
+        return head;
+}
+
+static int fuse_read_single_forget(struct fuse_conn *fc,
+                                   struct fuse_copy_state *cs,
+                                   size_t nbytes)
+__releases(fc->lock)
+{
+        int err;
+        struct fuse_forget_link *forget = dequeue_forget(fc, 1, NULL);
+        struct fuse_forget_in arg = {
+                .nlookup = forget->forget_one.nlookup,
+        };
+        struct fuse_in_header ih = {
+                .opcode = FUSE_FORGET,
+                .nodeid = forget->forget_one.nodeid,
+                .unique = fuse_get_unique(fc),
+                .len = sizeof(ih) + sizeof(arg),
+        };
+
+        spin_unlock(&fc->lock);
+        kfree(forget);
+        if (nbytes < ih.len)
+                return -EINVAL;
+
+        err = fuse_copy_one(cs, &ih, sizeof(ih));
+        if (!err)
+                err = fuse_copy_one(cs, &arg, sizeof(arg));
+        fuse_copy_finish(cs);
+
+        if (err)
+                return err;
+
+        return ih.len;
+}
+
+static int fuse_read_batch_forget(struct fuse_conn *fc,
+                                   struct fuse_copy_state *cs, size_t nbytes)
+__releases(fc->lock)
+{
+        int err;
+        unsigned max_forgets;
+        unsigned count;
+        struct fuse_forget_link *head;
+        struct fuse_batch_forget_in arg = { .count = 0 };
+        struct fuse_in_header ih = {
+                .opcode = FUSE_BATCH_FORGET,
+                .unique = fuse_get_unique(fc),
+                .len = sizeof(ih) + sizeof(arg),
+        };
+
+        if (nbytes < ih.len) {
+                spin_unlock(&fc->lock);
+                return -EINVAL;
+        }
+
+        max_forgets = (nbytes - ih.len) / sizeof(struct fuse_forget_one);
+        head = dequeue_forget(fc, max_forgets, &count);
+        spin_unlock(&fc->lock);
+
+        arg.count = count;
+        ih.len += count * sizeof(struct fuse_forget_one);
+        err = fuse_copy_one(cs, &ih, sizeof(ih));
+        if (!err)
+                err = fuse_copy_one(cs, &arg, sizeof(arg));
+
+        while (head) {
+                struct fuse_forget_link *forget = head;
+
+                if (!err) {
+                        err = fuse_copy_one(cs, &forget->forget_one,
+                                            sizeof(forget->forget_one));
+                }
+                head = forget->next;
+                kfree(forget);
+        }
+
+        fuse_copy_finish(cs);
+
+        if (err)
+                return err;
+
+        return ih.len;
+}
+
+static int fuse_read_forget(struct fuse_conn *fc, struct fuse_copy_state *cs,
+                            size_t nbytes)
+__releases(fc->lock)
+{
+        if (fc->minor < 16 || fc->forget_list_head.next->next == NULL)
+                return fuse_read_single_forget(fc, cs, nbytes);
+        else
+                return fuse_read_batch_forget(fc, cs, nbytes);
+}
+
 /*
  * Read a single request into the userspace filesystem's buffer.  This
  * function waits until a request is available, then removes it from
@@ -998,6 +1126,14 @@ static ssize_t fuse_dev_do_read(struct fuse_conn *fc, struct file *file,
                 return fuse_read_interrupt(fc, cs, nbytes, req);
         }
 
+        if (forget_pending(fc)) {
+                if (list_empty(&fc->pending) || fc->forget_batch-- > 0)
+                        return fuse_read_forget(fc, cs, nbytes);
+
+                if (fc->forget_batch <= -8)
+                        fc->forget_batch = 16;
+        }
+
         req = list_entry(fc->pending.next, struct fuse_req, list);
         req->state = FUSE_REQ_READING;
         list_move(&req->list, &fc->io);
@@ -1090,7 +1226,7 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
         if (!fc)
                 return -EPERM;
 
-        bufs = kmalloc(pipe->buffers * sizeof (struct pipe_buffer), GFP_KERNEL);
+        bufs = kmalloc(pipe->buffers * sizeof(struct pipe_buffer), GFP_KERNEL);
         if (!bufs)
                 return -ENOMEM;
 
@@ -1626,7 +1762,7 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
         if (!fc)
                 return -EPERM;
 
-        bufs = kmalloc(pipe->buffers * sizeof (struct pipe_buffer), GFP_KERNEL);
+        bufs = kmalloc(pipe->buffers * sizeof(struct pipe_buffer), GFP_KERNEL);
         if (!bufs)
                 return -ENOMEM;
 
@@ -1770,6 +1906,8 @@ __acquires(fc->lock)
         flush_bg_queue(fc);
         end_requests(fc, &fc->pending);
         end_requests(fc, &fc->processing);
+        while (forget_pending(fc))
+                kfree(dequeue_forget(fc, 1, NULL));
 }
 
 /*
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index c9627c95482d..042af7346ec1 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -10,9 +10,9 @@
 
 #include <linux/pagemap.h>
 #include <linux/file.h>
-#include <linux/gfp.h>
 #include <linux/sched.h>
 #include <linux/namei.h>
+#include <linux/slab.h>
 
 #if BITS_PER_LONG >= 64
 static inline void fuse_dentry_settime(struct dentry *entry, u64 time)
@@ -156,8 +156,12 @@ u64 fuse_get_attr_version(struct fuse_conn *fc)
  */
 static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
 {
-        struct inode *inode = entry->d_inode;
+        struct inode *inode;
 
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
+
+        inode = entry->d_inode;
         if (inode && is_bad_inode(inode))
                 return 0;
         else if (fuse_dentry_time(entry) < get_jiffies_64()) {
@@ -165,7 +169,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
                 struct fuse_entry_out outarg;
                 struct fuse_conn *fc;
                 struct fuse_req *req;
-                struct fuse_req *forget_req;
+                struct fuse_forget_link *forget;
                 struct dentry *parent;
                 u64 attr_version;
 
@@ -178,8 +182,8 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
                 if (IS_ERR(req))
                         return 0;
 
-                forget_req = fuse_get_req(fc);
-                if (IS_ERR(forget_req)) {
+                forget = fuse_alloc_forget();
+                if (!forget) {
                         fuse_put_request(fc, req);
                         return 0;
                 }
@@ -199,15 +203,14 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
                 if (!err) {
                         struct fuse_inode *fi = get_fuse_inode(inode);
                         if (outarg.nodeid != get_node_id(inode)) {
-                                fuse_send_forget(fc, forget_req,
-                                                 outarg.nodeid, 1);
+                                fuse_queue_forget(fc, forget, outarg.nodeid, 1);
                                 return 0;
                         }
                         spin_lock(&fc->lock);
                         fi->nlookup++;
                         spin_unlock(&fc->lock);
                 }
-                fuse_put_request(fc, forget_req);
+                kfree(forget);
                 if (err || (outarg.attr.mode ^ inode->i_mode) & S_IFMT)
                         return 0;
 
@@ -259,7 +262,7 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, struct qstr *name,
 {
         struct fuse_conn *fc = get_fuse_conn_super(sb);
         struct fuse_req *req;
-        struct fuse_req *forget_req;
+        struct fuse_forget_link *forget;
         u64 attr_version;
         int err;
 
@@ -273,9 +276,9 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, struct qstr *name,
         if (IS_ERR(req))
                 goto out;
 
-        forget_req = fuse_get_req(fc);
-        err = PTR_ERR(forget_req);
-        if (IS_ERR(forget_req)) {
+        forget = fuse_alloc_forget();
+        err = -ENOMEM;
+        if (!forget) {
                 fuse_put_request(fc, req);
                 goto out;
         }
@@ -301,13 +304,13 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, struct qstr *name,
                            attr_version);
         err = -ENOMEM;
         if (!*inode) {
-                fuse_send_forget(fc, forget_req, outarg->nodeid, 1);
+                fuse_queue_forget(fc, forget, outarg->nodeid, 1);
                 goto out;
         }
         err = 0;
 
  out_put_forget:
-        fuse_put_request(fc, forget_req);
+        kfree(forget);
  out:
         return err;
 }
@@ -347,7 +350,7 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
         }
 
         entry = newent ? newent : entry;
-        entry->d_op = &fuse_dentry_operations;
+        d_set_d_op(entry, &fuse_dentry_operations);
         if (outarg_valid)
                 fuse_change_entry_timeout(entry, &outarg);
         else
@@ -374,7 +377,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode,
         struct inode *inode;
         struct fuse_conn *fc = get_fuse_conn(dir);
         struct fuse_req *req;
-        struct fuse_req *forget_req;
+        struct fuse_forget_link *forget;
         struct fuse_create_in inarg;
         struct fuse_open_out outopen;
         struct fuse_entry_out outentry;
@@ -388,9 +391,9 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode,
         if (flags & O_DIRECT)
                 return -EINVAL;
 
-        forget_req = fuse_get_req(fc);
-        if (IS_ERR(forget_req))
-                return PTR_ERR(forget_req);
+        forget = fuse_alloc_forget();
+        if (!forget)
+                return -ENOMEM;
 
         req = fuse_get_req(fc);
         err = PTR_ERR(req);
@@ -448,10 +451,10 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode,
         if (!inode) {
                 flags &= ~(O_CREAT | O_EXCL | O_TRUNC);
                 fuse_sync_release(ff, flags);
-                fuse_send_forget(fc, forget_req, outentry.nodeid, 1);
+                fuse_queue_forget(fc, forget, outentry.nodeid, 1);
                 return -ENOMEM;
         }
-        fuse_put_request(fc, forget_req);
+        kfree(forget);
         d_instantiate(entry, inode);
         fuse_change_entry_timeout(entry, &outentry);
         fuse_invalidate_attr(dir);
@@ -469,7 +472,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode,
  out_put_request:
         fuse_put_request(fc, req);
  out_put_forget_req:
-        fuse_put_request(fc, forget_req);
+        kfree(forget);
         return err;
 }
 
@@ -483,12 +486,12 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_req *req,
         struct fuse_entry_out outarg;
         struct inode *inode;
         int err;
-        struct fuse_req *forget_req;
+        struct fuse_forget_link *forget;
 
-        forget_req = fuse_get_req(fc);
-        if (IS_ERR(forget_req)) {
+        forget = fuse_alloc_forget();
+        if (!forget) {
                 fuse_put_request(fc, req);
-                return PTR_ERR(forget_req);
+                return -ENOMEM;
         }
 
         memset(&outarg, 0, sizeof(outarg));
@@ -515,10 +518,10 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_req *req,
         inode = fuse_iget(dir->i_sb, outarg.nodeid, outarg.generation,
                           &outarg.attr, entry_attr_timeout(&outarg), 0);
         if (!inode) {
-                fuse_send_forget(fc, forget_req, outarg.nodeid, 1);
+                fuse_queue_forget(fc, forget, outarg.nodeid, 1);
                 return -ENOMEM;
         }
-        fuse_put_request(fc, forget_req);
+        kfree(forget);
 
         if (S_ISDIR(inode->i_mode)) {
                 struct dentry *alias;
@@ -541,7 +544,7 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_req *req,
         return 0;
 
  out_put_forget_req:
-        fuse_put_request(fc, forget_req);
+        kfree(forget);
         return err;
 }
 
@@ -981,12 +984,15 @@ static int fuse_access(struct inode *inode, int mask)
  * access request is sent.  Execute permission is still checked
  * locally based on file mode.
  */
-static int fuse_permission(struct inode *inode, int mask)
+static int fuse_permission(struct inode *inode, int mask, unsigned int flags)
 {
         struct fuse_conn *fc = get_fuse_conn(inode);
         bool refreshed = false;
         int err = 0;
 
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
         if (!fuse_allow_task(fc, current))
                 return -EACCES;
 
@@ -1001,7 +1007,7 @@ static int fuse_permission(struct inode *inode, int mask)
         }
 
         if (fc->flags & FUSE_DEFAULT_PERMISSIONS) {
-                err = generic_permission(inode, mask, NULL);
+                err = generic_permission(inode, mask, flags, NULL);
 
                 /* If permission is denied, try to refresh file
                    attributes.  This is also needed, because the root
@@ -1009,7 +1015,8 @@ static int fuse_permission(struct inode *inode, int mask)
                 if (err == -EACCES && !refreshed) {
                         err = fuse_do_getattr(inode, NULL, NULL);
                         if (!err)
-                                err = generic_permission(inode, mask, NULL);
+                                err = generic_permission(inode, mask,
+                                                        flags, NULL);
                 }
 
                 /* Note: the opposite of the above test does not
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 9242d294fe90..95da1bc1c826 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/module.h>
+#include <linux/compat.h>
 
 static const struct file_operations fuse_direct_io_file_operations;
 
@@ -1628,6 +1629,94 @@ static int fuse_ioctl_copy_user(struct page **pages, struct iovec *iov,
 }
 
 /*
+ * CUSE servers compiled on 32bit broke on 64bit kernels because the
+ * ABI was defined to be 'struct iovec' which is different on 32bit
+ * and 64bit.  Fortunately we can determine which structure the server
+ * used from the size of the reply.
+ */
+static int fuse_copy_ioctl_iovec_old(struct iovec *dst, void *src,
+                                     size_t transferred, unsigned count,
+                                     bool is_compat)
+{
+#ifdef CONFIG_COMPAT
+        if (count * sizeof(struct compat_iovec) == transferred) {
+                struct compat_iovec *ciov = src;
+                unsigned i;
+
+                /*
+                 * With this interface a 32bit server cannot support
+                 * non-compat (i.e. ones coming from 64bit apps) ioctl
+                 * requests
+                 */
+                if (!is_compat)
+                        return -EINVAL;
+
+                for (i = 0; i < count; i++) {
+                        dst[i].iov_base = compat_ptr(ciov[i].iov_base);
+                        dst[i].iov_len = ciov[i].iov_len;
+                }
+                return 0;
+        }
+#endif
+
+        if (count * sizeof(struct iovec) != transferred)
+                return -EIO;
+
+        memcpy(dst, src, transferred);
+        return 0;
+}
+
+/* Make sure iov_length() won't overflow */
+static int fuse_verify_ioctl_iov(struct iovec *iov, size_t count)
+{
+        size_t n;
+        u32 max = FUSE_MAX_PAGES_PER_REQ << PAGE_SHIFT;
+
+        for (n = 0; n < count; n++) {
+                if (iov->iov_len > (size_t) max)
+                        return -ENOMEM;
+                max -= iov->iov_len;
+        }
+        return 0;
+}
+
+static int fuse_copy_ioctl_iovec(struct fuse_conn *fc, struct iovec *dst,
+                                 void *src, size_t transferred, unsigned count,
+                                 bool is_compat)
+{
+        unsigned i;
+        struct fuse_ioctl_iovec *fiov = src;
+
+        if (fc->minor < 16) {
+                return fuse_copy_ioctl_iovec_old(dst, src, transferred,
+                                                 count, is_compat);
+        }
+
+        if (count * sizeof(struct fuse_ioctl_iovec) != transferred)
+                return -EIO;
+
+        for (i = 0; i < count; i++) {
+                /* Did the server supply an inappropriate value? */
+                if (fiov[i].base != (unsigned long) fiov[i].base ||
+                    fiov[i].len != (unsigned long) fiov[i].len)
+                        return -EIO;
+
+                dst[i].iov_base = (void __user *) (unsigned long) fiov[i].base;
+                dst[i].iov_len = (size_t) fiov[i].len;
+
+#ifdef CONFIG_COMPAT
+                if (is_compat &&
+                    (ptr_to_compat(dst[i].iov_base) != fiov[i].base ||
+                     (compat_size_t) dst[i].iov_len != fiov[i].len))
+                        return -EIO;
+#endif
+        }
+
+        return 0;
+}
+
+
+/*
  * For ioctls, there is no generic way to determine how much memory
  * needs to be read and/or written.  Furthermore, ioctls are allowed
  * to dereference the passed pointer, so the parameter requires deep
@@ -1687,18 +1776,25 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
         struct fuse_ioctl_out outarg;
         struct fuse_req *req = NULL;
         struct page **pages = NULL;
-        struct page *iov_page = NULL;
+        struct iovec *iov_page = NULL;
         struct iovec *in_iov = NULL, *out_iov = NULL;
         unsigned int in_iovs = 0, out_iovs = 0, num_pages = 0, max_pages;
         size_t in_size, out_size, transferred;
         int err;
 
+#if BITS_PER_LONG == 32
+        inarg.flags |= FUSE_IOCTL_32BIT;
+#else
+        if (flags & FUSE_IOCTL_COMPAT)
+                inarg.flags |= FUSE_IOCTL_32BIT;
+#endif
+
         /* assume all the iovs returned by client always fits in a page */
-        BUILD_BUG_ON(sizeof(struct iovec) * FUSE_IOCTL_MAX_IOV > PAGE_SIZE);
+        BUILD_BUG_ON(sizeof(struct fuse_ioctl_iovec) * FUSE_IOCTL_MAX_IOV > PAGE_SIZE);
 
         err = -ENOMEM;
         pages = kzalloc(sizeof(pages[0]) * FUSE_MAX_PAGES_PER_REQ, GFP_KERNEL);
-        iov_page = alloc_page(GFP_KERNEL);
+        iov_page = (struct iovec *) __get_free_page(GFP_KERNEL);
         if (!pages || !iov_page)
                 goto out;
 
@@ -1707,7 +1803,7 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
          * RETRY from server is not allowed.
          */
         if (!(flags & FUSE_IOCTL_UNRESTRICTED)) {
-                struct iovec *iov = page_address(iov_page);
+                struct iovec *iov = iov_page;
 
                 iov->iov_base = (void __user *)arg;
                 iov->iov_len = _IOC_SIZE(cmd);
@@ -1788,7 +1884,7 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
 
         /* did it ask for retry? */
         if (outarg.flags & FUSE_IOCTL_RETRY) {
-                char *vaddr;
+                void *vaddr;
 
                 /* no retry if in restricted mode */
                 err = -EIO;
@@ -1808,18 +1904,25 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
                     in_iovs + out_iovs > FUSE_IOCTL_MAX_IOV)
                         goto out;
 
-                err = -EIO;
-                if ((in_iovs + out_iovs) * sizeof(struct iovec) != transferred)
-                        goto out;
-
-                /* okay, copy in iovs and retry */
                 vaddr = kmap_atomic(pages[0], KM_USER0);
-                memcpy(page_address(iov_page), vaddr, transferred);
+                err = fuse_copy_ioctl_iovec(fc, iov_page, vaddr,
+                                            transferred, in_iovs + out_iovs,
+                                            (flags & FUSE_IOCTL_COMPAT) != 0);
                 kunmap_atomic(vaddr, KM_USER0);
+                if (err)
+                        goto out;
 
-                in_iov = page_address(iov_page);
+                in_iov = iov_page;
                 out_iov = in_iov + in_iovs;
 
+                err = fuse_verify_ioctl_iov(in_iov, in_iovs);
+                if (err)
+                        goto out;
+
+                err = fuse_verify_ioctl_iov(out_iov, out_iovs);
+                if (err)
+                        goto out;
+
                 goto retry;
         }
 
@@ -1831,8 +1934,7 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
  out:
         if (req)
                 fuse_put_request(fc, req);
-        if (iov_page)
-                __free_page(iov_page);
+        free_page((unsigned long) iov_page);
         while (num_pages)
                 __free_page(pages[--num_pages]);
         kfree(pages);
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 57d4a3a0f102..ae5744a2f9e9 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -53,6 +53,12 @@ extern struct mutex fuse_mutex;
 extern unsigned max_user_bgreq;
 extern unsigned max_user_congthresh;
 
+/* One forget request */
+struct fuse_forget_link {
+        struct fuse_forget_one forget_one;
+        struct fuse_forget_link *next;
+};
+
 /** FUSE inode */
 struct fuse_inode {
         /** Inode data */
@@ -66,7 +72,7 @@ struct fuse_inode {
         u64 nlookup;
 
         /** The request used for sending the FORGET message */
-        struct fuse_req *forget_req;
+        struct fuse_forget_link *forget;
 
         /** Time in jiffies until the file attributes are valid */
         u64 i_time;
@@ -255,7 +261,6 @@ struct fuse_req {
 
         /** Data for asynchronous requests */
         union {
-                struct fuse_forget_in forget_in;
                 struct {
                         struct fuse_release_in in;
                         struct path path;
@@ -369,6 +374,13 @@ struct fuse_conn {
         /** Pending interrupts */
         struct list_head interrupts;
 
+        /** Queue of pending forgets */
+        struct fuse_forget_link forget_list_head;
+        struct fuse_forget_link *forget_list_tail;
+
+        /** Batching of FORGET requests (positive indicates FORGET batch) */
+        int forget_batch;
+
         /** Flag indicating if connection is blocked.  This will be
             the case before the INIT reply is received, and if there
             are too many outstading backgrounds requests */
@@ -543,8 +555,10 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, struct qstr *name,
 /**
  * Send FORGET command
  */
-void fuse_send_forget(struct fuse_conn *fc, struct fuse_req *req,
-                      u64 nodeid, u64 nlookup);
+void fuse_queue_forget(struct fuse_conn *fc, struct fuse_forget_link *forget,
+                       u64 nodeid, u64 nlookup);
+
+struct fuse_forget_link *fuse_alloc_forget(void);
 
 /**
  * Initialize READ or READDIR request
@@ -656,11 +670,6 @@ void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req);
 void fuse_request_send(struct fuse_conn *fc, struct fuse_req *req);
 
 /**
- * Send a request with no reply
- */
-void fuse_request_send_noreply(struct fuse_conn *fc, struct fuse_req *req);
-
-/**
  * Send a request in the background
  */
 void fuse_request_send_background(struct fuse_conn *fc, struct fuse_req *req);
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index cfce3ad86a92..f62b32cffea9 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -71,6 +71,11 @@ struct fuse_mount_data {
         unsigned blksize;
 };
 
+struct fuse_forget_link *fuse_alloc_forget()
+{
+        return kzalloc(sizeof(struct fuse_forget_link), GFP_KERNEL);
+}
+
 static struct inode *fuse_alloc_inode(struct super_block *sb)
 {
         struct inode *inode;
@@ -90,8 +95,8 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
         INIT_LIST_HEAD(&fi->queued_writes);
         INIT_LIST_HEAD(&fi->writepages);
         init_waitqueue_head(&fi->page_waitq);
-        fi->forget_req = fuse_request_alloc();
-        if (!fi->forget_req) {
+        fi->forget = fuse_alloc_forget();
+        if (!fi->forget) {
                 kmem_cache_free(fuse_inode_cachep, inode);
                 return NULL;
         }
@@ -99,27 +104,20 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
         return inode;
 }
 
-static void fuse_destroy_inode(struct inode *inode)
+static void fuse_i_callback(struct rcu_head *head)
 {
-        struct fuse_inode *fi = get_fuse_inode(inode);
-        BUG_ON(!list_empty(&fi->write_files));
-        BUG_ON(!list_empty(&fi->queued_writes));
-        if (fi->forget_req)
-                fuse_request_free(fi->forget_req);
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(fuse_inode_cachep, inode);
 }
 
-void fuse_send_forget(struct fuse_conn *fc, struct fuse_req *req,
-                      u64 nodeid, u64 nlookup)
+static void fuse_destroy_inode(struct inode *inode)
 {
-        struct fuse_forget_in *inarg = &req->misc.forget_in;
-        inarg->nlookup = nlookup;
-        req->in.h.opcode = FUSE_FORGET;
-        req->in.h.nodeid = nodeid;
-        req->in.numargs = 1;
-        req->in.args[0].size = sizeof(struct fuse_forget_in);
-        req->in.args[0].value = inarg;
-        fuse_request_send_noreply(fc, req);
+        struct fuse_inode *fi = get_fuse_inode(inode);
+        BUG_ON(!list_empty(&fi->write_files));
+        BUG_ON(!list_empty(&fi->queued_writes));
+        kfree(fi->forget);
+        call_rcu(&inode->i_rcu, fuse_i_callback);
 }
 
 static void fuse_evict_inode(struct inode *inode)
@@ -129,8 +127,8 @@ static void fuse_evict_inode(struct inode *inode)
         if (inode->i_sb->s_flags & MS_ACTIVE) {
                 struct fuse_conn *fc = get_fuse_conn(inode);
                 struct fuse_inode *fi = get_fuse_inode(inode);
-                fuse_send_forget(fc, fi->forget_req, fi->nodeid, fi->nlookup);
-                fi->forget_req = NULL;
+                fuse_queue_forget(fc, fi->forget, fi->nodeid, fi->nlookup);
+                fi->forget = NULL;
         }
 }
 
@@ -534,6 +532,7 @@ void fuse_conn_init(struct fuse_conn *fc)
         INIT_LIST_HEAD(&fc->interrupts);
         INIT_LIST_HEAD(&fc->bg_queue);
         INIT_LIST_HEAD(&fc->entry);
+        fc->forget_list_tail = &fc->forget_list_head;
         atomic_set(&fc->num_waiting, 0);
         fc->max_background = FUSE_DEFAULT_MAX_BACKGROUND;
         fc->congestion_threshold = FUSE_DEFAULT_CONGESTION_THRESHOLD;
@@ -619,7 +618,7 @@ static struct dentry *fuse_get_dentry(struct super_block *sb,
 
         entry = d_obtain_alias(inode);
         if (!IS_ERR(entry) && get_node_id(inode) != FUSE_ROOT_ID) {
-                entry->d_op = &fuse_dentry_operations;
+                d_set_d_op(entry, &fuse_dentry_operations);
                 fuse_invalidate_entry_cache(entry);
         }
 
@@ -721,7 +720,7 @@ static struct dentry *fuse_get_parent(struct dentry *child)
 
         parent = d_obtain_alias(inode);
         if (!IS_ERR(parent) && get_node_id(inode) != FUSE_ROOT_ID) {
-                parent->d_op = &fuse_dentry_operations;
+                d_set_d_op(parent, &fuse_dentry_operations);
                 fuse_invalidate_entry_cache(parent);
         }
 
diff --git a/fs/generic_acl.c b/fs/generic_acl.c
index 6bc9e3a5a693..06c48a891832 100644
--- a/fs/generic_acl.c
+++ b/fs/generic_acl.c
@@ -190,14 +190,20 @@ generic_acl_chmod(struct inode *inode)
 }
 
 int
-generic_check_acl(struct inode *inode, int mask)
+generic_check_acl(struct inode *inode, int mask, unsigned int flags)
 {
-        struct posix_acl *acl = get_cached_acl(inode, ACL_TYPE_ACCESS);
-
-        if (acl) {
-                int error = posix_acl_permission(inode, acl, mask);
-                posix_acl_release(acl);
-                return error;
+        if (flags & IPERM_FLAG_RCU) {
+                if (!negative_cached_acl(inode, ACL_TYPE_ACCESS))
+                        return -ECHILD;
+        } else {
+                struct posix_acl *acl;
+
+                acl = get_cached_acl(inode, ACL_TYPE_ACCESS);
+                if (acl) {
+                        int error = posix_acl_permission(inode, acl, mask);
+                        posix_acl_release(acl);
+                        return error;
+                }
         }
         return -EAGAIN;
 }
diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
index 48171f4c943d..7118f1a780a9 100644
--- a/fs/gfs2/acl.c
+++ b/fs/gfs2/acl.c
@@ -75,11 +75,14 @@ static struct posix_acl *gfs2_acl_get(struct gfs2_inode *ip, int type)
  * Returns: errno
  */
 
-int gfs2_check_acl(struct inode *inode, int mask)
+int gfs2_check_acl(struct inode *inode, int mask, unsigned int flags)
 {
         struct posix_acl *acl;
         int error;
 
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
         acl = gfs2_acl_get(GFS2_I(inode), ACL_TYPE_ACCESS);
         if (IS_ERR(acl))
                 return PTR_ERR(acl);
diff --git a/fs/gfs2/acl.h b/fs/gfs2/acl.h
index b522b0cb39ea..a93907c8159b 100644
--- a/fs/gfs2/acl.h
+++ b/fs/gfs2/acl.h
@@ -16,7 +16,7 @@
 #define GFS2_POSIX_ACL_DEFAULT          "posix_acl_default"
 #define GFS2_ACL_MAX_ENTRIES            25
 
-extern int gfs2_check_acl(struct inode *inode, int mask);
+extern int gfs2_check_acl(struct inode *inode, int mask, unsigned int);
 extern int gfs2_acl_create(struct gfs2_inode *dip, struct inode *inode);
 extern int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr);
 extern const struct xattr_handler gfs2_xattr_system_handler;
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 5476c066d4ee..3c4039d5eef1 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -763,7 +763,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
         int metadata;
         unsigned int revokes = 0;
         int x;
-        int error;
+        int error = 0;
 
         if (!*top)
                 sm->sm_first = 0;
@@ -780,7 +780,11 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
         if (metadata)
                 revokes = (height) ? sdp->sd_inptrs : sdp->sd_diptrs;
 
-        error = gfs2_rindex_hold(sdp, &ip->i_alloc->al_ri_gh);
+        if (ip != GFS2_I(sdp->sd_rindex))
+                error = gfs2_rindex_hold(sdp, &ip->i_alloc->al_ri_gh);
+        else if (!sdp->sd_rgrps)
+                error = gfs2_ri_update(ip);
+
         if (error)
                 return error;
 
@@ -879,7 +883,8 @@ out_rg_gunlock:
 out_rlist:
         gfs2_rlist_free(&rlist);
 out:
-        gfs2_glock_dq_uninit(&ip->i_alloc->al_ri_gh);
+        if (ip != GFS2_I(sdp->sd_rindex))
+                gfs2_glock_dq_uninit(&ip->i_alloc->al_ri_gh);
         return error;
 }
 
diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c
index 6798755b3858..4a456338b873 100644
--- a/fs/gfs2/dentry.c
+++ b/fs/gfs2/dentry.c
@@ -11,6 +11,7 @@
 #include <linux/completion.h>
 #include <linux/buffer_head.h>
 #include <linux/gfs2_ondisk.h>
+#include <linux/namei.h>
 #include <linux/crc32.h>
 
 #include "gfs2.h"
@@ -34,15 +35,23 @@
 
 static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd)
 {
-        struct dentry *parent = dget_parent(dentry);
-        struct gfs2_sbd *sdp = GFS2_SB(parent->d_inode);
-        struct gfs2_inode *dip = GFS2_I(parent->d_inode);
-        struct inode *inode = dentry->d_inode;
+        struct dentry *parent;
+        struct gfs2_sbd *sdp;
+        struct gfs2_inode *dip;
+        struct inode *inode;
         struct gfs2_holder d_gh;
         struct gfs2_inode *ip = NULL;
         int error;
         int had_lock = 0;
 
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
+
+        parent = dget_parent(dentry);
+        sdp = GFS2_SB(parent->d_inode);
+        dip = GFS2_I(parent->d_inode);
+        inode = dentry->d_inode;
+
         if (inode) {
                 if (is_bad_inode(inode))
                         goto invalid;
@@ -100,13 +109,14 @@ fail:
         return 0;
 }
 
-static int gfs2_dhash(struct dentry *dentry, struct qstr *str)
+static int gfs2_dhash(const struct dentry *dentry, const struct inode *inode,
+                struct qstr *str)
 {
         str->hash = gfs2_disk_hash(str->name, str->len);
         return 0;
 }
 
-static int gfs2_dentry_delete(struct dentry *dentry)
+static int gfs2_dentry_delete(const struct dentry *dentry)
 {
         struct gfs2_inode *ginode;
 
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index 5ab3839dfcb9..97012ecff560 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -130,7 +130,7 @@ static struct dentry *gfs2_get_parent(struct dentry *child)
 
         dentry = d_obtain_alias(gfs2_lookupi(child->d_inode, &gfs2_qdotdot, 1));
         if (!IS_ERR(dentry))
-                dentry->d_op = &gfs2_dops;
+                d_set_d_op(dentry, &gfs2_dops);
         return dentry;
 }
 
@@ -158,7 +158,7 @@ static struct dentry *gfs2_get_dentry(struct super_block *sb,
 out_inode:
         dentry = d_obtain_alias(inode);
         if (!IS_ERR(dentry))
-                dentry->d_op = &gfs2_dops;
+                d_set_d_op(dentry, &gfs2_dops);
         return dentry;
 }
 
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index aa996471ec5c..fca6689e12e6 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -241,7 +241,7 @@ static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask)
             !capable(CAP_LINUX_IMMUTABLE))
                 goto out;
         if (!IS_IMMUTABLE(inode)) {
-                error = gfs2_permission(inode, MAY_WRITE);
+                error = gfs2_permission(inode, MAY_WRITE, 0);
                 if (error)
                         goto out;
         }
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index f92c17704169..08a8beb152e6 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -541,21 +541,6 @@ out_locked:
         spin_unlock(&gl->gl_spin);
 }
 
-static unsigned int gfs2_lm_lock(struct gfs2_sbd *sdp, void *lock,
-                                 unsigned int req_state,
-                                 unsigned int flags)
-{
-        int ret = LM_OUT_ERROR;
-
-        if (!sdp->sd_lockstruct.ls_ops->lm_lock)
-                return req_state == LM_ST_UNLOCKED ? 0 : req_state;
-
-        if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
-                ret = sdp->sd_lockstruct.ls_ops->lm_lock(lock,
-                                                         req_state, flags);
-        return ret;
-}
-
 /**
  * do_xmote - Calls the DLM to change the state of a lock
  * @gl: The lock state
@@ -575,13 +560,14 @@ __acquires(&gl->gl_spin)
 
         lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP |
                       LM_FLAG_PRIORITY);
-        BUG_ON(gl->gl_state == target);
-        BUG_ON(gl->gl_state == gl->gl_target);
+        GLOCK_BUG_ON(gl, gl->gl_state == target);
+        GLOCK_BUG_ON(gl, gl->gl_state == gl->gl_target);
         if ((target == LM_ST_UNLOCKED || target == LM_ST_DEFERRED) &&
             glops->go_inval) {
                 set_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags);
                 do_error(gl, 0); /* Fail queued try locks */
         }
+        gl->gl_req = target;
         spin_unlock(&gl->gl_spin);
         if (glops->go_xmote_th)
                 glops->go_xmote_th(gl);
@@ -594,15 +580,17 @@ __acquires(&gl->gl_spin)
             gl->gl_state == LM_ST_DEFERRED) &&
             !(lck_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)))
                 lck_flags |= LM_FLAG_TRY_1CB;
-        ret = gfs2_lm_lock(sdp, gl, target, lck_flags);
 
-        if (!(ret & LM_OUT_ASYNC)) {
-                finish_xmote(gl, ret);
+        if (sdp->sd_lockstruct.ls_ops->lm_lock) {
+                /* lock_dlm */
+                ret = sdp->sd_lockstruct.ls_ops->lm_lock(gl, target, lck_flags);
+                GLOCK_BUG_ON(gl, ret);
+        } else { /* lock_nolock */
+                finish_xmote(gl, target);
                 if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
                         gfs2_glock_put(gl);
-        } else {
-                GLOCK_BUG_ON(gl, ret != LM_OUT_ASYNC);
         }
+
         spin_lock(&gl->gl_spin);
 }
 
@@ -951,17 +939,22 @@ int gfs2_glock_wait(struct gfs2_holder *gh)
 
 void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...)
 {
+        struct va_format vaf;
         va_list args;
 
         va_start(args, fmt);
+
         if (seq) {
                 struct gfs2_glock_iter *gi = seq->private;
                 vsprintf(gi->string, fmt, args);
                 seq_printf(seq, gi->string);
         } else {
-                printk(KERN_ERR " ");
-                vprintk(fmt, args);
+                vaf.fmt = fmt;
+                vaf.va = &args;
+
+                printk(KERN_ERR " %pV", &vaf);
         }
+
         va_end(args);
 }
 
@@ -1361,24 +1354,28 @@ static int gfs2_should_freeze(const struct gfs2_glock *gl)
  * @gl: Pointer to the glock
  * @ret: The return value from the dlm
  *
+ * The gl_reply field is under the gl_spin lock so that it is ok
+ * to use a bitfield shared with other glock state fields.
  */
 
 void gfs2_glock_complete(struct gfs2_glock *gl, int ret)
 {
         struct lm_lockstruct *ls = &gl->gl_sbd->sd_lockstruct;
 
+        spin_lock(&gl->gl_spin);
         gl->gl_reply = ret;
 
         if (unlikely(test_bit(DFL_BLOCK_LOCKS, &ls->ls_flags))) {
-                spin_lock(&gl->gl_spin);
                 if (gfs2_should_freeze(gl)) {
                         set_bit(GLF_FROZEN, &gl->gl_flags);
                         spin_unlock(&gl->gl_spin);
                         return;
                 }
-                spin_unlock(&gl->gl_spin);
         }
+
+        spin_unlock(&gl->gl_spin);
         set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
+        smp_wmb();
         gfs2_glock_hold(gl);
         if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
                 gfs2_glock_put(gl);
@@ -1626,18 +1623,17 @@ static const char *hflags2str(char *buf, unsigned flags, unsigned long iflags)
 static int dump_holder(struct seq_file *seq, const struct gfs2_holder *gh)
 {
         struct task_struct *gh_owner = NULL;
-        char buffer[KSYM_SYMBOL_LEN];
         char flags_buf[32];
 
-        sprint_symbol(buffer, gh->gh_ip);
         if (gh->gh_owner_pid)
                 gh_owner = pid_task(gh->gh_owner_pid, PIDTYPE_PID);
-        gfs2_print_dbg(seq, " H: s:%s f:%s e:%d p:%ld [%s] %s\n",
-                  state2str(gh->gh_state),
-                  hflags2str(flags_buf, gh->gh_flags, gh->gh_iflags),
-                  gh->gh_error, 
-                  gh->gh_owner_pid ? (long)pid_nr(gh->gh_owner_pid) : -1,
-                  gh_owner ? gh_owner->comm : "(ended)", buffer);
+        gfs2_print_dbg(seq, " H: s:%s f:%s e:%d p:%ld [%s] %pS\n",
+                       state2str(gh->gh_state),
+                       hflags2str(flags_buf, gh->gh_flags, gh->gh_iflags),
+                       gh->gh_error,
+                       gh->gh_owner_pid ? (long)pid_nr(gh->gh_owner_pid) : -1,
+                       gh_owner ? gh_owner->comm : "(ended)",
+                       (void *)gh->gh_ip);
         return 0;
 }
 
@@ -1782,12 +1778,13 @@ int __init gfs2_glock_init(void)
         }
 #endif
 
-        glock_workqueue = alloc_workqueue("glock_workqueue", WQ_RESCUER |
+        glock_workqueue = alloc_workqueue("glock_workqueue", WQ_MEM_RECLAIM |
                                           WQ_HIGHPRI | WQ_FREEZEABLE, 0);
         if (IS_ERR(glock_workqueue))
                 return PTR_ERR(glock_workqueue);
-        gfs2_delete_workqueue = alloc_workqueue("delete_workqueue", WQ_RESCUER |
-                                                WQ_FREEZEABLE, 0);
+        gfs2_delete_workqueue = alloc_workqueue("delete_workqueue",
+                                                WQ_MEM_RECLAIM | WQ_FREEZEABLE,
+                                                0);
         if (IS_ERR(gfs2_delete_workqueue)) {
                 destroy_workqueue(glock_workqueue);
                 return PTR_ERR(gfs2_delete_workqueue);
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index db1c26d6d220..691851ceb615 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -87,11 +87,10 @@ enum {
 #define GL_ASYNC                0x00000040
 #define GL_EXACT                0x00000080
 #define GL_SKIP                 0x00000100
-#define GL_ATIME                0x00000200
 #define GL_NOCACHE              0x00000400
   
 /*
- * lm_lock() and lm_async_cb return flags
+ * lm_async_cb return flags
  *
  * LM_OUT_ST_MASK
  * Masks the lower two bits of lock state in the returned value.
@@ -99,15 +98,11 @@ enum {
  * LM_OUT_CANCELED
  * The lock request was canceled.
  *
- * LM_OUT_ASYNC
- * The result of the request will be returned in an LM_CB_ASYNC callback.
- *
  */
 
 #define LM_OUT_ST_MASK          0x00000003
 #define LM_OUT_CANCELED         0x00000008
-#define LM_OUT_ASYNC            0x00000080
-#define LM_OUT_ERROR            0x00000100
+#define LM_OUT_ERROR            0x00000004
 
 /*
  * lm_recovery_done() messages
@@ -124,25 +119,12 @@ struct lm_lockops {
         void (*lm_unmount) (struct gfs2_sbd *sdp);
         void (*lm_withdraw) (struct gfs2_sbd *sdp);
         void (*lm_put_lock) (struct kmem_cache *cachep, struct gfs2_glock *gl);
-        unsigned int (*lm_lock) (struct gfs2_glock *gl,
-                                 unsigned int req_state, unsigned int flags);
+        int (*lm_lock) (struct gfs2_glock *gl, unsigned int req_state,
+                        unsigned int flags);
         void (*lm_cancel) (struct gfs2_glock *gl);
         const match_table_t *lm_tokens;
 };
 
-#define LM_FLAG_TRY             0x00000001
-#define LM_FLAG_TRY_1CB         0x00000002
-#define LM_FLAG_NOEXP           0x00000004
-#define LM_FLAG_ANY             0x00000008
-#define LM_FLAG_PRIORITY        0x00000010
-
-#define GL_ASYNC                0x00000040
-#define GL_EXACT                0x00000080
-#define GL_SKIP                 0x00000100
-#define GL_NOCACHE              0x00000400
-
-#define GLR_TRYFAILED           13
-
 extern struct workqueue_struct *gfs2_delete_workqueue;
 static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock *gl)
 {
@@ -212,6 +194,8 @@ int gfs2_glock_nq_num(struct gfs2_sbd *sdp,
 int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs);
 void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs);
 void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs);
+
+__attribute__ ((format(printf, 2, 3)))
 void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...);
 
 /**
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 0d149dcc04e5..263561bf1a50 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -325,7 +325,6 @@ static void trans_go_sync(struct gfs2_glock *gl)
 
         if (gl->gl_state != LM_ST_UNLOCKED &&
             test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
-                flush_workqueue(gfs2_delete_workqueue);
                 gfs2_meta_syncfs(sdp);
                 gfs2_log_shutdown(sdp);
         }
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 764fbb49efc8..a79790c06275 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -11,6 +11,7 @@
 #define __INCORE_DOT_H__
 
 #include <linux/fs.h>
+#include <linux/kobject.h>
 #include <linux/workqueue.h>
 #include <linux/dlm.h>
 #include <linux/buffer_head.h>
@@ -207,12 +208,14 @@ struct gfs2_glock {
 
         spinlock_t gl_spin;
 
-        unsigned int gl_state;
-        unsigned int gl_target;
-        unsigned int gl_reply;
+        /* State fields protected by gl_spin */
+        unsigned int gl_state:2,        /* Current state */
+                     gl_target:2,       /* Target state */
+                     gl_demote_state:2, /* State requested by remote node */
+                     gl_req:2,          /* State in last dlm request */
+                     gl_reply:8;        /* Last reply from the dlm */
+
         unsigned int gl_hash;
-        unsigned int gl_req;
-        unsigned int gl_demote_state; /* state requested by remote node */
         unsigned long gl_demote_time; /* time of first demote request */
         struct list_head gl_holders;
 
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index e1213f7f9217..2232b3c780bd 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -509,7 +509,7 @@ struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
         }
 
         if (!is_root) {
-                error = gfs2_permission(dir, MAY_EXEC);
+                error = gfs2_permission(dir, MAY_EXEC, 0);
                 if (error)
                         goto out;
         }
@@ -539,7 +539,7 @@ static int create_ok(struct gfs2_inode *dip, const struct qstr *name,
 {
         int error;
 
-        error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC);
+        error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC, 0);
         if (error)
                 return error;
 
@@ -916,17 +916,8 @@ static int __gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
         if (error)
                 return error;
 
-        if ((attr->ia_valid & ATTR_SIZE) &&
-            attr->ia_size != i_size_read(inode)) {
-                error = vmtruncate(inode, attr->ia_size);
-                if (error)
-                        return error;
-        }
-
         setattr_copy(inode, attr);
         mark_inode_dirty(inode);
-
-        gfs2_assert_warn(GFS2_SB(inode), !error);
         gfs2_trans_add_bh(ip->i_gl, dibh, 1);
         gfs2_dinode_out(ip, dibh->b_data);
         brelse(dibh);
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index d8499fadcc53..732a183efdb3 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -113,7 +113,7 @@ extern struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
 extern struct inode *gfs2_createi(struct gfs2_holder *ghs,
                                   const struct qstr *name,
                                   unsigned int mode, dev_t dev);
-extern int gfs2_permission(struct inode *inode, int mask);
+extern int gfs2_permission(struct inode *inode, int mask, unsigned int flags);
 extern int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr);
 extern struct inode *gfs2_lookup_simple(struct inode *dip, const char *name);
 extern void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf);
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 1c09425b45fd..6e493aee28f8 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -146,15 +146,13 @@ static u32 make_flags(const u32 lkid, const unsigned int gfs_flags,
         return lkf;
 }
 
-static unsigned int gdlm_lock(struct gfs2_glock *gl,
-                              unsigned int req_state, unsigned int flags)
+static int gdlm_lock(struct gfs2_glock *gl, unsigned int req_state,
+                     unsigned int flags)
 {
         struct lm_lockstruct *ls = &gl->gl_sbd->sd_lockstruct;
-        int error;
         int req;
         u32 lkf;
 
-        gl->gl_req = req_state;
         req = make_mode(req_state);
         lkf = make_flags(gl->gl_lksb.sb_lkid, flags, req);
 
@@ -162,13 +160,8 @@ static unsigned int gdlm_lock(struct gfs2_glock *gl,
          * Submit the actual lock request.
          */
 
-        error = dlm_lock(ls->ls_dlm, req, &gl->gl_lksb, lkf, gl->gl_strname,
-                         GDLM_STRNAME_BYTES - 1, 0, gdlm_ast, gl, gdlm_bast);
-        if (error == -EAGAIN)
-                return 0;
-        if (error)
-                return LM_OUT_ERROR;
-        return LM_OUT_ASYNC;
+        return dlm_lock(ls->ls_dlm, req, &gl->gl_lksb, lkf, gl->gl_strname,
+                        GDLM_STRNAME_BYTES - 1, 0, gdlm_ast, gl, gdlm_bast);
 }
 
 static void gdlm_put_lock(struct kmem_cache *cachep, struct gfs2_glock *gl)
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 3eb1393f7b81..2aeabd4218cc 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -440,7 +440,7 @@ static int gfs2_lookup_root(struct super_block *sb, struct dentry **dptr,
                 iput(inode);
                 return -ENOMEM;
         }
-        dentry->d_op = &gfs2_dops;
+        d_set_d_op(dentry, &gfs2_dops);
         *dptr = dentry;
         return 0;
 }
diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index 12cbea7502c2..1501db4f0e6d 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -106,7 +106,7 @@ static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry,
 {
         struct inode *inode = NULL;
 
-        dentry->d_op = &gfs2_dops;
+        d_set_d_op(dentry, &gfs2_dops);
 
         inode = gfs2_lookupi(dir, &dentry->d_name, 0);
         if (inode && IS_ERR(inode))
@@ -166,7 +166,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
         if (error)
                 goto out_child;
 
-        error = gfs2_permission(dir, MAY_WRITE | MAY_EXEC);
+        error = gfs2_permission(dir, MAY_WRITE | MAY_EXEC, 0);
         if (error)
                 goto out_gunlock;
 
@@ -289,7 +289,7 @@ static int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
         if (IS_APPEND(&dip->i_inode))
                 return -EPERM;
 
-        error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC);
+        error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC, 0);
         if (error)
                 return error;
 
@@ -822,7 +822,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
                         }
                 }
         } else {
-                error = gfs2_permission(ndir, MAY_WRITE | MAY_EXEC);
+                error = gfs2_permission(ndir, MAY_WRITE | MAY_EXEC, 0);
                 if (error)
                         goto out_gunlock;
 
@@ -857,7 +857,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
         /* Check out the dir to be renamed */
 
         if (dir_rename) {
-                error = gfs2_permission(odentry->d_inode, MAY_WRITE);
+                error = gfs2_permission(odentry->d_inode, MAY_WRITE, 0);
                 if (error)
                         goto out_gunlock;
         }
@@ -1041,13 +1041,17 @@ static void gfs2_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
  * Returns: errno
  */
 
-int gfs2_permission(struct inode *inode, int mask)
+int gfs2_permission(struct inode *inode, int mask, unsigned int flags)
 {
-        struct gfs2_inode *ip = GFS2_I(inode);
+        struct gfs2_inode *ip;
         struct gfs2_holder i_gh;
         int error;
         int unlock = 0;
 
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
+        ip = GFS2_I(inode);
         if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) {
                 error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
                 if (error)
@@ -1058,7 +1062,7 @@ int gfs2_permission(struct inode *inode, int mask)
         if ((mask & MAY_WRITE) && IS_IMMUTABLE(inode))
                 error = -EACCES;
         else
-                error = generic_permission(inode, mask, gfs2_check_acl);
+                error = generic_permission(inode, mask, flags, gfs2_check_acl);
         if (unlock)
                 gfs2_glock_dq_uninit(&i_gh);
 
@@ -1069,7 +1073,6 @@ static int setattr_chown(struct inode *inode, struct iattr *attr)
 {
         struct gfs2_inode *ip = GFS2_I(inode);
         struct gfs2_sbd *sdp = GFS2_SB(inode);
-        struct buffer_head *dibh;
         u32 ouid, ogid, nuid, ngid;
         int error;
 
@@ -1100,25 +1103,10 @@ static int setattr_chown(struct inode *inode, struct iattr *attr)
         if (error)
                 goto out_gunlock_q;
 
-        error = gfs2_meta_inode_buffer(ip, &dibh);
+        error = gfs2_setattr_simple(ip, attr);
         if (error)
                 goto out_end_trans;
 
-        if ((attr->ia_valid & ATTR_SIZE) &&
-            attr->ia_size != i_size_read(inode)) {
-                int error;
-
-                error = vmtruncate(inode, attr->ia_size);
-                gfs2_assert_warn(sdp, !error);
-        }
-
-        setattr_copy(inode, attr);
-        mark_inode_dirty(inode);
-
-        gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-        gfs2_dinode_out(ip, dibh->b_data);
-        brelse(dibh);
-
         if (ouid != NO_QUOTA_CHANGE || ogid != NO_QUOTA_CHANGE) {
                 u64 blocks = gfs2_get_inode_blocks(&ip->i_inode);
                 gfs2_quota_change(ip, -blocks, ouid, ogid);
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index f606baf9ba72..a689901963de 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -666,6 +666,10 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
                         qp->qu_limit = cpu_to_be64(fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift);
                         qd->qd_qb.qb_limit = qp->qu_limit;
                 }
+                if (fdq->d_fieldmask & FS_DQ_BCOUNT) {
+                        qp->qu_value = cpu_to_be64(fdq->d_bcount >> sdp->sd_fsb2bb_shift);
+                        qd->qd_qb.qb_value = qp->qu_value;
+                }
         }
 
         /* Write the quota into the quota file on disk */
@@ -1509,7 +1513,7 @@ out:
 }
 
 /* GFS2 only supports a subset of the XFS fields */
-#define GFS2_FIELDMASK (FS_DQ_BSOFT|FS_DQ_BHARD)
+#define GFS2_FIELDMASK (FS_DQ_BSOFT|FS_DQ_BHARD|FS_DQ_BCOUNT)
 
 static int gfs2_set_dqblk(struct super_block *sb, int type, qid_t id,
                           struct fs_disk_quota *fdq)
@@ -1569,9 +1573,15 @@ static int gfs2_set_dqblk(struct super_block *sb, int type, qid_t id,
         if ((fdq->d_fieldmask & FS_DQ_BSOFT) &&
             ((fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_warn)))
                 fdq->d_fieldmask ^= FS_DQ_BSOFT;
+
         if ((fdq->d_fieldmask & FS_DQ_BHARD) &&
             ((fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_limit)))
                 fdq->d_fieldmask ^= FS_DQ_BHARD;
+
+        if ((fdq->d_fieldmask & FS_DQ_BCOUNT) &&
+            ((fdq->d_bcount >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_value)))
+                fdq->d_fieldmask ^= FS_DQ_BCOUNT;
+
         if (fdq->d_fieldmask == 0)
                 goto out_i;
 
@@ -1620,4 +1630,3 @@ const struct quotactl_ops gfs2_quotactl_ops = {
         .get_dqblk      = gfs2_get_dqblk,
         .set_dqblk      = gfs2_set_dqblk,
 };
-
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 33c8407b876f..7293ea27020c 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -500,7 +500,7 @@ u64 gfs2_ri_total(struct gfs2_sbd *sdp)
         for (rgrps = 0;; rgrps++) {
                 loff_t pos = rgrps * sizeof(struct gfs2_rindex);
 
-                if (pos + sizeof(struct gfs2_rindex) >= i_size_read(inode))
+                if (pos + sizeof(struct gfs2_rindex) > i_size_read(inode))
                         break;
                 error = gfs2_internal_read(ip, &ra_state, buf, &pos,
                                            sizeof(struct gfs2_rindex));
@@ -583,7 +583,7 @@ static int read_rindex_entry(struct gfs2_inode *ip,
  * Returns: 0 on successful update, error code otherwise
  */
 
-static int gfs2_ri_update(struct gfs2_inode *ip)
+int gfs2_ri_update(struct gfs2_inode *ip)
 {
         struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
         struct inode *inode = &ip->i_inode;
@@ -614,46 +614,6 @@ static int gfs2_ri_update(struct gfs2_inode *ip)
 }
 
 /**
- * gfs2_ri_update_special - Pull in a new resource index from the disk
- *
- * This is a special version that's safe to call from gfs2_inplace_reserve_i.
- * In this case we know that we don't have any resource groups in memory yet.
- *
- * @ip: pointer to the rindex inode
- *
- * Returns: 0 on successful update, error code otherwise
- */
-static int gfs2_ri_update_special(struct gfs2_inode *ip)
-{
-        struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-        struct inode *inode = &ip->i_inode;
-        struct file_ra_state ra_state;
-        struct gfs2_rgrpd *rgd;
-        unsigned int max_data = 0;
-        int error;
-
-        file_ra_state_init(&ra_state, inode->i_mapping);
-        for (sdp->sd_rgrps = 0;; sdp->sd_rgrps++) {
-                /* Ignore partials */
-                if ((sdp->sd_rgrps + 1) * sizeof(struct gfs2_rindex) >
-                    i_size_read(inode))
-                        break;
-                error = read_rindex_entry(ip, &ra_state);
-                if (error) {
-                        clear_rgrpdi(sdp);
-                        return error;
-                }
-        }
-        list_for_each_entry(rgd, &sdp->sd_rindex_list, rd_list)
-                if (rgd->rd_data > max_data)
-                        max_data = rgd->rd_data;
-        sdp->sd_max_rg_data = max_data;
-
-        sdp->sd_rindex_uptodate = 1;
-        return 0;
-}
-
-/**
  * gfs2_rindex_hold - Grab a lock on the rindex
  * @sdp: The GFS2 superblock
  * @ri_gh: the glock holder
@@ -1226,16 +1186,25 @@ int gfs2_inplace_reserve_i(struct gfs2_inode *ip, int hold_rindex,
                         error = gfs2_rindex_hold(sdp, &al->al_ri_gh);
                 else if (!sdp->sd_rgrps) /* We may not have the rindex read
                                             in, so: */
-                        error = gfs2_ri_update_special(ip);
+                        error = gfs2_ri_update(ip);
                 if (error)
                         return error;
         }
 
+try_again:
         do {
                 error = get_local_rgrp(ip, &last_unlinked);
                 /* If there is no space, flushing the log may release some */
-                if (error)
+                if (error) {
+                        if (ip == GFS2_I(sdp->sd_rindex) &&
+                            !sdp->sd_rindex_uptodate) {
+                                error = gfs2_ri_update(ip);
+                                if (error)
+                                        return error;
+                                goto try_again;
+                        }
                         gfs2_log_flush(sdp, NULL);
+                }
         } while (error && tries++ < 3);
 
         if (error) {
diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h
index 0e35c0466f9a..50c2bb04369c 100644
--- a/fs/gfs2/rgrp.h
+++ b/fs/gfs2/rgrp.h
@@ -48,6 +48,7 @@ extern int gfs2_inplace_reserve_i(struct gfs2_inode *ip, int hold_rindex,
 
 extern void gfs2_inplace_release(struct gfs2_inode *ip);
 
+extern int gfs2_ri_update(struct gfs2_inode *ip);
 extern int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n);
 extern int gfs2_alloc_di(struct gfs2_inode *ip, u64 *bn, u64 *generation);
 
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 2b2c4997430b..16c2ecac7eb7 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1405,11 +1405,18 @@ static struct inode *gfs2_alloc_inode(struct super_block *sb)
         return &ip->i_inode;
 }
 
-static void gfs2_destroy_inode(struct inode *inode)
+static void gfs2_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(gfs2_inode_cachep, inode);
 }
 
+static void gfs2_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, gfs2_i_callback);
+}
+
 const struct super_operations gfs2_super_ops = {
         .alloc_inode            = gfs2_alloc_inode,
         .destroy_inode          = gfs2_destroy_inode,
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index 30b58f07c8a6..439b61c03262 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -1296,10 +1296,8 @@ fail:
 
 int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data)
 {
-        struct inode *inode = &ip->i_inode;
         struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
         struct gfs2_ea_location el;
-        struct buffer_head *dibh;
         int error;
 
         error = gfs2_ea_find(ip, GFS2_EATYPE_SYS, GFS2_POSIX_ACL_ACCESS, &el);
@@ -1321,26 +1319,7 @@ int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data)
         if (error)
                 return error;
 
-        error = gfs2_meta_inode_buffer(ip, &dibh);
-        if (error)
-                goto out_trans_end;
-
-        if ((attr->ia_valid & ATTR_SIZE) &&
-            attr->ia_size != i_size_read(inode)) {
-                int error;
-
-                error = vmtruncate(inode, attr->ia_size);
-                gfs2_assert_warn(GFS2_SB(inode), !error);
-        }
-
-        setattr_copy(inode, attr);
-        mark_inode_dirty(inode);
-
-        gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-        gfs2_dinode_out(ip, dibh->b_data);
-        brelse(dibh);
-
-out_trans_end:
+        error = gfs2_setattr_simple(ip, attr);
         gfs2_trans_end(sdp);
         return error;
 }
diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c
index 2b3b8611b41b..ea4aefe7c652 100644
--- a/fs/hfs/dir.c
+++ b/fs/hfs/dir.c
@@ -25,7 +25,7 @@ static struct dentry *hfs_lookup(struct inode *dir, struct dentry *dentry,
         struct inode *inode = NULL;
         int res;
 
-        dentry->d_op = &hfs_dentry_operations;
+        d_set_d_op(dentry, &hfs_dentry_operations);
 
         hfs_find_init(HFS_SB(dir->i_sb)->cat_tree, &fd);
         hfs_cat_build_key(dir->i_sb, fd.search_key, dir->i_ino, &dentry->d_name);
diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h
index c8cffb81e849..ad97c2d58287 100644
--- a/fs/hfs/hfs_fs.h
+++ b/fs/hfs/hfs_fs.h
@@ -213,10 +213,14 @@ extern int hfs_part_find(struct super_block *, sector_t *, sector_t *);
 /* string.c */
 extern const struct dentry_operations hfs_dentry_operations;
 
-extern int hfs_hash_dentry(struct dentry *, struct qstr *);
+extern int hfs_hash_dentry(const struct dentry *, const struct inode *,
+                struct qstr *);
 extern int hfs_strcmp(const unsigned char *, unsigned int,
                       const unsigned char *, unsigned int);
-extern int hfs_compare_dentry(struct dentry *, struct qstr *, struct qstr *);
+extern int hfs_compare_dentry(const struct dentry *parent,
+                const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name);
 
 /* trans.c */
 extern void hfs_asc2mac(struct super_block *, struct hfs_name *, struct qstr *);
diff --git a/fs/hfs/string.c b/fs/hfs/string.c
index 927a5af79428..495a976a3cc9 100644
--- a/fs/hfs/string.c
+++ b/fs/hfs/string.c
@@ -51,7 +51,8 @@ static unsigned char caseorder[256] = {
 /*
  * Hash a string to an integer in a case-independent way
  */
-int hfs_hash_dentry(struct dentry *dentry, struct qstr *this)
+int hfs_hash_dentry(const struct dentry *dentry, const struct inode *inode,
+                struct qstr *this)
 {
         const unsigned char *name = this->name;
         unsigned int hash, len = this->len;
@@ -92,21 +93,21 @@ int hfs_strcmp(const unsigned char *s1, unsigned int len1,
  * Test for equality of two strings in the HFS filename character ordering.
  * return 1 on failure and 0 on success
  */
-int hfs_compare_dentry(struct dentry *dentry, struct qstr *s1, struct qstr *s2)
+int hfs_compare_dentry(const struct dentry *parent, const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name)
 {
         const unsigned char *n1, *n2;
-        int len;
 
-        len = s1->len;
         if (len >= HFS_NAMELEN) {
-                if (s2->len < HFS_NAMELEN)
+                if (name->len < HFS_NAMELEN)
                         return 1;
                 len = HFS_NAMELEN;
-        } else if (len != s2->len)
+        } else if (len != name->len)
                 return 1;
 
-        n1 = s1->name;
-        n2 = s2->name;
+        n1 = str;
+        n2 = name->name;
         while (len--) {
                 if (caseorder[*n1++] != caseorder[*n2++])
                         return 1;
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index 4824c27cebb8..0bef62aa4f42 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -167,11 +167,18 @@ static struct inode *hfs_alloc_inode(struct super_block *sb)
         return i ? &i->vfs_inode : NULL;
 }
 
-static void hfs_destroy_inode(struct inode *inode)
+static void hfs_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(hfs_inode_cachep, HFS_I(inode));
 }
 
+static void hfs_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, hfs_i_callback);
+}
+
 static const struct super_operations hfs_super_operations = {
         .alloc_inode    = hfs_alloc_inode,
         .destroy_inode  = hfs_destroy_inode,
@@ -427,7 +434,7 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent)
         if (!sb->s_root)
                 goto bail_iput;
 
-        sb->s_root->d_op = &hfs_dentry_operations;
+        d_set_d_op(sb->s_root, &hfs_dentry_operations);
 
         /* everything's okay */
         return 0;
diff --git a/fs/hfs/sysdep.c b/fs/hfs/sysdep.c
index 7478f5c219aa..19cf291eb91f 100644
--- a/fs/hfs/sysdep.c
+++ b/fs/hfs/sysdep.c
@@ -8,15 +8,20 @@
  * This file contains the code to do various system dependent things.
  */
 
+#include <linux/namei.h>
 #include "hfs_fs.h"
 
 /* dentry case-handling: just lowercase everything */
 
 static int hfs_revalidate_dentry(struct dentry *dentry, struct nameidata *nd)
 {
-        struct inode *inode = dentry->d_inode;
+        struct inode *inode;
         int diff;
 
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
+
+        inode = dentry->d_inode;
         if(!inode)
                 return 1;
 
diff --git a/fs/hfsplus/bfind.c b/fs/hfsplus/bfind.c
index d182438c7ae4..5d799c13205f 100644
--- a/fs/hfsplus/bfind.c
+++ b/fs/hfsplus/bfind.c
@@ -22,7 +22,8 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd)
                 return -ENOMEM;
         fd->search_key = ptr;
         fd->key = ptr + tree->max_key_len + 2;
-        dprint(DBG_BNODE_REFS, "find_init: %d (%p)\n", tree->cnid, __builtin_return_address(0));
+        dprint(DBG_BNODE_REFS, "find_init: %d (%p)\n",
+                tree->cnid, __builtin_return_address(0));
         mutex_lock(&tree->tree_lock);
         return 0;
 }
@@ -31,7 +32,8 @@ void hfs_find_exit(struct hfs_find_data *fd)
 {
         hfs_bnode_put(fd->bnode);
         kfree(fd->search_key);
-        dprint(DBG_BNODE_REFS, "find_exit: %d (%p)\n", fd->tree->cnid, __builtin_return_address(0));
+        dprint(DBG_BNODE_REFS, "find_exit: %d (%p)\n",
+                fd->tree->cnid, __builtin_return_address(0));
         mutex_unlock(&fd->tree->tree_lock);
         fd->tree = NULL;
 }
diff --git a/fs/hfsplus/bitmap.c b/fs/hfsplus/bitmap.c
index ad57f5991eb1..1cad80c789cb 100644
--- a/fs/hfsplus/bitmap.c
+++ b/fs/hfsplus/bitmap.c
@@ -15,7 +15,8 @@
 
 #define PAGE_CACHE_BITS (PAGE_CACHE_SIZE * 8)
 
-int hfsplus_block_allocate(struct super_block *sb, u32 size, u32 offset, u32 *max)
+int hfsplus_block_allocate(struct super_block *sb, u32 size,
+                u32 offset, u32 *max)
 {
         struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
         struct page *page;
diff --git a/fs/hfsplus/bnode.c b/fs/hfsplus/bnode.c
index 29da6574ba77..1c42cc5b899f 100644
--- a/fs/hfsplus/bnode.c
+++ b/fs/hfsplus/bnode.c
@@ -42,7 +42,7 @@ void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len)
 u16 hfs_bnode_read_u16(struct hfs_bnode *node, int off)
 {
         __be16 data;
-        // optimize later...
+        /* TODO: optimize later... */
         hfs_bnode_read(node, &data, off, 2);
         return be16_to_cpu(data);
 }
@@ -50,7 +50,7 @@ u16 hfs_bnode_read_u16(struct hfs_bnode *node, int off)
 u8 hfs_bnode_read_u8(struct hfs_bnode *node, int off)
 {
         u8 data;
-        // optimize later...
+        /* TODO: optimize later... */
         hfs_bnode_read(node, &data, off, 1);
         return data;
 }
@@ -96,7 +96,7 @@ void hfs_bnode_write(struct hfs_bnode *node, void *buf, int off, int len)
 void hfs_bnode_write_u16(struct hfs_bnode *node, int off, u16 data)
 {
         __be16 v = cpu_to_be16(data);
-        // optimize later...
+        /* TODO: optimize later... */
         hfs_bnode_write(node, &v, off, 2);
 }
 
@@ -212,7 +212,8 @@ void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len)
                                 dst_page--;
                         }
                         src -= len;
-                        memmove(kmap(*dst_page) + src, kmap(*src_page) + src, len);
+                        memmove(kmap(*dst_page) + src,
+                                kmap(*src_page) + src, len);
                         kunmap(*src_page);
                         set_page_dirty(*dst_page);
                         kunmap(*dst_page);
@@ -250,14 +251,16 @@ void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len)
 
                 if (src == dst) {
                         l = min(len, (int)PAGE_CACHE_SIZE - src);
-                        memmove(kmap(*dst_page) + src, kmap(*src_page) + src, l);
+                        memmove(kmap(*dst_page) + src,
+                                kmap(*src_page) + src, l);
                         kunmap(*src_page);
                         set_page_dirty(*dst_page);
                         kunmap(*dst_page);
 
                         while ((len -= l) != 0) {
                                 l = min(len, (int)PAGE_CACHE_SIZE);
-                                memmove(kmap(*++dst_page), kmap(*++src_page), l);
+                                memmove(kmap(*++dst_page),
+                                        kmap(*++src_page), l);
                                 kunmap(*src_page);
                                 set_page_dirty(*dst_page);
                                 kunmap(*dst_page);
@@ -268,7 +271,8 @@ void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len)
                         do {
                                 src_ptr = kmap(*src_page) + src;
                                 dst_ptr = kmap(*dst_page) + dst;
-                                if (PAGE_CACHE_SIZE - src < PAGE_CACHE_SIZE - dst) {
+                                if (PAGE_CACHE_SIZE - src <
+                                                PAGE_CACHE_SIZE - dst) {
                                         l = PAGE_CACHE_SIZE - src;
                                         src = 0;
                                         dst += l;
@@ -340,7 +344,8 @@ void hfs_bnode_unlink(struct hfs_bnode *node)
                         return;
                 tmp->next = node->next;
                 cnid = cpu_to_be32(tmp->next);
-                hfs_bnode_write(tmp, &cnid, offsetof(struct hfs_bnode_desc, next), 4);
+                hfs_bnode_write(tmp, &cnid,
+                        offsetof(struct hfs_bnode_desc, next), 4);
                 hfs_bnode_put(tmp);
         } else if (node->type == HFS_NODE_LEAF)
                 tree->leaf_head = node->next;
@@ -351,15 +356,15 @@ void hfs_bnode_unlink(struct hfs_bnode *node)
                         return;
                 tmp->prev = node->prev;
                 cnid = cpu_to_be32(tmp->prev);
-                hfs_bnode_write(tmp, &cnid, offsetof(struct hfs_bnode_desc, prev), 4);
+                hfs_bnode_write(tmp, &cnid,
+                        offsetof(struct hfs_bnode_desc, prev), 4);
                 hfs_bnode_put(tmp);
         } else if (node->type == HFS_NODE_LEAF)
                 tree->leaf_tail = node->prev;
 
-        // move down?
-        if (!node->prev && !node->next) {
-                printk(KERN_DEBUG "hfs_btree_del_level\n");
-        }
+        /* move down? */
+        if (!node->prev && !node->next)
+                dprint(DBG_BNODE_MOD, "hfs_btree_del_level\n");
         if (!node->parent) {
                 tree->root = 0;
                 tree->depth = 0;
@@ -379,16 +384,16 @@ struct hfs_bnode *hfs_bnode_findhash(struct hfs_btree *tree, u32 cnid)
         struct hfs_bnode *node;
 
         if (cnid >= tree->node_count) {
-                printk(KERN_ERR "hfs: request for non-existent node %d in B*Tree\n", cnid);
+                printk(KERN_ERR "hfs: request for non-existent node "
+                                "%d in B*Tree\n",
+                        cnid);
                 return NULL;
         }
 
         for (node = tree->node_hash[hfs_bnode_hash(cnid)];
-             node; node = node->next_hash) {
-                if (node->this == cnid) {
+                        node; node = node->next_hash)
+                if (node->this == cnid)
                         return node;
-                }
-        }
         return NULL;
 }
 
@@ -402,7 +407,9 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid)
         loff_t off;
 
         if (cnid >= tree->node_count) {
-                printk(KERN_ERR "hfs: request for non-existent node %d in B*Tree\n", cnid);
+                printk(KERN_ERR "hfs: request for non-existent node "
+                                "%d in B*Tree\n",
+                        cnid);
                 return NULL;
         }
 
@@ -429,7 +436,8 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid)
         } else {
                 spin_unlock(&tree->hash_lock);
                 kfree(node);
-                wait_event(node2->lock_wq, !test_bit(HFS_BNODE_NEW, &node2->flags));
+                wait_event(node2->lock_wq,
+                        !test_bit(HFS_BNODE_NEW, &node2->flags));
                 return node2;
         }
         spin_unlock(&tree->hash_lock);
@@ -483,7 +491,8 @@ struct hfs_bnode *hfs_bnode_find(struct hfs_btree *tree, u32 num)
         if (node) {
                 hfs_bnode_get(node);
                 spin_unlock(&tree->hash_lock);
-                wait_event(node->lock_wq, !test_bit(HFS_BNODE_NEW, &node->flags));
+                wait_event(node->lock_wq,
+                        !test_bit(HFS_BNODE_NEW, &node->flags));
                 if (test_bit(HFS_BNODE_ERROR, &node->flags))
                         goto node_error;
                 return node;
@@ -497,7 +506,8 @@ struct hfs_bnode *hfs_bnode_find(struct hfs_btree *tree, u32 num)
         if (!test_bit(HFS_BNODE_NEW, &node->flags))
                 return node;
 
-        desc = (struct hfs_bnode_desc *)(kmap(node->page[0]) + node->page_offset);
+        desc = (struct hfs_bnode_desc *)(kmap(node->page[0]) +
+                        node->page_offset);
         node->prev = be32_to_cpu(desc->prev);
         node->next = be32_to_cpu(desc->next);
         node->num_recs = be16_to_cpu(desc->num_recs);
@@ -556,11 +566,13 @@ node_error:
 
 void hfs_bnode_free(struct hfs_bnode *node)
 {
-        //int i;
+#if 0
+        int i;
 
-        //for (i = 0; i < node->tree->pages_per_bnode; i++)
-        //      if (node->page[i])
-        //              page_cache_release(node->page[i]);
+        for (i = 0; i < node->tree->pages_per_bnode; i++)
+                if (node->page[i])
+                        page_cache_release(node->page[i]);
+#endif
         kfree(node);
 }
 
@@ -607,7 +619,8 @@ void hfs_bnode_get(struct hfs_bnode *node)
         if (node) {
                 atomic_inc(&node->refcnt);
                 dprint(DBG_BNODE_REFS, "get_node(%d:%d): %d\n",
-                       node->tree->cnid, node->this, atomic_read(&node->refcnt));
+                        node->tree->cnid, node->this,
+                        atomic_read(&node->refcnt));
         }
 }
 
@@ -619,7 +632,8 @@ void hfs_bnode_put(struct hfs_bnode *node)
                 int i;
 
                 dprint(DBG_BNODE_REFS, "put_node(%d:%d): %d\n",
-                       node->tree->cnid, node->this, atomic_read(&node->refcnt));
+                        node->tree->cnid, node->this,
+                        atomic_read(&node->refcnt));
                 BUG_ON(!atomic_read(&node->refcnt));
                 if (!atomic_dec_and_lock(&node->refcnt, &tree->hash_lock))
                         return;
diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c
index 2f39d05443e1..2312de34bd42 100644
--- a/fs/hfsplus/brec.c
+++ b/fs/hfsplus/brec.c
@@ -39,7 +39,8 @@ u16 hfs_brec_keylen(struct hfs_bnode *node, u16 rec)
            !(node->tree->attributes & HFS_TREE_VARIDXKEYS)) {
                 retval = node->tree->max_key_len + 2;
         } else {
-                recoff = hfs_bnode_read_u16(node, node->tree->node_size - (rec + 1) * 2);
+                recoff = hfs_bnode_read_u16(node,
+                        node->tree->node_size - (rec + 1) * 2);
                 if (!recoff)
                         return 0;
 
@@ -84,7 +85,8 @@ again:
         end_rec_off = tree->node_size - (node->num_recs + 1) * 2;
         end_off = hfs_bnode_read_u16(node, end_rec_off);
         end_rec_off -= 2;
-        dprint(DBG_BNODE_MOD, "insert_rec: %d, %d, %d, %d\n", rec, size, end_off, end_rec_off);
+        dprint(DBG_BNODE_MOD, "insert_rec: %d, %d, %d, %d\n",
+                rec, size, end_off, end_rec_off);
         if (size > end_rec_off - end_off) {
                 if (new_node)
                         panic("not enough room!\n");
@@ -99,7 +101,9 @@ again:
         }
         node->num_recs++;
         /* write new last offset */
-        hfs_bnode_write_u16(node, offsetof(struct hfs_bnode_desc, num_recs), node->num_recs);
+        hfs_bnode_write_u16(node,
+                offsetof(struct hfs_bnode_desc, num_recs),
+                node->num_recs);
         hfs_bnode_write_u16(node, end_rec_off, end_off + size);
         data_off = end_off;
         data_rec_off = end_rec_off + 2;
@@ -151,7 +155,8 @@ skip:
                 if (tree->attributes & HFS_TREE_VARIDXKEYS)
                         key_len = be16_to_cpu(fd->search_key->key_len) + 2;
                 else {
-                        fd->search_key->key_len = cpu_to_be16(tree->max_key_len);
+                        fd->search_key->key_len =
+                                cpu_to_be16(tree->max_key_len);
                         key_len = tree->max_key_len + 2;
                 }
                 goto again;
@@ -180,7 +185,8 @@ again:
                 mark_inode_dirty(tree->inode);
         }
         hfs_bnode_dump(node);
-        dprint(DBG_BNODE_MOD, "remove_rec: %d, %d\n", fd->record, fd->keylength + fd->entrylength);
+        dprint(DBG_BNODE_MOD, "remove_rec: %d, %d\n",
+                fd->record, fd->keylength + fd->entrylength);
         if (!--node->num_recs) {
                 hfs_bnode_unlink(node);
                 if (!node->parent)
@@ -194,7 +200,9 @@ again:
                 __hfs_brec_find(node, fd);
                 goto again;
         }
-        hfs_bnode_write_u16(node, offsetof(struct hfs_bnode_desc, num_recs), node->num_recs);
+        hfs_bnode_write_u16(node,
+                offsetof(struct hfs_bnode_desc, num_recs),
+                node->num_recs);
 
         if (rec_off == end_off)
                 goto skip;
@@ -364,7 +372,8 @@ again:
                 newkeylen = hfs_bnode_read_u16(node, 14) + 2;
         else
                 fd->keylength = newkeylen = tree->max_key_len + 2;
-        dprint(DBG_BNODE_MOD, "update_rec: %d, %d, %d\n", rec, fd->keylength, newkeylen);
+        dprint(DBG_BNODE_MOD, "update_rec: %d, %d, %d\n",
+                rec, fd->keylength, newkeylen);
 
         rec_off = tree->node_size - (rec + 2) * 2;
         end_rec_off = tree->node_size - (parent->num_recs + 1) * 2;
@@ -375,7 +384,7 @@ again:
                 end_off = hfs_bnode_read_u16(parent, end_rec_off);
                 if (end_rec_off - end_off < diff) {
 
-                        printk(KERN_DEBUG "hfs: splitting index node...\n");
+                        dprint(DBG_BNODE_MOD, "hfs: splitting index node.\n");
                         fd->bnode = parent;
                         new_node = hfs_bnode_split(fd);
                         if (IS_ERR(new_node))
@@ -383,7 +392,8 @@ again:
                         parent = fd->bnode;
                         rec = fd->record;
                         rec_off = tree->node_size - (rec + 2) * 2;
-                        end_rec_off = tree->node_size - (parent->num_recs + 1) * 2;
+                        end_rec_off = tree->node_size -
+                                (parent->num_recs + 1) * 2;
                 }
         }
 
diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c
index 22e4d4e32999..21023d9f8ff3 100644
--- a/fs/hfsplus/btree.c
+++ b/fs/hfsplus/btree.c
@@ -51,7 +51,8 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id)
                 goto free_inode;
 
         /* Load the header */
-        head = (struct hfs_btree_header_rec *)(kmap(page) + sizeof(struct hfs_bnode_desc));
+        head = (struct hfs_btree_header_rec *)(kmap(page) +
+                sizeof(struct hfs_bnode_desc));
         tree->root = be32_to_cpu(head->root);
         tree->leaf_count = be32_to_cpu(head->leaf_count);
         tree->leaf_head = be32_to_cpu(head->leaf_head);
@@ -115,7 +116,9 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id)
 
         tree->node_size_shift = ffs(size) - 1;
 
-        tree->pages_per_bnode = (tree->node_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+        tree->pages_per_bnode =
+                (tree->node_size + PAGE_CACHE_SIZE - 1) >>
+                PAGE_CACHE_SHIFT;
 
         kunmap(page);
         page_cache_release(page);
@@ -144,8 +147,10 @@ void hfs_btree_close(struct hfs_btree *tree)
                 while ((node = tree->node_hash[i])) {
                         tree->node_hash[i] = node->next_hash;
                         if (atomic_read(&node->refcnt))
-                                printk(KERN_CRIT "hfs: node %d:%d still has %d user(s)!\n",
-                                        node->tree->cnid, node->this, atomic_read(&node->refcnt));
+                                printk(KERN_CRIT "hfs: node %d:%d "
+                                                "still has %d user(s)!\n",
+                                        node->tree->cnid, node->this,
+                                        atomic_read(&node->refcnt));
                         hfs_bnode_free(node);
                         tree->node_hash_cnt--;
                 }
@@ -166,7 +171,8 @@ void hfs_btree_write(struct hfs_btree *tree)
                 return;
         /* Load the header */
         page = node->page[0];
-        head = (struct hfs_btree_header_rec *)(kmap(page) + sizeof(struct hfs_bnode_desc));
+        head = (struct hfs_btree_header_rec *)(kmap(page) +
+                sizeof(struct hfs_bnode_desc));
 
         head->root = cpu_to_be32(tree->root);
         head->leaf_count = cpu_to_be32(tree->leaf_count);
@@ -272,7 +278,8 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree)
                                                 tree->free_nodes--;
                                                 mark_inode_dirty(tree->inode);
                                                 hfs_bnode_put(node);
-                                                return hfs_bnode_create(tree, idx);
+                                                return hfs_bnode_create(tree,
+                                                        idx);
                                         }
                                 }
                         }
@@ -287,7 +294,7 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree)
                 kunmap(*pagep);
                 nidx = node->next;
                 if (!nidx) {
-                        printk(KERN_DEBUG "hfs: create new bmap node...\n");
+                        dprint(DBG_BNODE_MOD, "hfs: create new bmap node.\n");
                         next_node = hfs_bmap_new_bmap(node, idx);
                 } else
                         next_node = hfs_bnode_find(tree, nidx);
@@ -329,7 +336,9 @@ void hfs_bmap_free(struct hfs_bnode *node)
                 hfs_bnode_put(node);
                 if (!i) {
                         /* panic */;
-                        printk(KERN_CRIT "hfs: unable to free bnode %u. bmap not found!\n", node->this);
+                        printk(KERN_CRIT "hfs: unable to free bnode %u. "
+                                        "bmap not found!\n",
+                                node->this);
                         return;
                 }
                 node = hfs_bnode_find(tree, i);
@@ -337,7 +346,9 @@ void hfs_bmap_free(struct hfs_bnode *node)
                         return;
                 if (node->type != HFS_NODE_MAP) {
                         /* panic */;
-                        printk(KERN_CRIT "hfs: invalid bmap found! (%u,%d)\n", node->this, node->type);
+                        printk(KERN_CRIT "hfs: invalid bmap found! "
+                                        "(%u,%d)\n",
+                                node->this, node->type);
                         hfs_bnode_put(node);
                         return;
                 }
@@ -350,7 +361,9 @@ void hfs_bmap_free(struct hfs_bnode *node)
         m = 1 << (~nidx & 7);
         byte = data[off];
         if (!(byte & m)) {
-                printk(KERN_CRIT "hfs: trying to free free bnode %u(%d)\n", node->this, node->type);
+                printk(KERN_CRIT "hfs: trying to free free bnode "
+                                "%u(%d)\n",
+                        node->this, node->type);
                 kunmap(page);
                 hfs_bnode_put(node);
                 return;
diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c
index 8af45fc5b051..b4ba1b319333 100644
--- a/fs/hfsplus/catalog.c
+++ b/fs/hfsplus/catalog.c
@@ -91,7 +91,8 @@ void hfsplus_cat_set_perms(struct inode *inode, struct hfsplus_perm *perms)
                 perms->dev = 0;
 }
 
-static int hfsplus_cat_build_record(hfsplus_cat_entry *entry, u32 cnid, struct inode *inode)
+static int hfsplus_cat_build_record(hfsplus_cat_entry *entry,
+                u32 cnid, struct inode *inode)
 {
         struct hfsplus_sb_info *sbi = HFSPLUS_SB(inode->i_sb);
 
@@ -128,20 +129,32 @@ static int hfsplus_cat_build_record(hfsplus_cat_entry *entry, u32 cnid, struct i
                 if (cnid == inode->i_ino) {
                         hfsplus_cat_set_perms(inode, &file->permissions);
                         if (S_ISLNK(inode->i_mode)) {
-                                file->user_info.fdType = cpu_to_be32(HFSP_SYMLINK_TYPE);
-                                file->user_info.fdCreator = cpu_to_be32(HFSP_SYMLINK_CREATOR);
+                                file->user_info.fdType =
+                                        cpu_to_be32(HFSP_SYMLINK_TYPE);
+                                file->user_info.fdCreator =
+                                        cpu_to_be32(HFSP_SYMLINK_CREATOR);
                         } else {
-                                file->user_info.fdType = cpu_to_be32(sbi->type);
-                                file->user_info.fdCreator = cpu_to_be32(sbi->creator);
+                                file->user_info.fdType =
+                                        cpu_to_be32(sbi->type);
+                                file->user_info.fdCreator =
+                                        cpu_to_be32(sbi->creator);
                         }
-                        if ((file->permissions.rootflags | file->permissions.userflags) & HFSPLUS_FLG_IMMUTABLE)
-                                file->flags |= cpu_to_be16(HFSPLUS_FILE_LOCKED);
+                        if (HFSPLUS_FLG_IMMUTABLE &
+                                        (file->permissions.rootflags |
+                                        file->permissions.userflags))
+                                file->flags |=
+                                        cpu_to_be16(HFSPLUS_FILE_LOCKED);
                 } else {
-                        file->user_info.fdType = cpu_to_be32(HFSP_HARDLINK_TYPE);
-                        file->user_info.fdCreator = cpu_to_be32(HFSP_HFSPLUS_CREATOR);
-                        file->user_info.fdFlags = cpu_to_be16(0x100);
-                        file->create_date = HFSPLUS_I(sbi->hidden_dir)->create_date;
-                        file->permissions.dev = cpu_to_be32(HFSPLUS_I(inode)->linkid);
+                        file->user_info.fdType =
+                                cpu_to_be32(HFSP_HARDLINK_TYPE);
+                        file->user_info.fdCreator =
+                                cpu_to_be32(HFSP_HFSPLUS_CREATOR);
+                        file->user_info.fdFlags =
+                                cpu_to_be16(0x100);
+                        file->create_date =
+                                HFSPLUS_I(sbi->hidden_dir)->create_date;
+                        file->permissions.dev =
+                                cpu_to_be32(HFSPLUS_I(inode)->linkid);
                 }
                 return sizeof(*file);
         }
@@ -182,12 +195,14 @@ int hfsplus_find_cat(struct super_block *sb, u32 cnid,
                 return -EIO;
         }
 
-        hfsplus_cat_build_key_uni(fd->search_key, be32_to_cpu(tmp.thread.parentID),
-                                 &tmp.thread.nodeName);
+        hfsplus_cat_build_key_uni(fd->search_key,
+                be32_to_cpu(tmp.thread.parentID),
+                &tmp.thread.nodeName);
         return hfs_brec_find(fd);
 }
 
-int hfsplus_create_cat(u32 cnid, struct inode *dir, struct qstr *str, struct inode *inode)
+int hfsplus_create_cat(u32 cnid, struct inode *dir,
+                struct qstr *str, struct inode *inode)
 {
         struct super_block *sb = dir->i_sb;
         struct hfs_find_data fd;
@@ -195,13 +210,15 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir, struct qstr *str, struct ino
         int entry_size;
         int err;
 
-        dprint(DBG_CAT_MOD, "create_cat: %s,%u(%d)\n", str->name, cnid, inode->i_nlink);
+        dprint(DBG_CAT_MOD, "create_cat: %s,%u(%d)\n",
+                str->name, cnid, inode->i_nlink);
         hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
 
         hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
-        entry_size = hfsplus_fill_cat_thread(sb, &entry, S_ISDIR(inode->i_mode) ?
+        entry_size = hfsplus_fill_cat_thread(sb, &entry,
+                S_ISDIR(inode->i_mode) ?
                         HFSPLUS_FOLDER_THREAD : HFSPLUS_FILE_THREAD,
-                        dir->i_ino, str);
+                dir->i_ino, str);
         err = hfs_brec_find(&fd);
         if (err != -ENOENT) {
                 if (!err)
@@ -227,7 +244,8 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir, struct qstr *str, struct ino
 
         dir->i_size++;
         dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
-        mark_inode_dirty(dir);
+        hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY);
+
         hfs_find_exit(&fd);
         return 0;
 
@@ -249,7 +267,8 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
         int err, off;
         u16 type;
 
-        dprint(DBG_CAT_MOD, "delete_cat: %s,%u\n", str ? str->name : NULL, cnid);
+        dprint(DBG_CAT_MOD, "delete_cat: %s,%u\n",
+                str ? str->name : NULL, cnid);
         hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
 
         if (!str) {
@@ -260,11 +279,15 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
                 if (err)
                         goto out;
 
-                off = fd.entryoffset + offsetof(struct hfsplus_cat_thread, nodeName);
+                off = fd.entryoffset +
+                        offsetof(struct hfsplus_cat_thread, nodeName);
                 fd.search_key->cat.parent = cpu_to_be32(dir->i_ino);
-                hfs_bnode_read(fd.bnode, &fd.search_key->cat.name.length, off, 2);
+                hfs_bnode_read(fd.bnode,
+                        &fd.search_key->cat.name.length, off, 2);
                 len = be16_to_cpu(fd.search_key->cat.name.length) * 2;
-                hfs_bnode_read(fd.bnode, &fd.search_key->cat.name.unicode, off + 2, len);
+                hfs_bnode_read(fd.bnode,
+                        &fd.search_key->cat.name.unicode,
+                        off + 2, len);
                 fd.search_key->key_len = cpu_to_be16(6 + len);
         } else
                 hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str);
@@ -281,7 +304,8 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
                 hfsplus_free_fork(sb, cnid, &fork, HFSPLUS_TYPE_DATA);
 #endif
 
-                off = fd.entryoffset + offsetof(struct hfsplus_cat_file, rsrc_fork);
+                off = fd.entryoffset +
+                        offsetof(struct hfsplus_cat_file, rsrc_fork);
                 hfs_bnode_read(fd.bnode, &fork, off, sizeof(fork));
                 hfsplus_free_fork(sb, cnid, &fork, HFSPLUS_TYPE_RSRC);
         }
@@ -308,7 +332,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
 
         dir->i_size--;
         dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
-        mark_inode_dirty(dir);
+        hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY);
 out:
         hfs_find_exit(&fd);
 
@@ -325,7 +349,8 @@ int hfsplus_rename_cat(u32 cnid,
         int entry_size, type;
         int err = 0;
 
-        dprint(DBG_CAT_MOD, "rename_cat: %u - %lu,%s - %lu,%s\n", cnid, src_dir->i_ino, src_name->name,
+        dprint(DBG_CAT_MOD, "rename_cat: %u - %lu,%s - %lu,%s\n",
+                cnid, src_dir->i_ino, src_name->name,
                 dst_dir->i_ino, dst_name->name);
         hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &src_fd);
         dst_fd = src_fd;
@@ -353,7 +378,6 @@ int hfsplus_rename_cat(u32 cnid,
                 goto out;
         dst_dir->i_size++;
         dst_dir->i_mtime = dst_dir->i_ctime = CURRENT_TIME_SEC;
-        mark_inode_dirty(dst_dir);
 
         /* finally remove the old entry */
         hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name);
@@ -365,7 +389,6 @@ int hfsplus_rename_cat(u32 cnid,
                 goto out;
         src_dir->i_size--;
         src_dir->i_mtime = src_dir->i_ctime = CURRENT_TIME_SEC;
-        mark_inode_dirty(src_dir);
 
         /* remove old thread entry */
         hfsplus_cat_build_key(sb, src_fd.search_key, cnid, NULL);
@@ -379,7 +402,8 @@ int hfsplus_rename_cat(u32 cnid,
 
         /* create new thread entry */
         hfsplus_cat_build_key(sb, dst_fd.search_key, cnid, NULL);
-        entry_size = hfsplus_fill_cat_thread(sb, &entry, type, dst_dir->i_ino, dst_name);
+        entry_size = hfsplus_fill_cat_thread(sb, &entry, type,
+                dst_dir->i_ino, dst_name);
         err = hfs_brec_find(&dst_fd);
         if (err != -ENOENT) {
                 if (!err)
@@ -387,6 +411,9 @@ int hfsplus_rename_cat(u32 cnid,
                 goto out;
         }
         err = hfs_brec_insert(&dst_fd, &entry, entry_size);
+
+        hfsplus_mark_inode_dirty(dst_dir, HFSPLUS_I_CAT_DIRTY);
+        hfsplus_mark_inode_dirty(src_dir, HFSPLUS_I_CAT_DIRTY);
 out:
         hfs_bnode_put(dst_fd.bnode);
         hfs_find_exit(&src_fd);
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index 9d59c0571f59..f896dc843026 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -37,7 +37,7 @@ static struct dentry *hfsplus_lookup(struct inode *dir, struct dentry *dentry,
 
         sb = dir->i_sb;
 
-        dentry->d_op = &hfsplus_dentry_operations;
+        d_set_d_op(dentry, &hfsplus_dentry_operations);
         dentry->d_fsdata = NULL;
         hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
         hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, &dentry->d_name);
@@ -66,11 +66,17 @@ again:
                         goto fail;
                 }
                 cnid = be32_to_cpu(entry.file.id);
-                if (entry.file.user_info.fdType == cpu_to_be32(HFSP_HARDLINK_TYPE) &&
-                    entry.file.user_info.fdCreator == cpu_to_be32(HFSP_HFSPLUS_CREATOR) &&
-                    (entry.file.create_date == HFSPLUS_I(HFSPLUS_SB(sb)->hidden_dir)->create_date ||
-                     entry.file.create_date == HFSPLUS_I(sb->s_root->d_inode)->create_date) &&
-                    HFSPLUS_SB(sb)->hidden_dir) {
+                if (entry.file.user_info.fdType ==
+                                cpu_to_be32(HFSP_HARDLINK_TYPE) &&
+                                entry.file.user_info.fdCreator ==
+                                cpu_to_be32(HFSP_HFSPLUS_CREATOR) &&
+                                (entry.file.create_date ==
+                                        HFSPLUS_I(HFSPLUS_SB(sb)->hidden_dir)->
+                                                create_date ||
+                                entry.file.create_date ==
+                                        HFSPLUS_I(sb->s_root->d_inode)->
+                                                create_date) &&
+                                HFSPLUS_SB(sb)->hidden_dir) {
                         struct qstr str;
                         char name[32];
 
@@ -83,11 +89,13 @@ again:
                                 linkid = 0;
                         } else {
                                 dentry->d_fsdata = (void *)(unsigned long)cnid;
-                                linkid = be32_to_cpu(entry.file.permissions.dev);
+                                linkid =
+                                        be32_to_cpu(entry.file.permissions.dev);
                                 str.len = sprintf(name, "iNode%d", linkid);
                                 str.name = name;
                                 hfsplus_cat_build_key(sb, fd.search_key,
-                                        HFSPLUS_SB(sb)->hidden_dir->i_ino, &str);
+                                        HFSPLUS_SB(sb)->hidden_dir->i_ino,
+                                        &str);
                                 goto again;
                         }
                 } else if (!dentry->d_fsdata)
@@ -139,7 +147,8 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir)
                 filp->f_pos++;
                 /* fall through */
         case 1:
-                hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, fd.entrylength);
+                hfs_bnode_read(fd.bnode, &entry, fd.entryoffset,
+                        fd.entrylength);
                 if (be16_to_cpu(entry.type) != HFSPLUS_FOLDER_THREAD) {
                         printk(KERN_ERR "hfs: bad catalog folder thread\n");
                         err = -EIO;
@@ -169,14 +178,16 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir)
                         err = -EIO;
                         goto out;
                 }
-                hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, fd.entrylength);
+                hfs_bnode_read(fd.bnode, &entry, fd.entryoffset,
+                        fd.entrylength);
                 type = be16_to_cpu(entry.type);
                 len = HFSPLUS_MAX_STRLEN;
                 err = hfsplus_uni2asc(sb, &fd.key->cat.name, strbuf, &len);
                 if (err)
                         goto out;
                 if (type == HFSPLUS_FOLDER) {
-                        if (fd.entrylength < sizeof(struct hfsplus_cat_folder)) {
+                        if (fd.entrylength <
+                                        sizeof(struct hfsplus_cat_folder)) {
                                 printk(KERN_ERR "hfs: small dir entry\n");
                                 err = -EIO;
                                 goto out;
@@ -202,7 +213,7 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir)
                         err = -EIO;
                         goto out;
                 }
-        next:
+next:
                 filp->f_pos++;
                 if (filp->f_pos >= inode->i_size)
                         goto out;
@@ -273,7 +284,8 @@ static int hfsplus_link(struct dentry *src_dentry, struct inode *dst_dir,
                 HFSPLUS_I(inode)->linkid = id;
                 cnid = sbi->next_cnid++;
                 src_dentry->d_fsdata = (void *)(unsigned long)cnid;
-                res = hfsplus_create_cat(cnid, src_dir, &src_dentry->d_name, inode);
+                res = hfsplus_create_cat(cnid, src_dir,
+                        &src_dentry->d_name, inode);
                 if (res)
                         /* panic? */
                         goto out;
@@ -485,6 +497,7 @@ const struct inode_operations hfsplus_dir_inode_operations = {
 };
 
 const struct file_operations hfsplus_dir_operations = {
+        .fsync          = hfsplus_file_fsync,
         .read           = generic_read_dir,
         .readdir        = hfsplus_readdir,
         .unlocked_ioctl = hfsplus_ioctl,
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index 0c9cb1820a52..52a0bcaa7b6d 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -83,7 +83,8 @@ static u32 hfsplus_ext_lastblock(struct hfsplus_extent *ext)
         return be32_to_cpu(ext->start_block) + be32_to_cpu(ext->block_count);
 }
 
-static void __hfsplus_ext_write_extent(struct inode *inode, struct hfs_find_data *fd)
+static void __hfsplus_ext_write_extent(struct inode *inode,
+                struct hfs_find_data *fd)
 {
         struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
         int res;
@@ -95,24 +96,32 @@ static void __hfsplus_ext_write_extent(struct inode *inode, struct hfs_find_data
                                 HFSPLUS_TYPE_RSRC : HFSPLUS_TYPE_DATA);
 
         res = hfs_brec_find(fd);
-        if (hip->flags & HFSPLUS_FLG_EXT_NEW) {
+        if (hip->extent_state & HFSPLUS_EXT_NEW) {
                 if (res != -ENOENT)
                         return;
                 hfs_brec_insert(fd, hip->cached_extents,
                                 sizeof(hfsplus_extent_rec));
-                hip->flags &= ~(HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW);
+                hip->extent_state &= ~(HFSPLUS_EXT_DIRTY | HFSPLUS_EXT_NEW);
         } else {
                 if (res)
                         return;
                 hfs_bnode_write(fd->bnode, hip->cached_extents,
                                 fd->entryoffset, fd->entrylength);
-                hip->flags &= ~HFSPLUS_FLG_EXT_DIRTY;
+                hip->extent_state &= ~HFSPLUS_EXT_DIRTY;
         }
+
+        /*
+         * We can't just use hfsplus_mark_inode_dirty here, because we
+         * also get called from hfsplus_write_inode, which should not
+         * redirty the inode.  Instead the callers have to be careful
+         * to explicily mark the inode dirty, too.
+         */
+        set_bit(HFSPLUS_I_EXT_DIRTY, &hip->flags);
 }
 
 static void hfsplus_ext_write_extent_locked(struct inode *inode)
 {
-        if (HFSPLUS_I(inode)->flags & HFSPLUS_FLG_EXT_DIRTY) {
+        if (HFSPLUS_I(inode)->extent_state & HFSPLUS_EXT_DIRTY) {
                 struct hfs_find_data fd;
 
                 hfs_find_init(HFSPLUS_SB(inode->i_sb)->ext_tree, &fd);
@@ -144,18 +153,20 @@ static inline int __hfsplus_ext_read_extent(struct hfs_find_data *fd,
                 return -ENOENT;
         if (fd->entrylength != sizeof(hfsplus_extent_rec))
                 return -EIO;
-        hfs_bnode_read(fd->bnode, extent, fd->entryoffset, sizeof(hfsplus_extent_rec));
+        hfs_bnode_read(fd->bnode, extent, fd->entryoffset,
+                sizeof(hfsplus_extent_rec));
         return 0;
 }
 
-static inline int __hfsplus_ext_cache_extent(struct hfs_find_data *fd, struct inode *inode, u32 block)
+static inline int __hfsplus_ext_cache_extent(struct hfs_find_data *fd,
+                struct inode *inode, u32 block)
 {
         struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
         int res;
 
         WARN_ON(!mutex_is_locked(&hip->extents_lock));
 
-        if (hip->flags & HFSPLUS_FLG_EXT_DIRTY)
+        if (hip->extent_state & HFSPLUS_EXT_DIRTY)
                 __hfsplus_ext_write_extent(inode, fd);
 
         res = __hfsplus_ext_read_extent(fd, hip->cached_extents, inode->i_ino,
@@ -164,10 +175,11 @@ static inline int __hfsplus_ext_cache_extent(struct hfs_find_data *fd, struct in
                                                 HFSPLUS_TYPE_DATA);
         if (!res) {
                 hip->cached_start = be32_to_cpu(fd->key->ext.start_block);
-                hip->cached_blocks = hfsplus_ext_block_count(hip->cached_extents);
+                hip->cached_blocks =
+                        hfsplus_ext_block_count(hip->cached_extents);
         } else {
                 hip->cached_start = hip->cached_blocks = 0;
-                hip->flags &= ~(HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW);
+                hip->extent_state &= ~(HFSPLUS_EXT_DIRTY | HFSPLUS_EXT_NEW);
         }
         return res;
 }
@@ -197,6 +209,7 @@ int hfsplus_get_block(struct inode *inode, sector_t iblock,
         struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
         int res = -EIO;
         u32 ablock, dblock, mask;
+        int was_dirty = 0;
         int shift;
 
         /* Convert inode block to disk allocation block */
@@ -223,27 +236,37 @@ int hfsplus_get_block(struct inode *inode, sector_t iblock,
                 return -EIO;
 
         mutex_lock(&hip->extents_lock);
+
+        /*
+         * hfsplus_ext_read_extent will write out a cached extent into
+         * the extents btree.  In that case we may have to mark the inode
+         * dirty even for a pure read of an extent here.
+         */
+        was_dirty = (hip->extent_state & HFSPLUS_EXT_DIRTY);
         res = hfsplus_ext_read_extent(inode, ablock);
-        if (!res) {
-                dblock = hfsplus_ext_find_block(hip->cached_extents,
-                                                ablock - hip->cached_start);
-        } else {
+        if (res) {
                 mutex_unlock(&hip->extents_lock);
                 return -EIO;
         }
+        dblock = hfsplus_ext_find_block(hip->cached_extents,
+                                        ablock - hip->cached_start);
         mutex_unlock(&hip->extents_lock);
 
 done:
-        dprint(DBG_EXTENT, "get_block(%lu): %llu - %u\n", inode->i_ino, (long long)iblock, dblock);
+        dprint(DBG_EXTENT, "get_block(%lu): %llu - %u\n",
+                inode->i_ino, (long long)iblock, dblock);
         mask = (1 << sbi->fs_shift) - 1;
-        map_bh(bh_result, sb, (dblock << sbi->fs_shift) + sbi->blockoffset + (iblock & mask));
+        map_bh(bh_result, sb,
+                (dblock << sbi->fs_shift) + sbi->blockoffset +
+                        (iblock & mask));
         if (create) {
                 set_buffer_new(bh_result);
                 hip->phys_size += sb->s_blocksize;
                 hip->fs_blocks++;
                 inode_add_bytes(inode, sb->s_blocksize);
-                mark_inode_dirty(inode);
         }
+        if (create || was_dirty)
+                mark_inode_dirty(inode);
         return 0;
 }
 
@@ -326,7 +349,8 @@ found:
         }
 }
 
-int hfsplus_free_fork(struct super_block *sb, u32 cnid, struct hfsplus_fork_raw *fork, int type)
+int hfsplus_free_fork(struct super_block *sb, u32 cnid,
+                struct hfsplus_fork_raw *fork, int type)
 {
         struct hfs_find_data fd;
         hfsplus_extent_rec ext_entry;
@@ -373,12 +397,13 @@ int hfsplus_file_extend(struct inode *inode)
         u32 start, len, goal;
         int res;
 
-        if (sbi->alloc_file->i_size * 8 <
-            sbi->total_blocks - sbi->free_blocks + 8) {
-                // extend alloc file
-                printk(KERN_ERR "hfs: extend alloc file! (%Lu,%u,%u)\n",
-                                sbi->alloc_file->i_size * 8,
-                                sbi->total_blocks, sbi->free_blocks);
+        if (sbi->total_blocks - sbi->free_blocks + 8 >
+                        sbi->alloc_file->i_size * 8) {
+                /* extend alloc file */
+                printk(KERN_ERR "hfs: extend alloc file! "
+                                "(%llu,%u,%u)\n",
+                        sbi->alloc_file->i_size * 8,
+                        sbi->total_blocks, sbi->free_blocks);
                 return -ENOSPC;
         }
 
@@ -429,7 +454,7 @@ int hfsplus_file_extend(struct inode *inode)
                                          start, len);
                 if (!res) {
                         hfsplus_dump_extent(hip->cached_extents);
-                        hip->flags |= HFSPLUS_FLG_EXT_DIRTY;
+                        hip->extent_state |= HFSPLUS_EXT_DIRTY;
                         hip->cached_blocks += len;
                 } else if (res == -ENOSPC)
                         goto insert_extent;
@@ -438,7 +463,7 @@ out:
         mutex_unlock(&hip->extents_lock);
         if (!res) {
                 hip->alloc_blocks += len;
-                mark_inode_dirty(inode);
+                hfsplus_mark_inode_dirty(inode, HFSPLUS_I_ALLOC_DIRTY);
         }
         return res;
 
@@ -450,7 +475,7 @@ insert_extent:
         hip->cached_extents[0].start_block = cpu_to_be32(start);
         hip->cached_extents[0].block_count = cpu_to_be32(len);
         hfsplus_dump_extent(hip->cached_extents);
-        hip->flags |= HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW;
+        hip->extent_state |= HFSPLUS_EXT_DIRTY | HFSPLUS_EXT_NEW;
         hip->cached_start = hip->alloc_blocks;
         hip->cached_blocks = len;
 
@@ -466,8 +491,9 @@ void hfsplus_file_truncate(struct inode *inode)
         u32 alloc_cnt, blk_cnt, start;
         int res;
 
-        dprint(DBG_INODE, "truncate: %lu, %Lu -> %Lu\n",
-                inode->i_ino, (long long)hip->phys_size, inode->i_size);
+        dprint(DBG_INODE, "truncate: %lu, %llu -> %llu\n",
+                inode->i_ino, (long long)hip->phys_size,
+                inode->i_size);
 
         if (inode->i_size > hip->phys_size) {
                 struct address_space *mapping = inode->i_mapping;
@@ -481,7 +507,8 @@ void hfsplus_file_truncate(struct inode *inode)
                                                 &page, &fsdata);
                 if (res)
                         return;
-                res = pagecache_write_end(NULL, mapping, size, 0, 0, page, fsdata);
+                res = pagecache_write_end(NULL, mapping, size,
+                        0, 0, page, fsdata);
                 if (res < 0)
                         return;
                 mark_inode_dirty(inode);
@@ -513,12 +540,12 @@ void hfsplus_file_truncate(struct inode *inode)
                                      alloc_cnt - start, alloc_cnt - blk_cnt);
                 hfsplus_dump_extent(hip->cached_extents);
                 if (blk_cnt > start) {
-                        hip->flags |= HFSPLUS_FLG_EXT_DIRTY;
+                        hip->extent_state |= HFSPLUS_EXT_DIRTY;
                         break;
                 }
                 alloc_cnt = start;
                 hip->cached_start = hip->cached_blocks = 0;
-                hip->flags &= ~(HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW);
+                hip->extent_state &= ~(HFSPLUS_EXT_DIRTY | HFSPLUS_EXT_NEW);
                 hfs_brec_remove(&fd);
         }
         hfs_find_exit(&fd);
@@ -527,7 +554,8 @@ void hfsplus_file_truncate(struct inode *inode)
         hip->alloc_blocks = blk_cnt;
 out:
         hip->phys_size = inode->i_size;
-        hip->fs_blocks = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
+        hip->fs_blocks = (inode->i_size + sb->s_blocksize - 1) >>
+                sb->s_blocksize_bits;
         inode_set_bytes(inode, hip->fs_blocks << sb->s_blocksize_bits);
-        mark_inode_dirty(inode);
+        hfsplus_mark_inode_dirty(inode, HFSPLUS_I_ALLOC_DIRTY);
 }
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index cb3653efb57a..d6857523336d 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -23,13 +23,16 @@
 #define DBG_EXTENT      0x00000020
 #define DBG_BITMAP      0x00000040
 
-//#define DBG_MASK      (DBG_EXTENT|DBG_INODE|DBG_BNODE_MOD)
-//#define DBG_MASK      (DBG_BNODE_MOD|DBG_CAT_MOD|DBG_INODE)
-//#define DBG_MASK      (DBG_CAT_MOD|DBG_BNODE_REFS|DBG_INODE|DBG_EXTENT)
+#if 0
+#define DBG_MASK        (DBG_EXTENT|DBG_INODE|DBG_BNODE_MOD)
+#define DBG_MASK        (DBG_BNODE_MOD|DBG_CAT_MOD|DBG_INODE)
+#define DBG_MASK        (DBG_CAT_MOD|DBG_BNODE_REFS|DBG_INODE|DBG_EXTENT)
+#endif
 #define DBG_MASK        (0)
 
 #define dprint(flg, fmt, args...) \
-        if (flg & DBG_MASK) printk(fmt , ## args)
+        if (flg & DBG_MASK) \
+                printk(fmt , ## args)
 
 /* Runtime config options */
 #define HFSPLUS_DEF_CR_TYPE    0x3F3F3F3F  /* '????' */
@@ -37,7 +40,8 @@
 #define HFSPLUS_TYPE_DATA 0x00
 #define HFSPLUS_TYPE_RSRC 0xFF
 
-typedef int (*btree_keycmp)(const hfsplus_btree_key *, const hfsplus_btree_key *);
+typedef int (*btree_keycmp)(const hfsplus_btree_key *,
+                const hfsplus_btree_key *);
 
 #define NODE_HASH_SIZE  256
 
@@ -61,7 +65,6 @@ struct hfs_btree {
         unsigned int max_key_len;
         unsigned int depth;
 
-        //unsigned int map1_size, map_size;
         struct mutex tree_lock;
 
         unsigned int pages_per_bnode;
@@ -107,8 +110,8 @@ struct hfsplus_vh;
 struct hfs_btree;
 
 struct hfsplus_sb_info {
-        struct buffer_head *s_vhbh;
         struct hfsplus_vh *s_vhdr;
+        struct hfsplus_vh *s_backup_vhdr;
         struct hfs_btree *ext_tree;
         struct hfs_btree *cat_tree;
         struct hfs_btree *attr_tree;
@@ -118,7 +121,8 @@ struct hfsplus_sb_info {
 
         /* Runtime variables */
         u32 blockoffset;
-        u32 sect_count;
+        sector_t part_start;
+        sector_t sect_count;
         int fs_shift;
 
         /* immutable data from the volume header */
@@ -155,6 +159,12 @@ struct hfsplus_sb_info {
 #define HFSPLUS_SB_FORCE        2
 #define HFSPLUS_SB_HFSX         3
 #define HFSPLUS_SB_CASEFOLD     4
+#define HFSPLUS_SB_NOBARRIER    5
+
+static inline struct hfsplus_sb_info *HFSPLUS_SB(struct super_block *sb)
+{
+        return sb->s_fs_info;
+}
 
 
 struct hfsplus_inode_info {
@@ -170,7 +180,7 @@ struct hfsplus_inode_info {
         u32 cached_blocks;
         hfsplus_extent_rec first_extents;
         hfsplus_extent_rec cached_extents;
-        unsigned long flags;
+        unsigned int extent_state;
         struct mutex extents_lock;
 
         /*
@@ -185,6 +195,11 @@ struct hfsplus_inode_info {
         u32 linkid;
 
         /*
+         * Accessed using atomic bitops.
+         */
+        unsigned long flags;
+
+        /*
          * Protected by i_mutex.
          */
         sector_t fs_blocks;
@@ -195,12 +210,34 @@ struct hfsplus_inode_info {
         struct inode vfs_inode;
 };
 
-#define HFSPLUS_FLG_RSRC        0x0001
-#define HFSPLUS_FLG_EXT_DIRTY   0x0002
-#define HFSPLUS_FLG_EXT_NEW     0x0004
+#define HFSPLUS_EXT_DIRTY       0x0001
+#define HFSPLUS_EXT_NEW         0x0002
+
+#define HFSPLUS_I_RSRC          0       /* represents a resource fork */
+#define HFSPLUS_I_CAT_DIRTY     1       /* has changes in the catalog tree */
+#define HFSPLUS_I_EXT_DIRTY     2       /* has changes in the extent tree */
+#define HFSPLUS_I_ALLOC_DIRTY   3       /* has changes in the allocation file */
+
+#define HFSPLUS_IS_RSRC(inode) \
+        test_bit(HFSPLUS_I_RSRC, &HFSPLUS_I(inode)->flags)
+
+static inline struct hfsplus_inode_info *HFSPLUS_I(struct inode *inode)
+{
+        return list_entry(inode, struct hfsplus_inode_info, vfs_inode);
+}
 
-#define HFSPLUS_IS_DATA(inode)   (!(HFSPLUS_I(inode)->flags & HFSPLUS_FLG_RSRC))
-#define HFSPLUS_IS_RSRC(inode)   (HFSPLUS_I(inode)->flags & HFSPLUS_FLG_RSRC)
+/*
+ * Mark an inode dirty, and also mark the btree in which the
+ * specific type of metadata is stored.
+ * For data or metadata that gets written back by into the catalog btree
+ * by hfsplus_write_inode a plain mark_inode_dirty call is enough.
+ */
+static inline void hfsplus_mark_inode_dirty(struct inode *inode,
+                unsigned int flag)
+{
+        set_bit(flag, &HFSPLUS_I(inode)->flags);
+        mark_inode_dirty(inode);
+}
 
 struct hfs_find_data {
         /* filled by caller */
@@ -318,9 +355,12 @@ int hfs_brec_read(struct hfs_find_data *, void *, int);
 int hfs_brec_goto(struct hfs_find_data *, int);
 
 /* catalog.c */
-int hfsplus_cat_case_cmp_key(const hfsplus_btree_key *, const hfsplus_btree_key *);
-int hfsplus_cat_bin_cmp_key(const hfsplus_btree_key *, const hfsplus_btree_key *);
-void hfsplus_cat_build_key(struct super_block *sb, hfsplus_btree_key *, u32, struct qstr *);
+int hfsplus_cat_case_cmp_key(const hfsplus_btree_key *,
+                const hfsplus_btree_key *);
+int hfsplus_cat_bin_cmp_key(const hfsplus_btree_key *,
+                const hfsplus_btree_key *);
+void hfsplus_cat_build_key(struct super_block *sb,
+                hfsplus_btree_key *, u32, struct qstr *);
 int hfsplus_find_cat(struct super_block *, u32, struct hfs_find_data *);
 int hfsplus_create_cat(u32, struct inode *, struct qstr *, struct inode *);
 int hfsplus_delete_cat(u32, struct inode *, struct qstr *);
@@ -336,7 +376,8 @@ extern const struct file_operations hfsplus_dir_operations;
 int hfsplus_ext_cmp_key(const hfsplus_btree_key *, const hfsplus_btree_key *);
 void hfsplus_ext_write_extent(struct inode *);
 int hfsplus_get_block(struct inode *, sector_t, struct buffer_head *, int);
-int hfsplus_free_fork(struct super_block *, u32, struct hfsplus_fork_raw *, int);
+int hfsplus_free_fork(struct super_block *, u32,
+                struct hfsplus_fork_raw *, int);
 int hfsplus_file_extend(struct inode *);
 void hfsplus_file_truncate(struct inode *);
 
@@ -351,6 +392,7 @@ int hfsplus_cat_read_inode(struct inode *, struct hfs_find_data *);
 int hfsplus_cat_write_inode(struct inode *);
 struct inode *hfsplus_new_inode(struct super_block *, int);
 void hfsplus_delete_inode(struct inode *);
+int hfsplus_file_fsync(struct file *file, int datasync);
 
 /* ioctl.c */
 long hfsplus_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
@@ -362,6 +404,7 @@ ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size);
 
 /* options.c */
 int hfsplus_parse_options(char *, struct hfsplus_sb_info *);
+int hfsplus_parse_options_remount(char *input, int *force);
 void hfsplus_fill_defaults(struct hfsplus_sb_info *);
 int hfsplus_show_options(struct seq_file *, struct vfsmount *);
 
@@ -375,45 +418,26 @@ extern u16 hfsplus_decompose_table[];
 extern u16 hfsplus_compose_table[];
 
 /* unicode.c */
-int hfsplus_strcasecmp(const struct hfsplus_unistr *, const struct hfsplus_unistr *);
-int hfsplus_strcmp(const struct hfsplus_unistr *, const struct hfsplus_unistr *);
-int hfsplus_uni2asc(struct super_block *, const struct hfsplus_unistr *, char *, int *);
-int hfsplus_asc2uni(struct super_block *, struct hfsplus_unistr *, const char *, int);
-int hfsplus_hash_dentry(struct dentry *dentry, struct qstr *str);
-int hfsplus_compare_dentry(struct dentry *dentry, struct qstr *s1, struct qstr *s2);
+int hfsplus_strcasecmp(const struct hfsplus_unistr *,
+                const struct hfsplus_unistr *);
+int hfsplus_strcmp(const struct hfsplus_unistr *,
+                const struct hfsplus_unistr *);
+int hfsplus_uni2asc(struct super_block *,
+                const struct hfsplus_unistr *, char *, int *);
+int hfsplus_asc2uni(struct super_block *,
+                struct hfsplus_unistr *, const char *, int);
+int hfsplus_hash_dentry(const struct dentry *dentry,
+                const struct inode *inode, struct qstr *str);
+int hfsplus_compare_dentry(const struct dentry *parent,
+                const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name);
 
 /* wrapper.c */
 int hfsplus_read_wrapper(struct super_block *);
-
 int hfs_part_find(struct super_block *, sector_t *, sector_t *);
-
-/* access macros */
-static inline struct hfsplus_sb_info *HFSPLUS_SB(struct super_block *sb)
-{
-        return sb->s_fs_info;
-}
-
-static inline struct hfsplus_inode_info *HFSPLUS_I(struct inode *inode)
-{
-        return list_entry(inode, struct hfsplus_inode_info, vfs_inode);
-}
-
-#define sb_bread512(sb, sec, data) ({                   \
-        struct buffer_head *__bh;                       \
-        sector_t __block;                               \
-        loff_t __start;                                 \
-        int __offset;                                   \
-                                                        \
-        __start = (loff_t)(sec) << HFSPLUS_SECTOR_SHIFT;\
-        __block = __start >> (sb)->s_blocksize_bits;    \
-        __offset = __start & ((sb)->s_blocksize - 1);   \
-        __bh = sb_bread((sb), __block);                 \
-        if (likely(__bh != NULL))                       \
-                data = (void *)(__bh->b_data + __offset);\
-        else                                            \
-                data = NULL;                            \
-        __bh;                                           \
-})
+int hfsplus_submit_bio(struct block_device *bdev, sector_t sector,
+                void *data, int rw);
 
 /* time macros */
 #define __hfsp_mt2ut(t)         (be32_to_cpu(t) - 2082844800U)
diff --git a/fs/hfsplus/hfsplus_raw.h b/fs/hfsplus/hfsplus_raw.h
index 6892899fd6fb..927cdd6d5bf5 100644
--- a/fs/hfsplus/hfsplus_raw.h
+++ b/fs/hfsplus/hfsplus_raw.h
@@ -36,7 +36,8 @@
 #define HFSP_WRAPOFF_EMBEDSIG     0x7C
 #define HFSP_WRAPOFF_EMBEDEXT     0x7E
 
-#define HFSP_HIDDENDIR_NAME     "\xe2\x90\x80\xe2\x90\x80\xe2\x90\x80\xe2\x90\x80HFS+ Private Data"
+#define HFSP_HIDDENDIR_NAME \
+        "\xe2\x90\x80\xe2\x90\x80\xe2\x90\x80\xe2\x90\x80HFS+ Private Data"
 
 #define HFSP_HARDLINK_TYPE      0x686c6e6b      /* 'hlnk' */
 #define HFSP_HFSPLUS_CREATOR    0x6866732b      /* 'hfs+' */
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 8afd7e84f98d..a8df651747f0 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -8,6 +8,7 @@
  * Inode handling routines
  */
 
+#include <linux/blkdev.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
@@ -77,7 +78,8 @@ static int hfsplus_releasepage(struct page *page, gfp_t mask)
         if (!tree)
                 return 0;
         if (tree->node_size >= PAGE_CACHE_SIZE) {
-                nidx = page->index >> (tree->node_size_shift - PAGE_CACHE_SHIFT);
+                nidx = page->index >>
+                        (tree->node_size_shift - PAGE_CACHE_SHIFT);
                 spin_lock(&tree->hash_lock);
                 node = hfs_bnode_findhash(tree, nidx);
                 if (!node)
@@ -90,7 +92,8 @@ static int hfsplus_releasepage(struct page *page, gfp_t mask)
                 }
                 spin_unlock(&tree->hash_lock);
         } else {
-                nidx = page->index << (PAGE_CACHE_SHIFT - tree->node_size_shift);
+                nidx = page->index <<
+                        (PAGE_CACHE_SHIFT - tree->node_size_shift);
                 i = 1 << (PAGE_CACHE_SHIFT - tree->node_size_shift);
                 spin_lock(&tree->hash_lock);
                 do {
@@ -166,8 +169,8 @@ const struct dentry_operations hfsplus_dentry_operations = {
         .d_compare    = hfsplus_compare_dentry,
 };
 
-static struct dentry *hfsplus_file_lookup(struct inode *dir, struct dentry *dentry,
-                                          struct nameidata *nd)
+static struct dentry *hfsplus_file_lookup(struct inode *dir,
+                struct dentry *dentry, struct nameidata *nd)
 {
         struct hfs_find_data fd;
         struct super_block *sb = dir->i_sb;
@@ -190,7 +193,9 @@ static struct dentry *hfsplus_file_lookup(struct inode *dir, struct dentry *dent
         inode->i_ino = dir->i_ino;
         INIT_LIST_HEAD(&hip->open_dir_list);
         mutex_init(&hip->extents_lock);
-        hip->flags = HFSPLUS_FLG_RSRC;
+        hip->extent_state = 0;
+        hip->flags = 0;
+        set_bit(HFSPLUS_I_RSRC, &hip->flags);
 
         hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
         err = hfsplus_find_cat(sb, dir->i_ino, &fd);
@@ -219,7 +224,8 @@ out:
         return NULL;
 }
 
-static void hfsplus_get_perms(struct inode *inode, struct hfsplus_perm *perms, int dir)
+static void hfsplus_get_perms(struct inode *inode,
+                struct hfsplus_perm *perms, int dir)
 {
         struct hfsplus_sb_info *sbi = HFSPLUS_SB(inode->i_sb);
         u16 mode;
@@ -302,29 +308,41 @@ static int hfsplus_setattr(struct dentry *dentry, struct iattr *attr)
         return 0;
 }
 
-static int hfsplus_file_fsync(struct file *filp, int datasync)
+int hfsplus_file_fsync(struct file *file, int datasync)
 {
-        struct inode *inode = filp->f_mapping->host;
-        struct super_block * sb;
-        int ret, err;
-
-        /* sync the inode to buffers */
-        ret = write_inode_now(inode, 0);
-
-        /* sync the superblock to buffers */
-        sb = inode->i_sb;
-        if (sb->s_dirt) {
-                if (!(sb->s_flags & MS_RDONLY))
-                        hfsplus_sync_fs(sb, 1);
-                else
-                        sb->s_dirt = 0;
+        struct inode *inode = file->f_mapping->host;
+        struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(inode->i_sb);
+        int error = 0, error2;
+
+        /*
+         * Sync inode metadata into the catalog and extent trees.
+         */
+        sync_inode_metadata(inode, 1);
+
+        /*
+         * And explicitly write out the btrees.
+         */
+        if (test_and_clear_bit(HFSPLUS_I_CAT_DIRTY, &hip->flags))
+                error = filemap_write_and_wait(sbi->cat_tree->inode->i_mapping);
+
+        if (test_and_clear_bit(HFSPLUS_I_EXT_DIRTY, &hip->flags)) {
+                error2 =
+                        filemap_write_and_wait(sbi->ext_tree->inode->i_mapping);
+                if (!error)
+                        error = error2;
         }
 
-        /* .. finally sync the buffers to disk */
-        err = sync_blockdev(sb->s_bdev);
-        if (!ret)
-                ret = err;
-        return ret;
+        if (test_and_clear_bit(HFSPLUS_I_ALLOC_DIRTY, &hip->flags)) {
+                error2 = filemap_write_and_wait(sbi->alloc_file->i_mapping);
+                if (!error)
+                        error = error2;
+        }
+
+        if (!test_bit(HFSPLUS_SB_NOBARRIER, &sbi->flags))
+                blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
+
+        return error;
 }
 
 static const struct inode_operations hfsplus_file_inode_operations = {
@@ -337,7 +355,7 @@ static const struct inode_operations hfsplus_file_inode_operations = {
 };
 
 static const struct file_operations hfsplus_file_operations = {
-        .llseek         = generic_file_llseek,
+        .llseek         = generic_file_llseek,
         .read           = do_sync_read,
         .aio_read       = generic_file_aio_read,
         .write          = do_sync_write,
@@ -370,6 +388,7 @@ struct inode *hfsplus_new_inode(struct super_block *sb, int mode)
         INIT_LIST_HEAD(&hip->open_dir_list);
         mutex_init(&hip->extents_lock);
         atomic_set(&hip->opencnt, 0);
+        hip->extent_state = 0;
         hip->flags = 0;
         memset(hip->first_extents, 0, sizeof(hfsplus_extent_rec));
         memset(hip->cached_extents, 0, sizeof(hfsplus_extent_rec));
@@ -457,7 +476,8 @@ void hfsplus_inode_read_fork(struct inode *inode, struct hfsplus_fork_raw *fork)
         }
 }
 
-void hfsplus_inode_write_fork(struct inode *inode, struct hfsplus_fork_raw *fork)
+void hfsplus_inode_write_fork(struct inode *inode,
+                struct hfsplus_fork_raw *fork)
 {
         memcpy(&fork->extents, &HFSPLUS_I(inode)->first_extents,
                sizeof(hfsplus_extent_rec));
@@ -499,13 +519,14 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd)
                 hfs_bnode_read(fd->bnode, &entry, fd->entryoffset,
                                         sizeof(struct hfsplus_cat_file));
 
-                hfsplus_inode_read_fork(inode, HFSPLUS_IS_DATA(inode) ?
-                                        &file->data_fork : &file->rsrc_fork);
+                hfsplus_inode_read_fork(inode, HFSPLUS_IS_RSRC(inode) ?
+                                        &file->rsrc_fork : &file->data_fork);
                 hfsplus_get_perms(inode, &file->permissions, 0);
                 inode->i_nlink = 1;
                 if (S_ISREG(inode->i_mode)) {
                         if (file->permissions.dev)
-                                inode->i_nlink = be32_to_cpu(file->permissions.dev);
+                                inode->i_nlink =
+                                        be32_to_cpu(file->permissions.dev);
                         inode->i_op = &hfsplus_file_inode_operations;
                         inode->i_fop = &hfsplus_file_operations;
                         inode->i_mapping->a_ops = &hfsplus_aops;
@@ -578,7 +599,9 @@ int hfsplus_cat_write_inode(struct inode *inode)
                                         sizeof(struct hfsplus_cat_file));
                 hfsplus_inode_write_fork(inode, &file->data_fork);
                 hfsplus_cat_set_perms(inode, &file->permissions);
-                if ((file->permissions.rootflags | file->permissions.userflags) & HFSPLUS_FLG_IMMUTABLE)
+                if (HFSPLUS_FLG_IMMUTABLE &
+                                (file->permissions.rootflags |
+                                        file->permissions.userflags))
                         file->flags |= cpu_to_be16(HFSPLUS_FILE_LOCKED);
                 else
                         file->flags &= cpu_to_be16(~HFSPLUS_FILE_LOCKED);
@@ -588,6 +611,8 @@ int hfsplus_cat_write_inode(struct inode *inode)
                 hfs_bnode_write(fd.bnode, &entry, fd.entryoffset,
                                          sizeof(struct hfsplus_cat_file));
         }
+
+        set_bit(HFSPLUS_I_CAT_DIRTY, &HFSPLUS_I(inode)->flags);
 out:
         hfs_find_exit(&fd);
         return 0;
diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c
index 40a85a3ded6e..508ce662ce12 100644
--- a/fs/hfsplus/ioctl.c
+++ b/fs/hfsplus/ioctl.c
@@ -28,7 +28,7 @@ static int hfsplus_ioctl_getflags(struct file *file, int __user *user_flags)
 
         if (inode->i_flags & S_IMMUTABLE)
                 flags |= FS_IMMUTABLE_FL;
-        if (inode->i_flags |= S_APPEND)
+        if (inode->i_flags & S_APPEND)
                 flags |= FS_APPEND_FL;
         if (hip->userflags & HFSPLUS_FLG_NODUMP)
                 flags |= FS_NODUMP_FL;
@@ -147,9 +147,11 @@ int hfsplus_setxattr(struct dentry *dentry, const char *name,
                         res = -ERANGE;
         } else
                 res = -EOPNOTSUPP;
-        if (!res)
+        if (!res) {
                 hfs_bnode_write(fd.bnode, &entry, fd.entryoffset,
                                 sizeof(struct hfsplus_cat_file));
+                hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY);
+        }
 out:
         hfs_find_exit(&fd);
         return res;
diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c
index f9ab276a4d8d..bb62a5882147 100644
--- a/fs/hfsplus/options.c
+++ b/fs/hfsplus/options.c
@@ -23,6 +23,7 @@ enum {
         opt_umask, opt_uid, opt_gid,
         opt_part, opt_session, opt_nls,
         opt_nodecompose, opt_decompose,
+        opt_barrier, opt_nobarrier,
         opt_force, opt_err
 };
 
@@ -37,6 +38,8 @@ static const match_table_t tokens = {
         { opt_nls, "nls=%s" },
         { opt_decompose, "decompose" },
         { opt_nodecompose, "nodecompose" },
+        { opt_barrier, "barrier" },
+        { opt_nobarrier, "nobarrier" },
         { opt_force, "force" },
         { opt_err, NULL }
 };
@@ -65,6 +68,32 @@ static inline int match_fourchar(substring_t *arg, u32 *result)
         return 0;
 }
 
+int hfsplus_parse_options_remount(char *input, int *force)
+{
+        char *p;
+        substring_t args[MAX_OPT_ARGS];
+        int token;
+
+        if (!input)
+                return 0;
+
+        while ((p = strsep(&input, ",")) != NULL) {
+                if (!*p)
+                        continue;
+
+                token = match_token(p, tokens, args);
+                switch (token) {
+                case opt_force:
+                        *force = 1;
+                        break;
+                default:
+                        break;
+                }
+        }
+
+        return 1;
+}
+
 /* Parse options from mount. Returns 0 on failure */
 /* input is the options passed to mount() as a string */
 int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi)
@@ -136,7 +165,9 @@ int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi)
                         if (p)
                                 sbi->nls = load_nls(p);
                         if (!sbi->nls) {
-                                printk(KERN_ERR "hfs: unable to load nls mapping \"%s\"\n", p);
+                                printk(KERN_ERR "hfs: unable to load "
+                                                "nls mapping \"%s\"\n",
+                                        p);
                                 kfree(p);
                                 return 0;
                         }
@@ -148,6 +179,12 @@ int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi)
                 case opt_nodecompose:
                         set_bit(HFSPLUS_SB_NODECOMPOSE, &sbi->flags);
                         break;
+                case opt_barrier:
+                        clear_bit(HFSPLUS_SB_NOBARRIER, &sbi->flags);
+                        break;
+                case opt_nobarrier:
+                        set_bit(HFSPLUS_SB_NOBARRIER, &sbi->flags);
+                        break;
                 case opt_force:
                         set_bit(HFSPLUS_SB_FORCE, &sbi->flags);
                         break;
@@ -177,7 +214,8 @@ int hfsplus_show_options(struct seq_file *seq, struct vfsmount *mnt)
                 seq_printf(seq, ",creator=%.4s", (char *)&sbi->creator);
         if (sbi->type != HFSPLUS_DEF_CR_TYPE)
                 seq_printf(seq, ",type=%.4s", (char *)&sbi->type);
-        seq_printf(seq, ",umask=%o,uid=%u,gid=%u", sbi->umask, sbi->uid, sbi->gid);
+        seq_printf(seq, ",umask=%o,uid=%u,gid=%u", sbi->umask,
+                sbi->uid, sbi->gid);
         if (sbi->part >= 0)
                 seq_printf(seq, ",part=%u", sbi->part);
         if (sbi->session >= 0)
@@ -186,5 +224,7 @@ int hfsplus_show_options(struct seq_file *seq, struct vfsmount *mnt)
                 seq_printf(seq, ",nls=%s", sbi->nls->charset);
         if (test_bit(HFSPLUS_SB_NODECOMPOSE, &sbi->flags))
                 seq_printf(seq, ",nodecompose");
+        if (test_bit(HFSPLUS_SB_NOBARRIER, &sbi->flags))
+                seq_printf(seq, ",nobarrier");
         return 0;
 }
diff --git a/fs/hfsplus/part_tbl.c b/fs/hfsplus/part_tbl.c
index 208b16c645cc..d66ad113b1cc 100644
--- a/fs/hfsplus/part_tbl.c
+++ b/fs/hfsplus/part_tbl.c
@@ -2,7 +2,8 @@
  * linux/fs/hfsplus/part_tbl.c
  *
  * Copyright (C) 1996-1997  Paul H. Hargrove
- * This file may be distributed under the terms of the GNU General Public License.
+ * This file may be distributed under the terms of
+ * the GNU General Public License.
  *
  * Original code to handle the new style Mac partition table based on
  * a patch contributed by Holger Schemel (aeglos@valinor.owl.de).
@@ -13,6 +14,7 @@
  *
  */
 
+#include <linux/slab.h>
 #include "hfsplus_fs.h"
 
 /* offsets to various blocks */
@@ -58,77 +60,94 @@ struct new_pmap {
  */
 struct old_pmap {
         __be16          pdSig;  /* Signature bytes */
-        struct  old_pmap_entry {
+        struct old_pmap_entry {
                 __be32  pdStart;
                 __be32  pdSize;
                 __be32  pdFSID;
         }       pdEntry[42];
 } __packed;
 
+static int hfs_parse_old_pmap(struct super_block *sb, struct old_pmap *pm,
+                sector_t *part_start, sector_t *part_size)
+{
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
+        int i;
+
+        for (i = 0; i < 42; i++) {
+                struct old_pmap_entry *p = &pm->pdEntry[i];
+
+                if (p->pdStart && p->pdSize &&
+                    p->pdFSID == cpu_to_be32(0x54465331)/*"TFS1"*/ &&
+                    (sbi->part < 0 || sbi->part == i)) {
+                        *part_start += be32_to_cpu(p->pdStart);
+                        *part_size = be32_to_cpu(p->pdSize);
+                        return 0;
+                }
+        }
+
+        return -ENOENT;
+}
+
+static int hfs_parse_new_pmap(struct super_block *sb, struct new_pmap *pm,
+                sector_t *part_start, sector_t *part_size)
+{
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
+        int size = be32_to_cpu(pm->pmMapBlkCnt);
+        int res;
+        int i = 0;
+
+        do {
+                if (!memcmp(pm->pmPartType, "Apple_HFS", 9) &&
+                    (sbi->part < 0 || sbi->part == i)) {
+                        *part_start += be32_to_cpu(pm->pmPyPartStart);
+                        *part_size = be32_to_cpu(pm->pmPartBlkCnt);
+                        return 0;
+                }
+
+                if (++i >= size)
+                        return -ENOENT;
+
+                res = hfsplus_submit_bio(sb->s_bdev,
+                                         *part_start + HFS_PMAP_BLK + i,
+                                         pm, READ);
+                if (res)
+                        return res;
+        } while (pm->pmSig == cpu_to_be16(HFS_NEW_PMAP_MAGIC));
+
+        return -ENOENT;
+}
+
 /*
- * hfs_part_find()
- *
- * Parse the partition map looking for the
- * start and length of the 'part'th HFS partition.
+ * Parse the partition map looking for the start and length of a
+ * HFS/HFS+ partition.
  */
 int hfs_part_find(struct super_block *sb,
-                  sector_t *part_start, sector_t *part_size)
+                sector_t *part_start, sector_t *part_size)
 {
-        struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
-        struct buffer_head *bh;
-        __be16 *data;
-        int i, size, res;
+        void *data;
+        int res;
+
+        data = kmalloc(HFSPLUS_SECTOR_SIZE, GFP_KERNEL);
+        if (!data)
+                return -ENOMEM;
 
-        res = -ENOENT;
-        bh = sb_bread512(sb, *part_start + HFS_PMAP_BLK, data);
-        if (!bh)
-                return -EIO;
+        res = hfsplus_submit_bio(sb->s_bdev, *part_start + HFS_PMAP_BLK,
+                                 data, READ);
+        if (res)
+                return res;
 
-        switch (be16_to_cpu(*data)) {
+        switch (be16_to_cpu(*((__be16 *)data))) {
         case HFS_OLD_PMAP_MAGIC:
-          {
-                struct old_pmap *pm;
-                struct old_pmap_entry *p;
-
-                pm = (struct old_pmap *)bh->b_data;
-                p = pm->pdEntry;
-                size = 42;
-                for (i = 0; i < size; p++, i++) {
-                        if (p->pdStart && p->pdSize &&
-                            p->pdFSID == cpu_to_be32(0x54465331)/*"TFS1"*/ &&
-                            (sbi->part < 0 || sbi->part == i)) {
-                                *part_start += be32_to_cpu(p->pdStart);
-                                *part_size = be32_to_cpu(p->pdSize);
-                                res = 0;
-                        }
-                }
+                res = hfs_parse_old_pmap(sb, data, part_start, part_size);
                 break;
-          }
         case HFS_NEW_PMAP_MAGIC:
-          {
-                struct new_pmap *pm;
-
-                pm = (struct new_pmap *)bh->b_data;
-                size = be32_to_cpu(pm->pmMapBlkCnt);
-                for (i = 0; i < size;) {
-                        if (!memcmp(pm->pmPartType,"Apple_HFS", 9) &&
-                            (sbi->part < 0 || sbi->part == i)) {
-                                *part_start += be32_to_cpu(pm->pmPyPartStart);
-                                *part_size = be32_to_cpu(pm->pmPartBlkCnt);
-                                res = 0;
-                                break;
-                        }
-                        brelse(bh);
-                        bh = sb_bread512(sb, *part_start + HFS_PMAP_BLK + ++i, pm);
-                        if (!bh)
-                                return -EIO;
-                        if (pm->pmSig != cpu_to_be16(HFS_NEW_PMAP_MAGIC))
-                                break;
-                }
+                res = hfs_parse_new_pmap(sb, data, part_start, part_size);
+                break;
+        default:
+                res = -ENOENT;
                 break;
-          }
         }
-        brelse(bh);
 
+        kfree(data);
         return res;
 }
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 52cc746d3ba3..6ee6ad20acf2 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/pagemap.h>
+#include <linux/blkdev.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/vfs.h>
@@ -66,6 +67,7 @@ struct inode *hfsplus_iget(struct super_block *sb, unsigned long ino)
         INIT_LIST_HEAD(&HFSPLUS_I(inode)->open_dir_list);
         mutex_init(&HFSPLUS_I(inode)->extents_lock);
         HFSPLUS_I(inode)->flags = 0;
+        HFSPLUS_I(inode)->extent_state = 0;
         HFSPLUS_I(inode)->rsrc_inode = NULL;
         atomic_set(&HFSPLUS_I(inode)->opencnt, 0);
 
@@ -157,45 +159,65 @@ int hfsplus_sync_fs(struct super_block *sb, int wait)
 {
         struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
         struct hfsplus_vh *vhdr = sbi->s_vhdr;
+        int write_backup = 0;
+        int error, error2;
+
+        if (!wait)
+                return 0;
 
         dprint(DBG_SUPER, "hfsplus_write_super\n");
 
-        mutex_lock(&sbi->vh_mutex);
-        mutex_lock(&sbi->alloc_mutex);
         sb->s_dirt = 0;
 
+        /*
+         * Explicitly write out the special metadata inodes.
+         *
+         * While these special inodes are marked as hashed and written
+         * out peridocically by the flusher threads we redirty them
+         * during writeout of normal inodes, and thus the life lock
+         * prevents us from getting the latest state to disk.
+         */
+        error = filemap_write_and_wait(sbi->cat_tree->inode->i_mapping);
+        error2 = filemap_write_and_wait(sbi->ext_tree->inode->i_mapping);
+        if (!error)
+                error = error2;
+        error2 = filemap_write_and_wait(sbi->alloc_file->i_mapping);
+        if (!error)
+                error = error2;
+
+        mutex_lock(&sbi->vh_mutex);
+        mutex_lock(&sbi->alloc_mutex);
         vhdr->free_blocks = cpu_to_be32(sbi->free_blocks);
         vhdr->next_cnid = cpu_to_be32(sbi->next_cnid);
         vhdr->folder_count = cpu_to_be32(sbi->folder_count);
         vhdr->file_count = cpu_to_be32(sbi->file_count);
 
-        mark_buffer_dirty(sbi->s_vhbh);
         if (test_and_clear_bit(HFSPLUS_SB_WRITEBACKUP, &sbi->flags)) {
-                if (sbi->sect_count) {
-                        struct buffer_head *bh;
-                        u32 block, offset;
-
-                        block = sbi->blockoffset;
-                        block += (sbi->sect_count - 2) >> (sb->s_blocksize_bits - 9);
-                        offset = ((sbi->sect_count - 2) << 9) & (sb->s_blocksize - 1);
-                        printk(KERN_DEBUG "hfs: backup: %u,%u,%u,%u\n",
-                                          sbi->blockoffset, sbi->sect_count,
-                                          block, offset);
-                        bh = sb_bread(sb, block);
-                        if (bh) {
-                                vhdr = (struct hfsplus_vh *)(bh->b_data + offset);
-                                if (be16_to_cpu(vhdr->signature) == HFSPLUS_VOLHEAD_SIG) {
-                                        memcpy(vhdr, sbi->s_vhdr, sizeof(*vhdr));
-                                        mark_buffer_dirty(bh);
-                                        brelse(bh);
-                                } else
-                                        printk(KERN_WARNING "hfs: backup not found!\n");
-                        }
-                }
+                memcpy(sbi->s_backup_vhdr, sbi->s_vhdr, sizeof(*sbi->s_vhdr));
+                write_backup = 1;
         }
+
+        error2 = hfsplus_submit_bio(sb->s_bdev,
+                                   sbi->part_start + HFSPLUS_VOLHEAD_SECTOR,
+                                   sbi->s_vhdr, WRITE_SYNC);
+        if (!error)
+                error = error2;
+        if (!write_backup)
+                goto out;
+
+        error2 = hfsplus_submit_bio(sb->s_bdev,
+                                  sbi->part_start + sbi->sect_count - 2,
+                                  sbi->s_backup_vhdr, WRITE_SYNC);
+        if (!error)
+                error2 = error;
+out:
         mutex_unlock(&sbi->alloc_mutex);
         mutex_unlock(&sbi->vh_mutex);
-        return 0;
+
+        if (!test_bit(HFSPLUS_SB_NOBARRIER, &sbi->flags))
+                blkdev_issue_flush(sb->s_bdev, GFP_KERNEL, NULL);
+
+        return error;
 }
 
 static void hfsplus_write_super(struct super_block *sb)
@@ -215,23 +237,22 @@ static void hfsplus_put_super(struct super_block *sb)
         if (!sb->s_fs_info)
                 return;
 
-        if (sb->s_dirt)
-                hfsplus_write_super(sb);
         if (!(sb->s_flags & MS_RDONLY) && sbi->s_vhdr) {
                 struct hfsplus_vh *vhdr = sbi->s_vhdr;
 
                 vhdr->modify_date = hfsp_now2mt();
                 vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_UNMNT);
                 vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_INCNSTNT);
-                mark_buffer_dirty(sbi->s_vhbh);
-                sync_dirty_buffer(sbi->s_vhbh);
+
+                hfsplus_sync_fs(sb, 1);
         }
 
         hfs_btree_close(sbi->cat_tree);
         hfs_btree_close(sbi->ext_tree);
         iput(sbi->alloc_file);
         iput(sbi->hidden_dir);
-        brelse(sbi->s_vhbh);
+        kfree(sbi->s_vhdr);
+        kfree(sbi->s_backup_vhdr);
         unload_nls(sbi->nls);
         kfree(sb->s_fs_info);
         sb->s_fs_info = NULL;
@@ -263,26 +284,31 @@ static int hfsplus_remount(struct super_block *sb, int *flags, char *data)
                 return 0;
         if (!(*flags & MS_RDONLY)) {
                 struct hfsplus_vh *vhdr = HFSPLUS_SB(sb)->s_vhdr;
-                struct hfsplus_sb_info sbi;
+                int force = 0;
 
-                memset(&sbi, 0, sizeof(struct hfsplus_sb_info));
-                sbi.nls = HFSPLUS_SB(sb)->nls;
-                if (!hfsplus_parse_options(data, &sbi))
+                if (!hfsplus_parse_options_remount(data, &force))
                         return -EINVAL;
 
                 if (!(vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_UNMNT))) {
-                        printk(KERN_WARNING "hfs: filesystem was not cleanly unmounted, "
-                               "running fsck.hfsplus is recommended.  leaving read-only.\n");
+                        printk(KERN_WARNING "hfs: filesystem was "
+                                        "not cleanly unmounted, "
+                                        "running fsck.hfsplus is recommended.  "
+                                        "leaving read-only.\n");
                         sb->s_flags |= MS_RDONLY;
                         *flags |= MS_RDONLY;
-                } else if (test_bit(HFSPLUS_SB_FORCE, &sbi.flags)) {
+                } else if (force) {
                         /* nothing */
-                } else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) {
-                        printk(KERN_WARNING "hfs: filesystem is marked locked, leaving read-only.\n");
+                } else if (vhdr->attributes &
+                                cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) {
+                        printk(KERN_WARNING "hfs: filesystem is marked locked, "
+                                        "leaving read-only.\n");
                         sb->s_flags |= MS_RDONLY;
                         *flags |= MS_RDONLY;
-                } else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_JOURNALED)) {
-                        printk(KERN_WARNING "hfs: filesystem is marked journaled, leaving read-only.\n");
+                } else if (vhdr->attributes &
+                                cpu_to_be32(HFSPLUS_VOL_JOURNALED)) {
+                        printk(KERN_WARNING "hfs: filesystem is "
+                                        "marked journaled, "
+                                        "leaving read-only.\n");
                         sb->s_flags |= MS_RDONLY;
                         *flags |= MS_RDONLY;
                 }
@@ -372,17 +398,22 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
         sb->s_maxbytes = MAX_LFS_FILESIZE;
 
         if (!(vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_UNMNT))) {
-                printk(KERN_WARNING "hfs: Filesystem was not cleanly unmounted, "
-                       "running fsck.hfsplus is recommended.  mounting read-only.\n");
+                printk(KERN_WARNING "hfs: Filesystem was "
+                                "not cleanly unmounted, "
+                                "running fsck.hfsplus is recommended.  "
+                                "mounting read-only.\n");
                 sb->s_flags |= MS_RDONLY;
         } else if (test_and_clear_bit(HFSPLUS_SB_FORCE, &sbi->flags)) {
                 /* nothing */
         } else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) {
                 printk(KERN_WARNING "hfs: Filesystem is marked locked, mounting read-only.\n");
                 sb->s_flags |= MS_RDONLY;
-        } else if ((vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_JOURNALED)) && !(sb->s_flags & MS_RDONLY)) {
-                printk(KERN_WARNING "hfs: write access to a journaled filesystem is not supported, "
-                       "use the force option at your own risk, mounting read-only.\n");
+        } else if ((vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_JOURNALED)) &&
+                        !(sb->s_flags & MS_RDONLY)) {
+                printk(KERN_WARNING "hfs: write access to "
+                                "a journaled filesystem is not supported, "
+                                "use the force option at your own risk, "
+                                "mounting read-only.\n");
                 sb->s_flags |= MS_RDONLY;
         }
 
@@ -419,7 +450,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
                 err = -ENOMEM;
                 goto cleanup;
         }
-        sb->s_root->d_op = &hfsplus_dentry_operations;
+        d_set_d_op(sb->s_root, &hfsplus_dentry_operations);
 
         str.len = sizeof(HFSP_HIDDENDIR_NAME) - 1;
         str.name = HFSP_HIDDENDIR_NAME;
@@ -449,19 +480,16 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
         be32_add_cpu(&vhdr->write_count, 1);
         vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_UNMNT);
         vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_INCNSTNT);
-        mark_buffer_dirty(sbi->s_vhbh);
-        sync_dirty_buffer(sbi->s_vhbh);
+        hfsplus_sync_fs(sb, 1);
 
         if (!sbi->hidden_dir) {
-                printk(KERN_DEBUG "hfs: create hidden dir...\n");
-
                 mutex_lock(&sbi->vh_mutex);
                 sbi->hidden_dir = hfsplus_new_inode(sb, S_IFDIR);
                 hfsplus_create_cat(sbi->hidden_dir->i_ino, sb->s_root->d_inode,
                                    &str, sbi->hidden_dir);
                 mutex_unlock(&sbi->vh_mutex);
 
-                mark_inode_dirty(sbi->hidden_dir);
+                hfsplus_mark_inode_dirty(sbi->hidden_dir, HFSPLUS_I_CAT_DIRTY);
         }
 out:
         unload_nls(sbi->nls);
@@ -488,11 +516,19 @@ static struct inode *hfsplus_alloc_inode(struct super_block *sb)
         return i ? &i->vfs_inode : NULL;
 }
 
-static void hfsplus_destroy_inode(struct inode *inode)
+static void hfsplus_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(hfsplus_inode_cachep, HFSPLUS_I(inode));
 }
 
+static void hfsplus_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, hfsplus_i_callback);
+}
+
 #define HFSPLUS_INODE_SIZE      sizeof(struct hfsplus_inode_info)
 
 static struct dentry *hfsplus_mount(struct file_system_type *fs_type,
diff --git a/fs/hfsplus/unicode.c b/fs/hfsplus/unicode.c
index b66d67de882c..a3f0bfcc881e 100644
--- a/fs/hfsplus/unicode.c
+++ b/fs/hfsplus/unicode.c
@@ -17,14 +17,14 @@
 /* Returns folded char, or 0 if ignorable */
 static inline u16 case_fold(u16 c)
 {
-        u16 tmp;
-
-        tmp = hfsplus_case_fold_table[c >> 8];
-        if (tmp)
-                tmp = hfsplus_case_fold_table[tmp + (c & 0xff)];
-        else
-                tmp = c;
-        return tmp;
+        u16 tmp;
+
+        tmp = hfsplus_case_fold_table[c >> 8];
+        if (tmp)
+                tmp = hfsplus_case_fold_table[tmp + (c & 0xff)];
+        else
+                tmp = c;
+        return tmp;
 }
 
 /* Compare unicode strings, return values like normal strcmp */
@@ -118,7 +118,9 @@ static u16 *hfsplus_compose_lookup(u16 *p, u16 cc)
         return NULL;
 }
 
-int hfsplus_uni2asc(struct super_block *sb, const struct hfsplus_unistr *ustr, char *astr, int *len_p)
+int hfsplus_uni2asc(struct super_block *sb,
+                const struct hfsplus_unistr *ustr,
+                char *astr, int *len_p)
 {
         const hfsplus_unichr *ip;
         struct nls_table *nls = HFSPLUS_SB(sb)->nls;
@@ -171,7 +173,8 @@ int hfsplus_uni2asc(struct super_block *sb, const struct hfsplus_unistr *ustr, c
                                 goto same;
                         c1 = be16_to_cpu(*ip);
                         if (likely(compose))
-                                ce1 = hfsplus_compose_lookup(hfsplus_compose_table, c1);
+                                ce1 = hfsplus_compose_lookup(
+                                        hfsplus_compose_table, c1);
                         if (ce1)
                                 break;
                         switch (c0) {
@@ -199,7 +202,8 @@ int hfsplus_uni2asc(struct super_block *sb, const struct hfsplus_unistr *ustr, c
                 if (ce2) {
                         i = 1;
                         while (i < ustrlen) {
-                                ce1 = hfsplus_compose_lookup(ce2, be16_to_cpu(ip[i]));
+                                ce1 = hfsplus_compose_lookup(ce2,
+                                        be16_to_cpu(ip[i]));
                                 if (!ce1)
                                         break;
                                 i++;
@@ -211,7 +215,7 @@ int hfsplus_uni2asc(struct super_block *sb, const struct hfsplus_unistr *ustr, c
                                 goto done;
                         }
                 }
-        same:
+same:
                 switch (c0) {
                 case 0:
                         cc = 0x2400;
@@ -222,7 +226,7 @@ int hfsplus_uni2asc(struct super_block *sb, const struct hfsplus_unistr *ustr, c
                 default:
                         cc = c0;
                 }
-        done:
+done:
                 res = nls->uni2char(cc, op, len);
                 if (res < 0) {
                         if (res == -ENAMETOOLONG)
@@ -320,7 +324,8 @@ int hfsplus_asc2uni(struct super_block *sb, struct hfsplus_unistr *ustr,
  * Composed unicode characters are decomposed and case-folding is performed
  * if the appropriate bits are (un)set on the superblock.
  */
-int hfsplus_hash_dentry(struct dentry *dentry, struct qstr *str)
+int hfsplus_hash_dentry(const struct dentry *dentry, const struct inode *inode,
+                struct qstr *str)
 {
         struct super_block *sb = dentry->d_sb;
         const char *astr;
@@ -363,9 +368,12 @@ int hfsplus_hash_dentry(struct dentry *dentry, struct qstr *str)
  * Composed unicode characters are decomposed and case-folding is performed
  * if the appropriate bits are (un)set on the superblock.
  */
-int hfsplus_compare_dentry(struct dentry *dentry, struct qstr *s1, struct qstr *s2)
+int hfsplus_compare_dentry(const struct dentry *parent,
+                const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name)
 {
-        struct super_block *sb = dentry->d_sb;
+        struct super_block *sb = parent->d_sb;
         int casefold, decompose, size;
         int dsize1, dsize2, len1, len2;
         const u16 *dstr1, *dstr2;
@@ -375,10 +383,10 @@ int hfsplus_compare_dentry(struct dentry *dentry, struct qstr *s1, struct qstr *
 
         casefold = test_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags);
         decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
-        astr1 = s1->name;
-        len1 = s1->len;
-        astr2 = s2->name;
-        len2 = s2->len;
+        astr1 = str;
+        len1 = len;
+        astr2 = name->name;
+        len2 = name->len;
         dsize1 = dsize2 = 0;
         dstr1 = dstr2 = NULL;
 
@@ -388,7 +396,9 @@ int hfsplus_compare_dentry(struct dentry *dentry, struct qstr *s1, struct qstr *
                         astr1 += size;
                         len1 -= size;
 
-                        if (!decompose || !(dstr1 = decompose_unichar(c, &dsize1))) {
+                        if (decompose)
+                                dstr1 = decompose_unichar(c, &dsize1);
+                        if (!decompose || !dstr1) {
                                 c1 = c;
                                 dstr1 = &c1;
                                 dsize1 = 1;
@@ -400,7 +410,9 @@ int hfsplus_compare_dentry(struct dentry *dentry, struct qstr *s1, struct qstr *
                         astr2 += size;
                         len2 -= size;
 
-                        if (!decompose || !(dstr2 = decompose_unichar(c, &dsize2))) {
+                        if (decompose)
+                                dstr2 = decompose_unichar(c, &dsize2);
+                        if (!decompose || !dstr2) {
                                 c2 = c;
                                 dstr2 = &c2;
                                 dsize2 = 1;
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index 8972c20b3216..196231794f64 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -24,6 +24,40 @@ struct hfsplus_wd {
         u16 embed_count;
 };
 
+static void hfsplus_end_io_sync(struct bio *bio, int err)
+{
+        if (err)
+                clear_bit(BIO_UPTODATE, &bio->bi_flags);
+        complete(bio->bi_private);
+}
+
+int hfsplus_submit_bio(struct block_device *bdev, sector_t sector,
+                void *data, int rw)
+{
+        DECLARE_COMPLETION_ONSTACK(wait);
+        struct bio *bio;
+
+        bio = bio_alloc(GFP_NOIO, 1);
+        bio->bi_sector = sector;
+        bio->bi_bdev = bdev;
+        bio->bi_end_io = hfsplus_end_io_sync;
+        bio->bi_private = &wait;
+
+        /*
+         * We always submit one sector at a time, so bio_add_page must not fail.
+         */
+        if (bio_add_page(bio, virt_to_page(data), HFSPLUS_SECTOR_SIZE,
+                         offset_in_page(data)) != HFSPLUS_SECTOR_SIZE)
+                BUG();
+
+        submit_bio(rw, bio);
+        wait_for_completion(&wait);
+
+        if (!bio_flagged(bio, BIO_UPTODATE))
+                return -EIO;
+        return 0;
+}
+
 static int hfsplus_read_mdb(void *bufptr, struct hfsplus_wd *wd)
 {
         u32 extent;
@@ -40,12 +74,14 @@ static int hfsplus_read_mdb(void *bufptr, struct hfsplus_wd *wd)
            !(attrib & HFSP_WRAP_ATTRIB_SPARED))
                 return 0;
 
-        wd->ablk_size = be32_to_cpu(*(__be32 *)(bufptr + HFSP_WRAPOFF_ABLKSIZE));
+        wd->ablk_size =
+                be32_to_cpu(*(__be32 *)(bufptr + HFSP_WRAPOFF_ABLKSIZE));
         if (wd->ablk_size < HFSPLUS_SECTOR_SIZE)
                 return 0;
         if (wd->ablk_size % HFSPLUS_SECTOR_SIZE)
                 return 0;
-        wd->ablk_start = be16_to_cpu(*(__be16 *)(bufptr + HFSP_WRAPOFF_ABLKSTART));
+        wd->ablk_start =
+                be16_to_cpu(*(__be16 *)(bufptr + HFSP_WRAPOFF_ABLKSTART));
 
         extent = get_unaligned_be32(bufptr + HFSP_WRAPOFF_EMBEDEXT);
         wd->embed_start = (extent >> 16) & 0xFFFF;
@@ -68,7 +104,8 @@ static int hfsplus_get_last_session(struct super_block *sb,
         if (HFSPLUS_SB(sb)->session >= 0) {
                 te.cdte_track = HFSPLUS_SB(sb)->session;
                 te.cdte_format = CDROM_LBA;
-                res = ioctl_by_bdev(sb->s_bdev, CDROMREADTOCENTRY, (unsigned long)&te);
+                res = ioctl_by_bdev(sb->s_bdev,
+                        CDROMREADTOCENTRY, (unsigned long)&te);
                 if (!res && (te.cdte_ctrl & CDROM_DATA_TRACK) == 4) {
                         *start = (sector_t)te.cdte_addr.lba << 2;
                         return 0;
@@ -77,7 +114,8 @@ static int hfsplus_get_last_session(struct super_block *sb,
                 return -EINVAL;
         }
         ms_info.addr_format = CDROM_LBA;
-        res = ioctl_by_bdev(sb->s_bdev, CDROMMULTISESSION, (unsigned long)&ms_info);
+        res = ioctl_by_bdev(sb->s_bdev, CDROMMULTISESSION,
+                (unsigned long)&ms_info);
         if (!res && ms_info.xa_flag)
                 *start = (sector_t)ms_info.addr.lba << 2;
         return 0;
@@ -88,100 +126,112 @@ static int hfsplus_get_last_session(struct super_block *sb,
 int hfsplus_read_wrapper(struct super_block *sb)
 {
         struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
-        struct buffer_head *bh;
-        struct hfsplus_vh *vhdr;
         struct hfsplus_wd wd;
         sector_t part_start, part_size;
         u32 blocksize;
+        int error = 0;
 
+        error = -EINVAL;
         blocksize = sb_min_blocksize(sb, HFSPLUS_SECTOR_SIZE);
         if (!blocksize)
-                return -EINVAL;
+                goto out;
 
         if (hfsplus_get_last_session(sb, &part_start, &part_size))
-                return -EINVAL;
+                goto out;
         if ((u64)part_start + part_size > 0x100000000ULL) {
                 pr_err("hfs: volumes larger than 2TB are not supported yet\n");
-                return -EINVAL;
+                goto out;
         }
-        while (1) {
-                bh = sb_bread512(sb, part_start + HFSPLUS_VOLHEAD_SECTOR, vhdr);
-                if (!bh)
-                        return -EIO;
-
-                if (vhdr->signature == cpu_to_be16(HFSP_WRAP_MAGIC)) {
-                        if (!hfsplus_read_mdb(vhdr, &wd))
-                                goto error;
-                        wd.ablk_size >>= HFSPLUS_SECTOR_SHIFT;
-                        part_start += wd.ablk_start + wd.embed_start * wd.ablk_size;
-                        part_size = wd.embed_count * wd.ablk_size;
-                        brelse(bh);
-                        bh = sb_bread512(sb, part_start + HFSPLUS_VOLHEAD_SECTOR, vhdr);
-                        if (!bh)
-                                return -EIO;
-                }
-                if (vhdr->signature == cpu_to_be16(HFSPLUS_VOLHEAD_SIG))
-                        break;
-                if (vhdr->signature == cpu_to_be16(HFSPLUS_VOLHEAD_SIGX)) {
-                        set_bit(HFSPLUS_SB_HFSX, &sbi->flags);
-                        break;
-                }
-                brelse(bh);
 
-                /* check for a partition block
+        error = -ENOMEM;
+        sbi->s_vhdr = kmalloc(HFSPLUS_SECTOR_SIZE, GFP_KERNEL);
+        if (!sbi->s_vhdr)
+                goto out;
+        sbi->s_backup_vhdr = kmalloc(HFSPLUS_SECTOR_SIZE, GFP_KERNEL);
+        if (!sbi->s_backup_vhdr)
+                goto out_free_vhdr;
+
+reread:
+        error = hfsplus_submit_bio(sb->s_bdev,
+                                   part_start + HFSPLUS_VOLHEAD_SECTOR,
+                                   sbi->s_vhdr, READ);
+        if (error)
+                goto out_free_backup_vhdr;
+
+        error = -EINVAL;
+        switch (sbi->s_vhdr->signature) {
+        case cpu_to_be16(HFSPLUS_VOLHEAD_SIGX):
+                set_bit(HFSPLUS_SB_HFSX, &sbi->flags);
+                /*FALLTHRU*/
+        case cpu_to_be16(HFSPLUS_VOLHEAD_SIG):
+                break;
+        case cpu_to_be16(HFSP_WRAP_MAGIC):
+                if (!hfsplus_read_mdb(sbi->s_vhdr, &wd))
+                        goto out;
+                wd.ablk_size >>= HFSPLUS_SECTOR_SHIFT;
+                part_start += wd.ablk_start + wd.embed_start * wd.ablk_size;
+                part_size = wd.embed_count * wd.ablk_size;
+                goto reread;
+        default:
+                /*
+                 * Check for a partition block.
+                 *
                  * (should do this only for cdrom/loop though)
                  */
                 if (hfs_part_find(sb, &part_start, &part_size))
-                        return -EINVAL;
+                        goto out;
+                goto reread;
+        }
+
+        error = hfsplus_submit_bio(sb->s_bdev,
+                                   part_start + part_size - 2,
+                                   sbi->s_backup_vhdr, READ);
+        if (error)
+                goto out_free_backup_vhdr;
+
+        error = -EINVAL;
+        if (sbi->s_backup_vhdr->signature != sbi->s_vhdr->signature) {
+                printk(KERN_WARNING
+                        "hfs: invalid secondary volume header\n");
+                goto out_free_backup_vhdr;
         }
 
-        blocksize = be32_to_cpu(vhdr->blocksize);
-        brelse(bh);
+        blocksize = be32_to_cpu(sbi->s_vhdr->blocksize);
 
-        /* block size must be at least as large as a sector
-         * and a multiple of 2
+        /*
+         * Block size must be at least as large as a sector and a multiple of 2.
          */
-        if (blocksize < HFSPLUS_SECTOR_SIZE ||
-            ((blocksize - 1) & blocksize))
-                return -EINVAL;
+        if (blocksize < HFSPLUS_SECTOR_SIZE || ((blocksize - 1) & blocksize))
+                goto out_free_backup_vhdr;
         sbi->alloc_blksz = blocksize;
         sbi->alloc_blksz_shift = 0;
         while ((blocksize >>= 1) != 0)
                 sbi->alloc_blksz_shift++;
         blocksize = min(sbi->alloc_blksz, (u32)PAGE_SIZE);
 
-        /* align block size to block offset */
+        /*
+         * Align block size to block offset.
+         */
         while (part_start & ((blocksize >> HFSPLUS_SECTOR_SHIFT) - 1))
                 blocksize >>= 1;
 
         if (sb_set_blocksize(sb, blocksize) != blocksize) {
-                printk(KERN_ERR "hfs: unable to set blocksize to %u!\n", blocksize);
-                return -EINVAL;
+                printk(KERN_ERR "hfs: unable to set blocksize to %u!\n",
+                        blocksize);
+                goto out_free_backup_vhdr;
         }
 
         sbi->blockoffset =
                 part_start >> (sb->s_blocksize_bits - HFSPLUS_SECTOR_SHIFT);
+        sbi->part_start = part_start;
         sbi->sect_count = part_size;
         sbi->fs_shift = sbi->alloc_blksz_shift - sb->s_blocksize_bits;
-
-        bh = sb_bread512(sb, part_start + HFSPLUS_VOLHEAD_SECTOR, vhdr);
-        if (!bh)
-                return -EIO;
-
-        /* should still be the same... */
-        if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags)) {
-                if (vhdr->signature != cpu_to_be16(HFSPLUS_VOLHEAD_SIGX))
-                        goto error;
-        } else {
-                if (vhdr->signature != cpu_to_be16(HFSPLUS_VOLHEAD_SIG))
-                        goto error;
-        }
-
-        sbi->s_vhbh = bh;
-        sbi->s_vhdr = vhdr;
-
         return 0;
- error:
-        brelse(bh);
-        return -EINVAL;
+
+out_free_backup_vhdr:
+        kfree(sbi->s_backup_vhdr);
+out_free_vhdr:
+        kfree(sbi->s_vhdr);
+out:
+        return error;
 }
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 2c0f148a49e6..d3244d949a4e 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -32,7 +32,7 @@ static inline struct hostfs_inode_info *HOSTFS_I(struct inode *inode)
 
 #define FILE_HOSTFS_I(file) HOSTFS_I((file)->f_path.dentry->d_inode)
 
-static int hostfs_d_delete(struct dentry *dentry)
+static int hostfs_d_delete(const struct dentry *dentry)
 {
         return 1;
 }
@@ -92,12 +92,10 @@ __uml_setup("hostfs=", hostfs_args,
 
 static char *__dentry_name(struct dentry *dentry, char *name)
 {
-        char *p = __dentry_path(dentry, name, PATH_MAX);
+        char *p = dentry_path_raw(dentry, name, PATH_MAX);
         char *root;
         size_t len;
 
-        spin_unlock(&dcache_lock);
-
         root = dentry->d_sb->s_fs_info;
         len = strlen(root);
         if (IS_ERR(p)) {
@@ -123,25 +121,23 @@ static char *dentry_name(struct dentry *dentry)
         if (!name)
                 return NULL;
 
-        spin_lock(&dcache_lock);
         return __dentry_name(dentry, name); /* will unlock */
 }
 
 static char *inode_name(struct inode *ino)
 {
         struct dentry *dentry;
-        char *name = __getname();
-        if (!name)
-                return NULL;
+        char *name;
 
-        spin_lock(&dcache_lock);
-        if (list_empty(&ino->i_dentry)) {
-                spin_unlock(&dcache_lock);
-                __putname(name);
+        dentry = d_find_alias(ino);
+        if (!dentry)
                 return NULL;
-        }
-        dentry = list_first_entry(&ino->i_dentry, struct dentry, d_alias);
-        return __dentry_name(dentry, name); /* will unlock */
+
+        name = dentry_name(dentry);
+
+        dput(dentry);
+
+        return name;
 }
 
 static char *follow_link(char *link)
@@ -251,11 +247,18 @@ static void hostfs_evict_inode(struct inode *inode)
         }
 }
 
-static void hostfs_destroy_inode(struct inode *inode)
+static void hostfs_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kfree(HOSTFS_I(inode));
 }
 
+static void hostfs_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, hostfs_i_callback);
+}
+
 static int hostfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
 {
         const char *root_path = vfs->mnt_sb->s_fs_info;
@@ -609,7 +612,7 @@ struct dentry *hostfs_lookup(struct inode *ino, struct dentry *dentry,
                 goto out_put;
 
         d_add(dentry, inode);
-        dentry->d_op = &hostfs_dentry_ops;
+        d_set_d_op(dentry, &hostfs_dentry_ops);
         return NULL;
 
  out_put:
@@ -746,11 +749,14 @@ int hostfs_rename(struct inode *from_ino, struct dentry *from,
         return err;
 }
 
-int hostfs_permission(struct inode *ino, int desired)
+int hostfs_permission(struct inode *ino, int desired, unsigned int flags)
 {
         char *name;
         int r = 0, w = 0, x = 0, err;
 
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
         if (desired & MAY_READ) r = 1;
         if (desired & MAY_WRITE) w = 1;
         if (desired & MAY_EXEC) x = 1;
@@ -765,7 +771,7 @@ int hostfs_permission(struct inode *ino, int desired)
                 err = access_file(name, r, w, x);
         __putname(name);
         if (!err)
-                err = generic_permission(ino, desired, NULL);
+                err = generic_permission(ino, desired, flags, NULL);
         return err;
 }
 
diff --git a/fs/hpfs/dentry.c b/fs/hpfs/dentry.c
index 67d9d36b3d5f..32c13a94e1e9 100644
--- a/fs/hpfs/dentry.c
+++ b/fs/hpfs/dentry.c
@@ -12,7 +12,8 @@
  * Note: the dentry argument is the parent dentry.
  */
 
-static int hpfs_hash_dentry(struct dentry *dentry, struct qstr *qstr)
+static int hpfs_hash_dentry(const struct dentry *dentry, const struct inode *inode,
+                struct qstr *qstr)
 {
         unsigned long    hash;
         int              i;
@@ -34,19 +35,25 @@ static int hpfs_hash_dentry(struct dentry *dentry, struct qstr *qstr)
         return 0;
 }
 
-static int hpfs_compare_dentry(struct dentry *dentry, struct qstr *a, struct qstr *b)
+static int hpfs_compare_dentry(const struct dentry *parent,
+                const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name)
 {
-        unsigned al=a->len;
-        unsigned bl=b->len;
-        hpfs_adjust_length(a->name, &al);
+        unsigned al = len;
+        unsigned bl = name->len;
+
+        hpfs_adjust_length(str, &al);
         /*hpfs_adjust_length(b->name, &bl);*/
-        /* 'a' is the qstr of an already existing dentry, so the name
-         * must be valid. 'b' must be validated first.
+
+        /*
+         * 'str' is the nane of an already existing dentry, so the name
+         * must be valid. 'name' must be validated first.
          */
 
-        if (hpfs_chk_name(b->name, &bl))
+        if (hpfs_chk_name(name->name, &bl))
                 return 1;
-        if (hpfs_compare_names(dentry->d_sb, a->name, al, b->name, bl, 0))
+        if (hpfs_compare_names(parent->d_sb, str, al, name->name, bl, 0))
                 return 1;
         return 0;
 }
@@ -58,5 +65,5 @@ static const struct dentry_operations hpfs_dentry_operations = {
 
 void hpfs_set_dentry_operations(struct dentry *dentry)
 {
-        dentry->d_op = &hpfs_dentry_operations;
+        d_set_d_op(dentry, &hpfs_dentry_operations);
 }
diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c
index 11c2b4080f65..f4ad9e31ddc4 100644
--- a/fs/hpfs/namei.c
+++ b/fs/hpfs/namei.c
@@ -419,7 +419,7 @@ again:
                         unlock_kernel();
                         return -ENOSPC;
                 }
-                if (generic_permission(inode, MAY_WRITE, NULL) ||
+                if (generic_permission(inode, MAY_WRITE, 0, NULL) ||
                     !S_ISREG(inode->i_mode) ||
                     get_write_access(inode)) {
                         d_rehash(dentry);
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index 6c5f01597c3a..49935ba78db8 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -177,11 +177,18 @@ static struct inode *hpfs_alloc_inode(struct super_block *sb)
         return &ei->vfs_inode;
 }
 
-static void hpfs_destroy_inode(struct inode *inode)
+static void hpfs_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(hpfs_inode_cachep, hpfs_i(inode));
 }
 
+static void hpfs_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, hpfs_i_callback);
+}
+
 static void init_once(void *foo)
 {
         struct hpfs_inode_info *ei = (struct hpfs_inode_info *) foo;
diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c
index f702b5f713fc..87ed48e0343d 100644
--- a/fs/hppfs/hppfs.c
+++ b/fs/hppfs/hppfs.c
@@ -632,11 +632,18 @@ void hppfs_evict_inode(struct inode *ino)
         mntput(ino->i_sb->s_fs_info);
 }
 
-static void hppfs_destroy_inode(struct inode *inode)
+static void hppfs_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kfree(HPPFS_I(inode));
 }
 
+static void hppfs_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, hppfs_i_callback);
+}
+
 static const struct super_operations hppfs_sbops = {
         .alloc_inode    = hppfs_alloc_inode,
         .destroy_inode  = hppfs_destroy_inode,
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index a5fe68189eed..9885082b470f 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -663,11 +663,18 @@ static struct inode *hugetlbfs_alloc_inode(struct super_block *sb)
         return &p->vfs_inode;
 }
 
+static void hugetlbfs_i_callback(struct rcu_head *head)
+{
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
+        kmem_cache_free(hugetlbfs_inode_cachep, HUGETLBFS_I(inode));
+}
+
 static void hugetlbfs_destroy_inode(struct inode *inode)
 {
         hugetlbfs_inc_free_inodes(HUGETLBFS_SB(inode->i_sb));
         mpol_free_shared_policy(&HUGETLBFS_I(inode)->policy);
-        kmem_cache_free(hugetlbfs_inode_cachep, HUGETLBFS_I(inode));
+        call_rcu(&inode->i_rcu, hugetlbfs_i_callback);
 }
 
 static const struct address_space_operations hugetlbfs_aops = {
diff --git a/fs/inode.c b/fs/inode.c
index ae2727ab0c3a..da85e56378f3 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -102,26 +102,29 @@ static DECLARE_RWSEM(iprune_sem);
  */
 struct inodes_stat_t inodes_stat;
 
-static struct percpu_counter nr_inodes __cacheline_aligned_in_smp;
-static struct percpu_counter nr_inodes_unused __cacheline_aligned_in_smp;
+static DEFINE_PER_CPU(unsigned int, nr_inodes);
 
 static struct kmem_cache *inode_cachep __read_mostly;
 
-static inline int get_nr_inodes(void)
+static int get_nr_inodes(void)
 {
-        return percpu_counter_sum_positive(&nr_inodes);
+        int i;
+        int sum = 0;
+        for_each_possible_cpu(i)
+                sum += per_cpu(nr_inodes, i);
+        return sum < 0 ? 0 : sum;
 }
 
 static inline int get_nr_inodes_unused(void)
 {
-        return percpu_counter_sum_positive(&nr_inodes_unused);
+        return inodes_stat.nr_unused;
 }
 
 int get_nr_dirty_inodes(void)
 {
+        /* not actually dirty inodes, but a wild approximation */
         int nr_dirty = get_nr_inodes() - get_nr_inodes_unused();
         return nr_dirty > 0 ? nr_dirty : 0;
-
 }
 
 /*
@@ -132,7 +135,6 @@ int proc_nr_inodes(ctl_table *table, int write,
                    void __user *buffer, size_t *lenp, loff_t *ppos)
 {
         inodes_stat.nr_inodes = get_nr_inodes();
-        inodes_stat.nr_unused = get_nr_inodes_unused();
         return proc_dointvec(table, write, buffer, lenp, ppos);
 }
 #endif
@@ -224,7 +226,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
         inode->i_fsnotify_mask = 0;
 #endif
 
-        percpu_counter_inc(&nr_inodes);
+        this_cpu_inc(nr_inodes);
 
         return 0;
 out:
@@ -255,6 +257,12 @@ static struct inode *alloc_inode(struct super_block *sb)
         return inode;
 }
 
+void free_inode_nonrcu(struct inode *inode)
+{
+        kmem_cache_free(inode_cachep, inode);
+}
+EXPORT_SYMBOL(free_inode_nonrcu);
+
 void __destroy_inode(struct inode *inode)
 {
         BUG_ON(inode_has_buffers(inode));
@@ -266,10 +274,17 @@ void __destroy_inode(struct inode *inode)
         if (inode->i_default_acl && inode->i_default_acl != ACL_NOT_CACHED)
                 posix_acl_release(inode->i_default_acl);
 #endif
-        percpu_counter_dec(&nr_inodes);
+        this_cpu_dec(nr_inodes);
 }
 EXPORT_SYMBOL(__destroy_inode);
 
+static void i_callback(struct rcu_head *head)
+{
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
+        kmem_cache_free(inode_cachep, inode);
+}
+
 static void destroy_inode(struct inode *inode)
 {
         BUG_ON(!list_empty(&inode->i_lru));
@@ -277,7 +292,7 @@ static void destroy_inode(struct inode *inode)
         if (inode->i_sb->s_op->destroy_inode)
                 inode->i_sb->s_op->destroy_inode(inode);
         else
-                kmem_cache_free(inode_cachep, (inode));
+                call_rcu(&inode->i_rcu, i_callback);
 }
 
 /*
@@ -335,7 +350,7 @@ static void inode_lru_list_add(struct inode *inode)
 {
         if (list_empty(&inode->i_lru)) {
                 list_add(&inode->i_lru, &inode_lru);
-                percpu_counter_inc(&nr_inodes_unused);
+                inodes_stat.nr_unused++;
         }
 }
 
@@ -343,7 +358,7 @@ static void inode_lru_list_del(struct inode *inode)
 {
         if (!list_empty(&inode->i_lru)) {
                 list_del_init(&inode->i_lru);
-                percpu_counter_dec(&nr_inodes_unused);
+                inodes_stat.nr_unused--;
         }
 }
 
@@ -430,6 +445,7 @@ void end_writeback(struct inode *inode)
         BUG_ON(!(inode->i_state & I_FREEING));
         BUG_ON(inode->i_state & I_CLEAR);
         inode_sync_wait(inode);
+        /* don't need i_lock here, no concurrent mods to i_state */
         inode->i_state = I_FREEING | I_CLEAR;
 }
 EXPORT_SYMBOL(end_writeback);
@@ -513,7 +529,7 @@ void evict_inodes(struct super_block *sb)
                 list_move(&inode->i_lru, &dispose);
                 list_del_init(&inode->i_wb_list);
                 if (!(inode->i_state & (I_DIRTY | I_SYNC)))
-                        percpu_counter_dec(&nr_inodes_unused);
+                        inodes_stat.nr_unused--;
         }
         spin_unlock(&inode_lock);
 
@@ -554,7 +570,7 @@ int invalidate_inodes(struct super_block *sb)
                 list_move(&inode->i_lru, &dispose);
                 list_del_init(&inode->i_wb_list);
                 if (!(inode->i_state & (I_DIRTY | I_SYNC)))
-                        percpu_counter_dec(&nr_inodes_unused);
+                        inodes_stat.nr_unused--;
         }
         spin_unlock(&inode_lock);
 
@@ -616,7 +632,7 @@ static void prune_icache(int nr_to_scan)
                 if (atomic_read(&inode->i_count) ||
                     (inode->i_state & ~I_REFERENCED)) {
                         list_del_init(&inode->i_lru);
-                        percpu_counter_dec(&nr_inodes_unused);
+                        inodes_stat.nr_unused--;
                         continue;
                 }
 
@@ -650,7 +666,7 @@ static void prune_icache(int nr_to_scan)
                  */
                 list_move(&inode->i_lru, &freeable);
                 list_del_init(&inode->i_wb_list);
-                percpu_counter_dec(&nr_inodes_unused);
+                inodes_stat.nr_unused--;
         }
         if (current_is_kswapd())
                 __count_vm_events(KSWAPD_INODESTEAL, reap);
@@ -1648,8 +1664,6 @@ void __init inode_init(void)
                                          SLAB_MEM_SPREAD),
                                          init_once);
         register_shrinker(&icache_shrinker);
-        percpu_counter_init(&nr_inodes, 0);
-        percpu_counter_init(&nr_inodes_unused, 0);
 
         /* Hash may have been set up in inode_init_early */
         if (!hashdist)
diff --git a/fs/internal.h b/fs/internal.h
index e43b9a4dbf4e..9687c2ee2735 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -63,6 +63,7 @@ extern int copy_mount_string(const void __user *, char **);
 
 extern void free_vfsmnt(struct vfsmount *);
 extern struct vfsmount *alloc_vfsmnt(const char *);
+extern unsigned int mnt_get_count(struct vfsmount *mnt);
 extern struct vfsmount *__lookup_mnt(struct vfsmount *, struct dentry *, int);
 extern void mnt_set_mountpoint(struct vfsmount *, struct dentry *,
                                 struct vfsmount *);
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index bfdeb82a53be..844a7903c72f 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -26,16 +26,32 @@
 
 #define BEQUIET
 
-static int isofs_hashi(struct dentry *parent, struct qstr *qstr);
-static int isofs_hash(struct dentry *parent, struct qstr *qstr);
-static int isofs_dentry_cmpi(struct dentry *dentry, struct qstr *a, struct qstr *b);
-static int isofs_dentry_cmp(struct dentry *dentry, struct qstr *a, struct qstr *b);
+static int isofs_hashi(const struct dentry *parent, const struct inode *inode,
+                struct qstr *qstr);
+static int isofs_hash(const struct dentry *parent, const struct inode *inode,
+                struct qstr *qstr);
+static int isofs_dentry_cmpi(const struct dentry *parent,
+                const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name);
+static int isofs_dentry_cmp(const struct dentry *parent,
+                const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name);
 
 #ifdef CONFIG_JOLIET
-static int isofs_hashi_ms(struct dentry *parent, struct qstr *qstr);
-static int isofs_hash_ms(struct dentry *parent, struct qstr *qstr);
-static int isofs_dentry_cmpi_ms(struct dentry *dentry, struct qstr *a, struct qstr *b);
-static int isofs_dentry_cmp_ms(struct dentry *dentry, struct qstr *a, struct qstr *b);
+static int isofs_hashi_ms(const struct dentry *parent, const struct inode *inode,
+                struct qstr *qstr);
+static int isofs_hash_ms(const struct dentry *parent, const struct inode *inode,
+                struct qstr *qstr);
+static int isofs_dentry_cmpi_ms(const struct dentry *parent,
+                const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name);
+static int isofs_dentry_cmp_ms(const struct dentry *parent,
+                const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name);
 #endif
 
 static void isofs_put_super(struct super_block *sb)
@@ -65,11 +81,18 @@ static struct inode *isofs_alloc_inode(struct super_block *sb)
         return &ei->vfs_inode;
 }
 
-static void isofs_destroy_inode(struct inode *inode)
+static void isofs_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(isofs_inode_cachep, ISOFS_I(inode));
 }
 
+static void isofs_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, isofs_i_callback);
+}
+
 static void init_once(void *foo)
 {
         struct iso_inode_info *ei = foo;
@@ -160,7 +183,7 @@ struct iso9660_options{
  * Compute the hash for the isofs name corresponding to the dentry.
  */
 static int
-isofs_hash_common(struct dentry *dentry, struct qstr *qstr, int ms)
+isofs_hash_common(const struct dentry *dentry, struct qstr *qstr, int ms)
 {
         const char *name;
         int len;
@@ -181,7 +204,7 @@ isofs_hash_common(struct dentry *dentry, struct qstr *qstr, int ms)
  * Compute the hash for the isofs name corresponding to the dentry.
  */
 static int
-isofs_hashi_common(struct dentry *dentry, struct qstr *qstr, int ms)
+isofs_hashi_common(const struct dentry *dentry, struct qstr *qstr, int ms)
 {
         const char *name;
         int len;
@@ -206,100 +229,94 @@ isofs_hashi_common(struct dentry *dentry, struct qstr *qstr, int ms)
 }
 
 /*
- * Case insensitive compare of two isofs names.
- */
-static int isofs_dentry_cmpi_common(struct dentry *dentry, struct qstr *a,
-                                struct qstr *b, int ms)
-{
-        int alen, blen;
-
-        /* A filename cannot end in '.' or we treat it like it has none */
-        alen = a->len;
-        blen = b->len;
-        if (ms) {
-                while (alen && a->name[alen-1] == '.')
-                        alen--;
-                while (blen && b->name[blen-1] == '.')
-                        blen--;
-        }
-        if (alen == blen) {
-                if (strnicmp(a->name, b->name, alen) == 0)
-                        return 0;
-        }
-        return 1;
-}
-
-/*
- * Case sensitive compare of two isofs names.
+ * Compare of two isofs names.
  */
-static int isofs_dentry_cmp_common(struct dentry *dentry, struct qstr *a,
-                                        struct qstr *b, int ms)
+static int isofs_dentry_cmp_common(
+                unsigned int len, const char *str,
+                const struct qstr *name, int ms, int ci)
 {
         int alen, blen;
 
         /* A filename cannot end in '.' or we treat it like it has none */
-        alen = a->len;
-        blen = b->len;
+        alen = name->len;
+        blen = len;
         if (ms) {
-                while (alen && a->name[alen-1] == '.')
+                while (alen && name->name[alen-1] == '.')
                         alen--;
-                while (blen && b->name[blen-1] == '.')
+                while (blen && str[blen-1] == '.')
                         blen--;
         }
         if (alen == blen) {
-                if (strncmp(a->name, b->name, alen) == 0)
-                        return 0;
+                if (ci) {
+                        if (strnicmp(name->name, str, alen) == 0)
+                                return 0;
+                } else {
+                        if (strncmp(name->name, str, alen) == 0)
+                                return 0;
+                }
         }
         return 1;
 }
 
 static int
-isofs_hash(struct dentry *dentry, struct qstr *qstr)
+isofs_hash(const struct dentry *dentry, const struct inode *inode,
+                struct qstr *qstr)
 {
         return isofs_hash_common(dentry, qstr, 0);
 }
 
 static int
-isofs_hashi(struct dentry *dentry, struct qstr *qstr)
+isofs_hashi(const struct dentry *dentry, const struct inode *inode,
+                struct qstr *qstr)
 {
         return isofs_hashi_common(dentry, qstr, 0);
 }
 
 static int
-isofs_dentry_cmp(struct dentry *dentry,struct qstr *a,struct qstr *b)
+isofs_dentry_cmp(const struct dentry *parent, const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name)
 {
-        return isofs_dentry_cmp_common(dentry, a, b, 0);
+        return isofs_dentry_cmp_common(len, str, name, 0, 0);
 }
 
 static int
-isofs_dentry_cmpi(struct dentry *dentry,struct qstr *a,struct qstr *b)
+isofs_dentry_cmpi(const struct dentry *parent, const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name)
 {
-        return isofs_dentry_cmpi_common(dentry, a, b, 0);
+        return isofs_dentry_cmp_common(len, str, name, 0, 1);
 }
 
 #ifdef CONFIG_JOLIET
 static int
-isofs_hash_ms(struct dentry *dentry, struct qstr *qstr)
+isofs_hash_ms(const struct dentry *dentry, const struct inode *inode,
+                struct qstr *qstr)
 {
         return isofs_hash_common(dentry, qstr, 1);
 }
 
 static int
-isofs_hashi_ms(struct dentry *dentry, struct qstr *qstr)
+isofs_hashi_ms(const struct dentry *dentry, const struct inode *inode,
+                struct qstr *qstr)
 {
         return isofs_hashi_common(dentry, qstr, 1);
 }
 
 static int
-isofs_dentry_cmp_ms(struct dentry *dentry,struct qstr *a,struct qstr *b)
+isofs_dentry_cmp_ms(const struct dentry *parent, const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name)
 {
-        return isofs_dentry_cmp_common(dentry, a, b, 1);
+        return isofs_dentry_cmp_common(len, str, name, 1, 0);
 }
 
 static int
-isofs_dentry_cmpi_ms(struct dentry *dentry,struct qstr *a,struct qstr *b)
+isofs_dentry_cmpi_ms(const struct dentry *parent, const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name)
 {
-        return isofs_dentry_cmpi_common(dentry, a, b, 1);
+        return isofs_dentry_cmp_common(len, str, name, 1, 1);
 }
 #endif
 
@@ -932,7 +949,7 @@ root_found:
                 table += 2;
         if (opt.check == 'r')
                 table++;
-        s->s_root->d_op = &isofs_dentry_ops[table];
+        d_set_d_op(s->s_root, &isofs_dentry_ops[table]);
 
         kfree(opt.iocharset);
 
diff --git a/fs/isofs/namei.c b/fs/isofs/namei.c
index 0d23abfd4280..679a849c3b27 100644
--- a/fs/isofs/namei.c
+++ b/fs/isofs/namei.c
@@ -37,7 +37,8 @@ isofs_cmp(struct dentry *dentry, const char *compare, int dlen)
 
         qstr.name = compare;
         qstr.len = dlen;
-        return dentry->d_op->d_compare(dentry, &dentry->d_name, &qstr);
+        return dentry->d_op->d_compare(NULL, NULL, NULL, NULL,
+                        dentry->d_name.len, dentry->d_name.name, &qstr);
 }
 
 /*
@@ -171,7 +172,7 @@ struct dentry *isofs_lookup(struct inode *dir, struct dentry *dentry, struct nam
         struct inode *inode;
         struct page *page;
 
-        dentry->d_op = dir->i_sb->s_root->d_op;
+        d_set_d_op(dentry, dir->i_sb->s_root->d_op);
 
         page = alloc_page(GFP_USER);
         if (!page)
diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c
index 54a92fd02bbd..95b79672150a 100644
--- a/fs/jffs2/acl.c
+++ b/fs/jffs2/acl.c
@@ -259,11 +259,14 @@ static int jffs2_set_acl(struct inode *inode, int type, struct posix_acl *acl)
         return rc;
 }
 
-int jffs2_check_acl(struct inode *inode, int mask)
+int jffs2_check_acl(struct inode *inode, int mask, unsigned int flags)
 {
         struct posix_acl *acl;
         int rc;
 
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
         acl = jffs2_get_acl(inode, ACL_TYPE_ACCESS);
         if (IS_ERR(acl))
                 return PTR_ERR(acl);
diff --git a/fs/jffs2/acl.h b/fs/jffs2/acl.h
index 5e42de8d9541..3119f59253d3 100644
--- a/fs/jffs2/acl.h
+++ b/fs/jffs2/acl.h
@@ -26,7 +26,7 @@ struct jffs2_acl_header {
 
 #ifdef CONFIG_JFFS2_FS_POSIX_ACL
 
-extern int jffs2_check_acl(struct inode *, int);
+extern int jffs2_check_acl(struct inode *, int, unsigned int);
 extern int jffs2_acl_chmod(struct inode *);
 extern int jffs2_init_acl_pre(struct inode *, struct inode *, int *);
 extern int jffs2_init_acl_post(struct inode *);
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index c86041b866a4..853b8e300084 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -40,11 +40,18 @@ static struct inode *jffs2_alloc_inode(struct super_block *sb)
         return &f->vfs_inode;
 }
 
-static void jffs2_destroy_inode(struct inode *inode)
+static void jffs2_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(jffs2_inode_cachep, JFFS2_INODE_INFO(inode));
 }
 
+static void jffs2_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, jffs2_i_callback);
+}
+
 static void jffs2_i_init_once(void *foo)
 {
         struct jffs2_inode_info *f = foo;
diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c
index 1057a4998e4e..e5de9422fa32 100644
--- a/fs/jfs/acl.c
+++ b/fs/jfs/acl.c
@@ -114,10 +114,14 @@ out:
         return rc;
 }
 
-int jfs_check_acl(struct inode *inode, int mask)
+int jfs_check_acl(struct inode *inode, int mask, unsigned int flags)
 {
-        struct posix_acl *acl = jfs_get_acl(inode, ACL_TYPE_ACCESS);
+        struct posix_acl *acl;
+
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
 
+        acl = jfs_get_acl(inode, ACL_TYPE_ACCESS);
         if (IS_ERR(acl))
                 return PTR_ERR(acl);
         if (acl) {
diff --git a/fs/jfs/jfs_acl.h b/fs/jfs/jfs_acl.h
index 54e07559878d..f9285c4900fa 100644
--- a/fs/jfs/jfs_acl.h
+++ b/fs/jfs/jfs_acl.h
@@ -20,7 +20,7 @@
 
 #ifdef CONFIG_JFS_POSIX_ACL
 
-int jfs_check_acl(struct inode *, int);
+int jfs_check_acl(struct inode *, int, unsigned int flags);
 int jfs_init_acl(tid_t, struct inode *, struct inode *);
 int jfs_acl_chmod(struct inode *inode);
 
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 231ca4af9bce..4414e3a42264 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -18,6 +18,7 @@
  */
 
 #include <linux/fs.h>
+#include <linux/namei.h>
 #include <linux/ctype.h>
 #include <linux/quotaops.h>
 #include <linux/exportfs.h>
@@ -1465,7 +1466,7 @@ static struct dentry *jfs_lookup(struct inode *dip, struct dentry *dentry, struc
         jfs_info("jfs_lookup: name = %s", name);
 
         if (JFS_SBI(dip->i_sb)->mntflag & JFS_OS2)
-                dentry->d_op = &jfs_ci_dentry_operations;
+                d_set_d_op(dentry, &jfs_ci_dentry_operations);
 
         if ((name[0] == '.') && (len == 1))
                 inum = dip->i_ino;
@@ -1494,7 +1495,7 @@ static struct dentry *jfs_lookup(struct inode *dip, struct dentry *dentry, struc
         dentry = d_splice_alias(ip, dentry);
 
         if (dentry && (JFS_SBI(dip->i_sb)->mntflag & JFS_OS2))
-                dentry->d_op = &jfs_ci_dentry_operations;
+                d_set_d_op(dentry, &jfs_ci_dentry_operations);
 
         return dentry;
 }
@@ -1573,7 +1574,8 @@ const struct file_operations jfs_dir_operations = {
         .llseek         = generic_file_llseek,
 };
 
-static int jfs_ci_hash(struct dentry *dir, struct qstr *this)
+static int jfs_ci_hash(const struct dentry *dir, const struct inode *inode,
+                struct qstr *this)
 {
         unsigned long hash;
         int i;
@@ -1586,32 +1588,63 @@ static int jfs_ci_hash(struct dentry *dir, struct qstr *this)
         return 0;
 }
 
-static int jfs_ci_compare(struct dentry *dir, struct qstr *a, struct qstr *b)
+static int jfs_ci_compare(const struct dentry *parent,
+                const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name)
 {
         int i, result = 1;
 
-        if (a->len != b->len)
+        if (len != name->len)
                 goto out;
-        for (i=0; i < a->len; i++) {
-                if (tolower(a->name[i]) != tolower(b->name[i]))
+        for (i=0; i < len; i++) {
+                if (tolower(str[i]) != tolower(name->name[i]))
                         goto out;
         }
         result = 0;
+out:
+        return result;
+}
 
+static int jfs_ci_revalidate(struct dentry *dentry, struct nameidata *nd)
+{
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
         /*
-         * We want creates to preserve case.  A negative dentry, a, that
-         * has a different case than b may cause a new entry to be created
-         * with the wrong case.  Since we can't tell if a comes from a negative
-         * dentry, we blindly replace it with b.  This should be harmless if
-         * a is not a negative dentry.
+         * This is not negative dentry. Always valid.
+         *
+         * Note, rename() to existing directory entry will have ->d_inode,
+         * and will use existing name which isn't specified name by user.
+         *
+         * We may be able to drop this positive dentry here. But dropping
+         * positive dentry isn't good idea. So it's unsupported like
+         * rename("filename", "FILENAME") for now.
          */
-        memcpy((unsigned char *)a->name, b->name, a->len);
-out:
-        return result;
+        if (dentry->d_inode)
+                return 1;
+
+        /*
+         * This may be nfsd (or something), anyway, we can't see the
+         * intent of this. So, since this can be for creation, drop it.
+         */
+        if (!nd)
+                return 0;
+
+        /*
+         * Drop the negative dentry, in order to make sure to use the
+         * case sensitive name which is specified by user if this is
+         * for creation.
+         */
+        if (!(nd->flags & (LOOKUP_CONTINUE | LOOKUP_PARENT))) {
+                if (nd->flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
+                        return 0;
+        }
+        return 1;
 }
 
 const struct dentry_operations jfs_ci_dentry_operations =
 {
         .d_hash = jfs_ci_hash,
         .d_compare = jfs_ci_compare,
+        .d_revalidate = jfs_ci_revalidate,
 };
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 0669fc1cc3bf..3150d766e0d4 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -115,6 +115,14 @@ static struct inode *jfs_alloc_inode(struct super_block *sb)
         return &jfs_inode->vfs_inode;
 }
 
+static void jfs_i_callback(struct rcu_head *head)
+{
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        struct jfs_inode_info *ji = JFS_IP(inode);
+        INIT_LIST_HEAD(&inode->i_dentry);
+        kmem_cache_free(jfs_inode_cachep, ji);
+}
+
 static void jfs_destroy_inode(struct inode *inode)
 {
         struct jfs_inode_info *ji = JFS_IP(inode);
@@ -128,7 +136,7 @@ static void jfs_destroy_inode(struct inode *inode)
                 ji->active_ag = -1;
         }
         spin_unlock_irq(&ji->ag_lock);
-        kmem_cache_free(jfs_inode_cachep, ji);
+        call_rcu(&inode->i_rcu, jfs_i_callback);
 }
 
 static int jfs_statfs(struct dentry *dentry, struct kstatfs *buf)
@@ -517,7 +525,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
                 goto out_no_root;
 
         if (sbi->mntflag & JFS_OS2)
-                sb->s_root->d_op = &jfs_ci_dentry_operations;
+                d_set_d_op(sb->s_root, &jfs_ci_dentry_operations);
 
         /* logical blocks are represented by 40 bits in pxd_t, etc. */
         sb->s_maxbytes = ((u64) sb->s_blocksize) << 40;
diff --git a/fs/libfs.c b/fs/libfs.c
index a3accdf528ad..889311e3d06b 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -16,6 +16,11 @@
 
 #include <asm/uaccess.h>
 
+static inline int simple_positive(struct dentry *dentry)
+{
+        return dentry->d_inode && !d_unhashed(dentry);
+}
+
 int simple_getattr(struct vfsmount *mnt, struct dentry *dentry,
                    struct kstat *stat)
 {
@@ -37,7 +42,7 @@ int simple_statfs(struct dentry *dentry, struct kstatfs *buf)
  * Retaining negative dentries for an in-memory filesystem just wastes
  * memory and lookup time: arrange for them to be deleted immediately.
  */
-static int simple_delete_dentry(struct dentry *dentry)
+static int simple_delete_dentry(const struct dentry *dentry)
 {
         return 1;
 }
@@ -54,7 +59,7 @@ struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, struct na
 
         if (dentry->d_name.len > NAME_MAX)
                 return ERR_PTR(-ENAMETOOLONG);
-        dentry->d_op = &simple_dentry_operations;
+        d_set_d_op(dentry, &simple_dentry_operations);
         d_add(dentry, NULL);
         return NULL;
 }
@@ -76,7 +81,8 @@ int dcache_dir_close(struct inode *inode, struct file *file)
 
 loff_t dcache_dir_lseek(struct file *file, loff_t offset, int origin)
 {
-        mutex_lock(&file->f_path.dentry->d_inode->i_mutex);
+        struct dentry *dentry = file->f_path.dentry;
+        mutex_lock(&dentry->d_inode->i_mutex);
         switch (origin) {
                 case 1:
                         offset += file->f_pos;
@@ -84,7 +90,7 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int origin)
                         if (offset >= 0)
                                 break;
                 default:
-                        mutex_unlock(&file->f_path.dentry->d_inode->i_mutex);
+                        mutex_unlock(&dentry->d_inode->i_mutex);
                         return -EINVAL;
         }
         if (offset != file->f_pos) {
@@ -94,21 +100,24 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int origin)
                         struct dentry *cursor = file->private_data;
                         loff_t n = file->f_pos - 2;
 
-                        spin_lock(&dcache_lock);
+                        spin_lock(&dentry->d_lock);
+                        /* d_lock not required for cursor */
                         list_del(&cursor->d_u.d_child);
-                        p = file->f_path.dentry->d_subdirs.next;
-                        while (n && p != &file->f_path.dentry->d_subdirs) {
+                        p = dentry->d_subdirs.next;
+                        while (n && p != &dentry->d_subdirs) {
                                 struct dentry *next;
                                 next = list_entry(p, struct dentry, d_u.d_child);
-                                if (!d_unhashed(next) && next->d_inode)
+                                spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
+                                if (simple_positive(next))
                                         n--;
+                                spin_unlock(&next->d_lock);
                                 p = p->next;
                         }
                         list_add_tail(&cursor->d_u.d_child, p);
-                        spin_unlock(&dcache_lock);
+                        spin_unlock(&dentry->d_lock);
                 }
         }
-        mutex_unlock(&file->f_path.dentry->d_inode->i_mutex);
+        mutex_unlock(&dentry->d_inode->i_mutex);
         return offset;
 }
 
@@ -148,29 +157,35 @@ int dcache_readdir(struct file * filp, void * dirent, filldir_t filldir)
                         i++;
                         /* fallthrough */
                 default:
-                        spin_lock(&dcache_lock);
+                        spin_lock(&dentry->d_lock);
                         if (filp->f_pos == 2)
                                 list_move(q, &dentry->d_subdirs);
 
                         for (p=q->next; p != &dentry->d_subdirs; p=p->next) {
                                 struct dentry *next;
                                 next = list_entry(p, struct dentry, d_u.d_child);
-                                if (d_unhashed(next) || !next->d_inode)
+                                spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
+                                if (!simple_positive(next)) {
+                                        spin_unlock(&next->d_lock);
                                         continue;
+                                }
 
-                                spin_unlock(&dcache_lock);
+                                spin_unlock(&next->d_lock);
+                                spin_unlock(&dentry->d_lock);
                                 if (filldir(dirent, next->d_name.name, 
                                             next->d_name.len, filp->f_pos, 
                                             next->d_inode->i_ino, 
                                             dt_type(next->d_inode)) < 0)
                                         return 0;
-                                spin_lock(&dcache_lock);
+                                spin_lock(&dentry->d_lock);
+                                spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
                                 /* next is still alive */
                                 list_move(q, p);
+                                spin_unlock(&next->d_lock);
                                 p = q;
                                 filp->f_pos++;
                         }
-                        spin_unlock(&dcache_lock);
+                        spin_unlock(&dentry->d_lock);
         }
         return 0;
 }
@@ -259,23 +274,23 @@ int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *den
         return 0;
 }
 
-static inline int simple_positive(struct dentry *dentry)
-{
-        return dentry->d_inode && !d_unhashed(dentry);
-}
-
 int simple_empty(struct dentry *dentry)
 {
         struct dentry *child;
         int ret = 0;
 
-        spin_lock(&dcache_lock);
-        list_for_each_entry(child, &dentry->d_subdirs, d_u.d_child)
-                if (simple_positive(child))
+        spin_lock(&dentry->d_lock);
+        list_for_each_entry(child, &dentry->d_subdirs, d_u.d_child) {
+                spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
+                if (simple_positive(child)) {
+                        spin_unlock(&child->d_lock);
                         goto out;
+                }
+                spin_unlock(&child->d_lock);
+        }
         ret = 1;
 out:
-        spin_unlock(&dcache_lock);
+        spin_unlock(&dentry->d_lock);
         return ret;
 }
 
diff --git a/fs/locks.c b/fs/locks.c
index 8729347bcd1a..08415b2a6d36 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1389,7 +1389,7 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp)
                 if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0))
                         goto out;
                 if ((arg == F_WRLCK)
-                    && ((atomic_read(&dentry->d_count) > 1)
+                    && ((dentry->d_count > 1)
                         || (atomic_read(&inode->i_count) > 1)))
                         goto out;
         }
diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c
index 409dfd65e9a1..f9ddf0c388c8 100644
--- a/fs/logfs/dir.c
+++ b/fs/logfs/dir.c
@@ -555,9 +555,11 @@ static int logfs_symlink(struct inode *dir, struct dentry *dentry,
         return __logfs_create(dir, dentry, inode, target, destlen);
 }
 
-static int logfs_permission(struct inode *inode, int mask)
+static int logfs_permission(struct inode *inode, int mask, unsigned int flags)
 {
-        return generic_permission(inode, mask, NULL);
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+        return generic_permission(inode, mask, flags, NULL);
 }
 
 static int logfs_link(struct dentry *old_dentry, struct inode *dir,
diff --git a/fs/logfs/inode.c b/fs/logfs/inode.c
index d8c71ece098f..03b8c240aeda 100644
--- a/fs/logfs/inode.c
+++ b/fs/logfs/inode.c
@@ -141,13 +141,20 @@ struct inode *logfs_safe_iget(struct super_block *sb, ino_t ino, int *is_cached)
         return __logfs_iget(sb, ino);
 }
 
+static void logfs_i_callback(struct rcu_head *head)
+{
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
+        kmem_cache_free(logfs_inode_cache, logfs_inode(inode));
+}
+
 static void __logfs_destroy_inode(struct inode *inode)
 {
         struct logfs_inode *li = logfs_inode(inode);
 
         BUG_ON(li->li_block);
         list_del(&li->li_freeing_list);
-        kmem_cache_free(logfs_inode_cache, li);
+        call_rcu(&inode->i_rcu, logfs_i_callback);
 }
 
 static void logfs_destroy_inode(struct inode *inode)
diff --git a/fs/logfs/journal.c b/fs/logfs/journal.c
index f46ee8b0e135..9da29706f91c 100644
--- a/fs/logfs/journal.c
+++ b/fs/logfs/journal.c
@@ -828,7 +828,7 @@ void do_logfs_journal_wl_pass(struct super_block *sb)
                 super->s_journal_seg[i] = segno;
                 super->s_journal_ec[i] = ec;
                 logfs_set_segment_reserved(sb, segno);
-                err = btree_insert32(head, segno, (void *)1, GFP_KERNEL);
+                err = btree_insert32(head, segno, (void *)1, GFP_NOFS);
                 BUG_ON(err); /* mempool should prevent this */
                 err = logfs_erase_segment(sb, segno, 1);
                 BUG_ON(err); /* FIXME: remount-ro would be nicer */
diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c
index 6127baf0e188..ee99a9f5dfd3 100644
--- a/fs/logfs/readwrite.c
+++ b/fs/logfs/readwrite.c
@@ -1994,6 +1994,9 @@ static int do_write_inode(struct inode *inode)
 
         /* FIXME: transaction is part of logfs_block now.  Is that enough? */
         err = logfs_write_buf(master_inode, page, 0);
+        if (err)
+                move_page_to_inode(inode, page);
+
         logfs_put_write_page(page);
         return err;
 }
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index fb2020858a34..ae0b83f476a6 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -68,11 +68,18 @@ static struct inode *minix_alloc_inode(struct super_block *sb)
         return &ei->vfs_inode;
 }
 
-static void minix_destroy_inode(struct inode *inode)
+static void minix_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(minix_inode_cachep, minix_i(inode));
 }
 
+static void minix_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, minix_i_callback);
+}
+
 static void init_once(void *foo)
 {
         struct minix_inode_info *ei = (struct minix_inode_info *) foo;
diff --git a/fs/minix/namei.c b/fs/minix/namei.c
index c0d35a3accef..1b9e07728a9f 100644
--- a/fs/minix/namei.c
+++ b/fs/minix/namei.c
@@ -23,7 +23,7 @@ static struct dentry *minix_lookup(struct inode * dir, struct dentry *dentry, st
         struct inode * inode = NULL;
         ino_t ino;
 
-        dentry->d_op = dir->i_sb->s_root->d_op;
+        d_set_d_op(dentry, dir->i_sb->s_root->d_op);
 
         if (dentry->d_name.len > minix_sb(dir->i_sb)->s_namelen)
                 return ERR_PTR(-ENAMETOOLONG);
diff --git a/fs/namei.c b/fs/namei.c
index 5362af9b7372..24ece10470b6 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -169,8 +169,8 @@ EXPORT_SYMBOL(putname);
 /*
  * This does basic POSIX ACL permission checking
  */
-static int acl_permission_check(struct inode *inode, int mask,
-                int (*check_acl)(struct inode *inode, int mask))
+static int acl_permission_check(struct inode *inode, int mask, unsigned int flags,
+                int (*check_acl)(struct inode *inode, int mask, unsigned int flags))
 {
         umode_t                 mode = inode->i_mode;
 
@@ -180,7 +180,7 @@ static int acl_permission_check(struct inode *inode, int mask,
                 mode >>= 6;
         else {
                 if (IS_POSIXACL(inode) && (mode & S_IRWXG) && check_acl) {
-                        int error = check_acl(inode, mask);
+                        int error = check_acl(inode, mask, flags);
                         if (error != -EAGAIN)
                                 return error;
                 }
@@ -198,25 +198,30 @@ static int acl_permission_check(struct inode *inode, int mask,
 }
 
 /**
- * generic_permission  -  check for access rights on a Posix-like filesystem
+ * generic_permission -  check for access rights on a Posix-like filesystem
  * @inode:      inode to check access rights for
  * @mask:       right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
  * @check_acl:  optional callback to check for Posix ACLs
+ * @flags:      IPERM_FLAG_ flags.
  *
  * Used to check for read/write/execute permissions on a file.
  * We use "fsuid" for this, letting us set arbitrary permissions
  * for filesystem access without changing the "normal" uids which
- * are used for other things..
+ * are used for other things.
+ *
+ * generic_permission is rcu-walk aware. It returns -ECHILD in case an rcu-walk
+ * request cannot be satisfied (eg. requires blocking or too much complexity).
+ * It would then be called again in ref-walk mode.
  */
-int generic_permission(struct inode *inode, int mask,
-                int (*check_acl)(struct inode *inode, int mask))
+int generic_permission(struct inode *inode, int mask, unsigned int flags,
+        int (*check_acl)(struct inode *inode, int mask, unsigned int flags))
 {
         int ret;
 
         /*
          * Do the basic POSIX ACL permission checks.
          */
-        ret = acl_permission_check(inode, mask, check_acl);
+        ret = acl_permission_check(inode, mask, flags, check_acl);
         if (ret != -EACCES)
                 return ret;
 
@@ -271,9 +276,10 @@ int inode_permission(struct inode *inode, int mask)
         }
 
         if (inode->i_op->permission)
-                retval = inode->i_op->permission(inode, mask);
+                retval = inode->i_op->permission(inode, mask, 0);
         else
-                retval = generic_permission(inode, mask, inode->i_op->check_acl);
+                retval = generic_permission(inode, mask, 0,
+                                inode->i_op->check_acl);
 
         if (retval)
                 return retval;
@@ -362,6 +368,18 @@ void path_get(struct path *path)
 EXPORT_SYMBOL(path_get);
 
 /**
+ * path_get_long - get a long reference to a path
+ * @path: path to get the reference to
+ *
+ * Given a path increment the reference count to the dentry and the vfsmount.
+ */
+void path_get_long(struct path *path)
+{
+        mntget_long(path->mnt);
+        dget(path->dentry);
+}
+
+/**
  * path_put - put a reference to a path
  * @path: path to put the reference to
  *
@@ -375,6 +393,185 @@ void path_put(struct path *path)
 EXPORT_SYMBOL(path_put);
 
 /**
+ * path_put_long - put a long reference to a path
+ * @path: path to put the reference to
+ *
+ * Given a path decrement the reference count to the dentry and the vfsmount.
+ */
+void path_put_long(struct path *path)
+{
+        dput(path->dentry);
+        mntput_long(path->mnt);
+}
+
+/**
+ * nameidata_drop_rcu - drop this nameidata out of rcu-walk
+ * @nd: nameidata pathwalk data to drop
+ * Returns: 0 on success, -ECHILD on failure
+ *
+ * Path walking has 2 modes, rcu-walk and ref-walk (see
+ * Documentation/filesystems/path-lookup.txt). __drop_rcu* functions attempt
+ * to drop out of rcu-walk mode and take normal reference counts on dentries
+ * and vfsmounts to transition to rcu-walk mode. __drop_rcu* functions take
+ * refcounts at the last known good point before rcu-walk got stuck, so
+ * ref-walk may continue from there. If this is not successful (eg. a seqcount
+ * has changed), then failure is returned and path walk restarts from the
+ * beginning in ref-walk mode.
+ *
+ * nameidata_drop_rcu attempts to drop the current nd->path and nd->root into
+ * ref-walk. Must be called from rcu-walk context.
+ */
+static int nameidata_drop_rcu(struct nameidata *nd)
+{
+        struct fs_struct *fs = current->fs;
+        struct dentry *dentry = nd->path.dentry;
+
+        BUG_ON(!(nd->flags & LOOKUP_RCU));
+        if (nd->root.mnt) {
+                spin_lock(&fs->lock);
+                if (nd->root.mnt != fs->root.mnt ||
+                                nd->root.dentry != fs->root.dentry)
+                        goto err_root;
+        }
+        spin_lock(&dentry->d_lock);
+        if (!__d_rcu_to_refcount(dentry, nd->seq))
+                goto err;
+        BUG_ON(nd->inode != dentry->d_inode);
+        spin_unlock(&dentry->d_lock);
+        if (nd->root.mnt) {
+                path_get(&nd->root);
+                spin_unlock(&fs->lock);
+        }
+        mntget(nd->path.mnt);
+
+        rcu_read_unlock();
+        br_read_unlock(vfsmount_lock);
+        nd->flags &= ~LOOKUP_RCU;
+        return 0;
+err:
+        spin_unlock(&dentry->d_lock);
+err_root:
+        if (nd->root.mnt)
+                spin_unlock(&fs->lock);
+        return -ECHILD;
+}
+
+/* Try to drop out of rcu-walk mode if we were in it, otherwise do nothing.  */
+static inline int nameidata_drop_rcu_maybe(struct nameidata *nd)
+{
+        if (nd->flags & LOOKUP_RCU)
+                return nameidata_drop_rcu(nd);
+        return 0;
+}
+
+/**
+ * nameidata_dentry_drop_rcu - drop nameidata and dentry out of rcu-walk
+ * @nd: nameidata pathwalk data to drop
+ * @dentry: dentry to drop
+ * Returns: 0 on success, -ECHILD on failure
+ *
+ * nameidata_dentry_drop_rcu attempts to drop the current nd->path and nd->root,
+ * and dentry into ref-walk. @dentry must be a path found by a do_lookup call on
+ * @nd. Must be called from rcu-walk context.
+ */
+static int nameidata_dentry_drop_rcu(struct nameidata *nd, struct dentry *dentry)
+{
+        struct fs_struct *fs = current->fs;
+        struct dentry *parent = nd->path.dentry;
+
+        BUG_ON(!(nd->flags & LOOKUP_RCU));
+        if (nd->root.mnt) {
+                spin_lock(&fs->lock);
+                if (nd->root.mnt != fs->root.mnt ||
+                                nd->root.dentry != fs->root.dentry)
+                        goto err_root;
+        }
+        spin_lock(&parent->d_lock);
+        spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
+        if (!__d_rcu_to_refcount(dentry, nd->seq))
+                goto err;
+        /*
+         * If the sequence check on the child dentry passed, then the child has
+         * not been removed from its parent. This means the parent dentry must
+         * be valid and able to take a reference at this point.
+         */
+        BUG_ON(!IS_ROOT(dentry) && dentry->d_parent != parent);
+        BUG_ON(!parent->d_count);
+        parent->d_count++;
+        spin_unlock(&dentry->d_lock);
+        spin_unlock(&parent->d_lock);
+        if (nd->root.mnt) {
+                path_get(&nd->root);
+                spin_unlock(&fs->lock);
+        }
+        mntget(nd->path.mnt);
+
+        rcu_read_unlock();
+        br_read_unlock(vfsmount_lock);
+        nd->flags &= ~LOOKUP_RCU;
+        return 0;
+err:
+        spin_unlock(&dentry->d_lock);
+        spin_unlock(&parent->d_lock);
+err_root:
+        if (nd->root.mnt)
+                spin_unlock(&fs->lock);
+        return -ECHILD;
+}
+
+/* Try to drop out of rcu-walk mode if we were in it, otherwise do nothing.  */
+static inline int nameidata_dentry_drop_rcu_maybe(struct nameidata *nd, struct dentry *dentry)
+{
+        if (nd->flags & LOOKUP_RCU)
+                return nameidata_dentry_drop_rcu(nd, dentry);
+        return 0;
+}
+
+/**
+ * nameidata_drop_rcu_last - drop nameidata ending path walk out of rcu-walk
+ * @nd: nameidata pathwalk data to drop
+ * Returns: 0 on success, -ECHILD on failure
+ *
+ * nameidata_drop_rcu_last attempts to drop the current nd->path into ref-walk.
+ * nd->path should be the final element of the lookup, so nd->root is discarded.
+ * Must be called from rcu-walk context.
+ */
+static int nameidata_drop_rcu_last(struct nameidata *nd)
+{
+        struct dentry *dentry = nd->path.dentry;
+
+        BUG_ON(!(nd->flags & LOOKUP_RCU));
+        nd->flags &= ~LOOKUP_RCU;
+        nd->root.mnt = NULL;
+        spin_lock(&dentry->d_lock);
+        if (!__d_rcu_to_refcount(dentry, nd->seq))
+                goto err_unlock;
+        BUG_ON(nd->inode != dentry->d_inode);
+        spin_unlock(&dentry->d_lock);
+
+        mntget(nd->path.mnt);
+
+        rcu_read_unlock();
+        br_read_unlock(vfsmount_lock);
+
+        return 0;
+
+err_unlock:
+        spin_unlock(&dentry->d_lock);
+        rcu_read_unlock();
+        br_read_unlock(vfsmount_lock);
+        return -ECHILD;
+}
+
+/* Try to drop out of rcu-walk mode if we were in it, otherwise do nothing.  */
+static inline int nameidata_drop_rcu_last_maybe(struct nameidata *nd)
+{
+        if (likely(nd->flags & LOOKUP_RCU))
+                return nameidata_drop_rcu_last(nd);
+        return 0;
+}
+
+/**
  * release_open_intent - free up open intent resources
  * @nd: pointer to nameidata
  */
@@ -386,10 +583,26 @@ void release_open_intent(struct nameidata *nd)
                 fput(nd->intent.open.file);
 }
 
+static int d_revalidate(struct dentry *dentry, struct nameidata *nd)
+{
+        int status;
+
+        status = dentry->d_op->d_revalidate(dentry, nd);
+        if (status == -ECHILD) {
+                if (nameidata_dentry_drop_rcu(nd, dentry))
+                        return status;
+                status = dentry->d_op->d_revalidate(dentry, nd);
+        }
+
+        return status;
+}
+
 static inline struct dentry *
 do_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
-        int status = dentry->d_op->d_revalidate(dentry, nd);
+        int status;
+
+        status = d_revalidate(dentry, nd);
         if (unlikely(status <= 0)) {
                 /*
                  * The dentry failed validation.
@@ -397,19 +610,36 @@ do_revalidate(struct dentry *dentry, struct nameidata *nd)
                  * the dentry otherwise d_revalidate is asking us
                  * to return a fail status.
                  */
-                if (!status) {
+                if (status < 0) {
+                        /* If we're in rcu-walk, we don't have a ref */
+                        if (!(nd->flags & LOOKUP_RCU))
+                                dput(dentry);
+                        dentry = ERR_PTR(status);
+
+                } else {
+                        /* Don't d_invalidate in rcu-walk mode */
+                        if (nameidata_dentry_drop_rcu_maybe(nd, dentry))
+                                return ERR_PTR(-ECHILD);
                         if (!d_invalidate(dentry)) {
                                 dput(dentry);
                                 dentry = NULL;
                         }
-                } else {
-                        dput(dentry);
-                        dentry = ERR_PTR(status);
                 }
         }
         return dentry;
 }
 
+static inline int need_reval_dot(struct dentry *dentry)
+{
+        if (likely(!(dentry->d_flags & DCACHE_OP_REVALIDATE)))
+                return 0;
+
+        if (likely(!(dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT)))
+                return 0;
+
+        return 1;
+}
+
 /*
  * force_reval_path - force revalidation of a dentry
  *
@@ -433,13 +663,12 @@ force_reval_path(struct path *path, struct nameidata *nd)
 
         /*
          * only check on filesystems where it's possible for the dentry to
-         * become stale. It's assumed that if this flag is set then the
-         * d_revalidate op will also be defined.
+         * become stale.
          */
-        if (!(dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT))
+        if (!need_reval_dot(dentry))
                 return 0;
 
-        status = dentry->d_op->d_revalidate(dentry, nd);
+        status = d_revalidate(dentry, nd);
         if (status > 0)
                 return 0;
 
@@ -459,26 +688,27 @@ force_reval_path(struct path *path, struct nameidata *nd)
  * short-cut DAC fails, then call ->permission() to do more
  * complete permission check.
  */
-static int exec_permission(struct inode *inode)
+static inline int exec_permission(struct inode *inode, unsigned int flags)
 {
         int ret;
 
         if (inode->i_op->permission) {
-                ret = inode->i_op->permission(inode, MAY_EXEC);
-                if (!ret)
-                        goto ok;
-                return ret;
+                ret = inode->i_op->permission(inode, MAY_EXEC, flags);
+        } else {
+                ret = acl_permission_check(inode, MAY_EXEC, flags,
+                                inode->i_op->check_acl);
         }
-        ret = acl_permission_check(inode, MAY_EXEC, inode->i_op->check_acl);
-        if (!ret)
+        if (likely(!ret))
                 goto ok;
+        if (ret == -ECHILD)
+                return ret;
 
         if (capable(CAP_DAC_OVERRIDE) || capable(CAP_DAC_READ_SEARCH))
                 goto ok;
 
         return ret;
 ok:
-        return security_inode_permission(inode, MAY_EXEC);
+        return security_inode_exec_permission(inode, flags);
 }
 
 static __always_inline void set_root(struct nameidata *nd)
@@ -489,8 +719,23 @@ static __always_inline void set_root(struct nameidata *nd)
 
 static int link_path_walk(const char *, struct nameidata *);
 
+static __always_inline void set_root_rcu(struct nameidata *nd)
+{
+        if (!nd->root.mnt) {
+                struct fs_struct *fs = current->fs;
+                unsigned seq;
+
+                do {
+                        seq = read_seqcount_begin(&fs->seq);
+                        nd->root = fs->root;
+                } while (read_seqcount_retry(&fs->seq, seq));
+        }
+}
+
 static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *link)
 {
+        int ret;
+
         if (IS_ERR(link))
                 goto fail;
 
@@ -500,8 +745,10 @@ static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *l
                 nd->path = nd->root;
                 path_get(&nd->root);
         }
+        nd->inode = nd->path.dentry->d_inode;
 
-        return link_path_walk(link, nd);
+        ret = link_path_walk(link, nd);
+        return ret;
 fail:
         path_put(&nd->path);
         return PTR_ERR(link);
@@ -516,11 +763,12 @@ static void path_put_conditional(struct path *path, struct nameidata *nd)
 
 static inline void path_to_nameidata(struct path *path, struct nameidata *nd)
 {
-        dput(nd->path.dentry);
-        if (nd->path.mnt != path->mnt) {
-                mntput(nd->path.mnt);
-                nd->path.mnt = path->mnt;
+        if (!(nd->flags & LOOKUP_RCU)) {
+                dput(nd->path.dentry);
+                if (nd->path.mnt != path->mnt)
+                        mntput(nd->path.mnt);
         }
+        nd->path.mnt = path->mnt;
         nd->path.dentry = path->dentry;
 }
 
@@ -535,9 +783,11 @@ __do_follow_link(struct path *path, struct nameidata *nd, void **p)
 
         if (path->mnt != nd->path.mnt) {
                 path_to_nameidata(path, nd);
+                nd->inode = nd->path.dentry->d_inode;
                 dget(dentry);
         }
         mntget(path->mnt);
+
         nd->last_type = LAST_BIND;
         *p = dentry->d_inode->i_op->follow_link(dentry, nd);
         error = PTR_ERR(*p);
@@ -591,6 +841,20 @@ loop:
         return err;
 }
 
+static int follow_up_rcu(struct path *path)
+{
+        struct vfsmount *parent;
+        struct dentry *mountpoint;
+
+        parent = path->mnt->mnt_parent;
+        if (parent == path->mnt)
+                return 0;
+        mountpoint = path->mnt->mnt_mountpoint;
+        path->dentry = mountpoint;
+        path->mnt = parent;
+        return 1;
+}
+
 int follow_up(struct path *path)
 {
         struct vfsmount *parent;
@@ -612,9 +876,24 @@ int follow_up(struct path *path)
         return 1;
 }
 
-/* no need for dcache_lock, as serialization is taken care in
- * namespace.c
+/*
+ * serialization is taken care of in namespace.c
  */
+static void __follow_mount_rcu(struct nameidata *nd, struct path *path,
+                                struct inode **inode)
+{
+        while (d_mountpoint(path->dentry)) {
+                struct vfsmount *mounted;
+                mounted = __lookup_mnt(path->mnt, path->dentry, 1);
+                if (!mounted)
+                        return;
+                path->mnt = mounted;
+                path->dentry = mounted->mnt_root;
+                nd->seq = read_seqcount_begin(&path->dentry->d_seq);
+                *inode = path->dentry->d_inode;
+        }
+}
+
 static int __follow_mount(struct path *path)
 {
         int res = 0;
@@ -645,9 +924,6 @@ static void follow_mount(struct path *path)
         }
 }
 
-/* no need for dcache_lock, as serialization is taken care in
- * namespace.c
- */
 int follow_down(struct path *path)
 {
         struct vfsmount *mounted;
@@ -663,7 +939,42 @@ int follow_down(struct path *path)
         return 0;
 }
 
-static __always_inline void follow_dotdot(struct nameidata *nd)
+static int follow_dotdot_rcu(struct nameidata *nd)
+{
+        struct inode *inode = nd->inode;
+
+        set_root_rcu(nd);
+
+        while(1) {
+                if (nd->path.dentry == nd->root.dentry &&
+                    nd->path.mnt == nd->root.mnt) {
+                        break;
+                }
+                if (nd->path.dentry != nd->path.mnt->mnt_root) {
+                        struct dentry *old = nd->path.dentry;
+                        struct dentry *parent = old->d_parent;
+                        unsigned seq;
+
+                        seq = read_seqcount_begin(&parent->d_seq);
+                        if (read_seqcount_retry(&old->d_seq, nd->seq))
+                                return -ECHILD;
+                        inode = parent->d_inode;
+                        nd->path.dentry = parent;
+                        nd->seq = seq;
+                        break;
+                }
+                if (!follow_up_rcu(&nd->path))
+                        break;
+                nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
+                inode = nd->path.dentry->d_inode;
+        }
+        __follow_mount_rcu(nd, &nd->path, &inode);
+        nd->inode = inode;
+
+        return 0;
+}
+
+static void follow_dotdot(struct nameidata *nd)
 {
         set_root(nd);
 
@@ -684,6 +995,7 @@ static __always_inline void follow_dotdot(struct nameidata *nd)
                         break;
         }
         follow_mount(&nd->path);
+        nd->inode = nd->path.dentry->d_inode;
 }
 
 /*
@@ -721,17 +1033,17 @@ static struct dentry *d_alloc_and_lookup(struct dentry *parent,
  *  It _is_ time-critical.
  */
 static int do_lookup(struct nameidata *nd, struct qstr *name,
-                     struct path *path)
+                        struct path *path, struct inode **inode)
 {
         struct vfsmount *mnt = nd->path.mnt;
-        struct dentry *dentry, *parent;
+        struct dentry *dentry, *parent = nd->path.dentry;
         struct inode *dir;
         /*
          * See if the low-level filesystem might want
          * to use its own hash..
          */
-        if (nd->path.dentry->d_op && nd->path.dentry->d_op->d_hash) {
-                int err = nd->path.dentry->d_op->d_hash(nd->path.dentry, name);
+        if (unlikely(parent->d_flags & DCACHE_OP_HASH)) {
+                int err = parent->d_op->d_hash(parent, nd->inode, name);
                 if (err < 0)
                         return err;
         }
@@ -741,21 +1053,44 @@ static int do_lookup(struct nameidata *nd, struct qstr *name,
          * of a false negative due to a concurrent rename, we're going to
          * do the non-racy lookup, below.
          */
-        dentry = __d_lookup(nd->path.dentry, name);
-        if (!dentry)
-                goto need_lookup;
+        if (nd->flags & LOOKUP_RCU) {
+                unsigned seq;
+
+                *inode = nd->inode;
+                dentry = __d_lookup_rcu(parent, name, &seq, inode);
+                if (!dentry) {
+                        if (nameidata_drop_rcu(nd))
+                                return -ECHILD;
+                        goto need_lookup;
+                }
+                /* Memory barrier in read_seqcount_begin of child is enough */
+                if (__read_seqcount_retry(&parent->d_seq, nd->seq))
+                        return -ECHILD;
+
+                nd->seq = seq;
+                if (dentry->d_flags & DCACHE_OP_REVALIDATE)
+                        goto need_revalidate;
+                path->mnt = mnt;
+                path->dentry = dentry;
+                __follow_mount_rcu(nd, path, inode);
+        } else {
+                dentry = __d_lookup(parent, name);
+                if (!dentry)
+                        goto need_lookup;
 found:
-        if (dentry->d_op && dentry->d_op->d_revalidate)
-                goto need_revalidate;
+                if (dentry->d_flags & DCACHE_OP_REVALIDATE)
+                        goto need_revalidate;
 done:
-        path->mnt = mnt;
-        path->dentry = dentry;
-        __follow_mount(path);
+                path->mnt = mnt;
+                path->dentry = dentry;
+                __follow_mount(path);
+                *inode = path->dentry->d_inode;
+        }
         return 0;
 
 need_lookup:
-        parent = nd->path.dentry;
         dir = parent->d_inode;
+        BUG_ON(nd->inode != dir);
 
         mutex_lock(&dir->i_mutex);
         /*
@@ -817,7 +1152,6 @@ static inline int follow_on_final(struct inode *inode, unsigned lookup_flags)
 static int link_path_walk(const char *name, struct nameidata *nd)
 {
         struct path next;
-        struct inode *inode;
         int err;
         unsigned int lookup_flags = nd->flags;
         
@@ -826,18 +1160,28 @@ static int link_path_walk(const char *name, struct nameidata *nd)
         if (!*name)
                 goto return_reval;
 
-        inode = nd->path.dentry->d_inode;
         if (nd->depth)
                 lookup_flags = LOOKUP_FOLLOW | (nd->flags & LOOKUP_CONTINUE);
 
         /* At this point we know we have a real path component. */
         for(;;) {
+                struct inode *inode;
                 unsigned long hash;
                 struct qstr this;
                 unsigned int c;
 
                 nd->flags |= LOOKUP_CONTINUE;
-                err = exec_permission(inode);
+                if (nd->flags & LOOKUP_RCU) {
+                        err = exec_permission(nd->inode, IPERM_FLAG_RCU);
+                        if (err == -ECHILD) {
+                                if (nameidata_drop_rcu(nd))
+                                        return -ECHILD;
+                                goto exec_again;
+                        }
+                } else {
+exec_again:
+                        err = exec_permission(nd->inode, 0);
+                }
                 if (err)
                         break;
 
@@ -868,37 +1212,44 @@ static int link_path_walk(const char *name, struct nameidata *nd)
                 if (this.name[0] == '.') switch (this.len) {
                         default:
                                 break;
-                        case 2: 
+                        case 2:
                                 if (this.name[1] != '.')
                                         break;
-                                follow_dotdot(nd);
-                                inode = nd->path.dentry->d_inode;
+                                if (nd->flags & LOOKUP_RCU) {
+                                        if (follow_dotdot_rcu(nd))
+                                                return -ECHILD;
+                                } else
+                                        follow_dotdot(nd);
                                 /* fallthrough */
                         case 1:
                                 continue;
                 }
                 /* This does the actual lookups.. */
-                err = do_lookup(nd, &this, &next);
+                err = do_lookup(nd, &this, &next, &inode);
                 if (err)
                         break;
-
                 err = -ENOENT;
-                inode = next.dentry->d_inode;
                 if (!inode)
                         goto out_dput;
 
                 if (inode->i_op->follow_link) {
+                        /* We commonly drop rcu-walk here */
+                        if (nameidata_dentry_drop_rcu_maybe(nd, next.dentry))
+                                return -ECHILD;
+                        BUG_ON(inode != next.dentry->d_inode);
                         err = do_follow_link(&next, nd);
                         if (err)
                                 goto return_err;
+                        nd->inode = nd->path.dentry->d_inode;
                         err = -ENOENT;
-                        inode = nd->path.dentry->d_inode;
-                        if (!inode)
+                        if (!nd->inode)
                                 break;
-                } else
+                } else {
                         path_to_nameidata(&next, nd);
+                        nd->inode = inode;
+                }
                 err = -ENOTDIR; 
-                if (!inode->i_op->lookup)
+                if (!nd->inode->i_op->lookup)
                         break;
                 continue;
                 /* here ends the main loop */
@@ -913,32 +1264,39 @@ last_component:
                 if (this.name[0] == '.') switch (this.len) {
                         default:
                                 break;
-                        case 2: 
+                        case 2:
                                 if (this.name[1] != '.')
                                         break;
-                                follow_dotdot(nd);
-                                inode = nd->path.dentry->d_inode;
+                                if (nd->flags & LOOKUP_RCU) {
+                                        if (follow_dotdot_rcu(nd))
+                                                return -ECHILD;
+                                } else
+                                        follow_dotdot(nd);
                                 /* fallthrough */
                         case 1:
                                 goto return_reval;
                 }
-                err = do_lookup(nd, &this, &next);
+                err = do_lookup(nd, &this, &next, &inode);
                 if (err)
                         break;
-                inode = next.dentry->d_inode;
                 if (follow_on_final(inode, lookup_flags)) {
+                        if (nameidata_dentry_drop_rcu_maybe(nd, next.dentry))
+                                return -ECHILD;
+                        BUG_ON(inode != next.dentry->d_inode);
                         err = do_follow_link(&next, nd);
                         if (err)
                                 goto return_err;
-                        inode = nd->path.dentry->d_inode;
-                } else
+                        nd->inode = nd->path.dentry->d_inode;
+                } else {
                         path_to_nameidata(&next, nd);
+                        nd->inode = inode;
+                }
                 err = -ENOENT;
-                if (!inode)
+                if (!nd->inode)
                         break;
                 if (lookup_flags & LOOKUP_DIRECTORY) {
                         err = -ENOTDIR; 
-                        if (!inode->i_op->lookup)
+                        if (!nd->inode->i_op->lookup)
                                 break;
                 }
                 goto return_base;
@@ -958,25 +1316,43 @@ return_reval:
                  * We bypassed the ordinary revalidation routines.
                  * We may need to check the cached dentry for staleness.
                  */
-                if (nd->path.dentry && nd->path.dentry->d_sb &&
-                    (nd->path.dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT)) {
-                        err = -ESTALE;
+                if (need_reval_dot(nd->path.dentry)) {
                         /* Note: we do not d_invalidate() */
-                        if (!nd->path.dentry->d_op->d_revalidate(
-                                        nd->path.dentry, nd))
+                        err = d_revalidate(nd->path.dentry, nd);
+                        if (!err)
+                                err = -ESTALE;
+                        if (err < 0)
                                 break;
                 }
 return_base:
+                if (nameidata_drop_rcu_last_maybe(nd))
+                        return -ECHILD;
                 return 0;
 out_dput:
-                path_put_conditional(&next, nd);
+                if (!(nd->flags & LOOKUP_RCU))
+                        path_put_conditional(&next, nd);
                 break;
         }
-        path_put(&nd->path);
+        if (!(nd->flags & LOOKUP_RCU))
+                path_put(&nd->path);
 return_err:
         return err;
 }
 
+static inline int path_walk_rcu(const char *name, struct nameidata *nd)
+{
+        current->total_link_count = 0;
+
+        return link_path_walk(name, nd);
+}
+
+static inline int path_walk_simple(const char *name, struct nameidata *nd)
+{
+        current->total_link_count = 0;
+
+        return link_path_walk(name, nd);
+}
+
 static int path_walk(const char *name, struct nameidata *nd)
 {
         struct path save = nd->path;
@@ -1002,6 +1378,93 @@ static int path_walk(const char *name, struct nameidata *nd)
         return result;
 }
 
+static void path_finish_rcu(struct nameidata *nd)
+{
+        if (nd->flags & LOOKUP_RCU) {
+                /* RCU dangling. Cancel it. */
+                nd->flags &= ~LOOKUP_RCU;
+                nd->root.mnt = NULL;
+                rcu_read_unlock();
+                br_read_unlock(vfsmount_lock);
+        }
+        if (nd->file)
+                fput(nd->file);
+}
+
+static int path_init_rcu(int dfd, const char *name, unsigned int flags, struct nameidata *nd)
+{
+        int retval = 0;
+        int fput_needed;
+        struct file *file;
+
+        nd->last_type = LAST_ROOT; /* if there are only slashes... */
+        nd->flags = flags | LOOKUP_RCU;
+        nd->depth = 0;
+        nd->root.mnt = NULL;
+        nd->file = NULL;
+
+        if (*name=='/') {
+                struct fs_struct *fs = current->fs;
+                unsigned seq;
+
+                br_read_lock(vfsmount_lock);
+                rcu_read_lock();
+
+                do {
+                        seq = read_seqcount_begin(&fs->seq);
+                        nd->root = fs->root;
+                        nd->path = nd->root;
+                        nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
+                } while (read_seqcount_retry(&fs->seq, seq));
+
+        } else if (dfd == AT_FDCWD) {
+                struct fs_struct *fs = current->fs;
+                unsigned seq;
+
+                br_read_lock(vfsmount_lock);
+                rcu_read_lock();
+
+                do {
+                        seq = read_seqcount_begin(&fs->seq);
+                        nd->path = fs->pwd;
+                        nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
+                } while (read_seqcount_retry(&fs->seq, seq));
+
+        } else {
+                struct dentry *dentry;
+
+                file = fget_light(dfd, &fput_needed);
+                retval = -EBADF;
+                if (!file)
+                        goto out_fail;
+
+                dentry = file->f_path.dentry;
+
+                retval = -ENOTDIR;
+                if (!S_ISDIR(dentry->d_inode->i_mode))
+                        goto fput_fail;
+
+                retval = file_permission(file, MAY_EXEC);
+                if (retval)
+                        goto fput_fail;
+
+                nd->path = file->f_path;
+                if (fput_needed)
+                        nd->file = file;
+
+                nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
+                br_read_lock(vfsmount_lock);
+                rcu_read_lock();
+        }
+        nd->inode = nd->path.dentry->d_inode;
+        return 0;
+
+fput_fail:
+        fput_light(file, fput_needed);
+out_fail:
+        return retval;
+}
+
 static int path_init(int dfd, const char *name, unsigned int flags, struct nameidata *nd)
 {
         int retval = 0;
@@ -1042,6 +1505,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, struct namei
 
                 fput_light(file, fput_needed);
         }
+        nd->inode = nd->path.dentry->d_inode;
         return 0;
 
 fput_fail:
@@ -1054,16 +1518,53 @@ out_fail:
 static int do_path_lookup(int dfd, const char *name,
                                 unsigned int flags, struct nameidata *nd)
 {
-        int retval = path_init(dfd, name, flags, nd);
-        if (!retval)
-                retval = path_walk(name, nd);
-        if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry &&
-                                nd->path.dentry->d_inode))
-                audit_inode(name, nd->path.dentry);
+        int retval;
+
+        /*
+         * Path walking is largely split up into 2 different synchronisation
+         * schemes, rcu-walk and ref-walk (explained in
+         * Documentation/filesystems/path-lookup.txt). These share much of the
+         * path walk code, but some things particularly setup, cleanup, and
+         * following mounts are sufficiently divergent that functions are
+         * duplicated. Typically there is a function foo(), and its RCU
+         * analogue, foo_rcu().
+         *
+         * -ECHILD is the error number of choice (just to avoid clashes) that
+         * is returned if some aspect of an rcu-walk fails. Such an error must
+         * be handled by restarting a traditional ref-walk (which will always
+         * be able to complete).
+         */
+        retval = path_init_rcu(dfd, name, flags, nd);
+        if (unlikely(retval))
+                return retval;
+        retval = path_walk_rcu(name, nd);
+        path_finish_rcu(nd);
         if (nd->root.mnt) {
                 path_put(&nd->root);
                 nd->root.mnt = NULL;
         }
+
+        if (unlikely(retval == -ECHILD || retval == -ESTALE)) {
+                /* slower, locked walk */
+                if (retval == -ESTALE)
+                        flags |= LOOKUP_REVAL;
+                retval = path_init(dfd, name, flags, nd);
+                if (unlikely(retval))
+                        return retval;
+                retval = path_walk(name, nd);
+                if (nd->root.mnt) {
+                        path_put(&nd->root);
+                        nd->root.mnt = NULL;
+                }
+        }
+
+        if (likely(!retval)) {
+                if (unlikely(!audit_dummy_context())) {
+                        if (nd->path.dentry && nd->inode)
+                                audit_inode(name, nd->path.dentry);
+                }
+        }
+
         return retval;
 }
 
@@ -1106,10 +1607,11 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
         path_get(&nd->path);
         nd->root = nd->path;
         path_get(&nd->root);
+        nd->inode = nd->path.dentry->d_inode;
 
         retval = path_walk(name, nd);
         if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry &&
-                                nd->path.dentry->d_inode))
+                                nd->inode))
                 audit_inode(name, nd->path.dentry);
 
         path_put(&nd->root);
@@ -1125,7 +1627,7 @@ static struct dentry *__lookup_hash(struct qstr *name,
         struct dentry *dentry;
         int err;
 
-        err = exec_permission(inode);
+        err = exec_permission(inode, 0);
         if (err)
                 return ERR_PTR(err);
 
@@ -1133,8 +1635,8 @@ static struct dentry *__lookup_hash(struct qstr *name,
          * See if the low-level filesystem might want
          * to use its own hash..
          */
-        if (base->d_op && base->d_op->d_hash) {
-                err = base->d_op->d_hash(base, name);
+        if (base->d_flags & DCACHE_OP_HASH) {
+                err = base->d_op->d_hash(base, inode, name);
                 dentry = ERR_PTR(err);
                 if (err < 0)
                         goto out;
@@ -1147,7 +1649,7 @@ static struct dentry *__lookup_hash(struct qstr *name,
          */
         dentry = d_lookup(base, name);
 
-        if (dentry && dentry->d_op && dentry->d_op->d_revalidate)
+        if (dentry && (dentry->d_flags & DCACHE_OP_REVALIDATE))
                 dentry = do_revalidate(dentry, nd);
 
         if (!dentry)
@@ -1490,6 +1992,7 @@ out_unlock:
         mutex_unlock(&dir->d_inode->i_mutex);
         dput(nd->path.dentry);
         nd->path.dentry = path->dentry;
+
         if (error)
                 return error;
         /* Don't check for write permission, don't truncate */
@@ -1584,6 +2087,9 @@ exit:
         return ERR_PTR(error);
 }
 
+/*
+ * Handle O_CREAT case for do_filp_open
+ */
 static struct file *do_last(struct nameidata *nd, struct path *path,
                             int open_flag, int acc_mode,
                             int mode, const char *pathname)
@@ -1597,50 +2103,25 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
                 follow_dotdot(nd);
                 dir = nd->path.dentry;
         case LAST_DOT:
-                if (nd->path.mnt->mnt_sb->s_type->fs_flags & FS_REVAL_DOT) {
-                        if (!dir->d_op->d_revalidate(dir, nd)) {
+                if (need_reval_dot(dir)) {
+                        error = d_revalidate(nd->path.dentry, nd);
+                        if (!error)
                                 error = -ESTALE;
+                        if (error < 0)
                                 goto exit;
-                        }
                 }
                 /* fallthrough */
         case LAST_ROOT:
-                if (open_flag & O_CREAT)
-                        goto exit;
-                /* fallthrough */
+                goto exit;
         case LAST_BIND:
                 audit_inode(pathname, dir);
                 goto ok;
         }
 
         /* trailing slashes? */
-        if (nd->last.name[nd->last.len]) {
-                if (open_flag & O_CREAT)
-                        goto exit;
-                nd->flags |= LOOKUP_DIRECTORY | LOOKUP_FOLLOW;
-        }
-
-        /* just plain open? */
-        if (!(open_flag & O_CREAT)) {
-                error = do_lookup(nd, &nd->last, path);
-                if (error)
-                        goto exit;
-                error = -ENOENT;
-                if (!path->dentry->d_inode)
-                        goto exit_dput;
-                if (path->dentry->d_inode->i_op->follow_link)
-                        return NULL;
-                error = -ENOTDIR;
-                if (nd->flags & LOOKUP_DIRECTORY) {
-                        if (!path->dentry->d_inode->i_op->lookup)
-                                goto exit_dput;
-                }
-                path_to_nameidata(path, nd);
-                audit_inode(pathname, nd->path.dentry);
-                goto ok;
-        }
+        if (nd->last.name[nd->last.len])
+                goto exit;
 
-        /* OK, it's O_CREAT */
         mutex_lock(&dir->d_inode->i_mutex);
 
         path->dentry = lookup_hash(nd);
@@ -1711,8 +2192,9 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
                 return NULL;
 
         path_to_nameidata(path, nd);
+        nd->inode = path->dentry->d_inode;
         error = -EISDIR;
-        if (S_ISDIR(path->dentry->d_inode->i_mode))
+        if (S_ISDIR(nd->inode->i_mode))
                 goto exit;
 ok:
         filp = finish_open(nd, open_flag, acc_mode);
@@ -1743,11 +2225,14 @@ struct file *do_filp_open(int dfd, const char *pathname,
         struct path path;
         int count = 0;
         int flag = open_to_namei_flags(open_flag);
-        int force_reval = 0;
+        int flags;
 
         if (!(open_flag & O_CREAT))
                 mode = 0;
 
+        /* Must never be set by userspace */
+        open_flag &= ~FMODE_NONOTIFY;
+
         /*
          * O_SYNC is implemented as __O_SYNC|O_DSYNC.  As many places only
          * check for O_DSYNC if the need any syncing at all we enforce it's
@@ -1769,54 +2254,84 @@ struct file *do_filp_open(int dfd, const char *pathname,
         if (open_flag & O_APPEND)
                 acc_mode |= MAY_APPEND;
 
-        /* find the parent */
-reval:
-        error = path_init(dfd, pathname, LOOKUP_PARENT, &nd);
+        flags = LOOKUP_OPEN;
+        if (open_flag & O_CREAT) {
+                flags |= LOOKUP_CREATE;
+                if (open_flag & O_EXCL)
+                        flags |= LOOKUP_EXCL;
+        }
+        if (open_flag & O_DIRECTORY)
+                flags |= LOOKUP_DIRECTORY;
+        if (!(open_flag & O_NOFOLLOW))
+                flags |= LOOKUP_FOLLOW;
+
+        filp = get_empty_filp();
+        if (!filp)
+                return ERR_PTR(-ENFILE);
+
+        filp->f_flags = open_flag;
+        nd.intent.open.file = filp;
+        nd.intent.open.flags = flag;
+        nd.intent.open.create_mode = mode;
+
+        if (open_flag & O_CREAT)
+                goto creat;
+
+        /* !O_CREAT, simple open */
+        error = do_path_lookup(dfd, pathname, flags, &nd);
+        if (unlikely(error))
+                goto out_filp;
+        error = -ELOOP;
+        if (!(nd.flags & LOOKUP_FOLLOW)) {
+                if (nd.inode->i_op->follow_link)
+                        goto out_path;
+        }
+        error = -ENOTDIR;
+        if (nd.flags & LOOKUP_DIRECTORY) {
+                if (!nd.inode->i_op->lookup)
+                        goto out_path;
+        }
+        audit_inode(pathname, nd.path.dentry);
+        filp = finish_open(&nd, open_flag, acc_mode);
+        return filp;
+
+creat:
+        /* OK, have to create the file. Find the parent. */
+        error = path_init_rcu(dfd, pathname,
+                        LOOKUP_PARENT | (flags & LOOKUP_REVAL), &nd);
         if (error)
-                return ERR_PTR(error);
-        if (force_reval)
-                nd.flags |= LOOKUP_REVAL;
+                goto out_filp;
+        error = path_walk_rcu(pathname, &nd);
+        path_finish_rcu(&nd);
+        if (unlikely(error == -ECHILD || error == -ESTALE)) {
+                /* slower, locked walk */
+                if (error == -ESTALE) {
+reval:
+                        flags |= LOOKUP_REVAL;
+                }
+                error = path_init(dfd, pathname,
+                                LOOKUP_PARENT | (flags & LOOKUP_REVAL), &nd);
+                if (error)
+                        goto out_filp;
 
-        current->total_link_count = 0;
-        error = link_path_walk(pathname, &nd);
-        if (error) {
-                filp = ERR_PTR(error);
-                goto out;
+                error = path_walk_simple(pathname, &nd);
         }
-        if (unlikely(!audit_dummy_context()) && (open_flag & O_CREAT))
+        if (unlikely(error))
+                goto out_filp;
+        if (unlikely(!audit_dummy_context()))
                 audit_inode(pathname, nd.path.dentry);
 
         /*
          * We have the parent and last component.
          */
-
-        error = -ENFILE;
-        filp = get_empty_filp();
-        if (filp == NULL)
-                goto exit_parent;
-        nd.intent.open.file = filp;
-        filp->f_flags = open_flag;
-        nd.intent.open.flags = flag;
-        nd.intent.open.create_mode = mode;
-        nd.flags &= ~LOOKUP_PARENT;
-        nd.flags |= LOOKUP_OPEN;
-        if (open_flag & O_CREAT) {
-                nd.flags |= LOOKUP_CREATE;
-                if (open_flag & O_EXCL)
-                        nd.flags |= LOOKUP_EXCL;
-        }
-        if (open_flag & O_DIRECTORY)
-                nd.flags |= LOOKUP_DIRECTORY;
-        if (!(open_flag & O_NOFOLLOW))
-                nd.flags |= LOOKUP_FOLLOW;
+        nd.flags = flags;
         filp = do_last(&nd, &path, open_flag, acc_mode, mode, pathname);
         while (unlikely(!filp)) { /* trailing symlink */
                 struct path holder;
-                struct inode *inode = path.dentry->d_inode;
                 void *cookie;
                 error = -ELOOP;
                 /* S_ISDIR part is a temporary automount kludge */
-                if (!(nd.flags & LOOKUP_FOLLOW) && !S_ISDIR(inode->i_mode))
+                if (!(nd.flags & LOOKUP_FOLLOW) && !S_ISDIR(nd.inode->i_mode))
                         goto exit_dput;
                 if (count++ == 32)
                         goto exit_dput;
@@ -1837,36 +2352,33 @@ reval:
                         goto exit_dput;
                 error = __do_follow_link(&path, &nd, &cookie);
                 if (unlikely(error)) {
+                        if (!IS_ERR(cookie) && nd.inode->i_op->put_link)
+                                nd.inode->i_op->put_link(path.dentry, &nd, cookie);
                         /* nd.path had been dropped */
-                        if (!IS_ERR(cookie) && inode->i_op->put_link)
-                                inode->i_op->put_link(path.dentry, &nd, cookie);
-                        path_put(&path);
-                        release_open_intent(&nd);
-                        filp = ERR_PTR(error);
-                        goto out;
+                        nd.path = path;
+                        goto out_path;
                 }
                 holder = path;
                 nd.flags &= ~LOOKUP_PARENT;
                 filp = do_last(&nd, &path, open_flag, acc_mode, mode, pathname);
-                if (inode->i_op->put_link)
-                        inode->i_op->put_link(holder.dentry, &nd, cookie);
+                if (nd.inode->i_op->put_link)
+                        nd.inode->i_op->put_link(holder.dentry, &nd, cookie);
                 path_put(&holder);
         }
 out:
         if (nd.root.mnt)
                 path_put(&nd.root);
-        if (filp == ERR_PTR(-ESTALE) && !force_reval) {
-                force_reval = 1;
+        if (filp == ERR_PTR(-ESTALE) && !(flags & LOOKUP_REVAL))
                 goto reval;
-        }
         return filp;
 
 exit_dput:
         path_put_conditional(&path, &nd);
+out_path:
+        path_put(&nd.path);
+out_filp:
         if (!IS_ERR(nd.intent.open.file))
                 release_open_intent(&nd);
-exit_parent:
-        path_put(&nd.path);
         filp = ERR_PTR(error);
         goto out;
 }
@@ -2127,12 +2639,10 @@ void dentry_unhash(struct dentry *dentry)
 {
         dget(dentry);
         shrink_dcache_parent(dentry);
-        spin_lock(&dcache_lock);
         spin_lock(&dentry->d_lock);
-        if (atomic_read(&dentry->d_count) == 2)
+        if (dentry->d_count == 2)
                 __d_drop(dentry);
         spin_unlock(&dentry->d_lock);
-        spin_unlock(&dcache_lock);
 }
 
 int vfs_rmdir(struct inode *dir, struct dentry *dentry)
diff --git a/fs/namespace.c b/fs/namespace.c
index 3dbfc072ec70..3ddfd9046c44 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -138,6 +138,64 @@ void mnt_release_group_id(struct vfsmount *mnt)
         mnt->mnt_group_id = 0;
 }
 
+/*
+ * vfsmount lock must be held for read
+ */
+static inline void mnt_add_count(struct vfsmount *mnt, int n)
+{
+#ifdef CONFIG_SMP
+        this_cpu_add(mnt->mnt_pcp->mnt_count, n);
+#else
+        preempt_disable();
+        mnt->mnt_count += n;
+        preempt_enable();
+#endif
+}
+
+static inline void mnt_set_count(struct vfsmount *mnt, int n)
+{
+#ifdef CONFIG_SMP
+        this_cpu_write(mnt->mnt_pcp->mnt_count, n);
+#else
+        mnt->mnt_count = n;
+#endif
+}
+
+/*
+ * vfsmount lock must be held for read
+ */
+static inline void mnt_inc_count(struct vfsmount *mnt)
+{
+        mnt_add_count(mnt, 1);
+}
+
+/*
+ * vfsmount lock must be held for read
+ */
+static inline void mnt_dec_count(struct vfsmount *mnt)
+{
+        mnt_add_count(mnt, -1);
+}
+
+/*
+ * vfsmount lock must be held for write
+ */
+unsigned int mnt_get_count(struct vfsmount *mnt)
+{
+#ifdef CONFIG_SMP
+        unsigned int count = atomic_read(&mnt->mnt_longrefs);
+        int cpu;
+
+        for_each_possible_cpu(cpu) {
+                count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_count;
+        }
+
+        return count;
+#else
+        return mnt->mnt_count;
+#endif
+}
+
 struct vfsmount *alloc_vfsmnt(const char *name)
 {
         struct vfsmount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL);
@@ -154,7 +212,17 @@ struct vfsmount *alloc_vfsmnt(const char *name)
                                 goto out_free_id;
                 }
 
-                atomic_set(&mnt->mnt_count, 1);
+#ifdef CONFIG_SMP
+                mnt->mnt_pcp = alloc_percpu(struct mnt_pcp);
+                if (!mnt->mnt_pcp)
+                        goto out_free_devname;
+
+                atomic_set(&mnt->mnt_longrefs, 1);
+#else
+                mnt->mnt_count = 1;
+                mnt->mnt_writers = 0;
+#endif
+
                 INIT_LIST_HEAD(&mnt->mnt_hash);
                 INIT_LIST_HEAD(&mnt->mnt_child);
                 INIT_LIST_HEAD(&mnt->mnt_mounts);
@@ -166,13 +234,6 @@ struct vfsmount *alloc_vfsmnt(const char *name)
 #ifdef CONFIG_FSNOTIFY
                 INIT_HLIST_HEAD(&mnt->mnt_fsnotify_marks);
 #endif
-#ifdef CONFIG_SMP
-                mnt->mnt_writers = alloc_percpu(int);
-                if (!mnt->mnt_writers)
-                        goto out_free_devname;
-#else
-                mnt->mnt_writers = 0;
-#endif
         }
         return mnt;
 
@@ -216,32 +277,32 @@ int __mnt_is_readonly(struct vfsmount *mnt)
 }
 EXPORT_SYMBOL_GPL(__mnt_is_readonly);
 
-static inline void inc_mnt_writers(struct vfsmount *mnt)
+static inline void mnt_inc_writers(struct vfsmount *mnt)
 {
 #ifdef CONFIG_SMP
-        (*per_cpu_ptr(mnt->mnt_writers, smp_processor_id()))++;
+        this_cpu_inc(mnt->mnt_pcp->mnt_writers);
 #else
         mnt->mnt_writers++;
 #endif
 }
 
-static inline void dec_mnt_writers(struct vfsmount *mnt)
+static inline void mnt_dec_writers(struct vfsmount *mnt)
 {
 #ifdef CONFIG_SMP
-        (*per_cpu_ptr(mnt->mnt_writers, smp_processor_id()))--;
+        this_cpu_dec(mnt->mnt_pcp->mnt_writers);
 #else
         mnt->mnt_writers--;
 #endif
 }
 
-static unsigned int count_mnt_writers(struct vfsmount *mnt)
+static unsigned int mnt_get_writers(struct vfsmount *mnt)
 {
 #ifdef CONFIG_SMP
         unsigned int count = 0;
         int cpu;
 
         for_each_possible_cpu(cpu) {
-                count += *per_cpu_ptr(mnt->mnt_writers, cpu);
+                count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_writers;
         }
 
         return count;
@@ -273,9 +334,9 @@ int mnt_want_write(struct vfsmount *mnt)
         int ret = 0;
 
         preempt_disable();
-        inc_mnt_writers(mnt);
+        mnt_inc_writers(mnt);
         /*
-         * The store to inc_mnt_writers must be visible before we pass
+         * The store to mnt_inc_writers must be visible before we pass
          * MNT_WRITE_HOLD loop below, so that the slowpath can see our
          * incremented count after it has set MNT_WRITE_HOLD.
          */
@@ -289,7 +350,7 @@ int mnt_want_write(struct vfsmount *mnt)
          */
         smp_rmb();
         if (__mnt_is_readonly(mnt)) {
-                dec_mnt_writers(mnt);
+                mnt_dec_writers(mnt);
                 ret = -EROFS;
                 goto out;
         }
@@ -317,7 +378,7 @@ int mnt_clone_write(struct vfsmount *mnt)
         if (__mnt_is_readonly(mnt))
                 return -EROFS;
         preempt_disable();
-        inc_mnt_writers(mnt);
+        mnt_inc_writers(mnt);
         preempt_enable();
         return 0;
 }
@@ -351,7 +412,7 @@ EXPORT_SYMBOL_GPL(mnt_want_write_file);
 void mnt_drop_write(struct vfsmount *mnt)
 {
         preempt_disable();
-        dec_mnt_writers(mnt);
+        mnt_dec_writers(mnt);
         preempt_enable();
 }
 EXPORT_SYMBOL_GPL(mnt_drop_write);
@@ -384,7 +445,7 @@ static int mnt_make_readonly(struct vfsmount *mnt)
          * MNT_WRITE_HOLD, so it can't be decremented by another CPU while
          * we're counting up here.
          */
-        if (count_mnt_writers(mnt) > 0)
+        if (mnt_get_writers(mnt) > 0)
                 ret = -EBUSY;
         else
                 mnt->mnt_flags |= MNT_READONLY;
@@ -418,7 +479,7 @@ void free_vfsmnt(struct vfsmount *mnt)
         kfree(mnt->mnt_devname);
         mnt_free_id(mnt);
 #ifdef CONFIG_SMP
-        free_percpu(mnt->mnt_writers);
+        free_percpu(mnt->mnt_pcp);
 #endif
         kmem_cache_free(mnt_cache, mnt);
 }
@@ -492,6 +553,27 @@ static void __touch_mnt_namespace(struct mnt_namespace *ns)
 }
 
 /*
+ * Clear dentry's mounted state if it has no remaining mounts.
+ * vfsmount_lock must be held for write.
+ */
+static void dentry_reset_mounted(struct vfsmount *mnt, struct dentry *dentry)
+{
+        unsigned u;
+
+        for (u = 0; u < HASH_SIZE; u++) {
+                struct vfsmount *p;
+
+                list_for_each_entry(p, &mount_hashtable[u], mnt_hash) {
+                        if (p->mnt_mountpoint == dentry)
+                                return;
+                }
+        }
+        spin_lock(&dentry->d_lock);
+        dentry->d_flags &= ~DCACHE_MOUNTED;
+        spin_unlock(&dentry->d_lock);
+}
+
+/*
  * vfsmount lock must be held for write
  */
 static void detach_mnt(struct vfsmount *mnt, struct path *old_path)
@@ -502,7 +584,7 @@ static void detach_mnt(struct vfsmount *mnt, struct path *old_path)
         mnt->mnt_mountpoint = mnt->mnt_root;
         list_del_init(&mnt->mnt_child);
         list_del_init(&mnt->mnt_hash);
-        old_path->dentry->d_mounted--;
+        dentry_reset_mounted(old_path->mnt, old_path->dentry);
 }
 
 /*
@@ -513,7 +595,9 @@ void mnt_set_mountpoint(struct vfsmount *mnt, struct dentry *dentry,
 {
         child_mnt->mnt_parent = mntget(mnt);
         child_mnt->mnt_mountpoint = dget(dentry);
-        dentry->d_mounted++;
+        spin_lock(&dentry->d_lock);
+        dentry->d_flags |= DCACHE_MOUNTED;
+        spin_unlock(&dentry->d_lock);
 }
 
 /*
@@ -629,9 +713,10 @@ static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root,
         return NULL;
 }
 
-static inline void __mntput(struct vfsmount *mnt)
+static inline void mntfree(struct vfsmount *mnt)
 {
         struct super_block *sb = mnt->mnt_sb;
+
         /*
          * This probably indicates that somebody messed
          * up a mnt_want/drop_write() pair.  If this
@@ -639,38 +724,123 @@ static inline void __mntput(struct vfsmount *mnt)
          * to make r/w->r/o transitions.
          */
         /*
-         * atomic_dec_and_lock() used to deal with ->mnt_count decrements
-         * provides barriers, so count_mnt_writers() below is safe.  AV
+         * The locking used to deal with mnt_count decrement provides barriers,
+         * so mnt_get_writers() below is safe.
          */
-        WARN_ON(count_mnt_writers(mnt));
+        WARN_ON(mnt_get_writers(mnt));
         fsnotify_vfsmount_delete(mnt);
         dput(mnt->mnt_root);
         free_vfsmnt(mnt);
         deactivate_super(sb);
 }
 
-void mntput_no_expire(struct vfsmount *mnt)
-{
-repeat:
-        if (atomic_add_unless(&mnt->mnt_count, -1, 1))
-                return;
+#ifdef CONFIG_SMP
+static inline void __mntput(struct vfsmount *mnt, int longrefs)
+{
+        if (!longrefs) {
+put_again:
+                br_read_lock(vfsmount_lock);
+                if (likely(atomic_read(&mnt->mnt_longrefs))) {
+                        mnt_dec_count(mnt);
+                        br_read_unlock(vfsmount_lock);
+                        return;
+                }
+                br_read_unlock(vfsmount_lock);
+        } else {
+                BUG_ON(!atomic_read(&mnt->mnt_longrefs));
+                if (atomic_add_unless(&mnt->mnt_longrefs, -1, 1))
+                        return;
+        }
+
         br_write_lock(vfsmount_lock);
-        if (!atomic_dec_and_test(&mnt->mnt_count)) {
+        if (!longrefs)
+                mnt_dec_count(mnt);
+        else
+                atomic_dec(&mnt->mnt_longrefs);
+        if (mnt_get_count(mnt)) {
                 br_write_unlock(vfsmount_lock);
                 return;
         }
-        if (likely(!mnt->mnt_pinned)) {
+        if (unlikely(mnt->mnt_pinned)) {
+                mnt_add_count(mnt, mnt->mnt_pinned + 1);
+                mnt->mnt_pinned = 0;
                 br_write_unlock(vfsmount_lock);
-                __mntput(mnt);
+                acct_auto_close_mnt(mnt);
+                goto put_again;
+        }
+        br_write_unlock(vfsmount_lock);
+        mntfree(mnt);
+}
+#else
+static inline void __mntput(struct vfsmount *mnt, int longrefs)
+{
+put_again:
+        mnt_dec_count(mnt);
+        if (likely(mnt_get_count(mnt)))
                 return;
+        br_write_lock(vfsmount_lock);
+        if (unlikely(mnt->mnt_pinned)) {
+                mnt_add_count(mnt, mnt->mnt_pinned + 1);
+                mnt->mnt_pinned = 0;
+                br_write_unlock(vfsmount_lock);
+                acct_auto_close_mnt(mnt);
+                goto put_again;
         }
-        atomic_add(mnt->mnt_pinned + 1, &mnt->mnt_count);
-        mnt->mnt_pinned = 0;
         br_write_unlock(vfsmount_lock);
-        acct_auto_close_mnt(mnt);
-        goto repeat;
+        mntfree(mnt);
+}
+#endif
+
+static void mntput_no_expire(struct vfsmount *mnt)
+{
+        __mntput(mnt, 0);
+}
+
+void mntput(struct vfsmount *mnt)
+{
+        if (mnt) {
+                /* avoid cacheline pingpong, hope gcc doesn't get "smart" */
+                if (unlikely(mnt->mnt_expiry_mark))
+                        mnt->mnt_expiry_mark = 0;
+                __mntput(mnt, 0);
+        }
+}
+EXPORT_SYMBOL(mntput);
+
+struct vfsmount *mntget(struct vfsmount *mnt)
+{
+        if (mnt)
+                mnt_inc_count(mnt);
+        return mnt;
 }
-EXPORT_SYMBOL(mntput_no_expire);
+EXPORT_SYMBOL(mntget);
+
+void mntput_long(struct vfsmount *mnt)
+{
+#ifdef CONFIG_SMP
+        if (mnt) {
+                /* avoid cacheline pingpong, hope gcc doesn't get "smart" */
+                if (unlikely(mnt->mnt_expiry_mark))
+                        mnt->mnt_expiry_mark = 0;
+                __mntput(mnt, 1);
+        }
+#else
+        mntput(mnt);
+#endif
+}
+EXPORT_SYMBOL(mntput_long);
+
+struct vfsmount *mntget_long(struct vfsmount *mnt)
+{
+#ifdef CONFIG_SMP
+        if (mnt)
+                atomic_inc(&mnt->mnt_longrefs);
+        return mnt;
+#else
+        return mntget(mnt);
+#endif
+}
+EXPORT_SYMBOL(mntget_long);
 
 void mnt_pin(struct vfsmount *mnt)
 {
@@ -678,19 +848,17 @@ void mnt_pin(struct vfsmount *mnt)
         mnt->mnt_pinned++;
         br_write_unlock(vfsmount_lock);
 }
-
 EXPORT_SYMBOL(mnt_pin);
 
 void mnt_unpin(struct vfsmount *mnt)
 {
         br_write_lock(vfsmount_lock);
         if (mnt->mnt_pinned) {
-                atomic_inc(&mnt->mnt_count);
+                mnt_inc_count(mnt);
                 mnt->mnt_pinned--;
         }
         br_write_unlock(vfsmount_lock);
 }
-
 EXPORT_SYMBOL(mnt_unpin);
 
 static inline void mangle(struct seq_file *m, const char *s)
@@ -985,12 +1153,13 @@ int may_umount_tree(struct vfsmount *mnt)
         int minimum_refs = 0;
         struct vfsmount *p;
 
-        br_read_lock(vfsmount_lock);
+        /* write lock needed for mnt_get_count */
+        br_write_lock(vfsmount_lock);
         for (p = mnt; p; p = next_mnt(p, mnt)) {
-                actual_refs += atomic_read(&p->mnt_count);
+                actual_refs += mnt_get_count(p);
                 minimum_refs += 2;
         }
-        br_read_unlock(vfsmount_lock);
+        br_write_unlock(vfsmount_lock);
 
         if (actual_refs > minimum_refs)
                 return 0;
@@ -1017,10 +1186,10 @@ int may_umount(struct vfsmount *mnt)
 {
         int ret = 1;
         down_read(&namespace_sem);
-        br_read_lock(vfsmount_lock);
+        br_write_lock(vfsmount_lock);
         if (propagate_mount_busy(mnt, 2))
                 ret = 0;
-        br_read_unlock(vfsmount_lock);
+        br_write_unlock(vfsmount_lock);
         up_read(&namespace_sem);
         return ret;
 }
@@ -1047,7 +1216,7 @@ void release_mounts(struct list_head *head)
                         dput(dentry);
                         mntput(m);
                 }
-                mntput(mnt);
+                mntput_long(mnt);
         }
 }
 
@@ -1073,7 +1242,7 @@ void umount_tree(struct vfsmount *mnt, int propagate, struct list_head *kill)
                 list_del_init(&p->mnt_child);
                 if (p->mnt_parent != p) {
                         p->mnt_parent->mnt_ghosts++;
-                        p->mnt_mountpoint->d_mounted--;
+                        dentry_reset_mounted(p->mnt_parent, p->mnt_mountpoint);
                 }
                 change_mnt_propagation(p, MS_PRIVATE);
         }
@@ -1102,8 +1271,16 @@ static int do_umount(struct vfsmount *mnt, int flags)
                     flags & (MNT_FORCE | MNT_DETACH))
                         return -EINVAL;
 
-                if (atomic_read(&mnt->mnt_count) != 2)
+                /*
+                 * probably don't strictly need the lock here if we examined
+                 * all race cases, but it's a slowpath.
+                 */
+                br_write_lock(vfsmount_lock);
+                if (mnt_get_count(mnt) != 2) {
+                        br_write_lock(vfsmount_lock);
                         return -EBUSY;
+                }
+                br_write_unlock(vfsmount_lock);
 
                 if (!xchg(&mnt->mnt_expiry_mark, 1))
                         return -EAGAIN;
@@ -1792,7 +1969,7 @@ int do_add_mount(struct vfsmount *newmnt, struct path *path,
 
 unlock:
         up_write(&namespace_sem);
-        mntput(newmnt);
+        mntput_long(newmnt);
         return err;
 }
 
@@ -2125,11 +2302,11 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
                 if (fs) {
                         if (p == fs->root.mnt) {
                                 rootmnt = p;
-                                fs->root.mnt = mntget(q);
+                                fs->root.mnt = mntget_long(q);
                         }
                         if (p == fs->pwd.mnt) {
                                 pwdmnt = p;
-                                fs->pwd.mnt = mntget(q);
+                                fs->pwd.mnt = mntget_long(q);
                         }
                 }
                 p = next_mnt(p, mnt_ns->root);
@@ -2138,9 +2315,9 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
         up_write(&namespace_sem);
 
         if (rootmnt)
-                mntput(rootmnt);
+                mntput_long(rootmnt);
         if (pwdmnt)
-                mntput(pwdmnt);
+                mntput_long(pwdmnt);
 
         return new_ns;
 }
@@ -2327,6 +2504,7 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
         touch_mnt_namespace(current->nsproxy->mnt_ns);
         br_write_unlock(vfsmount_lock);
         chroot_fs_refs(&root, &new);
+
         error = 0;
         path_put(&root_parent);
         path_put(&parent_path);
@@ -2353,6 +2531,7 @@ static void __init init_mount_tree(void)
         mnt = do_kern_mount("rootfs", 0, "rootfs", NULL);
         if (IS_ERR(mnt))
                 panic("Can't create rootfs");
+
         ns = create_mnt_ns(mnt);
         if (IS_ERR(ns))
                 panic("Can't allocate initial namespace");
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index f22b12e7d337..28f136d4aaec 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -17,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/vmalloc.h>
 #include <linux/mm.h>
+#include <linux/namei.h>
 #include <asm/uaccess.h>
 #include <asm/byteorder.h>
 
@@ -74,9 +75,12 @@ const struct inode_operations ncp_dir_inode_operations =
  * Dentry operations routines
  */
 static int ncp_lookup_validate(struct dentry *, struct nameidata *);
-static int ncp_hash_dentry(struct dentry *, struct qstr *);
-static int ncp_compare_dentry (struct dentry *, struct qstr *, struct qstr *);
-static int ncp_delete_dentry(struct dentry *);
+static int ncp_hash_dentry(const struct dentry *, const struct inode *,
+                struct qstr *);
+static int ncp_compare_dentry(const struct dentry *, const struct inode *,
+                const struct dentry *, const struct inode *,
+                unsigned int, const char *, const struct qstr *);
+static int ncp_delete_dentry(const struct dentry *);
 
 static const struct dentry_operations ncp_dentry_operations =
 {
@@ -113,10 +117,10 @@ static inline int ncp_preserve_entry_case(struct inode *i, __u32 nscreator)
 
 #define ncp_preserve_case(i)    (ncp_namespace(i) != NW_NS_DOS)
 
-static inline int ncp_case_sensitive(struct dentry *dentry)
+static inline int ncp_case_sensitive(const struct inode *i)
 {
 #ifdef CONFIG_NCPFS_NFS_NS
-        return ncp_namespace(dentry->d_inode) == NW_NS_NFS;
+        return ncp_namespace(i) == NW_NS_NFS;
 #else
         return 0;
 #endif /* CONFIG_NCPFS_NFS_NS */
@@ -127,14 +131,16 @@ static inline int ncp_case_sensitive(struct dentry *dentry)
  * is case-sensitive.
  */
 static int 
-ncp_hash_dentry(struct dentry *dentry, struct qstr *this)
+ncp_hash_dentry(const struct dentry *dentry, const struct inode *inode,
+                struct qstr *this)
 {
-        if (!ncp_case_sensitive(dentry)) {
+        if (!ncp_case_sensitive(inode)) {
+                struct super_block *sb = dentry->d_sb;
                 struct nls_table *t;
                 unsigned long hash;
                 int i;
 
-                t = NCP_IO_TABLE(dentry);
+                t = NCP_IO_TABLE(sb);
                 hash = init_name_hash();
                 for (i=0; i<this->len ; i++)
                         hash = partial_name_hash(ncp_tolower(t, this->name[i]),
@@ -145,15 +151,17 @@ ncp_hash_dentry(struct dentry *dentry, struct qstr *this)
 }
 
 static int
-ncp_compare_dentry(struct dentry *dentry, struct qstr *a, struct qstr *b)
+ncp_compare_dentry(const struct dentry *parent, const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name)
 {
-        if (a->len != b->len)
+        if (len != name->len)
                 return 1;
 
-        if (ncp_case_sensitive(dentry))
-                return strncmp(a->name, b->name, a->len);
+        if (ncp_case_sensitive(pinode))
+                return strncmp(str, name->name, len);
 
-        return ncp_strnicmp(NCP_IO_TABLE(dentry), a->name, b->name, a->len);
+        return ncp_strnicmp(NCP_IO_TABLE(pinode->i_sb), str, name->name, len);
 }
 
 /*
@@ -162,7 +170,7 @@ ncp_compare_dentry(struct dentry *dentry, struct qstr *a, struct qstr *b)
  * Closing files can be safely postponed until iput() - it's done there anyway.
  */
 static int
-ncp_delete_dentry(struct dentry * dentry)
+ncp_delete_dentry(const struct dentry * dentry)
 {
         struct inode *inode = dentry->d_inode;
 
@@ -301,6 +309,9 @@ ncp_lookup_validate(struct dentry *dentry, struct nameidata *nd)
         int res, val = 0, len;
         __u8 __name[NCP_MAXPATHLEN + 1];
 
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
+
         parent = dget_parent(dentry);
         dir = parent->d_inode;
 
@@ -384,21 +395,21 @@ ncp_dget_fpos(struct dentry *dentry, struct dentry *parent, unsigned long fpos)
         }
 
         /* If a pointer is invalid, we search the dentry. */
-        spin_lock(&dcache_lock);
+        spin_lock(&parent->d_lock);
         next = parent->d_subdirs.next;
         while (next != &parent->d_subdirs) {
                 dent = list_entry(next, struct dentry, d_u.d_child);
                 if ((unsigned long)dent->d_fsdata == fpos) {
                         if (dent->d_inode)
-                                dget_locked(dent);
+                                dget(dent);
                         else
                                 dent = NULL;
-                        spin_unlock(&dcache_lock);
+                        spin_unlock(&parent->d_lock);
                         goto out;
                 }
                 next = next->next;
         }
-        spin_unlock(&dcache_lock);
+        spin_unlock(&parent->d_lock);
         return NULL;
 
 out:
@@ -592,7 +603,7 @@ ncp_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
         qname.hash = full_name_hash(qname.name, qname.len);
 
         if (dentry->d_op && dentry->d_op->d_hash)
-                if (dentry->d_op->d_hash(dentry, &qname) != 0)
+                if (dentry->d_op->d_hash(dentry, dentry->d_inode, &qname) != 0)
                         goto end_advance;
 
         newdent = d_lookup(dentry, &qname);
@@ -611,35 +622,12 @@ ncp_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
                         shrink_dcache_parent(newdent);
 
                 /*
-                 * It is not as dangerous as it looks.  NetWare's OS2 namespace is
-                 * case preserving yet case insensitive.  So we update dentry's name
-                 * as received from server.  We found dentry via d_lookup with our
-                 * hash, so we know that hash does not change, and so replacing name
-                 * should be reasonably safe.
+                 * NetWare's OS2 namespace is case preserving yet case
+                 * insensitive.  So we update dentry's name as received from
+                 * server. Parent dir's i_mutex is locked because we're in
+                 * readdir.
                  */
-                if (qname.len == newdent->d_name.len &&
-                    memcmp(newdent->d_name.name, qname.name, newdent->d_name.len)) {
-                        struct inode *inode = newdent->d_inode;
-
-                        /*
-                         * Inside ncpfs all uses of d_name are either for debugging,
-                         * or on functions which acquire inode mutex (mknod, creat,
-                         * lookup).  So grab i_mutex here, to be sure.  d_path
-                         * uses dcache_lock when generating path, so we should too.
-                         * And finally d_compare is protected by dentry's d_lock, so
-                         * here we go.
-                         */
-                        if (inode)
-                                mutex_lock(&inode->i_mutex);
-                        spin_lock(&dcache_lock);
-                        spin_lock(&newdent->d_lock);
-                        memcpy((char *) newdent->d_name.name, qname.name,
-                                                                newdent->d_name.len);
-                        spin_unlock(&newdent->d_lock);
-                        spin_unlock(&dcache_lock);
-                        if (inode)
-                                mutex_unlock(&inode->i_mutex);
-                }
+                dentry_update_name_case(newdent, &qname);
         }
 
         if (!newdent->d_inode) {
@@ -649,7 +637,7 @@ ncp_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
                 entry->ino = iunique(dir->i_sb, 2);
                 inode = ncp_iget(dir->i_sb, entry);
                 if (inode) {
-                        newdent->d_op = &ncp_dentry_operations;
+                        d_set_d_op(newdent, &ncp_dentry_operations);
                         d_instantiate(newdent, inode);
                         if (!hashed)
                                 d_rehash(newdent);
@@ -657,7 +645,7 @@ ncp_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
         } else {
                 struct inode *inode = newdent->d_inode;
 
-                mutex_lock(&inode->i_mutex);
+                mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
                 ncp_update_inode2(inode, entry);
                 mutex_unlock(&inode->i_mutex);
         }
@@ -905,7 +893,7 @@ static struct dentry *ncp_lookup(struct inode *dir, struct dentry *dentry, struc
         if (inode) {
                 ncp_new_dentry(dentry);
 add_entry:
-                dentry->d_op = &ncp_dentry_operations;
+                d_set_d_op(dentry, &ncp_dentry_operations);
                 d_add(dentry, inode);
                 error = 0;
         }
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index 8fb93b604e73..9b39a5dd4131 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -29,6 +29,7 @@
 #include <linux/vfs.h>
 #include <linux/mount.h>
 #include <linux/seq_file.h>
+#include <linux/namei.h>
 
 #include <linux/ncp_fs.h>
 
@@ -58,11 +59,18 @@ static struct inode *ncp_alloc_inode(struct super_block *sb)
         return &ei->vfs_inode;
 }
 
-static void ncp_destroy_inode(struct inode *inode)
+static void ncp_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(ncp_inode_cachep, NCP_FINFO(inode));
 }
 
+static void ncp_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, ncp_i_callback);
+}
+
 static void init_once(void *foo)
 {
         struct ncp_inode_info *ei = (struct ncp_inode_info *) foo;
@@ -309,7 +317,12 @@ static void ncp_stop_tasks(struct ncp_server *server) {
         sk->sk_write_space  = server->write_space;
         release_sock(sk);
         del_timer_sync(&server->timeout_tm);
-        flush_scheduled_work();
+
+        flush_work_sync(&server->rcv.tq);
+        if (sk->sk_socket->type == SOCK_STREAM)
+                flush_work_sync(&server->tx.tq);
+        else
+                flush_work_sync(&server->timeout_tq);
 }
 
 static int  ncp_show_options(struct seq_file *seq, struct vfsmount *mnt)
@@ -710,7 +723,7 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
         sb->s_root = d_alloc_root(root_inode);
         if (!sb->s_root)
                 goto out_no_root;
-        sb->s_root->d_op = &ncp_root_dentry_operations;
+        d_set_d_op(sb->s_root, &ncp_root_dentry_operations);
         return 0;
 
 out_no_root:
diff --git a/fs/ncpfs/ncplib_kernel.h b/fs/ncpfs/ncplib_kernel.h
index 3c57eca634ce..1220df75ff22 100644
--- a/fs/ncpfs/ncplib_kernel.h
+++ b/fs/ncpfs/ncplib_kernel.h
@@ -135,7 +135,7 @@ int ncp__vol2io(struct ncp_server *, unsigned char *, unsigned int *,
                                 const unsigned char *, unsigned int, int);
 
 #define NCP_ESC                 ':'
-#define NCP_IO_TABLE(dentry)    (NCP_SERVER((dentry)->d_inode)->nls_io)
+#define NCP_IO_TABLE(sb)        (NCP_SBP(sb)->nls_io)
 #define ncp_tolower(t, c)       nls_tolower(t, c)
 #define ncp_toupper(t, c)       nls_toupper(t, c)
 #define ncp_strnicmp(t, s1, s2, len) \
@@ -150,15 +150,15 @@ int ncp__io2vol(unsigned char *, unsigned int *,
 int ncp__vol2io(unsigned char *, unsigned int *,
                                 const unsigned char *, unsigned int, int);
 
-#define NCP_IO_TABLE(dentry)    NULL
+#define NCP_IO_TABLE(sb)        NULL
 #define ncp_tolower(t, c)       tolower(c)
 #define ncp_toupper(t, c)       toupper(c)
 #define ncp_io2vol(S,m,i,n,k,U) ncp__io2vol(m,i,n,k,U)
 #define ncp_vol2io(S,m,i,n,k,U) ncp__vol2io(m,i,n,k,U)
 
 
-static inline int ncp_strnicmp(struct nls_table *t, const unsigned char *s1,
-                const unsigned char *s2, int len)
+static inline int ncp_strnicmp(const struct nls_table *t,
+                const unsigned char *s1, const unsigned char *s2, int len)
 {
         while (len--) {
                 if (tolower(*s1++) != tolower(*s2++))
@@ -193,7 +193,7 @@ ncp_renew_dentries(struct dentry *parent)
         struct list_head *next;
         struct dentry *dentry;
 
-        spin_lock(&dcache_lock);
+        spin_lock(&parent->d_lock);
         next = parent->d_subdirs.next;
         while (next != &parent->d_subdirs) {
                 dentry = list_entry(next, struct dentry, d_u.d_child);
@@ -205,7 +205,7 @@ ncp_renew_dentries(struct dentry *parent)
 
                 next = next->next;
         }
-        spin_unlock(&dcache_lock);
+        spin_unlock(&parent->d_lock);
 }
 
 static inline void
@@ -215,7 +215,7 @@ ncp_invalidate_dircache_entries(struct dentry *parent)
         struct list_head *next;
         struct dentry *dentry;
 
-        spin_lock(&dcache_lock);
+        spin_lock(&parent->d_lock);
         next = parent->d_subdirs.next;
         while (next != &parent->d_subdirs) {
                 dentry = list_entry(next, struct dentry, d_u.d_child);
@@ -223,7 +223,7 @@ ncp_invalidate_dircache_entries(struct dentry *parent)
                 ncp_age_dentry(server, dentry);
                 next = next->next;
         }
-        spin_unlock(&dcache_lock);
+        spin_unlock(&parent->d_lock);
 }
 
 struct ncp_cache_head {
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index f0a384e2ae63..d33da530097a 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -57,7 +57,7 @@ static int nfs_rename(struct inode *, struct dentry *,
                       struct inode *, struct dentry *);
 static int nfs_fsync_dir(struct file *, int);
 static loff_t nfs_llseek_dir(struct file *, loff_t, int);
-static int nfs_readdir_clear_array(struct page*, gfp_t);
+static void nfs_readdir_clear_array(struct page*);
 
 const struct file_operations nfs_dir_operations = {
         .llseek         = nfs_llseek_dir,
@@ -83,8 +83,8 @@ const struct inode_operations nfs_dir_inode_operations = {
         .setattr        = nfs_setattr,
 };
 
-const struct address_space_operations nfs_dir_addr_space_ops = {
-        .releasepage = nfs_readdir_clear_array,
+const struct address_space_operations nfs_dir_aops = {
+        .freepage = nfs_readdir_clear_array,
 };
 
 #ifdef CONFIG_NFS_V3
@@ -178,6 +178,7 @@ typedef struct {
         struct page     *page;
         unsigned long   page_index;
         u64             *dir_cookie;
+        u64             last_cookie;
         loff_t          current_index;
         decode_dirent_t decode;
 
@@ -213,17 +214,15 @@ void nfs_readdir_release_array(struct page *page)
  * we are freeing strings created by nfs_add_to_readdir_array()
  */
 static
-int nfs_readdir_clear_array(struct page *page, gfp_t mask)
+void nfs_readdir_clear_array(struct page *page)
 {
-        struct nfs_cache_array *array = nfs_readdir_get_array(page);
+        struct nfs_cache_array *array;
         int i;
 
-        if (IS_ERR(array))
-                return PTR_ERR(array);
+        array = kmap_atomic(page, KM_USER0);
         for (i = 0; i < array->size; i++)
                 kfree(array->array[i].string.name);
-        nfs_readdir_release_array(page);
-        return 0;
+        kunmap_atomic(array, KM_USER0);
 }
 
 /*
@@ -272,7 +271,7 @@ int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page)
                 goto out;
         array->last_cookie = entry->cookie;
         array->size++;
-        if (entry->eof == 1)
+        if (entry->eof != 0)
                 array->eof_index = array->size;
 out:
         nfs_readdir_release_array(page);
@@ -312,15 +311,14 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des
         for (i = 0; i < array->size; i++) {
                 if (array->array[i].cookie == *desc->dir_cookie) {
                         desc->cache_entry_index = i;
-                        status = 0;
-                        goto out;
+                        return 0;
                 }
         }
-        if (i == array->eof_index) {
-                desc->eof = 1;
+        if (array->eof_index >= 0) {
                 status = -EBADCOOKIE;
+                if (*desc->dir_cookie == array->last_cookie)
+                        desc->eof = 1;
         }
-out:
         return status;
 }
 
@@ -328,10 +326,7 @@ static
 int nfs_readdir_search_array(nfs_readdir_descriptor_t *desc)
 {
         struct nfs_cache_array *array;
-        int status = -EBADCOOKIE;
-
-        if (desc->dir_cookie == NULL)
-                goto out;
+        int status;
 
         array = nfs_readdir_get_array(desc->page);
         if (IS_ERR(array)) {
@@ -344,6 +339,10 @@ int nfs_readdir_search_array(nfs_readdir_descriptor_t *desc)
         else
                 status = nfs_readdir_search_for_cookie(array, desc);
 
+        if (status == -EAGAIN) {
+                desc->last_cookie = array->last_cookie;
+                desc->page_index++;
+        }
         nfs_readdir_release_array(desc->page);
 out:
         return status;
@@ -439,7 +438,7 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
         if (dentry == NULL)
                 return;
 
-        dentry->d_op = NFS_PROTO(dir)->dentry_ops;
+        d_set_d_op(dentry, NFS_PROTO(dir)->dentry_ops);
         inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr);
         if (IS_ERR(inode))
                 goto out;
@@ -490,7 +489,7 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
 
                 count++;
 
-                if (desc->plus == 1)
+                if (desc->plus != 0)
                         nfs_prime_dcache(desc->file->f_path.dentry, entry);
 
                 status = nfs_readdir_add_to_array(entry, page);
@@ -498,7 +497,7 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
                         break;
         } while (!entry->eof);
 
-        if (count == 0 || (status == -EBADCOOKIE && entry->eof == 1)) {
+        if (count == 0 || (status == -EBADCOOKIE && entry->eof != 0)) {
                 array = nfs_readdir_get_array(page);
                 if (!IS_ERR(array)) {
                         array->eof_index = array->size;
@@ -563,7 +562,7 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page,
         unsigned int array_size = ARRAY_SIZE(pages);
 
         entry.prev_cookie = 0;
-        entry.cookie = *desc->dir_cookie;
+        entry.cookie = desc->last_cookie;
         entry.eof = 0;
         entry.fh = nfs_alloc_fhandle();
         entry.fattr = nfs_alloc_fattr();
@@ -636,6 +635,8 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page)
 static
 void cache_page_release(nfs_readdir_descriptor_t *desc)
 {
+        if (!desc->page->mapping)
+                nfs_readdir_clear_array(desc->page);
         page_cache_release(desc->page);
         desc->page = NULL;
 }
@@ -660,9 +661,8 @@ int find_cache_page(nfs_readdir_descriptor_t *desc)
                 return PTR_ERR(desc->page);
 
         res = nfs_readdir_search_array(desc);
-        if (res == 0)
-                return 0;
-        cache_page_release(desc);
+        if (res != 0)
+                cache_page_release(desc);
         return res;
 }
 
@@ -672,22 +672,16 @@ int readdir_search_pagecache(nfs_readdir_descriptor_t *desc)
 {
         int res;
 
-        if (desc->page_index == 0)
+        if (desc->page_index == 0) {
                 desc->current_index = 0;
-        while (1) {
-                res = find_cache_page(desc);
-                if (res != -EAGAIN)
-                        break;
-                desc->page_index++;
+                desc->last_cookie = 0;
         }
+        do {
+                res = find_cache_page(desc);
+        } while (res == -EAGAIN);
         return res;
 }
 
-static inline unsigned int dt_type(struct inode *inode)
-{
-        return (inode->i_mode >> 12) & 15;
-}
-
 /*
  * Once we've found the start of the dirent within a page: fill 'er up...
  */
@@ -717,13 +711,12 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc, void *dirent,
                         break;
                 }
                 file->f_pos++;
-                desc->cache_entry_index = i;
                 if (i < (array->size-1))
                         *desc->dir_cookie = array->array[i+1].cookie;
                 else
                         *desc->dir_cookie = array->last_cookie;
         }
-        if (i == array->eof_index)
+        if (array->eof_index >= 0)
                 desc->eof = 1;
 
         nfs_readdir_release_array(desc->page);
@@ -764,6 +757,7 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent,
         }
 
         desc->page_index = 0;
+        desc->last_cookie = *desc->dir_cookie;
         desc->page = page;
 
         status = nfs_readdir_xdr_to_array(desc, page, inode);
@@ -791,7 +785,7 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
         struct inode    *inode = dentry->d_inode;
         nfs_readdir_descriptor_t my_desc,
                         *desc = &my_desc;
-        int res = -ENOMEM;
+        int res;
 
         dfprintk(FILE, "NFS: readdir(%s/%s) starting at cookie %llu\n",
                         dentry->d_parent->d_name.name, dentry->d_name.name,
@@ -816,7 +810,7 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
         if (res < 0)
                 goto out;
 
-        while (desc->eof != 1) {
+        do {
                 res = readdir_search_pagecache(desc);
 
                 if (res == -EBADCOOKIE) {
@@ -844,7 +838,7 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
                 res = nfs_do_filldir(desc, dirent, filldir);
                 if (res < 0)
                         break;
-        }
+        } while (!desc->eof);
 out:
         nfs_unblock_sillyrename(dentry);
         if (res > 0)
@@ -944,7 +938,8 @@ static int nfs_check_verifier(struct inode *dir, struct dentry *dentry)
  * component of the path.
  * We check for this using LOOKUP_CONTINUE and LOOKUP_PARENT.
  */
-static inline unsigned int nfs_lookup_check_intent(struct nameidata *nd, unsigned int mask)
+static inline unsigned int nfs_lookup_check_intent(struct nameidata *nd,
+                                                unsigned int mask)
 {
         if (nd->flags & (LOOKUP_CONTINUE|LOOKUP_PARENT))
                 return 0;
@@ -1024,7 +1019,7 @@ int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry,
  * If the parent directory is seen to have changed, we throw out the
  * cached dentry and do a new lookup.
  */
-static int nfs_lookup_revalidate(struct dentry * dentry, struct nameidata *nd)
+static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
         struct inode *dir;
         struct inode *inode;
@@ -1033,6 +1028,9 @@ static int nfs_lookup_revalidate(struct dentry * dentry, struct nameidata *nd)
         struct nfs_fattr *fattr = NULL;
         int error;
 
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
+
         parent = dget_parent(dentry);
         dir = parent->d_inode;
         nfs_inc_stats(dir, NFSIOS_DENTRYREVALIDATE);
@@ -1123,7 +1121,7 @@ out_error:
 /*
  * This is called from dput() when d_count is going to 0.
  */
-static int nfs_dentry_delete(struct dentry *dentry)
+static int nfs_dentry_delete(const struct dentry *dentry)
 {
         dfprintk(VFS, "NFS: dentry_delete(%s/%s, %x)\n",
                 dentry->d_parent->d_name.name, dentry->d_name.name,
@@ -1194,7 +1192,7 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru
         if (dentry->d_name.len > NFS_SERVER(dir)->namelen)
                 goto out;
 
-        dentry->d_op = NFS_PROTO(dir)->dentry_ops;
+        d_set_d_op(dentry, NFS_PROTO(dir)->dentry_ops);
 
         /*
          * If we're doing an exclusive create, optimize away the lookup
@@ -1339,7 +1337,7 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
                 res = ERR_PTR(-ENAMETOOLONG);
                 goto out;
         }
-        dentry->d_op = NFS_PROTO(dir)->dentry_ops;
+        d_set_d_op(dentry, NFS_PROTO(dir)->dentry_ops);
 
         /* Let vfs_create() deal with O_EXCL. Instantiate, but don't hash
          * the dentry. */
@@ -1724,11 +1722,9 @@ static int nfs_unlink(struct inode *dir, struct dentry *dentry)
         dfprintk(VFS, "NFS: unlink(%s/%ld, %s)\n", dir->i_sb->s_id,
                 dir->i_ino, dentry->d_name.name);
 
-        spin_lock(&dcache_lock);
         spin_lock(&dentry->d_lock);
-        if (atomic_read(&dentry->d_count) > 1) {
+        if (dentry->d_count > 1) {
                 spin_unlock(&dentry->d_lock);
-                spin_unlock(&dcache_lock);
                 /* Start asynchronous writeout of the inode */
                 write_inode_now(dentry->d_inode, 0);
                 error = nfs_sillyrename(dir, dentry);
@@ -1739,7 +1735,6 @@ static int nfs_unlink(struct inode *dir, struct dentry *dentry)
                 need_rehash = 1;
         }
         spin_unlock(&dentry->d_lock);
-        spin_unlock(&dcache_lock);
         error = nfs_safe_remove(dentry);
         if (!error || error == -ENOENT) {
                 nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
@@ -1874,7 +1869,7 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
         dfprintk(VFS, "NFS: rename(%s/%s -> %s/%s, ct=%d)\n",
                  old_dentry->d_parent->d_name.name, old_dentry->d_name.name,
                  new_dentry->d_parent->d_name.name, new_dentry->d_name.name,
-                 atomic_read(&new_dentry->d_count));
+                 new_dentry->d_count);
 
         /*
          * For non-directories, check whether the target is busy and if so,
@@ -1892,7 +1887,7 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
                         rehash = new_dentry;
                 }
 
-                if (atomic_read(&new_dentry->d_count) > 2) {
+                if (new_dentry->d_count > 2) {
                         int err;
 
                         /* copy the target dentry's name */
@@ -2194,11 +2189,14 @@ int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags)
         return nfs_do_access(inode, cred, nfs_open_permission_mask(openflags));
 }
 
-int nfs_permission(struct inode *inode, int mask)
+int nfs_permission(struct inode *inode, int mask, unsigned int flags)
 {
         struct rpc_cred *cred;
         int res = 0;
 
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
         nfs_inc_stats(inode, NFSIOS_VFSACCESS);
 
         if ((mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0)
@@ -2246,7 +2244,7 @@ out:
 out_notsup:
         res = nfs_revalidate_inode(NFS_SERVER(inode), inode);
         if (res == 0)
-                res = generic_permission(inode, mask, NULL);
+                res = generic_permission(inode, mask, flags, NULL);
         goto out;
 }
 
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 60677f9f1311..7bf029ef4084 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -693,6 +693,7 @@ do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 {
         struct inode *inode = filp->f_mapping->host;
         int status = 0;
+        unsigned int saved_type = fl->fl_type;
 
         /* Try local locking first */
         posix_test_lock(filp, fl);
@@ -700,6 +701,7 @@ do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
                 /* found a conflict */
                 goto out;
         }
+        fl->fl_type = saved_type;
 
         if (nfs_have_delegation(inode, FMODE_READ))
                 goto out_noconflict;
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index ac7b814ce162..5596c6a2881e 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -63,9 +63,11 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i
                  * This again causes shrink_dcache_for_umount_subtree() to
                  * Oops, since the test for IS_ROOT() will fail.
                  */
-                spin_lock(&dcache_lock);
+                spin_lock(&sb->s_root->d_inode->i_lock);
+                spin_lock(&sb->s_root->d_lock);
                 list_del_init(&sb->s_root->d_alias);
-                spin_unlock(&dcache_lock);
+                spin_unlock(&sb->s_root->d_lock);
+                spin_unlock(&sb->s_root->d_inode->i_lock);
         }
         return 0;
 }
@@ -119,7 +121,7 @@ struct dentry *nfs_get_root(struct super_block *sb, struct nfs_fh *mntfh)
         security_d_instantiate(ret, inode);
 
         if (ret->d_op == NULL)
-                ret->d_op = server->nfs_client->rpc_ops->dentry_ops;
+                d_set_d_op(ret, server->nfs_client->rpc_ops->dentry_ops);
 out:
         nfs_free_fattr(fsinfo.fattr);
         return ret;
@@ -226,7 +228,7 @@ struct dentry *nfs4_get_root(struct super_block *sb, struct nfs_fh *mntfh)
         security_d_instantiate(ret, inode);
 
         if (ret->d_op == NULL)
-                ret->d_op = server->nfs_client->rpc_ops->dentry_ops;
+                d_set_d_op(ret, server->nfs_client->rpc_ops->dentry_ops);
 
 out:
         nfs_free_fattr(fattr);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 314f57164602..017daa3bed38 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -289,6 +289,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
                 } else if (S_ISDIR(inode->i_mode)) {
                         inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops;
                         inode->i_fop = &nfs_dir_operations;
+                        inode->i_data.a_ops = &nfs_dir_aops;
                         if (nfs_server_capable(inode, NFS_CAP_READDIRPLUS))
                                 set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags);
                         /* Deal with crossing mountpoints */
@@ -1437,11 +1438,18 @@ struct inode *nfs_alloc_inode(struct super_block *sb)
         return &nfsi->vfs_inode;
 }
 
-void nfs_destroy_inode(struct inode *inode)
+static void nfs_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(nfs_inode_cachep, NFS_I(inode));
 }
 
+void nfs_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, nfs_i_callback);
+}
+
 static inline void nfs4_init_once(struct nfs_inode *nfsi)
 {
 #ifdef CONFIG_NFS_V4
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index eceafe74f473..4f981f1f6689 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -505,13 +505,13 @@ static struct rpc_procinfo mnt3_procedures[] = {
 
 static struct rpc_version mnt_version1 = {
         .number         = 1,
-        .nrprocs        = 2,
+        .nrprocs        = ARRAY_SIZE(mnt_procedures),
         .procs          = mnt_procedures,
 };
 
 static struct rpc_version mnt_version3 = {
         .number         = 3,
-        .nrprocs        = 2,
+        .nrprocs        = ARRAY_SIZE(mnt3_procedures),
         .procs          = mnt3_procedures,
 };
 
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index db6aa3673cf3..74aaf3963c10 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -49,12 +49,17 @@ char *nfs_path(const char *base,
                const struct dentry *dentry,
                char *buffer, ssize_t buflen)
 {
-        char *end = buffer+buflen;
+        char *end;
         int namelen;
+        unsigned seq;
 
+rename_retry:
+        end = buffer+buflen;
         *--end = '\0';
         buflen--;
-        spin_lock(&dcache_lock);
+
+        seq = read_seqbegin(&rename_lock);
+        rcu_read_lock();
         while (!IS_ROOT(dentry) && dentry != droot) {
                 namelen = dentry->d_name.len;
                 buflen -= namelen + 1;
@@ -65,7 +70,9 @@ char *nfs_path(const char *base,
                 *--end = '/';
                 dentry = dentry->d_parent;
         }
-        spin_unlock(&dcache_lock);
+        rcu_read_unlock();
+        if (read_seqretry(&rename_lock, seq))
+                goto rename_retry;
         if (*end != '/') {
                 if (--buflen < 0)
                         goto Elong;
@@ -82,7 +89,9 @@ char *nfs_path(const char *base,
         memcpy(end, base, namelen);
         return end;
 Elong_unlock:
-        spin_unlock(&dcache_lock);
+        rcu_read_unlock();
+        if (read_seqretry(&rename_lock, seq))
+                goto rename_retry;
 Elong:
         return ERR_PTR(-ENAMETOOLONG);
 }
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 6a653ffd8e4e..4435e5e1f904 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3361,6 +3361,8 @@ static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen)
         ret = nfs_revalidate_inode(server, inode);
         if (ret < 0)
                 return ret;
+        if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_ACL)
+                nfs_zap_acl_cache(inode);
         ret = nfs4_read_cached_acl(inode, buf, buflen);
         if (ret != -ENOENT)
                 return ret;
@@ -3389,6 +3391,13 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
         nfs_inode_return_delegation(inode);
         buf_to_pages(buf, buflen, arg.acl_pages, &arg.acl_pgbase);
         ret = nfs4_call_sync(server, &msg, &arg, &res, 1);
+        /*
+         * Acl update can result in inode attribute update.
+         * so mark the attribute cache invalid.
+         */
+        spin_lock(&inode->i_lock);
+        NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATTR;
+        spin_unlock(&inode->i_lock);
         nfs_access_zap_cache(inode);
         nfs_zap_acl_cache(inode);
         return ret;
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 137b549e63db..b68536cc9046 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -115,7 +115,7 @@ int nfs_set_page_tag_locked(struct nfs_page *req)
 {
         if (!nfs_lock_request_dontget(req))
                 return 0;
-        if (req->wb_page != NULL)
+        if (test_bit(PG_MAPPED, &req->wb_flags))
                 radix_tree_tag_set(&NFS_I(req->wb_context->path.dentry->d_inode)->nfs_page_tree, req->wb_index, NFS_PAGE_TAG_LOCKED);
         return 1;
 }
@@ -125,7 +125,7 @@ int nfs_set_page_tag_locked(struct nfs_page *req)
  */
 void nfs_clear_page_tag_locked(struct nfs_page *req)
 {
-        if (req->wb_page != NULL) {
+        if (test_bit(PG_MAPPED, &req->wb_flags)) {
                 struct inode *inode = req->wb_context->path.dentry->d_inode;
                 struct nfs_inode *nfsi = NFS_I(inode);
 
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index e4b62c6f5a6e..aedcaa7f291f 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -152,7 +152,6 @@ static void nfs_readpage_release(struct nfs_page *req)
                         (long long)NFS_FILEID(req->wb_context->path.dentry->d_inode),
                         req->wb_bytes,
                         (long long)req_offset(req));
-        nfs_clear_request(req);
         nfs_release_request(req);
 }
 
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 3c045044fca2..4100630c9a5b 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1069,12 +1069,10 @@ static int nfs_parse_mount_options(char *raw,
                         mnt->flags |= NFS_MOUNT_VER3;
                         mnt->version = 3;
                         break;
-#ifdef CONFIG_NFS_V4
                 case Opt_v4:
                         mnt->flags &= ~NFS_MOUNT_VER3;
                         mnt->version = 4;
                         break;
-#endif
                 case Opt_udp:
                         mnt->flags &= ~NFS_MOUNT_TCP;
                         mnt->nfs_server.protocol = XPRT_TRANSPORT_UDP;
@@ -1286,12 +1284,10 @@ static int nfs_parse_mount_options(char *raw,
                                 mnt->flags |= NFS_MOUNT_VER3;
                                 mnt->version = 3;
                                 break;
-#ifdef CONFIG_NFS_V4
                         case NFS4_VERSION:
                                 mnt->flags &= ~NFS_MOUNT_VER3;
                                 mnt->version = 4;
                                 break;
-#endif
                         default:
                                 goto out_invalid_value;
                         }
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 7bdec8531400..8fe9eb47a97f 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -496,7 +496,7 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry)
 
         dfprintk(VFS, "NFS: silly-rename(%s/%s, ct=%d)\n",
                 dentry->d_parent->d_name.name, dentry->d_name.name,
-                atomic_read(&dentry->d_count));
+                dentry->d_count);
         nfs_inc_stats(dir, NFSIOS_SILLYRENAME);
 
         /*
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 4c14c17a5276..10d648ea128b 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -390,6 +390,7 @@ static int nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
                 if (nfs_have_delegation(inode, FMODE_WRITE))
                         nfsi->change_attr++;
         }
+        set_bit(PG_MAPPED, &req->wb_flags);
         SetPagePrivate(req->wb_page);
         set_page_private(req->wb_page, (unsigned long)req);
         nfsi->npages++;
@@ -415,6 +416,7 @@ static void nfs_inode_remove_request(struct nfs_page *req)
         spin_lock(&inode->i_lock);
         set_page_private(req->wb_page, 0);
         ClearPagePrivate(req->wb_page);
+        clear_bit(PG_MAPPED, &req->wb_flags);
         radix_tree_delete(&nfsi->nfs_page_tree, req->wb_index);
         nfsi->npages--;
         if (!nfsi->npages) {
@@ -422,7 +424,6 @@ static void nfs_inode_remove_request(struct nfs_page *req)
                 iput(inode);
         } else
                 spin_unlock(&inode->i_lock);
-        nfs_clear_request(req);
         nfs_release_request(req);
 }
 
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 2a533a0af2a9..7e84a852cdae 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -260,9 +260,11 @@ void fill_post_wcc(struct svc_fh *fhp)
         err = vfs_getattr(fhp->fh_export->ex_path.mnt, fhp->fh_dentry,
                         &fhp->fh_post_attr);
         fhp->fh_post_change = fhp->fh_dentry->d_inode->i_version;
-        if (err)
+        if (err) {
                 fhp->fh_post_saved = 0;
-        else
+                /* Grab the ctime anyway - set_change_info might use it */
+                fhp->fh_post_attr.ctime = fhp->fh_dentry->d_inode->i_ctime;
+        } else
                 fhp->fh_post_saved = 1;
 }
 
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 116cab970e0f..fbd18c3074bb 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4336,7 +4336,7 @@ __nfs4_state_shutdown(void)
 void
 nfs4_state_shutdown(void)
 {
-        cancel_rearming_delayed_workqueue(laundry_wq, &laundromat_work);
+        cancel_delayed_work_sync(&laundromat_work);
         destroy_workqueue(laundry_wq);
         locks_end_grace(&nfsd4_manager);
         nfs4_lock_state();
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 184938fcff04..3a359023c9f7 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1756,8 +1756,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
                 goto out_dput_new;
 
         if (svc_msnfs(ffhp) &&
-                ((atomic_read(&odentry->d_count) > 1)
-                 || (atomic_read(&ndentry->d_count) > 1))) {
+                ((odentry->d_count > 1) || (ndentry->d_count > 1))) {
                         host_err = -EPERM;
                         goto out_dput_new;
         }
@@ -1843,7 +1842,7 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
         if (type != S_IFDIR) { /* It's UNLINK */
 #ifdef MSNFS
                 if ((fhp->fh_export->ex_flags & NFSEXP_MSNFS) &&
-                        (atomic_read(&rdentry->d_count) > 1)) {
+                        (rdentry->d_count > 1)) {
                         host_err = -EPERM;
                 } else
 #endif
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 4d476ff08ae6..60fce3dc5cb5 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -484,18 +484,17 @@ static inline bool nfsd4_not_cached(struct nfsd4_compoundres *resp)
 static inline void
 set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp)
 {
-        BUG_ON(!fhp->fh_pre_saved || !fhp->fh_post_saved);
-        cinfo->atomic = 1;
+        BUG_ON(!fhp->fh_pre_saved);
+        cinfo->atomic = fhp->fh_post_saved;
         cinfo->change_supported = IS_I_VERSION(fhp->fh_dentry->d_inode);
-        if (cinfo->change_supported) {
-                cinfo->before_change = fhp->fh_pre_change;
-                cinfo->after_change = fhp->fh_post_change;
-        } else {
-                cinfo->before_ctime_sec = fhp->fh_pre_ctime.tv_sec;
-                cinfo->before_ctime_nsec = fhp->fh_pre_ctime.tv_nsec;
-                cinfo->after_ctime_sec = fhp->fh_post_attr.ctime.tv_sec;
-                cinfo->after_ctime_nsec = fhp->fh_post_attr.ctime.tv_nsec;
-        }
+
+        cinfo->before_change = fhp->fh_pre_change;
+        cinfo->after_change = fhp->fh_post_change;
+        cinfo->before_ctime_sec = fhp->fh_pre_ctime.tv_sec;
+        cinfo->before_ctime_nsec = fhp->fh_pre_ctime.tv_nsec;
+        cinfo->after_ctime_sec = fhp->fh_post_attr.ctime.tv_sec;
+        cinfo->after_ctime_nsec = fhp->fh_post_attr.ctime.tv_nsec;
+
 }
 
 int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *, void *);
diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c
index 8b782b062baa..3ee67c67cc52 100644
--- a/fs/nilfs2/bmap.c
+++ b/fs/nilfs2/bmap.c
@@ -35,7 +35,20 @@
 
 struct inode *nilfs_bmap_get_dat(const struct nilfs_bmap *bmap)
 {
-        return nilfs_dat_inode(NILFS_I_NILFS(bmap->b_inode));
+        return NILFS_I_NILFS(bmap->b_inode)->ns_dat;
+}
+
+static int nilfs_bmap_convert_error(struct nilfs_bmap *bmap,
+                                     const char *fname, int err)
+{
+        struct inode *inode = bmap->b_inode;
+
+        if (err == -EINVAL) {
+                nilfs_error(inode->i_sb, fname,
+                            "broken bmap (inode number=%lu)\n", inode->i_ino);
+                err = -EIO;
+        }
+        return err;
 }
 
 /**
@@ -66,8 +79,10 @@ int nilfs_bmap_lookup_at_level(struct nilfs_bmap *bmap, __u64 key, int level,
 
         down_read(&bmap->b_sem);
         ret = bmap->b_ops->bop_lookup(bmap, key, level, ptrp);
-        if (ret < 0)
+        if (ret < 0) {
+                ret = nilfs_bmap_convert_error(bmap, __func__, ret);
                 goto out;
+        }
         if (NILFS_BMAP_USE_VBN(bmap)) {
                 ret = nilfs_dat_translate(nilfs_bmap_get_dat(bmap), *ptrp,
                                           &blocknr);
@@ -88,7 +103,8 @@ int nilfs_bmap_lookup_contig(struct nilfs_bmap *bmap, __u64 key, __u64 *ptrp,
         down_read(&bmap->b_sem);
         ret = bmap->b_ops->bop_lookup_contig(bmap, key, ptrp, maxblocks);
         up_read(&bmap->b_sem);
-        return ret;
+
+        return nilfs_bmap_convert_error(bmap, __func__, ret);
 }
 
 static int nilfs_bmap_do_insert(struct nilfs_bmap *bmap, __u64 key, __u64 ptr)
@@ -144,7 +160,8 @@ int nilfs_bmap_insert(struct nilfs_bmap *bmap,
         down_write(&bmap->b_sem);
         ret = nilfs_bmap_do_insert(bmap, key, rec);
         up_write(&bmap->b_sem);
-        return ret;
+
+        return nilfs_bmap_convert_error(bmap, __func__, ret);
 }
 
 static int nilfs_bmap_do_delete(struct nilfs_bmap *bmap, __u64 key)
@@ -180,9 +197,12 @@ int nilfs_bmap_last_key(struct nilfs_bmap *bmap, unsigned long *key)
 
         down_read(&bmap->b_sem);
         ret = bmap->b_ops->bop_last_key(bmap, &lastkey);
-        if (!ret)
-                *key = lastkey;
         up_read(&bmap->b_sem);
+
+        if (ret < 0)
+                ret = nilfs_bmap_convert_error(bmap, __func__, ret);
+        else
+                *key = lastkey;
         return ret;
 }
 
@@ -210,7 +230,8 @@ int nilfs_bmap_delete(struct nilfs_bmap *bmap, unsigned long key)
         down_write(&bmap->b_sem);
         ret = nilfs_bmap_do_delete(bmap, key);
         up_write(&bmap->b_sem);
-        return ret;
+
+        return nilfs_bmap_convert_error(bmap, __func__, ret);
 }
 
 static int nilfs_bmap_do_truncate(struct nilfs_bmap *bmap, unsigned long key)
@@ -261,7 +282,8 @@ int nilfs_bmap_truncate(struct nilfs_bmap *bmap, unsigned long key)
         down_write(&bmap->b_sem);
         ret = nilfs_bmap_do_truncate(bmap, key);
         up_write(&bmap->b_sem);
-        return ret;
+
+        return nilfs_bmap_convert_error(bmap, __func__, ret);
 }
 
 /**
@@ -300,7 +322,8 @@ int nilfs_bmap_propagate(struct nilfs_bmap *bmap, struct buffer_head *bh)
         down_write(&bmap->b_sem);
         ret = bmap->b_ops->bop_propagate(bmap, bh);
         up_write(&bmap->b_sem);
-        return ret;
+
+        return nilfs_bmap_convert_error(bmap, __func__, ret);
 }
 
 /**
@@ -344,7 +367,8 @@ int nilfs_bmap_assign(struct nilfs_bmap *bmap,
         down_write(&bmap->b_sem);
         ret = bmap->b_ops->bop_assign(bmap, bh, blocknr, binfo);
         up_write(&bmap->b_sem);
-        return ret;
+
+        return nilfs_bmap_convert_error(bmap, __func__, ret);
 }
 
 /**
@@ -373,7 +397,8 @@ int nilfs_bmap_mark(struct nilfs_bmap *bmap, __u64 key, int level)
         down_write(&bmap->b_sem);
         ret = bmap->b_ops->bop_mark(bmap, key, level);
         up_write(&bmap->b_sem);
-        return ret;
+
+        return nilfs_bmap_convert_error(bmap, __func__, ret);
 }
 
 /**
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index 5115814cb745..388e9e8f5286 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -104,8 +104,7 @@ int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr,
         if (pblocknr == 0) {
                 pblocknr = blocknr;
                 if (inode->i_ino != NILFS_DAT_INO) {
-                        struct inode *dat =
-                                nilfs_dat_inode(NILFS_I_NILFS(inode));
+                        struct inode *dat = NILFS_I_NILFS(inode)->ns_dat;
 
                         /* blocknr is a virtual block number */
                         err = nilfs_dat_translate(dat, blocknr, &pblocknr);
diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index cb003c8ee1f6..9d45773b79e6 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -91,7 +91,6 @@ static void nilfs_commit_chunk(struct page *page,
                                unsigned from, unsigned to)
 {
         struct inode *dir = mapping->host;
-        struct nilfs_sb_info *sbi = NILFS_SB(dir->i_sb);
         loff_t pos = page_offset(page) + from;
         unsigned len = to - from;
         unsigned nr_dirty, copied;
@@ -103,7 +102,7 @@ static void nilfs_commit_chunk(struct page *page,
                 i_size_write(dir, pos + copied);
         if (IS_DIRSYNC(dir))
                 nilfs_set_transaction_flag(NILFS_TI_SYNC);
-        err = nilfs_set_file_dirty(sbi, dir, nr_dirty);
+        err = nilfs_set_file_dirty(dir, nr_dirty);
         WARN_ON(err); /* do not happen */
         unlock_page(page);
 }
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index c9a30d7ff6fc..2f560c9fb808 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -155,6 +155,7 @@ const struct inode_operations nilfs_file_inode_operations = {
         .truncate       = nilfs_truncate,
         .setattr        = nilfs_setattr,
         .permission     = nilfs_permission,
+        .fiemap         = nilfs_fiemap,
 };
 
 /* end of file */
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index 33ad25ddd5c4..caf9a6a3fb54 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -176,7 +176,6 @@ int nilfs_gccache_wait_and_mark_dirty(struct buffer_head *bh)
 int nilfs_init_gcinode(struct inode *inode)
 {
         struct nilfs_inode_info *ii = NILFS_I(inode);
-        struct the_nilfs *nilfs = NILFS_SB(inode->i_sb)->s_nilfs;
 
         inode->i_mode = S_IFREG;
         mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
@@ -186,14 +185,6 @@ int nilfs_init_gcinode(struct inode *inode)
         ii->i_flags = 0;
         nilfs_bmap_init_gc(ii->i_bmap);
 
-        /*
-         * Add the inode to GC inode list. Garbage Collection
-         * is serialized and no two processes manipulate the
-         * list simultaneously.
-         */
-        igrab(inode);
-        list_add(&NILFS_I(inode)->i_dirty, &nilfs->ns_gc_inodes);
-
         return 0;
 }
 
diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c
index 9f8a2da67f90..bfc73d3a30ed 100644
--- a/fs/nilfs2/ifile.c
+++ b/fs/nilfs2/ifile.c
@@ -149,14 +149,9 @@ int nilfs_ifile_get_inode_block(struct inode *ifile, ino_t ino,
         }
 
         err = nilfs_palloc_get_entry_block(ifile, ino, 0, out_bh);
-        if (unlikely(err)) {
-                if (err == -EINVAL)
-                        nilfs_error(sb, __func__, "ifile is broken");
-                else
-                        nilfs_warning(sb, __func__,
-                                      "unable to read inode: %lu",
-                                      (unsigned long) ino);
-        }
+        if (unlikely(err))
+                nilfs_warning(sb, __func__, "unable to read inode: %lu",
+                              (unsigned long) ino);
         return err;
 }
 
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 71d4bc8464e0..2fd440d8d6b8 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -58,7 +58,7 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff,
         struct nilfs_inode_info *ii = NILFS_I(inode);
         __u64 blknum = 0;
         int err = 0, ret;
-        struct inode *dat = nilfs_dat_inode(NILFS_I_NILFS(inode));
+        struct inode *dat = NILFS_I_NILFS(inode)->ns_dat;
         unsigned maxblocks = bh_result->b_size >> inode->i_blkbits;
 
         down_read(&NILFS_MDT(dat)->mi_sem);
@@ -96,11 +96,6 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff,
                                        inode->i_ino,
                                        (unsigned long long)blkoff);
                                 err = 0;
-                        } else if (err == -EINVAL) {
-                                nilfs_error(inode->i_sb, __func__,
-                                            "broken bmap (inode=%lu)\n",
-                                            inode->i_ino);
-                                err = -EIO;
                         }
                         nilfs_transaction_abort(inode->i_sb);
                         goto out;
@@ -109,6 +104,7 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff,
                 nilfs_transaction_commit(inode->i_sb); /* never fails */
                 /* Error handling should be detailed */
                 set_buffer_new(bh_result);
+                set_buffer_delay(bh_result);
                 map_bh(bh_result, inode->i_sb, 0); /* dbn must be changed
                                                       to proper value */
         } else if (ret == -ENOENT) {
@@ -185,10 +181,9 @@ static int nilfs_set_page_dirty(struct page *page)
 
         if (ret) {
                 struct inode *inode = page->mapping->host;
-                struct nilfs_sb_info *sbi = NILFS_SB(inode->i_sb);
                 unsigned nr_dirty = 1 << (PAGE_SHIFT - inode->i_blkbits);
 
-                nilfs_set_file_dirty(sbi, inode, nr_dirty);
+                nilfs_set_file_dirty(inode, nr_dirty);
         }
         return ret;
 }
@@ -229,7 +224,7 @@ static int nilfs_write_end(struct file *file, struct address_space *mapping,
                                                   start + copied);
         copied = generic_write_end(file, mapping, pos, len, copied, page,
                                    fsdata);
-        nilfs_set_file_dirty(NILFS_SB(inode->i_sb), inode, nr_dirty);
+        nilfs_set_file_dirty(inode, nr_dirty);
         err = nilfs_transaction_commit(inode->i_sb);
         return err ? : copied;
 }
@@ -425,13 +420,12 @@ static int __nilfs_read_inode(struct super_block *sb,
                               struct nilfs_root *root, unsigned long ino,
                               struct inode *inode)
 {
-        struct nilfs_sb_info *sbi = NILFS_SB(sb);
-        struct inode *dat = nilfs_dat_inode(sbi->s_nilfs);
+        struct the_nilfs *nilfs = NILFS_SB(sb)->s_nilfs;
         struct buffer_head *bh;
         struct nilfs_inode *raw_inode;
         int err;
 
-        down_read(&NILFS_MDT(dat)->mi_sem);     /* XXX */
+        down_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
         err = nilfs_ifile_get_inode_block(root->ifile, ino, &bh);
         if (unlikely(err))
                 goto bad_inode;
@@ -461,7 +455,7 @@ static int __nilfs_read_inode(struct super_block *sb,
         }
         nilfs_ifile_unmap_inode(root->ifile, ino, bh);
         brelse(bh);
-        up_read(&NILFS_MDT(dat)->mi_sem);       /* XXX */
+        up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
         nilfs_set_inode_flags(inode);
         return 0;
 
@@ -470,7 +464,7 @@ static int __nilfs_read_inode(struct super_block *sb,
         brelse(bh);
 
  bad_inode:
-        up_read(&NILFS_MDT(dat)->mi_sem);       /* XXX */
+        up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
         return err;
 }
 
@@ -629,7 +623,7 @@ static void nilfs_truncate_bmap(struct nilfs_inode_info *ii,
 
         if (!test_bit(NILFS_I_BMAP, &ii->i_state))
                 return;
- repeat:
+repeat:
         ret = nilfs_bmap_last_key(ii->i_bmap, &b);
         if (ret == -ENOENT)
                 return;
@@ -646,14 +640,10 @@ static void nilfs_truncate_bmap(struct nilfs_inode_info *ii,
                      nilfs_bmap_truncate(ii->i_bmap, b) == 0))
                 goto repeat;
 
- failed:
-        if (ret == -EINVAL)
-                nilfs_error(ii->vfs_inode.i_sb, __func__,
-                            "bmap is broken (ino=%lu)", ii->vfs_inode.i_ino);
-        else
-                nilfs_warning(ii->vfs_inode.i_sb, __func__,
-                              "failed to truncate bmap (ino=%lu, err=%d)",
-                              ii->vfs_inode.i_ino, ret);
+failed:
+        nilfs_warning(ii->vfs_inode.i_sb, __func__,
+                      "failed to truncate bmap (ino=%lu, err=%d)",
+                      ii->vfs_inode.i_ino, ret);
 }
 
 void nilfs_truncate(struct inode *inode)
@@ -682,7 +672,7 @@ void nilfs_truncate(struct inode *inode)
                 nilfs_set_transaction_flag(NILFS_TI_SYNC);
 
         nilfs_mark_inode_dirty(inode);
-        nilfs_set_file_dirty(NILFS_SB(sb), inode, 0);
+        nilfs_set_file_dirty(inode, 0);
         nilfs_transaction_commit(sb);
         /* May construct a logical segment and may fail in sync mode.
            But truncate has no return value. */
@@ -785,20 +775,24 @@ out_err:
         return err;
 }
 
-int nilfs_permission(struct inode *inode, int mask)
+int nilfs_permission(struct inode *inode, int mask, unsigned int flags)
 {
-        struct nilfs_root *root = NILFS_I(inode)->i_root;
+        struct nilfs_root *root;
 
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
+        root = NILFS_I(inode)->i_root;
         if ((mask & MAY_WRITE) && root &&
             root->cno != NILFS_CPTREE_CURRENT_CNO)
                 return -EROFS; /* snapshot is not writable */
 
-        return generic_permission(inode, mask, NULL);
+        return generic_permission(inode, mask, flags, NULL);
 }
 
-int nilfs_load_inode_block(struct nilfs_sb_info *sbi, struct inode *inode,
-                           struct buffer_head **pbh)
+int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh)
 {
+        struct nilfs_sb_info *sbi = NILFS_SB(inode->i_sb);
         struct nilfs_inode_info *ii = NILFS_I(inode);
         int err;
 
@@ -839,9 +833,9 @@ int nilfs_inode_dirty(struct inode *inode)
         return ret;
 }
 
-int nilfs_set_file_dirty(struct nilfs_sb_info *sbi, struct inode *inode,
-                         unsigned nr_dirty)
+int nilfs_set_file_dirty(struct inode *inode, unsigned nr_dirty)
 {
+        struct nilfs_sb_info *sbi = NILFS_SB(inode->i_sb);
         struct nilfs_inode_info *ii = NILFS_I(inode);
 
         atomic_add(nr_dirty, &sbi->s_nilfs->ns_ndirtyblks);
@@ -874,11 +868,10 @@ int nilfs_set_file_dirty(struct nilfs_sb_info *sbi, struct inode *inode,
 
 int nilfs_mark_inode_dirty(struct inode *inode)
 {
-        struct nilfs_sb_info *sbi = NILFS_SB(inode->i_sb);
         struct buffer_head *ibh;
         int err;
 
-        err = nilfs_load_inode_block(sbi, inode, &ibh);
+        err = nilfs_load_inode_block(inode, &ibh);
         if (unlikely(err)) {
                 nilfs_warning(inode->i_sb, __func__,
                               "failed to reget inode block.\n");
@@ -920,3 +913,134 @@ void nilfs_dirty_inode(struct inode *inode)
         nilfs_mark_inode_dirty(inode);
         nilfs_transaction_commit(inode->i_sb); /* never fails */
 }
+
+int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+                 __u64 start, __u64 len)
+{
+        struct the_nilfs *nilfs = NILFS_I_NILFS(inode);
+        __u64 logical = 0, phys = 0, size = 0;
+        __u32 flags = 0;
+        loff_t isize;
+        sector_t blkoff, end_blkoff;
+        sector_t delalloc_blkoff;
+        unsigned long delalloc_blklen;
+        unsigned int blkbits = inode->i_blkbits;
+        int ret, n;
+
+        ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
+        if (ret)
+                return ret;
+
+        mutex_lock(&inode->i_mutex);
+
+        isize = i_size_read(inode);
+
+        blkoff = start >> blkbits;
+        end_blkoff = (start + len - 1) >> blkbits;
+
+        delalloc_blklen = nilfs_find_uncommitted_extent(inode, blkoff,
+                                                        &delalloc_blkoff);
+
+        do {
+                __u64 blkphy;
+                unsigned int maxblocks;
+
+                if (delalloc_blklen && blkoff == delalloc_blkoff) {
+                        if (size) {
+                                /* End of the current extent */
+                                ret = fiemap_fill_next_extent(
+                                        fieinfo, logical, phys, size, flags);
+                                if (ret)
+                                        break;
+                        }
+                        if (blkoff > end_blkoff)
+                                break;
+
+                        flags = FIEMAP_EXTENT_MERGED | FIEMAP_EXTENT_DELALLOC;
+                        logical = blkoff << blkbits;
+                        phys = 0;
+                        size = delalloc_blklen << blkbits;
+
+                        blkoff = delalloc_blkoff + delalloc_blklen;
+                        delalloc_blklen = nilfs_find_uncommitted_extent(
+                                inode, blkoff, &delalloc_blkoff);
+                        continue;
+                }
+
+                /*
+                 * Limit the number of blocks that we look up so as
+                 * not to get into the next delayed allocation extent.
+                 */
+                maxblocks = INT_MAX;
+                if (delalloc_blklen)
+                        maxblocks = min_t(sector_t, delalloc_blkoff - blkoff,
+                                          maxblocks);
+                blkphy = 0;
+
+                down_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
+                n = nilfs_bmap_lookup_contig(
+                        NILFS_I(inode)->i_bmap, blkoff, &blkphy, maxblocks);
+                up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
+
+                if (n < 0) {
+                        int past_eof;
+
+                        if (unlikely(n != -ENOENT))
+                                break; /* error */
+
+                        /* HOLE */
+                        blkoff++;
+                        past_eof = ((blkoff << blkbits) >= isize);
+
+                        if (size) {
+                                /* End of the current extent */
+
+                                if (past_eof)
+                                        flags |= FIEMAP_EXTENT_LAST;
+
+                                ret = fiemap_fill_next_extent(
+                                        fieinfo, logical, phys, size, flags);
+                                if (ret)
+                                        break;
+                                size = 0;
+                        }
+                        if (blkoff > end_blkoff || past_eof)
+                                break;
+                } else {
+                        if (size) {
+                                if (phys && blkphy << blkbits == phys + size) {
+                                        /* The current extent goes on */
+                                        size += n << blkbits;
+                                } else {
+                                        /* Terminate the current extent */
+                                        ret = fiemap_fill_next_extent(
+                                                fieinfo, logical, phys, size,
+                                                flags);
+                                        if (ret || blkoff > end_blkoff)
+                                                break;
+
+                                        /* Start another extent */
+                                        flags = FIEMAP_EXTENT_MERGED;
+                                        logical = blkoff << blkbits;
+                                        phys = blkphy << blkbits;
+                                        size = n << blkbits;
+                                }
+                        } else {
+                                /* Start a new extent */
+                                flags = FIEMAP_EXTENT_MERGED;
+                                logical = blkoff << blkbits;
+                                phys = blkphy << blkbits;
+                                size = n << blkbits;
+                        }
+                        blkoff += n;
+                }
+                cond_resched();
+        } while (true);
+
+        /* If ret is 1 then we just hit the end of the extent array */
+        if (ret == 1)
+                ret = 0;
+
+        mutex_unlock(&inode->i_mutex);
+        return ret;
+}
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index e00d9457c256..496738963fdb 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -233,7 +233,7 @@ nilfs_ioctl_do_get_vinfo(struct the_nilfs *nilfs, __u64 *posp, int flags,
         int ret;
 
         down_read(&nilfs->ns_segctor_sem);
-        ret = nilfs_dat_get_vinfo(nilfs_dat_inode(nilfs), buf, size, nmembs);
+        ret = nilfs_dat_get_vinfo(nilfs->ns_dat, buf, size, nmembs);
         up_read(&nilfs->ns_segctor_sem);
         return ret;
 }
@@ -242,8 +242,7 @@ static ssize_t
 nilfs_ioctl_do_get_bdescs(struct the_nilfs *nilfs, __u64 *posp, int flags,
                           void *buf, size_t size, size_t nmembs)
 {
-        struct inode *dat = nilfs_dat_inode(nilfs);
-        struct nilfs_bmap *bmap = NILFS_I(dat)->i_bmap;
+        struct nilfs_bmap *bmap = NILFS_I(nilfs->ns_dat)->i_bmap;
         struct nilfs_bdesc *bdescs = buf;
         int ret, i;
 
@@ -337,6 +336,7 @@ static int nilfs_ioctl_move_blocks(struct super_block *sb,
                                    struct nilfs_argv *argv, void *buf)
 {
         size_t nmembs = argv->v_nmembs;
+        struct the_nilfs *nilfs = NILFS_SB(sb)->s_nilfs;
         struct inode *inode;
         struct nilfs_vdesc *vdesc;
         struct buffer_head *bh, *n;
@@ -353,6 +353,17 @@ static int nilfs_ioctl_move_blocks(struct super_block *sb,
                         ret = PTR_ERR(inode);
                         goto failed;
                 }
+                if (list_empty(&NILFS_I(inode)->i_dirty)) {
+                        /*
+                         * Add the inode to GC inode list. Garbage Collection
+                         * is serialized and no two processes manipulate the
+                         * list simultaneously.
+                         */
+                        igrab(inode);
+                        list_add(&NILFS_I(inode)->i_dirty,
+                                 &nilfs->ns_gc_inodes);
+                }
+
                 do {
                         ret = nilfs_ioctl_move_inode_block(inode, vdesc,
                                                            &buffers);
@@ -409,7 +420,7 @@ static int nilfs_ioctl_free_vblocknrs(struct the_nilfs *nilfs,
         size_t nmembs = argv->v_nmembs;
         int ret;
 
-        ret = nilfs_dat_freev(nilfs_dat_inode(nilfs), buf, nmembs);
+        ret = nilfs_dat_freev(nilfs->ns_dat, buf, nmembs);
 
         return (ret < 0) ? ret : nmembs;
 }
@@ -418,8 +429,7 @@ static int nilfs_ioctl_mark_blocks_dirty(struct the_nilfs *nilfs,
                                          struct nilfs_argv *argv, void *buf)
 {
         size_t nmembs = argv->v_nmembs;
-        struct inode *dat = nilfs_dat_inode(nilfs);
-        struct nilfs_bmap *bmap = NILFS_I(dat)->i_bmap;
+        struct nilfs_bmap *bmap = NILFS_I(nilfs->ns_dat)->i_bmap;
         struct nilfs_bdesc *bdescs = buf;
         int ret, i;
 
@@ -438,7 +448,7 @@ static int nilfs_ioctl_mark_blocks_dirty(struct the_nilfs *nilfs,
                         /* skip dead block */
                         continue;
                 if (bdescs[i].bd_level == 0) {
-                        ret = nilfs_mdt_mark_block_dirty(dat,
+                        ret = nilfs_mdt_mark_block_dirty(nilfs->ns_dat,
                                                          bdescs[i].bd_offset);
                         if (ret < 0) {
                                 WARN_ON(ret == -ENOENT);
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index 39a5b84e2c9f..6a0e2a189f60 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -237,8 +237,6 @@ static int nilfs_mdt_read_block(struct inode *inode, unsigned long block,
  *
  * %-ENOENT - the specified block does not exist (hole block)
  *
- * %-EINVAL - bmap is broken. (the caller should call nilfs_error())
- *
  * %-EROFS - Read only filesystem (for create mode)
  */
 int nilfs_mdt_get_block(struct inode *inode, unsigned long blkoff, int create,
@@ -273,8 +271,6 @@ int nilfs_mdt_get_block(struct inode *inode, unsigned long blkoff, int create,
  * %-ENOMEM - Insufficient memory available.
  *
  * %-EIO - I/O error
- *
- * %-EINVAL - bmap is broken. (the caller should call nilfs_error())
  */
 int nilfs_mdt_delete_block(struct inode *inode, unsigned long block)
 {
@@ -350,8 +346,6 @@ int nilfs_mdt_forget_block(struct inode *inode, unsigned long block)
  * %-EIO - I/O error
  *
  * %-ENOENT - the specified block does not exist (hole block)
- *
- * %-EINVAL - bmap is broken. (the caller should call nilfs_error())
  */
 int nilfs_mdt_mark_block_dirty(struct inode *inode, unsigned long block)
 {
@@ -499,31 +493,29 @@ int nilfs_mdt_freeze_buffer(struct inode *inode, struct buffer_head *bh)
         struct buffer_head *bh_frozen;
         struct page *page;
         int blkbits = inode->i_blkbits;
-        int ret = -ENOMEM;
 
         page = grab_cache_page(&shadow->frozen_data, bh->b_page->index);
         if (!page)
-                return ret;
+                return -ENOMEM;
 
         if (!page_has_buffers(page))
                 create_empty_buffers(page, 1 << blkbits, 0);
 
         bh_frozen = nilfs_page_get_nth_block(page, bh_offset(bh) >> blkbits);
-        if (bh_frozen) {
-                if (!buffer_uptodate(bh_frozen))
-                        nilfs_copy_buffer(bh_frozen, bh);
-                if (list_empty(&bh_frozen->b_assoc_buffers)) {
-                        list_add_tail(&bh_frozen->b_assoc_buffers,
-                                      &shadow->frozen_buffers);
-                        set_buffer_nilfs_redirected(bh);
-                } else {
-                        brelse(bh_frozen); /* already frozen */
-                }
-                ret = 0;
+
+        if (!buffer_uptodate(bh_frozen))
+                nilfs_copy_buffer(bh_frozen, bh);
+        if (list_empty(&bh_frozen->b_assoc_buffers)) {
+                list_add_tail(&bh_frozen->b_assoc_buffers,
+                              &shadow->frozen_buffers);
+                set_buffer_nilfs_redirected(bh);
+        } else {
+                brelse(bh_frozen); /* already frozen */
         }
+
         unlock_page(page);
         page_cache_release(page);
-        return ret;
+        return 0;
 }
 
 struct buffer_head *
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 6e9557ecf161..98034271cd02 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -577,6 +577,7 @@ const struct inode_operations nilfs_dir_inode_operations = {
         .rename         = nilfs_rename,
         .setattr        = nilfs_setattr,
         .permission     = nilfs_permission,
+        .fiemap         = nilfs_fiemap,
 };
 
 const struct inode_operations nilfs_special_inode_operations = {
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index f7560da5a567..777e8fd04304 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -190,11 +190,6 @@ static inline int nilfs_doing_construction(void)
         return nilfs_test_transaction_flag(NILFS_TI_WRITER);
 }
 
-static inline struct inode *nilfs_dat_inode(const struct the_nilfs *nilfs)
-{
-        return nilfs->ns_dat;
-}
-
 /*
  * function prototype
  */
@@ -256,14 +251,14 @@ extern void nilfs_update_inode(struct inode *, struct buffer_head *);
 extern void nilfs_truncate(struct inode *);
 extern void nilfs_evict_inode(struct inode *);
 extern int nilfs_setattr(struct dentry *, struct iattr *);
-int nilfs_permission(struct inode *inode, int mask);
-extern int nilfs_load_inode_block(struct nilfs_sb_info *, struct inode *,
-                                  struct buffer_head **);
+int nilfs_permission(struct inode *inode, int mask, unsigned int flags);
+int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh);
 extern int nilfs_inode_dirty(struct inode *);
-extern int nilfs_set_file_dirty(struct nilfs_sb_info *, struct inode *,
-                                unsigned);
+int nilfs_set_file_dirty(struct inode *inode, unsigned nr_dirty);
 extern int nilfs_mark_inode_dirty(struct inode *);
 extern void nilfs_dirty_inode(struct inode *);
+int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+                 __u64 start, __u64 len);
 
 /* super.c */
 extern struct inode *nilfs_alloc_inode(struct super_block *);
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index a6c3c2e817f8..0c432416cfef 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -491,7 +491,7 @@ unsigned nilfs_page_count_clean_buffers(struct page *page,
         }
         return nc;
 }
- 
+
 void nilfs_mapping_init_once(struct address_space *mapping)
 {
         memset(mapping, 0, sizeof(*mapping));
@@ -546,3 +546,87 @@ int __nilfs_clear_page_dirty(struct page *page)
         }
         return TestClearPageDirty(page);
 }
+
+/**
+ * nilfs_find_uncommitted_extent - find extent of uncommitted data
+ * @inode: inode
+ * @start_blk: start block offset (in)
+ * @blkoff: start offset of the found extent (out)
+ *
+ * This function searches an extent of buffers marked "delayed" which
+ * starts from a block offset equal to or larger than @start_blk.  If
+ * such an extent was found, this will store the start offset in
+ * @blkoff and return its length in blocks.  Otherwise, zero is
+ * returned.
+ */
+unsigned long nilfs_find_uncommitted_extent(struct inode *inode,
+                                            sector_t start_blk,
+                                            sector_t *blkoff)
+{
+        unsigned int i;
+        pgoff_t index;
+        unsigned int nblocks_in_page;
+        unsigned long length = 0;
+        sector_t b;
+        struct pagevec pvec;
+        struct page *page;
+
+        if (inode->i_mapping->nrpages == 0)
+                return 0;
+
+        index = start_blk >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+        nblocks_in_page = 1U << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+        pagevec_init(&pvec, 0);
+
+repeat:
+        pvec.nr = find_get_pages_contig(inode->i_mapping, index, PAGEVEC_SIZE,
+                                        pvec.pages);
+        if (pvec.nr == 0)
+                return length;
+
+        if (length > 0 && pvec.pages[0]->index > index)
+                goto out;
+
+        b = pvec.pages[0]->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+        i = 0;
+        do {
+                page = pvec.pages[i];
+
+                lock_page(page);
+                if (page_has_buffers(page)) {
+                        struct buffer_head *bh, *head;
+
+                        bh = head = page_buffers(page);
+                        do {
+                                if (b < start_blk)
+                                        continue;
+                                if (buffer_delay(bh)) {
+                                        if (length == 0)
+                                                *blkoff = b;
+                                        length++;
+                                } else if (length > 0) {
+                                        goto out_locked;
+                                }
+                        } while (++b, bh = bh->b_this_page, bh != head);
+                } else {
+                        if (length > 0)
+                                goto out_locked;
+
+                        b += nblocks_in_page;
+                }
+                unlock_page(page);
+
+        } while (++i < pagevec_count(&pvec));
+
+        index = page->index + 1;
+        pagevec_release(&pvec);
+        cond_resched();
+        goto repeat;
+
+out_locked:
+        unlock_page(page);
+out:
+        pagevec_release(&pvec);
+        return length;
+}
diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h
index fb9e8a8a2038..622df27cd891 100644
--- a/fs/nilfs2/page.h
+++ b/fs/nilfs2/page.h
@@ -66,6 +66,9 @@ void nilfs_mapping_init(struct address_space *mapping,
                         struct backing_dev_info *bdi,
                         const struct address_space_operations *aops);
 unsigned nilfs_page_count_clean_buffers(struct page *, unsigned, unsigned);
+unsigned long nilfs_find_uncommitted_extent(struct inode *inode,
+                                            sector_t start_blk,
+                                            sector_t *blkoff);
 
 #define NILFS_PAGE_BUG(page, m, a...) \
         do { nilfs_page_bug(page); BUG(); } while (0)
diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index 5d2711c28da7..3dfcd3b7d389 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -535,7 +535,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
                 if (unlikely(err))
                         goto failed_page;
 
-                err = nilfs_set_file_dirty(sbi, inode, 1);
+                err = nilfs_set_file_dirty(inode, 1);
                 if (unlikely(err))
                         goto failed_page;
 
diff --git a/fs/nilfs2/sb.h b/fs/nilfs2/sb.h
index 35a07157b980..7a17715f215f 100644
--- a/fs/nilfs2/sb.h
+++ b/fs/nilfs2/sb.h
@@ -27,14 +27,6 @@
 #include <linux/types.h>
 #include <linux/fs.h>
 
-/*
- * Mount options
- */
-struct nilfs_mount_options {
-        unsigned long mount_opt;
-        __u64 snapshot_cno;
-};
-
 struct the_nilfs;
 struct nilfs_sc_info;
 
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 687d090cea34..55ebae5c7f39 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -504,17 +504,6 @@ static int nilfs_segctor_add_file_block(struct nilfs_sc_info *sci,
         return err;
 }
 
-static int nilfs_handle_bmap_error(int err, const char *fname,
-                                   struct inode *inode, struct super_block *sb)
-{
-        if (err == -EINVAL) {
-                nilfs_error(sb, fname, "broken bmap (inode=%lu)\n",
-                            inode->i_ino);
-                err = -EIO;
-        }
-        return err;
-}
-
 /*
  * Callback functions that enumerate, mark, and collect dirty blocks
  */
@@ -524,9 +513,8 @@ static int nilfs_collect_file_data(struct nilfs_sc_info *sci,
         int err;
 
         err = nilfs_bmap_propagate(NILFS_I(inode)->i_bmap, bh);
-        if (unlikely(err < 0))
-                return nilfs_handle_bmap_error(err, __func__, inode,
-                                               sci->sc_super);
+        if (err < 0)
+                return err;
 
         err = nilfs_segctor_add_file_block(sci, bh, inode,
                                            sizeof(struct nilfs_binfo_v));
@@ -539,13 +527,7 @@ static int nilfs_collect_file_node(struct nilfs_sc_info *sci,
                                    struct buffer_head *bh,
                                    struct inode *inode)
 {
-        int err;
-
-        err = nilfs_bmap_propagate(NILFS_I(inode)->i_bmap, bh);
-        if (unlikely(err < 0))
-                return nilfs_handle_bmap_error(err, __func__, inode,
-                                               sci->sc_super);
-        return 0;
+        return nilfs_bmap_propagate(NILFS_I(inode)->i_bmap, bh);
 }
 
 static int nilfs_collect_file_bmap(struct nilfs_sc_info *sci,
@@ -588,9 +570,8 @@ static int nilfs_collect_dat_data(struct nilfs_sc_info *sci,
         int err;
 
         err = nilfs_bmap_propagate(NILFS_I(inode)->i_bmap, bh);
-        if (unlikely(err < 0))
-                return nilfs_handle_bmap_error(err, __func__, inode,
-                                               sci->sc_super);
+        if (err < 0)
+                return err;
 
         err = nilfs_segctor_add_file_block(sci, bh, inode, sizeof(__le64));
         if (!err)
@@ -776,9 +757,8 @@ static int nilfs_test_metadata_dirty(struct the_nilfs *nilfs,
                 ret++;
         if (nilfs_mdt_fetch_dirty(nilfs->ns_sufile))
                 ret++;
-        if (ret || nilfs_doing_gc())
-                if (nilfs_mdt_fetch_dirty(nilfs_dat_inode(nilfs)))
-                        ret++;
+        if ((ret || nilfs_doing_gc()) && nilfs_mdt_fetch_dirty(nilfs->ns_dat))
+                ret++;
         return ret;
 }
 
@@ -814,7 +794,7 @@ static void nilfs_segctor_clear_metadata_dirty(struct nilfs_sc_info *sci)
         nilfs_mdt_clear_dirty(sci->sc_root->ifile);
         nilfs_mdt_clear_dirty(nilfs->ns_cpfile);
         nilfs_mdt_clear_dirty(nilfs->ns_sufile);
-        nilfs_mdt_clear_dirty(nilfs_dat_inode(nilfs));
+        nilfs_mdt_clear_dirty(nilfs->ns_dat);
 }
 
 static int nilfs_segctor_create_checkpoint(struct nilfs_sc_info *sci)
@@ -923,7 +903,7 @@ static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci,
                               nilfs->ns_nongc_ctime : sci->sc_seg_ctime);
         raw_sr->sr_flags = 0;
 
-        nilfs_write_inode_common(nilfs_dat_inode(nilfs), (void *)raw_sr +
+        nilfs_write_inode_common(nilfs->ns_dat, (void *)raw_sr +
                                  NILFS_SR_DAT_OFFSET(isz), 1);
         nilfs_write_inode_common(nilfs->ns_cpfile, (void *)raw_sr +
                                  NILFS_SR_CPFILE_OFFSET(isz), 1);
@@ -1179,7 +1159,7 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
                 sci->sc_stage.scnt++;  /* Fall through */
         case NILFS_ST_DAT:
  dat_stage:
-                err = nilfs_segctor_scan_file(sci, nilfs_dat_inode(nilfs),
+                err = nilfs_segctor_scan_file(sci, nilfs->ns_dat,
                                               &nilfs_sc_dat_ops);
                 if (unlikely(err))
                         break;
@@ -1563,7 +1543,6 @@ nilfs_segctor_update_payload_blocknr(struct nilfs_sc_info *sci,
         return 0;
 
  failed_bmap:
-        err = nilfs_handle_bmap_error(err, __func__, inode, sci->sc_super);
         return err;
 }
 
@@ -1783,6 +1762,7 @@ static void nilfs_clear_copied_buffers(struct list_head *list, int err)
                                 if (!err) {
                                         set_buffer_uptodate(bh);
                                         clear_buffer_dirty(bh);
+                                        clear_buffer_delay(bh);
                                         clear_buffer_nilfs_volatile(bh);
                                 }
                                 brelse(bh); /* for b_assoc_buffers */
@@ -1909,6 +1889,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
                                     b_assoc_buffers) {
                         set_buffer_uptodate(bh);
                         clear_buffer_dirty(bh);
+                        clear_buffer_delay(bh);
                         clear_buffer_nilfs_volatile(bh);
                         clear_buffer_nilfs_redirected(bh);
                         if (bh == segbuf->sb_super_root) {
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index f804d41ec9d3..70dfdd532b83 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -47,7 +47,6 @@
 #include <linux/crc32.h>
 #include <linux/vfs.h>
 #include <linux/writeback.h>
-#include <linux/kobject.h>
 #include <linux/seq_file.h>
 #include <linux/mount.h>
 #include "nilfs.h"
@@ -111,12 +110,17 @@ void nilfs_error(struct super_block *sb, const char *function,
                  const char *fmt, ...)
 {
         struct nilfs_sb_info *sbi = NILFS_SB(sb);
+        struct va_format vaf;
         va_list args;
 
         va_start(args, fmt);
-        printk(KERN_CRIT "NILFS error (device %s): %s: ", sb->s_id, function);
-        vprintk(fmt, args);
-        printk("\n");
+
+        vaf.fmt = fmt;
+        vaf.va = &args;
+
+        printk(KERN_CRIT "NILFS error (device %s): %s: %pV\n",
+               sb->s_id, function, &vaf);
+
         va_end(args);
 
         if (!(sb->s_flags & MS_RDONLY)) {
@@ -136,13 +140,17 @@ void nilfs_error(struct super_block *sb, const char *function,
 void nilfs_warning(struct super_block *sb, const char *function,
                    const char *fmt, ...)
 {
+        struct va_format vaf;
         va_list args;
 
         va_start(args, fmt);
-        printk(KERN_WARNING "NILFS warning (device %s): %s: ",
-               sb->s_id, function);
-        vprintk(fmt, args);
-        printk("\n");
+
+        vaf.fmt = fmt;
+        vaf.va = &args;
+
+        printk(KERN_WARNING "NILFS warning (device %s): %s: %pV\n",
+               sb->s_id, function, &vaf);
+
         va_end(args);
 }
 
@@ -162,10 +170,13 @@ struct inode *nilfs_alloc_inode(struct super_block *sb)
         return &ii->vfs_inode;
 }
 
-void nilfs_destroy_inode(struct inode *inode)
+static void nilfs_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
         struct nilfs_mdt_info *mdi = NILFS_MDT(inode);
 
+        INIT_LIST_HEAD(&inode->i_dentry);
+
         if (mdi) {
                 kfree(mdi->mi_bgl); /* kfree(NULL) is safe */
                 kfree(mdi);
@@ -173,6 +184,11 @@ void nilfs_destroy_inode(struct inode *inode)
         kmem_cache_free(nilfs_inode_cachep, NILFS_I(inode));
 }
 
+void nilfs_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, nilfs_i_callback);
+}
+
 static int nilfs_sync_super(struct nilfs_sb_info *sbi, int flag)
 {
         struct the_nilfs *nilfs = sbi->s_nilfs;
@@ -838,7 +854,7 @@ static int nilfs_attach_snapshot(struct super_block *s, __u64 cno,
 
 static int nilfs_tree_was_touched(struct dentry *root_dentry)
 {
-        return atomic_read(&root_dentry->d_count) > 1;
+        return root_dentry->d_count > 1;
 }
 
 /**
@@ -1002,11 +1018,11 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data)
         struct nilfs_sb_info *sbi = NILFS_SB(sb);
         struct the_nilfs *nilfs = sbi->s_nilfs;
         unsigned long old_sb_flags;
-        struct nilfs_mount_options old_opts;
+        unsigned long old_mount_opt;
         int err;
 
         old_sb_flags = sb->s_flags;
-        old_opts.mount_opt = sbi->s_mount_opt;
+        old_mount_opt = sbi->s_mount_opt;
 
         if (!parse_options(data, sb, 1)) {
                 err = -EINVAL;
@@ -1075,7 +1091,7 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data)
 
  restore_opts:
         sb->s_flags = old_sb_flags;
-        sbi->s_mount_opt = old_opts.mount_opt;
+        sbi->s_mount_opt = old_mount_opt;
         return err;
 }
 
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 0254be2d73c6..ad4ac607cf57 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -329,7 +329,6 @@ int load_nilfs(struct the_nilfs *nilfs, struct nilfs_sb_info *sbi)
         printk(KERN_INFO "NILFS: recovery complete.\n");
 
  skip_recovery:
-        set_nilfs_loaded(nilfs);
         nilfs_clear_recovery_info(&ri);
         sbi->s_super->s_flags = s_flags;
         return 0;
@@ -651,12 +650,11 @@ int nilfs_discard_segments(struct the_nilfs *nilfs, __u64 *segnump,
 
 int nilfs_count_free_blocks(struct the_nilfs *nilfs, sector_t *nblocks)
 {
-        struct inode *dat = nilfs_dat_inode(nilfs);
         unsigned long ncleansegs;
 
-        down_read(&NILFS_MDT(dat)->mi_sem);     /* XXX */
+        down_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
         ncleansegs = nilfs_sufile_get_ncleansegs(nilfs->ns_sufile);
-        up_read(&NILFS_MDT(dat)->mi_sem);       /* XXX */
+        up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
         *nblocks = (sector_t)ncleansegs * nilfs->ns_blocks_per_segment;
         return 0;
 }
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index 69226e14b745..fd85e4c05c6b 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -36,8 +36,6 @@
 /* the_nilfs struct */
 enum {
         THE_NILFS_INIT = 0,     /* Information from super_block is set */
-        THE_NILFS_LOADED,       /* Roll-back/roll-forward has done and
-                                   the latest checkpoint was loaded */
         THE_NILFS_DISCONTINUED, /* 'next' pointer chain has broken */
         THE_NILFS_GC_RUNNING,   /* gc process is running */
         THE_NILFS_SB_DIRTY,     /* super block is dirty */
@@ -178,7 +176,6 @@ static inline int nilfs_##name(struct the_nilfs *nilfs)			\
 }
 
 THE_NILFS_FNS(INIT, init)
-THE_NILFS_FNS(LOADED, loaded)
 THE_NILFS_FNS(DISCONTINUED, discontinued)
 THE_NILFS_FNS(GC_RUNNING, gc_running)
 THE_NILFS_FNS(SB_DIRTY, sb_dirty)
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index b04f88eed09e..f35794b97e8e 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -92,7 +92,11 @@ static int fanotify_get_response_from_access(struct fsnotify_group *group,
 
         pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
-        wait_event(group->fanotify_data.access_waitq, event->response);
+        wait_event(group->fanotify_data.access_waitq, event->response ||
+                                atomic_read(&group->fanotify_data.bypass_perm));
+
+        if (!event->response) /* bypass_perm set */
+                return 0;
 
         /* userspace responded, convert to something usable */
         spin_lock(&event->lock);
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 063224812b7e..8b61220cffc5 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -106,20 +106,29 @@ static int create_fd(struct fsnotify_group *group, struct fsnotify_event *event)
         return client_fd;
 }
 
-static ssize_t fill_event_metadata(struct fsnotify_group *group,
+static int fill_event_metadata(struct fsnotify_group *group,
                                    struct fanotify_event_metadata *metadata,
                                    struct fsnotify_event *event)
 {
+        int ret = 0;
+
         pr_debug("%s: group=%p metadata=%p event=%p\n", __func__,
                  group, metadata, event);
 
         metadata->event_len = FAN_EVENT_METADATA_LEN;
+        metadata->metadata_len = FAN_EVENT_METADATA_LEN;
         metadata->vers = FANOTIFY_METADATA_VERSION;
         metadata->mask = event->mask & FAN_ALL_OUTGOING_EVENTS;
         metadata->pid = pid_vnr(event->tgid);
-        metadata->fd = create_fd(group, event);
+        if (unlikely(event->mask & FAN_Q_OVERFLOW))
+                metadata->fd = FAN_NOFD;
+        else {
+                metadata->fd = create_fd(group, event);
+                if (metadata->fd < 0)
+                        ret = metadata->fd;
+        }
 
-        return metadata->fd;
+        return ret;
 }
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
@@ -200,7 +209,7 @@ static int prepare_for_access_response(struct fsnotify_group *group,
 
         mutex_lock(&group->fanotify_data.access_mutex);
 
-        if (group->fanotify_data.bypass_perm) {
+        if (atomic_read(&group->fanotify_data.bypass_perm)) {
                 mutex_unlock(&group->fanotify_data.access_mutex);
                 kmem_cache_free(fanotify_response_event_cache, re);
                 event->response = FAN_ALLOW;
@@ -257,24 +266,34 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 
         pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
-        fd = fill_event_metadata(group, &fanotify_event_metadata, event);
-        if (fd < 0)
-                return fd;
+        ret = fill_event_metadata(group, &fanotify_event_metadata, event);
+        if (ret < 0)
+                goto out;
 
+        fd = fanotify_event_metadata.fd;
         ret = prepare_for_access_response(group, event, fd);
         if (ret)
                 goto out_close_fd;
 
         ret = -EFAULT;
-        if (copy_to_user(buf, &fanotify_event_metadata, FAN_EVENT_METADATA_LEN))
+        if (copy_to_user(buf, &fanotify_event_metadata,
+                         fanotify_event_metadata.event_len))
                 goto out_kill_access_response;
 
-        return FAN_EVENT_METADATA_LEN;
+        return fanotify_event_metadata.event_len;
 
 out_kill_access_response:
         remove_access_response(group, event, fd);
 out_close_fd:
-        sys_close(fd);
+        if (fd != FAN_NOFD)
+                sys_close(fd);
+out:
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+        if (event->mask & FAN_ALL_PERM_EVENTS) {
+                event->response = FAN_DENY;
+                wake_up(&group->fanotify_data.access_waitq);
+        }
+#endif
         return ret;
 }
 
@@ -382,7 +401,7 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 
         mutex_lock(&group->fanotify_data.access_mutex);
 
-        group->fanotify_data.bypass_perm = true;
+        atomic_inc(&group->fanotify_data.bypass_perm);
 
         list_for_each_entry_safe(re, lre, &group->fanotify_data.access_list, list) {
                 pr_debug("%s: found group=%p re=%p event=%p\n", __func__, group,
@@ -586,11 +605,10 @@ static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
 {
         struct fsnotify_mark *fsn_mark;
         __u32 added;
+        int ret = 0;
 
         fsn_mark = fsnotify_find_vfsmount_mark(group, mnt);
         if (!fsn_mark) {
-                int ret;
-
                 if (atomic_read(&group->num_marks) > group->fanotify_data.max_marks)
                         return -ENOSPC;
 
@@ -600,17 +618,16 @@ static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
 
                 fsnotify_init_mark(fsn_mark, fanotify_free_mark);
                 ret = fsnotify_add_mark(fsn_mark, group, NULL, mnt, 0);
-                if (ret) {
-                        fanotify_free_mark(fsn_mark);
-                        return ret;
-                }
+                if (ret)
+                        goto err;
         }
         added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
-        fsnotify_put_mark(fsn_mark);
+
         if (added & ~mnt->mnt_fsnotify_mask)
                 fsnotify_recalc_vfsmount_mask(mnt);
-
-        return 0;
+err:
+        fsnotify_put_mark(fsn_mark);
+        return ret;
 }
 
 static int fanotify_add_inode_mark(struct fsnotify_group *group,
@@ -619,6 +636,7 @@ static int fanotify_add_inode_mark(struct fsnotify_group *group,
 {
         struct fsnotify_mark *fsn_mark;
         __u32 added;
+        int ret = 0;
 
         pr_debug("%s: group=%p inode=%p\n", __func__, group, inode);
 
@@ -634,8 +652,6 @@ static int fanotify_add_inode_mark(struct fsnotify_group *group,
 
         fsn_mark = fsnotify_find_inode_mark(group, inode);
         if (!fsn_mark) {
-                int ret;
-
                 if (atomic_read(&group->num_marks) > group->fanotify_data.max_marks)
                         return -ENOSPC;
 
@@ -645,16 +661,16 @@ static int fanotify_add_inode_mark(struct fsnotify_group *group,
 
                 fsnotify_init_mark(fsn_mark, fanotify_free_mark);
                 ret = fsnotify_add_mark(fsn_mark, group, inode, NULL, 0);
-                if (ret) {
-                        fanotify_free_mark(fsn_mark);
-                        return ret;
-                }
+                if (ret)
+                        goto err;
         }
         added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
-        fsnotify_put_mark(fsn_mark);
+
         if (added & ~inode->i_fsnotify_mask)
                 fsnotify_recalc_inode_mask(inode);
-        return 0;
+err:
+        fsnotify_put_mark(fsn_mark);
+        return ret;
 }
 
 /* fanotify syscalls */
@@ -687,8 +703,10 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 
         /* fsnotify_alloc_group takes a ref.  Dropped in fanotify_release */
         group = fsnotify_alloc_group(&fanotify_fsnotify_ops);
-        if (IS_ERR(group))
+        if (IS_ERR(group)) {
+                free_uid(user);
                 return PTR_ERR(group);
+        }
 
         group->fanotify_data.user = user;
         atomic_inc(&user->fanotify_listeners);
@@ -698,6 +716,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
         mutex_init(&group->fanotify_data.access_mutex);
         init_waitqueue_head(&group->fanotify_data.access_waitq);
         INIT_LIST_HEAD(&group->fanotify_data.access_list);
+        atomic_set(&group->fanotify_data.bypass_perm, 0);
 #endif
         switch (flags & FAN_ALL_CLASS_BITS) {
         case FAN_CLASS_NOTIF:
@@ -764,8 +783,10 @@ SYSCALL_DEFINE(fanotify_mark)(int fanotify_fd, unsigned int flags,
         if (flags & ~FAN_ALL_MARK_FLAGS)
                 return -EINVAL;
         switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE | FAN_MARK_FLUSH)) {
-        case FAN_MARK_ADD:
+        case FAN_MARK_ADD:              /* fallthrough */
         case FAN_MARK_REMOVE:
+                if (!mask)
+                        return -EINVAL;
         case FAN_MARK_FLUSH:
                 break;
         default:
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 20dc218707ca..79b47cbb5cd8 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -59,7 +59,7 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode)
         /* determine if the children should tell inode about their events */
         watched = fsnotify_inode_watches_children(inode);
 
-        spin_lock(&dcache_lock);
+        spin_lock(&inode->i_lock);
         /* run all of the dentries associated with this inode.  Since this is a
          * directory, there damn well better only be one item on this list */
         list_for_each_entry(alias, &inode->i_dentry, d_alias) {
@@ -68,19 +68,21 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode)
                 /* run all of the children of the original inode and fix their
                  * d_flags to indicate parental interest (their parent is the
                  * original inode) */
+                spin_lock(&alias->d_lock);
                 list_for_each_entry(child, &alias->d_subdirs, d_u.d_child) {
                         if (!child->d_inode)
                                 continue;
 
-                        spin_lock(&child->d_lock);
+                        spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
                         if (watched)
                                 child->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED;
                         else
                                 child->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED;
                         spin_unlock(&child->d_lock);
                 }
+                spin_unlock(&alias->d_lock);
         }
-        spin_unlock(&dcache_lock);
+        spin_unlock(&inode->i_lock);
 }
 
 /* Notify this dentry's parent about a child's events. */
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 444c305a468c..4cd5d5d78f9f 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -752,6 +752,7 @@ SYSCALL_DEFINE1(inotify_init1, int, flags)
         if (ret >= 0)
                 return ret;
 
+        fsnotify_put_group(group);
         atomic_dec(&user->inotify_devs);
 out_free_uid:
         free_uid(user);
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index 93622b175fc7..a627ed82c0a3 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -332,6 +332,13 @@ struct inode *ntfs_alloc_big_inode(struct super_block *sb)
         return NULL;
 }
 
+static void ntfs_i_callback(struct rcu_head *head)
+{
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
+        kmem_cache_free(ntfs_big_inode_cache, NTFS_I(inode));
+}
+
 void ntfs_destroy_big_inode(struct inode *inode)
 {
         ntfs_inode *ni = NTFS_I(inode);
@@ -340,7 +347,7 @@ void ntfs_destroy_big_inode(struct inode *inode)
         BUG_ON(ni->page);
         if (!atomic_dec_and_test(&ni->count))
                 BUG();
-        kmem_cache_free(ntfs_big_inode_cache, NTFS_I(inode));
+        call_rcu(&inode->i_rcu, ntfs_i_callback);
 }
 
 static inline ntfs_inode *ntfs_alloc_extent_inode(void)
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index 391915093fe1..704f6b1742f3 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -291,13 +291,17 @@ static int ocfs2_set_acl(handle_t *handle,
         return ret;
 }
 
-int ocfs2_check_acl(struct inode *inode, int mask)
+int ocfs2_check_acl(struct inode *inode, int mask, unsigned int flags)
 {
-        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+        struct ocfs2_super *osb;
         struct buffer_head *di_bh = NULL;
         struct posix_acl *acl;
         int ret = -EAGAIN;
 
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
+        osb = OCFS2_SB(inode->i_sb);
         if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
                 return ret;
 
diff --git a/fs/ocfs2/acl.h b/fs/ocfs2/acl.h
index 5c5d31f05853..4fe7c9cf4bfb 100644
--- a/fs/ocfs2/acl.h
+++ b/fs/ocfs2/acl.h
@@ -26,7 +26,7 @@ struct ocfs2_acl_entry {
         __le32 e_id;
 };
 
-extern int ocfs2_check_acl(struct inode *, int);
+extern int ocfs2_check_acl(struct inode *, int, unsigned int);
 extern int ocfs2_acl_chmod(struct inode *);
 extern int ocfs2_init_acl(handle_t *, struct inode *, struct inode *,
                           struct buffer_head *, struct buffer_head *,
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index f1e962cb3b73..0d7c5540ad66 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -573,11 +573,14 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
         /* this io's submitter should not have unlocked this before we could */
         BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
 
+        if (ocfs2_iocb_is_sem_locked(iocb)) {
+                up_read(&inode->i_alloc_sem);
+                ocfs2_iocb_clear_sem_locked(iocb);
+        }
+
         ocfs2_iocb_clear_rw_locked(iocb);
 
         level = ocfs2_iocb_rw_locked_level(iocb);
-        if (!level)
-                up_read(&inode->i_alloc_sem);
         ocfs2_rw_unlock(inode, level);
 
         if (is_async)
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index 76bfdfda691a..eceb456037c1 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -68,8 +68,27 @@ static inline void ocfs2_iocb_set_rw_locked(struct kiocb *iocb, int level)
         else
                 clear_bit(1, (unsigned long *)&iocb->private);
 }
+
+/*
+ * Using a named enum representing lock types in terms of #N bit stored in
+ * iocb->private, which is going to be used for communication bewteen
+ * ocfs2_dio_end_io() and ocfs2_file_aio_write/read().
+ */
+enum ocfs2_iocb_lock_bits {
+        OCFS2_IOCB_RW_LOCK = 0,
+        OCFS2_IOCB_RW_LOCK_LEVEL,
+        OCFS2_IOCB_SEM,
+        OCFS2_IOCB_NUM_LOCKS
+};
+
 #define ocfs2_iocb_clear_rw_locked(iocb) \
-        clear_bit(0, (unsigned long *)&iocb->private)
+        clear_bit(OCFS2_IOCB_RW_LOCK, (unsigned long *)&iocb->private)
 #define ocfs2_iocb_rw_locked_level(iocb) \
-        test_bit(1, (unsigned long *)&iocb->private)
+        test_bit(OCFS2_IOCB_RW_LOCK_LEVEL, (unsigned long *)&iocb->private)
+#define ocfs2_iocb_set_sem_locked(iocb) \
+        set_bit(OCFS2_IOCB_SEM, (unsigned long *)&iocb->private)
+#define ocfs2_iocb_clear_sem_locked(iocb) \
+        clear_bit(OCFS2_IOCB_SEM, (unsigned long *)&iocb->private)
+#define ocfs2_iocb_is_sem_locked(iocb) \
+        test_bit(OCFS2_IOCB_SEM, (unsigned long *)&iocb->private)
 #endif /* OCFS2_FILE_H */
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 9f26ac9be2a4..9e3d45bcb5fd 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -307,8 +307,7 @@ static void o2hb_arm_write_timeout(struct o2hb_region *reg)
 
 static void o2hb_disarm_write_timeout(struct o2hb_region *reg)
 {
-        cancel_delayed_work(&reg->hr_write_timeout_work);
-        flush_scheduled_work();
+        cancel_delayed_work_sync(&reg->hr_write_timeout_work);
 }
 
 static inline void o2hb_bio_wait_init(struct o2hb_bio_wait_ctxt *wc)
diff --git a/fs/ocfs2/cluster/masklog.c b/fs/ocfs2/cluster/masklog.c
index c7fba396392d..6c61771469af 100644
--- a/fs/ocfs2/cluster/masklog.c
+++ b/fs/ocfs2/cluster/masklog.c
@@ -113,10 +113,11 @@ static struct mlog_attribute mlog_attrs[MLOG_MAX_BITS] = {
         define_mask(QUOTA),
         define_mask(REFCOUNT),
         define_mask(BASTS),
+        define_mask(RESERVATIONS),
+        define_mask(CLUSTER),
         define_mask(ERROR),
         define_mask(NOTICE),
         define_mask(KTHREAD),
-        define_mask(RESERVATIONS),
 };
 
 static struct attribute *mlog_attr_ptrs[MLOG_MAX_BITS] = {NULL, };
diff --git a/fs/ocfs2/cluster/masklog.h b/fs/ocfs2/cluster/masklog.h
index ea2ed9f56c94..34d6544357d9 100644
--- a/fs/ocfs2/cluster/masklog.h
+++ b/fs/ocfs2/cluster/masklog.h
@@ -81,7 +81,7 @@
 #include <linux/sched.h>
 
 /* bits that are frequently given and infrequently matched in the low word */
-/* NOTE: If you add a flag, you need to also update mlog.c! */
+/* NOTE: If you add a flag, you need to also update masklog.c! */
 #define ML_ENTRY        0x0000000000000001ULL /* func call entry */
 #define ML_EXIT         0x0000000000000002ULL /* func call exit */
 #define ML_TCP          0x0000000000000004ULL /* net cluster/tcp.c */
@@ -114,13 +114,14 @@
 #define ML_XATTR        0x0000000020000000ULL /* ocfs2 extended attributes */
 #define ML_QUOTA        0x0000000040000000ULL /* ocfs2 quota operations */
 #define ML_REFCOUNT     0x0000000080000000ULL /* refcount tree operations */
-#define ML_BASTS        0x0000001000000000ULL /* dlmglue asts and basts */
+#define ML_BASTS        0x0000000100000000ULL /* dlmglue asts and basts */
+#define ML_RESERVATIONS 0x0000000200000000ULL /* ocfs2 alloc reservations */
+#define ML_CLUSTER      0x0000000400000000ULL /* cluster stack */
+
 /* bits that are infrequently given and frequently matched in the high word */
-#define ML_ERROR        0x0000000100000000ULL /* sent to KERN_ERR */
-#define ML_NOTICE       0x0000000200000000ULL /* setn to KERN_NOTICE */
-#define ML_KTHREAD      0x0000000400000000ULL /* kernel thread activity */
-#define ML_RESERVATIONS 0x0000000800000000ULL /* ocfs2 alloc reservations */
-#define ML_CLUSTER      0x0000001000000000ULL /* cluster stack */
+#define ML_ERROR        0x1000000000000000ULL /* sent to KERN_ERR */
+#define ML_NOTICE       0x2000000000000000ULL /* setn to KERN_NOTICE */
+#define ML_KTHREAD      0x4000000000000000ULL /* kernel thread activity */
 
 #define MLOG_INITIAL_AND_MASK (ML_ERROR|ML_NOTICE)
 #define MLOG_INITIAL_NOT_MASK (ML_ENTRY|ML_EXIT)
diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c
index cf3e16696216..a87366750f23 100644
--- a/fs/ocfs2/cluster/quorum.c
+++ b/fs/ocfs2/cluster/quorum.c
@@ -325,5 +325,7 @@ void o2quo_init(void)
 
 void o2quo_exit(void)
 {
-        flush_scheduled_work();
+        struct o2quo_state *qs = &o2quo_state;
+
+        flush_work_sync(&qs->qs_work);
 }
diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c
index 895532ac4d98..6d80ecc7834f 100644
--- a/fs/ocfs2/dcache.c
+++ b/fs/ocfs2/dcache.c
@@ -52,9 +52,15 @@ void ocfs2_dentry_attach_gen(struct dentry *dentry)
 static int ocfs2_dentry_revalidate(struct dentry *dentry,
                                    struct nameidata *nd)
 {
-        struct inode *inode = dentry->d_inode;
+        struct inode *inode;
         int ret = 0;    /* if all else fails, just return false */
-        struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb);
+        struct ocfs2_super *osb;
+
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
+
+        inode = dentry->d_inode;
+        osb = OCFS2_SB(dentry->d_sb);
 
         mlog_entry("(0x%p, '%.*s')\n", dentry,
                    dentry->d_name.len, dentry->d_name.name);
@@ -169,23 +175,25 @@ struct dentry *ocfs2_find_local_alias(struct inode *inode,
         struct list_head *p;
         struct dentry *dentry = NULL;
 
-        spin_lock(&dcache_lock);
-
+        spin_lock(&inode->i_lock);
         list_for_each(p, &inode->i_dentry) {
                 dentry = list_entry(p, struct dentry, d_alias);
 
+                spin_lock(&dentry->d_lock);
                 if (ocfs2_match_dentry(dentry, parent_blkno, skip_unhashed)) {
                         mlog(0, "dentry found: %.*s\n",
                              dentry->d_name.len, dentry->d_name.name);
 
-                        dget_locked(dentry);
+                        dget_dlock(dentry);
+                        spin_unlock(&dentry->d_lock);
                         break;
                 }
+                spin_unlock(&dentry->d_lock);
 
                 dentry = NULL;
         }
 
-        spin_unlock(&dcache_lock);
+        spin_unlock(&inode->i_lock);
 
         return dentry;
 }
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index c49f6de0e7ab..d417b3f9b0c7 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -2461,8 +2461,10 @@ static int ocfs2_dx_dir_attach_index(struct ocfs2_super *osb,
 
         di->i_dx_root = cpu_to_le64(dr_blkno);
 
+        spin_lock(&OCFS2_I(dir)->ip_lock);
         OCFS2_I(dir)->ip_dyn_features |= OCFS2_INDEXED_DIR_FL;
         di->i_dyn_features = cpu_to_le16(OCFS2_I(dir)->ip_dyn_features);
+        spin_unlock(&OCFS2_I(dir)->ip_lock);
 
         ocfs2_journal_dirty(handle, di_bh);
 
@@ -4466,8 +4468,10 @@ static int ocfs2_dx_dir_remove_index(struct inode *dir,
                 goto out_commit;
         }
 
+        spin_lock(&OCFS2_I(dir)->ip_lock);
         OCFS2_I(dir)->ip_dyn_features &= ~OCFS2_INDEXED_DIR_FL;
         di->i_dyn_features = cpu_to_le16(OCFS2_I(dir)->ip_dyn_features);
+        spin_unlock(&OCFS2_I(dir)->ip_lock);
         di->i_dx_root = cpu_to_le64(0ULL);
 
         ocfs2_journal_dirty(handle, di_bh);
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index f564b0e5f80d..59f0f6bdfc62 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -2346,7 +2346,8 @@ static void dlm_deref_lockres_worker(struct dlm_work_item *item, void *data)
  */
 static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm,
                                       struct dlm_lock_resource *res,
-                                      int *numlocks)
+                                      int *numlocks,
+                                      int *hasrefs)
 {
         int ret;
         int i;
@@ -2356,6 +2357,9 @@ static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm,
 
         assert_spin_locked(&res->spinlock);
 
+        *numlocks = 0;
+        *hasrefs = 0;
+
         ret = -EINVAL;
         if (res->owner == DLM_LOCK_RES_OWNER_UNKNOWN) {
                 mlog(0, "cannot migrate lockres with unknown owner!\n");
@@ -2386,7 +2390,13 @@ static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm,
         }
 
         *numlocks = count;
-        mlog(0, "migrateable lockres having %d locks\n", *numlocks);
+
+        count = find_next_bit(res->refmap, O2NM_MAX_NODES, 0);
+        if (count < O2NM_MAX_NODES)
+                *hasrefs = 1;
+
+        mlog(0, "%s: res %.*s, Migrateable, locks %d, refs %d\n", dlm->name,
+             res->lockname.len, res->lockname.name, *numlocks, *hasrefs);
 
 leave:
         return ret;
@@ -2408,7 +2418,7 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
         const char *name;
         unsigned int namelen;
         int mle_added = 0;
-        int numlocks;
+        int numlocks, hasrefs;
         int wake = 0;
 
         if (!dlm_grab(dlm))
@@ -2417,13 +2427,13 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
         name = res->lockname.name;
         namelen = res->lockname.len;
 
-        mlog(0, "migrating %.*s to %u\n", namelen, name, target);
+        mlog(0, "%s: Migrating %.*s to %u\n", dlm->name, namelen, name, target);
 
         /*
          * ensure this lockres is a proper candidate for migration
          */
         spin_lock(&res->spinlock);
-        ret = dlm_is_lockres_migrateable(dlm, res, &numlocks);
+        ret = dlm_is_lockres_migrateable(dlm, res, &numlocks, &hasrefs);
         if (ret < 0) {
                 spin_unlock(&res->spinlock);
                 goto leave;
@@ -2431,10 +2441,8 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
         spin_unlock(&res->spinlock);
 
         /* no work to do */
-        if (numlocks == 0) {
-                mlog(0, "no locks were found on this lockres! done!\n");
+        if (numlocks == 0 && !hasrefs)
                 goto leave;
-        }
 
         /*
          * preallocate up front
@@ -2459,14 +2467,14 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
          * find a node to migrate the lockres to
          */
 
-        mlog(0, "picking a migration node\n");
         spin_lock(&dlm->spinlock);
         /* pick a new node */
         if (!test_bit(target, dlm->domain_map) ||
             target >= O2NM_MAX_NODES) {
                 target = dlm_pick_migration_target(dlm, res);
         }
-        mlog(0, "node %u chosen for migration\n", target);
+        mlog(0, "%s: res %.*s, Node %u chosen for migration\n", dlm->name,
+             namelen, name, target);
 
         if (target >= O2NM_MAX_NODES ||
             !test_bit(target, dlm->domain_map)) {
@@ -2667,7 +2675,7 @@ int dlm_empty_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res)
 {
         int ret;
         int lock_dropped = 0;
-        int numlocks;
+        int numlocks, hasrefs;
 
         spin_lock(&res->spinlock);
         if (res->owner != dlm->node_num) {
@@ -2681,8 +2689,8 @@ int dlm_empty_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res)
         }
 
         /* No need to migrate a lockres having no locks */
-        ret = dlm_is_lockres_migrateable(dlm, res, &numlocks);
-        if (ret >= 0 && numlocks == 0) {
+        ret = dlm_is_lockres_migrateable(dlm, res, &numlocks, &hasrefs);
+        if (ret >= 0 && numlocks == 0 && !hasrefs) {
                 spin_unlock(&res->spinlock);
                 goto leave;
         }
@@ -2915,6 +2923,12 @@ static u8 dlm_pick_migration_target(struct dlm_ctxt *dlm,
                 }
                 queue++;
         }
+
+        nodenum = find_next_bit(res->refmap, O2NM_MAX_NODES, 0);
+        if (nodenum < O2NM_MAX_NODES) {
+                spin_unlock(&res->spinlock);
+                return nodenum;
+        }
         spin_unlock(&res->spinlock);
         mlog(0, "have not found a suitable target yet! checking domain map\n");
 
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index b2df490a19ed..8c5c0eddc365 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -351,11 +351,18 @@ static struct inode *dlmfs_alloc_inode(struct super_block *sb)
         return &ip->ip_vfs_inode;
 }
 
-static void dlmfs_destroy_inode(struct inode *inode)
+static void dlmfs_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(dlmfs_inode_cache, DLMFS_I(inode));
 }
 
+static void dlmfs_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, dlmfs_i_callback);
+}
+
 static void dlmfs_evict_inode(struct inode *inode)
 {
         int status;
diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c
index 19ad145d2af3..6adafa576065 100644
--- a/fs/ocfs2/export.c
+++ b/fs/ocfs2/export.c
@@ -138,7 +138,7 @@ check_gen:
 
         result = d_obtain_alias(inode);
         if (!IS_ERR(result))
-                result->d_op = &ocfs2_dentry_ops;
+                d_set_d_op(result, &ocfs2_dentry_ops);
         else
                 mlog_errno(PTR_ERR(result));
 
@@ -176,7 +176,7 @@ static struct dentry *ocfs2_get_parent(struct dentry *child)
 
         parent = d_obtain_alias(ocfs2_iget(OCFS2_SB(dir->i_sb), blkno, 0, 0));
         if (!IS_ERR(parent))
-                parent->d_op = &ocfs2_dentry_ops;
+                d_set_d_op(parent, &ocfs2_dentry_ops);
 
 bail_unlock:
         ocfs2_inode_unlock(dir, 0);
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 77b4c04a2809..bdadbae09094 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1307,10 +1307,13 @@ bail:
         return err;
 }
 
-int ocfs2_permission(struct inode *inode, int mask)
+int ocfs2_permission(struct inode *inode, int mask, unsigned int flags)
 {
         int ret;
 
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
         mlog_entry_void();
 
         ret = ocfs2_inode_lock(inode, NULL, 0);
@@ -1320,7 +1323,7 @@ int ocfs2_permission(struct inode *inode, int mask)
                 goto out;
         }
 
-        ret = generic_permission(inode, mask, ocfs2_check_acl);
+        ret = generic_permission(inode, mask, flags, ocfs2_check_acl);
 
         ocfs2_inode_unlock(inode, 0);
 out:
@@ -2241,11 +2244,15 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 
         mutex_lock(&inode->i_mutex);
 
+        ocfs2_iocb_clear_sem_locked(iocb);
+
 relock:
         /* to match setattr's i_mutex -> i_alloc_sem -> rw_lock ordering */
         if (direct_io) {
                 down_read(&inode->i_alloc_sem);
                 have_alloc_sem = 1;
+                /* communicate with ocfs2_dio_end_io */
+                ocfs2_iocb_set_sem_locked(iocb);
         }
 
         /*
@@ -2382,8 +2389,10 @@ out:
                 ocfs2_rw_unlock(inode, rw_level);
 
 out_sems:
-        if (have_alloc_sem)
+        if (have_alloc_sem) {
                 up_read(&inode->i_alloc_sem);
+                ocfs2_iocb_clear_sem_locked(iocb);
+        }
 
         mutex_unlock(&inode->i_mutex);
 
@@ -2527,6 +2536,8 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
                 goto bail;
         }
 
+        ocfs2_iocb_clear_sem_locked(iocb);
+
         /*
          * buffered reads protect themselves in ->readpage().  O_DIRECT reads
          * need locks to protect pending reads from racing with truncate.
@@ -2534,6 +2545,7 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
         if (filp->f_flags & O_DIRECT) {
                 down_read(&inode->i_alloc_sem);
                 have_alloc_sem = 1;
+                ocfs2_iocb_set_sem_locked(iocb);
 
                 ret = ocfs2_rw_lock(inode, 0);
                 if (ret < 0) {
@@ -2575,8 +2587,10 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
         }
 
 bail:
-        if (have_alloc_sem)
+        if (have_alloc_sem) {
                 up_read(&inode->i_alloc_sem);
+                ocfs2_iocb_clear_sem_locked(iocb);
+        }
         if (rw_level != -1)
                 ocfs2_rw_unlock(inode, rw_level);
         mlog_exit(ret);
diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h
index 97bf761c9e7c..f5afbbef6703 100644
--- a/fs/ocfs2/file.h
+++ b/fs/ocfs2/file.h
@@ -61,7 +61,7 @@ int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh,
 int ocfs2_setattr(struct dentry *dentry, struct iattr *attr);
 int ocfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
                   struct kstat *stat);
-int ocfs2_permission(struct inode *inode, int mask);
+int ocfs2_permission(struct inode *inode, int mask, unsigned int flags);
 
 int ocfs2_should_update_atime(struct inode *inode,
                               struct vfsmount *vfsmnt);
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index ff5744e1e36f..d14cad6e2e41 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -147,7 +147,7 @@ static struct dentry *ocfs2_lookup(struct inode *dir, struct dentry *dentry,
         spin_unlock(&oi->ip_lock);
 
 bail_add:
-        dentry->d_op = &ocfs2_dentry_ops;
+        d_set_d_op(dentry, &ocfs2_dentry_ops);
         ret = d_splice_alias(inode, dentry);
 
         if (inode) {
@@ -415,7 +415,7 @@ static int ocfs2_mknod(struct inode *dir,
                 mlog_errno(status);
                 goto leave;
         }
-        dentry->d_op = &ocfs2_dentry_ops;
+        d_set_d_op(dentry, &ocfs2_dentry_ops);
 
         status = ocfs2_add_entry(handle, dentry, inode,
                                  OCFS2_I(inode)->ip_blkno, parent_fe_bh,
@@ -743,7 +743,7 @@ static int ocfs2_link(struct dentry *old_dentry,
         }
 
         ihold(inode);
-        dentry->d_op = &ocfs2_dentry_ops;
+        d_set_d_op(dentry, &ocfs2_dentry_ops);
         d_instantiate(dentry, inode);
 
 out_commit:
@@ -1794,7 +1794,7 @@ static int ocfs2_symlink(struct inode *dir,
                 mlog_errno(status);
                 goto bail;
         }
-        dentry->d_op = &ocfs2_dentry_ops;
+        d_set_d_op(dentry, &ocfs2_dentry_ops);
 
         status = ocfs2_add_entry(handle, dentry, inode,
                                  le64_to_cpu(fe->i_blkno), parent_fe_bh,
@@ -2459,7 +2459,7 @@ int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
                 goto out_commit;
         }
 
-        dentry->d_op = &ocfs2_dentry_ops;
+        d_set_d_op(dentry, &ocfs2_dentry_ops);
         d_instantiate(dentry, inode);
         status = 0;
 out_commit:
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index c2e4f8222e2f..bf2e7764920e 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -350,7 +350,7 @@ enum {
 #define OCFS2_LAST_LOCAL_SYSTEM_INODE LOCAL_GROUP_QUOTA_SYSTEM_INODE
         NUM_SYSTEM_INODES
 };
-#define NUM_GLOBAL_SYSTEM_INODES OCFS2_LAST_GLOBAL_SYSTEM_INODE
+#define NUM_GLOBAL_SYSTEM_INODES OCFS2_FIRST_LOCAL_SYSTEM_INODE
 #define NUM_LOCAL_SYSTEM_INODES \
                 (NUM_SYSTEM_INODES - OCFS2_FIRST_LOCAL_SYSTEM_INODE)
 
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index cfeab7ce3697..17ff46fa8a10 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -569,11 +569,18 @@ static struct inode *ocfs2_alloc_inode(struct super_block *sb)
         return &oi->vfs_inode;
 }
 
-static void ocfs2_destroy_inode(struct inode *inode)
+static void ocfs2_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(ocfs2_inode_cachep, OCFS2_I(inode));
 }
 
+static void ocfs2_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, ocfs2_i_callback);
+}
+
 static unsigned long long ocfs2_max_file_offset(unsigned int bbits,
                                                 unsigned int cbits)
 {
diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c
index 911e61f348fc..a2a5bff774e3 100644
--- a/fs/openpromfs/inode.c
+++ b/fs/openpromfs/inode.c
@@ -343,11 +343,18 @@ static struct inode *openprom_alloc_inode(struct super_block *sb)
         return &oi->vfs_inode;
 }
 
-static void openprom_destroy_inode(struct inode *inode)
+static void openprom_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(op_inode_cachep, OP_I(inode));
 }
 
+static void openprom_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, openprom_i_callback);
+}
+
 static struct inode *openprom_iget(struct super_block *sb, ino_t ino)
 {
         struct inode *inode;
diff --git a/fs/pipe.c b/fs/pipe.c
index 04629f36e397..68f1f8e4e23b 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -999,12 +999,12 @@ struct file *create_write_pipe(int flags)
                 goto err;
 
         err = -ENOMEM;
-        path.dentry = d_alloc(pipe_mnt->mnt_sb->s_root, &name);
+        path.dentry = d_alloc_pseudo(pipe_mnt->mnt_sb, &name);
         if (!path.dentry)
                 goto err_inode;
         path.mnt = mntget(pipe_mnt);
 
-        path.dentry->d_op = &pipefs_dentry_operations;
+        d_set_d_op(path.dentry, &pipefs_dentry_operations);
         d_instantiate(path.dentry, inode);
 
         err = -ENFILE;
@@ -1253,6 +1253,10 @@ out:
         return ret;
 }
 
+static const struct super_operations pipefs_ops = {
+        .destroy_inode = free_inode_nonrcu,
+};
+
 /*
  * pipefs should _never_ be mounted by userland - too much of security hassle,
  * no real gain from having the whole whorehouse mounted. So we don't need
@@ -1262,7 +1266,7 @@ out:
 static struct dentry *pipefs_mount(struct file_system_type *fs_type,
                          int flags, const char *dev_name, void *data)
 {
-        return mount_pseudo(fs_type, "pipe:", NULL, PIPEFS_MAGIC);
+        return mount_pseudo(fs_type, "pipe:", &pipefs_ops, PIPEFS_MAGIC);
 }
 
 static struct file_system_type pipe_fs_type = {
@@ -1288,7 +1292,7 @@ static int __init init_pipe_fs(void)
 static void __exit exit_pipe_fs(void)
 {
         unregister_filesystem(&pipe_fs_type);
-        mntput(pipe_mnt);
+        mntput_long(pipe_mnt);
 }
 
 fs_initcall(init_pipe_fs);
diff --git a/fs/pnode.c b/fs/pnode.c
index 8066b8dd748f..d42514e32380 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -288,7 +288,7 @@ out:
  */
 static inline int do_refcount_check(struct vfsmount *mnt, int count)
 {
-        int mycount = atomic_read(&mnt->mnt_count) - mnt->mnt_ghosts;
+        int mycount = mnt_get_count(mnt) - mnt->mnt_ghosts;
         return (mycount > count);
 }
 
@@ -300,7 +300,7 @@ static inline int do_refcount_check(struct vfsmount *mnt, int count)
  * Check if any of these mounts that **do not have submounts**
  * have more references than 'refcnt'. If so return busy.
  *
- * vfsmount lock must be held for read or write
+ * vfsmount lock must be held for write
  */
 int propagate_mount_busy(struct vfsmount *mnt, int refcnt)
 {
diff --git a/fs/proc/Makefile b/fs/proc/Makefile
index 2758e2afc518..288a49e098bf 100644
--- a/fs/proc/Makefile
+++ b/fs/proc/Makefile
@@ -15,6 +15,7 @@ proc-y	+= devices.o
 proc-y  += interrupts.o
 proc-y  += loadavg.o
 proc-y  += meminfo.o
+proc-y  += proc_console.o
 proc-y  += stat.o
 proc-y  += uptime.o
 proc-y  += version.o
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 182845147fe4..b20962c71a52 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1407,6 +1407,82 @@ static const struct file_operations proc_pid_sched_operations = {
 
 #endif
 
+#ifdef CONFIG_SCHED_AUTOGROUP
+/*
+ * Print out autogroup related information:
+ */
+static int sched_autogroup_show(struct seq_file *m, void *v)
+{
+        struct inode *inode = m->private;
+        struct task_struct *p;
+
+        p = get_proc_task(inode);
+        if (!p)
+                return -ESRCH;
+        proc_sched_autogroup_show_task(p, m);
+
+        put_task_struct(p);
+
+        return 0;
+}
+
+static ssize_t
+sched_autogroup_write(struct file *file, const char __user *buf,
+            size_t count, loff_t *offset)
+{
+        struct inode *inode = file->f_path.dentry->d_inode;
+        struct task_struct *p;
+        char buffer[PROC_NUMBUF];
+        long nice;
+        int err;
+
+        memset(buffer, 0, sizeof(buffer));
+        if (count > sizeof(buffer) - 1)
+                count = sizeof(buffer) - 1;
+        if (copy_from_user(buffer, buf, count))
+                return -EFAULT;
+
+        err = strict_strtol(strstrip(buffer), 0, &nice);
+        if (err)
+                return -EINVAL;
+
+        p = get_proc_task(inode);
+        if (!p)
+                return -ESRCH;
+
+        err = nice;
+        err = proc_sched_autogroup_set_nice(p, &err);
+        if (err)
+                count = err;
+
+        put_task_struct(p);
+
+        return count;
+}
+
+static int sched_autogroup_open(struct inode *inode, struct file *filp)
+{
+        int ret;
+
+        ret = single_open(filp, sched_autogroup_show, NULL);
+        if (!ret) {
+                struct seq_file *m = filp->private_data;
+
+                m->private = inode;
+        }
+        return ret;
+}
+
+static const struct file_operations proc_pid_sched_autogroup_operations = {
+        .open           = sched_autogroup_open,
+        .read           = seq_read,
+        .write          = sched_autogroup_write,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+};
+
+#endif /* CONFIG_SCHED_AUTOGROUP */
+
 static ssize_t comm_write(struct file *file, const char __user *buf,
                                 size_t count, loff_t *offset)
 {
@@ -1719,10 +1795,16 @@ static int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat
  */
 static int pid_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
-        struct inode *inode = dentry->d_inode;
-        struct task_struct *task = get_proc_task(inode);
+        struct inode *inode;
+        struct task_struct *task;
         const struct cred *cred;
 
+        if (nd && nd->flags & LOOKUP_RCU)
+                return -ECHILD;
+
+        inode = dentry->d_inode;
+        task = get_proc_task(inode);
+
         if (task) {
                 if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) ||
                     task_dumpable(task)) {
@@ -1744,7 +1826,7 @@ static int pid_revalidate(struct dentry *dentry, struct nameidata *nd)
         return 0;
 }
 
-static int pid_delete_dentry(struct dentry * dentry)
+static int pid_delete_dentry(const struct dentry * dentry)
 {
         /* Is the task we represent dead?
          * If so, then don't put the dentry on the lru list,
@@ -1888,12 +1970,19 @@ static int proc_fd_link(struct inode *inode, struct path *path)
 
 static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
-        struct inode *inode = dentry->d_inode;
-        struct task_struct *task = get_proc_task(inode);
-        int fd = proc_fd(inode);
+        struct inode *inode;
+        struct task_struct *task;
+        int fd;
         struct files_struct *files;
         const struct cred *cred;
 
+        if (nd && nd->flags & LOOKUP_RCU)
+                return -ECHILD;
+
+        inode = dentry->d_inode;
+        task = get_proc_task(inode);
+        fd = proc_fd(inode);
+
         if (task) {
                 files = get_files_struct(task);
                 if (files) {
@@ -1969,7 +2058,7 @@ static struct dentry *proc_fd_instantiate(struct inode *dir,
         inode->i_op = &proc_pid_link_inode_operations;
         inode->i_size = 64;
         ei->op.proc_get_link = proc_fd_link;
-        dentry->d_op = &tid_fd_dentry_operations;
+        d_set_d_op(dentry, &tid_fd_dentry_operations);
         d_add(dentry, inode);
         /* Close the race of the process dying before we return the dentry */
         if (tid_fd_revalidate(dentry, NULL))
@@ -2101,11 +2190,13 @@ static const struct file_operations proc_fd_operations = {
  * /proc/pid/fd needs a special permission handler so that a process can still
  * access /proc/self/fd after it has executed a setuid().
  */
-static int proc_fd_permission(struct inode *inode, int mask)
+static int proc_fd_permission(struct inode *inode, int mask, unsigned int flags)
 {
         int rv;
 
-        rv = generic_permission(inode, mask, NULL);
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+        rv = generic_permission(inode, mask, flags, NULL);
         if (rv == 0)
                 return 0;
         if (task_pid(current) == proc_pid(inode))
@@ -2137,7 +2228,7 @@ static struct dentry *proc_fdinfo_instantiate(struct inode *dir,
         ei->fd = fd;
         inode->i_mode = S_IFREG | S_IRUSR;
         inode->i_fop = &proc_fdinfo_file_operations;
-        dentry->d_op = &tid_fd_dentry_operations;
+        d_set_d_op(dentry, &tid_fd_dentry_operations);
         d_add(dentry, inode);
         /* Close the race of the process dying before we return the dentry */
         if (tid_fd_revalidate(dentry, NULL))
@@ -2196,7 +2287,7 @@ static struct dentry *proc_pident_instantiate(struct inode *dir,
         if (p->fop)
                 inode->i_fop = p->fop;
         ei->op = p->op;
-        dentry->d_op = &pid_dentry_operations;
+        d_set_d_op(dentry, &pid_dentry_operations);
         d_add(dentry, inode);
         /* Close the race of the process dying before we return the dentry */
         if (pid_revalidate(dentry, NULL))
@@ -2563,8 +2654,14 @@ static const struct pid_entry proc_base_stuff[] = {
  */
 static int proc_base_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
-        struct inode *inode = dentry->d_inode;
-        struct task_struct *task = get_proc_task(inode);
+        struct inode *inode;
+        struct task_struct *task;
+
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
+
+        inode = dentry->d_inode;
+        task = get_proc_task(inode);
         if (task) {
                 put_task_struct(task);
                 return 1;
@@ -2615,7 +2712,7 @@ static struct dentry *proc_base_instantiate(struct inode *dir,
         if (p->fop)
                 inode->i_fop = p->fop;
         ei->op = p->op;
-        dentry->d_op = &proc_base_dentry_operations;
+        d_set_d_op(dentry, &proc_base_dentry_operations);
         d_add(dentry, inode);
         error = NULL;
 out:
@@ -2733,6 +2830,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_SCHED_DEBUG
         REG("sched",      S_IRUGO|S_IWUSR, proc_pid_sched_operations),
 #endif
+#ifdef CONFIG_SCHED_AUTOGROUP
+        REG("autogroup",  S_IRUGO|S_IWUSR, proc_pid_sched_autogroup_operations),
+#endif
         REG("comm",      S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
 #ifdef CONFIG_HAVE_ARCH_TRACEHOOK
         INF("syscall",    S_IRUSR, proc_pid_syscall),
@@ -2926,7 +3026,7 @@ static struct dentry *proc_pid_instantiate(struct inode *dir,
         inode->i_nlink = 2 + pid_entry_count_dirs(tgid_base_stuff,
                 ARRAY_SIZE(tgid_base_stuff));
 
-        dentry->d_op = &pid_dentry_operations;
+        d_set_d_op(dentry, &pid_dentry_operations);
 
         d_add(dentry, inode);
         /* Close the race of the process dying before we return the dentry */
@@ -3169,7 +3269,7 @@ static struct dentry *proc_task_instantiate(struct inode *dir,
         inode->i_nlink = 2 + pid_entry_count_dirs(tid_base_stuff,
                 ARRAY_SIZE(tid_base_stuff));
 
-        dentry->d_op = &pid_dentry_operations;
+        d_set_d_op(dentry, &pid_dentry_operations);
 
         d_add(dentry, inode);
         /* Close the race of the process dying before we return the dentry */
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index dd29f0337661..f766be29d2c7 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -400,7 +400,7 @@ static const struct inode_operations proc_link_inode_operations = {
  * smarter: we could keep a "volatile" flag in the 
  * inode to indicate which ones to keep.
  */
-static int proc_delete_dentry(struct dentry * dentry)
+static int proc_delete_dentry(const struct dentry * dentry)
 {
         return 1;
 }
@@ -439,7 +439,7 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
 out_unlock:
 
         if (inode) {
-                dentry->d_op = &proc_dentry_operations;
+                d_set_d_op(dentry, &proc_dentry_operations);
                 d_add(dentry, inode);
                 return NULL;
         }
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 3ddb6068177c..6bcb926b101b 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -65,11 +65,18 @@ static struct inode *proc_alloc_inode(struct super_block *sb)
         return inode;
 }
 
-static void proc_destroy_inode(struct inode *inode)
+static void proc_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(proc_inode_cachep, PROC_I(inode));
 }
 
+static void proc_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, proc_i_callback);
+}
+
 static void init_once(void *foo)
 {
         struct proc_inode *ei = (struct proc_inode *) foo;
diff --git a/fs/proc/proc_console.c b/fs/proc/proc_console.c
new file mode 100644
index 000000000000..8a707609f528
--- /dev/null
+++ b/fs/proc/proc_console.c
@@ -0,0 +1,114 @@
+/*
+ * Copyright (c) 2010 Werner Fink, Jiri Slaby
+ *
+ * Licensed under GPLv2
+ */
+
+#include <linux/console.h>
+#include <linux/kernel.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/tty_driver.h>
+
+/*
+ * This is handler for /proc/consoles
+ */
+static int show_console_dev(struct seq_file *m, void *v)
+{
+        static const struct {
+                short flag;
+                char name;
+        } con_flags[] = {
+                { CON_ENABLED,          'E' },
+                { CON_CONSDEV,          'C' },
+                { CON_BOOT,             'B' },
+                { CON_PRINTBUFFER,      'p' },
+                { CON_BRL,              'b' },
+                { CON_ANYTIME,          'a' },
+        };
+        char flags[ARRAY_SIZE(con_flags) + 1];
+        struct console *con = v;
+        unsigned int a;
+        int len;
+        dev_t dev = 0;
+
+        if (con->device) {
+                const struct tty_driver *driver;
+                int index;
+                driver = con->device(con, &index);
+                if (driver) {
+                        dev = MKDEV(driver->major, driver->minor_start);
+                        dev += index;
+                }
+        }
+
+        for (a = 0; a < ARRAY_SIZE(con_flags); a++)
+                flags[a] = (con->flags & con_flags[a].flag) ?
+                        con_flags[a].name : ' ';
+        flags[a] = 0;
+
+        seq_printf(m, "%s%d%n", con->name, con->index, &len);
+        len = 21 - len;
+        if (len < 1)
+                len = 1;
+        seq_printf(m, "%*c%c%c%c (%s)", len, ' ', con->read ? 'R' : '-',
+                        con->write ? 'W' : '-', con->unblank ? 'U' : '-',
+                        flags);
+        if (dev)
+                seq_printf(m, " %4d:%d", MAJOR(dev), MINOR(dev));
+
+        seq_printf(m, "\n");
+
+        return 0;
+}
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+        struct console *con;
+        loff_t off = 0;
+
+        acquire_console_sem();
+        for_each_console(con)
+                if (off++ == *pos)
+                        break;
+
+        return con;
+}
+
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+        struct console *con = v;
+        ++*pos;
+        return con->next;
+}
+
+static void c_stop(struct seq_file *m, void *v)
+{
+        release_console_sem();
+}
+
+static const struct seq_operations consoles_op = {
+        .start  = c_start,
+        .next   = c_next,
+        .stop   = c_stop,
+        .show   = show_console_dev
+};
+
+static int consoles_open(struct inode *inode, struct file *file)
+{
+        return seq_open(file, &consoles_op);
+}
+
+static const struct file_operations proc_consoles_operations = {
+        .open           = consoles_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = seq_release,
+};
+
+static int register_proc_consoles(void)
+{
+        proc_create("consoles", 0, NULL, &proc_consoles_operations);
+        return 0;
+}
+module_init(register_proc_consoles);
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index b652cb00906b..09a1f92a34ef 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -5,6 +5,7 @@
 #include <linux/sysctl.h>
 #include <linux/proc_fs.h>
 #include <linux/security.h>
+#include <linux/namei.h>
 #include "internal.h"
 
 static const struct dentry_operations proc_sys_dentry_operations;
@@ -120,7 +121,7 @@ static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
                 goto out;
 
         err = NULL;
-        dentry->d_op = &proc_sys_dentry_operations;
+        d_set_d_op(dentry, &proc_sys_dentry_operations);
         d_add(dentry, inode);
 
 out:
@@ -201,7 +202,7 @@ static int proc_sys_fill_cache(struct file *filp, void *dirent,
                                 dput(child);
                                 return -ENOMEM;
                         } else {
-                                child->d_op = &proc_sys_dentry_operations;
+                                d_set_d_op(child, &proc_sys_dentry_operations);
                                 d_add(child, inode);
                         }
                 } else {
@@ -294,7 +295,7 @@ out:
         return ret;
 }
 
-static int proc_sys_permission(struct inode *inode, int mask)
+static int proc_sys_permission(struct inode *inode, int mask,unsigned int flags)
 {
         /*
          * sysctl entries that are not writeable,
@@ -304,6 +305,9 @@ static int proc_sys_permission(struct inode *inode, int mask)
         struct ctl_table *table;
         int error;
 
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
         /* Executable files are not allowed under /proc/sys/ */
         if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))
                 return -EACCES;
@@ -389,23 +393,30 @@ static const struct inode_operations proc_sys_dir_operations = {
 
 static int proc_sys_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
         return !PROC_I(dentry->d_inode)->sysctl->unregistering;
 }
 
-static int proc_sys_delete(struct dentry *dentry)
+static int proc_sys_delete(const struct dentry *dentry)
 {
         return !!PROC_I(dentry->d_inode)->sysctl->unregistering;
 }
 
-static int proc_sys_compare(struct dentry *dir, struct qstr *qstr,
-                            struct qstr *name)
+static int proc_sys_compare(const struct dentry *parent,
+                const struct inode *pinode,
+                const struct dentry *dentry, const struct inode *inode,
+                unsigned int len, const char *str, const struct qstr *name)
 {
-        struct dentry *dentry = container_of(qstr, struct dentry, d_name);
-        if (qstr->len != name->len)
+        /* Although proc doesn't have negative dentries, rcu-walk means
+         * that inode here can be NULL */
+        if (!inode)
+                return 0;
+        if (name->len != len)
                 return 1;
-        if (memcmp(qstr->name, name->name, name->len))
+        if (memcmp(name->name, str, len))
                 return 1;
-        return !sysctl_is_seen(PROC_I(dentry->d_inode)->sysctl);
+        return !sysctl_is_seen(PROC_I(inode)->sysctl);
 }
 
 static const struct dentry_operations proc_sys_dentry_operations = {
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 2367fb3f70bc..74802bc5ded9 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -499,7 +499,7 @@ static int __init parse_crash_elf64_headers(void)
         /* Do some basic Verification. */
         if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0 ||
                 (ehdr.e_type != ET_CORE) ||
-                !vmcore_elf_check_arch(&ehdr) ||
+                !vmcore_elf64_check_arch(&ehdr) ||
                 ehdr.e_ident[EI_CLASS] != ELFCLASS64 ||
                 ehdr.e_ident[EI_VERSION] != EV_CURRENT ||
                 ehdr.e_version != EV_CURRENT ||
diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c
index fcada42f1aa3..e63b4171d583 100644
--- a/fs/qnx4/inode.c
+++ b/fs/qnx4/inode.c
@@ -425,11 +425,18 @@ static struct inode *qnx4_alloc_inode(struct super_block *sb)
         return &ei->vfs_inode;
 }
 
-static void qnx4_destroy_inode(struct inode *inode)
+static void qnx4_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(qnx4_inode_cachep, qnx4_i(inode));
 }
 
+static void qnx4_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, qnx4_i_callback);
+}
+
 static void init_once(void *foo)
 {
         struct qnx4_inode_info *ei = (struct qnx4_inode_info *) foo;
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index b243117b8752..2575682a9ead 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -529,11 +529,18 @@ static struct inode *reiserfs_alloc_inode(struct super_block *sb)
         return &ei->vfs_inode;
 }
 
-static void reiserfs_destroy_inode(struct inode *inode)
+static void reiserfs_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(reiserfs_inode_cachep, REISERFS_I(inode));
 }
 
+static void reiserfs_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, reiserfs_i_callback);
+}
+
 static void init_once(void *foo)
 {
         struct reiserfs_inode_info *ei = (struct reiserfs_inode_info *)foo;
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 5d04a7828e7a..3cfb2e933644 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -870,11 +870,14 @@ out:
         return err;
 }
 
-static int reiserfs_check_acl(struct inode *inode, int mask)
+static int reiserfs_check_acl(struct inode *inode, int mask, unsigned int flags)
 {
         struct posix_acl *acl;
         int error = -EAGAIN; /* do regular unix permission checks by default */
 
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
         acl = reiserfs_get_acl(inode, ACL_TYPE_ACCESS);
 
         if (acl) {
@@ -951,8 +954,10 @@ static int xattr_mount_check(struct super_block *s)
         return 0;
 }
 
-int reiserfs_permission(struct inode *inode, int mask)
+int reiserfs_permission(struct inode *inode, int mask, unsigned int flags)
 {
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
         /*
          * We don't do permission checks on the internal objects.
          * Permissions are determined by the "owning" object.
@@ -965,13 +970,16 @@ int reiserfs_permission(struct inode *inode, int mask)
          * Stat data v1 doesn't support ACLs.
          */
         if (get_inode_sd_version(inode) != STAT_DATA_V1)
-                return generic_permission(inode, mask, reiserfs_check_acl);
+                return generic_permission(inode, mask, flags,
+                                        reiserfs_check_acl);
 #endif
-        return generic_permission(inode, mask, NULL);
+        return generic_permission(inode, mask, flags, NULL);
 }
 
 static int xattr_hide_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
         return -EPERM;
 }
 
@@ -990,7 +998,7 @@ int reiserfs_lookup_privroot(struct super_block *s)
                                 strlen(PRIVROOT_NAME));
         if (!IS_ERR(dentry)) {
                 REISERFS_SB(s)->priv_root = dentry;
-                dentry->d_op = &xattr_lookup_poison_ops;
+                d_set_d_op(dentry, &xattr_lookup_poison_ops);
                 if (dentry->d_inode)
                         dentry->d_inode->i_flags |= S_PRIVATE;
         } else
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index 6647f90e55cd..2305e3121cb1 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -400,11 +400,18 @@ static struct inode *romfs_alloc_inode(struct super_block *sb)
 /*
  * return a spent inode to the slab cache
  */
-static void romfs_destroy_inode(struct inode *inode)
+static void romfs_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(romfs_inode_cachep, ROMFS_I(inode));
 }
 
+static void romfs_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, romfs_i_callback);
+}
+
 /*
  * get filesystem statistics
  */
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 24de30ba34c1..20700b9f2b4c 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -440,11 +440,18 @@ static struct inode *squashfs_alloc_inode(struct super_block *sb)
 }
 
 
-static void squashfs_destroy_inode(struct inode *inode)
+static void squashfs_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(squashfs_inode_cachep, squashfs_i(inode));
 }
 
+static void squashfs_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, squashfs_i_callback);
+}
+
 
 static struct file_system_type squashfs_fs_type = {
         .owner = THIS_MODULE,
diff --git a/fs/super.c b/fs/super.c
index ca696155cd9a..823e061faa87 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -30,6 +30,7 @@
 #include <linux/idr.h>
 #include <linux/mutex.h>
 #include <linux/backing-dev.h>
+#include <linux/rculist_bl.h>
 #include "internal.h"
 
 
@@ -71,7 +72,7 @@ static struct super_block *alloc_super(struct file_system_type *type)
                 INIT_LIST_HEAD(&s->s_files);
 #endif
                 INIT_LIST_HEAD(&s->s_instances);
-                INIT_HLIST_HEAD(&s->s_anon);
+                INIT_HLIST_BL_HEAD(&s->s_anon);
                 INIT_LIST_HEAD(&s->s_inodes);
                 INIT_LIST_HEAD(&s->s_dentry_lru);
                 init_rwsem(&s->s_umount);
@@ -1139,7 +1140,7 @@ static struct vfsmount *fs_set_subtype(struct vfsmount *mnt, const char *fstype)
         return mnt;
 
  err:
-        mntput(mnt);
+        mntput_long(mnt);
         return ERR_PTR(err);
 }
 
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 7e54bac8c4b0..ea9120a830d8 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -231,7 +231,7 @@ void release_sysfs_dirent(struct sysfs_dirent * sd)
                 goto repeat;
 }
 
-static int sysfs_dentry_delete(struct dentry *dentry)
+static int sysfs_dentry_delete(const struct dentry *dentry)
 {
         struct sysfs_dirent *sd = dentry->d_fsdata;
         return !!(sd->s_flags & SYSFS_FLAG_REMOVED);
@@ -239,9 +239,13 @@ static int sysfs_dentry_delete(struct dentry *dentry)
 
 static int sysfs_dentry_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
-        struct sysfs_dirent *sd = dentry->d_fsdata;
+        struct sysfs_dirent *sd;
         int is_dir;
 
+        if (nd->flags & LOOKUP_RCU)
+                return -ECHILD;
+
+        sd = dentry->d_fsdata;
         mutex_lock(&sysfs_mutex);
 
         /* The sysfs dirent has been deleted */
@@ -701,7 +705,7 @@ static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry,
         /* instantiate and hash dentry */
         ret = d_find_alias(inode);
         if (!ret) {
-                dentry->d_op = &sysfs_dentry_ops;
+                d_set_d_op(dentry, &sysfs_dentry_ops);
                 dentry->d_fsdata = sysfs_get(sd);
                 d_add(dentry, inode);
         } else {
diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c
index cffb1fd8ba33..0a12eb89cd32 100644
--- a/fs/sysfs/inode.c
+++ b/fs/sysfs/inode.c
@@ -19,6 +19,7 @@
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/sysfs.h>
 #include <linux/xattr.h>
 #include <linux/security.h>
 #include "sysfs.h"
@@ -348,13 +349,18 @@ int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const void *ns, const cha
                 return -ENOENT;
 }
 
-int sysfs_permission(struct inode *inode, int mask)
+int sysfs_permission(struct inode *inode, int mask, unsigned int flags)
 {
-        struct sysfs_dirent *sd = inode->i_private;
+        struct sysfs_dirent *sd;
+
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
+        sd = inode->i_private;
 
         mutex_lock(&sysfs_mutex);
         sysfs_refresh_inode(sd, inode);
         mutex_unlock(&sysfs_mutex);
 
-        return generic_permission(inode, mask, NULL);
+        return generic_permission(inode, mask, flags, NULL);
 }
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index d9be60a2e956..3d28af31d863 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -9,6 +9,7 @@
  */
 
 #include <linux/lockdep.h>
+#include <linux/kobject_ns.h>
 #include <linux/fs.h>
 
 struct sysfs_open_dirent;
@@ -200,7 +201,7 @@ static inline void __sysfs_put(struct sysfs_dirent *sd)
 struct inode *sysfs_get_inode(struct super_block *sb, struct sysfs_dirent *sd);
 void sysfs_evict_inode(struct inode *inode);
 int sysfs_sd_setattr(struct sysfs_dirent *sd, struct iattr *iattr);
-int sysfs_permission(struct inode *inode, int mask);
+int sysfs_permission(struct inode *inode, int mask, unsigned int flags);
 int sysfs_setattr(struct dentry *dentry, struct iattr *iattr);
 int sysfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat);
 int sysfs_setxattr(struct dentry *dentry, const char *name, const void *value,
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index de44d067b9e6..0630eb969a28 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -333,11 +333,18 @@ static struct inode *sysv_alloc_inode(struct super_block *sb)
         return &si->vfs_inode;
 }
 
-static void sysv_destroy_inode(struct inode *inode)
+static void sysv_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(sysv_inode_cachep, SYSV_I(inode));
 }
 
+static void sysv_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, sysv_i_callback);
+}
+
 static void init_once(void *p)
 {
         struct sysv_inode_info *si = (struct sysv_inode_info *)p;
diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c
index 11e7f7d11cd0..b5e68da2db32 100644
--- a/fs/sysv/namei.c
+++ b/fs/sysv/namei.c
@@ -27,7 +27,8 @@ static int add_nondir(struct dentry *dentry, struct inode *inode)
         return err;
 }
 
-static int sysv_hash(struct dentry *dentry, struct qstr *qstr)
+static int sysv_hash(const struct dentry *dentry, const struct inode *inode,
+                struct qstr *qstr)
 {
         /* Truncate the name in place, avoids having to define a compare
            function. */
@@ -47,7 +48,7 @@ static struct dentry *sysv_lookup(struct inode * dir, struct dentry * dentry, st
         struct inode * inode = NULL;
         ino_t ino;
 
-        dentry->d_op = dir->i_sb->s_root->d_op;
+        d_set_d_op(dentry, dir->i_sb->s_root->d_op);
         if (dentry->d_name.len > SYSV_NAMELEN)
                 return ERR_PTR(-ENAMETOOLONG);
         ino = sysv_inode_by_name(dentry);
diff --git a/fs/sysv/super.c b/fs/sysv/super.c
index 3d9c62be0c10..76712aefc4ab 100644
--- a/fs/sysv/super.c
+++ b/fs/sysv/super.c
@@ -346,7 +346,7 @@ static int complete_read_super(struct super_block *sb, int silent, int size)
         if (sbi->s_forced_ro)
                 sb->s_flags |= MS_RDONLY;
         if (sbi->s_truncate)
-                sb->s_root->d_op = &sysv_dentry_operations;
+                d_set_d_op(sb->s_root, &sysv_dentry_operations);
         return 1;
 }
 
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 91fac54c70e3..6e11c2975dcf 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -272,12 +272,20 @@ static struct inode *ubifs_alloc_inode(struct super_block *sb)
         return &ui->vfs_inode;
 };
 
+static void ubifs_i_callback(struct rcu_head *head)
+{
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        struct ubifs_inode *ui = ubifs_inode(inode);
+        INIT_LIST_HEAD(&inode->i_dentry);
+        kmem_cache_free(ubifs_inode_slab, ui);
+}
+
 static void ubifs_destroy_inode(struct inode *inode)
 {
         struct ubifs_inode *ui = ubifs_inode(inode);
 
         kfree(ui->data);
-        kmem_cache_free(ubifs_inode_slab, inode);
+        call_rcu(&inode->i_rcu, ubifs_i_callback);
 }
 
 /*
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 4a5c7c61836a..b539d53320fb 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -139,11 +139,18 @@ static struct inode *udf_alloc_inode(struct super_block *sb)
         return &ei->vfs_inode;
 }
 
-static void udf_destroy_inode(struct inode *inode)
+static void udf_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(udf_inode_cachep, UDF_I(inode));
 }
 
+static void udf_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, udf_i_callback);
+}
+
 static void init_once(void *foo)
 {
         struct udf_inode_info *ei = (struct udf_inode_info *)foo;
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index 2c47daed56da..2c61ac5d4e48 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -1412,11 +1412,18 @@ static struct inode *ufs_alloc_inode(struct super_block *sb)
         return &ei->vfs_inode;
 }
 
-static void ufs_destroy_inode(struct inode *inode)
+static void ufs_i_callback(struct rcu_head *head)
 {
+        struct inode *inode = container_of(head, struct inode, i_rcu);
+        INIT_LIST_HEAD(&inode->i_dentry);
         kmem_cache_free(ufs_inode_cachep, UFS_I(inode));
 }
 
+static void ufs_destroy_inode(struct inode *inode)
+{
+        call_rcu(&inode->i_rcu, ufs_i_callback);
+}
+
 static void init_once(void *foo)
 {
         struct ufs_inode_info *ei = (struct ufs_inode_info *) foo;
diff --git a/fs/xfs/linux-2.6/xfs_acl.c b/fs/xfs/linux-2.6/xfs_acl.c
index b2771862fd3d..39f4f809bb68 100644
--- a/fs/xfs/linux-2.6/xfs_acl.c
+++ b/fs/xfs/linux-2.6/xfs_acl.c
@@ -219,12 +219,13 @@ xfs_set_acl(struct inode *inode, int type, struct posix_acl *acl)
 }
 
 int
-xfs_check_acl(struct inode *inode, int mask)
+xfs_check_acl(struct inode *inode, int mask, unsigned int flags)
 {
-        struct xfs_inode *ip = XFS_I(inode);
+        struct xfs_inode *ip;
         struct posix_acl *acl;
         int error = -EAGAIN;
 
+        ip = XFS_I(inode);
         trace_xfs_check_acl(ip);
 
         /*
@@ -234,6 +235,12 @@ xfs_check_acl(struct inode *inode, int mask)
         if (!XFS_IFORK_Q(ip))
                 return -EAGAIN;
 
+        if (flags & IPERM_FLAG_RCU) {
+                if (!negative_cached_acl(inode, ACL_TYPE_ACCESS))
+                        return -ECHILD;
+                return -EAGAIN;
+        }
+
         acl = xfs_get_acl(inode, ACL_TYPE_ACCESS);
         if (IS_ERR(acl))
                 return PTR_ERR(acl);
diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h
index 0135e2a669d7..11dd72070cbb 100644
--- a/fs/xfs/xfs_acl.h
+++ b/fs/xfs/xfs_acl.h
@@ -42,7 +42,7 @@ struct xfs_acl {
 #define SGI_ACL_DEFAULT_SIZE    (sizeof(SGI_ACL_DEFAULT)-1)
 
 #ifdef CONFIG_XFS_POSIX_ACL
-extern int xfs_check_acl(struct inode *inode, int mask);
+extern int xfs_check_acl(struct inode *inode, int mask, unsigned int flags);
 extern struct posix_acl *xfs_get_acl(struct inode *inode, int type);
 extern int xfs_inherit_acl(struct inode *inode, struct posix_acl *default_acl);
 extern int xfs_acl_chmod(struct inode *inode);
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index 0cdd26932d8e..d7de5a3f7867 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -91,6 +91,17 @@ xfs_inode_alloc(
         return ip;
 }
 
+STATIC void
+xfs_inode_free_callback(
+        struct rcu_head         *head)
+{
+        struct inode            *inode = container_of(head, struct inode, i_rcu);
+        struct xfs_inode        *ip = XFS_I(inode);
+
+        INIT_LIST_HEAD(&inode->i_dentry);
+        kmem_zone_free(xfs_inode_zone, ip);
+}
+
 void
 xfs_inode_free(
         struct xfs_inode        *ip)
@@ -134,7 +145,7 @@ xfs_inode_free(
         ASSERT(!spin_is_locked(&ip->i_flags_lock));
         ASSERT(completion_done(&ip->i_flush));
 
-        kmem_zone_free(xfs_inode_zone, ip);
+        call_rcu(&ip->i_vnode.i_rcu, xfs_inode_free_callback);
 }
 
 /*
diff --git a/fs/xfs/xfs_mru_cache.c b/fs/xfs/xfs_mru_cache.c
index 45ce15dc5b2b..edfa178bafb6 100644
--- a/fs/xfs/xfs_mru_cache.c
+++ b/fs/xfs/xfs_mru_cache.c
@@ -408,7 +408,7 @@ xfs_mru_cache_flush(
         spin_lock(&mru->lock);
         if (mru->queued) {
                 spin_unlock(&mru->lock);
-                cancel_rearming_delayed_workqueue(xfs_mru_reap_wq, &mru->work);
+                cancel_delayed_work_sync(&mru->work);
                 spin_lock(&mru->lock);
         }
 
diff --git a/fs/xfs/xfs_rename.c b/fs/xfs/xfs_rename.c
index d2af0a8381a6..77a59891734e 100644
--- a/fs/xfs/xfs_rename.c
+++ b/fs/xfs/xfs_rename.c
@@ -297,6 +297,7 @@ xfs_rename(
          * it and some incremental backup programs won't work without it.
          */
         xfs_trans_ichgtime(tp, src_ip, XFS_ICHGTIME_CHG);
+        xfs_trans_log_inode(tp, src_ip, XFS_ILOG_CORE);
 
         /*
          * Adjust the link count on src_dp.  This is necessary when