300 files changed, 16655 insertions, 7772 deletions

diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 047c791427aa..24eb01087b6d 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -30,8 +30,8 @@
 #include <linux/parser.h>
 #include <linux/idr.h>
 #include <net/9p/9p.h>
-#include <net/9p/transport.h>
 #include <net/9p/client.h>
+#include <net/9p/transport.h>
 #include "v9fs.h"
 #include "v9fs_vfs.h"
 
@@ -55,7 +55,7 @@ enum {
         Opt_err
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         {Opt_debug, "debug=%x"},
         {Opt_dfltuid, "dfltuid=%u"},
         {Opt_dfltgid, "dfltgid=%u"},
@@ -234,7 +234,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
         if (!v9ses->clnt->dotu)
                 v9ses->flags &= ~V9FS_EXTENDED;
 
-        v9ses->maxdata = v9ses->clnt->msize;
+        v9ses->maxdata = v9ses->clnt->msize - P9_IOHDRSZ;
 
         /* for legacy mode, fall back to V9FS_ACCESS_ANY */
         if (!v9fs_extended(v9ses) &&
diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h
index 57997fa14e69..c295ba786edd 100644
--- a/fs/9p/v9fs_vfs.h
+++ b/fs/9p/v9fs_vfs.h
@@ -46,9 +46,11 @@ extern struct dentry_operations v9fs_cached_dentry_operations;
 
 struct inode *v9fs_get_inode(struct super_block *sb, int mode);
 ino_t v9fs_qid2ino(struct p9_qid *qid);
-void v9fs_stat2inode(struct p9_stat *, struct inode *, struct super_block *);
+void v9fs_stat2inode(struct p9_wstat *, struct inode *, struct super_block *);
 int v9fs_dir_release(struct inode *inode, struct file *filp);
 int v9fs_file_open(struct inode *inode, struct file *file);
-void v9fs_inode2stat(struct inode *inode, struct p9_stat *stat);
+void v9fs_inode2stat(struct inode *inode, struct p9_wstat *stat);
 void v9fs_dentry_release(struct dentry *);
 int v9fs_uflags2omode(int uflags, int extended);
+
+ssize_t v9fs_file_readn(struct file *, char *, char __user *, u32, u64);
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 97d3aed57983..6fcb1e7095cf 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -38,7 +38,6 @@
 
 #include "v9fs.h"
 #include "v9fs_vfs.h"
-#include "fid.h"
 
 /**
  * v9fs_vfs_readpage - read an entire page in from 9P
@@ -53,14 +52,12 @@ static int v9fs_vfs_readpage(struct file *filp, struct page *page)
         int retval;
         loff_t offset;
         char *buffer;
-        struct p9_fid *fid;
 
         P9_DPRINTK(P9_DEBUG_VFS, "\n");
-        fid = filp->private_data;
         buffer = kmap(page);
         offset = page_offset(page);
 
-        retval = p9_client_readn(fid, buffer, offset, PAGE_CACHE_SIZE);
+        retval = v9fs_file_readn(filp, buffer, NULL, offset, PAGE_CACHE_SIZE);
         if (retval < 0)
                 goto done;
 
diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c
index e298fe194093..873cd31baa47 100644
--- a/fs/9p/vfs_dir.c
+++ b/fs/9p/vfs_dir.c
@@ -45,7 +45,7 @@
  *
  */
 
-static inline int dt_type(struct p9_stat *mistat)
+static inline int dt_type(struct p9_wstat *mistat)
 {
         unsigned long perm = mistat->mode;
         int rettype = DT_REG;
@@ -69,32 +69,58 @@ static inline int dt_type(struct p9_stat *mistat)
 static int v9fs_dir_readdir(struct file *filp, void *dirent, filldir_t filldir)
 {
         int over;
+        struct p9_wstat st;
+        int err;
         struct p9_fid *fid;
-        struct v9fs_session_info *v9ses;
-        struct inode *inode;
-        struct p9_stat *st;
+        int buflen;
+        char *statbuf;
+        int n, i = 0;
 
         P9_DPRINTK(P9_DEBUG_VFS, "name %s\n", filp->f_path.dentry->d_name.name);
-        inode = filp->f_path.dentry->d_inode;
-        v9ses = v9fs_inode2v9ses(inode);
         fid = filp->private_data;
-        while ((st = p9_client_dirread(fid, filp->f_pos)) != NULL) {
-                if (IS_ERR(st))
-                        return PTR_ERR(st);
 
-                over = filldir(dirent, st->name.str, st->name.len, filp->f_pos,
-                        v9fs_qid2ino(&st->qid), dt_type(st));
+        buflen = fid->clnt->msize - P9_IOHDRSZ;
+        statbuf = kmalloc(buflen, GFP_KERNEL);
+        if (!statbuf)
+                return -ENOMEM;
 
-                if (over)
+        while (1) {
+                err = v9fs_file_readn(filp, statbuf, NULL, buflen,
+                                                                fid->rdir_fpos);
+                if (err <= 0)
                         break;
 
-                filp->f_pos += st->size;
-                kfree(st);
-                st = NULL;
+                n = err;
+                while (i < n) {
+                        err = p9stat_read(statbuf + i, buflen-i, &st,
+                                                        fid->clnt->dotu);
+                        if (err) {
+                                P9_DPRINTK(P9_DEBUG_VFS, "returned %d\n", err);
+                                err = -EIO;
+                                p9stat_free(&st);
+                                goto free_and_exit;
+                        }
+
+                        i += st.size+2;
+                        fid->rdir_fpos += st.size+2;
+
+                        over = filldir(dirent, st.name, strlen(st.name),
+                            filp->f_pos, v9fs_qid2ino(&st.qid), dt_type(&st));
+
+                        filp->f_pos += st.size+2;
+
+                        p9stat_free(&st);
+
+                        if (over) {
+                                err = 0;
+                                goto free_and_exit;
+                        }
+                }
         }
 
-        kfree(st);
-        return 0;
+free_and_exit:
+        kfree(statbuf);
+        return err;
 }
 
 
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 52944d2249a4..041c52692284 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -120,23 +120,72 @@ static int v9fs_file_lock(struct file *filp, int cmd, struct file_lock *fl)
 }
 
 /**
- * v9fs_file_read - read from a file
+ * v9fs_file_readn - read from a file
  * @filp: file pointer to read
  * @data: data buffer to read data into
+ * @udata: user data buffer to read data into
  * @count: size of buffer
  * @offset: offset at which to read data
  *
  */
+
+ssize_t
+v9fs_file_readn(struct file *filp, char *data, char __user *udata, u32 count,
+               u64 offset)
+{
+        int n, total;
+        struct p9_fid *fid = filp->private_data;
+
+        P9_DPRINTK(P9_DEBUG_VFS, "fid %d offset %llu count %d\n", fid->fid,
+                                        (long long unsigned) offset, count);
+
+        n = 0;
+        total = 0;
+        do {
+                n = p9_client_read(fid, data, udata, offset, count);
+                if (n <= 0)
+                        break;
+
+                if (data)
+                        data += n;
+                if (udata)
+                        udata += n;
+
+                offset += n;
+                count -= n;
+                total += n;
+        } while (count > 0 && n == (fid->clnt->msize - P9_IOHDRSZ));
+
+        if (n < 0)
+                total = n;
+
+        return total;
+}
+
+/**
+ * v9fs_file_read - read from a file
+ * @filp: file pointer to read
+ * @udata: user data buffer to read data into
+ * @count: size of buffer
+ * @offset: offset at which to read data
+ *
+ */
+
 static ssize_t
-v9fs_file_read(struct file *filp, char __user * data, size_t count,
+v9fs_file_read(struct file *filp, char __user *udata, size_t count,
                loff_t * offset)
 {
         int ret;
         struct p9_fid *fid;
 
-        P9_DPRINTK(P9_DEBUG_VFS, "\n");
+        P9_DPRINTK(P9_DEBUG_VFS, "count %d offset %lld\n", count, *offset);
         fid = filp->private_data;
-        ret = p9_client_uread(fid, data, *offset, count);
+
+        if (count > (fid->clnt->msize - P9_IOHDRSZ))
+                ret = v9fs_file_readn(filp, NULL, udata, count, *offset);
+        else
+                ret = p9_client_read(fid, NULL, udata, *offset, count);
+
         if (ret > 0)
                 *offset += ret;
 
@@ -156,19 +205,38 @@ static ssize_t
 v9fs_file_write(struct file *filp, const char __user * data,
                 size_t count, loff_t * offset)
 {
-        int ret;
+        int n, rsize, total = 0;
         struct p9_fid *fid;
+        struct p9_client *clnt;
         struct inode *inode = filp->f_path.dentry->d_inode;
+        int origin = *offset;
 
         P9_DPRINTK(P9_DEBUG_VFS, "data %p count %d offset %x\n", data,
                 (int)count, (int)*offset);
 
         fid = filp->private_data;
-        ret = p9_client_uwrite(fid, data, *offset, count);
-        if (ret > 0) {
-                invalidate_inode_pages2_range(inode->i_mapping, *offset,
-                                                                *offset+ret);
-                *offset += ret;
+        clnt = fid->clnt;
+
+        rsize = fid->iounit;
+        if (!rsize || rsize > clnt->msize-P9_IOHDRSZ)
+                rsize = clnt->msize - P9_IOHDRSZ;
+
+        do {
+                if (count < rsize)
+                        rsize = count;
+
+                n = p9_client_write(fid, NULL, data+total, *offset+total,
+                                                                        rsize);
+                if (n <= 0)
+                        break;
+                count -= n;
+                total += n;
+        } while (count > 0);
+
+        if (total > 0) {
+                invalidate_inode_pages2_range(inode->i_mapping, origin,
+                                                                origin+total);
+                *offset += total;
         }
 
         if (*offset > inode->i_size) {
@@ -176,7 +244,10 @@ v9fs_file_write(struct file *filp, const char __user * data,
                 inode->i_blocks = (inode->i_size + 512 - 1) >> 9;
         }
 
-        return ret;
+        if (n < 0)
+                return n;
+
+        return total;
 }
 
 static const struct file_operations v9fs_cached_file_operations = {
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index e83aa5ebe861..8314d3f43b71 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -334,7 +334,7 @@ v9fs_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
 {
         int err, umode;
         struct inode *ret;
-        struct p9_stat *st;
+        struct p9_wstat *st;
 
         ret = NULL;
         st = p9_client_stat(fid);
@@ -417,6 +417,8 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
         struct p9_fid *dfid, *ofid, *fid;
         struct inode *inode;
 
+        P9_DPRINTK(P9_DEBUG_VFS, "name %s\n", dentry->d_name.name);
+
         err = 0;
         ofid = NULL;
         fid = NULL;
@@ -424,6 +426,7 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
         dfid = v9fs_fid_clone(dentry->d_parent);
         if (IS_ERR(dfid)) {
                 err = PTR_ERR(dfid);
+                P9_DPRINTK(P9_DEBUG_VFS, "fid clone failed %d\n", err);
                 dfid = NULL;
                 goto error;
         }
@@ -432,18 +435,22 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
         ofid = p9_client_walk(dfid, 0, NULL, 1);
         if (IS_ERR(ofid)) {
                 err = PTR_ERR(ofid);
+                P9_DPRINTK(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err);
                 ofid = NULL;
                 goto error;
         }
 
         err = p9_client_fcreate(ofid, name, perm, mode, extension);
-        if (err < 0)
+        if (err < 0) {
+                P9_DPRINTK(P9_DEBUG_VFS, "p9_client_fcreate failed %d\n", err);
                 goto error;
+        }
 
         /* now walk from the parent so we can get unopened fid */
         fid = p9_client_walk(dfid, 1, &name, 0);
         if (IS_ERR(fid)) {
                 err = PTR_ERR(fid);
+                P9_DPRINTK(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err);
                 fid = NULL;
                 goto error;
         } else
@@ -453,6 +460,7 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
         inode = v9fs_inode_from_fid(v9ses, fid, dir->i_sb);
         if (IS_ERR(inode)) {
                 err = PTR_ERR(inode);
+                P9_DPRINTK(P9_DEBUG_VFS, "inode creation failed %d\n", err);
                 goto error;
         }
 
@@ -734,7 +742,7 @@ v9fs_vfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
         int err;
         struct v9fs_session_info *v9ses;
         struct p9_fid *fid;
-        struct p9_stat *st;
+        struct p9_wstat *st;
 
         P9_DPRINTK(P9_DEBUG_VFS, "dentry: %p\n", dentry);
         err = -EPERM;
@@ -815,10 +823,9 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr)
  */
 
 void
-v9fs_stat2inode(struct p9_stat *stat, struct inode *inode,
+v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode,
         struct super_block *sb)
 {
-        int n;
         char ext[32];
         struct v9fs_session_info *v9ses = sb->s_fs_info;
 
@@ -842,11 +849,7 @@ v9fs_stat2inode(struct p9_stat *stat, struct inode *inode,
                 int major = -1;
                 int minor = -1;
 
-                n = stat->extension.len;
-                if (n > sizeof(ext)-1)
-                        n = sizeof(ext)-1;
-                memmove(ext, stat->extension.str, n);
-                ext[n] = 0;
+                strncpy(ext, stat->extension, sizeof(ext));
                 sscanf(ext, "%c %u %u", &type, &major, &minor);
                 switch (type) {
                 case 'c':
@@ -857,10 +860,11 @@ v9fs_stat2inode(struct p9_stat *stat, struct inode *inode,
                         break;
                 default:
                         P9_DPRINTK(P9_DEBUG_ERROR,
-                                "Unknown special type %c (%.*s)\n", type,
-                                stat->extension.len, stat->extension.str);
+                                "Unknown special type %c %s\n", type,
+                                stat->extension);
                 };
                 inode->i_rdev = MKDEV(major, minor);
+                init_special_inode(inode, inode->i_mode, inode->i_rdev);
         } else
                 inode->i_rdev = 0;
 
@@ -904,7 +908,7 @@ static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen)
 
         struct v9fs_session_info *v9ses;
         struct p9_fid *fid;
-        struct p9_stat *st;
+        struct p9_wstat *st;
 
         P9_DPRINTK(P9_DEBUG_VFS, " %s\n", dentry->d_name.name);
         retval = -EPERM;
@@ -926,15 +930,10 @@ static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen)
         }
 
         /* copy extension buffer into buffer */
-        if (st->extension.len < buflen)
-                buflen = st->extension.len + 1;
-
-        memmove(buffer, st->extension.str, buflen - 1);
-        buffer[buflen-1] = 0;
+        strncpy(buffer, st->extension, buflen);
 
         P9_DPRINTK(P9_DEBUG_VFS,
-                "%s -> %.*s (%s)\n", dentry->d_name.name, st->extension.len,
-                st->extension.str, buffer);
+                "%s -> %s (%s)\n", dentry->d_name.name, st->extension, buffer);
 
         retval = buflen;
 
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index bf59c3960494..d6cb1a0ca724 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -111,7 +111,7 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags,
         struct inode *inode = NULL;
         struct dentry *root = NULL;
         struct v9fs_session_info *v9ses = NULL;
-        struct p9_stat *st = NULL;
+        struct p9_wstat *st = NULL;
         int mode = S_IRWXUGO | S_ISVTX;
         uid_t uid = current->fsuid;
         gid_t gid = current->fsgid;
@@ -161,10 +161,14 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags,
 
         sb->s_root = root;
         root->d_inode->i_ino = v9fs_qid2ino(&st->qid);
+
         v9fs_stat2inode(st, root->d_inode, sb);
+
         v9fs_fid_add(root, fid);
+        p9stat_free(st);
         kfree(st);
 
+P9_DPRINTK(P9_DEBUG_VFS, " return simple set mount\n");
         return simple_set_mnt(mnt, sb);
 
 release_sb:
diff --git a/fs/Kconfig b/fs/Kconfig
index abccb5dab9a8..e46297f020c1 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -6,61 +6,9 @@ menu "File systems"
 
 if BLOCK
 
-config EXT2_FS
-        tristate "Second extended fs support"
-        help
-          Ext2 is a standard Linux file system for hard disks.
-
-          To compile this file system support as a module, choose M here: the
-          module will be called ext2.
-
-          If unsure, say Y.
-
-config EXT2_FS_XATTR
-        bool "Ext2 extended attributes"
-        depends on EXT2_FS
-        help
-          Extended attributes are name:value pairs associated with inodes by
-          the kernel or by users (see the attr(5) manual page, or visit
-          <http://acl.bestbits.at/> for details).
-
-          If unsure, say N.
-
-config EXT2_FS_POSIX_ACL
-        bool "Ext2 POSIX Access Control Lists"
-        depends on EXT2_FS_XATTR
-        select FS_POSIX_ACL
-        help
-          Posix Access Control Lists (ACLs) support permissions for users and
-          groups beyond the owner/group/world scheme.
-
-          To learn more about Access Control Lists, visit the Posix ACLs for
-          Linux website <http://acl.bestbits.at/>.
-
-          If you don't know what Access Control Lists are, say N
-
-config EXT2_FS_SECURITY
-        bool "Ext2 Security Labels"
-        depends on EXT2_FS_XATTR
-        help
-          Security labels support alternative access control models
-          implemented by security modules like SELinux.  This option
-          enables an extended attribute handler for file security
-          labels in the ext2 filesystem.
-
-          If you are not using a security module that requires using
-          extended attributes for file security labels, say N.
-
-config EXT2_FS_XIP
-        bool "Ext2 execute in place support"
-        depends on EXT2_FS && MMU
-        help
-          Execute in place can be used on memory-backed block devices. If you
-          enable this option, you can select to mount block devices which are
-          capable of this feature without using the page cache.
-
-          If you do not use a block device that is capable of using this,
-          or if unsure, say N.
+source "fs/ext2/Kconfig"
+source "fs/ext3/Kconfig"
+source "fs/ext4/Kconfig"
 
 config FS_XIP
 # execute in place
@@ -68,211 +16,15 @@ config FS_XIP
         depends on EXT2_FS_XIP
         default y
 
-config EXT3_FS
-        tristate "Ext3 journalling file system support"
-        select JBD
-        help
-          This is the journalling version of the Second extended file system
-          (often called ext3), the de facto standard Linux file system
-          (method to organize files on a storage device) for hard disks.
-
-          The journalling code included in this driver means you do not have
-          to run e2fsck (file system checker) on your file systems after a
-          crash.  The journal keeps track of any changes that were being made
-          at the time the system crashed, and can ensure that your file system
-          is consistent without the need for a lengthy check.
-
-          Other than adding the journal to the file system, the on-disk format
-          of ext3 is identical to ext2.  It is possible to freely switch
-          between using the ext3 driver and the ext2 driver, as long as the
-          file system has been cleanly unmounted, or e2fsck is run on the file
-          system.
-
-          To add a journal on an existing ext2 file system or change the
-          behavior of ext3 file systems, you can use the tune2fs utility ("man
-          tune2fs").  To modify attributes of files and directories on ext3
-          file systems, use chattr ("man chattr").  You need to be using
-          e2fsprogs version 1.20 or later in order to create ext3 journals
-          (available at <http://sourceforge.net/projects/e2fsprogs/>).
-
-          To compile this file system support as a module, choose M here: the
-          module will be called ext3.
-
-config EXT3_FS_XATTR
-        bool "Ext3 extended attributes"
-        depends on EXT3_FS
-        default y
-        help
-          Extended attributes are name:value pairs associated with inodes by
-          the kernel or by users (see the attr(5) manual page, or visit
-          <http://acl.bestbits.at/> for details).
-
-          If unsure, say N.
-
-          You need this for POSIX ACL support on ext3.
-
-config EXT3_FS_POSIX_ACL
-        bool "Ext3 POSIX Access Control Lists"
-        depends on EXT3_FS_XATTR
-        select FS_POSIX_ACL
-        help
-          Posix Access Control Lists (ACLs) support permissions for users and
-          groups beyond the owner/group/world scheme.
-
-          To learn more about Access Control Lists, visit the Posix ACLs for
-          Linux website <http://acl.bestbits.at/>.
-
-          If you don't know what Access Control Lists are, say N
-
-config EXT3_FS_SECURITY
-        bool "Ext3 Security Labels"
-        depends on EXT3_FS_XATTR
-        help
-          Security labels support alternative access control models
-          implemented by security modules like SELinux.  This option
-          enables an extended attribute handler for file security
-          labels in the ext3 filesystem.
-
-          If you are not using a security module that requires using
-          extended attributes for file security labels, say N.
-
-config EXT4DEV_FS
-        tristate "Ext4dev/ext4 extended fs support development (EXPERIMENTAL)"
-        depends on EXPERIMENTAL
-        select JBD2
-        select CRC16
-        help
-          Ext4dev is a predecessor filesystem of the next generation
-          extended fs ext4, based on ext3 filesystem code. It will be
-          renamed ext4 fs later, once ext4dev is mature and stabilized.
-
-          Unlike the change from ext2 filesystem to ext3 filesystem,
-          the on-disk format of ext4dev is not the same as ext3 any more:
-          it is based on extent maps and it supports 48-bit physical block
-          numbers. These combined on-disk format changes will allow
-          ext4dev/ext4 to handle more than 16 TB filesystem volumes --
-          a hard limit that ext3 cannot overcome without changing the
-          on-disk format.
-
-          Other than extent maps and 48-bit block numbers, ext4dev also is
-          likely to have other new features such as persistent preallocation,
-          high resolution time stamps, and larger file support etc.  These
-          features will be added to ext4dev gradually.
-
-          To compile this file system support as a module, choose M here. The
-          module will be called ext4dev.
-
-          If unsure, say N.
-
-config EXT4DEV_FS_XATTR
-        bool "Ext4dev extended attributes"
-        depends on EXT4DEV_FS
-        default y
-        help
-          Extended attributes are name:value pairs associated with inodes by
-          the kernel or by users (see the attr(5) manual page, or visit
-          <http://acl.bestbits.at/> for details).
-
-          If unsure, say N.
-
-          You need this for POSIX ACL support on ext4dev/ext4.
-
-config EXT4DEV_FS_POSIX_ACL
-        bool "Ext4dev POSIX Access Control Lists"
-        depends on EXT4DEV_FS_XATTR
-        select FS_POSIX_ACL
-        help
-          POSIX Access Control Lists (ACLs) support permissions for users and
-          groups beyond the owner/group/world scheme.
-
-          To learn more about Access Control Lists, visit the POSIX ACLs for
-          Linux website <http://acl.bestbits.at/>.
-
-          If you don't know what Access Control Lists are, say N
-
-config EXT4DEV_FS_SECURITY
-        bool "Ext4dev Security Labels"
-        depends on EXT4DEV_FS_XATTR
-        help
-          Security labels support alternative access control models
-          implemented by security modules like SELinux.  This option
-          enables an extended attribute handler for file security
-          labels in the ext4dev/ext4 filesystem.
-
-          If you are not using a security module that requires using
-          extended attributes for file security labels, say N.
-
-config JBD
-        tristate
-        help
-          This is a generic journalling layer for block devices.  It is
-          currently used by the ext3 and OCFS2 file systems, but it could
-          also be used to add journal support to other file systems or block
-          devices such as RAID or LVM.
-
-          If you are using the ext3 or OCFS2 file systems, you need to
-          say Y here. If you are not using ext3 OCFS2 then you will probably
-          want to say N.
-
-          To compile this device as a module, choose M here: the module will be
-          called jbd.  If you are compiling ext3 or OCFS2 into the kernel,
-          you cannot compile this code as a module.
-
-config JBD_DEBUG
-        bool "JBD (ext3) debugging support"
-        depends on JBD && DEBUG_FS
-        help
-          If you are using the ext3 journaled file system (or potentially any
-          other file system/device using JBD), this option allows you to
-          enable debugging output while the system is running, in order to
-          help track down any problems you are having.  By default the
-          debugging output will be turned off.
-
-          If you select Y here, then you will be able to turn on debugging
-          with "echo N > /sys/kernel/debug/jbd/jbd-debug", where N is a
-          number between 1 and 5, the higher the number, the more debugging
-          output is generated.  To turn debugging off again, do
-          "echo 0 > /sys/kernel/debug/jbd/jbd-debug".
-
-config JBD2
-        tristate
-        select CRC32
-        help
-          This is a generic journaling layer for block devices that support
-          both 32-bit and 64-bit block numbers.  It is currently used by
-          the ext4dev/ext4 filesystem, but it could also be used to add
-          journal support to other file systems or block devices such
-          as RAID or LVM.
-
-          If you are using ext4dev/ext4, you need to say Y here. If you are not
-          using ext4dev/ext4 then you will probably want to say N.
-
-          To compile this device as a module, choose M here. The module will be
-          called jbd2.  If you are compiling ext4dev/ext4 into the kernel,
-          you cannot compile this code as a module.
-
-config JBD2_DEBUG
-        bool "JBD2 (ext4dev/ext4) debugging support"
-        depends on JBD2 && DEBUG_FS
-        help
-          If you are using the ext4dev/ext4 journaled file system (or
-          potentially any other filesystem/device using JBD2), this option
-          allows you to enable debugging output while the system is running,
-          in order to help track down any problems you are having.
-          By default, the debugging output will be turned off.
-
-          If you select Y here, then you will be able to turn on debugging
-          with "echo N > /sys/kernel/debug/jbd2/jbd2-debug", where N is a
-          number between 1 and 5. The higher the number, the more debugging
-          output is generated.  To turn debugging off again, do
-          "echo 0 > /sys/kernel/debug/jbd2/jbd2-debug".
+source "fs/jbd/Kconfig"
+source "fs/jbd2/Kconfig"
 
 config FS_MBCACHE
 # Meta block cache for Extended Attributes (ext2/ext3/ext4)
         tristate
-        depends on EXT2_FS_XATTR || EXT3_FS_XATTR || EXT4DEV_FS_XATTR
-        default y if EXT2_FS=y || EXT3_FS=y || EXT4DEV_FS=y
-        default m if EXT2_FS=m || EXT3_FS=m || EXT4DEV_FS=m
+        depends on EXT2_FS_XATTR || EXT3_FS_XATTR || EXT4_FS_XATTR
+        default y if EXT2_FS=y || EXT3_FS=y || EXT4_FS=y
+        default m if EXT2_FS=m || EXT3_FS=m || EXT4_FS=m
 
 config REISERFS_FS
         tristate "Reiserfs support"
@@ -419,6 +171,14 @@ config FS_POSIX_ACL
         bool
         default n
 
+config FILE_LOCKING
+        bool "Enable POSIX file locking API" if EMBEDDED
+        default y
+        help
+          This option enables standard file locking support, required
+          for filesystems like NFS and for the flock() system
+          call. Disabling this option saves about 11k.
+
 source "fs/xfs/Kconfig"
 source "fs/gfs2/Kconfig"
 
@@ -426,7 +186,7 @@ config OCFS2_FS
         tristate "OCFS2 file system support"
         depends on NET && SYSFS
         select CONFIGFS_FS
-        select JBD
+        select JBD2
         select CRC32
         help
           OCFS2 is a general purpose extent based shared disk cluster file
@@ -497,6 +257,16 @@ config OCFS2_DEBUG_FS
           this option for debugging only as it is likely to decrease
           performance of the filesystem.
 
+config OCFS2_COMPAT_JBD
+        bool "Use JBD for compatibility"
+        depends on OCFS2_FS
+        default n
+        select JBD
+        help
+          The ocfs2 filesystem now uses JBD2 for its journalling.  JBD2
+          is backwards compatible with JBD.  It is safe to say N here.
+          However, if you really want to use the original JBD, say Y here.
+
 endif # BLOCK
 
 config DNOTIFY
@@ -633,7 +403,7 @@ config AUTOFS4_FS
           N here.
 
 config FUSE_FS
-        tristate "Filesystem in Userspace support"
+        tristate "FUSE (Filesystem in Userspace) support"
         help
           With FUSE it is possible to implement a fully functional filesystem
           in a userspace program.
@@ -1136,195 +906,7 @@ config EFS_FS
           To compile the EFS file system support as a module, choose M here: the
           module will be called efs.
 
-config JFFS2_FS
-        tristate "Journalling Flash File System v2 (JFFS2) support"
-        select CRC32
-        depends on MTD
-        help
-          JFFS2 is the second generation of the Journalling Flash File System
-          for use on diskless embedded devices. It provides improved wear
-          levelling, compression and support for hard links. You cannot use
-          this on normal block devices, only on 'MTD' devices.
-
-          Further information on the design and implementation of JFFS2 is
-          available at <http://sources.redhat.com/jffs2/>.
-
-config JFFS2_FS_DEBUG
-        int "JFFS2 debugging verbosity (0 = quiet, 2 = noisy)"
-        depends on JFFS2_FS
-        default "0"
-        help
-          This controls the amount of debugging messages produced by the JFFS2
-          code. Set it to zero for use in production systems. For evaluation,
-          testing and debugging, it's advisable to set it to one. This will
-          enable a few assertions and will print debugging messages at the
-          KERN_DEBUG loglevel, where they won't normally be visible. Level 2
-          is unlikely to be useful - it enables extra debugging in certain
-          areas which at one point needed debugging, but when the bugs were
-          located and fixed, the detailed messages were relegated to level 2.
-
-          If reporting bugs, please try to have available a full dump of the
-          messages at debug level 1 while the misbehaviour was occurring.
-
-config JFFS2_FS_WRITEBUFFER
-        bool "JFFS2 write-buffering support"
-        depends on JFFS2_FS
-        default y
-        help
-          This enables the write-buffering support in JFFS2.
-
-          This functionality is required to support JFFS2 on the following
-          types of flash devices:
-            - NAND flash
-            - NOR flash with transparent ECC
-            - DataFlash
-
-config JFFS2_FS_WBUF_VERIFY
-        bool "Verify JFFS2 write-buffer reads"
-        depends on JFFS2_FS_WRITEBUFFER
-        default n
-        help
-          This causes JFFS2 to read back every page written through the
-          write-buffer, and check for errors.
-
-config JFFS2_SUMMARY
-        bool "JFFS2 summary support (EXPERIMENTAL)"
-        depends on JFFS2_FS && EXPERIMENTAL
-        default n
-        help
-          This feature makes it possible to use summary information
-          for faster filesystem mount.
-
-          The summary information can be inserted into a filesystem image
-          by the utility 'sumtool'.
-
-          If unsure, say 'N'.
-
-config JFFS2_FS_XATTR
-        bool "JFFS2 XATTR support (EXPERIMENTAL)"
-        depends on JFFS2_FS && EXPERIMENTAL
-        default n
-        help
-          Extended attributes are name:value pairs associated with inodes by
-          the kernel or by users (see the attr(5) manual page, or visit
-          <http://acl.bestbits.at/> for details).
-
-          If unsure, say N.
-
-config JFFS2_FS_POSIX_ACL
-        bool "JFFS2 POSIX Access Control Lists"
-        depends on JFFS2_FS_XATTR
-        default y
-        select FS_POSIX_ACL
-        help
-          Posix Access Control Lists (ACLs) support permissions for users and
-          groups beyond the owner/group/world scheme.
-
-          To learn more about Access Control Lists, visit the Posix ACLs for
-          Linux website <http://acl.bestbits.at/>.
-
-          If you don't know what Access Control Lists are, say N
-
-config JFFS2_FS_SECURITY
-        bool "JFFS2 Security Labels"
-        depends on JFFS2_FS_XATTR
-        default y
-        help
-          Security labels support alternative access control models
-          implemented by security modules like SELinux.  This option
-          enables an extended attribute handler for file security
-          labels in the jffs2 filesystem.
-
-          If you are not using a security module that requires using
-          extended attributes for file security labels, say N.
-
-config JFFS2_COMPRESSION_OPTIONS
-        bool "Advanced compression options for JFFS2"
-        depends on JFFS2_FS
-        default n
-        help
-          Enabling this option allows you to explicitly choose which
-          compression modules, if any, are enabled in JFFS2. Removing
-          compressors can mean you cannot read existing file systems,
-          and enabling experimental compressors can mean that you
-          write a file system which cannot be read by a standard kernel.
-
-          If unsure, you should _definitely_ say 'N'.
-
-config JFFS2_ZLIB
-        bool "JFFS2 ZLIB compression support" if JFFS2_COMPRESSION_OPTIONS
-        select ZLIB_INFLATE
-        select ZLIB_DEFLATE
-        depends on JFFS2_FS
-        default y
-        help
-          Zlib is designed to be a free, general-purpose, legally unencumbered,
-          lossless data-compression library for use on virtually any computer
-          hardware and operating system. See <http://www.gzip.org/zlib/> for
-          further information.
-
-          Say 'Y' if unsure.
-
-config JFFS2_LZO
-        bool "JFFS2 LZO compression support" if JFFS2_COMPRESSION_OPTIONS
-        select LZO_COMPRESS
-        select LZO_DECOMPRESS
-        depends on JFFS2_FS
-        default n
-        help
-          minilzo-based compression. Generally works better than Zlib.
-
-          This feature was added in July, 2007. Say 'N' if you need
-          compatibility with older bootloaders or kernels.
-
-config JFFS2_RTIME
-        bool "JFFS2 RTIME compression support" if JFFS2_COMPRESSION_OPTIONS
-        depends on JFFS2_FS
-        default y
-        help
-          Rtime does manage to recompress already-compressed data. Say 'Y' if unsure.
-
-config JFFS2_RUBIN
-        bool "JFFS2 RUBIN compression support" if JFFS2_COMPRESSION_OPTIONS
-        depends on JFFS2_FS
-        default n
-        help
-          RUBINMIPS and DYNRUBIN compressors. Say 'N' if unsure.
-
-choice
-        prompt "JFFS2 default compression mode" if JFFS2_COMPRESSION_OPTIONS
-        default JFFS2_CMODE_PRIORITY
-        depends on JFFS2_FS
-        help
-          You can set here the default compression mode of JFFS2 from
-          the available compression modes. Don't touch if unsure.
-
-config JFFS2_CMODE_NONE
-        bool "no compression"
-        help
-          Uses no compression.
-
-config JFFS2_CMODE_PRIORITY
-        bool "priority"
-        help
-          Tries the compressors in a predefined order and chooses the first
-          successful one.
-
-config JFFS2_CMODE_SIZE
-        bool "size (EXPERIMENTAL)"
-        help
-          Tries all compressors and chooses the one which has the smallest
-          result.
-
-config JFFS2_CMODE_FAVOURLZO
-        bool "Favour LZO"
-        help
-          Tries all compressors and chooses the one which has the smallest
-          result but gives some preference to LZO (which has faster
-          decompression) at the expense of size.
-
-endchoice
-
+source "fs/jffs2/Kconfig"
 # UBIFS File system configuration
 source "fs/ubifs/Kconfig"
 
@@ -1765,6 +1347,28 @@ config SUNRPC_XPRT_RDMA
 
           If unsure, say N.
 
+config SUNRPC_REGISTER_V4
+        bool "Register local RPC services via rpcbind v4 (EXPERIMENTAL)"
+        depends on SUNRPC && EXPERIMENTAL
+        default n
+        help
+          Sun added support for registering RPC services at an IPv6
+          address by creating two new versions of the rpcbind protocol
+          (RFC 1833).
+
+          This option enables support in the kernel RPC server for
+          registering kernel RPC services via version 4 of the rpcbind
+          protocol.  If you enable this option, you must run a portmapper
+          daemon that supports rpcbind protocol version 4.
+
+          Serving NFS over IPv6 from knfsd (the kernel's NFS server)
+          requires that you enable this option and use a portmapper that
+          supports rpcbind version 4.
+
+          If unsure, say N to get traditional behavior (register kernel
+          RPC services using only rpcbind version 2).  Distributions
+          using the legacy Linux portmapper daemon must say N here.
+
 config RPCSEC_GSS_KRB5
         tristate "Secure RPC: Kerberos V mechanism (EXPERIMENTAL)"
         depends on SUNRPC && EXPERIMENTAL
@@ -1859,148 +1463,7 @@ config SMB_NLS_REMOTE
 
           smbmount from samba 2.2.0 or later supports this.
 
-config CIFS
-        tristate "CIFS support (advanced network filesystem, SMBFS successor)"
-        depends on INET
-        select NLS
-        help
-          This is the client VFS module for the Common Internet File System
-          (CIFS) protocol which is the successor to the Server Message Block 
-          (SMB) protocol, the native file sharing mechanism for most early
-          PC operating systems.  The CIFS protocol is fully supported by 
-          file servers such as Windows 2000 (including Windows 2003, NT 4  
-          and Windows XP) as well by Samba (which provides excellent CIFS
-          server support for Linux and many other operating systems). Limited
-          support for OS/2 and Windows ME and similar servers is provided as
-          well.
-
-          The cifs module provides an advanced network file system
-          client for mounting to CIFS compliant servers.  It includes
-          support for DFS (hierarchical name space), secure per-user
-          session establishment via Kerberos or NTLM or NTLMv2,
-          safe distributed caching (oplock), optional packet
-          signing, Unicode and other internationalization improvements.
-          If you need to mount to Samba or Windows from this machine, say Y.
-
-config CIFS_STATS
-        bool "CIFS statistics"
-        depends on CIFS
-        help
-          Enabling this option will cause statistics for each server share
-          mounted by the cifs client to be displayed in /proc/fs/cifs/Stats
-
-config CIFS_STATS2
-        bool "Extended statistics"
-        depends on CIFS_STATS
-        help
-          Enabling this option will allow more detailed statistics on SMB
-          request timing to be displayed in /proc/fs/cifs/DebugData and also
-          allow optional logging of slow responses to dmesg (depending on the
-          value of /proc/fs/cifs/cifsFYI, see fs/cifs/README for more details).
-          These additional statistics may have a minor effect on performance
-          and memory utilization.
-
-          Unless you are a developer or are doing network performance analysis
-          or tuning, say N.
-
-config CIFS_WEAK_PW_HASH
-        bool "Support legacy servers which use weaker LANMAN security"
-        depends on CIFS
-        help
-          Modern CIFS servers including Samba and most Windows versions
-          (since 1997) support stronger NTLM (and even NTLMv2 and Kerberos)
-          security mechanisms. These hash the password more securely
-          than the mechanisms used in the older LANMAN version of the
-          SMB protocol but LANMAN based authentication is needed to
-          establish sessions with some old SMB servers.
-
-          Enabling this option allows the cifs module to mount to older
-          LANMAN based servers such as OS/2 and Windows 95, but such
-          mounts may be less secure than mounts using NTLM or more recent
-          security mechanisms if you are on a public network.  Unless you
-          have a need to access old SMB servers (and are on a private
-          network) you probably want to say N.  Even if this support
-          is enabled in the kernel build, LANMAN authentication will not be
-          used automatically. At runtime LANMAN mounts are disabled but
-          can be set to required (or optional) either in
-          /proc/fs/cifs (see fs/cifs/README for more detail) or via an
-          option on the mount command. This support is disabled by
-          default in order to reduce the possibility of a downgrade
-          attack.
-
-          If unsure, say N.
-
-config CIFS_UPCALL
-          bool "Kerberos/SPNEGO advanced session setup"
-          depends on CIFS && KEYS
-          help
-            Enables an upcall mechanism for CIFS which accesses
-            userspace helper utilities to provide SPNEGO packaged (RFC 4178)
-            Kerberos tickets which are needed to mount to certain secure servers
-            (for which more secure Kerberos authentication is required). If
-            unsure, say N.
-
-config CIFS_XATTR
-        bool "CIFS extended attributes"
-        depends on CIFS
-        help
-          Extended attributes are name:value pairs associated with inodes by
-          the kernel or by users (see the attr(5) manual page, or visit
-          <http://acl.bestbits.at/> for details).  CIFS maps the name of
-          extended attributes beginning with the user namespace prefix
-          to SMB/CIFS EAs. EAs are stored on Windows servers without the
-          user namespace prefix, but their names are seen by Linux cifs clients
-          prefaced by the user namespace prefix. The system namespace
-          (used by some filesystems to store ACLs) is not supported at
-          this time.
-
-          If unsure, say N.
-
-config CIFS_POSIX
-        bool "CIFS POSIX Extensions"
-        depends on CIFS_XATTR
-        help
-          Enabling this option will cause the cifs client to attempt to
-          negotiate a newer dialect with servers, such as Samba 3.0.5
-          or later, that optionally can handle more POSIX like (rather
-          than Windows like) file behavior.  It also enables
-          support for POSIX ACLs (getfacl and setfacl) to servers
-          (such as Samba 3.10 and later) which can negotiate
-          CIFS POSIX ACL support.  If unsure, say N.
-
-config CIFS_DEBUG2
-        bool "Enable additional CIFS debugging routines"
-        depends on CIFS
-        help
-           Enabling this option adds a few more debugging routines
-           to the cifs code which slightly increases the size of
-           the cifs module and can cause additional logging of debug
-           messages in some error paths, slowing performance. This
-           option can be turned off unless you are debugging
-           cifs problems.  If unsure, say N.
-
-config CIFS_EXPERIMENTAL
-          bool "CIFS Experimental Features (EXPERIMENTAL)"
-          depends on CIFS && EXPERIMENTAL
-          help
-            Enables cifs features under testing. These features are
-            experimental and currently include DFS support and directory 
-            change notification ie fcntl(F_DNOTIFY), as well as the upcall
-            mechanism which will be used for Kerberos session negotiation
-            and uid remapping.  Some of these features also may depend on 
-            setting a value of 1 to the pseudo-file /proc/fs/cifs/Experimental
-            (which is disabled by default). See the file fs/cifs/README 
-            for more details.  If unsure, say N.
-
-config CIFS_DFS_UPCALL
-          bool "DFS feature support (EXPERIMENTAL)"
-          depends on CIFS_EXPERIMENTAL
-          depends on KEYS
-          help
-            Enables an upcall mechanism for CIFS which contacts userspace
-            helper utilities to provide server name resolution (host names to
-            IP addresses) which is needed for implicit mounts of DFS junction
-            points. If unsure, say N.
+source "fs/cifs/Kconfig"
 
 config NCP_FS
         tristate "NCP file system support (to mount NetWare volumes)"
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt
index 4a551af6f3fc..ce9fb3fbfae4 100644
--- a/fs/Kconfig.binfmt
+++ b/fs/Kconfig.binfmt
@@ -25,7 +25,7 @@ config BINFMT_ELF
 
 config COMPAT_BINFMT_ELF
         bool
-        depends on COMPAT && MMU
+        depends on COMPAT && BINFMT_ELF
 
 config BINFMT_ELF_FDPIC
         bool "Kernel support for FDPIC ELF binaries"
@@ -40,6 +40,28 @@ config BINFMT_ELF_FDPIC
 
           It is also possible to run FDPIC ELF binaries on MMU linux also.
 
+config CORE_DUMP_DEFAULT_ELF_HEADERS
+        bool "Write ELF core dumps with partial segments"
+        default n
+        depends on BINFMT_ELF
+        help
+          ELF core dump files describe each memory mapping of the crashed
+          process, and can contain or omit the memory contents of each one.
+          The contents of an unmodified text mapping are omitted by default.
+
+          For an unmodified text mapping of an ELF object, including just
+          the first page of the file in a core dump makes it possible to
+          identify the build ID bits in the file, without paying the i/o
+          cost and disk space to dump all the text.  However, versions of
+          GDB before 6.7 are confused by ELF core dump files in this format.
+
+          The core dump behavior can be controlled per process using
+          the /proc/PID/coredump_filter pseudo-file; this setting is
+          inherited.  See Documentation/filesystems/proc.txt for details.
+
+          This config option changes the default setting of coredump_filter
+          seen at boot time.  If unsure, say N.
+
 config BINFMT_FLAT
         bool "Kernel support for flat binaries"
         depends on !MMU && (!FRV || BROKEN)
@@ -59,10 +81,12 @@ config BINFMT_SHARED_FLAT
         help
           Support FLAT shared libraries
 
+config HAVE_AOUT
+       def_bool n
+
 config BINFMT_AOUT
         tristate "Kernel support for a.out and ECOFF binaries"
-        depends on ARCH_SUPPORTS_AOUT && \
-                (X86_32 || ALPHA || ARM || M68K)
+        depends on HAVE_AOUT
         ---help---
           A.out (Assembler.OUTput) is a set of formats for libraries and
           executables used in the earliest versions of UNIX.  Linux used
diff --git a/fs/Makefile b/fs/Makefile
index a1482a5eff15..2168c902d5ca 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -7,8 +7,8 @@
 
 obj-y :=        open.o read_write.o file_table.o super.o \
                 char_dev.o stat.o exec.o pipe.o namei.o fcntl.o \
-                ioctl.o readdir.o select.o fifo.o locks.o dcache.o inode.o \
-                attr.o bad_inode.o file.o filesystems.o namespace.o aio.o \
+                ioctl.o readdir.o select.o fifo.o dcache.o inode.o \
+                attr.o bad_inode.o file.o filesystems.o namespace.o \
                 seq_file.o xattr.o libfs.o fs-writeback.o \
                 pnode.o drop_caches.o splice.o sync.o utimes.o \
                 stack.o
@@ -27,6 +27,8 @@ obj-$(CONFIG_ANON_INODES)	+= anon_inodes.o
 obj-$(CONFIG_SIGNALFD)          += signalfd.o
 obj-$(CONFIG_TIMERFD)           += timerfd.o
 obj-$(CONFIG_EVENTFD)           += eventfd.o
+obj-$(CONFIG_AIO)               += aio.o
+obj-$(CONFIG_FILE_LOCKING)      += locks.o
 obj-$(CONFIG_COMPAT)            += compat.o compat_ioctl.o
 
 nfsd-$(CONFIG_NFSD)             := nfsctl.o
@@ -69,7 +71,7 @@ obj-$(CONFIG_DLM)		+= dlm/
 # Do not add any filesystems before this line
 obj-$(CONFIG_REISERFS_FS)       += reiserfs/
 obj-$(CONFIG_EXT3_FS)           += ext3/ # Before ext2 so root fs can be ext3
-obj-$(CONFIG_EXT4DEV_FS)        += ext4/ # Before ext2 so root fs can be ext4dev
+obj-$(CONFIG_EXT4_FS)           += ext4/ # Before ext2 so root fs can be ext4
 obj-$(CONFIG_JBD)               += jbd/
 obj-$(CONFIG_JBD2)              += jbd2/
 obj-$(CONFIG_EXT2_FS)           += ext2/
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index 26f3b43726bb..7f83a46f2b7e 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -157,7 +157,7 @@ static int adfs_show_options(struct seq_file *seq, struct vfsmount *mnt)
 
 enum {Opt_uid, Opt_gid, Opt_ownmask, Opt_othmask, Opt_err};
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         {Opt_uid, "uid=%u"},
         {Opt_gid, "gid=%u"},
         {Opt_ownmask, "ownmask=%o"},
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 3a89094f93d0..8989c93193ed 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -135,7 +135,7 @@ enum {
         Opt_verbose, Opt_volume, Opt_ignore, Opt_err,
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         {Opt_bs, "bs=%u"},
         {Opt_mode, "mode=%o"},
         {Opt_mufs, "mufs"},
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 525f7c56e068..a3901769a96c 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -50,8 +50,8 @@ const struct address_space_operations afs_fs_aops = {
         .launder_page   = afs_launder_page,
         .releasepage    = afs_releasepage,
         .invalidatepage = afs_invalidatepage,
-        .prepare_write  = afs_prepare_write,
-        .commit_write   = afs_commit_write,
+        .write_begin    = afs_write_begin,
+        .write_end      = afs_write_end,
         .writepage      = afs_writepage,
         .writepages     = afs_writepages,
 };
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 3cb6920ff30b..67f259d99cd6 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -728,8 +728,12 @@ extern int afs_volume_release_fileserver(struct afs_vnode *,
  */
 extern int afs_set_page_dirty(struct page *);
 extern void afs_put_writeback(struct afs_writeback *);
-extern int afs_prepare_write(struct file *, struct page *, unsigned, unsigned);
-extern int afs_commit_write(struct file *, struct page *, unsigned, unsigned);
+extern int afs_write_begin(struct file *file, struct address_space *mapping,
+                        loff_t pos, unsigned len, unsigned flags,
+                        struct page **pagep, void **fsdata);
+extern int afs_write_end(struct file *file, struct address_space *mapping,
+                        loff_t pos, unsigned len, unsigned copied,
+                        struct page *page, void *fsdata);
 extern int afs_writepage(struct page *, struct writeback_control *);
 extern int afs_writepages(struct address_space *, struct writeback_control *);
 extern int afs_write_inode(struct inode *, int);
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 250d8c4d66e4..aee239a048cb 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -64,7 +64,7 @@ enum {
         afs_opt_vol,
 };
 
-static match_table_t afs_options_list = {
+static const match_table_t afs_options_list = {
         { afs_opt_cell,         "cell=%s"       },
         { afs_opt_rwpath,       "rwpath"        },
         { afs_opt_vol,          "vol=%s"        },
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 065b4e10681a..d6b85dab35fc 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -84,15 +84,23 @@ void afs_put_writeback(struct afs_writeback *wb)
  * partly or wholly fill a page that's under preparation for writing
  */
 static int afs_fill_page(struct afs_vnode *vnode, struct key *key,
-                         unsigned start, unsigned len, struct page *page)
+                         loff_t pos, unsigned len, struct page *page)
 {
+        loff_t i_size;
+        unsigned eof;
         int ret;
 
-        _enter(",,%u,%u", start, len);
+        _enter(",,%llu,%u", (unsigned long long)pos, len);
 
-        ASSERTCMP(start + len, <=, PAGE_SIZE);
+        ASSERTCMP(len, <=, PAGE_CACHE_SIZE);
 
-        ret = afs_vnode_fetch_data(vnode, key, start, len, page);
+        i_size = i_size_read(&vnode->vfs_inode);
+        if (pos + len > i_size)
+                eof = i_size;
+        else
+                eof = PAGE_CACHE_SIZE;
+
+        ret = afs_vnode_fetch_data(vnode, key, 0, eof, page);
         if (ret < 0) {
                 if (ret == -ENOENT) {
                         _debug("got NOENT from server"
@@ -107,109 +115,55 @@ static int afs_fill_page(struct afs_vnode *vnode, struct key *key,
 }
 
 /*
- * prepare a page for being written to
- */
-static int afs_prepare_page(struct afs_vnode *vnode, struct page *page,
-                            struct key *key, unsigned offset, unsigned to)
-{
-        unsigned eof, tail, start, stop, len;
-        loff_t i_size, pos;
-        void *p;
-        int ret;
-
-        _enter("");
-
-        if (offset == 0 && to == PAGE_SIZE)
-                return 0;
-
-        p = kmap_atomic(page, KM_USER0);
-
-        i_size = i_size_read(&vnode->vfs_inode);
-        pos = (loff_t) page->index << PAGE_SHIFT;
-        if (pos >= i_size) {
-                /* partial write, page beyond EOF */
-                _debug("beyond");
-                if (offset > 0)
-                        memset(p, 0, offset);
-                if (to < PAGE_SIZE)
-                        memset(p + to, 0, PAGE_SIZE - to);
-                kunmap_atomic(p, KM_USER0);
-                return 0;
-        }
-
-        if (i_size - pos >= PAGE_SIZE) {
-                /* partial write, page entirely before EOF */
-                _debug("before");
-                tail = eof = PAGE_SIZE;
-        } else {
-                /* partial write, page overlaps EOF */
-                eof = i_size - pos;
-                _debug("overlap %u", eof);
-                tail = max(eof, to);
-                if (tail < PAGE_SIZE)
-                        memset(p + tail, 0, PAGE_SIZE - tail);
-                if (offset > eof)
-                        memset(p + eof, 0, PAGE_SIZE - eof);
-        }
-
-        kunmap_atomic(p, KM_USER0);
-
-        ret = 0;
-        if (offset > 0 || eof > to) {
-                /* need to fill one or two bits that aren't going to be written
-                 * (cover both fillers in one read if there are two) */
-                start = (offset > 0) ? 0 : to;
-                stop = (eof > to) ? eof : offset;
-                len = stop - start;
-                _debug("wr=%u-%u av=0-%u rd=%u@%u",
-                       offset, to, eof, start, len);
-                ret = afs_fill_page(vnode, key, start, len, page);
-        }
-
-        _leave(" = %d", ret);
-        return ret;
-}
-
-/*
  * prepare to perform part of a write to a page
- * - the caller holds the page locked, preventing it from being written out or
- *   modified by anyone else
  */
-int afs_prepare_write(struct file *file, struct page *page,
-                      unsigned offset, unsigned to)
+int afs_write_begin(struct file *file, struct address_space *mapping,
+                    loff_t pos, unsigned len, unsigned flags,
+                    struct page **pagep, void **fsdata)
 {
         struct afs_writeback *candidate, *wb;
         struct afs_vnode *vnode = AFS_FS_I(file->f_dentry->d_inode);
+        struct page *page;
         struct key *key = file->private_data;
-        pgoff_t index;
+        unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+        unsigned to = from + len;
+        pgoff_t index = pos >> PAGE_CACHE_SHIFT;
         int ret;
 
         _enter("{%x:%u},{%lx},%u,%u",
-               vnode->fid.vid, vnode->fid.vnode, page->index, offset, to);
+               vnode->fid.vid, vnode->fid.vnode, index, from, to);
 
         candidate = kzalloc(sizeof(*candidate), GFP_KERNEL);
         if (!candidate)
                 return -ENOMEM;
         candidate->vnode = vnode;
-        candidate->first = candidate->last = page->index;
-        candidate->offset_first = offset;
+        candidate->first = candidate->last = index;
+        candidate->offset_first = from;
         candidate->to_last = to;
         candidate->usage = 1;
         candidate->state = AFS_WBACK_PENDING;
         init_waitqueue_head(&candidate->waitq);
 
+        page = __grab_cache_page(mapping, index);
+        if (!page) {
+                kfree(candidate);
+                return -ENOMEM;
+        }
+        *pagep = page;
+        /* page won't leak in error case: it eventually gets cleaned off LRU */
+
         if (!PageUptodate(page)) {
                 _debug("not up to date");
-                ret = afs_prepare_page(vnode, page, key, offset, to);
+                ret = afs_fill_page(vnode, key, pos, len, page);
                 if (ret < 0) {
                         kfree(candidate);
                         _leave(" = %d [prep]", ret);
                         return ret;
                 }
+                SetPageUptodate(page);
         }
 
 try_again:
-        index = page->index;
         spin_lock(&vnode->writeback_lock);
 
         /* see if this page is already pending a writeback under a suitable key
@@ -242,8 +196,8 @@ try_again:
 subsume_in_current_wb:
         _debug("subsume");
         ASSERTRANGE(wb->first, <=, index, <=, wb->last);
-        if (index == wb->first && offset < wb->offset_first)
-                wb->offset_first = offset;
+        if (index == wb->first && from < wb->offset_first)
+                wb->offset_first = from;
         if (index == wb->last && to > wb->to_last)
                 wb->to_last = to;
         spin_unlock(&vnode->writeback_lock);
@@ -289,17 +243,17 @@ flush_conflicting_wb:
 /*
  * finalise part of a write to a page
  */
-int afs_commit_write(struct file *file, struct page *page,
-                     unsigned offset, unsigned to)
+int afs_write_end(struct file *file, struct address_space *mapping,
+                  loff_t pos, unsigned len, unsigned copied,
+                  struct page *page, void *fsdata)
 {
         struct afs_vnode *vnode = AFS_FS_I(file->f_dentry->d_inode);
         loff_t i_size, maybe_i_size;
 
-        _enter("{%x:%u},{%lx},%u,%u",
-               vnode->fid.vid, vnode->fid.vnode, page->index, offset, to);
+        _enter("{%x:%u},{%lx}",
+               vnode->fid.vid, vnode->fid.vnode, page->index);
 
-        maybe_i_size = (loff_t) page->index << PAGE_SHIFT;
-        maybe_i_size += to;
+        maybe_i_size = pos + copied;
 
         i_size = i_size_read(&vnode->vfs_inode);
         if (maybe_i_size > i_size) {
@@ -310,12 +264,13 @@ int afs_commit_write(struct file *file, struct page *page,
                 spin_unlock(&vnode->writeback_lock);
         }
 
-        SetPageUptodate(page);
         set_page_dirty(page);
         if (PageDirty(page))
                 _debug("dirtied");
+        unlock_page(page);
+        page_cache_release(page);
 
-        return 0;
+        return copied;
 }
 
 /*
diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c
index dda510d31f84..b70eea1e8c59 100644
--- a/fs/autofs/inode.c
+++ b/fs/autofs/inode.c
@@ -59,7 +59,7 @@ static const struct super_operations autofs_sops = {
 
 enum {Opt_err, Opt_fd, Opt_uid, Opt_gid, Opt_pgrp, Opt_minproto, Opt_maxproto};
 
-static match_table_t autofs_tokens = {
+static const match_table_t autofs_tokens = {
         {Opt_fd, "fd=%u"},
         {Opt_uid, "uid=%u"},
         {Opt_gid, "gid=%u"},
diff --git a/fs/autofs4/Makefile b/fs/autofs4/Makefile
index f2c3b79e94d2..a811c1f7d9ab 100644
--- a/fs/autofs4/Makefile
+++ b/fs/autofs4/Makefile
@@ -4,4 +4,4 @@
 
 obj-$(CONFIG_AUTOFS4_FS) += autofs4.o
 
-autofs4-objs := init.o inode.o root.o symlink.o waitq.o expire.o
+autofs4-objs := init.o inode.o root.o symlink.o waitq.o expire.o dev-ioctl.o
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index 69a2f5c92319..e0f16da00e54 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -14,6 +14,7 @@
 /* Internal header file for autofs */
 
 #include <linux/auto_fs4.h>
+#include <linux/auto_dev-ioctl.h>
 #include <linux/mutex.h>
 #include <linux/list.h>
 
@@ -21,6 +22,11 @@
 #define AUTOFS_IOC_FIRST     AUTOFS_IOC_READY
 #define AUTOFS_IOC_COUNT     32
 
+#define AUTOFS_DEV_IOCTL_IOC_FIRST      (AUTOFS_DEV_IOCTL_VERSION)
+#define AUTOFS_DEV_IOCTL_IOC_COUNT      (AUTOFS_IOC_COUNT - 11)
+
+#define AUTOFS_TYPE_TRIGGER     (AUTOFS_TYPE_DIRECT|AUTOFS_TYPE_OFFSET)
+
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/time.h>
@@ -35,11 +41,27 @@
 /* #define DEBUG */
 
 #ifdef DEBUG
-#define DPRINTK(fmt,args...) do { printk(KERN_DEBUG "pid %d: %s: " fmt "\n" , current->pid , __func__ , ##args); } while(0)
+#define DPRINTK(fmt, args...)                           \
+do {                                                    \
+        printk(KERN_DEBUG "pid %d: %s: " fmt "\n",      \
+                current->pid, __func__, ##args);        \
+} while (0)
 #else
-#define DPRINTK(fmt,args...) do {} while(0)
+#define DPRINTK(fmt, args...) do {} while (0)
 #endif
 
+#define AUTOFS_WARN(fmt, args...)                       \
+do {                                                    \
+        printk(KERN_WARNING "pid %d: %s: " fmt "\n",    \
+                current->pid, __func__, ##args);        \
+} while (0)
+
+#define AUTOFS_ERROR(fmt, args...)                      \
+do {                                                    \
+        printk(KERN_ERR "pid %d: %s: " fmt "\n",        \
+                current->pid, __func__, ##args);        \
+} while (0)
+
 /* 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
@@ -61,6 +83,9 @@ struct autofs_info {
         unsigned long last_used;
         atomic_t count;
 
+        uid_t uid;
+        gid_t gid;
+
         mode_t  mode;
         size_t  size;
 
@@ -92,10 +117,6 @@ struct autofs_wait_queue {
 
 #define AUTOFS_SBI_MAGIC 0x6d4a556d
 
-#define AUTOFS_TYPE_INDIRECT     0x0001
-#define AUTOFS_TYPE_DIRECT       0x0002
-#define AUTOFS_TYPE_OFFSET       0x0004
-
 struct autofs_sb_info {
         u32 magic;
         int pipefd;
@@ -169,6 +190,17 @@ int autofs4_expire_run(struct super_block *, struct vfsmount *,
                         struct autofs_packet_expire __user *);
 int autofs4_expire_multi(struct super_block *, struct vfsmount *,
                         struct autofs_sb_info *, int __user *);
+struct dentry *autofs4_expire_direct(struct super_block *sb,
+                                     struct vfsmount *mnt,
+                                     struct autofs_sb_info *sbi, int how);
+struct dentry *autofs4_expire_indirect(struct super_block *sb,
+                                       struct vfsmount *mnt,
+                                       struct autofs_sb_info *sbi, int how);
+
+/* Device node initialization */
+
+int autofs_dev_ioctl_init(void);
+void autofs_dev_ioctl_exit(void);
 
 /* Operations structures */
 
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
new file mode 100644
index 000000000000..625abf5422e2
--- /dev/null
+++ b/fs/autofs4/dev-ioctl.c
@@ -0,0 +1,863 @@
+/*
+ * Copyright 2008 Red Hat, Inc. All rights reserved.
+ * Copyright 2008 Ian Kent <raven@themaw.net>
+ *
+ * This file is part of the Linux kernel and is made available under
+ * the terms of the GNU General Public License, version 2, or at your
+ * option, any later version, incorporated herein by reference.
+ */
+
+#include <linux/module.h>
+#include <linux/vmalloc.h>
+#include <linux/miscdevice.h>
+#include <linux/init.h>
+#include <linux/wait.h>
+#include <linux/namei.h>
+#include <linux/fcntl.h>
+#include <linux/file.h>
+#include <linux/fdtable.h>
+#include <linux/sched.h>
+#include <linux/compat.h>
+#include <linux/syscalls.h>
+#include <linux/smp_lock.h>
+#include <linux/magic.h>
+#include <linux/dcache.h>
+#include <linux/uaccess.h>
+
+#include "autofs_i.h"
+
+/*
+ * This module implements an interface for routing autofs ioctl control
+ * commands via a miscellaneous device file.
+ *
+ * The alternate interface is needed because we need to be able open
+ * an ioctl file descriptor on an autofs mount that may be covered by
+ * another mount. This situation arises when starting automount(8)
+ * or other user space daemon which uses direct mounts or offset
+ * mounts (used for autofs lazy mount/umount of nested mount trees),
+ * which have been left busy at at service shutdown.
+ */
+
+#define AUTOFS_DEV_IOCTL_SIZE   sizeof(struct autofs_dev_ioctl)
+
+typedef int (*ioctl_fn)(struct file *, struct autofs_sb_info *,
+                        struct autofs_dev_ioctl *);
+
+static int check_name(const char *name)
+{
+        if (!strchr(name, '/'))
+                return -EINVAL;
+        return 0;
+}
+
+/*
+ * Check a string doesn't overrun the chunk of
+ * memory we copied from user land.
+ */
+static int invalid_str(char *str, void *end)
+{
+        while ((void *) str <= end)
+                if (!*str++)
+                        return 0;
+        return -EINVAL;
+}
+
+/*
+ * Check that the user compiled against correct version of autofs
+ * misc device code.
+ *
+ * As well as checking the version compatibility this always copies
+ * the kernel interface version out.
+ */
+static int check_dev_ioctl_version(int cmd, struct autofs_dev_ioctl *param)
+{
+        int err = 0;
+
+        if ((AUTOFS_DEV_IOCTL_VERSION_MAJOR != param->ver_major) ||
+            (AUTOFS_DEV_IOCTL_VERSION_MINOR < param->ver_minor)) {
+                AUTOFS_WARN("ioctl control interface version mismatch: "
+                     "kernel(%u.%u), user(%u.%u), cmd(%d)",
+                     AUTOFS_DEV_IOCTL_VERSION_MAJOR,
+                     AUTOFS_DEV_IOCTL_VERSION_MINOR,
+                     param->ver_major, param->ver_minor, cmd);
+                err = -EINVAL;
+        }
+
+        /* Fill in the kernel version. */
+        param->ver_major = AUTOFS_DEV_IOCTL_VERSION_MAJOR;
+        param->ver_minor = AUTOFS_DEV_IOCTL_VERSION_MINOR;
+
+        return err;
+}
+
+/*
+ * Copy parameter control struct, including a possible path allocated
+ * at the end of the struct.
+ */
+static struct autofs_dev_ioctl *copy_dev_ioctl(struct autofs_dev_ioctl __user *in)
+{
+        struct autofs_dev_ioctl tmp, *ads;
+
+        if (copy_from_user(&tmp, in, sizeof(tmp)))
+                return ERR_PTR(-EFAULT);
+
+        if (tmp.size < sizeof(tmp))
+                return ERR_PTR(-EINVAL);
+
+        ads = kmalloc(tmp.size, GFP_KERNEL);
+        if (!ads)
+                return ERR_PTR(-ENOMEM);
+
+        if (copy_from_user(ads, in, tmp.size)) {
+                kfree(ads);
+                return ERR_PTR(-EFAULT);
+        }
+
+        return ads;
+}
+
+static inline void free_dev_ioctl(struct autofs_dev_ioctl *param)
+{
+        kfree(param);
+        return;
+}
+
+/*
+ * Check sanity of parameter control fields and if a path is present
+ * check that it has a "/" and is terminated.
+ */
+static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param)
+{
+        int err = -EINVAL;
+
+        if (check_dev_ioctl_version(cmd, param)) {
+                AUTOFS_WARN("invalid device control module version "
+                     "supplied for cmd(0x%08x)", cmd);
+                goto out;
+        }
+
+        if (param->size > sizeof(*param)) {
+                err = check_name(param->path);
+                if (err) {
+                        AUTOFS_WARN("invalid path supplied for cmd(0x%08x)",
+                                    cmd);
+                        goto out;
+                }
+
+                err = invalid_str(param->path,
+                                 (void *) ((size_t) param + param->size));
+                if (err) {
+                        AUTOFS_WARN("invalid path supplied for cmd(0x%08x)",
+                                    cmd);
+                        goto out;
+                }
+        }
+
+        err = 0;
+out:
+        return err;
+}
+
+/*
+ * Get the autofs super block info struct from the file opened on
+ * the autofs mount point.
+ */
+static struct autofs_sb_info *autofs_dev_ioctl_sbi(struct file *f)
+{
+        struct autofs_sb_info *sbi = NULL;
+        struct inode *inode;
+
+        if (f) {
+                inode = f->f_path.dentry->d_inode;
+                sbi = autofs4_sbi(inode->i_sb);
+        }
+        return sbi;
+}
+
+/* Return autofs module protocol version */
+static int autofs_dev_ioctl_protover(struct file *fp,
+                                     struct autofs_sb_info *sbi,
+                                     struct autofs_dev_ioctl *param)
+{
+        param->arg1 = sbi->version;
+        return 0;
+}
+
+/* Return autofs module protocol sub version */
+static int autofs_dev_ioctl_protosubver(struct file *fp,
+                                        struct autofs_sb_info *sbi,
+                                        struct autofs_dev_ioctl *param)
+{
+        param->arg1 = sbi->sub_version;
+        return 0;
+}
+
+/*
+ * Walk down the mount stack looking for an autofs mount that
+ * has the requested device number (aka. new_encode_dev(sb->s_dev).
+ */
+static int autofs_dev_ioctl_find_super(struct nameidata *nd, dev_t devno)
+{
+        struct dentry *dentry;
+        struct inode *inode;
+        struct super_block *sb;
+        dev_t s_dev;
+        unsigned int err;
+
+        err = -ENOENT;
+
+        /* Lookup the dentry name at the base of our mount point */
+        dentry = d_lookup(nd->path.dentry, &nd->last);
+        if (!dentry)
+                goto out;
+
+        dput(nd->path.dentry);
+        nd->path.dentry = dentry;
+
+        /* And follow the mount stack looking for our autofs mount */
+        while (follow_down(&nd->path.mnt, &nd->path.dentry)) {
+                inode = nd->path.dentry->d_inode;
+                if (!inode)
+                        break;
+
+                sb = inode->i_sb;
+                s_dev = new_encode_dev(sb->s_dev);
+                if (devno == s_dev) {
+                        if (sb->s_magic == AUTOFS_SUPER_MAGIC) {
+                                err = 0;
+                                break;
+                        }
+                }
+        }
+out:
+        return err;
+}
+
+/*
+ * Walk down the mount stack looking for an autofs mount that
+ * has the requested mount type (ie. indirect, direct or offset).
+ */
+static int autofs_dev_ioctl_find_sbi_type(struct nameidata *nd, unsigned int type)
+{
+        struct dentry *dentry;
+        struct autofs_info *ino;
+        unsigned int err;
+
+        err = -ENOENT;
+
+        /* Lookup the dentry name at the base of our mount point */
+        dentry = d_lookup(nd->path.dentry, &nd->last);
+        if (!dentry)
+                goto out;
+
+        dput(nd->path.dentry);
+        nd->path.dentry = dentry;
+
+        /* And follow the mount stack looking for our autofs mount */
+        while (follow_down(&nd->path.mnt, &nd->path.dentry)) {
+                ino = autofs4_dentry_ino(nd->path.dentry);
+                if (ino && ino->sbi->type & type) {
+                        err = 0;
+                        break;
+                }
+        }
+out:
+        return err;
+}
+
+static void autofs_dev_ioctl_fd_install(unsigned int fd, struct file *file)
+{
+        struct files_struct *files = current->files;
+        struct fdtable *fdt;
+
+        spin_lock(&files->file_lock);
+        fdt = files_fdtable(files);
+        BUG_ON(fdt->fd[fd] != NULL);
+        rcu_assign_pointer(fdt->fd[fd], file);
+        FD_SET(fd, fdt->close_on_exec);
+        spin_unlock(&files->file_lock);
+}
+
+
+/*
+ * Open a file descriptor on the autofs mount point corresponding
+ * to the given path and device number (aka. new_encode_dev(sb->s_dev)).
+ */
+static int autofs_dev_ioctl_open_mountpoint(const char *path, dev_t devid)
+{
+        struct file *filp;
+        struct nameidata nd;
+        int err, fd;
+
+        fd = get_unused_fd();
+        if (likely(fd >= 0)) {
+                /* Get nameidata of the parent directory */
+                err = path_lookup(path, LOOKUP_PARENT, &nd);
+                if (err)
+                        goto out;
+
+                /*
+                 * Search down, within the parent, looking for an
+                 * autofs super block that has the device number
+                 * corresponding to the autofs fs we want to open.
+                 */
+                err = autofs_dev_ioctl_find_super(&nd, devid);
+                if (err) {
+                        path_put(&nd.path);
+                        goto out;
+                }
+
+                filp = dentry_open(nd.path.dentry, nd.path.mnt, O_RDONLY);
+                if (IS_ERR(filp)) {
+                        err = PTR_ERR(filp);
+                        goto out;
+                }
+
+                autofs_dev_ioctl_fd_install(fd, filp);
+        }
+
+        return fd;
+
+out:
+        put_unused_fd(fd);
+        return err;
+}
+
+/* Open a file descriptor on an autofs mount point */
+static int autofs_dev_ioctl_openmount(struct file *fp,
+                                      struct autofs_sb_info *sbi,
+                                      struct autofs_dev_ioctl *param)
+{
+        const char *path;
+        dev_t devid;
+        int err, fd;
+
+        /* param->path has already been checked */
+        if (!param->arg1)
+                return -EINVAL;
+
+        param->ioctlfd = -1;
+
+        path = param->path;
+        devid = param->arg1;
+
+        err = 0;
+        fd = autofs_dev_ioctl_open_mountpoint(path, devid);
+        if (unlikely(fd < 0)) {
+                err = fd;
+                goto out;
+        }
+
+        param->ioctlfd = fd;
+out:
+        return err;
+}
+
+/* Close file descriptor allocated above (user can also use close(2)). */
+static int autofs_dev_ioctl_closemount(struct file *fp,
+                                       struct autofs_sb_info *sbi,
+                                       struct autofs_dev_ioctl *param)
+{
+        return sys_close(param->ioctlfd);
+}
+
+/*
+ * Send "ready" status for an existing wait (either a mount or an expire
+ * request).
+ */
+static int autofs_dev_ioctl_ready(struct file *fp,
+                                  struct autofs_sb_info *sbi,
+                                  struct autofs_dev_ioctl *param)
+{
+        autofs_wqt_t token;
+
+        token = (autofs_wqt_t) param->arg1;
+        return autofs4_wait_release(sbi, token, 0);
+}
+
+/*
+ * Send "fail" status for an existing wait (either a mount or an expire
+ * request).
+ */
+static int autofs_dev_ioctl_fail(struct file *fp,
+                                 struct autofs_sb_info *sbi,
+                                 struct autofs_dev_ioctl *param)
+{
+        autofs_wqt_t token;
+        int status;
+
+        token = (autofs_wqt_t) param->arg1;
+        status = param->arg2 ? param->arg2 : -ENOENT;
+        return autofs4_wait_release(sbi, token, status);
+}
+
+/*
+ * Set the pipe fd for kernel communication to the daemon.
+ *
+ * Normally this is set at mount using an option but if we
+ * are reconnecting to a busy mount then we need to use this
+ * to tell the autofs mount about the new kernel pipe fd. In
+ * order to protect mounts against incorrectly setting the
+ * pipefd we also require that the autofs mount be catatonic.
+ *
+ * This also sets the process group id used to identify the
+ * controlling process (eg. the owning automount(8) daemon).
+ */
+static int autofs_dev_ioctl_setpipefd(struct file *fp,
+                                      struct autofs_sb_info *sbi,
+                                      struct autofs_dev_ioctl *param)
+{
+        int pipefd;
+        int err = 0;
+
+        if (param->arg1 == -1)
+                return -EINVAL;
+
+        pipefd = param->arg1;
+
+        mutex_lock(&sbi->wq_mutex);
+        if (!sbi->catatonic) {
+                mutex_unlock(&sbi->wq_mutex);
+                return -EBUSY;
+        } else {
+                struct file *pipe = fget(pipefd);
+                if (!pipe->f_op || !pipe->f_op->write) {
+                        err = -EPIPE;
+                        fput(pipe);
+                        goto out;
+                }
+                sbi->oz_pgrp = task_pgrp_nr(current);
+                sbi->pipefd = pipefd;
+                sbi->pipe = pipe;
+                sbi->catatonic = 0;
+        }
+out:
+        mutex_unlock(&sbi->wq_mutex);
+        return err;
+}
+
+/*
+ * Make the autofs mount point catatonic, no longer responsive to
+ * mount requests. Also closes the kernel pipe file descriptor.
+ */
+static int autofs_dev_ioctl_catatonic(struct file *fp,
+                                      struct autofs_sb_info *sbi,
+                                      struct autofs_dev_ioctl *param)
+{
+        autofs4_catatonic_mode(sbi);
+        return 0;
+}
+
+/* Set the autofs mount timeout */
+static int autofs_dev_ioctl_timeout(struct file *fp,
+                                    struct autofs_sb_info *sbi,
+                                    struct autofs_dev_ioctl *param)
+{
+        unsigned long timeout;
+
+        timeout = param->arg1;
+        param->arg1 = sbi->exp_timeout / HZ;
+        sbi->exp_timeout = timeout * HZ;
+        return 0;
+}
+
+/*
+ * Return the uid and gid of the last request for the mount
+ *
+ * When reconstructing an autofs mount tree with active mounts
+ * we need to re-connect to mounts that may have used the original
+ * process uid and gid (or string variations of them) for mount
+ * lookups within the map entry.
+ */
+static int autofs_dev_ioctl_requester(struct file *fp,
+                                      struct autofs_sb_info *sbi,
+                                      struct autofs_dev_ioctl *param)
+{
+        struct autofs_info *ino;
+        struct nameidata nd;
+        const char *path;
+        dev_t devid;
+        int err = -ENOENT;
+
+        if (param->size <= sizeof(*param)) {
+                err = -EINVAL;
+                goto out;
+        }
+
+        path = param->path;
+        devid = sbi->sb->s_dev;
+
+        param->arg1 = param->arg2 = -1;
+
+        /* Get nameidata of the parent directory */
+        err = path_lookup(path, LOOKUP_PARENT, &nd);
+        if (err)
+                goto out;
+
+        err = autofs_dev_ioctl_find_super(&nd, devid);
+        if (err)
+                goto out_release;
+
+        ino = autofs4_dentry_ino(nd.path.dentry);
+        if (ino) {
+                err = 0;
+                autofs4_expire_wait(nd.path.dentry);
+                spin_lock(&sbi->fs_lock);
+                param->arg1 = ino->uid;
+                param->arg2 = ino->gid;
+                spin_unlock(&sbi->fs_lock);
+        }
+
+out_release:
+        path_put(&nd.path);
+out:
+        return err;
+}
+
+/*
+ * Call repeatedly until it returns -EAGAIN, meaning there's nothing
+ * more that can be done.
+ */
+static int autofs_dev_ioctl_expire(struct file *fp,
+                                   struct autofs_sb_info *sbi,
+                                   struct autofs_dev_ioctl *param)
+{
+        struct dentry *dentry;
+        struct vfsmount *mnt;
+        int err = -EAGAIN;
+        int how;
+
+        how = param->arg1;
+        mnt = fp->f_path.mnt;
+
+        if (sbi->type & AUTOFS_TYPE_TRIGGER)
+                dentry = autofs4_expire_direct(sbi->sb, mnt, sbi, how);
+        else
+                dentry = autofs4_expire_indirect(sbi->sb, mnt, sbi, how);
+
+        if (dentry) {
+                struct autofs_info *ino = autofs4_dentry_ino(dentry);
+
+                /*
+                 * This is synchronous because it makes the daemon a
+                 * little easier
+                */
+                err = autofs4_wait(sbi, dentry, NFY_EXPIRE);
+
+                spin_lock(&sbi->fs_lock);
+                if (ino->flags & AUTOFS_INF_MOUNTPOINT) {
+                        ino->flags &= ~AUTOFS_INF_MOUNTPOINT;
+                        sbi->sb->s_root->d_mounted++;
+                }
+                ino->flags &= ~AUTOFS_INF_EXPIRING;
+                complete_all(&ino->expire_complete);
+                spin_unlock(&sbi->fs_lock);
+                dput(dentry);
+        }
+
+        return err;
+}
+
+/* Check if autofs mount point is in use */
+static int autofs_dev_ioctl_askumount(struct file *fp,
+                                      struct autofs_sb_info *sbi,
+                                      struct autofs_dev_ioctl *param)
+{
+        param->arg1 = 0;
+        if (may_umount(fp->f_path.mnt))
+                param->arg1 = 1;
+        return 0;
+}
+
+/*
+ * Check if the given path is a mountpoint.
+ *
+ * If we are supplied with the file descriptor of an autofs
+ * mount we're looking for a specific mount. In this case
+ * the path is considered a mountpoint if it is itself a
+ * mountpoint or contains a mount, such as a multi-mount
+ * without a root mount. In this case we return 1 if the
+ * path is a mount point and the super magic of the covering
+ * mount if there is one or 0 if it isn't a mountpoint.
+ *
+ * If we aren't supplied with a file descriptor then we
+ * lookup the nameidata of the path and check if it is the
+ * root of a mount. If a type is given we are looking for
+ * a particular autofs mount and if we don't find a match
+ * we return fail. If the located nameidata path is the
+ * root of a mount we return 1 along with the super magic
+ * of the mount or 0 otherwise.
+ *
+ * In both cases the the device number (as returned by
+ * new_encode_dev()) is also returned.
+ */
+static int autofs_dev_ioctl_ismountpoint(struct file *fp,
+                                         struct autofs_sb_info *sbi,
+                                         struct autofs_dev_ioctl *param)
+{
+        struct nameidata nd;
+        const char *path;
+        unsigned int type;
+        int err = -ENOENT;
+
+        if (param->size <= sizeof(*param)) {
+                err = -EINVAL;
+                goto out;
+        }
+
+        path = param->path;
+        type = param->arg1;
+
+        param->arg1 = 0;
+        param->arg2 = 0;
+
+        if (!fp || param->ioctlfd == -1) {
+                if (type == AUTOFS_TYPE_ANY) {
+                        struct super_block *sb;
+
+                        err = path_lookup(path, LOOKUP_FOLLOW, &nd);
+                        if (err)
+                                goto out;
+
+                        sb = nd.path.dentry->d_sb;
+                        param->arg1 = new_encode_dev(sb->s_dev);
+                } else {
+                        struct autofs_info *ino;
+
+                        err = path_lookup(path, LOOKUP_PARENT, &nd);
+                        if (err)
+                                goto out;
+
+                        err = autofs_dev_ioctl_find_sbi_type(&nd, type);
+                        if (err)
+                                goto out_release;
+
+                        ino = autofs4_dentry_ino(nd.path.dentry);
+                        param->arg1 = autofs4_get_dev(ino->sbi);
+                }
+
+                err = 0;
+                if (nd.path.dentry->d_inode &&
+                    nd.path.mnt->mnt_root == nd.path.dentry) {
+                        err = 1;
+                        param->arg2 = nd.path.dentry->d_inode->i_sb->s_magic;
+                }
+        } else {
+                dev_t devid = new_encode_dev(sbi->sb->s_dev);
+
+                err = path_lookup(path, LOOKUP_PARENT, &nd);
+                if (err)
+                        goto out;
+
+                err = autofs_dev_ioctl_find_super(&nd, devid);
+                if (err)
+                        goto out_release;
+
+                param->arg1 = autofs4_get_dev(sbi);
+
+                err = have_submounts(nd.path.dentry);
+
+                if (nd.path.mnt->mnt_mountpoint != nd.path.mnt->mnt_root) {
+                        if (follow_down(&nd.path.mnt, &nd.path.dentry)) {
+                                struct inode *inode = nd.path.dentry->d_inode;
+                                param->arg2 = inode->i_sb->s_magic;
+                        }
+                }
+        }
+
+out_release:
+        path_put(&nd.path);
+out:
+        return err;
+}
+
+/*
+ * Our range of ioctl numbers isn't 0 based so we need to shift
+ * the array index by _IOC_NR(AUTOFS_CTL_IOC_FIRST) for the table
+ * lookup.
+ */
+#define cmd_idx(cmd)    (cmd - _IOC_NR(AUTOFS_DEV_IOCTL_IOC_FIRST))
+
+static ioctl_fn lookup_dev_ioctl(unsigned int cmd)
+{
+        static struct {
+                int cmd;
+                ioctl_fn fn;
+        } _ioctls[] = {
+                {cmd_idx(AUTOFS_DEV_IOCTL_VERSION_CMD), NULL},
+                {cmd_idx(AUTOFS_DEV_IOCTL_PROTOVER_CMD),
+                         autofs_dev_ioctl_protover},
+                {cmd_idx(AUTOFS_DEV_IOCTL_PROTOSUBVER_CMD),
+                         autofs_dev_ioctl_protosubver},
+                {cmd_idx(AUTOFS_DEV_IOCTL_OPENMOUNT_CMD),
+                         autofs_dev_ioctl_openmount},
+                {cmd_idx(AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD),
+                         autofs_dev_ioctl_closemount},
+                {cmd_idx(AUTOFS_DEV_IOCTL_READY_CMD),
+                         autofs_dev_ioctl_ready},
+                {cmd_idx(AUTOFS_DEV_IOCTL_FAIL_CMD),
+                         autofs_dev_ioctl_fail},
+                {cmd_idx(AUTOFS_DEV_IOCTL_SETPIPEFD_CMD),
+                         autofs_dev_ioctl_setpipefd},
+                {cmd_idx(AUTOFS_DEV_IOCTL_CATATONIC_CMD),
+                         autofs_dev_ioctl_catatonic},
+                {cmd_idx(AUTOFS_DEV_IOCTL_TIMEOUT_CMD),
+                         autofs_dev_ioctl_timeout},
+                {cmd_idx(AUTOFS_DEV_IOCTL_REQUESTER_CMD),
+                         autofs_dev_ioctl_requester},
+                {cmd_idx(AUTOFS_DEV_IOCTL_EXPIRE_CMD),
+                         autofs_dev_ioctl_expire},
+                {cmd_idx(AUTOFS_DEV_IOCTL_ASKUMOUNT_CMD),
+                         autofs_dev_ioctl_askumount},
+                {cmd_idx(AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD),
+                         autofs_dev_ioctl_ismountpoint}
+        };
+        unsigned int idx = cmd_idx(cmd);
+
+        return (idx >= ARRAY_SIZE(_ioctls)) ? NULL : _ioctls[idx].fn;
+}
+
+/* ioctl dispatcher */
+static int _autofs_dev_ioctl(unsigned int command, struct autofs_dev_ioctl __user *user)
+{
+        struct autofs_dev_ioctl *param;
+        struct file *fp;
+        struct autofs_sb_info *sbi;
+        unsigned int cmd_first, cmd;
+        ioctl_fn fn = NULL;
+        int err = 0;
+
+        /* only root can play with this */
+        if (!capable(CAP_SYS_ADMIN))
+                return -EPERM;
+
+        cmd_first = _IOC_NR(AUTOFS_DEV_IOCTL_IOC_FIRST);
+        cmd = _IOC_NR(command);
+
+        if (_IOC_TYPE(command) != _IOC_TYPE(AUTOFS_DEV_IOCTL_IOC_FIRST) ||
+            cmd - cmd_first >= AUTOFS_DEV_IOCTL_IOC_COUNT) {
+                return -ENOTTY;
+        }
+
+        /* Copy the parameters into kernel space. */
+        param = copy_dev_ioctl(user);
+        if (IS_ERR(param))
+                return PTR_ERR(param);
+
+        err = validate_dev_ioctl(command, param);
+        if (err)
+                goto out;
+
+        /* The validate routine above always sets the version */
+        if (cmd == AUTOFS_DEV_IOCTL_VERSION_CMD)
+                goto done;
+
+        fn = lookup_dev_ioctl(cmd);
+        if (!fn) {
+                AUTOFS_WARN("unknown command 0x%08x", command);
+                return -ENOTTY;
+        }
+
+        fp = NULL;
+        sbi = NULL;
+
+        /*
+         * For obvious reasons the openmount can't have a file
+         * descriptor yet. We don't take a reference to the
+         * file during close to allow for immediate release.
+         */
+        if (cmd != AUTOFS_DEV_IOCTL_OPENMOUNT_CMD &&
+            cmd != AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD) {
+                fp = fget(param->ioctlfd);
+                if (!fp) {
+                        if (cmd == AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD)
+                                goto cont;
+                        err = -EBADF;
+                        goto out;
+                }
+
+                if (!fp->f_op) {
+                        err = -ENOTTY;
+                        fput(fp);
+                        goto out;
+                }
+
+                sbi = autofs_dev_ioctl_sbi(fp);
+                if (!sbi || sbi->magic != AUTOFS_SBI_MAGIC) {
+                        err = -EINVAL;
+                        fput(fp);
+                        goto out;
+                }
+
+                /*
+                 * Admin needs to be able to set the mount catatonic in
+                 * order to be able to perform the re-open.
+                 */
+                if (!autofs4_oz_mode(sbi) &&
+                    cmd != AUTOFS_DEV_IOCTL_CATATONIC_CMD) {
+                        err = -EACCES;
+                        fput(fp);
+                        goto out;
+                }
+        }
+cont:
+        err = fn(fp, sbi, param);
+
+        if (fp)
+                fput(fp);
+done:
+        if (err >= 0 && copy_to_user(user, param, AUTOFS_DEV_IOCTL_SIZE))
+                err = -EFAULT;
+out:
+        free_dev_ioctl(param);
+        return err;
+}
+
+static long autofs_dev_ioctl(struct file *file, uint command, ulong u)
+{
+        int err;
+        err = _autofs_dev_ioctl(command, (struct autofs_dev_ioctl __user *) u);
+        return (long) err;
+}
+
+#ifdef CONFIG_COMPAT
+static long autofs_dev_ioctl_compat(struct file *file, uint command, ulong u)
+{
+        return (long) autofs_dev_ioctl(file, command, (ulong) compat_ptr(u));
+}
+#else
+#define autofs_dev_ioctl_compat NULL
+#endif
+
+static const struct file_operations _dev_ioctl_fops = {
+        .unlocked_ioctl  = autofs_dev_ioctl,
+        .compat_ioctl = autofs_dev_ioctl_compat,
+        .owner   = THIS_MODULE,
+};
+
+static struct miscdevice _autofs_dev_ioctl_misc = {
+        .minor          = MISC_DYNAMIC_MINOR,
+        .name           = AUTOFS_DEVICE_NAME,
+        .fops           = &_dev_ioctl_fops
+};
+
+/* Register/deregister misc character device */
+int autofs_dev_ioctl_init(void)
+{
+        int r;
+
+        r = misc_register(&_autofs_dev_ioctl_misc);
+        if (r) {
+                AUTOFS_ERROR("misc_register failed for control device");
+                return r;
+        }
+
+        return 0;
+}
+
+void autofs_dev_ioctl_exit(void)
+{
+        misc_deregister(&_autofs_dev_ioctl_misc);
+        return;
+}
+
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index cdabb796ff01..cde2f8e8935a 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -244,10 +244,10 @@ cont:
 }
 
 /* Check if we can expire a direct mount (possibly a tree) */
-static struct dentry *autofs4_expire_direct(struct super_block *sb,
-                                            struct vfsmount *mnt,
-                                            struct autofs_sb_info *sbi,
-                                            int how)
+struct dentry *autofs4_expire_direct(struct super_block *sb,
+                                     struct vfsmount *mnt,
+                                     struct autofs_sb_info *sbi,
+                                     int how)
 {
         unsigned long timeout;
         struct dentry *root = dget(sb->s_root);
@@ -283,10 +283,10 @@ static struct dentry *autofs4_expire_direct(struct super_block *sb,
  *  - it is unused by any user process
  *  - it has been unused for exp_timeout time
  */
-static struct dentry *autofs4_expire_indirect(struct super_block *sb,
-                                              struct vfsmount *mnt,
-                                              struct autofs_sb_info *sbi,
-                                              int how)
+struct dentry *autofs4_expire_indirect(struct super_block *sb,
+                                       struct vfsmount *mnt,
+                                       struct autofs_sb_info *sbi,
+                                       int how)
 {
         unsigned long timeout;
         struct dentry *root = sb->s_root;
@@ -479,7 +479,7 @@ int autofs4_expire_multi(struct super_block *sb, struct vfsmount *mnt,
         if (arg && get_user(do_now, arg))
                 return -EFAULT;
 
-        if (sbi->type & AUTOFS_TYPE_DIRECT)
+        if (sbi->type & AUTOFS_TYPE_TRIGGER)
                 dentry = autofs4_expire_direct(sb, mnt, sbi, do_now);
         else
                 dentry = autofs4_expire_indirect(sb, mnt, sbi, do_now);
diff --git a/fs/autofs4/init.c b/fs/autofs4/init.c
index 723a1c5e361b..9722e4bd8957 100644
--- a/fs/autofs4/init.c
+++ b/fs/autofs4/init.c
@@ -29,11 +29,20 @@ static struct file_system_type autofs_fs_type = {
 
 static int __init init_autofs4_fs(void)
 {
-        return register_filesystem(&autofs_fs_type);
+        int err;
+
+        err = register_filesystem(&autofs_fs_type);
+        if (err)
+                return err;
+
+        autofs_dev_ioctl_init();
+
+        return err;
 }
 
 static void __exit exit_autofs4_fs(void)
 {
+        autofs_dev_ioctl_exit();
         unregister_filesystem(&autofs_fs_type);
 }
 
diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c
index 7bb3e5ba0537..c7e65bb30ba0 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -53,6 +53,8 @@ struct autofs_info *autofs4_init_ino(struct autofs_info *ino,
                 atomic_set(&ino->count, 0);
         }
 
+        ino->uid = 0;
+        ino->gid = 0;
         ino->mode = mode;
         ino->last_used = jiffies;
 
@@ -213,7 +215,7 @@ static const struct super_operations autofs4_sops = {
 enum {Opt_err, Opt_fd, Opt_uid, Opt_gid, Opt_pgrp, Opt_minproto, Opt_maxproto,
         Opt_indirect, Opt_direct, Opt_offset};
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         {Opt_fd, "fd=%u"},
         {Opt_uid, "uid=%u"},
         {Opt_gid, "gid=%u"},
@@ -288,7 +290,7 @@ static int parse_options(char *options, int *pipefd, uid_t *uid, gid_t *gid,
                         *type = AUTOFS_TYPE_DIRECT;
                         break;
                 case Opt_offset:
-                        *type = AUTOFS_TYPE_DIRECT | AUTOFS_TYPE_OFFSET;
+                        *type = AUTOFS_TYPE_OFFSET;
                         break;
                 default:
                         return 1;
@@ -336,7 +338,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
         sbi->sb = s;
         sbi->version = 0;
         sbi->sub_version = 0;
-        sbi->type = 0;
+        sbi->type = AUTOFS_TYPE_INDIRECT;
         sbi->min_proto = 0;
         sbi->max_proto = 0;
         mutex_init(&sbi->wq_mutex);
@@ -378,7 +380,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
         }
 
         root_inode->i_fop = &autofs4_root_operations;
-        root_inode->i_op = sbi->type & AUTOFS_TYPE_DIRECT ?
+        root_inode->i_op = sbi->type & AUTOFS_TYPE_TRIGGER ?
                         &autofs4_direct_root_inode_operations :
                         &autofs4_indirect_root_inode_operations;
 
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 35216d18d8b5..4b67c2a2d77c 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -337,7 +337,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
                  * is very similar for indirect mounts except only dentrys
                  * in the root of the autofs file system may be negative.
                  */
-                if (sbi->type & (AUTOFS_TYPE_DIRECT|AUTOFS_TYPE_OFFSET))
+                if (sbi->type & AUTOFS_TYPE_TRIGGER)
                         return -ENOENT;
                 else if (!IS_ROOT(dentry->d_parent))
                         return -ENOENT;
@@ -348,7 +348,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
                 return -ENOMEM;
 
         /* If this is a direct mount request create a dummy name */
-        if (IS_ROOT(dentry) && (sbi->type & AUTOFS_TYPE_DIRECT))
+        if (IS_ROOT(dentry) && sbi->type & AUTOFS_TYPE_TRIGGER)
                 qstr.len = sprintf(name, "%p", dentry);
         else {
                 qstr.len = autofs4_getpath(sbi, dentry, &name);
@@ -406,11 +406,11 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
                                 type = autofs_ptype_expire_multi;
                 } else {
                         if (notify == NFY_MOUNT)
-                                type = (sbi->type & AUTOFS_TYPE_DIRECT) ?
+                                type = (sbi->type & AUTOFS_TYPE_TRIGGER) ?
                                         autofs_ptype_missing_direct :
                                          autofs_ptype_missing_indirect;
                         else
-                                type = (sbi->type & AUTOFS_TYPE_DIRECT) ?
+                                type = (sbi->type & AUTOFS_TYPE_TRIGGER) ?
                                         autofs_ptype_expire_direct :
                                         autofs_ptype_expire_indirect;
                 }
@@ -457,6 +457,40 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
 
         status = wq->status;
 
+        /*
+         * For direct and offset mounts we need to track the requester's
+         * uid and gid in the dentry info struct. This is so it can be
+         * supplied, on request, by the misc device ioctl interface.
+         * This is needed during daemon resatart when reconnecting
+         * to existing, active, autofs mounts. The uid and gid (and
+         * related string values) may be used for macro substitution
+         * in autofs mount maps.
+         */
+        if (!status) {
+                struct autofs_info *ino;
+                struct dentry *de = NULL;
+
+                /* direct mount or browsable map */
+                ino = autofs4_dentry_ino(dentry);
+                if (!ino) {
+                        /* If not lookup actual dentry used */
+                        de = d_lookup(dentry->d_parent, &dentry->d_name);
+                        if (de)
+                                ino = autofs4_dentry_ino(de);
+                }
+
+                /* Set mount requester */
+                if (ino) {
+                        spin_lock(&sbi->fs_lock);
+                        ino->uid = wq->uid;
+                        ino->gid = wq->gid;
+                        spin_unlock(&sbi->fs_lock);
+                }
+
+                if (de)
+                        dput(de);
+        }
+
         /* Are we the last process to need status? */
         mutex_lock(&sbi->wq_mutex);
         if (!--wq->wait_ctr)
diff --git a/fs/befs/befs_fs_types.h b/fs/befs/befs_fs_types.h
index e2595c2c403a..7893eaa1e58c 100644
--- a/fs/befs/befs_fs_types.h
+++ b/fs/befs/befs_fs_types.h
@@ -55,8 +55,12 @@ enum super_flags {
 };
 
 #define BEFS_BYTEORDER_NATIVE 0x42494745
+#define BEFS_BYTEORDER_NATIVE_LE (__force fs32)cpu_to_le32(BEFS_BYTEORDER_NATIVE)
+#define BEFS_BYTEORDER_NATIVE_BE (__force fs32)cpu_to_be32(BEFS_BYTEORDER_NATIVE)
 
 #define BEFS_SUPER_MAGIC BEFS_SUPER_MAGIC1
+#define BEFS_SUPER_MAGIC1_LE (__force fs32)cpu_to_le32(BEFS_SUPER_MAGIC1)
+#define BEFS_SUPER_MAGIC1_BE (__force fs32)cpu_to_be32(BEFS_SUPER_MAGIC1)
 
 /*
  * Flags of inode
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 740f53672a8a..b6dfee37c7b7 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -650,7 +650,7 @@ enum {
         Opt_uid, Opt_gid, Opt_charset, Opt_debug, Opt_err,
 };
 
-static match_table_t befs_tokens = {
+static const match_table_t befs_tokens = {
         {Opt_uid, "uid=%d"},
         {Opt_gid, "gid=%d"},
         {Opt_charset, "iocharset=%s"},
@@ -809,8 +809,8 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
 
         /* account for offset of super block on x86 */
         disk_sb = (befs_super_block *) bh->b_data;
-        if ((le32_to_cpu(disk_sb->magic1) == BEFS_SUPER_MAGIC1) ||
-            (be32_to_cpu(disk_sb->magic1) == BEFS_SUPER_MAGIC1)) {
+        if ((disk_sb->magic1 == BEFS_SUPER_MAGIC1_LE) ||
+            (disk_sb->magic1 == BEFS_SUPER_MAGIC1_BE)) {
                 befs_debug(sb, "Using PPC superblock location");
         } else {
                 befs_debug(sb, "Using x86 superblock location");
diff --git a/fs/befs/super.c b/fs/befs/super.c
index 8c3401ff6d6a..41f2b4d0093e 100644
--- a/fs/befs/super.c
+++ b/fs/befs/super.c
@@ -26,10 +26,10 @@ befs_load_sb(struct super_block *sb, befs_super_block * disk_sb)
         befs_sb_info *befs_sb = BEFS_SB(sb);
 
         /* Check the byte order of the filesystem */
-        if (le32_to_cpu(disk_sb->fs_byte_order) == BEFS_BYTEORDER_NATIVE)
+        if (disk_sb->fs_byte_order == BEFS_BYTEORDER_NATIVE_LE)
             befs_sb->byte_order = BEFS_BYTESEX_LE;
-        else if (be32_to_cpu(disk_sb->fs_byte_order) == BEFS_BYTEORDER_NATIVE)
-            befs_sb->byte_order = BEFS_BYTESEX_BE;      
+        else if (disk_sb->fs_byte_order == BEFS_BYTEORDER_NATIVE_BE)
+            befs_sb->byte_order = BEFS_BYTESEX_BE;
 
         befs_sb->magic1 = fs32_to_cpu(sb, disk_sb->magic1);
         befs_sb->magic2 = fs32_to_cpu(sb, disk_sb->magic2);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 655ed8d30a86..8fcfa398d350 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -683,7 +683,7 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
                          * switch really is going to happen - do this in
                          * flush_thread().      - akpm
                          */
-                        SET_PERSONALITY(loc->elf_ex, 0);
+                        SET_PERSONALITY(loc->elf_ex);
 
                         interpreter = open_exec(elf_interpreter);
                         retval = PTR_ERR(interpreter);
@@ -734,7 +734,7 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
                         goto out_free_dentry;
         } else {
                 /* Executables without an interpreter also need a personality  */
-                SET_PERSONALITY(loc->elf_ex, 0);
+                SET_PERSONALITY(loc->elf_ex);
         }
 
         /* Flush all traces of the currently running executable */
@@ -748,7 +748,7 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 
         /* Do this immediately, since STACK_TOP as used in setup_arg_pages
            may depend on the personality.  */
-        SET_PERSONALITY(loc->elf_ex, 0);
+        SET_PERSONALITY(loc->elf_ex);
         if (elf_read_implies_exec(loc->elf_ex, executable_stack))
                 current->personality |= READ_IMPLIES_EXEC;
 
@@ -1156,16 +1156,24 @@ static int dump_seek(struct file *file, loff_t off)
 static unsigned long vma_dump_size(struct vm_area_struct *vma,
                                    unsigned long mm_flags)
 {
+#define FILTER(type)    (mm_flags & (1UL << MMF_DUMP_##type))
+
         /* The vma can be set up to tell us the answer directly.  */
         if (vma->vm_flags & VM_ALWAYSDUMP)
                 goto whole;
 
+        /* Hugetlb memory check */
+        if (vma->vm_flags & VM_HUGETLB) {
+                if ((vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_SHARED))
+                        goto whole;
+                if (!(vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_PRIVATE))
+                        goto whole;
+        }
+
         /* Do not dump I/O mapped devices or special mappings */
         if (vma->vm_flags & (VM_IO | VM_RESERVED))
                 return 0;
 
-#define FILTER(type)    (mm_flags & (1UL << MMF_DUMP_##type))
-
         /* By default, dump shared memory if mapped from an anonymous file. */
         if (vma->vm_flags & VM_SHARED) {
                 if (vma->vm_file->f_path.dentry->d_inode->i_nlink == 0 ?
@@ -1333,20 +1341,15 @@ static void fill_prstatus(struct elf_prstatus *prstatus,
         prstatus->pr_pgrp = task_pgrp_vnr(p);
         prstatus->pr_sid = task_session_vnr(p);
         if (thread_group_leader(p)) {
+                struct task_cputime cputime;
+
                 /*
-                 * This is the record for the group leader.  Add in the
-                 * cumulative times of previous dead threads.  This total
-                 * won't include the time of each live thread whose state
-                 * is included in the core dump.  The final total reported
-                 * to our parent process when it calls wait4 will include
-                 * those sums as well as the little bit more time it takes
-                 * this and each other thread to finish dying after the
-                 * core dump synchronization phase.
+                 * This is the record for the group leader.  It shows the
+                 * group-wide total, not its individual thread total.
                  */
-                cputime_to_timeval(cputime_add(p->utime, p->signal->utime),
-                                   &prstatus->pr_utime);
-                cputime_to_timeval(cputime_add(p->stime, p->signal->stime),
-                                   &prstatus->pr_stime);
+                thread_group_cputime(p, &cputime);
+                cputime_to_timeval(cputime.utime, &prstatus->pr_utime);
+                cputime_to_timeval(cputime.stime, &prstatus->pr_stime);
         } else {
                 cputime_to_timeval(p->utime, &prstatus->pr_utime);
                 cputime_to_timeval(p->stime, &prstatus->pr_stime);
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 80c1f952ef78..5b5424cb3391 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -25,6 +25,7 @@
 #include <linux/fcntl.h>
 #include <linux/slab.h>
 #include <linux/pagemap.h>
+#include <linux/security.h>
 #include <linux/highmem.h>
 #include <linux/highuid.h>
 #include <linux/personality.h>
@@ -455,8 +456,19 @@ error_kill:
 }
 
 /*****************************************************************************/
+
+#ifndef ELF_BASE_PLATFORM
+/*
+ * AT_BASE_PLATFORM indicates the "real" hardware/microarchitecture.
+ * If the arch defines ELF_BASE_PLATFORM (in asm/elf.h), the value
+ * will be copied to the user stack in the same manner as AT_PLATFORM.
+ */
+#define ELF_BASE_PLATFORM NULL
+#endif
+
 /*
- * present useful information to the program
+ * present useful information to the program by shovelling it onto the new
+ * process's stack
  */
 static int create_elf_fdpic_tables(struct linux_binprm *bprm,
                                    struct mm_struct *mm,
@@ -466,15 +478,19 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
         unsigned long sp, csp, nitems;
         elf_caddr_t __user *argv, *envp;
         size_t platform_len = 0, len;
-        char *k_platform;
-        char __user *u_platform, *p;
+        char *k_platform, *k_base_platform;
+        char __user *u_platform, *u_base_platform, *p;
         long hwcap;
         int loop;
         int nr; /* reset for each csp adjustment */
 
-        /* we're going to shovel a whole load of stuff onto the stack */
 #ifdef CONFIG_MMU
-        sp = bprm->p;
+        /* In some cases (e.g. Hyper-Threading), we want to avoid L1 evictions
+         * by the processes running on the same package. One thing we can do is
+         * to shuffle the initial stack for them, so we give the architecture
+         * an opportunity to do so here.
+         */
+        sp = arch_align_stack(bprm->p);
 #else
         sp = mm->start_stack;
 
@@ -483,11 +499,14 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
                 return -EFAULT;
 #endif
 
-        /* get hold of platform and hardware capabilities masks for the machine
-         * we are running on.  In some cases (Sparc), this info is impossible
-         * to get, in others (i386) it is merely difficult.
-         */
         hwcap = ELF_HWCAP;
+
+        /*
+         * If this architecture has a platform capability string, copy it
+         * to userspace.  In some cases (Sparc), this info is impossible
+         * for userspace to get any other way, in others (i386) it is
+         * merely difficult.
+         */
         k_platform = ELF_PLATFORM;
         u_platform = NULL;
 
@@ -499,19 +518,20 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
                         return -EFAULT;
         }
 
-#if defined(__i386__) && defined(CONFIG_SMP)
-        /* in some cases (e.g. Hyper-Threading), we want to avoid L1 evictions
-         * by the processes running on the same package. One thing we can do is
-         * to shuffle the initial stack for them.
-         *
-         * the conditionals here are unneeded, but kept in to make the code
-         * behaviour the same as pre change unless we have hyperthreaded
-         * processors. This keeps Mr Marcelo Person happier but should be
-         * removed for 2.5
+        /*
+         * If this architecture has a "base" platform capability
+         * string, copy it to userspace.
          */
-        if (smp_num_siblings > 1)
-                sp = sp - ((current->pid % 64) << 7);
-#endif
+        k_base_platform = ELF_BASE_PLATFORM;
+        u_base_platform = NULL;
+
+        if (k_base_platform) {
+                platform_len = strlen(k_base_platform) + 1;
+                sp -= platform_len;
+                u_base_platform = (char __user *) sp;
+                if (__copy_to_user(u_base_platform, k_base_platform, platform_len) != 0)
+                        return -EFAULT;
+        }
 
         sp &= ~7UL;
 
@@ -541,9 +561,13 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
         }
 
         /* force 16 byte _final_ alignment here for generality */
-#define DLINFO_ITEMS 13
+#define DLINFO_ITEMS 15
 
-        nitems = 1 + DLINFO_ITEMS + (k_platform ? 1 : 0) + AT_VECTOR_SIZE_ARCH;
+        nitems = 1 + DLINFO_ITEMS + (k_platform ? 1 : 0) +
+                (k_base_platform ? 1 : 0) + AT_VECTOR_SIZE_ARCH;
+
+        if (bprm->interp_flags & BINPRM_FLAGS_EXECFD)
+                nitems++;
 
         csp = sp;
         sp -= nitems * 2 * sizeof(unsigned long);
@@ -575,6 +599,19 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
                             (elf_addr_t) (unsigned long) u_platform);
         }
 
+        if (k_base_platform) {
+                nr = 0;
+                csp -= 2 * sizeof(unsigned long);
+                NEW_AUX_ENT(AT_BASE_PLATFORM,
+                            (elf_addr_t) (unsigned long) u_base_platform);
+        }
+
+        if (bprm->interp_flags & BINPRM_FLAGS_EXECFD) {
+                nr = 0;
+                csp -= 2 * sizeof(unsigned long);
+                NEW_AUX_ENT(AT_EXECFD, bprm->interp_data);
+        }
+
         nr = 0;
         csp -= DLINFO_ITEMS * 2 * sizeof(unsigned long);
         NEW_AUX_ENT(AT_HWCAP,   hwcap);
@@ -590,6 +627,8 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
         NEW_AUX_ENT(AT_EUID,    (elf_addr_t) current->euid);
         NEW_AUX_ENT(AT_GID,     (elf_addr_t) current->gid);
         NEW_AUX_ENT(AT_EGID,    (elf_addr_t) current->egid);
+        NEW_AUX_ENT(AT_SECURE,  security_bprm_secureexec(bprm));
+        NEW_AUX_ENT(AT_EXECFN,  bprm->exec);
 
 #ifdef ARCH_DLINFO
         nr = 0;
@@ -1351,20 +1390,15 @@ static void fill_prstatus(struct elf_prstatus *prstatus,
         prstatus->pr_pgrp = task_pgrp_vnr(p);
         prstatus->pr_sid = task_session_vnr(p);
         if (thread_group_leader(p)) {
+                struct task_cputime cputime;
+
                 /*
-                 * This is the record for the group leader.  Add in the
-                 * cumulative times of previous dead threads.  This total
-                 * won't include the time of each live thread whose state
-                 * is included in the core dump.  The final total reported
-                 * to our parent process when it calls wait4 will include
-                 * those sums as well as the little bit more time it takes
-                 * this and each other thread to finish dying after the
-                 * core dump synchronization phase.
+                 * This is the record for the group leader.  It shows the
+                 * group-wide total, not its individual thread total.
                  */
-                cputime_to_timeval(cputime_add(p->utime, p->signal->utime),
-                                   &prstatus->pr_utime);
-                cputime_to_timeval(cputime_add(p->stime, p->signal->stime),
-                                   &prstatus->pr_stime);
+                thread_group_cputime(p, &cputime);
+                cputime_to_timeval(cputime.utime, &prstatus->pr_utime);
+                cputime_to_timeval(cputime.stime, &prstatus->pr_stime);
         } else {
                 cputime_to_timeval(p->utime, &prstatus->pr_utime);
                 cputime_to_timeval(p->stime, &prstatus->pr_stime);
diff --git a/fs/binfmt_em86.c b/fs/binfmt_em86.c
index f9c88d0c8ced..32fb00b52cd0 100644
--- a/fs/binfmt_em86.c
+++ b/fs/binfmt_em86.c
@@ -43,7 +43,7 @@ static int load_em86(struct linux_binprm *bprm,struct pt_regs *regs)
                         return -ENOEXEC;
         }
 
-        bprm->sh_bang = 1;      /* Well, the bang-shell is implicit... */
+        bprm->recursion_depth++; /* Well, the bang-shell is implicit... */
         allow_write_access(bprm->file);
         fput(bprm->file);
         bprm->file = NULL;
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index dfc0197905ca..ccb781a6a804 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -229,13 +229,13 @@ static int decompress_exec(
         ret = 10;
         if (buf[3] & EXTRA_FIELD) {
                 ret += 2 + buf[10] + (buf[11] << 8);
-                if (unlikely(LBUFSIZE == ret)) {
+                if (unlikely(LBUFSIZE <= ret)) {
                         DBG_FLT("binfmt_flat: buffer overflow (EXTRA)?\n");
                         goto out_free_buf;
                 }
         }
         if (buf[3] & ORIG_NAME) {
-                for (; ret < LBUFSIZE && (buf[ret] != 0); ret++)
+                while (ret < LBUFSIZE && buf[ret++] != 0)
                         ;
                 if (unlikely(LBUFSIZE == ret)) {
                         DBG_FLT("binfmt_flat: buffer overflow (ORIG_NAME)?\n");
@@ -243,7 +243,7 @@ static int decompress_exec(
                 }
         }
         if (buf[3] & COMMENT) {
-                for (;  ret < LBUFSIZE && (buf[ret] != 0); ret++)
+                while (ret < LBUFSIZE && buf[ret++] != 0)
                         ;
                 if (unlikely(LBUFSIZE == ret)) {
                         DBG_FLT("binfmt_flat: buffer overflow (COMMENT)?\n");
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 8d7e88e02e0f..f2744ab4e5b3 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -117,7 +117,7 @@ static int load_misc_binary(struct linux_binprm *bprm, struct pt_regs *regs)
                 goto _ret;
 
         retval = -ENOEXEC;
-        if (bprm->misc_bang)
+        if (bprm->recursion_depth > BINPRM_MAX_RECURSION)
                 goto _ret;
 
         /* to keep locking time low, we copy the interpreter string */
@@ -197,7 +197,7 @@ static int load_misc_binary(struct linux_binprm *bprm, struct pt_regs *regs)
         if (retval < 0)
                 goto _error;
 
-        bprm->misc_bang = 1;
+        bprm->recursion_depth++;
 
         retval = search_binary_handler (bprm, regs);
         if (retval < 0)
diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c
index 9e3963f7ebf1..08343505e184 100644
--- a/fs/binfmt_script.c
+++ b/fs/binfmt_script.c
@@ -22,14 +22,15 @@ static int load_script(struct linux_binprm *bprm,struct pt_regs *regs)
         char interp[BINPRM_BUF_SIZE];
         int retval;
 
-        if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!') || (bprm->sh_bang)) 
+        if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!') ||
+            (bprm->recursion_depth > BINPRM_MAX_RECURSION))
                 return -ENOEXEC;
         /*
          * This section does the #! interpretation.
          * Sorta complicated, but hopefully it will work.  -TYT
          */
 
-        bprm->sh_bang = 1;
+        bprm->recursion_depth++;
         allow_write_access(bprm->file);
         fput(bprm->file);
         bprm->file = NULL;
diff --git a/fs/binfmt_som.c b/fs/binfmt_som.c
index 68be580ba289..74e587a52796 100644
--- a/fs/binfmt_som.c
+++ b/fs/binfmt_som.c
@@ -306,3 +306,5 @@ static void __exit exit_som_binfmt(void)
 
 core_initcall(init_som_binfmt);
 module_exit(exit_som_binfmt);
+
+MODULE_LICENSE("GPL");
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index c3e174b35fe6..19caf7c962ac 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -107,7 +107,8 @@ void bio_integrity_free(struct bio *bio, struct bio_set *bs)
         BUG_ON(bip == NULL);
 
         /* A cloned bio doesn't own the integrity metadata */
-        if (!bio_flagged(bio, BIO_CLONED) && bip->bip_buf != NULL)
+        if (!bio_flagged(bio, BIO_CLONED) && !bio_flagged(bio, BIO_FS_INTEGRITY)
+            && bip->bip_buf != NULL)
                 kfree(bip->bip_buf);
 
         mempool_free(bip->bip_vec, bs->bvec_pools[bip->bip_pool]);
@@ -150,6 +151,24 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 }
 EXPORT_SYMBOL(bio_integrity_add_page);
 
+static int bdev_integrity_enabled(struct block_device *bdev, int rw)
+{
+        struct blk_integrity *bi = bdev_get_integrity(bdev);
+
+        if (bi == NULL)
+                return 0;
+
+        if (rw == READ && bi->verify_fn != NULL &&
+            (bi->flags & INTEGRITY_FLAG_READ))
+                return 1;
+
+        if (rw == WRITE && bi->generate_fn != NULL &&
+            (bi->flags & INTEGRITY_FLAG_WRITE))
+                return 1;
+
+        return 0;
+}
+
 /**
  * bio_integrity_enabled - Check whether integrity can be passed
  * @bio:        bio to check
@@ -313,6 +332,14 @@ static void bio_integrity_generate(struct bio *bio)
         }
 }
 
+static inline unsigned short blk_integrity_tuple_size(struct blk_integrity *bi)
+{
+        if (bi)
+                return bi->tuple_size;
+
+        return 0;
+}
+
 /**
  * bio_integrity_prep - Prepare bio for integrity I/O
  * @bio:        bio to prepare
diff --git a/fs/bio.c b/fs/bio.c
index 3cba7ae34d75..77a55bcceedb 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -30,7 +30,7 @@
 
 static struct kmem_cache *bio_slab __read_mostly;
 
-mempool_t *bio_split_pool __read_mostly;
+static mempool_t *bio_split_pool __read_mostly;
 
 /*
  * if you change this list, also change bvec_alloc or things will
@@ -60,25 +60,46 @@ struct bio_vec *bvec_alloc_bs(gfp_t gfp_mask, int nr, unsigned long *idx, struct
         struct bio_vec *bvl;
 
         /*
-         * see comment near bvec_array define!
+         * If 'bs' is given, lookup the pool and do the mempool alloc.
+         * If not, this is a bio_kmalloc() allocation and just do a
+         * kzalloc() for the exact number of vecs right away.
          */
-        switch (nr) {
-                case   1        : *idx = 0; break;
-                case   2 ...   4: *idx = 1; break;
-                case   5 ...  16: *idx = 2; break;
-                case  17 ...  64: *idx = 3; break;
-                case  65 ... 128: *idx = 4; break;
-                case 129 ... BIO_MAX_PAGES: *idx = 5; break;
+        if (bs) {
+                /*
+                 * see comment near bvec_array define!
+                 */
+                switch (nr) {
+                case 1:
+                        *idx = 0;
+                        break;
+                case 2 ... 4:
+                        *idx = 1;
+                        break;
+                case 5 ... 16:
+                        *idx = 2;
+                        break;
+                case 17 ... 64:
+                        *idx = 3;
+                        break;
+                case 65 ... 128:
+                        *idx = 4;
+                        break;
+                case 129 ... BIO_MAX_PAGES:
+                        *idx = 5;
+                        break;
                 default:
                         return NULL;
-        }
-        /*
-         * idx now points to the pool we want to allocate from
-         */
+                }
 
-        bvl = mempool_alloc(bs->bvec_pools[*idx], gfp_mask);
-        if (bvl)
-                memset(bvl, 0, bvec_nr_vecs(*idx) * sizeof(struct bio_vec));
+                /*
+                 * idx now points to the pool we want to allocate from
+                 */
+                bvl = mempool_alloc(bs->bvec_pools[*idx], gfp_mask);
+                if (bvl)
+                        memset(bvl, 0,
+                                bvec_nr_vecs(*idx) * sizeof(struct bio_vec));
+        } else
+                bvl = kzalloc(nr * sizeof(struct bio_vec), gfp_mask);
 
         return bvl;
 }
@@ -107,10 +128,17 @@ static void bio_fs_destructor(struct bio *bio)
         bio_free(bio, fs_bio_set);
 }
 
+static void bio_kmalloc_destructor(struct bio *bio)
+{
+        kfree(bio->bi_io_vec);
+        kfree(bio);
+}
+
 void bio_init(struct bio *bio)
 {
         memset(bio, 0, sizeof(*bio));
         bio->bi_flags = 1 << BIO_UPTODATE;
+        bio->bi_comp_cpu = -1;
         atomic_set(&bio->bi_cnt, 1);
 }
 
@@ -118,19 +146,25 @@ void bio_init(struct bio *bio)
  * bio_alloc_bioset - allocate a bio for I/O
  * @gfp_mask:   the GFP_ mask given to the slab allocator
  * @nr_iovecs:  number of iovecs to pre-allocate
- * @bs:         the bio_set to allocate from
+ * @bs:         the bio_set to allocate from. If %NULL, just use kmalloc
  *
  * Description:
- *   bio_alloc_bioset will first try it's on mempool to satisfy the allocation.
+ *   bio_alloc_bioset will first try its own mempool to satisfy the allocation.
  *   If %__GFP_WAIT is set then we will block on the internal pool waiting
- *   for a &struct bio to become free.
+ *   for a &struct bio to become free. If a %NULL @bs is passed in, we will
+ *   fall back to just using @kmalloc to allocate the required memory.
  *
  *   allocate bio and iovecs from the memory pools specified by the
- *   bio_set structure.
+ *   bio_set structure, or @kmalloc if none given.
  **/
 struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 {
-        struct bio *bio = mempool_alloc(bs->bio_pool, gfp_mask);
+        struct bio *bio;
+
+        if (bs)
+                bio = mempool_alloc(bs->bio_pool, gfp_mask);
+        else
+                bio = kmalloc(sizeof(*bio), gfp_mask);
 
         if (likely(bio)) {
                 struct bio_vec *bvl = NULL;
@@ -141,7 +175,10 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 
                         bvl = bvec_alloc_bs(gfp_mask, nr_iovecs, &idx, bs);
                         if (unlikely(!bvl)) {
-                                mempool_free(bio, bs->bio_pool);
+                                if (bs)
+                                        mempool_free(bio, bs->bio_pool);
+                                else
+                                        kfree(bio);
                                 bio = NULL;
                                 goto out;
                         }
@@ -164,6 +201,23 @@ struct bio *bio_alloc(gfp_t gfp_mask, int nr_iovecs)
         return bio;
 }
 
+/*
+ * Like bio_alloc(), but doesn't use a mempool backing. This means that
+ * it CAN fail, but while bio_alloc() can only be used for allocations
+ * that have a short (finite) life span, bio_kmalloc() should be used
+ * for more permanent bio allocations (like allocating some bio's for
+ * initalization or setup purposes).
+ */
+struct bio *bio_kmalloc(gfp_t gfp_mask, int nr_iovecs)
+{
+        struct bio *bio = bio_alloc_bioset(gfp_mask, nr_iovecs, NULL);
+
+        if (bio)
+                bio->bi_destructor = bio_kmalloc_destructor;
+
+        return bio;
+}
+
 void zero_fill_bio(struct bio *bio)
 {
         unsigned long flags;
@@ -208,14 +262,6 @@ inline int bio_phys_segments(struct request_queue *q, struct bio *bio)
         return bio->bi_phys_segments;
 }
 
-inline int bio_hw_segments(struct request_queue *q, struct bio *bio)
-{
-        if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
-                blk_recount_segments(q, bio);
-
-        return bio->bi_hw_segments;
-}
-
 /**
  *      __bio_clone     -       clone a bio
  *      @bio: destination bio
@@ -350,8 +396,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
          */
 
         while (bio->bi_phys_segments >= q->max_phys_segments
-               || bio->bi_hw_segments >= q->max_hw_segments
-               || BIOVEC_VIRT_OVERSIZE(bio->bi_size)) {
+               || bio->bi_phys_segments >= q->max_hw_segments) {
 
                 if (retried_segments)
                         return 0;
@@ -395,13 +440,11 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
         }
 
         /* If we may be able to merge these biovecs, force a recount */
-        if (bio->bi_vcnt && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec) ||
-            BIOVEC_VIRT_MERGEABLE(bvec-1, bvec)))
+        if (bio->bi_vcnt && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec)))
                 bio->bi_flags &= ~(1 << BIO_SEG_VALID);
 
         bio->bi_vcnt++;
         bio->bi_phys_segments++;
-        bio->bi_hw_segments++;
  done:
         bio->bi_size += len;
         return len;
@@ -449,16 +492,19 @@ int bio_add_page(struct bio *bio, struct page *page, unsigned int len,
 
 struct bio_map_data {
         struct bio_vec *iovecs;
-        int nr_sgvecs;
         struct sg_iovec *sgvecs;
+        int nr_sgvecs;
+        int is_our_pages;
 };
 
 static void bio_set_map_data(struct bio_map_data *bmd, struct bio *bio,
-                             struct sg_iovec *iov, int iov_count)
+                             struct sg_iovec *iov, int iov_count,
+                             int is_our_pages)
 {
         memcpy(bmd->iovecs, bio->bi_io_vec, sizeof(struct bio_vec) * bio->bi_vcnt);
         memcpy(bmd->sgvecs, iov, sizeof(struct sg_iovec) * iov_count);
         bmd->nr_sgvecs = iov_count;
+        bmd->is_our_pages = is_our_pages;
         bio->bi_private = bmd;
 }
 
@@ -493,7 +539,8 @@ static struct bio_map_data *bio_alloc_map_data(int nr_segs, int iov_count,
 }
 
 static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
-                          struct sg_iovec *iov, int iov_count, int uncopy)
+                          struct sg_iovec *iov, int iov_count, int uncopy,
+                          int do_free_page)
 {
         int ret = 0, i;
         struct bio_vec *bvec;
@@ -536,7 +583,7 @@ static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
                         }
                 }
 
-                if (uncopy)
+                if (do_free_page)
                         __free_page(bvec->bv_page);
         }
 
@@ -553,10 +600,11 @@ static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
 int bio_uncopy_user(struct bio *bio)
 {
         struct bio_map_data *bmd = bio->bi_private;
-        int ret;
-
-        ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs, bmd->nr_sgvecs, 1);
+        int ret = 0;
 
+        if (!bio_flagged(bio, BIO_NULL_MAPPED))
+                ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs,
+                                     bmd->nr_sgvecs, 1, bmd->is_our_pages);
         bio_free_map_data(bmd);
         bio_put(bio);
         return ret;
@@ -565,16 +613,20 @@ int bio_uncopy_user(struct bio *bio)
 /**
  *      bio_copy_user_iov       -       copy user data to bio
  *      @q: destination block queue
+ *      @map_data: pointer to the rq_map_data holding pages (if necessary)
  *      @iov:   the iovec.
  *      @iov_count: number of elements in the iovec
  *      @write_to_vm: bool indicating writing to pages or not
+ *      @gfp_mask: memory allocation flags
  *
  *      Prepares and returns a bio for indirect user io, bouncing data
  *      to/from kernel pages as necessary. Must be paired with
  *      call bio_uncopy_user() on io completion.
  */
-struct bio *bio_copy_user_iov(struct request_queue *q, struct sg_iovec *iov,
-                              int iov_count, int write_to_vm)
+struct bio *bio_copy_user_iov(struct request_queue *q,
+                              struct rq_map_data *map_data,
+                              struct sg_iovec *iov, int iov_count,
+                              int write_to_vm, gfp_t gfp_mask)
 {
         struct bio_map_data *bmd;
         struct bio_vec *bvec;
@@ -597,25 +649,38 @@ struct bio *bio_copy_user_iov(struct request_queue *q, struct sg_iovec *iov,
                 len += iov[i].iov_len;
         }
 
-        bmd = bio_alloc_map_data(nr_pages, iov_count, GFP_KERNEL);
+        bmd = bio_alloc_map_data(nr_pages, iov_count, gfp_mask);
         if (!bmd)
                 return ERR_PTR(-ENOMEM);
 
         ret = -ENOMEM;
-        bio = bio_alloc(GFP_KERNEL, nr_pages);
+        bio = bio_alloc(gfp_mask, nr_pages);
         if (!bio)
                 goto out_bmd;
 
         bio->bi_rw |= (!write_to_vm << BIO_RW);
 
         ret = 0;
+        i = 0;
         while (len) {
-                unsigned int bytes = PAGE_SIZE;
+                unsigned int bytes;
+
+                if (map_data)
+                        bytes = 1U << (PAGE_SHIFT + map_data->page_order);
+                else
+                        bytes = PAGE_SIZE;
 
                 if (bytes > len)
                         bytes = len;
 
-                page = alloc_page(q->bounce_gfp | GFP_KERNEL);
+                if (map_data) {
+                        if (i == map_data->nr_entries) {
+                                ret = -ENOMEM;
+                                break;
+                        }
+                        page = map_data->pages[i++];
+                } else
+                        page = alloc_page(q->bounce_gfp | gfp_mask);
                 if (!page) {
                         ret = -ENOMEM;
                         break;
@@ -634,16 +699,17 @@ struct bio *bio_copy_user_iov(struct request_queue *q, struct sg_iovec *iov,
          * success
          */
         if (!write_to_vm) {
-                ret = __bio_copy_iov(bio, bio->bi_io_vec, iov, iov_count, 0);
+                ret = __bio_copy_iov(bio, bio->bi_io_vec, iov, iov_count, 0, 0);
                 if (ret)
                         goto cleanup;
         }
 
-        bio_set_map_data(bmd, bio, iov, iov_count);
+        bio_set_map_data(bmd, bio, iov, iov_count, map_data ? 0 : 1);
         return bio;
 cleanup:
-        bio_for_each_segment(bvec, bio, i)
-                __free_page(bvec->bv_page);
+        if (!map_data)
+                bio_for_each_segment(bvec, bio, i)
+                        __free_page(bvec->bv_page);
 
         bio_put(bio);
 out_bmd:
@@ -654,29 +720,32 @@ out_bmd:
 /**
  *      bio_copy_user   -       copy user data to bio
  *      @q: destination block queue
+ *      @map_data: pointer to the rq_map_data holding pages (if necessary)
  *      @uaddr: start of user address
  *      @len: length in bytes
  *      @write_to_vm: bool indicating writing to pages or not
+ *      @gfp_mask: memory allocation flags
  *
  *      Prepares and returns a bio for indirect user io, bouncing data
  *      to/from kernel pages as necessary. Must be paired with
  *      call bio_uncopy_user() on io completion.
  */
-struct bio *bio_copy_user(struct request_queue *q, unsigned long uaddr,
-                          unsigned int len, int write_to_vm)
+struct bio *bio_copy_user(struct request_queue *q, struct rq_map_data *map_data,
+                          unsigned long uaddr, unsigned int len,
+                          int write_to_vm, gfp_t gfp_mask)
 {
         struct sg_iovec iov;
 
         iov.iov_base = (void __user *)uaddr;
         iov.iov_len = len;
 
-        return bio_copy_user_iov(q, &iov, 1, write_to_vm);
+        return bio_copy_user_iov(q, map_data, &iov, 1, write_to_vm, gfp_mask);
 }
 
 static struct bio *__bio_map_user_iov(struct request_queue *q,
                                       struct block_device *bdev,
                                       struct sg_iovec *iov, int iov_count,
-                                      int write_to_vm)
+                                      int write_to_vm, gfp_t gfp_mask)
 {
         int i, j;
         int nr_pages = 0;
@@ -702,12 +771,12 @@ static struct bio *__bio_map_user_iov(struct request_queue *q,
         if (!nr_pages)
                 return ERR_PTR(-EINVAL);
 
-        bio = bio_alloc(GFP_KERNEL, nr_pages);
+        bio = bio_alloc(gfp_mask, nr_pages);
         if (!bio)
                 return ERR_PTR(-ENOMEM);
 
         ret = -ENOMEM;
-        pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL);
+        pages = kcalloc(nr_pages, sizeof(struct page *), gfp_mask);
         if (!pages)
                 goto out;
 
@@ -786,19 +855,21 @@ static struct bio *__bio_map_user_iov(struct request_queue *q,
  *      @uaddr: start of user address
  *      @len: length in bytes
  *      @write_to_vm: bool indicating writing to pages or not
+ *      @gfp_mask: memory allocation flags
  *
  *      Map the user space address into a bio suitable for io to a block
  *      device. Returns an error pointer in case of error.
  */
 struct bio *bio_map_user(struct request_queue *q, struct block_device *bdev,
-                         unsigned long uaddr, unsigned int len, int write_to_vm)
+                         unsigned long uaddr, unsigned int len, int write_to_vm,
+                         gfp_t gfp_mask)
 {
         struct sg_iovec iov;
 
         iov.iov_base = (void __user *)uaddr;
         iov.iov_len = len;
 
-        return bio_map_user_iov(q, bdev, &iov, 1, write_to_vm);
+        return bio_map_user_iov(q, bdev, &iov, 1, write_to_vm, gfp_mask);
 }
 
 /**
@@ -808,18 +879,19 @@ struct bio *bio_map_user(struct request_queue *q, struct block_device *bdev,
  *      @iov:   the iovec.
  *      @iov_count: number of elements in the iovec
  *      @write_to_vm: bool indicating writing to pages or not
+ *      @gfp_mask: memory allocation flags
  *
  *      Map the user space address into a bio suitable for io to a block
  *      device. Returns an error pointer in case of error.
  */
 struct bio *bio_map_user_iov(struct request_queue *q, struct block_device *bdev,
                              struct sg_iovec *iov, int iov_count,
-                             int write_to_vm)
+                             int write_to_vm, gfp_t gfp_mask)
 {
         struct bio *bio;
 
-        bio = __bio_map_user_iov(q, bdev, iov, iov_count, write_to_vm);
-
+        bio = __bio_map_user_iov(q, bdev, iov, iov_count, write_to_vm,
+                                 gfp_mask);
         if (IS_ERR(bio))
                 return bio;
 
@@ -976,48 +1048,13 @@ static void bio_copy_kern_endio(struct bio *bio, int err)
 struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len,
                           gfp_t gfp_mask, int reading)
 {
-        unsigned long kaddr = (unsigned long)data;
-        unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
-        unsigned long start = kaddr >> PAGE_SHIFT;
-        const int nr_pages = end - start;
         struct bio *bio;
         struct bio_vec *bvec;
-        struct bio_map_data *bmd;
-        int i, ret;
-        struct sg_iovec iov;
-
-        iov.iov_base = data;
-        iov.iov_len = len;
-
-        bmd = bio_alloc_map_data(nr_pages, 1, gfp_mask);
-        if (!bmd)
-                return ERR_PTR(-ENOMEM);
-
-        ret = -ENOMEM;
-        bio = bio_alloc(gfp_mask, nr_pages);
-        if (!bio)
-                goto out_bmd;
-
-        while (len) {
-                struct page *page;
-                unsigned int bytes = PAGE_SIZE;
-
-                if (bytes > len)
-                        bytes = len;
-
-                page = alloc_page(q->bounce_gfp | gfp_mask);
-                if (!page) {
-                        ret = -ENOMEM;
-                        goto cleanup;
-                }
-
-                if (bio_add_pc_page(q, bio, page, bytes, 0) < bytes) {
-                        ret = -EINVAL;
-                        goto cleanup;
-                }
+        int i;
 
-                len -= bytes;
-        }
+        bio = bio_copy_user(q, NULL, (unsigned long)data, len, 1, gfp_mask);
+        if (IS_ERR(bio))
+                return bio;
 
         if (!reading) {
                 void *p = data;
@@ -1030,20 +1067,9 @@ struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len,
                 }
         }
 
-        bio->bi_private = bmd;
         bio->bi_end_io = bio_copy_kern_endio;
 
-        bio_set_map_data(bmd, bio, &iov, 1);
         return bio;
-cleanup:
-        bio_for_each_segment(bvec, bio, i)
-                __free_page(bvec->bv_page);
-
-        bio_put(bio);
-out_bmd:
-        bio_free_map_data(bmd);
-
-        return ERR_PTR(ret);
 }
 
 /*
@@ -1230,9 +1256,9 @@ static void bio_pair_end_2(struct bio *bi, int err)
  * split a bio - only worry about a bio with a single page
  * in it's iovec
  */
-struct bio_pair *bio_split(struct bio *bi, mempool_t *pool, int first_sectors)
+struct bio_pair *bio_split(struct bio *bi, int first_sectors)
 {
-        struct bio_pair *bp = mempool_alloc(pool, GFP_NOIO);
+        struct bio_pair *bp = mempool_alloc(bio_split_pool, GFP_NOIO);
 
         if (!bp)
                 return bp;
@@ -1266,7 +1292,7 @@ struct bio_pair *bio_split(struct bio *bi, mempool_t *pool, int first_sectors)
         bp->bio2.bi_end_io = bio_pair_end_2;
 
         bp->bio1.bi_private = bi;
-        bp->bio2.bi_private = pool;
+        bp->bio2.bi_private = bio_split_pool;
 
         if (bio_integrity(bi))
                 bio_integrity_split(bi, bp, first_sectors);
@@ -1274,6 +1300,42 @@ struct bio_pair *bio_split(struct bio *bi, mempool_t *pool, int first_sectors)
         return bp;
 }
 
+/**
+ *      bio_sector_offset - Find hardware sector offset in bio
+ *      @bio:           bio to inspect
+ *      @index:         bio_vec index
+ *      @offset:        offset in bv_page
+ *
+ *      Return the number of hardware sectors between beginning of bio
+ *      and an end point indicated by a bio_vec index and an offset
+ *      within that vector's page.
+ */
+sector_t bio_sector_offset(struct bio *bio, unsigned short index,
+                           unsigned int offset)
+{
+        unsigned int sector_sz = queue_hardsect_size(bio->bi_bdev->bd_disk->queue);
+        struct bio_vec *bv;
+        sector_t sectors;
+        int i;
+
+        sectors = 0;
+
+        if (index >= bio->bi_idx)
+                index = bio->bi_vcnt - 1;
+
+        __bio_for_each_segment(bv, bio, i, 0) {
+                if (i == index) {
+                        if (offset > bv->bv_offset)
+                                sectors += (offset - bv->bv_offset) / sector_sz;
+                        break;
+                }
+
+                sectors += bv->bv_len / sector_sz;
+        }
+
+        return sectors;
+}
+EXPORT_SYMBOL(bio_sector_offset);
 
 /*
  * create memory pools for biovec's in a bio_set.
@@ -1376,6 +1438,7 @@ static int __init init_bio(void)
 subsys_initcall(init_bio);
 
 EXPORT_SYMBOL(bio_alloc);
+EXPORT_SYMBOL(bio_kmalloc);
 EXPORT_SYMBOL(bio_put);
 EXPORT_SYMBOL(bio_free);
 EXPORT_SYMBOL(bio_endio);
@@ -1383,7 +1446,6 @@ EXPORT_SYMBOL(bio_init);
 EXPORT_SYMBOL(__bio_clone);
 EXPORT_SYMBOL(bio_clone);
 EXPORT_SYMBOL(bio_phys_segments);
-EXPORT_SYMBOL(bio_hw_segments);
 EXPORT_SYMBOL(bio_add_page);
 EXPORT_SYMBOL(bio_add_pc_page);
 EXPORT_SYMBOL(bio_get_nr_vecs);
@@ -1393,7 +1455,6 @@ EXPORT_SYMBOL(bio_map_kern);
 EXPORT_SYMBOL(bio_copy_kern);
 EXPORT_SYMBOL(bio_pair_release);
 EXPORT_SYMBOL(bio_split);
-EXPORT_SYMBOL(bio_split_pool);
 EXPORT_SYMBOL(bio_copy_user);
 EXPORT_SYMBOL(bio_uncopy_user);
 EXPORT_SYMBOL(bioset_create);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index aff54219e049..218408eed1bb 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -540,22 +540,6 @@ EXPORT_SYMBOL(bd_release);
  *           /sys/block/sda/holders/dm-0 --> /sys/block/dm-0
  */
 
-static struct kobject *bdev_get_kobj(struct block_device *bdev)
-{
-        if (bdev->bd_contains != bdev)
-                return kobject_get(&bdev->bd_part->dev.kobj);
-        else
-                return kobject_get(&bdev->bd_disk->dev.kobj);
-}
-
-static struct kobject *bdev_get_holder(struct block_device *bdev)
-{
-        if (bdev->bd_contains != bdev)
-                return kobject_get(bdev->bd_part->holder_dir);
-        else
-                return kobject_get(bdev->bd_disk->holder_dir);
-}
-
 static int add_symlink(struct kobject *from, struct kobject *to)
 {
         if (!from || !to)
@@ -604,11 +588,11 @@ static int bd_holder_grab_dirs(struct block_device *bdev,
         if (!bo->hdev)
                 goto fail_put_sdir;
 
-        bo->sdev = bdev_get_kobj(bdev);
+        bo->sdev = kobject_get(&part_to_dev(bdev->bd_part)->kobj);
         if (!bo->sdev)
                 goto fail_put_hdev;
 
-        bo->hdir = bdev_get_holder(bdev);
+        bo->hdir = kobject_get(bdev->bd_part->holder_dir);
         if (!bo->hdir)
                 goto fail_put_sdev;
 
@@ -868,6 +852,87 @@ struct block_device *open_by_devnum(dev_t dev, unsigned mode)
 
 EXPORT_SYMBOL(open_by_devnum);
 
+/**
+ * flush_disk - invalidates all buffer-cache entries on a disk
+ *
+ * @bdev:      struct block device to be flushed
+ *
+ * Invalidates all buffer-cache entries on a disk. It should be called
+ * when a disk has been changed -- either by a media change or online
+ * resize.
+ */
+static void flush_disk(struct block_device *bdev)
+{
+        if (__invalidate_device(bdev)) {
+                char name[BDEVNAME_SIZE] = "";
+
+                if (bdev->bd_disk)
+                        disk_name(bdev->bd_disk, 0, name);
+                printk(KERN_WARNING "VFS: busy inodes on changed media or "
+                       "resized disk %s\n", name);
+        }
+
+        if (!bdev->bd_disk)
+                return;
+        if (disk_partitionable(bdev->bd_disk))
+                bdev->bd_invalidated = 1;
+}
+
+/**
+ * check_disk_size_change - checks for disk size change and adjusts bdev size.
+ * @disk: struct gendisk to check
+ * @bdev: struct bdev to adjust.
+ *
+ * This routine checks to see if the bdev size does not match the disk size
+ * and adjusts it if it differs.
+ */
+void check_disk_size_change(struct gendisk *disk, struct block_device *bdev)
+{
+        loff_t disk_size, bdev_size;
+
+        disk_size = (loff_t)get_capacity(disk) << 9;
+        bdev_size = i_size_read(bdev->bd_inode);
+        if (disk_size != bdev_size) {
+                char name[BDEVNAME_SIZE];
+
+                disk_name(disk, 0, name);
+                printk(KERN_INFO
+                       "%s: detected capacity change from %lld to %lld\n",
+                       name, bdev_size, disk_size);
+                i_size_write(bdev->bd_inode, disk_size);
+                flush_disk(bdev);
+        }
+}
+EXPORT_SYMBOL(check_disk_size_change);
+
+/**
+ * revalidate_disk - wrapper for lower-level driver's revalidate_disk call-back
+ * @disk: struct gendisk to be revalidated
+ *
+ * This routine is a wrapper for lower-level driver's revalidate_disk
+ * call-backs.  It is used to do common pre and post operations needed
+ * for all revalidate_disk operations.
+ */
+int revalidate_disk(struct gendisk *disk)
+{
+        struct block_device *bdev;
+        int ret = 0;
+
+        if (disk->fops->revalidate_disk)
+                ret = disk->fops->revalidate_disk(disk);
+
+        bdev = bdget_disk(disk, 0);
+        if (!bdev)
+                return ret;
+
+        mutex_lock(&bdev->bd_mutex);
+        check_disk_size_change(disk, bdev);
+        mutex_unlock(&bdev->bd_mutex);
+        bdput(bdev);
+        return ret;
+}
+EXPORT_SYMBOL(revalidate_disk);
+
 /*
  * This routine checks whether a removable media has been changed,
  * and invalidates all buffer-cache-entries in that case. This
@@ -887,13 +952,9 @@ int check_disk_change(struct block_device *bdev)
         if (!bdops->media_changed(bdev->bd_disk))
                 return 0;
 
-        if (__invalidate_device(bdev))
-                printk("VFS: busy inodes on changed media.\n");
-
+        flush_disk(bdev);
         if (bdops->revalidate_disk)
                 bdops->revalidate_disk(bdev->bd_disk);
-        if (bdev->bd_disk->minors > 1)
-                bdev->bd_invalidated = 1;
         return 1;
 }
 
@@ -927,10 +988,10 @@ static int __blkdev_put(struct block_device *bdev, int for_part);
 
 static int do_open(struct block_device *bdev, struct file *file, int for_part)
 {
-        struct module *owner = NULL;
         struct gendisk *disk;
+        struct hd_struct *part = NULL;
         int ret;
-        int part;
+        int partno;
         int perm = 0;
 
         if (file->f_mode & FMODE_READ)
@@ -948,25 +1009,27 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 
         ret = -ENXIO;
         file->f_mapping = bdev->bd_inode->i_mapping;
+
         lock_kernel();
-        disk = get_gendisk(bdev->bd_dev, &part);
-        if (!disk) {
-                unlock_kernel();
-                bdput(bdev);
-                return ret;
-        }
-        owner = disk->fops->owner;
+
+        disk = get_gendisk(bdev->bd_dev, &partno);
+        if (!disk)
+                goto out_unlock_kernel;
+        part = disk_get_part(disk, partno);
+        if (!part)
+                goto out_unlock_kernel;
 
         mutex_lock_nested(&bdev->bd_mutex, for_part);
         if (!bdev->bd_openers) {
                 bdev->bd_disk = disk;
+                bdev->bd_part = part;
                 bdev->bd_contains = bdev;
-                if (!part) {
+                if (!partno) {
                         struct backing_dev_info *bdi;
                         if (disk->fops->open) {
                                 ret = disk->fops->open(bdev->bd_inode, file);
                                 if (ret)
-                                        goto out_first;
+                                        goto out_clear;
                         }
                         if (!bdev->bd_openers) {
                                 bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
@@ -978,36 +1041,36 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
                         if (bdev->bd_invalidated)
                                 rescan_partitions(disk, bdev);
                 } else {
-                        struct hd_struct *p;
                         struct block_device *whole;
                         whole = bdget_disk(disk, 0);
                         ret = -ENOMEM;
                         if (!whole)
-                                goto out_first;
+                                goto out_clear;
                         BUG_ON(for_part);
                         ret = __blkdev_get(whole, file->f_mode, file->f_flags, 1);
                         if (ret)
-                                goto out_first;
+                                goto out_clear;
                         bdev->bd_contains = whole;
-                        p = disk->part[part - 1];
                         bdev->bd_inode->i_data.backing_dev_info =
                            whole->bd_inode->i_data.backing_dev_info;
-                        if (!(disk->flags & GENHD_FL_UP) || !p || !p->nr_sects) {
+                        if (!(disk->flags & GENHD_FL_UP) ||
+                            !part || !part->nr_sects) {
                                 ret = -ENXIO;
-                                goto out_first;
+                                goto out_clear;
                         }
-                        kobject_get(&p->dev.kobj);
-                        bdev->bd_part = p;
-                        bd_set_size(bdev, (loff_t) p->nr_sects << 9);
+                        bd_set_size(bdev, (loff_t)part->nr_sects << 9);
                 }
         } else {
+                disk_put_part(part);
                 put_disk(disk);
-                module_put(owner);
+                module_put(disk->fops->owner);
+                part = NULL;
+                disk = NULL;
                 if (bdev->bd_contains == bdev) {
                         if (bdev->bd_disk->fops->open) {
                                 ret = bdev->bd_disk->fops->open(bdev->bd_inode, file);
                                 if (ret)
-                                        goto out;
+                                        goto out_unlock_bdev;
                         }
                         if (bdev->bd_invalidated)
                                 rescan_partitions(bdev->bd_disk, bdev);
@@ -1020,19 +1083,24 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
         unlock_kernel();
         return 0;
 
-out_first:
+ out_clear:
         bdev->bd_disk = NULL;
+        bdev->bd_part = NULL;
         bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
         if (bdev != bdev->bd_contains)
                 __blkdev_put(bdev->bd_contains, 1);
         bdev->bd_contains = NULL;
-        put_disk(disk);
-        module_put(owner);
-out:
+ out_unlock_bdev:
         mutex_unlock(&bdev->bd_mutex);
+ out_unlock_kernel:
         unlock_kernel();
-        if (ret)
-                bdput(bdev);
+
+        disk_put_part(part);
+        if (disk)
+                module_put(disk->fops->owner);
+        put_disk(disk);
+        bdput(bdev);
+
         return ret;
 }
 
@@ -1117,11 +1185,8 @@ static int __blkdev_put(struct block_device *bdev, int for_part)
 
                 put_disk(disk);
                 module_put(owner);
-
-                if (bdev->bd_contains != bdev) {
-                        kobject_put(&bdev->bd_part->dev.kobj);
-                        bdev->bd_part = NULL;
-                }
+                disk_put_part(bdev->bd_part);
+                bdev->bd_part = NULL;
                 bdev->bd_disk = NULL;
                 bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
                 if (bdev != bdev->bd_contains)
@@ -1197,10 +1262,9 @@ EXPORT_SYMBOL(ioctl_by_bdev);
 
 /**
  * lookup_bdev  - lookup a struct block_device by name
- *
  * @path:       special file representing the block device
  *
- * Get a reference to the blockdevice at @path in the current
+ * Get a reference to the blockdevice at @pathname in the current
  * namespace if possible and return it.  Return ERR_PTR(error)
  * otherwise.
  */
diff --git a/fs/buffer.c b/fs/buffer.c
index ac78d4c19b3b..6569fda5cfed 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -76,8 +76,7 @@ EXPORT_SYMBOL(__lock_buffer);
 
 void unlock_buffer(struct buffer_head *bh)
 {
-        smp_mb__before_clear_bit();
-        clear_buffer_locked(bh);
+        clear_bit_unlock(BH_Lock, &bh->b_state);
         smp_mb__after_clear_bit();
         wake_up_bit(&bh->b_state, BH_Lock);
 }
diff --git a/fs/char_dev.c b/fs/char_dev.c
index 3cb7cda3d780..262fa10e213d 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -22,9 +22,6 @@
 #include <linux/mutex.h>
 #include <linux/backing-dev.h>
 
-#ifdef CONFIG_KMOD
-#include <linux/kmod.h>
-#endif
 #include "internal.h"
 
 /*
diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
new file mode 100644
index 000000000000..341a98965bd0
--- /dev/null
+++ b/fs/cifs/Kconfig
@@ -0,0 +1,142 @@
+config CIFS
+        tristate "CIFS support (advanced network filesystem, SMBFS successor)"
+        depends on INET
+        select NLS
+        help
+          This is the client VFS module for the Common Internet File System
+          (CIFS) protocol which is the successor to the Server Message Block
+          (SMB) protocol, the native file sharing mechanism for most early
+          PC operating systems.  The CIFS protocol is fully supported by
+          file servers such as Windows 2000 (including Windows 2003, NT 4
+          and Windows XP) as well by Samba (which provides excellent CIFS
+          server support for Linux and many other operating systems). Limited
+          support for OS/2 and Windows ME and similar servers is provided as
+          well.
+
+          The cifs module provides an advanced network file system
+          client for mounting to CIFS compliant servers.  It includes
+          support for DFS (hierarchical name space), secure per-user
+          session establishment via Kerberos or NTLM or NTLMv2,
+          safe distributed caching (oplock), optional packet
+          signing, Unicode and other internationalization improvements.
+          If you need to mount to Samba or Windows from this machine, say Y.
+
+config CIFS_STATS
+        bool "CIFS statistics"
+        depends on CIFS
+        help
+          Enabling this option will cause statistics for each server share
+          mounted by the cifs client to be displayed in /proc/fs/cifs/Stats
+
+config CIFS_STATS2
+        bool "Extended statistics"
+        depends on CIFS_STATS
+        help
+          Enabling this option will allow more detailed statistics on SMB
+          request timing to be displayed in /proc/fs/cifs/DebugData and also
+          allow optional logging of slow responses to dmesg (depending on the
+          value of /proc/fs/cifs/cifsFYI, see fs/cifs/README for more details).
+          These additional statistics may have a minor effect on performance
+          and memory utilization.
+
+          Unless you are a developer or are doing network performance analysis
+          or tuning, say N.
+
+config CIFS_WEAK_PW_HASH
+        bool "Support legacy servers which use weaker LANMAN security"
+        depends on CIFS
+        help
+          Modern CIFS servers including Samba and most Windows versions
+          (since 1997) support stronger NTLM (and even NTLMv2 and Kerberos)
+          security mechanisms. These hash the password more securely
+          than the mechanisms used in the older LANMAN version of the
+          SMB protocol but LANMAN based authentication is needed to
+          establish sessions with some old SMB servers.
+
+          Enabling this option allows the cifs module to mount to older
+          LANMAN based servers such as OS/2 and Windows 95, but such
+          mounts may be less secure than mounts using NTLM or more recent
+          security mechanisms if you are on a public network.  Unless you
+          have a need to access old SMB servers (and are on a private
+          network) you probably want to say N.  Even if this support
+          is enabled in the kernel build, LANMAN authentication will not be
+          used automatically. At runtime LANMAN mounts are disabled but
+          can be set to required (or optional) either in
+          /proc/fs/cifs (see fs/cifs/README for more detail) or via an
+          option on the mount command. This support is disabled by
+          default in order to reduce the possibility of a downgrade
+          attack.
+
+          If unsure, say N.
+
+config CIFS_UPCALL
+          bool "Kerberos/SPNEGO advanced session setup"
+          depends on CIFS && KEYS
+          help
+            Enables an upcall mechanism for CIFS which accesses
+            userspace helper utilities to provide SPNEGO packaged (RFC 4178)
+            Kerberos tickets which are needed to mount to certain secure servers
+            (for which more secure Kerberos authentication is required). If
+            unsure, say N.
+
+config CIFS_XATTR
+        bool "CIFS extended attributes"
+        depends on CIFS
+        help
+          Extended attributes are name:value pairs associated with inodes by
+          the kernel or by users (see the attr(5) manual page, or visit
+          <http://acl.bestbits.at/> for details).  CIFS maps the name of
+          extended attributes beginning with the user namespace prefix
+          to SMB/CIFS EAs. EAs are stored on Windows servers without the
+          user namespace prefix, but their names are seen by Linux cifs clients
+          prefaced by the user namespace prefix. The system namespace
+          (used by some filesystems to store ACLs) is not supported at
+          this time.
+
+          If unsure, say N.
+
+config CIFS_POSIX
+        bool "CIFS POSIX Extensions"
+        depends on CIFS_XATTR
+        help
+          Enabling this option will cause the cifs client to attempt to
+          negotiate a newer dialect with servers, such as Samba 3.0.5
+          or later, that optionally can handle more POSIX like (rather
+          than Windows like) file behavior.  It also enables
+          support for POSIX ACLs (getfacl and setfacl) to servers
+          (such as Samba 3.10 and later) which can negotiate
+          CIFS POSIX ACL support.  If unsure, say N.
+
+config CIFS_DEBUG2
+        bool "Enable additional CIFS debugging routines"
+        depends on CIFS
+        help
+           Enabling this option adds a few more debugging routines
+           to the cifs code which slightly increases the size of
+           the cifs module and can cause additional logging of debug
+           messages in some error paths, slowing performance. This
+           option can be turned off unless you are debugging
+           cifs problems.  If unsure, say N.
+
+config CIFS_EXPERIMENTAL
+          bool "CIFS Experimental Features (EXPERIMENTAL)"
+          depends on CIFS && EXPERIMENTAL
+          help
+            Enables cifs features under testing. These features are
+            experimental and currently include DFS support and directory
+            change notification ie fcntl(F_DNOTIFY), as well as the upcall
+            mechanism which will be used for Kerberos session negotiation
+            and uid remapping.  Some of these features also may depend on
+            setting a value of 1 to the pseudo-file /proc/fs/cifs/Experimental
+            (which is disabled by default). See the file fs/cifs/README
+            for more details.  If unsure, say N.
+
+config CIFS_DFS_UPCALL
+          bool "DFS feature support (EXPERIMENTAL)"
+          depends on CIFS_EXPERIMENTAL
+          depends on KEYS
+          help
+            Enables an upcall mechanism for CIFS which contacts userspace
+            helper utilities to provide server name resolution (host names to
+            IP addresses) which is needed for implicit mounts of DFS junction
+            points. If unsure, say N.
diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c
index 117ef4bba68e..fcee9298b620 100644
--- a/fs/cifs/cifs_spnego.c
+++ b/fs/cifs/cifs_spnego.c
@@ -66,11 +66,28 @@ struct key_type cifs_spnego_key_type = {
         .describe       = user_describe,
 };
 
-#define MAX_VER_STR_LEN   8 /* length of longest version string e.g.
-                                strlen("ver=0xFF") */
-#define MAX_MECH_STR_LEN 13 /* length of longest security mechanism name, eg
-                               in future could have strlen(";sec=ntlmsspi") */
-#define MAX_IPV6_ADDR_LEN 42 /* eg FEDC:BA98:7654:3210:FEDC:BA98:7654:3210/60 */
+/* length of longest version string e.g.  strlen("ver=0xFF") */
+#define MAX_VER_STR_LEN         8
+
+/* length of longest security mechanism name, eg in future could have
+ * strlen(";sec=ntlmsspi") */
+#define MAX_MECH_STR_LEN        13
+
+/* max possible addr len eg FEDC:BA98:7654:3210:FEDC:BA98:7654:3210/60 */
+#define MAX_IPV6_ADDR_LEN       42
+
+/* strlen of "host=" */
+#define HOST_KEY_LEN            5
+
+/* strlen of ";ip4=" or ";ip6=" */
+#define IP_KEY_LEN              5
+
+/* strlen of ";uid=0x" */
+#define UID_KEY_LEN             7
+
+/* strlen of ";user=" */
+#define USER_KEY_LEN            6
+
 /* get a key struct with a SPNEGO security blob, suitable for session setup */
 struct key *
 cifs_get_spnego_key(struct cifsSesInfo *sesInfo)
@@ -84,11 +101,11 @@ cifs_get_spnego_key(struct cifsSesInfo *sesInfo)
         /* length of fields (with semicolons): ver=0xyz ip4=ipaddress
            host=hostname sec=mechanism uid=0xFF user=username */
         desc_len = MAX_VER_STR_LEN +
-                   6 /* len of "host=" */ + strlen(hostname) +
-                   5 /* len of ";ipv4=" */ + MAX_IPV6_ADDR_LEN +
+                   HOST_KEY_LEN + strlen(hostname) +
+                   IP_KEY_LEN + MAX_IPV6_ADDR_LEN +
                    MAX_MECH_STR_LEN +
-                   7 /* len of ";uid=0x" */ + (sizeof(uid_t) * 2) +
-                   6 /* len of ";user=" */ + strlen(sesInfo->userName) + 1;
+                   UID_KEY_LEN + (sizeof(uid_t) * 2) +
+                   USER_KEY_LEN + strlen(sesInfo->userName) + 1;
 
         spnego_key = ERR_PTR(-ENOMEM);
         description = kzalloc(desc_len, GFP_KERNEL);
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 135c965c4137..f7b4a5cd837b 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -41,7 +41,7 @@ extern int cifs_create(struct inode *, struct dentry *, int,
                        struct nameidata *);
 extern struct dentry *cifs_lookup(struct inode *, struct dentry *,
                                   struct nameidata *);
-extern int cifs_unlink(struct inode *, struct dentry *);
+extern int cifs_unlink(struct inode *dir, struct dentry *dentry);
 extern int cifs_hardlink(struct dentry *, struct inode *, struct dentry *);
 extern int cifs_mknod(struct inode *, struct dentry *, int, dev_t);
 extern int cifs_mkdir(struct inode *, struct dentry *, int);
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 8dfd6f24d488..0d22479d99b7 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -309,6 +309,7 @@ struct cifs_search_info {
         __u32 resume_key;
         char *ntwrk_buf_start;
         char *srch_entries_start;
+        char *last_entry;
         char *presume_name;
         unsigned int resume_name_len;
         bool endOfSearch:1;
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index a729d083e6f4..0cff7fe986e8 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -179,6 +179,8 @@ extern int CIFSSMBSetPathInfo(const int xid, struct cifsTconInfo *tcon,
 extern int CIFSSMBSetFileInfo(const int xid, struct cifsTconInfo *tcon,
                         const FILE_BASIC_INFO *data, __u16 fid,
                         __u32 pid_of_opener);
+extern int CIFSSMBSetFileDisposition(const int xid, struct cifsTconInfo *tcon,
+                        bool delete_file, __u16 fid, __u32 pid_of_opener);
 #if 0
 extern int CIFSSMBSetAttrLegacy(int xid, struct cifsTconInfo *tcon,
                         char *fileName, __u16 dos_attributes,
@@ -229,7 +231,7 @@ extern int CIFSSMBRename(const int xid, struct cifsTconInfo *tcon,
                         const struct nls_table *nls_codepage,
                         int remap_special_chars);
 extern int CIFSSMBRenameOpenFile(const int xid, struct cifsTconInfo *pTcon,
-                        int netfid, char *target_name,
+                        int netfid, const char *target_name,
                         const struct nls_table *nls_codepage,
                         int remap_special_chars);
 extern int CIFSCreateHardLink(const int xid,
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 994de7c90474..6f4ffe15d68d 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -2017,7 +2017,7 @@ renameRetry:
 }
 
 int CIFSSMBRenameOpenFile(const int xid, struct cifsTconInfo *pTcon,
-                int netfid, char *target_name,
+                int netfid, const char *target_name,
                 const struct nls_table *nls_codepage, int remap)
 {
         struct smb_com_transaction2_sfi_req *pSMB  = NULL;
@@ -2071,7 +2071,7 @@ int CIFSSMBRenameOpenFile(const int xid, struct cifsTconInfo *pTcon,
                                         remap);
         }
         rename_info->target_name_len = cpu_to_le32(2 * len_of_str);
-        count = 12 /* sizeof(struct set_file_rename) */ + (2 * len_of_str) + 2;
+        count = 12 /* sizeof(struct set_file_rename) */ + (2 * len_of_str);
         byte_count += count;
         pSMB->DataCount = cpu_to_le16(count);
         pSMB->TotalDataCount = pSMB->DataCount;
@@ -3614,6 +3614,8 @@ findFirstRetry:
                 /* BB remember to free buffer if error BB */
                 rc = validate_t2((struct smb_t2_rsp *)pSMBr);
                 if (rc == 0) {
+                        unsigned int lnoff;
+
                         if (pSMBr->hdr.Flags2 & SMBFLG2_UNICODE)
                                 psrch_inf->unicode = true;
                         else
@@ -3636,6 +3638,17 @@ findFirstRetry:
                                         le16_to_cpu(parms->SearchCount);
                         psrch_inf->index_of_last_entry = 2 /* skip . and .. */ +
                                 psrch_inf->entries_in_buffer;
+                        lnoff = le16_to_cpu(parms->LastNameOffset);
+                        if (tcon->ses->server->maxBuf - MAX_CIFS_HDR_SIZE <
+                              lnoff) {
+                                cERROR(1, ("ignoring corrupt resume name"));
+                                psrch_inf->last_entry = NULL;
+                                return rc;
+                        }
+
+                        psrch_inf->last_entry = psrch_inf->srch_entries_start +
+                                                        lnoff;
+
                         *pnetfid = parms->SearchHandle;
                 } else {
                         cifs_buf_release(pSMB);
@@ -3725,6 +3738,8 @@ int CIFSFindNext(const int xid, struct cifsTconInfo *tcon,
                 rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 
                 if (rc == 0) {
+                        unsigned int lnoff;
+
                         /* BB fixme add lock for file (srch_info) struct here */
                         if (pSMBr->hdr.Flags2 & SMBFLG2_UNICODE)
                                 psrch_inf->unicode = true;
@@ -3751,6 +3766,16 @@ int CIFSFindNext(const int xid, struct cifsTconInfo *tcon,
                                                 le16_to_cpu(parms->SearchCount);
                         psrch_inf->index_of_last_entry +=
                                 psrch_inf->entries_in_buffer;
+                        lnoff = le16_to_cpu(parms->LastNameOffset);
+                        if (tcon->ses->server->maxBuf - MAX_CIFS_HDR_SIZE <
+                              lnoff) {
+                                cERROR(1, ("ignoring corrupt resume name"));
+                                psrch_inf->last_entry = NULL;
+                                return rc;
+                        } else
+                                psrch_inf->last_entry =
+                                        psrch_inf->srch_entries_start + lnoff;
+
 /*  cFYI(1,("fnxt2 entries in buf %d index_of_last %d",
             psrch_inf->entries_in_buffer, psrch_inf->index_of_last_entry)); */
 
@@ -4876,6 +4901,61 @@ CIFSSMBSetFileInfo(const int xid, struct cifsTconInfo *tcon,
         return rc;
 }
 
+int
+CIFSSMBSetFileDisposition(const int xid, struct cifsTconInfo *tcon,
+                          bool delete_file, __u16 fid, __u32 pid_of_opener)
+{
+        struct smb_com_transaction2_sfi_req *pSMB  = NULL;
+        char *data_offset;
+        int rc = 0;
+        __u16 params, param_offset, offset, byte_count, count;
+
+        cFYI(1, ("Set File Disposition (via SetFileInfo)"));
+        rc = small_smb_init(SMB_COM_TRANSACTION2, 15, tcon, (void **) &pSMB);
+
+        if (rc)
+                return rc;
+
+        pSMB->hdr.Pid = cpu_to_le16((__u16)pid_of_opener);
+        pSMB->hdr.PidHigh = cpu_to_le16((__u16)(pid_of_opener >> 16));
+
+        params = 6;
+        pSMB->MaxSetupCount = 0;
+        pSMB->Reserved = 0;
+        pSMB->Flags = 0;
+        pSMB->Timeout = 0;
+        pSMB->Reserved2 = 0;
+        param_offset = offsetof(struct smb_com_transaction2_sfi_req, Fid) - 4;
+        offset = param_offset + params;
+
+        data_offset = (char *) (&pSMB->hdr.Protocol) + offset;
+
+        count = 1;
+        pSMB->MaxParameterCount = cpu_to_le16(2);
+        /* BB find max SMB PDU from sess */
+        pSMB->MaxDataCount = cpu_to_le16(1000);
+        pSMB->SetupCount = 1;
+        pSMB->Reserved3 = 0;
+        pSMB->SubCommand = cpu_to_le16(TRANS2_SET_FILE_INFORMATION);
+        byte_count = 3 /* pad */  + params + count;
+        pSMB->DataCount = cpu_to_le16(count);
+        pSMB->ParameterCount = cpu_to_le16(params);
+        pSMB->TotalDataCount = pSMB->DataCount;
+        pSMB->TotalParameterCount = pSMB->ParameterCount;
+        pSMB->ParameterOffset = cpu_to_le16(param_offset);
+        pSMB->DataOffset = cpu_to_le16(offset);
+        pSMB->Fid = fid;
+        pSMB->InformationLevel = cpu_to_le16(SMB_SET_FILE_DISPOSITION_INFO);
+        pSMB->Reserved4 = 0;
+        pSMB->hdr.smb_buf_length += byte_count;
+        pSMB->ByteCount = cpu_to_le16(byte_count);
+        *data_offset = delete_file ? 1 : 0;
+        rc = SendReceiveNoRsp(xid, tcon->ses, (struct smb_hdr *) pSMB, 0);
+        if (rc)
+                cFYI(1, ("Send error in SetFileDisposition = %d", rc));
+
+        return rc;
+}
 
 int
 CIFSSMBSetPathInfo(const int xid, struct cifsTconInfo *tcon,
diff --git a/fs/cifs/dns_resolve.c b/fs/cifs/dns_resolve.c
index a2e0673e1b08..1e0c1bd8f2e4 100644
--- a/fs/cifs/dns_resolve.c
+++ b/fs/cifs/dns_resolve.c
@@ -29,19 +29,55 @@
 #include "cifsproto.h"
 #include "cifs_debug.h"
 
-static int dns_resolver_instantiate(struct key *key, const void *data,
+/* Checks if supplied name is IP address
+ * returns:
+ *              1 - name is IP
+ *              0 - name is not IP
+ */
+static int
+is_ip(const char *name)
+{
+        int rc;
+        struct sockaddr_in sin_server;
+        struct sockaddr_in6 sin_server6;
+
+        rc = cifs_inet_pton(AF_INET, name,
+                        &sin_server.sin_addr.s_addr);
+
+        if (rc <= 0) {
+                /* not ipv4 address, try ipv6 */
+                rc = cifs_inet_pton(AF_INET6, name,
+                                &sin_server6.sin6_addr.in6_u);
+                if (rc > 0)
+                        return 1;
+        } else {
+                return 1;
+        }
+        /* we failed translating address */
+        return 0;
+}
+
+static int
+dns_resolver_instantiate(struct key *key, const void *data,
                 size_t datalen)
 {
         int rc = 0;
         char *ip;
 
-        ip = kmalloc(datalen+1, GFP_KERNEL);
+        ip = kmalloc(datalen + 1, GFP_KERNEL);
         if (!ip)
                 return -ENOMEM;
 
         memcpy(ip, data, datalen);
         ip[datalen] = '\0';
 
+        /* make sure this looks like an address */
+        if (!is_ip((const char *) ip)) {
+                kfree(ip);
+                return -EINVAL;
+        }
+
+        key->type_data.x[0] = datalen;
         rcu_assign_pointer(key->payload.data, ip);
 
         return rc;
@@ -62,33 +98,6 @@ struct key_type key_type_dns_resolver = {
         .match       = user_match,
 };
 
-/* Checks if supplied name is IP address
- * returns:
- *              1 - name is IP
- *              0 - name is not IP
- */
-static int is_ip(const char *name)
-{
-        int rc;
-        struct sockaddr_in sin_server;
-        struct sockaddr_in6 sin_server6;
-
-        rc = cifs_inet_pton(AF_INET, name,
-                        &sin_server.sin_addr.s_addr);
-
-        if (rc <= 0) {
-                /* not ipv4 address, try ipv6 */
-                rc = cifs_inet_pton(AF_INET6, name,
-                                &sin_server6.sin6_addr.in6_u);
-                if (rc > 0)
-                        return 1;
-        } else {
-                return 1;
-        }
-        /* we failed translating address */
-        return 0;
-}
-
 /* Resolves server name to ip address.
  * input:
  *      unc - server UNC
@@ -140,6 +149,7 @@ dns_resolve_server_name_to_ip(const char *unc, char **ip_addr)
 
         rkey = request_key(&key_type_dns_resolver, name, "");
         if (!IS_ERR(rkey)) {
+                len = rkey->type_data.x[0];
                 data = rkey->payload.data;
         } else {
                 cERROR(1, ("%s: unable to resolve: %s", __func__, name));
@@ -148,11 +158,9 @@ dns_resolve_server_name_to_ip(const char *unc, char **ip_addr)
 
 skip_upcall:
         if (data) {
-                len = strlen(data);
-                *ip_addr = kmalloc(len+1, GFP_KERNEL);
+                *ip_addr = kmalloc(len + 1, GFP_KERNEL);
                 if (*ip_addr) {
-                        memcpy(*ip_addr, data, len);
-                        (*ip_addr)[len] = '\0';
+                        memcpy(*ip_addr, data, len + 1);
                         if (!IS_ERR(rkey))
                                 cFYI(1, ("%s: resolved: %s to %s", __func__,
                                                         name,
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index cbefe1f1f9fe..62d8bd8f14c0 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -107,7 +107,7 @@ static inline int cifs_open_inode_helper(struct inode *inode, struct file *file,
 
         /* want handles we can use to read with first
            in the list so we do not have to walk the
-           list to search for one in prepare_write */
+           list to search for one in write_begin */
         if ((file->f_flags & O_ACCMODE) == O_WRONLY) {
                 list_add_tail(&pCifsFile->flist,
                               &pCifsInode->openFileList);
@@ -915,7 +915,7 @@ ssize_t cifs_user_write(struct file *file, const char __user *write_data,
 }
 
 static ssize_t cifs_write(struct file *file, const char *write_data,
-        size_t write_size, loff_t *poffset)
+                          size_t write_size, loff_t *poffset)
 {
         int rc = 0;
         unsigned int bytes_written = 0;
@@ -1065,6 +1065,7 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode)
 struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode)
 {
         struct cifsFileInfo *open_file;
+        bool any_available = false;
         int rc;
 
         /* Having a null inode here (because mapping->host was set to zero by
@@ -1080,8 +1081,10 @@ struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode)
         read_lock(&GlobalSMBSeslock);
 refind_writable:
         list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
-                if (open_file->closePend)
+                if (open_file->closePend ||
+                    (!any_available && open_file->pid != current->tgid))
                         continue;
+
                 if (open_file->pfile &&
                     ((open_file->pfile->f_flags & O_RDWR) ||
                      (open_file->pfile->f_flags & O_WRONLY))) {
@@ -1131,6 +1134,11 @@ refind_writable:
                            of the loop here. */
                 }
         }
+        /* couldn't find useable FH with same pid, try any available */
+        if (!any_available) {
+                any_available = true;
+                goto refind_writable;
+        }
         read_unlock(&GlobalSMBSeslock);
         return NULL;
 }
@@ -1447,49 +1455,52 @@ static int cifs_writepage(struct page *page, struct writeback_control *wbc)
         return rc;
 }
 
-static int cifs_commit_write(struct file *file, struct page *page,
-        unsigned offset, unsigned to)
+static int cifs_write_end(struct file *file, struct address_space *mapping,
+                        loff_t pos, unsigned len, unsigned copied,
+                        struct page *page, void *fsdata)
 {
-        int xid;
-        int rc = 0;
-        struct inode *inode = page->mapping->host;
-        loff_t position = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
-        char *page_data;
+        int rc;
+        struct inode *inode = mapping->host;
 
-        xid = GetXid();
-        cFYI(1, ("commit write for page %p up to position %lld for %d",
-                 page, position, to));
-        spin_lock(&inode->i_lock);
-        if (position > inode->i_size)
-                i_size_write(inode, position);
+        cFYI(1, ("write_end for page %p from pos %lld with %d bytes",
+                 page, pos, copied));
+
+        if (!PageUptodate(page) && copied == PAGE_CACHE_SIZE)
+                SetPageUptodate(page);
 
-        spin_unlock(&inode->i_lock);
         if (!PageUptodate(page)) {
-                position =  ((loff_t)page->index << PAGE_CACHE_SHIFT) + offset;
-                /* can not rely on (or let) writepage write this data */
-                if (to < offset) {
-                        cFYI(1, ("Illegal offsets, can not copy from %d to %d",
-                                offset, to));
-                        FreeXid(xid);
-                        return rc;
-                }
+                char *page_data;
+                unsigned offset = pos & (PAGE_CACHE_SIZE - 1);
+                int xid;
+
+                xid = GetXid();
                 /* this is probably better than directly calling
                    partialpage_write since in this function the file handle is
                    known which we might as well leverage */
                 /* BB check if anything else missing out of ppw
                    such as updating last write time */
                 page_data = kmap(page);
-                rc = cifs_write(file, page_data + offset, to-offset,
-                                &position);
-                if (rc > 0)
-                        rc = 0;
-                /* else if (rc < 0) should we set writebehind rc? */
+                rc = cifs_write(file, page_data + offset, copied, &pos);
+                /* if (rc < 0) should we set writebehind rc? */
                 kunmap(page);
+
+                FreeXid(xid);
         } else {
+                rc = copied;
+                pos += copied;
                 set_page_dirty(page);
         }
 
-        FreeXid(xid);
+        if (rc > 0) {
+                spin_lock(&inode->i_lock);
+                if (pos > inode->i_size)
+                        i_size_write(inode, pos);
+                spin_unlock(&inode->i_lock);
+        }
+
+        unlock_page(page);
+        page_cache_release(page);
+
         return rc;
 }
 
@@ -1780,7 +1791,7 @@ static void cifs_copy_cache_pages(struct address_space *mapping,
                 SetPageUptodate(page);
                 unlock_page(page);
                 if (!pagevec_add(plru_pvec, page))
-                        __pagevec_lru_add(plru_pvec);
+                        __pagevec_lru_add_file(plru_pvec);
                 data += PAGE_CACHE_SIZE;
         }
         return;
@@ -1914,7 +1925,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
                 bytes_read = 0;
         }
 
-        pagevec_lru_add(&lru_pvec);
+        pagevec_lru_add_file(&lru_pvec);
 
 /* need to free smb_read_data buf before exit */
         if (smb_read_data) {
@@ -2035,49 +2046,44 @@ bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file)
                 return true;
 }
 
-static int cifs_prepare_write(struct file *file, struct page *page,
-        unsigned from, unsigned to)
+static int cifs_write_begin(struct file *file, struct address_space *mapping,
+                        loff_t pos, unsigned len, unsigned flags,
+                        struct page **pagep, void **fsdata)
 {
-        int rc = 0;
-        loff_t i_size;
-        loff_t offset;
+        pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+        loff_t offset = pos & (PAGE_CACHE_SIZE - 1);
 
-        cFYI(1, ("prepare write for page %p from %d to %d", page, from, to));
-        if (PageUptodate(page))
+        cFYI(1, ("write_begin from %lld len %d", (long long)pos, len));
+
+        *pagep = __grab_cache_page(mapping, index);
+        if (!*pagep)
+                return -ENOMEM;
+
+        if (PageUptodate(*pagep))
                 return 0;
 
         /* If we are writing a full page it will be up to date,
            no need to read from the server */
-        if ((to == PAGE_CACHE_SIZE) && (from == 0)) {
-                SetPageUptodate(page);
+        if (len == PAGE_CACHE_SIZE && flags & AOP_FLAG_UNINTERRUPTIBLE)
                 return 0;
-        }
 
-        offset = (loff_t)page->index << PAGE_CACHE_SHIFT;
-        i_size = i_size_read(page->mapping->host);
+        if ((file->f_flags & O_ACCMODE) != O_WRONLY) {
+                int rc;
 
-        if ((offset >= i_size) ||
-            ((from == 0) && (offset + to) >= i_size)) {
-                /*
-                 * We don't need to read data beyond the end of the file.
-                 * zero it, and set the page uptodate
-                 */
-                simple_prepare_write(file, page, from, to);
-                SetPageUptodate(page);
-        } else if ((file->f_flags & O_ACCMODE) != O_WRONLY) {
                 /* might as well read a page, it is fast enough */
-                rc = cifs_readpage_worker(file, page, &offset);
+                rc = cifs_readpage_worker(file, *pagep, &offset);
+
+                /* we do not need to pass errors back
+                   e.g. if we do not have read access to the file
+                   because cifs_write_end will attempt synchronous writes
+                   -- shaggy */
         } else {
                 /* we could try using another file handle if there is one -
                    but how would we lock it to prevent close of that handle
                    racing with this read? In any case
-                   this will be written out by commit_write so is fine */
+                   this will be written out by write_end so is fine */
         }
 
-        /* we do not need to pass errors back
-           e.g. if we do not have read access to the file
-           because cifs_commit_write will do the right thing.  -- shaggy */
-
         return 0;
 }
 
@@ -2086,8 +2092,8 @@ const struct address_space_operations cifs_addr_ops = {
         .readpages = cifs_readpages,
         .writepage = cifs_writepage,
         .writepages = cifs_writepages,
-        .prepare_write = cifs_prepare_write,
-        .commit_write = cifs_commit_write,
+        .write_begin = cifs_write_begin,
+        .write_end = cifs_write_end,
         .set_page_dirty = __set_page_dirty_nobuffers,
         /* .sync_page = cifs_sync_page, */
         /* .direct_IO = */
@@ -2102,8 +2108,8 @@ const struct address_space_operations cifs_addr_ops_smallbuf = {
         .readpage = cifs_readpage,
         .writepage = cifs_writepage,
         .writepages = cifs_writepages,
-        .prepare_write = cifs_prepare_write,
-        .commit_write = cifs_commit_write,
+        .write_begin = cifs_write_begin,
+        .write_end = cifs_write_end,
         .set_page_dirty = __set_page_dirty_nobuffers,
         /* .sync_page = cifs_sync_page, */
         /* .direct_IO = */
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 9c548f110102..a8c833345fc9 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -665,40 +665,201 @@ struct inode *cifs_iget(struct super_block *sb, unsigned long ino)
         return inode;
 }
 
-int cifs_unlink(struct inode *inode, struct dentry *direntry)
+static int
+cifs_set_file_info(struct inode *inode, struct iattr *attrs, int xid,
+                    char *full_path, __u32 dosattr)
+{
+        int rc;
+        int oplock = 0;
+        __u16 netfid;
+        __u32 netpid;
+        bool set_time = false;
+        struct cifsFileInfo *open_file;
+        struct cifsInodeInfo *cifsInode = CIFS_I(inode);
+        struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+        struct cifsTconInfo *pTcon = cifs_sb->tcon;
+        FILE_BASIC_INFO info_buf;
+
+        if (attrs->ia_valid & ATTR_ATIME) {
+                set_time = true;
+                info_buf.LastAccessTime =
+                        cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_atime));
+        } else
+                info_buf.LastAccessTime = 0;
+
+        if (attrs->ia_valid & ATTR_MTIME) {
+                set_time = true;
+                info_buf.LastWriteTime =
+                    cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_mtime));
+        } else
+                info_buf.LastWriteTime = 0;
+
+        /*
+         * Samba throws this field away, but windows may actually use it.
+         * Do not set ctime unless other time stamps are changed explicitly
+         * (i.e. by utimes()) since we would then have a mix of client and
+         * server times.
+         */
+        if (set_time && (attrs->ia_valid & ATTR_CTIME)) {
+                cFYI(1, ("CIFS - CTIME changed"));
+                info_buf.ChangeTime =
+                    cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_ctime));
+        } else
+                info_buf.ChangeTime = 0;
+
+        info_buf.CreationTime = 0;      /* don't change */
+        info_buf.Attributes = cpu_to_le32(dosattr);
+
+        /*
+         * If the file is already open for write, just use that fileid
+         */
+        open_file = find_writable_file(cifsInode);
+        if (open_file) {
+                netfid = open_file->netfid;
+                netpid = open_file->pid;
+                goto set_via_filehandle;
+        }
+
+        /*
+         * NT4 apparently returns success on this call, but it doesn't
+         * really work.
+         */
+        if (!(pTcon->ses->flags & CIFS_SES_NT4)) {
+                rc = CIFSSMBSetPathInfo(xid, pTcon, full_path,
+                                     &info_buf, cifs_sb->local_nls,
+                                     cifs_sb->mnt_cifs_flags &
+                                        CIFS_MOUNT_MAP_SPECIAL_CHR);
+                if (rc == 0) {
+                        cifsInode->cifsAttrs = dosattr;
+                        goto out;
+                } else if (rc != -EOPNOTSUPP && rc != -EINVAL)
+                        goto out;
+        }
+
+        cFYI(1, ("calling SetFileInfo since SetPathInfo for "
+                 "times not supported by this server"));
+        rc = CIFSSMBOpen(xid, pTcon, full_path, FILE_OPEN,
+                         SYNCHRONIZE | FILE_WRITE_ATTRIBUTES,
+                         CREATE_NOT_DIR, &netfid, &oplock,
+                         NULL, cifs_sb->local_nls,
+                         cifs_sb->mnt_cifs_flags &
+                                CIFS_MOUNT_MAP_SPECIAL_CHR);
+
+        if (rc != 0) {
+                if (rc == -EIO)
+                        rc = -EINVAL;
+                goto out;
+        }
+
+        netpid = current->tgid;
+
+set_via_filehandle:
+        rc = CIFSSMBSetFileInfo(xid, pTcon, &info_buf, netfid, netpid);
+        if (!rc)
+                cifsInode->cifsAttrs = dosattr;
+
+        if (open_file == NULL)
+                CIFSSMBClose(xid, pTcon, netfid);
+        else
+                atomic_dec(&open_file->wrtPending);
+out:
+        return rc;
+}
+
+/*
+ * open the given file (if it isn't already), set the DELETE_ON_CLOSE bit
+ * and rename it to a random name that hopefully won't conflict with
+ * anything else.
+ */
+static int
+cifs_rename_pending_delete(char *full_path, struct inode *inode, int xid)
+{
+        int oplock = 0;
+        int rc;
+        __u16 netfid;
+        struct cifsInodeInfo *cifsInode = CIFS_I(inode);
+        struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+        struct cifsTconInfo *tcon = cifs_sb->tcon;
+        __u32 dosattr;
+        FILE_BASIC_INFO *info_buf;
+
+        rc = CIFSSMBOpen(xid, tcon, full_path, FILE_OPEN,
+                         DELETE|FILE_WRITE_ATTRIBUTES,
+                         CREATE_NOT_DIR|CREATE_DELETE_ON_CLOSE,
+                         &netfid, &oplock, NULL, cifs_sb->local_nls,
+                         cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+        if (rc != 0)
+                goto out;
+
+        /* set ATTR_HIDDEN and clear ATTR_READONLY */
+        cifsInode = CIFS_I(inode);
+        dosattr = cifsInode->cifsAttrs & ~ATTR_READONLY;
+        if (dosattr == 0)
+                dosattr |= ATTR_NORMAL;
+        dosattr |= ATTR_HIDDEN;
+
+        info_buf = kzalloc(sizeof(*info_buf), GFP_KERNEL);
+        if (info_buf == NULL) {
+                rc = -ENOMEM;
+                goto out_close;
+        }
+        info_buf->Attributes = cpu_to_le32(dosattr);
+        rc = CIFSSMBSetFileInfo(xid, tcon, info_buf, netfid, current->tgid);
+        kfree(info_buf);
+        if (rc != 0)
+                goto out_close;
+        cifsInode->cifsAttrs = dosattr;
+
+        /* silly-rename the file */
+        CIFSSMBRenameOpenFile(xid, tcon, netfid, NULL, cifs_sb->local_nls,
+                                   cifs_sb->mnt_cifs_flags &
+                                            CIFS_MOUNT_MAP_SPECIAL_CHR);
+
+        /* set DELETE_ON_CLOSE */
+        rc = CIFSSMBSetFileDisposition(xid, tcon, true, netfid, current->tgid);
+
+        /*
+         * some samba versions return -ENOENT when we try to set the file
+         * disposition here. Likely a samba bug, but work around it for now
+         */
+        if (rc == -ENOENT)
+                rc = 0;
+
+out_close:
+        CIFSSMBClose(xid, tcon, netfid);
+out:
+        return rc;
+}
+
+int cifs_unlink(struct inode *dir, struct dentry *dentry)
 {
         int rc = 0;
         int xid;
-        struct cifs_sb_info *cifs_sb;
-        struct cifsTconInfo *pTcon;
         char *full_path = NULL;
-        struct cifsInodeInfo *cifsInode;
-        FILE_BASIC_INFO *pinfo_buf;
+        struct inode *inode = dentry->d_inode;
+        struct cifsInodeInfo *cifsInode = CIFS_I(inode);
+        struct super_block *sb = dir->i_sb;
+        struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
+        struct cifsTconInfo *tcon = cifs_sb->tcon;
+        struct iattr *attrs = NULL;
+        __u32 dosattr = 0, origattr = 0;
 
-        cFYI(1, ("cifs_unlink, inode = 0x%p", inode));
+        cFYI(1, ("cifs_unlink, dir=0x%p, dentry=0x%p", dir, dentry));
 
         xid = GetXid();
 
-        if (inode)
-                cifs_sb = CIFS_SB(inode->i_sb);
-        else
-                cifs_sb = CIFS_SB(direntry->d_sb);
-        pTcon = cifs_sb->tcon;
-
-        /* Unlink can be called from rename so we can not grab the sem here
-           since we deadlock otherwise */
-/*      mutex_lock(&direntry->d_sb->s_vfs_rename_mutex);*/
-        full_path = build_path_from_dentry(direntry);
-/*      mutex_unlock(&direntry->d_sb->s_vfs_rename_mutex);*/
+        /* Unlink can be called from rename so we can not take the
+         * sb->s_vfs_rename_mutex here */
+        full_path = build_path_from_dentry(dentry);
         if (full_path == NULL) {
                 FreeXid(xid);
                 return -ENOMEM;
         }
 
-        if ((pTcon->ses->capabilities & CAP_UNIX) &&
+        if ((tcon->ses->capabilities & CAP_UNIX) &&
                 (CIFS_UNIX_POSIX_PATH_OPS_CAP &
-                        le64_to_cpu(pTcon->fsUnixInfo.Capability))) {
-                rc = CIFSPOSIXDelFile(xid, pTcon, full_path,
+                        le64_to_cpu(tcon->fsUnixInfo.Capability))) {
+                rc = CIFSPOSIXDelFile(xid, tcon, full_path,
                         SMB_POSIX_UNLINK_FILE_TARGET, cifs_sb->local_nls,
                         cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
                 cFYI(1, ("posix del rc %d", rc));
@@ -706,125 +867,60 @@ int cifs_unlink(struct inode *inode, struct dentry *direntry)
                         goto psx_del_no_retry;
         }
 
-        rc = CIFSSMBDelFile(xid, pTcon, full_path, cifs_sb->local_nls,
+retry_std_delete:
+        rc = CIFSSMBDelFile(xid, tcon, full_path, cifs_sb->local_nls,
                         cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+
 psx_del_no_retry:
         if (!rc) {
-                if (direntry->d_inode)
-                        drop_nlink(direntry->d_inode);
+                if (inode)
+                        drop_nlink(inode);
         } else if (rc == -ENOENT) {
-                d_drop(direntry);
+                d_drop(dentry);
         } else if (rc == -ETXTBSY) {
-                int oplock = 0;
-                __u16 netfid;
-
-                rc = CIFSSMBOpen(xid, pTcon, full_path, FILE_OPEN, DELETE,
-                                 CREATE_NOT_DIR | CREATE_DELETE_ON_CLOSE,
-                                 &netfid, &oplock, NULL, cifs_sb->local_nls,
-                                 cifs_sb->mnt_cifs_flags &
-                                        CIFS_MOUNT_MAP_SPECIAL_CHR);
-                if (rc == 0) {
-                        CIFSSMBRenameOpenFile(xid, pTcon, netfid, NULL,
-                                              cifs_sb->local_nls,
-                                              cifs_sb->mnt_cifs_flags &
-                                                CIFS_MOUNT_MAP_SPECIAL_CHR);
-                        CIFSSMBClose(xid, pTcon, netfid);
-                        if (direntry->d_inode)
-                                drop_nlink(direntry->d_inode);
+                rc = cifs_rename_pending_delete(full_path, inode, xid);
+                if (rc == 0)
+                        drop_nlink(inode);
+        } else if (rc == -EACCES && dosattr == 0) {
+                attrs = kzalloc(sizeof(*attrs), GFP_KERNEL);
+                if (attrs == NULL) {
+                        rc = -ENOMEM;
+                        goto out_reval;
                 }
-        } else if (rc == -EACCES) {
-                /* try only if r/o attribute set in local lookup data? */
-                pinfo_buf = kzalloc(sizeof(FILE_BASIC_INFO), GFP_KERNEL);
-                if (pinfo_buf) {
-                        /* ATTRS set to normal clears r/o bit */
-                        pinfo_buf->Attributes = cpu_to_le32(ATTR_NORMAL);
-                        if (!(pTcon->ses->flags & CIFS_SES_NT4))
-                                rc = CIFSSMBSetPathInfo(xid, pTcon, full_path,
-                                                     pinfo_buf,
-                                                     cifs_sb->local_nls,
-                                                     cifs_sb->mnt_cifs_flags &
-                                                        CIFS_MOUNT_MAP_SPECIAL_CHR);
-                        else
-                                rc = -EOPNOTSUPP;
 
-                        if (rc == -EOPNOTSUPP) {
-                                int oplock = 0;
-                                __u16 netfid;
-                        /*      rc = CIFSSMBSetAttrLegacy(xid, pTcon,
-                                                          full_path,
-                                                          (__u16)ATTR_NORMAL,
-                                                          cifs_sb->local_nls);
-                           For some strange reason it seems that NT4 eats the
-                           old setattr call without actually setting the
-                           attributes so on to the third attempted workaround
-                           */
-
-                        /* BB could scan to see if we already have it open
-                           and pass in pid of opener to function */
-                                rc = CIFSSMBOpen(xid, pTcon, full_path,
-                                                 FILE_OPEN, SYNCHRONIZE |
-                                                 FILE_WRITE_ATTRIBUTES, 0,
-                                                 &netfid, &oplock, NULL,
-                                                 cifs_sb->local_nls,
-                                                 cifs_sb->mnt_cifs_flags &
-                                                    CIFS_MOUNT_MAP_SPECIAL_CHR);
-                                if (rc == 0) {
-                                        rc = CIFSSMBSetFileInfo(xid, pTcon,
-                                                                pinfo_buf,
-                                                                netfid,
-                                                                current->tgid);
-                                        CIFSSMBClose(xid, pTcon, netfid);
-                                }
-                        }
-                        kfree(pinfo_buf);
-                }
-                if (rc == 0) {
-                        rc = CIFSSMBDelFile(xid, pTcon, full_path,
-                                            cifs_sb->local_nls,
-                                            cifs_sb->mnt_cifs_flags &
-                                                CIFS_MOUNT_MAP_SPECIAL_CHR);
-                        if (!rc) {
-                                if (direntry->d_inode)
-                                        drop_nlink(direntry->d_inode);
-                        } else if (rc == -ETXTBSY) {
-                                int oplock = 0;
-                                __u16 netfid;
-
-                                rc = CIFSSMBOpen(xid, pTcon, full_path,
-                                                 FILE_OPEN, DELETE,
-                                                 CREATE_NOT_DIR |
-                                                 CREATE_DELETE_ON_CLOSE,
-                                                 &netfid, &oplock, NULL,
-                                                 cifs_sb->local_nls,
-                                                 cifs_sb->mnt_cifs_flags &
-                                                    CIFS_MOUNT_MAP_SPECIAL_CHR);
-                                if (rc == 0) {
-                                        CIFSSMBRenameOpenFile(xid, pTcon,
-                                                netfid, NULL,
-                                                cifs_sb->local_nls,
-                                                cifs_sb->mnt_cifs_flags &
-                                                    CIFS_MOUNT_MAP_SPECIAL_CHR);
-                                        CIFSSMBClose(xid, pTcon, netfid);
-                                        if (direntry->d_inode)
-                                                drop_nlink(direntry->d_inode);
-                                }
-                        /* BB if rc = -ETXTBUSY goto the rename logic BB */
-                        }
-                }
-        }
-        if (direntry->d_inode) {
-                cifsInode = CIFS_I(direntry->d_inode);
-                cifsInode->time = 0;    /* will force revalidate to get info
-                                           when needed */
-                direntry->d_inode->i_ctime = current_fs_time(inode->i_sb);
+                /* try to reset dos attributes */
+                origattr = cifsInode->cifsAttrs;
+                if (origattr == 0)
+                        origattr |= ATTR_NORMAL;
+                dosattr = origattr & ~ATTR_READONLY;
+                if (dosattr == 0)
+                        dosattr |= ATTR_NORMAL;
+                dosattr |= ATTR_HIDDEN;
+
+                rc = cifs_set_file_info(inode, attrs, xid, full_path, dosattr);
+                if (rc != 0)
+                        goto out_reval;
+
+                goto retry_std_delete;
         }
+
+        /* undo the setattr if we errored out and it's needed */
+        if (rc != 0 && dosattr != 0)
+                cifs_set_file_info(inode, attrs, xid, full_path, origattr);
+
+out_reval:
         if (inode) {
-                inode->i_ctime = inode->i_mtime = current_fs_time(inode->i_sb);
                 cifsInode = CIFS_I(inode);
-                cifsInode->time = 0;    /* force revalidate of dir as well */
+                cifsInode->time = 0;    /* will force revalidate to get info
+                                           when needed */
+                inode->i_ctime = current_fs_time(sb);
         }
+        dir->i_ctime = dir->i_mtime = current_fs_time(sb);
+        cifsInode = CIFS_I(dir);
+        CIFS_I(dir)->time = 0;  /* force revalidate of dir as well */
 
         kfree(full_path);
+        kfree(attrs);
         FreeXid(xid);
         return rc;
 }
@@ -869,7 +965,7 @@ static void posix_fill_in_inode(struct inode *tmp_inode,
 
 int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode)
 {
-        int rc = 0;
+        int rc = 0, tmprc;
         int xid;
         struct cifs_sb_info *cifs_sb;
         struct cifsTconInfo *pTcon;
@@ -931,6 +1027,7 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode)
                                 kfree(pInfo);
                                 goto mkdir_get_info;
                         }
+
                         /* Is an i_ino of zero legal? */
                         /* Are there sanity checks we can use to ensure that
                            the server is really filling in that field? */
@@ -1019,12 +1116,20 @@ mkdir_get_info:
                         if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) &&
                             (mode & S_IWUGO) == 0) {
                                 FILE_BASIC_INFO pInfo;
+                                struct cifsInodeInfo *cifsInode;
+                                u32 dosattrs;
+
                                 memset(&pInfo, 0, sizeof(pInfo));
-                                pInfo.Attributes = cpu_to_le32(ATTR_READONLY);
-                                CIFSSMBSetPathInfo(xid, pTcon, full_path,
-                                                &pInfo, cifs_sb->local_nls,
+                                cifsInode = CIFS_I(newinode);
+                                dosattrs = cifsInode->cifsAttrs|ATTR_READONLY;
+                                pInfo.Attributes = cpu_to_le32(dosattrs);
+                                tmprc = CIFSSMBSetPathInfo(xid, pTcon,
+                                                full_path, &pInfo,
+                                                cifs_sb->local_nls,
                                                 cifs_sb->mnt_cifs_flags &
                                                 CIFS_MOUNT_MAP_SPECIAL_CHR);
+                                if (tmprc == 0)
+                                        cifsInode->cifsAttrs = dosattrs;
                         }
                         if (direntry->d_inode) {
                                 if (cifs_sb->mnt_cifs_flags &
@@ -1096,117 +1201,141 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry)
         return rc;
 }
 
+static int
+cifs_do_rename(int xid, struct dentry *from_dentry, const char *fromPath,
+                struct dentry *to_dentry, const char *toPath)
+{
+        struct cifs_sb_info *cifs_sb = CIFS_SB(from_dentry->d_sb);
+        struct cifsTconInfo *pTcon = cifs_sb->tcon;
+        __u16 srcfid;
+        int oplock, rc;
+
+        /* try path-based rename first */
+        rc = CIFSSMBRename(xid, pTcon, fromPath, toPath, cifs_sb->local_nls,
+                           cifs_sb->mnt_cifs_flags &
+                                CIFS_MOUNT_MAP_SPECIAL_CHR);
+
+        /*
+         * don't bother with rename by filehandle unless file is busy and
+         * source Note that cross directory moves do not work with
+         * rename by filehandle to various Windows servers.
+         */
+        if (rc == 0 || rc != -ETXTBSY)
+                return rc;
+
+        /* open the file to be renamed -- we need DELETE perms */
+        rc = CIFSSMBOpen(xid, pTcon, fromPath, FILE_OPEN, DELETE,
+                         CREATE_NOT_DIR, &srcfid, &oplock, NULL,
+                         cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+                                CIFS_MOUNT_MAP_SPECIAL_CHR);
+
+        if (rc == 0) {
+                rc = CIFSSMBRenameOpenFile(xid, pTcon, srcfid,
+                                (const char *) to_dentry->d_name.name,
+                                cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+                                        CIFS_MOUNT_MAP_SPECIAL_CHR);
+
+                CIFSSMBClose(xid, pTcon, srcfid);
+        }
+
+        return rc;
+}
+
 int cifs_rename(struct inode *source_inode, struct dentry *source_direntry,
         struct inode *target_inode, struct dentry *target_direntry)
 {
-        char *fromName;
-        char *toName;
+        char *fromName = NULL;
+        char *toName = NULL;
         struct cifs_sb_info *cifs_sb_source;
         struct cifs_sb_info *cifs_sb_target;
         struct cifsTconInfo *pTcon;
+        FILE_UNIX_BASIC_INFO *info_buf_source = NULL;
+        FILE_UNIX_BASIC_INFO *info_buf_target;
         int xid;
-        int rc = 0;
-
-        xid = GetXid();
+        int rc;
 
         cifs_sb_target = CIFS_SB(target_inode->i_sb);
         cifs_sb_source = CIFS_SB(source_inode->i_sb);
         pTcon = cifs_sb_source->tcon;
 
+        xid = GetXid();
+
+        /*
+         * BB: this might be allowed if same server, but different share.
+         * Consider adding support for this
+         */
         if (pTcon != cifs_sb_target->tcon) {
-                FreeXid(xid);
-                return -EXDEV;  /* BB actually could be allowed if same server,
-                                   but different share.
-                                   Might eventually add support for this */
+                rc = -EXDEV;
+                goto cifs_rename_exit;
         }
 
-        /* we already  have the rename sem so we do not need to grab it again
-           here to protect the path integrity */
+        /*
+         * we already have the rename sem so we do not need to
+         * grab it again here to protect the path integrity
+         */
         fromName = build_path_from_dentry(source_direntry);
+        if (fromName == NULL) {
+                rc = -ENOMEM;
+                goto cifs_rename_exit;
+        }
+
         toName = build_path_from_dentry(target_direntry);
-        if ((fromName == NULL) || (toName == NULL)) {
+        if (toName == NULL) {
                 rc = -ENOMEM;
                 goto cifs_rename_exit;
         }
 
-        rc = CIFSSMBRename(xid, pTcon, fromName, toName,
-                           cifs_sb_source->local_nls,
-                           cifs_sb_source->mnt_cifs_flags &
-                                CIFS_MOUNT_MAP_SPECIAL_CHR);
+        rc = cifs_do_rename(xid, source_direntry, fromName,
+                            target_direntry, toName);
+
         if (rc == -EEXIST) {
-                /* check if they are the same file because rename of hardlinked
-                   files is a noop */
-                FILE_UNIX_BASIC_INFO *info_buf_source;
-                FILE_UNIX_BASIC_INFO *info_buf_target;
-
-                info_buf_source =
-                        kmalloc(2 * sizeof(FILE_UNIX_BASIC_INFO), GFP_KERNEL);
-                if (info_buf_source != NULL) {
+                if (pTcon->unix_ext) {
+                        /*
+                         * Are src and dst hardlinks of same inode? We can
+                         * only tell with unix extensions enabled
+                         */
+                        info_buf_source =
+                                kmalloc(2 * sizeof(FILE_UNIX_BASIC_INFO),
+                                                GFP_KERNEL);
+                        if (info_buf_source == NULL)
+                                goto unlink_target;
+
                         info_buf_target = info_buf_source + 1;
-                        if (pTcon->unix_ext)
-                                rc = CIFSSMBUnixQPathInfo(xid, pTcon, fromName,
-                                        info_buf_source,
-                                        cifs_sb_source->local_nls,
-                                        cifs_sb_source->mnt_cifs_flags &
+                        rc = CIFSSMBUnixQPathInfo(xid, pTcon, fromName,
+                                                info_buf_source,
+                                                cifs_sb_source->local_nls,
+                                                cifs_sb_source->mnt_cifs_flags &
                                                 CIFS_MOUNT_MAP_SPECIAL_CHR);
-                        /* else rc is still EEXIST so will fall through to
-                           unlink the target and retry rename */
-                        if (rc == 0) {
-                                rc = CIFSSMBUnixQPathInfo(xid, pTcon, toName,
-                                                info_buf_target,
+                        if (rc != 0)
+                                goto unlink_target;
+
+                        rc = CIFSSMBUnixQPathInfo(xid, pTcon,
+                                                toName, info_buf_target,
                                                 cifs_sb_target->local_nls,
                                                 /* remap based on source sb */
                                                 cifs_sb_source->mnt_cifs_flags &
-                                                    CIFS_MOUNT_MAP_SPECIAL_CHR);
-                        }
-                        if ((rc == 0) &&
-                            (info_buf_source->UniqueId ==
-                             info_buf_target->UniqueId)) {
-                        /* do not rename since the files are hardlinked which
-                           is a noop */
-                        } else {
-                        /* we either can not tell the files are hardlinked
-                           (as with Windows servers) or files are not
-                           hardlinked so delete the target manually before
-                           renaming to follow POSIX rather than Windows
-                           semantics */
-                                cifs_unlink(target_inode, target_direntry);
-                                rc = CIFSSMBRename(xid, pTcon, fromName,
-                                                   toName,
-                                                   cifs_sb_source->local_nls,
-                                                   cifs_sb_source->mnt_cifs_flags
-                                                   & CIFS_MOUNT_MAP_SPECIAL_CHR);
-                        }
-                        kfree(info_buf_source);
-                } /* if we can not get memory just leave rc as EEXIST */
-        }
-
-        if (rc)
-                cFYI(1, ("rename rc %d", rc));
-
-        if ((rc == -EIO) || (rc == -EEXIST)) {
-                int oplock = 0;
-                __u16 netfid;
-
-                /* BB FIXME Is Generic Read correct for rename? */
-                /* if renaming directory - we should not say CREATE_NOT_DIR,
-                   need to test renaming open directory, also GENERIC_READ
-                   might not right be right access to request */
-                rc = CIFSSMBOpen(xid, pTcon, fromName, FILE_OPEN, GENERIC_READ,
-                                 CREATE_NOT_DIR, &netfid, &oplock, NULL,
-                                 cifs_sb_source->local_nls,
-                                 cifs_sb_source->mnt_cifs_flags &
-                                        CIFS_MOUNT_MAP_SPECIAL_CHR);
-                if (rc == 0) {
-                        rc = CIFSSMBRenameOpenFile(xid, pTcon, netfid, toName,
-                                              cifs_sb_source->local_nls,
-                                              cifs_sb_source->mnt_cifs_flags &
                                                 CIFS_MOUNT_MAP_SPECIAL_CHR);
-                        CIFSSMBClose(xid, pTcon, netfid);
-                }
+
+                        if (rc == 0 && (info_buf_source->UniqueId ==
+                                        info_buf_target->UniqueId))
+                                /* same file, POSIX says that this is a noop */
+                                goto cifs_rename_exit;
+                } /* else ... BB we could add the same check for Windows by
+                     checking the UniqueId via FILE_INTERNAL_INFO */
+unlink_target:
+                /*
+                 * we either can not tell the files are hardlinked (as with
+                 * Windows servers) or files are not hardlinked. Delete the
+                 * target manually before renaming to follow POSIX rather than
+                 * Windows semantics
+                 */
+                cifs_unlink(target_inode, target_direntry);
+                rc = cifs_do_rename(xid, source_direntry, fromName,
+                                    target_direntry, toName);
         }
 
 cifs_rename_exit:
+        kfree(info_buf_source);
         kfree(fromName);
         kfree(toName);
         FreeXid(xid);
@@ -1507,101 +1636,6 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs,
 }
 
 static int
-cifs_set_file_info(struct inode *inode, struct iattr *attrs, int xid,
-                    char *full_path, __u32 dosattr)
-{
-        int rc;
-        int oplock = 0;
-        __u16 netfid;
-        __u32 netpid;
-        bool set_time = false;
-        struct cifsFileInfo *open_file;
-        struct cifsInodeInfo *cifsInode = CIFS_I(inode);
-        struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
-        struct cifsTconInfo *pTcon = cifs_sb->tcon;
-        FILE_BASIC_INFO info_buf;
-
-        if (attrs->ia_valid & ATTR_ATIME) {
-                set_time = true;
-                info_buf.LastAccessTime =
-                        cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_atime));
-        } else
-                info_buf.LastAccessTime = 0;
-
-        if (attrs->ia_valid & ATTR_MTIME) {
-                set_time = true;
-                info_buf.LastWriteTime =
-                    cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_mtime));
-        } else
-                info_buf.LastWriteTime = 0;
-
-        /*
-         * Samba throws this field away, but windows may actually use it.
-         * Do not set ctime unless other time stamps are changed explicitly
-         * (i.e. by utimes()) since we would then have a mix of client and
-         * server times.
-         */
-        if (set_time && (attrs->ia_valid & ATTR_CTIME)) {
-                cFYI(1, ("CIFS - CTIME changed"));
-                info_buf.ChangeTime =
-                    cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_ctime));
-        } else
-                info_buf.ChangeTime = 0;
-
-        info_buf.CreationTime = 0;      /* don't change */
-        info_buf.Attributes = cpu_to_le32(dosattr);
-
-        /*
-         * If the file is already open for write, just use that fileid
-         */
-        open_file = find_writable_file(cifsInode);
-        if (open_file) {
-                netfid = open_file->netfid;
-                netpid = open_file->pid;
-                goto set_via_filehandle;
-        }
-
-        /*
-         * NT4 apparently returns success on this call, but it doesn't
-         * really work.
-         */
-        if (!(pTcon->ses->flags & CIFS_SES_NT4)) {
-                rc = CIFSSMBSetPathInfo(xid, pTcon, full_path,
-                                     &info_buf, cifs_sb->local_nls,
-                                     cifs_sb->mnt_cifs_flags &
-                                        CIFS_MOUNT_MAP_SPECIAL_CHR);
-                if (rc != -EOPNOTSUPP && rc != -EINVAL)
-                        goto out;
-        }
-
-        cFYI(1, ("calling SetFileInfo since SetPathInfo for "
-                 "times not supported by this server"));
-        rc = CIFSSMBOpen(xid, pTcon, full_path, FILE_OPEN,
-                         SYNCHRONIZE | FILE_WRITE_ATTRIBUTES,
-                         CREATE_NOT_DIR, &netfid, &oplock,
-                         NULL, cifs_sb->local_nls,
-                         cifs_sb->mnt_cifs_flags &
-                                CIFS_MOUNT_MAP_SPECIAL_CHR);
-
-        if (rc != 0) {
-                if (rc == -EIO)
-                        rc = -EINVAL;
-                goto out;
-        }
-
-        netpid = current->tgid;
-
-set_via_filehandle:
-        rc = CIFSSMBSetFileInfo(xid, pTcon, &info_buf, netfid, netpid);
-        if (open_file == NULL)
-                CIFSSMBClose(xid, pTcon, netfid);
-        else
-                atomic_dec(&open_file->wrtPending);
-out:
-        return rc;
-}
-
-static int
 cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 {
         int rc;
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 4b17f8fe3157..88786ba02d27 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -150,8 +150,7 @@ cifs_buf_get(void)
    but it may be more efficient to always alloc same size
    albeit slightly larger than necessary and maxbuffersize
    defaults to this and can not be bigger */
-        ret_buf = (struct smb_hdr *) mempool_alloc(cifs_req_poolp,
-                                                   GFP_KERNEL | GFP_NOFS);
+        ret_buf = mempool_alloc(cifs_req_poolp, GFP_NOFS);
 
         /* clear the first few header bytes */
         /* for most paths, more is cleared in header_assemble */
@@ -188,8 +187,7 @@ cifs_small_buf_get(void)
    but it may be more efficient to always alloc same size
    albeit slightly larger than necessary and maxbuffersize
    defaults to this and can not be bigger */
-        ret_buf = (struct smb_hdr *) mempool_alloc(cifs_sm_req_poolp,
-                                                   GFP_KERNEL | GFP_NOFS);
+        ret_buf = mempool_alloc(cifs_sm_req_poolp, GFP_NOFS);
         if (ret_buf) {
         /* No need to clear memory here, cleared in header assemble */
         /*      memset(ret_buf, 0, sizeof(struct smb_hdr) + 27);*/
@@ -313,8 +311,6 @@ header_assemble(struct smb_hdr *buffer, char smb_command /* command */ ,
         buffer->Flags2 = SMBFLG2_KNOWS_LONG_NAMES;
         buffer->Pid = cpu_to_le16((__u16)current->tgid);
         buffer->PidHigh = cpu_to_le16((__u16)(current->tgid >> 16));
-        spin_lock(&GlobalMid_Lock);
-        spin_unlock(&GlobalMid_Lock);
         if (treeCon) {
                 buffer->Tid = treeCon->tid;
                 if (treeCon->ses) {
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 5f40ed3473f5..765adf12d54f 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -640,6 +640,70 @@ static int is_dir_changed(struct file *file)
 
 }
 
+static int cifs_save_resume_key(const char *current_entry,
+        struct cifsFileInfo *cifsFile)
+{
+        int rc = 0;
+        unsigned int len = 0;
+        __u16 level;
+        char *filename;
+
+        if ((cifsFile == NULL) || (current_entry == NULL))
+                return -EINVAL;
+
+        level = cifsFile->srch_inf.info_level;
+
+        if (level == SMB_FIND_FILE_UNIX) {
+                FILE_UNIX_INFO *pFindData = (FILE_UNIX_INFO *)current_entry;
+
+                filename = &pFindData->FileName[0];
+                if (cifsFile->srch_inf.unicode) {
+                        len = cifs_unicode_bytelen(filename);
+                } else {
+                        /* BB should we make this strnlen of PATH_MAX? */
+                        len = strnlen(filename, PATH_MAX);
+                }
+                cifsFile->srch_inf.resume_key = pFindData->ResumeKey;
+        } else if (level == SMB_FIND_FILE_DIRECTORY_INFO) {
+                FILE_DIRECTORY_INFO *pFindData =
+                        (FILE_DIRECTORY_INFO *)current_entry;
+                filename = &pFindData->FileName[0];
+                len = le32_to_cpu(pFindData->FileNameLength);
+                cifsFile->srch_inf.resume_key = pFindData->FileIndex;
+        } else if (level == SMB_FIND_FILE_FULL_DIRECTORY_INFO) {
+                FILE_FULL_DIRECTORY_INFO *pFindData =
+                        (FILE_FULL_DIRECTORY_INFO *)current_entry;
+                filename = &pFindData->FileName[0];
+                len = le32_to_cpu(pFindData->FileNameLength);
+                cifsFile->srch_inf.resume_key = pFindData->FileIndex;
+        } else if (level == SMB_FIND_FILE_ID_FULL_DIR_INFO) {
+                SEARCH_ID_FULL_DIR_INFO *pFindData =
+                        (SEARCH_ID_FULL_DIR_INFO *)current_entry;
+                filename = &pFindData->FileName[0];
+                len = le32_to_cpu(pFindData->FileNameLength);
+                cifsFile->srch_inf.resume_key = pFindData->FileIndex;
+        } else if (level == SMB_FIND_FILE_BOTH_DIRECTORY_INFO) {
+                FILE_BOTH_DIRECTORY_INFO *pFindData =
+                        (FILE_BOTH_DIRECTORY_INFO *)current_entry;
+                filename = &pFindData->FileName[0];
+                len = le32_to_cpu(pFindData->FileNameLength);
+                cifsFile->srch_inf.resume_key = pFindData->FileIndex;
+        } else if (level == SMB_FIND_FILE_INFO_STANDARD) {
+                FIND_FILE_STANDARD_INFO *pFindData =
+                        (FIND_FILE_STANDARD_INFO *)current_entry;
+                filename = &pFindData->FileName[0];
+                /* one byte length, no name conversion */
+                len = (unsigned int)pFindData->FileNameLength;
+                cifsFile->srch_inf.resume_key = pFindData->ResumeKey;
+        } else {
+                cFYI(1, ("Unknown findfirst level %d", level));
+                return -EINVAL;
+        }
+        cifsFile->srch_inf.resume_name_len = len;
+        cifsFile->srch_inf.presume_name = filename;
+        return rc;
+}
+
 /* find the corresponding entry in the search */
 /* Note that the SMB server returns search entries for . and .. which
    complicates logic here if we choose to parse for them and we do not
@@ -703,6 +767,7 @@ static int find_cifs_entry(const int xid, struct cifsTconInfo *pTcon,
         while ((index_to_find >= cifsFile->srch_inf.index_of_last_entry) &&
               (rc == 0) && !cifsFile->srch_inf.endOfSearch) {
                 cFYI(1, ("calling findnext2"));
+                cifs_save_resume_key(cifsFile->srch_inf.last_entry, cifsFile);
                 rc = CIFSFindNext(xid, pTcon, cifsFile->netfid,
                                   &cifsFile->srch_inf);
                 if (rc)
@@ -919,69 +984,6 @@ static int cifs_filldir(char *pfindEntry, struct file *file,
         return rc;
 }
 
-static int cifs_save_resume_key(const char *current_entry,
-        struct cifsFileInfo *cifsFile)
-{
-        int rc = 0;
-        unsigned int len = 0;
-        __u16 level;
-        char *filename;
-
-        if ((cifsFile == NULL) || (current_entry == NULL))
-                return -EINVAL;
-
-        level = cifsFile->srch_inf.info_level;
-
-        if (level == SMB_FIND_FILE_UNIX) {
-                FILE_UNIX_INFO *pFindData = (FILE_UNIX_INFO *)current_entry;
-
-                filename = &pFindData->FileName[0];
-                if (cifsFile->srch_inf.unicode) {
-                        len = cifs_unicode_bytelen(filename);
-                } else {
-                        /* BB should we make this strnlen of PATH_MAX? */
-                        len = strnlen(filename, PATH_MAX);
-                }
-                cifsFile->srch_inf.resume_key = pFindData->ResumeKey;
-        } else if (level == SMB_FIND_FILE_DIRECTORY_INFO) {
-                FILE_DIRECTORY_INFO *pFindData =
-                        (FILE_DIRECTORY_INFO *)current_entry;
-                filename = &pFindData->FileName[0];
-                len = le32_to_cpu(pFindData->FileNameLength);
-                cifsFile->srch_inf.resume_key = pFindData->FileIndex;
-        } else if (level == SMB_FIND_FILE_FULL_DIRECTORY_INFO) {
-                FILE_FULL_DIRECTORY_INFO *pFindData =
-                        (FILE_FULL_DIRECTORY_INFO *)current_entry;
-                filename = &pFindData->FileName[0];
-                len = le32_to_cpu(pFindData->FileNameLength);
-                cifsFile->srch_inf.resume_key = pFindData->FileIndex;
-        } else if (level == SMB_FIND_FILE_ID_FULL_DIR_INFO) {
-                SEARCH_ID_FULL_DIR_INFO *pFindData =
-                        (SEARCH_ID_FULL_DIR_INFO *)current_entry;
-                filename = &pFindData->FileName[0];
-                len = le32_to_cpu(pFindData->FileNameLength);
-                cifsFile->srch_inf.resume_key = pFindData->FileIndex;
-        } else if (level == SMB_FIND_FILE_BOTH_DIRECTORY_INFO) {
-                FILE_BOTH_DIRECTORY_INFO *pFindData =
-                        (FILE_BOTH_DIRECTORY_INFO *)current_entry;
-                filename = &pFindData->FileName[0];
-                len = le32_to_cpu(pFindData->FileNameLength);
-                cifsFile->srch_inf.resume_key = pFindData->FileIndex;
-        } else if (level == SMB_FIND_FILE_INFO_STANDARD) {
-                FIND_FILE_STANDARD_INFO *pFindData =
-                        (FIND_FILE_STANDARD_INFO *)current_entry;
-                filename = &pFindData->FileName[0];
-                /* one byte length, no name conversion */
-                len = (unsigned int)pFindData->FileNameLength;
-                cifsFile->srch_inf.resume_key = pFindData->ResumeKey;
-        } else {
-                cFYI(1, ("Unknown findfirst level %d", level));
-                return -EINVAL;
-        }
-        cifsFile->srch_inf.resume_name_len = len;
-        cifsFile->srch_inf.presume_name = filename;
-        return rc;
-}
 
 int cifs_readdir(struct file *file, void *direntry, filldir_t filldir)
 {
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 252fdc0567f1..2851d5da0c8c 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -624,8 +624,10 @@ CIFS_SessSetup(unsigned int xid, struct cifsSesInfo *ses, int first_time,
                                          ses, nls_cp);
 
 ssetup_exit:
-        if (spnego_key)
+        if (spnego_key) {
+                key_revoke(spnego_key);
                 key_put(spnego_key);
+        }
         kfree(str_area);
         if (resp_buf_type == CIFS_SMALL_BUFFER) {
                 cFYI(1, ("ssetup freeing small buf %p", iov[0].iov_base));
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index e286db9f5ee2..bf0e6d8e382a 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -50,8 +50,7 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct cifsSesInfo *ses)
                 return NULL;
         }
 
-        temp = (struct mid_q_entry *) mempool_alloc(cifs_mid_poolp,
-                                                    GFP_KERNEL | GFP_NOFS);
+        temp = mempool_alloc(cifs_mid_poolp, GFP_NOFS);
         if (temp == NULL)
                 return temp;
         else {
diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c
index 0d9b80ec689c..cfd29da714d1 100644
--- a/fs/coda/psdev.c
+++ b/fs/coda/psdev.c
@@ -362,9 +362,8 @@ static int init_coda_psdev(void)
                 goto out_chrdev;
         }               
         for (i = 0; i < MAX_CODADEVS; i++)
-                device_create_drvdata(coda_psdev_class, NULL,
-                                      MKDEV(CODA_PSDEV_MAJOR, i),
-                                      NULL, "cfs%d", i);
+                device_create(coda_psdev_class, NULL,
+                              MKDEV(CODA_PSDEV_MAJOR, i), NULL, "cfs%d", i);
         coda_sysctl_init();
         goto out;
 
diff --git a/fs/compat.c b/fs/compat.c
index 075d0509970d..5f9ec449c799 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -137,6 +137,45 @@ asmlinkage long compat_sys_utimes(char __user *filename, struct compat_timeval _
         return compat_sys_futimesat(AT_FDCWD, filename, t);
 }
 
+static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf)
+{
+        compat_ino_t ino = stat->ino;
+        typeof(ubuf->st_uid) uid = 0;
+        typeof(ubuf->st_gid) gid = 0;
+        int err;
+
+        SET_UID(uid, stat->uid);
+        SET_GID(gid, stat->gid);
+
+        if ((u64) stat->size > MAX_NON_LFS ||
+            !old_valid_dev(stat->dev) ||
+            !old_valid_dev(stat->rdev))
+                return -EOVERFLOW;
+        if (sizeof(ino) < sizeof(stat->ino) && ino != stat->ino)
+                return -EOVERFLOW;
+
+        if (clear_user(ubuf, sizeof(*ubuf)))
+                return -EFAULT;
+
+        err  = __put_user(old_encode_dev(stat->dev), &ubuf->st_dev);
+        err |= __put_user(ino, &ubuf->st_ino);
+        err |= __put_user(stat->mode, &ubuf->st_mode);
+        err |= __put_user(stat->nlink, &ubuf->st_nlink);
+        err |= __put_user(uid, &ubuf->st_uid);
+        err |= __put_user(gid, &ubuf->st_gid);
+        err |= __put_user(old_encode_dev(stat->rdev), &ubuf->st_rdev);
+        err |= __put_user(stat->size, &ubuf->st_size);
+        err |= __put_user(stat->atime.tv_sec, &ubuf->st_atime);
+        err |= __put_user(stat->atime.tv_nsec, &ubuf->st_atime_nsec);
+        err |= __put_user(stat->mtime.tv_sec, &ubuf->st_mtime);
+        err |= __put_user(stat->mtime.tv_nsec, &ubuf->st_mtime_nsec);
+        err |= __put_user(stat->ctime.tv_sec, &ubuf->st_ctime);
+        err |= __put_user(stat->ctime.tv_nsec, &ubuf->st_ctime_nsec);
+        err |= __put_user(stat->blksize, &ubuf->st_blksize);
+        err |= __put_user(stat->blocks, &ubuf->st_blocks);
+        return err;
+}
+
 asmlinkage long compat_sys_newstat(char __user * filename,
                 struct compat_stat __user *statbuf)
 {
@@ -1239,7 +1278,7 @@ static int compat_count(compat_uptr_t __user *argv, int max)
                         if (!p)
                                 break;
                         argv++;
-                        if(++i > max)
+                        if (i++ >= max)
                                 return -E2BIG;
                 }
         }
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 08e28c9bb416..3dbe2169cf36 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -26,8 +26,7 @@
 #include <linux/debugfs.h>
 #include <linux/fsnotify.h>
 #include <linux/string.h>
-
-#define DEBUGFS_MAGIC   0x64626720
+#include <linux/magic.h>
 
 static struct vfsmount *debugfs_mount;
 static int debugfs_mount_count;
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 488eb424f662..4a714f6c1bed 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -27,6 +27,7 @@
 #define DEVPTS_SUPER_MAGIC 0x1cd1
 
 #define DEVPTS_DEFAULT_MODE 0600
+#define PTMX_MINOR      2
 
 extern int pty_limit;                   /* Config limit on Unix98 ptys */
 static DEFINE_IDA(allocated_ptys);
@@ -48,7 +49,7 @@ enum {
         Opt_err
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         {Opt_uid, "uid=%u"},
         {Opt_gid, "gid=%u"},
         {Opt_mode, "mode=%o"},
@@ -169,15 +170,7 @@ static struct file_system_type devpts_fs_type = {
  * to the System V naming convention
  */
 
-static struct dentry *get_node(int num)
-{
-        char s[12];
-        struct dentry *root = devpts_root;
-        mutex_lock(&root->d_inode->i_mutex);
-        return lookup_one_len(s, root, sprintf(s, "%d", num));
-}
-
-int devpts_new_index(void)
+int devpts_new_index(struct inode *ptmx_inode)
 {
         int index;
         int ida_ret;
@@ -205,20 +198,21 @@ retry:
         return index;
 }
 
-void devpts_kill_index(int idx)
+void devpts_kill_index(struct inode *ptmx_inode, int idx)
 {
         mutex_lock(&allocated_ptys_lock);
         ida_remove(&allocated_ptys, idx);
         mutex_unlock(&allocated_ptys_lock);
 }
 
-int devpts_pty_new(struct tty_struct *tty)
+int devpts_pty_new(struct inode *ptmx_inode, struct tty_struct *tty)
 {
         int number = tty->index; /* tty layer puts index from devpts_new_index() in here */
         struct tty_driver *driver = tty->driver;
         dev_t device = MKDEV(driver->major, driver->minor_start+number);
         struct dentry *dentry;
         struct inode *inode = new_inode(devpts_mnt->mnt_sb);
+        char s[12];
 
         /* We're supposed to be given the slave end of a pty */
         BUG_ON(driver->type != TTY_DRIVER_TYPE_PTY);
@@ -233,10 +227,15 @@ int devpts_pty_new(struct tty_struct *tty)
         inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
         init_special_inode(inode, S_IFCHR|config.mode, device);
         inode->i_private = tty;
+        tty->driver_data = inode;
 
-        dentry = get_node(number);
-        if (!IS_ERR(dentry) && !dentry->d_inode) {
-                d_instantiate(dentry, inode);
+        sprintf(s, "%d", number);
+
+        mutex_lock(&devpts_root->d_inode->i_mutex);
+
+        dentry = d_alloc_name(devpts_root, s);
+        if (!IS_ERR(dentry)) {
+                d_add(dentry, inode);
                 fsnotify_create(devpts_root->d_inode, dentry);
         }
 
@@ -245,36 +244,31 @@ int devpts_pty_new(struct tty_struct *tty)
         return 0;
 }
 
-struct tty_struct *devpts_get_tty(int number)
+struct tty_struct *devpts_get_tty(struct inode *pts_inode, int number)
 {
-        struct dentry *dentry = get_node(number);
-        struct tty_struct *tty;
-
-        tty = NULL;
-        if (!IS_ERR(dentry)) {
-                if (dentry->d_inode)
-                        tty = dentry->d_inode->i_private;
-                dput(dentry);
-        }
+        BUG_ON(pts_inode->i_rdev == MKDEV(TTYAUX_MAJOR, PTMX_MINOR));
 
-        mutex_unlock(&devpts_root->d_inode->i_mutex);
-
-        return tty;
+        if (pts_inode->i_sb->s_magic == DEVPTS_SUPER_MAGIC)
+                return (struct tty_struct *)pts_inode->i_private;
+        return NULL;
 }
 
-void devpts_pty_kill(int number)
+void devpts_pty_kill(struct tty_struct *tty)
 {
-        struct dentry *dentry = get_node(number);
+        struct inode *inode = tty->driver_data;
+        struct dentry *dentry;
 
-        if (!IS_ERR(dentry)) {
-                struct inode *inode = dentry->d_inode;
-                if (inode) {
-                        inode->i_nlink--;
-                        d_delete(dentry);
-                        dput(dentry);
-                }
+        BUG_ON(inode->i_rdev == MKDEV(TTYAUX_MAJOR, PTMX_MINOR));
+
+        mutex_lock(&devpts_root->d_inode->i_mutex);
+
+        dentry = d_find_alias(inode);
+        if (dentry && !IS_ERR(dentry)) {
+                inode->i_nlink--;
+                d_delete(dentry);
                 dput(dentry);
         }
+
         mutex_unlock(&devpts_root->d_inode->i_mutex);
 }
 
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 9606ee848fd8..af0558dbe8b7 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -5,11 +5,11 @@
  *
  * O_DIRECT
  *
- * 04Jul2002    akpm@zip.com.au
+ * 04Jul2002    Andrew Morton
  *              Initial version
  * 11Sep2002    janetinc@us.ibm.com
  *              added readv/writev support.
- * 29Oct2002    akpm@zip.com.au
+ * 29Oct2002    Andrew Morton
  *              rewrote bio_add_page() support.
  * 30Oct2002    pbadari@us.ibm.com
  *              added support for non-aligned IO.
diff --git a/fs/dlm/config.c b/fs/dlm/config.c
index 89d2fb7b991a..fd9859f92fad 100644
--- a/fs/dlm/config.c
+++ b/fs/dlm/config.c
@@ -14,6 +14,9 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/configfs.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <net/ipv6.h>
 #include <net/sock.h>
 
 #include "config.h"
@@ -377,24 +380,24 @@ static struct config_item_type node_type = {
         .ct_owner = THIS_MODULE,
 };
 
-static struct dlm_cluster *to_cluster(struct config_item *i)
+static struct dlm_cluster *config_item_to_cluster(struct config_item *i)
 {
         return i ? container_of(to_config_group(i), struct dlm_cluster, group) :
                    NULL;
 }
 
-static struct dlm_space *to_space(struct config_item *i)
+static struct dlm_space *config_item_to_space(struct config_item *i)
 {
         return i ? container_of(to_config_group(i), struct dlm_space, group) :
                    NULL;
 }
 
-static struct dlm_comm *to_comm(struct config_item *i)
+static struct dlm_comm *config_item_to_comm(struct config_item *i)
 {
         return i ? container_of(i, struct dlm_comm, item) : NULL;
 }
 
-static struct dlm_node *to_node(struct config_item *i)
+static struct dlm_node *config_item_to_node(struct config_item *i)
 {
         return i ? container_of(i, struct dlm_node, item) : NULL;
 }
@@ -450,7 +453,7 @@ static struct config_group *make_cluster(struct config_group *g,
 
 static void drop_cluster(struct config_group *g, struct config_item *i)
 {
-        struct dlm_cluster *cl = to_cluster(i);
+        struct dlm_cluster *cl = config_item_to_cluster(i);
         struct config_item *tmp;
         int j;
 
@@ -468,7 +471,7 @@ static void drop_cluster(struct config_group *g, struct config_item *i)
 
 static void release_cluster(struct config_item *i)
 {
-        struct dlm_cluster *cl = to_cluster(i);
+        struct dlm_cluster *cl = config_item_to_cluster(i);
         kfree(cl->group.default_groups);
         kfree(cl);
 }
@@ -507,7 +510,7 @@ static struct config_group *make_space(struct config_group *g, const char *name)
 
 static void drop_space(struct config_group *g, struct config_item *i)
 {
-        struct dlm_space *sp = to_space(i);
+        struct dlm_space *sp = config_item_to_space(i);
         struct config_item *tmp;
         int j;
 
@@ -524,7 +527,7 @@ static void drop_space(struct config_group *g, struct config_item *i)
 
 static void release_space(struct config_item *i)
 {
-        struct dlm_space *sp = to_space(i);
+        struct dlm_space *sp = config_item_to_space(i);
         kfree(sp->group.default_groups);
         kfree(sp);
 }
@@ -546,7 +549,7 @@ static struct config_item *make_comm(struct config_group *g, const char *name)
 
 static void drop_comm(struct config_group *g, struct config_item *i)
 {
-        struct dlm_comm *cm = to_comm(i);
+        struct dlm_comm *cm = config_item_to_comm(i);
         if (local_comm == cm)
                 local_comm = NULL;
         dlm_lowcomms_close(cm->nodeid);
@@ -557,13 +560,13 @@ static void drop_comm(struct config_group *g, struct config_item *i)
 
 static void release_comm(struct config_item *i)
 {
-        struct dlm_comm *cm = to_comm(i);
+        struct dlm_comm *cm = config_item_to_comm(i);
         kfree(cm);
 }
 
 static struct config_item *make_node(struct config_group *g, const char *name)
 {
-        struct dlm_space *sp = to_space(g->cg_item.ci_parent);
+        struct dlm_space *sp = config_item_to_space(g->cg_item.ci_parent);
         struct dlm_node *nd;
 
         nd = kzalloc(sizeof(struct dlm_node), GFP_KERNEL);
@@ -585,8 +588,8 @@ static struct config_item *make_node(struct config_group *g, const char *name)
 
 static void drop_node(struct config_group *g, struct config_item *i)
 {
-        struct dlm_space *sp = to_space(g->cg_item.ci_parent);
-        struct dlm_node *nd = to_node(i);
+        struct dlm_space *sp = config_item_to_space(g->cg_item.ci_parent);
+        struct dlm_node *nd = config_item_to_node(i);
 
         mutex_lock(&sp->members_lock);
         list_del(&nd->list);
@@ -598,7 +601,7 @@ static void drop_node(struct config_group *g, struct config_item *i)
 
 static void release_node(struct config_item *i)
 {
-        struct dlm_node *nd = to_node(i);
+        struct dlm_node *nd = config_item_to_node(i);
         kfree(nd);
 }
 
@@ -632,7 +635,7 @@ void dlm_config_exit(void)
 static ssize_t show_cluster(struct config_item *i, struct configfs_attribute *a,
                             char *buf)
 {
-        struct dlm_cluster *cl = to_cluster(i);
+        struct dlm_cluster *cl = config_item_to_cluster(i);
         struct cluster_attribute *cla =
                         container_of(a, struct cluster_attribute, attr);
         return cla->show ? cla->show(cl, buf) : 0;
@@ -642,7 +645,7 @@ static ssize_t store_cluster(struct config_item *i,
                              struct configfs_attribute *a,
                              const char *buf, size_t len)
 {
-        struct dlm_cluster *cl = to_cluster(i);
+        struct dlm_cluster *cl = config_item_to_cluster(i);
         struct cluster_attribute *cla =
                 container_of(a, struct cluster_attribute, attr);
         return cla->store ? cla->store(cl, buf, len) : -EINVAL;
@@ -651,7 +654,7 @@ static ssize_t store_cluster(struct config_item *i,
 static ssize_t show_comm(struct config_item *i, struct configfs_attribute *a,
                          char *buf)
 {
-        struct dlm_comm *cm = to_comm(i);
+        struct dlm_comm *cm = config_item_to_comm(i);
         struct comm_attribute *cma =
                         container_of(a, struct comm_attribute, attr);
         return cma->show ? cma->show(cm, buf) : 0;
@@ -660,7 +663,7 @@ static ssize_t show_comm(struct config_item *i, struct configfs_attribute *a,
 static ssize_t store_comm(struct config_item *i, struct configfs_attribute *a,
                           const char *buf, size_t len)
 {
-        struct dlm_comm *cm = to_comm(i);
+        struct dlm_comm *cm = config_item_to_comm(i);
         struct comm_attribute *cma =
                 container_of(a, struct comm_attribute, attr);
         return cma->store ? cma->store(cm, buf, len) : -EINVAL;
@@ -714,7 +717,7 @@ static ssize_t comm_addr_write(struct dlm_comm *cm, const char *buf, size_t len)
 static ssize_t show_node(struct config_item *i, struct configfs_attribute *a,
                          char *buf)
 {
-        struct dlm_node *nd = to_node(i);
+        struct dlm_node *nd = config_item_to_node(i);
         struct node_attribute *nda =
                         container_of(a, struct node_attribute, attr);
         return nda->show ? nda->show(nd, buf) : 0;
@@ -723,7 +726,7 @@ static ssize_t show_node(struct config_item *i, struct configfs_attribute *a,
 static ssize_t store_node(struct config_item *i, struct configfs_attribute *a,
                           const char *buf, size_t len)
 {
-        struct dlm_node *nd = to_node(i);
+        struct dlm_node *nd = config_item_to_node(i);
         struct node_attribute *nda =
                 container_of(a, struct node_attribute, attr);
         return nda->store ? nda->store(nd, buf, len) : -EINVAL;
@@ -768,7 +771,7 @@ static struct dlm_space *get_space(char *name)
         i = config_group_find_item(space_list, name);
         mutex_unlock(&space_list->cg_subsys->su_mutex);
 
-        return to_space(i);
+        return config_item_to_space(i);
 }
 
 static void put_space(struct dlm_space *sp)
@@ -776,6 +779,33 @@ static void put_space(struct dlm_space *sp)
         config_item_put(&sp->group.cg_item);
 }
 
+static int addr_compare(struct sockaddr_storage *x, struct sockaddr_storage *y)
+{
+        switch (x->ss_family) {
+        case AF_INET: {
+                struct sockaddr_in *sinx = (struct sockaddr_in *)x;
+                struct sockaddr_in *siny = (struct sockaddr_in *)y;
+                if (sinx->sin_addr.s_addr != siny->sin_addr.s_addr)
+                        return 0;
+                if (sinx->sin_port != siny->sin_port)
+                        return 0;
+                break;
+        }
+        case AF_INET6: {
+                struct sockaddr_in6 *sinx = (struct sockaddr_in6 *)x;
+                struct sockaddr_in6 *siny = (struct sockaddr_in6 *)y;
+                if (!ipv6_addr_equal(&sinx->sin6_addr, &siny->sin6_addr))
+                        return 0;
+                if (sinx->sin6_port != siny->sin6_port)
+                        return 0;
+                break;
+        }
+        default:
+                return 0;
+        }
+        return 1;
+}
+
 static struct dlm_comm *get_comm(int nodeid, struct sockaddr_storage *addr)
 {
         struct config_item *i;
@@ -788,7 +818,7 @@ static struct dlm_comm *get_comm(int nodeid, struct sockaddr_storage *addr)
         mutex_lock(&clusters_root.subsys.su_mutex);
 
         list_for_each_entry(i, &comm_list->cg_children, ci_entry) {
-                cm = to_comm(i);
+                cm = config_item_to_comm(i);
 
                 if (nodeid) {
                         if (cm->nodeid != nodeid)
@@ -797,8 +827,7 @@ static struct dlm_comm *get_comm(int nodeid, struct sockaddr_storage *addr)
                         config_item_get(i);
                         break;
                 } else {
-                        if (!cm->addr_count ||
-                            memcmp(cm->addr[0], addr, sizeof(*addr)))
+                        if (!cm->addr_count || !addr_compare(cm->addr[0], addr))
                                 continue;
                         found = 1;
                         config_item_get(i);
diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h
index 5a7ac33b629c..868e4c9ef127 100644
--- a/fs/dlm/dlm_internal.h
+++ b/fs/dlm/dlm_internal.h
@@ -2,7 +2,7 @@
 *******************************************************************************
 **
 **  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
-**  Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
+**  Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
 **
 **  This copyrighted material is made available to anyone wishing to use,
 **  modify, copy, or redistribute it subject to the terms and conditions
@@ -441,8 +441,11 @@ struct dlm_ls {
         uint32_t                ls_global_id;   /* global unique lockspace ID */
         uint32_t                ls_exflags;
         int                     ls_lvblen;
-        int                     ls_count;       /* reference count */
+        int                     ls_count;       /* refcount of processes in
+                                                   the dlm using this ls */
+        int                     ls_create_count; /* create/release refcount */
         unsigned long           ls_flags;       /* LSFL_ */
+        unsigned long           ls_scan_time;
         struct kobject          ls_kobj;
 
         struct dlm_rsbtable     *ls_rsbtbl;
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index 499e16759e96..d910501de6d2 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -2,7 +2,7 @@
 *******************************************************************************
 **
 **  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
-**  Copyright (C) 2004-2007 Red Hat, Inc.  All rights reserved.
+**  Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
 **
 **  This copyrighted material is made available to anyone wishing to use,
 **  modify, copy, or redistribute it subject to the terms and conditions
@@ -23,6 +23,7 @@
 #include "lock.h"
 #include "recover.h"
 #include "requestqueue.h"
+#include "user.h"
 
 static int                      ls_count;
 static struct mutex             ls_lock;
@@ -211,19 +212,41 @@ void dlm_lockspace_exit(void)
         kset_unregister(dlm_kset);
 }
 
+static struct dlm_ls *find_ls_to_scan(void)
+{
+        struct dlm_ls *ls;
+
+        spin_lock(&lslist_lock);
+        list_for_each_entry(ls, &lslist, ls_list) {
+                if (time_after_eq(jiffies, ls->ls_scan_time +
+                                            dlm_config.ci_scan_secs * HZ)) {
+                        spin_unlock(&lslist_lock);
+                        return ls;
+                }
+        }
+        spin_unlock(&lslist_lock);
+        return NULL;
+}
+
 static int dlm_scand(void *data)
 {
         struct dlm_ls *ls;
+        int timeout_jiffies = dlm_config.ci_scan_secs * HZ;
 
         while (!kthread_should_stop()) {
-                list_for_each_entry(ls, &lslist, ls_list) {
+                ls = find_ls_to_scan();
+                if (ls) {
                         if (dlm_lock_recovery_try(ls)) {
+                                ls->ls_scan_time = jiffies;
                                 dlm_scan_rsbs(ls);
                                 dlm_scan_timeout(ls);
                                 dlm_unlock_recovery(ls);
+                        } else {
+                                ls->ls_scan_time += HZ;
                         }
+                } else {
+                        schedule_timeout_interruptible(timeout_jiffies);
                 }
-                schedule_timeout_interruptible(dlm_config.ci_scan_secs * HZ);
         }
         return 0;
 }
@@ -246,23 +269,6 @@ static void dlm_scand_stop(void)
         kthread_stop(scand_task);
 }
 
-static struct dlm_ls *dlm_find_lockspace_name(char *name, int namelen)
-{
-        struct dlm_ls *ls;
-
-        spin_lock(&lslist_lock);
-
-        list_for_each_entry(ls, &lslist, ls_list) {
-                if (ls->ls_namelen == namelen &&
-                    memcmp(ls->ls_name, name, namelen) == 0)
-                        goto out;
-        }
-        ls = NULL;
- out:
-        spin_unlock(&lslist_lock);
-        return ls;
-}
-
 struct dlm_ls *dlm_find_lockspace_global(uint32_t id)
 {
         struct dlm_ls *ls;
@@ -327,6 +333,7 @@ static void remove_lockspace(struct dlm_ls *ls)
         for (;;) {
                 spin_lock(&lslist_lock);
                 if (ls->ls_count == 0) {
+                        WARN_ON(ls->ls_create_count != 0);
                         list_del(&ls->ls_list);
                         spin_unlock(&lslist_lock);
                         return;
@@ -381,7 +388,7 @@ static int new_lockspace(char *name, int namelen, void **lockspace,
                          uint32_t flags, int lvblen)
 {
         struct dlm_ls *ls;
-        int i, size, error = -ENOMEM;
+        int i, size, error;
         int do_unreg = 0;
 
         if (namelen > DLM_LOCKSPACE_LEN)
@@ -393,12 +400,37 @@ static int new_lockspace(char *name, int namelen, void **lockspace,
         if (!try_module_get(THIS_MODULE))
                 return -EINVAL;
 
-        ls = dlm_find_lockspace_name(name, namelen);
-        if (ls) {
-                *lockspace = ls;
+        if (!dlm_user_daemon_available()) {
+                module_put(THIS_MODULE);
+                return -EUNATCH;
+        }
+
+        error = 0;
+
+        spin_lock(&lslist_lock);
+        list_for_each_entry(ls, &lslist, ls_list) {
+                WARN_ON(ls->ls_create_count <= 0);
+                if (ls->ls_namelen != namelen)
+                        continue;
+                if (memcmp(ls->ls_name, name, namelen))
+                        continue;
+                if (flags & DLM_LSFL_NEWEXCL) {
+                        error = -EEXIST;
+                        break;
+                }
+                ls->ls_create_count++;
                 module_put(THIS_MODULE);
-                return -EEXIST;
+                error = 1; /* not an error, return 0 */
+                break;
         }
+        spin_unlock(&lslist_lock);
+
+        if (error < 0)
+                goto out;
+        if (error)
+                goto ret_zero;
+
+        error = -ENOMEM;
 
         ls = kzalloc(sizeof(struct dlm_ls) + namelen, GFP_KERNEL);
         if (!ls)
@@ -408,6 +440,7 @@ static int new_lockspace(char *name, int namelen, void **lockspace,
         ls->ls_lvblen = lvblen;
         ls->ls_count = 0;
         ls->ls_flags = 0;
+        ls->ls_scan_time = jiffies;
 
         if (flags & DLM_LSFL_TIMEWARN)
                 set_bit(LSFL_TIMEWARN, &ls->ls_flags);
@@ -418,8 +451,9 @@ static int new_lockspace(char *name, int namelen, void **lockspace,
                 ls->ls_allocation = GFP_KERNEL;
 
         /* ls_exflags are forced to match among nodes, and we don't
-           need to require all nodes to have TIMEWARN or FS set */
-        ls->ls_exflags = (flags & ~(DLM_LSFL_TIMEWARN | DLM_LSFL_FS));
+           need to require all nodes to have some flags set */
+        ls->ls_exflags = (flags & ~(DLM_LSFL_TIMEWARN | DLM_LSFL_FS |
+                                    DLM_LSFL_NEWEXCL));
 
         size = dlm_config.ci_rsbtbl_size;
         ls->ls_rsbtbl_size = size;
@@ -510,6 +544,7 @@ static int new_lockspace(char *name, int namelen, void **lockspace,
         down_write(&ls->ls_in_recovery);
 
         spin_lock(&lslist_lock);
+        ls->ls_create_count = 1;
         list_add(&ls->ls_list, &lslist);
         spin_unlock(&lslist_lock);
 
@@ -548,7 +583,7 @@ static int new_lockspace(char *name, int namelen, void **lockspace,
         dlm_create_debug_file(ls);
 
         log_debug(ls, "join complete");
-
+ ret_zero:
         *lockspace = ls;
         return 0;
 
@@ -635,13 +670,34 @@ static int release_lockspace(struct dlm_ls *ls, int force)
         struct dlm_lkb *lkb;
         struct dlm_rsb *rsb;
         struct list_head *head;
-        int i;
-        int busy = lockspace_busy(ls);
+        int i, busy, rv;
+
+        busy = lockspace_busy(ls);
+
+        spin_lock(&lslist_lock);
+        if (ls->ls_create_count == 1) {
+                if (busy > force)
+                        rv = -EBUSY;
+                else {
+                        /* remove_lockspace takes ls off lslist */
+                        ls->ls_create_count = 0;
+                        rv = 0;
+                }
+        } else if (ls->ls_create_count > 1) {
+                rv = --ls->ls_create_count;
+        } else {
+                rv = -EINVAL;
+        }
+        spin_unlock(&lslist_lock);
 
-        if (busy > force)
-                return -EBUSY;
+        if (rv) {
+                log_debug(ls, "release_lockspace no remove %d", rv);
+                return rv;
+        }
+
+        dlm_device_deregister(ls);
 
-        if (force < 3)
+        if (force < 3 && dlm_user_daemon_available())
                 do_uevent(ls, 0);
 
         dlm_recoverd_stop(ls);
@@ -720,15 +776,10 @@ static int release_lockspace(struct dlm_ls *ls, int force)
         dlm_clear_members(ls);
         dlm_clear_members_gone(ls);
         kfree(ls->ls_node_array);
+        log_debug(ls, "release_lockspace final free");
         kobject_put(&ls->ls_kobj);
         /* The ls structure will be freed when the kobject is done with */
 
-        mutex_lock(&ls_lock);
-        ls_count--;
-        if (!ls_count)
-                threads_stop();
-        mutex_unlock(&ls_lock);
-
         module_put(THIS_MODULE);
         return 0;
 }
@@ -750,11 +801,38 @@ static int release_lockspace(struct dlm_ls *ls, int force)
 int dlm_release_lockspace(void *lockspace, int force)
 {
         struct dlm_ls *ls;
+        int error;
 
         ls = dlm_find_lockspace_local(lockspace);
         if (!ls)
                 return -EINVAL;
         dlm_put_lockspace(ls);
-        return release_lockspace(ls, force);
+
+        mutex_lock(&ls_lock);
+        error = release_lockspace(ls, force);
+        if (!error)
+                ls_count--;
+        else if (!ls_count)
+                threads_stop();
+        mutex_unlock(&ls_lock);
+
+        return error;
+}
+
+void dlm_stop_lockspaces(void)
+{
+        struct dlm_ls *ls;
+
+ restart:
+        spin_lock(&lslist_lock);
+        list_for_each_entry(ls, &lslist, ls_list) {
+                if (!test_bit(LSFL_RUNNING, &ls->ls_flags))
+                        continue;
+                spin_unlock(&lslist_lock);
+                log_error(ls, "no userland control daemon, stopping lockspace");
+                dlm_ls_stop(ls);
+                goto restart;
+        }
+        spin_unlock(&lslist_lock);
 }
 
diff --git a/fs/dlm/lockspace.h b/fs/dlm/lockspace.h
index 891eabbdd021..f879f87901f8 100644
--- a/fs/dlm/lockspace.h
+++ b/fs/dlm/lockspace.h
@@ -20,6 +20,7 @@ struct dlm_ls *dlm_find_lockspace_global(uint32_t id);
 struct dlm_ls *dlm_find_lockspace_local(void *id);
 struct dlm_ls *dlm_find_lockspace_device(int minor);
 void dlm_put_lockspace(struct dlm_ls *ls);
+void dlm_stop_lockspaces(void);
 
 #endif                          /* __LOCKSPACE_DOT_H__ */
 
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index 34f14a14fb4e..b3832c67194a 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2006-2007 Red Hat, Inc.  All rights reserved.
+ * Copyright (C) 2006-2008 Red Hat, Inc.  All rights reserved.
  *
  * This copyrighted material is made available to anyone wishing to use,
  * modify, copy, or redistribute it subject to the terms and conditions
@@ -15,7 +15,6 @@
 #include <linux/poll.h>
 #include <linux/signal.h>
 #include <linux/spinlock.h>
-#include <linux/smp_lock.h>
 #include <linux/dlm.h>
 #include <linux/dlm_device.h>
 
@@ -27,6 +26,8 @@
 
 static const char name_prefix[] = "dlm";
 static const struct file_operations device_fops;
+static atomic_t dlm_monitor_opened;
+static int dlm_monitor_unused = 1;
 
 #ifdef CONFIG_COMPAT
 
@@ -340,10 +341,15 @@ static int device_user_deadlock(struct dlm_user_proc *proc,
         return error;
 }
 
-static int create_misc_device(struct dlm_ls *ls, char *name)
+static int dlm_device_register(struct dlm_ls *ls, char *name)
 {
         int error, len;
 
+        /* The device is already registered.  This happens when the
+           lockspace is created multiple times from userspace. */
+        if (ls->ls_device.name)
+                return 0;
+
         error = -ENOMEM;
         len = strlen(name) + strlen(name_prefix) + 2;
         ls->ls_device.name = kzalloc(len, GFP_KERNEL);
@@ -363,6 +369,22 @@ fail:
         return error;
 }
 
+int dlm_device_deregister(struct dlm_ls *ls)
+{
+        int error;
+
+        /* The device is not registered.  This happens when the lockspace
+           was never used from userspace, or when device_create_lockspace()
+           calls dlm_release_lockspace() after the register fails. */
+        if (!ls->ls_device.name)
+                return 0;
+
+        error = misc_deregister(&ls->ls_device);
+        if (!error)
+                kfree(ls->ls_device.name);
+        return error;
+}
+
 static int device_user_purge(struct dlm_user_proc *proc,
                              struct dlm_purge_params *params)
 {
@@ -397,7 +419,7 @@ static int device_create_lockspace(struct dlm_lspace_params *params)
         if (!ls)
                 return -ENOENT;
 
-        error = create_misc_device(ls, params->name);
+        error = dlm_device_register(ls, params->name);
         dlm_put_lockspace(ls);
 
         if (error)
@@ -421,31 +443,22 @@ static int device_remove_lockspace(struct dlm_lspace_params *params)
         if (!ls)
                 return -ENOENT;
 
-        /* Deregister the misc device first, so we don't have
-         * a device that's not attached to a lockspace. If
-         * dlm_release_lockspace fails then we can recreate it
-         */
-        error = misc_deregister(&ls->ls_device);
-        if (error) {
-                dlm_put_lockspace(ls);
-                goto out;
-        }
-        kfree(ls->ls_device.name);
-
         if (params->flags & DLM_USER_LSFLG_FORCEFREE)
                 force = 2;
 
         lockspace = ls->ls_local_handle;
+        dlm_put_lockspace(ls);
 
-        /* dlm_release_lockspace waits for references to go to zero,
-           so all processes will need to close their device for the ls
-           before the release will procede */
+        /* The final dlm_release_lockspace waits for references to go to
+           zero, so all processes will need to close their device for the
+           ls before the release will proceed.  release also calls the
+           device_deregister above.  Converting a positive return value
+           from release to zero means that userspace won't know when its
+           release was the final one, but it shouldn't need to know. */
 
-        dlm_put_lockspace(ls);
         error = dlm_release_lockspace(lockspace, force);
-        if (error)
-                create_misc_device(ls, ls->ls_name);
- out:
+        if (error > 0)
+                error = 0;
         return error;
 }
 
@@ -623,17 +636,13 @@ static int device_open(struct inode *inode, struct file *file)
         struct dlm_user_proc *proc;
         struct dlm_ls *ls;
 
-        lock_kernel();
         ls = dlm_find_lockspace_device(iminor(inode));
-        if (!ls) {
-                unlock_kernel();
+        if (!ls)
                 return -ENOENT;
-        }
 
         proc = kzalloc(sizeof(struct dlm_user_proc), GFP_KERNEL);
         if (!proc) {
                 dlm_put_lockspace(ls);
-                unlock_kernel();
                 return -ENOMEM;
         }
 
@@ -645,7 +654,6 @@ static int device_open(struct inode *inode, struct file *file)
         spin_lock_init(&proc->locks_spin);
         init_waitqueue_head(&proc->wait);
         file->private_data = proc;
-        unlock_kernel();
 
         return 0;
 }
@@ -878,9 +886,28 @@ static unsigned int device_poll(struct file *file, poll_table *wait)
         return 0;
 }
 
+int dlm_user_daemon_available(void)
+{
+        /* dlm_controld hasn't started (or, has started, but not
+           properly populated configfs) */
+
+        if (!dlm_our_nodeid())
+                return 0;
+
+        /* This is to deal with versions of dlm_controld that don't
+           know about the monitor device.  We assume that if the
+           dlm_controld was started (above), but the monitor device
+           was never opened, that it's an old version.  dlm_controld
+           should open the monitor device before populating configfs. */
+
+        if (dlm_monitor_unused)
+                return 1;
+
+        return atomic_read(&dlm_monitor_opened) ? 1 : 0;
+}
+
 static int ctl_device_open(struct inode *inode, struct file *file)
 {
-        cycle_kernel_lock();
         file->private_data = NULL;
         return 0;
 }
@@ -890,6 +917,20 @@ static int ctl_device_close(struct inode *inode, struct file *file)
         return 0;
 }
 
+static int monitor_device_open(struct inode *inode, struct file *file)
+{
+        atomic_inc(&dlm_monitor_opened);
+        dlm_monitor_unused = 0;
+        return 0;
+}
+
+static int monitor_device_close(struct inode *inode, struct file *file)
+{
+        if (atomic_dec_and_test(&dlm_monitor_opened))
+                dlm_stop_lockspaces();
+        return 0;
+}
+
 static const struct file_operations device_fops = {
         .open    = device_open,
         .release = device_close,
@@ -913,19 +954,42 @@ static struct miscdevice ctl_device = {
         .minor = MISC_DYNAMIC_MINOR,
 };
 
+static const struct file_operations monitor_device_fops = {
+        .open    = monitor_device_open,
+        .release = monitor_device_close,
+        .owner   = THIS_MODULE,
+};
+
+static struct miscdevice monitor_device = {
+        .name  = "dlm-monitor",
+        .fops  = &monitor_device_fops,
+        .minor = MISC_DYNAMIC_MINOR,
+};
+
 int __init dlm_user_init(void)
 {
         int error;
 
+        atomic_set(&dlm_monitor_opened, 0);
+
         error = misc_register(&ctl_device);
-        if (error)
+        if (error) {
                 log_print("misc_register failed for control device");
+                goto out;
+        }
 
+        error = misc_register(&monitor_device);
+        if (error) {
+                log_print("misc_register failed for monitor device");
+                misc_deregister(&ctl_device);
+        }
+ out:
         return error;
 }
 
 void dlm_user_exit(void)
 {
         misc_deregister(&ctl_device);
+        misc_deregister(&monitor_device);
 }
 
diff --git a/fs/dlm/user.h b/fs/dlm/user.h
index d38e9f3e4151..35eb6a13d616 100644
--- a/fs/dlm/user.h
+++ b/fs/dlm/user.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2006 Red Hat, Inc.  All rights reserved.
+ * Copyright (C) 2006-2008 Red Hat, Inc.  All rights reserved.
  *
  * This copyrighted material is made available to anyone wishing to use,
  * modify, copy, or redistribute it subject to the terms and conditions
@@ -12,5 +12,7 @@
 void dlm_user_add_ast(struct dlm_lkb *lkb, int type);
 int dlm_user_init(void);
 void dlm_user_exit(void);
+int dlm_device_deregister(struct dlm_ls *ls);
+int dlm_user_daemon_available(void);
 
 #endif
diff --git a/fs/dquot.c b/fs/dquot.c
index 8ec4d6cc7633..da30a27f2242 100644
--- a/fs/dquot.c
+++ b/fs/dquot.c
@@ -9,8 +9,6 @@
  * implementation is based on one of the several variants of the LINUX
  * inode-subsystem with added complexity of the diskquota system.
  * 
- * Version: $Id: dquot.c,v 6.3 1996/11/17 18:35:34 mvw Exp mvw $
- * 
  * Author:      Marco van Wieringen <mvw@planets.elm.net>
  *
  * Fixes:   Dmitry Gorodchanin <pgmdsg@ibi.com>, 11 Feb 96
@@ -895,10 +893,9 @@ static void print_warning(struct dquot *dquot, const int warntype)
             warntype == QUOTA_NL_BSOFTBELOW || !need_print_warning(dquot))
                 return;
 
-        mutex_lock(&tty_mutex);
         tty = get_current_tty();
         if (!tty)
-                goto out_lock;
+                return;
         tty_write_message(tty, dquot->dq_sb->s_id);
         if (warntype == QUOTA_NL_ISOFTWARN || warntype == QUOTA_NL_BSOFTWARN)
                 tty_write_message(tty, ": warning, ");
@@ -926,8 +923,7 @@ static void print_warning(struct dquot *dquot, const int warntype)
                         break;
         }
         tty_write_message(tty, msg);
-out_lock:
-        mutex_unlock(&tty_mutex);
+        tty_kref_put(tty);
 }
 #endif
 
diff --git a/fs/ecryptfs/Makefile b/fs/ecryptfs/Makefile
index b4755a85996e..2cc9ee4ad2eb 100644
--- a/fs/ecryptfs/Makefile
+++ b/fs/ecryptfs/Makefile
@@ -4,4 +4,4 @@
 
 obj-$(CONFIG_ECRYPT_FS) += ecryptfs.o
 
-ecryptfs-objs := dentry.o file.o inode.o main.o super.o mmap.o read_write.o crypto.o keystore.o messaging.o netlink.o miscdev.o kthread.o debug.o
+ecryptfs-objs := dentry.o file.o inode.o main.o super.o mmap.o read_write.o crypto.o keystore.o messaging.o miscdev.o kthread.o debug.o
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index b73fb752c5f8..3504cf9df358 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -79,11 +79,6 @@
 #define ECRYPTFS_MAX_PKI_NAME_BYTES 16
 #define ECRYPTFS_DEFAULT_NUM_USERS 4
 #define ECRYPTFS_MAX_NUM_USERS 32768
-#define ECRYPTFS_TRANSPORT_NETLINK 0
-#define ECRYPTFS_TRANSPORT_CONNECTOR 1
-#define ECRYPTFS_TRANSPORT_RELAYFS 2
-#define ECRYPTFS_TRANSPORT_MISCDEV 3
-#define ECRYPTFS_DEFAULT_TRANSPORT ECRYPTFS_TRANSPORT_MISCDEV
 #define ECRYPTFS_XATTR_NAME "user.ecryptfs"
 
 #define RFC2440_CIPHER_DES3_EDE 0x02
@@ -400,8 +395,6 @@ struct ecryptfs_msg_ctx {
         struct mutex mux;
 };
 
-extern unsigned int ecryptfs_transport;
-
 struct ecryptfs_daemon;
 
 struct ecryptfs_daemon {
@@ -627,31 +620,20 @@ int
 ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
                   size_t size, int flags);
 int ecryptfs_read_xattr_region(char *page_virt, struct inode *ecryptfs_inode);
-int ecryptfs_process_helo(unsigned int transport, uid_t euid,
-                          struct user_namespace *user_ns, struct pid *pid);
+int ecryptfs_process_helo(uid_t euid, struct user_namespace *user_ns,
+                          struct pid *pid);
 int ecryptfs_process_quit(uid_t euid, struct user_namespace *user_ns,
                           struct pid *pid);
 int ecryptfs_process_response(struct ecryptfs_message *msg, uid_t euid,
                               struct user_namespace *user_ns, struct pid *pid,
                               u32 seq);
-int ecryptfs_send_message(unsigned int transport, char *data, int data_len,
+int ecryptfs_send_message(char *data, int data_len,
                           struct ecryptfs_msg_ctx **msg_ctx);
 int ecryptfs_wait_for_response(struct ecryptfs_msg_ctx *msg_ctx,
                                struct ecryptfs_message **emsg);
-int ecryptfs_init_messaging(unsigned int transport);
-void ecryptfs_release_messaging(unsigned int transport);
+int ecryptfs_init_messaging(void);
+void ecryptfs_release_messaging(void);
 
-int ecryptfs_send_netlink(char *data, int data_len,
-                          struct ecryptfs_msg_ctx *msg_ctx, u8 msg_type,
-                          u16 msg_flags, struct pid *daemon_pid);
-int ecryptfs_init_netlink(void);
-void ecryptfs_release_netlink(void);
-
-int ecryptfs_send_connector(char *data, int data_len,
-                            struct ecryptfs_msg_ctx *msg_ctx, u8 msg_type,
-                            u16 msg_flags, struct pid *daemon_pid);
-int ecryptfs_init_connector(void);
-void ecryptfs_release_connector(void);
 void
 ecryptfs_write_header_metadata(char *virt,
                                struct ecryptfs_crypt_stat *crypt_stat,
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 9244d653743e..eb3dc4c7ac06 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -71,12 +71,11 @@ struct ecryptfs_getdents_callback {
         void *dirent;
         struct dentry *dentry;
         filldir_t filldir;
-        int err;
         int filldir_called;
         int entries_written;
 };
 
-/* Inspired by generic filldir in fs/readir.c */
+/* Inspired by generic filldir in fs/readdir.c */
 static int
 ecryptfs_filldir(void *dirent, const char *name, int namelen, loff_t offset,
                  u64 ino, unsigned int d_type)
@@ -125,18 +124,18 @@ static int ecryptfs_readdir(struct file *file, void *dirent, filldir_t filldir)
         buf.dirent = dirent;
         buf.dentry = file->f_path.dentry;
         buf.filldir = filldir;
-retry:
         buf.filldir_called = 0;
         buf.entries_written = 0;
-        buf.err = 0;
         rc = vfs_readdir(lower_file, ecryptfs_filldir, (void *)&buf);
-        if (buf.err)
-                rc = buf.err;
-        if (buf.filldir_called && !buf.entries_written)
-                goto retry;
         file->f_pos = lower_file->f_pos;
+        if (rc < 0)
+                goto out;
+        if (buf.filldir_called && !buf.entries_written)
+                goto out;
         if (rc >= 0)
-                fsstack_copy_attr_atime(inode, lower_file->f_path.dentry->d_inode);
+                fsstack_copy_attr_atime(inode,
+                                        lower_file->f_path.dentry->d_inode);
+out:
         return rc;
 }
 
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index f5b76a331b9c..e22bc3961345 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -234,8 +234,8 @@ parse_tag_65_packet(struct ecryptfs_session_key *session_key, u8 *cipher_code,
         }
         i += data_len;
         if (message_len < (i + m_size)) {
-                ecryptfs_printk(KERN_ERR, "The received netlink message is "
-                                "shorter than expected\n");
+                ecryptfs_printk(KERN_ERR, "The message received from ecryptfsd "
+                                "is shorter than expected\n");
                 rc = -EIO;
                 goto out;
         }
@@ -438,8 +438,8 @@ decrypt_pki_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
         struct ecryptfs_msg_ctx *msg_ctx;
         struct ecryptfs_message *msg = NULL;
         char *auth_tok_sig;
-        char *netlink_message;
-        size_t netlink_message_length;
+        char *payload;
+        size_t payload_len;
         int rc;
 
         rc = ecryptfs_get_auth_tok_sig(&auth_tok_sig, auth_tok);
@@ -449,15 +449,15 @@ decrypt_pki_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
                 goto out;
         }
         rc = write_tag_64_packet(auth_tok_sig, &(auth_tok->session_key),
-                                 &netlink_message, &netlink_message_length);
+                                 &payload, &payload_len);
         if (rc) {
                 ecryptfs_printk(KERN_ERR, "Failed to write tag 64 packet\n");
                 goto out;
         }
-        rc = ecryptfs_send_message(ecryptfs_transport, netlink_message,
-                                   netlink_message_length, &msg_ctx);
+        rc = ecryptfs_send_message(payload, payload_len, &msg_ctx);
         if (rc) {
-                ecryptfs_printk(KERN_ERR, "Error sending netlink message\n");
+                ecryptfs_printk(KERN_ERR, "Error sending message to "
+                                "ecryptfsd\n");
                 goto out;
         }
         rc = ecryptfs_wait_for_response(msg_ctx, &msg);
@@ -1333,23 +1333,22 @@ pki_encrypt_session_key(struct ecryptfs_auth_tok *auth_tok,
                         struct ecryptfs_key_record *key_rec)
 {
         struct ecryptfs_msg_ctx *msg_ctx = NULL;
-        char *netlink_payload;
-        size_t netlink_payload_length;
+        char *payload = NULL;
+        size_t payload_len;
         struct ecryptfs_message *msg;
         int rc;
 
         rc = write_tag_66_packet(auth_tok->token.private_key.signature,
                                  ecryptfs_code_for_cipher_string(crypt_stat),
-                                 crypt_stat, &netlink_payload,
-                                 &netlink_payload_length);
+                                 crypt_stat, &payload, &payload_len);
         if (rc) {
                 ecryptfs_printk(KERN_ERR, "Error generating tag 66 packet\n");
                 goto out;
         }
-        rc = ecryptfs_send_message(ecryptfs_transport, netlink_payload,
-                                   netlink_payload_length, &msg_ctx);
+        rc = ecryptfs_send_message(payload, payload_len, &msg_ctx);
         if (rc) {
-                ecryptfs_printk(KERN_ERR, "Error sending netlink message\n");
+                ecryptfs_printk(KERN_ERR, "Error sending message to "
+                                "ecryptfsd\n");
                 goto out;
         }
         rc = ecryptfs_wait_for_response(msg_ctx, &msg);
@@ -1364,8 +1363,7 @@ pki_encrypt_session_key(struct ecryptfs_auth_tok *auth_tok,
                 ecryptfs_printk(KERN_ERR, "Error parsing tag 67 packet\n");
         kfree(msg);
 out:
-        if (netlink_payload)
-                kfree(netlink_payload);
+        kfree(payload);
         return rc;
 }
 /**
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 448dfd597b5f..046e027a4cb1 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -30,7 +30,6 @@
 #include <linux/namei.h>
 #include <linux/skbuff.h>
 #include <linux/crypto.h>
-#include <linux/netlink.h>
 #include <linux/mount.h>
 #include <linux/pagemap.h>
 #include <linux/key.h>
@@ -49,8 +48,7 @@ MODULE_PARM_DESC(ecryptfs_verbosity,
                  "0, which is Quiet)");
 
 /**
- * Module parameter that defines the number of netlink message buffer
- * elements
+ * Module parameter that defines the number of message buffer elements
  */
 unsigned int ecryptfs_message_buf_len = ECRYPTFS_DEFAULT_MSG_CTX_ELEMS;
 
@@ -60,9 +58,9 @@ MODULE_PARM_DESC(ecryptfs_message_buf_len,
 
 /**
  * Module parameter that defines the maximum guaranteed amount of time to wait
- * for a response through netlink.  The actual sleep time will be, more than
+ * for a response from ecryptfsd.  The actual sleep time will be, more than
  * likely, a small amount greater than this specified value, but only less if
- * the netlink message successfully arrives.
+ * the message successfully arrives.
  */
 signed long ecryptfs_message_wait_timeout = ECRYPTFS_MAX_MSG_CTX_TTL / HZ;
 
@@ -83,8 +81,6 @@ module_param(ecryptfs_number_of_users, uint, 0);
 MODULE_PARM_DESC(ecryptfs_number_of_users, "An estimate of the number of "
                  "concurrent users of eCryptfs");
 
-unsigned int ecryptfs_transport = ECRYPTFS_DEFAULT_TRANSPORT;
-
 void __ecryptfs_printk(const char *fmt, ...)
 {
         va_list args;
@@ -211,7 +207,7 @@ enum { ecryptfs_opt_sig, ecryptfs_opt_ecryptfs_sig,
        ecryptfs_opt_passthrough, ecryptfs_opt_xattr_metadata,
        ecryptfs_opt_encrypted_view, ecryptfs_opt_err };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         {ecryptfs_opt_sig, "sig=%s"},
         {ecryptfs_opt_ecryptfs_sig, "ecryptfs_sig=%s"},
         {ecryptfs_opt_cipher, "cipher=%s"},
@@ -779,10 +775,11 @@ static int __init ecryptfs_init(void)
                        "rc = [%d]\n", __func__, rc);
                 goto out_do_sysfs_unregistration;
         }
-        rc = ecryptfs_init_messaging(ecryptfs_transport);
+        rc = ecryptfs_init_messaging();
         if (rc) {
                 printk(KERN_ERR "Failure occured while attempting to "
-                                "initialize the eCryptfs netlink socket\n");
+                                "initialize the communications channel to "
+                                "ecryptfsd\n");
                 goto out_destroy_kthread;
         }
         rc = ecryptfs_init_crypto();
@@ -797,7 +794,7 @@ static int __init ecryptfs_init(void)
 
         goto out;
 out_release_messaging:
-        ecryptfs_release_messaging(ecryptfs_transport);
+        ecryptfs_release_messaging();
 out_destroy_kthread:
         ecryptfs_destroy_kthread();
 out_do_sysfs_unregistration:
@@ -818,7 +815,7 @@ static void __exit ecryptfs_exit(void)
         if (rc)
                 printk(KERN_ERR "Failure whilst attempting to destroy crypto; "
                        "rc = [%d]\n", rc);
-        ecryptfs_release_messaging(ecryptfs_transport);
+        ecryptfs_release_messaging();
         ecryptfs_destroy_kthread();
         do_sysfs_unregistration();
         unregister_filesystem(&ecryptfs_fs_type);
diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c
index 1b5c20058acb..c6983978a31e 100644
--- a/fs/ecryptfs/messaging.c
+++ b/fs/ecryptfs/messaging.c
@@ -134,12 +134,11 @@ out:
 }
 
 static int
-ecryptfs_send_message_locked(unsigned int transport, char *data, int data_len,
-                             u8 msg_type, struct ecryptfs_msg_ctx **msg_ctx);
+ecryptfs_send_message_locked(char *data, int data_len, u8 msg_type,
+                             struct ecryptfs_msg_ctx **msg_ctx);
 
 /**
  * ecryptfs_send_raw_message
- * @transport: Transport type
  * @msg_type: Message type
  * @daemon: Daemon struct for recipient of message
  *
@@ -150,38 +149,25 @@ ecryptfs_send_message_locked(unsigned int transport, char *data, int data_len,
  *
  * Returns zero on success; non-zero otherwise
  */
-static int ecryptfs_send_raw_message(unsigned int transport, u8 msg_type,
+static int ecryptfs_send_raw_message(u8 msg_type,
                                      struct ecryptfs_daemon *daemon)
 {
         struct ecryptfs_msg_ctx *msg_ctx;
         int rc;
 
-        switch(transport) {
-        case ECRYPTFS_TRANSPORT_NETLINK:
-                rc = ecryptfs_send_netlink(NULL, 0, NULL, msg_type, 0,
-                                           daemon->pid);
-                break;
-        case ECRYPTFS_TRANSPORT_MISCDEV:
-                rc = ecryptfs_send_message_locked(transport, NULL, 0, msg_type,
-                                                  &msg_ctx);
-                if (rc) {
-                        printk(KERN_ERR "%s: Error whilst attempting to send "
-                               "message via procfs; rc = [%d]\n", __func__, rc);
-                        goto out;
-                }
-                /* Raw messages are logically context-free (e.g., no
-                 * reply is expected), so we set the state of the
-                 * ecryptfs_msg_ctx object to indicate that it should
-                 * be freed as soon as the transport sends out the message. */
-                mutex_lock(&msg_ctx->mux);
-                msg_ctx->state = ECRYPTFS_MSG_CTX_STATE_NO_REPLY;
-                mutex_unlock(&msg_ctx->mux);
-                break;
-        case ECRYPTFS_TRANSPORT_CONNECTOR:
-        case ECRYPTFS_TRANSPORT_RELAYFS:
-        default:
-                rc = -ENOSYS;
+        rc = ecryptfs_send_message_locked(NULL, 0, msg_type, &msg_ctx);
+        if (rc) {
+                printk(KERN_ERR "%s: Error whilst attempting to send "
+                       "message to ecryptfsd; rc = [%d]\n", __func__, rc);
+                goto out;
         }
+        /* Raw messages are logically context-free (e.g., no
+         * reply is expected), so we set the state of the
+         * ecryptfs_msg_ctx object to indicate that it should
+         * be freed as soon as the message is sent. */
+        mutex_lock(&msg_ctx->mux);
+        msg_ctx->state = ECRYPTFS_MSG_CTX_STATE_NO_REPLY;
+        mutex_unlock(&msg_ctx->mux);
 out:
         return rc;
 }
@@ -227,7 +213,6 @@ out:
 
 /**
  * ecryptfs_process_helo
- * @transport: The underlying transport (netlink, etc.)
  * @euid: The user ID owner of the message
  * @user_ns: The namespace in which @euid applies
  * @pid: The process ID for the userspace program that sent the
@@ -239,8 +224,8 @@ out:
  * Returns zero after adding a new daemon to the hash list;
  * non-zero otherwise.
  */
-int ecryptfs_process_helo(unsigned int transport, uid_t euid,
-                          struct user_namespace *user_ns, struct pid *pid)
+int ecryptfs_process_helo(uid_t euid, struct user_namespace *user_ns,
+                          struct pid *pid)
 {
         struct ecryptfs_daemon *new_daemon;
         struct ecryptfs_daemon *old_daemon;
@@ -252,8 +237,7 @@ int ecryptfs_process_helo(unsigned int transport, uid_t euid,
                 printk(KERN_WARNING "Received request from user [%d] "
                        "to register daemon [0x%p]; unregistering daemon "
                        "[0x%p]\n", euid, pid, old_daemon->pid);
-                rc = ecryptfs_send_raw_message(transport, ECRYPTFS_MSG_QUIT,
-                                               old_daemon);
+                rc = ecryptfs_send_raw_message(ECRYPTFS_MSG_QUIT, old_daemon);
                 if (rc)
                         printk(KERN_WARNING "Failed to send QUIT "
                                "message to daemon [0x%p]; rc = [%d]\n",
@@ -467,8 +451,6 @@ out:
 
 /**
  * ecryptfs_send_message_locked
- * @transport: The transport over which to send the message (i.e.,
- *             netlink)
  * @data: The data to send
  * @data_len: The length of data
  * @msg_ctx: The message context allocated for the send
@@ -478,8 +460,8 @@ out:
  * Returns zero on success; non-zero otherwise
  */
 static int
-ecryptfs_send_message_locked(unsigned int transport, char *data, int data_len,
-                             u8 msg_type, struct ecryptfs_msg_ctx **msg_ctx)
+ecryptfs_send_message_locked(char *data, int data_len, u8 msg_type,
+                             struct ecryptfs_msg_ctx **msg_ctx)
 {
         struct ecryptfs_daemon *daemon;
         int rc;
@@ -503,20 +485,8 @@ ecryptfs_send_message_locked(unsigned int transport, char *data, int data_len,
         ecryptfs_msg_ctx_free_to_alloc(*msg_ctx);
         mutex_unlock(&(*msg_ctx)->mux);
         mutex_unlock(&ecryptfs_msg_ctx_lists_mux);
-        switch (transport) {
-        case ECRYPTFS_TRANSPORT_NETLINK:
-                rc = ecryptfs_send_netlink(data, data_len, *msg_ctx, msg_type,
-                                           0, daemon->pid);
-                break;
-        case ECRYPTFS_TRANSPORT_MISCDEV:
-                rc = ecryptfs_send_miscdev(data, data_len, *msg_ctx, msg_type,
-                                           0, daemon);
-                break;
-        case ECRYPTFS_TRANSPORT_CONNECTOR:
-        case ECRYPTFS_TRANSPORT_RELAYFS:
-        default:
-                rc = -ENOSYS;
-        }
+        rc = ecryptfs_send_miscdev(data, data_len, *msg_ctx, msg_type, 0,
+                                   daemon);
         if (rc)
                 printk(KERN_ERR "%s: Error attempting to send message to "
                        "userspace daemon; rc = [%d]\n", __func__, rc);
@@ -526,8 +496,6 @@ out:
 
 /**
  * ecryptfs_send_message
- * @transport: The transport over which to send the message (i.e.,
- *             netlink)
  * @data: The data to send
  * @data_len: The length of data
  * @msg_ctx: The message context allocated for the send
@@ -536,14 +504,14 @@ out:
  *
  * Returns zero on success; non-zero otherwise
  */
-int ecryptfs_send_message(unsigned int transport, char *data, int data_len,
+int ecryptfs_send_message(char *data, int data_len,
                           struct ecryptfs_msg_ctx **msg_ctx)
 {
         int rc;
 
         mutex_lock(&ecryptfs_daemon_hash_mux);
-        rc = ecryptfs_send_message_locked(transport, data, data_len,
-                                          ECRYPTFS_MSG_REQUEST, msg_ctx);
+        rc = ecryptfs_send_message_locked(data, data_len, ECRYPTFS_MSG_REQUEST,
+                                          msg_ctx);
         mutex_unlock(&ecryptfs_daemon_hash_mux);
         return rc;
 }
@@ -586,7 +554,7 @@ sleep:
         return rc;
 }
 
-int ecryptfs_init_messaging(unsigned int transport)
+int ecryptfs_init_messaging(void)
 {
         int i;
         int rc = 0;
@@ -639,27 +607,14 @@ int ecryptfs_init_messaging(unsigned int transport)
                 mutex_unlock(&ecryptfs_msg_ctx_arr[i].mux);
         }
         mutex_unlock(&ecryptfs_msg_ctx_lists_mux);
-        switch(transport) {
-        case ECRYPTFS_TRANSPORT_NETLINK:
-                rc = ecryptfs_init_netlink();
-                if (rc)
-                        ecryptfs_release_messaging(transport);
-                break;
-        case ECRYPTFS_TRANSPORT_MISCDEV:
-                rc = ecryptfs_init_ecryptfs_miscdev();
-                if (rc)
-                        ecryptfs_release_messaging(transport);
-                break;
-        case ECRYPTFS_TRANSPORT_CONNECTOR:
-        case ECRYPTFS_TRANSPORT_RELAYFS:
-        default:
-                rc = -ENOSYS;
-        }
+        rc = ecryptfs_init_ecryptfs_miscdev();
+        if (rc)
+                ecryptfs_release_messaging();
 out:
         return rc;
 }
 
-void ecryptfs_release_messaging(unsigned int transport)
+void ecryptfs_release_messaging(void)
 {
         if (ecryptfs_msg_ctx_arr) {
                 int i;
@@ -698,17 +653,6 @@ void ecryptfs_release_messaging(unsigned int transport)
                 kfree(ecryptfs_daemon_hash);
                 mutex_unlock(&ecryptfs_daemon_hash_mux);
         }
-        switch(transport) {
-        case ECRYPTFS_TRANSPORT_NETLINK:
-                ecryptfs_release_netlink();
-                break;
-        case ECRYPTFS_TRANSPORT_MISCDEV:
-                ecryptfs_destroy_ecryptfs_miscdev();
-                break;
-        case ECRYPTFS_TRANSPORT_CONNECTOR:
-        case ECRYPTFS_TRANSPORT_RELAYFS:
-        default:
-                break;
-        }
+        ecryptfs_destroy_ecryptfs_miscdev();
         return;
 }
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index 245c2dc02d5c..04d7b3fa1ac6 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -265,22 +265,34 @@ out:
 }
 
 /**
- * ecryptfs_prepare_write
+ * ecryptfs_write_begin
  * @file: The eCryptfs file
- * @page: The eCryptfs page
- * @from: The start byte from which we will write
- * @to: The end byte to which we will write
+ * @mapping: The eCryptfs object
+ * @pos: The file offset at which to start writing
+ * @len: Length of the write
+ * @flags: Various flags
+ * @pagep: Pointer to return the page
+ * @fsdata: Pointer to return fs data (unused)
  *
  * This function must zero any hole we create
  *
  * Returns zero on success; non-zero otherwise
  */
-static int ecryptfs_prepare_write(struct file *file, struct page *page,
-                                  unsigned from, unsigned to)
+static int ecryptfs_write_begin(struct file *file,
+                        struct address_space *mapping,
+                        loff_t pos, unsigned len, unsigned flags,
+                        struct page **pagep, void **fsdata)
 {
+        pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+        struct page *page;
         loff_t prev_page_end_size;
         int rc = 0;
 
+        page = __grab_cache_page(mapping, index);
+        if (!page)
+                return -ENOMEM;
+        *pagep = page;
+
         if (!PageUptodate(page)) {
                 struct ecryptfs_crypt_stat *crypt_stat =
                         &ecryptfs_inode_to_private(
@@ -289,8 +301,7 @@ static int ecryptfs_prepare_write(struct file *file, struct page *page,
                 if (!(crypt_stat->flags & ECRYPTFS_ENCRYPTED)
                     || (crypt_stat->flags & ECRYPTFS_NEW_FILE)) {
                         rc = ecryptfs_read_lower_page_segment(
-                                page, page->index, 0, PAGE_CACHE_SIZE,
-                                page->mapping->host);
+                                page, index, 0, PAGE_CACHE_SIZE, mapping->host);
                         if (rc) {
                                 printk(KERN_ERR "%s: Error attemping to read "
                                        "lower page segment; rc = [%d]\n",
@@ -316,8 +327,8 @@ static int ecryptfs_prepare_write(struct file *file, struct page *page,
                                 SetPageUptodate(page);
                         } else {
                                 rc = ecryptfs_read_lower_page_segment(
-                                        page, page->index, 0, PAGE_CACHE_SIZE,
-                                        page->mapping->host);
+                                        page, index, 0, PAGE_CACHE_SIZE,
+                                        mapping->host);
                                 if (rc) {
                                         printk(KERN_ERR "%s: Error reading "
                                                "page; rc = [%d]\n",
@@ -339,10 +350,10 @@ static int ecryptfs_prepare_write(struct file *file, struct page *page,
                         SetPageUptodate(page);
                 }
         }
-        prev_page_end_size = ((loff_t)page->index << PAGE_CACHE_SHIFT);
+        prev_page_end_size = ((loff_t)index << PAGE_CACHE_SHIFT);
         /* If creating a page or more of holes, zero them out via truncate.
          * Note, this will increase i_size. */
-        if (page->index != 0) {
+        if (index != 0) {
                 if (prev_page_end_size > i_size_read(page->mapping->host)) {
                         rc = ecryptfs_truncate(file->f_path.dentry,
                                                prev_page_end_size);
@@ -357,8 +368,8 @@ static int ecryptfs_prepare_write(struct file *file, struct page *page,
         }
         /* Writing to a new page, and creating a small hole from start
          * of page?  Zero it out. */
-        if ((i_size_read(page->mapping->host) == prev_page_end_size)
-            && (from != 0))
+        if ((i_size_read(mapping->host) == prev_page_end_size)
+            && (pos != 0))
                 zero_user(page, 0, PAGE_CACHE_SIZE);
 out:
         return rc;
@@ -445,21 +456,28 @@ int ecryptfs_write_inode_size_to_metadata(struct inode *ecryptfs_inode)
 }
 
 /**
- * ecryptfs_commit_write
+ * ecryptfs_write_end
  * @file: The eCryptfs file object
+ * @mapping: The eCryptfs object
+ * @pos: The file position
+ * @len: The length of the data (unused)
+ * @copied: The amount of data copied
  * @page: The eCryptfs page
- * @from: Ignored (we rotate the page IV on each write)
- * @to: Ignored
+ * @fsdata: The fsdata (unused)
  *
  * This is where we encrypt the data and pass the encrypted data to
  * the lower filesystem.  In OpenPGP-compatible mode, we operate on
  * entire underlying packets.
  */
-static int ecryptfs_commit_write(struct file *file, struct page *page,
-                                 unsigned from, unsigned to)
+static int ecryptfs_write_end(struct file *file,
+                        struct address_space *mapping,
+                        loff_t pos, unsigned len, unsigned copied,
+                        struct page *page, void *fsdata)
 {
-        loff_t pos;
-        struct inode *ecryptfs_inode = page->mapping->host;
+        pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+        unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+        unsigned to = from + copied;
+        struct inode *ecryptfs_inode = mapping->host;
         struct ecryptfs_crypt_stat *crypt_stat =
                 &ecryptfs_inode_to_private(file->f_path.dentry->d_inode)->crypt_stat;
         int rc;
@@ -471,25 +489,22 @@ static int ecryptfs_commit_write(struct file *file, struct page *page,
         } else
                 ecryptfs_printk(KERN_DEBUG, "Not a new file\n");
         ecryptfs_printk(KERN_DEBUG, "Calling fill_zeros_to_end_of_page"
-                        "(page w/ index = [0x%.16x], to = [%d])\n", page->index,
-                        to);
+                        "(page w/ index = [0x%.16x], to = [%d])\n", index, to);
         /* Fills in zeros if 'to' goes beyond inode size */
         rc = fill_zeros_to_end_of_page(page, to);
         if (rc) {
                 ecryptfs_printk(KERN_WARNING, "Error attempting to fill "
-                                "zeros in page with index = [0x%.16x]\n",
-                                page->index);
+                        "zeros in page with index = [0x%.16x]\n", index);
                 goto out;
         }
         rc = ecryptfs_encrypt_page(page);
         if (rc) {
                 ecryptfs_printk(KERN_WARNING, "Error encrypting page (upper "
-                                "index [0x%.16x])\n", page->index);
+                                "index [0x%.16x])\n", index);
                 goto out;
         }
-        pos = (((loff_t)page->index) << PAGE_CACHE_SHIFT) + to;
-        if (pos > i_size_read(ecryptfs_inode)) {
-                i_size_write(ecryptfs_inode, pos);
+        if (pos + copied > i_size_read(ecryptfs_inode)) {
+                i_size_write(ecryptfs_inode, pos + copied);
                 ecryptfs_printk(KERN_DEBUG, "Expanded file size to "
                                 "[0x%.16x]\n", i_size_read(ecryptfs_inode));
         }
@@ -497,7 +512,11 @@ static int ecryptfs_commit_write(struct file *file, struct page *page,
         if (rc)
                 printk(KERN_ERR "Error writing inode size to metadata; "
                        "rc = [%d]\n", rc);
+        else
+                rc = copied;
 out:
+        unlock_page(page);
+        page_cache_release(page);
         return rc;
 }
 
@@ -518,7 +537,7 @@ static sector_t ecryptfs_bmap(struct address_space *mapping, sector_t block)
 struct address_space_operations ecryptfs_aops = {
         .writepage = ecryptfs_writepage,
         .readpage = ecryptfs_readpage,
-        .prepare_write = ecryptfs_prepare_write,
-        .commit_write = ecryptfs_commit_write,
+        .write_begin = ecryptfs_write_begin,
+        .write_end = ecryptfs_write_end,
         .bmap = ecryptfs_bmap,
 };
diff --git a/fs/ecryptfs/netlink.c b/fs/ecryptfs/netlink.c
deleted file mode 100644
index e0abad62b395..000000000000
--- a/fs/ecryptfs/netlink.c
+++ /dev/null
@@ -1,249 +0,0 @@
-/**
- * eCryptfs: Linux filesystem encryption layer
- *
- * Copyright (C) 2004-2006 International Business Machines Corp.
- *   Author(s): Michael A. Halcrow <mhalcrow@us.ibm.com>
- *              Tyler Hicks <tyhicks@ou.edu>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version
- * 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
- * 02111-1307, USA.
- */
-
-#include <net/sock.h>
-#include <linux/hash.h>
-#include <linux/random.h>
-#include "ecryptfs_kernel.h"
-
-static struct sock *ecryptfs_nl_sock;
-
-/**
- * ecryptfs_send_netlink
- * @data: The data to include as the payload
- * @data_len: The byte count of the data
- * @msg_ctx: The netlink context that will be used to handle the
- *          response message
- * @msg_type: The type of netlink message to send
- * @msg_flags: The flags to include in the netlink header
- * @daemon_pid: The process id of the daemon to send the message to
- *
- * Sends the data to the specified daemon pid and uses the netlink
- * context element to store the data needed for validation upon
- * receiving the response.  The data and the netlink context can be
- * null if just sending a netlink header is sufficient.  Returns zero
- * upon sending the message; non-zero upon error.
- */
-int ecryptfs_send_netlink(char *data, int data_len,
-                          struct ecryptfs_msg_ctx *msg_ctx, u8 msg_type,
-                          u16 msg_flags, struct pid *daemon_pid)
-{
-        struct sk_buff *skb;
-        struct nlmsghdr *nlh;
-        struct ecryptfs_message *msg;
-        size_t payload_len;
-        int rc;
-
-        payload_len = ((data && data_len) ? (sizeof(*msg) + data_len) : 0);
-        skb = alloc_skb(NLMSG_SPACE(payload_len), GFP_KERNEL);
-        if (!skb) {
-                rc = -ENOMEM;
-                ecryptfs_printk(KERN_ERR, "Failed to allocate socket buffer\n");
-                goto out;
-        }
-        nlh = NLMSG_PUT(skb, pid_nr(daemon_pid), msg_ctx ? msg_ctx->counter : 0,
-                        msg_type, payload_len);
-        nlh->nlmsg_flags = msg_flags;
-        if (msg_ctx && payload_len) {
-                msg = (struct ecryptfs_message *)NLMSG_DATA(nlh);
-                msg->index = msg_ctx->index;
-                msg->data_len = data_len;
-                memcpy(msg->data, data, data_len);
-        }
-        rc = netlink_unicast(ecryptfs_nl_sock, skb, pid_nr(daemon_pid), 0);
-        if (rc < 0) {
-                ecryptfs_printk(KERN_ERR, "Failed to send eCryptfs netlink "
-                                "message; rc = [%d]\n", rc);
-                goto out;
-        }
-        rc = 0;
-        goto out;
-nlmsg_failure:
-        rc = -EMSGSIZE;
-        kfree_skb(skb);
-out:
-        return rc;
-}
-
-/**
- * ecryptfs_process_nl_reponse
- * @skb: The socket buffer containing the netlink message of state
- *       RESPONSE
- *
- * Processes a response message after sending a operation request to
- * userspace.  Attempts to assign the msg to a netlink context element
- * at the index specified in the msg.  The sk_buff and nlmsghdr must
- * be validated before this function. Returns zero upon delivery to
- * desired context element; non-zero upon delivery failure or error.
- */
-static int ecryptfs_process_nl_response(struct sk_buff *skb)
-{
-        struct nlmsghdr *nlh = nlmsg_hdr(skb);
-        struct ecryptfs_message *msg = NLMSG_DATA(nlh);
-        struct pid *pid;
-        int rc;
-
-        if (skb->len - NLMSG_HDRLEN - sizeof(*msg) != msg->data_len) {
-                rc = -EINVAL;
-                ecryptfs_printk(KERN_ERR, "Received netlink message with "
-                                "incorrectly specified data length\n");
-                goto out;
-        }
-        pid = find_get_pid(NETLINK_CREDS(skb)->pid);
-        rc = ecryptfs_process_response(msg, NETLINK_CREDS(skb)->uid, NULL,
-                                       pid, nlh->nlmsg_seq);
-        put_pid(pid);
-        if (rc)
-                printk(KERN_ERR
-                       "Error processing response message; rc = [%d]\n", rc);
-out:
-        return rc;
-}
-
-/**
- * ecryptfs_process_nl_helo
- * @skb: The socket buffer containing the nlmsghdr in HELO state
- *
- * Gets uid and pid of the skb and adds the values to the daemon id
- * hash. Returns zero after adding a new daemon id to the hash list;
- * non-zero otherwise.
- */
-static int ecryptfs_process_nl_helo(struct sk_buff *skb)
-{
-        struct pid *pid;
-        int rc;
-
-        pid = find_get_pid(NETLINK_CREDS(skb)->pid);
-        rc = ecryptfs_process_helo(ECRYPTFS_TRANSPORT_NETLINK,
-                                   NETLINK_CREDS(skb)->uid, NULL, pid);
-        put_pid(pid);
-        if (rc)
-                printk(KERN_WARNING "Error processing HELO; rc = [%d]\n", rc);
-        return rc;
-}
-
-/**
- * ecryptfs_process_nl_quit
- * @skb: The socket buffer containing the nlmsghdr in QUIT state
- *
- * Gets uid and pid of the skb and deletes the corresponding daemon
- * id, if it is the registered that is requesting the
- * deletion. Returns zero after deleting the desired daemon id;
- * non-zero otherwise.
- */
-static int ecryptfs_process_nl_quit(struct sk_buff *skb)
-{
-        struct pid *pid;
-        int rc;
-
-        pid = find_get_pid(NETLINK_CREDS(skb)->pid);
-        rc = ecryptfs_process_quit(NETLINK_CREDS(skb)->uid, NULL, pid);
-        put_pid(pid);
-        if (rc)
-                printk(KERN_WARNING
-                       "Error processing QUIT message; rc = [%d]\n", rc);
-        return rc;
-}
-
-/**
- * ecryptfs_receive_nl_message
- *
- * Callback function called by netlink system when a message arrives.
- * If the message looks to be valid, then an attempt is made to assign
- * it to its desired netlink context element and wake up the process
- * that is waiting for a response.
- */
-static void ecryptfs_receive_nl_message(struct sk_buff *skb)
-{
-        struct nlmsghdr *nlh;
-
-        nlh = nlmsg_hdr(skb);
-        if (!NLMSG_OK(nlh, skb->len)) {
-                ecryptfs_printk(KERN_ERR, "Received corrupt netlink "
-                                "message\n");
-                goto free;
-        }
-        switch (nlh->nlmsg_type) {
-                case ECRYPTFS_MSG_RESPONSE:
-                        if (ecryptfs_process_nl_response(skb)) {
-                                ecryptfs_printk(KERN_WARNING, "Failed to "
-                                                "deliver netlink response to "
-                                                "requesting operation\n");
-                        }
-                        break;
-                case ECRYPTFS_MSG_HELO:
-                        if (ecryptfs_process_nl_helo(skb)) {
-                                ecryptfs_printk(KERN_WARNING, "Failed to "
-                                                "fulfill HELO request\n");
-                        }
-                        break;
-                case ECRYPTFS_MSG_QUIT:
-                        if (ecryptfs_process_nl_quit(skb)) {
-                                ecryptfs_printk(KERN_WARNING, "Failed to "
-                                                "fulfill QUIT request\n");
-                        }
-                        break;
-                default:
-                        ecryptfs_printk(KERN_WARNING, "Dropping netlink "
-                                        "message of unrecognized type [%d]\n",
-                                        nlh->nlmsg_type);
-                        break;
-        }
-free:
-        kfree_skb(skb);
-}
-
-/**
- * ecryptfs_init_netlink
- *
- * Initializes the daemon id hash list, netlink context array, and
- * necessary locks.  Returns zero upon success; non-zero upon error.
- */
-int ecryptfs_init_netlink(void)
-{
-        int rc;
-
-        ecryptfs_nl_sock = netlink_kernel_create(&init_net, NETLINK_ECRYPTFS, 0,
-                                                 ecryptfs_receive_nl_message,
-                                                 NULL, THIS_MODULE);
-        if (!ecryptfs_nl_sock) {
-                rc = -EIO;
-                ecryptfs_printk(KERN_ERR, "Failed to create netlink socket\n");
-                goto out;
-        }
-        ecryptfs_nl_sock->sk_sndtimeo = ECRYPTFS_DEFAULT_SEND_TIMEOUT;
-        rc = 0;
-out:
-        return rc;
-}
-
-/**
- * ecryptfs_release_netlink
- *
- * Frees all memory used by the netlink context array and releases the
- * netlink socket.
- */
-void ecryptfs_release_netlink(void)
-{
-        netlink_kernel_release(ecryptfs_nl_sock);
-        ecryptfs_nl_sock = NULL;
-}
diff --git a/fs/efs/super.c b/fs/efs/super.c
index 567b134fa1f1..73b19cfc91fc 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -341,8 +341,6 @@ static int efs_statfs(struct dentry *dentry, struct kstatfs *buf) {
                         sb->inode_blocks *
                         (EFS_BLOCKSIZE / sizeof(struct efs_dinode));
         buf->f_ffree   = sb->inode_free;        /* free inodes */
-        buf->f_fsid.val[0] = (sb->fs_magic >> 16) & 0xffff; /* fs ID */
-        buf->f_fsid.val[1] =  sb->fs_magic        & 0xffff; /* fs ID */
         buf->f_namelen = EFS_MAXNAMELEN;        /* max filename length */
 
         return 0;
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 7cc0eb756b55..99368bda0261 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -927,14 +927,11 @@ errxit:
         /*
          * During the time we spent in the loop above, some other events
          * might have been queued by the poll callback. We re-insert them
-         * here (in case they are not already queued, or they're one-shot).
+         * inside the main ready-list here.
          */
         for (nepi = ep->ovflist; (epi = nepi) != NULL;
-             nepi = epi->next, epi->next = EP_UNACTIVE_PTR) {
-                if (!ep_is_linked(&epi->rdllink) &&
-                    (epi->event.events & ~EP_PRIVATE_BITS))
-                        list_add_tail(&epi->rdllink, &ep->rdllist);
-        }
+             nepi = epi->next, epi->next = EP_UNACTIVE_PTR)
+                list_add_tail(&epi->rdllink, &ep->rdllist);
         /*
          * We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after
          * releasing the lock, events will be queued in the normal way inside
diff --git a/fs/exec.c b/fs/exec.c
index cecee501ce78..4e834f16d9da 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -50,15 +50,12 @@
 #include <linux/cn_proc.h>
 #include <linux/audit.h>
 #include <linux/tracehook.h>
+#include <linux/kmod.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/tlb.h>
 
-#ifdef CONFIG_KMOD
-#include <linux/kmod.h>
-#endif
-
 #ifdef __alpha__
 /* for /sbin/loader handling in search_binary_handler() */
 #include <linux/a.out.h>
@@ -391,7 +388,7 @@ static int count(char __user * __user * argv, int max)
                         if (!p)
                                 break;
                         argv++;
-                        if(++i > max)
+                        if (i++ >= max)
                                 return -E2BIG;
                         cond_resched();
                 }
@@ -825,8 +822,6 @@ static int de_thread(struct task_struct *tsk)
                         schedule();
                 }
 
-                if (unlikely(task_child_reaper(tsk) == leader))
-                        task_active_pid_ns(tsk)->child_reaper = tsk;
                 /*
                  * The only record we have of the real-time age of a
                  * process, regardless of execs it's done, is start_time.
@@ -1189,7 +1184,7 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
                         return retval;
 
                 /* Remember if the application is TASO.  */
-                bprm->sh_bang = eh->ah.entry < 0x100000000UL;
+                bprm->taso = eh->ah.entry < 0x100000000UL;
 
                 bprm->file = file;
                 bprm->loader = loader;
@@ -1247,8 +1242,8 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
                 read_unlock(&binfmt_lock);
                 if (retval != -ENOEXEC || bprm->mm == NULL) {
                         break;
-#ifdef CONFIG_KMOD
-                }else{
+#ifdef CONFIG_MODULES
+                } else {
 #define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e))
                         if (printable(bprm->buf[0]) &&
                             printable(bprm->buf[1]) &&
@@ -1391,7 +1386,7 @@ EXPORT_SYMBOL(set_binfmt);
  * name into corename, which must have space for at least
  * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator.
  */
-static int format_corename(char *corename, int nr_threads, long signr)
+static int format_corename(char *corename, long signr)
 {
         const char *pat_ptr = core_pattern;
         int ispipe = (*pat_ptr == '|');
@@ -1498,8 +1493,7 @@ static int format_corename(char *corename, int nr_threads, long signr)
          * If core_pattern does not include a %p (as is the default)
          * and core_uses_pid is set, then .%pid will be appended to
          * the filename. Do not do this for piped commands. */
-        if (!ispipe && !pid_in_pattern
-            && (core_uses_pid || nr_threads)) {
+        if (!ispipe && !pid_in_pattern && core_uses_pid) {
                 rc = snprintf(out_ptr, out_end - out_ptr,
                               ".%d", task_tgid_vnr(current));
                 if (rc > out_end - out_ptr)
@@ -1762,7 +1756,7 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs)
          * uses lock_kernel()
          */
         lock_kernel();
-        ispipe = format_corename(corename, retval, signr);
+        ispipe = format_corename(corename, signr);
         unlock_kernel();
         /*
          * Don't bother to check the RLIMIT_CORE value if core_pattern points
diff --git a/fs/ext2/Kconfig b/fs/ext2/Kconfig
new file mode 100644
index 000000000000..14a6780fd034
--- /dev/null
+++ b/fs/ext2/Kconfig
@@ -0,0 +1,55 @@
+config EXT2_FS
+        tristate "Second extended fs support"
+        help
+          Ext2 is a standard Linux file system for hard disks.
+
+          To compile this file system support as a module, choose M here: the
+          module will be called ext2.
+
+          If unsure, say Y.
+
+config EXT2_FS_XATTR
+        bool "Ext2 extended attributes"
+        depends on EXT2_FS
+        help
+          Extended attributes are name:value pairs associated with inodes by
+          the kernel or by users (see the attr(5) manual page, or visit
+          <http://acl.bestbits.at/> for details).
+
+          If unsure, say N.
+
+config EXT2_FS_POSIX_ACL
+        bool "Ext2 POSIX Access Control Lists"
+        depends on EXT2_FS_XATTR
+        select FS_POSIX_ACL
+        help
+          Posix Access Control Lists (ACLs) support permissions for users and
+          groups beyond the owner/group/world scheme.
+
+          To learn more about Access Control Lists, visit the Posix ACLs for
+          Linux website <http://acl.bestbits.at/>.
+
+          If you don't know what Access Control Lists are, say N
+
+config EXT2_FS_SECURITY
+        bool "Ext2 Security Labels"
+        depends on EXT2_FS_XATTR
+        help
+          Security labels support alternative access control models
+          implemented by security modules like SELinux.  This option
+          enables an extended attribute handler for file security
+          labels in the ext2 filesystem.
+
+          If you are not using a security module that requires using
+          extended attributes for file security labels, say N.
+
+config EXT2_FS_XIP
+        bool "Ext2 execute in place support"
+        depends on EXT2_FS && MMU
+        help
+          Execute in place can be used on memory-backed block devices. If you
+          enable this option, you can select to mount block devices which are
+          capable of this feature without using the page cache.
+
+          If you do not use a block device that is capable of using this,
+          or if unsure, say N.
diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c
index 10bb02c3f25c..6dac7ba2d22d 100644
--- a/fs/ext2/balloc.c
+++ b/fs/ext2/balloc.c
@@ -1295,6 +1295,7 @@ retry_alloc:
          * turn off reservation for this allocation
          */
         if (my_rsv && (free_blocks < windowsz)
+                && (free_blocks > 0)
                 && (rsv_is_empty(&my_rsv->rsv_window)))
                 my_rsv = NULL;
 
@@ -1332,7 +1333,7 @@ retry_alloc:
                  * free blocks is less than half of the reservation
                  * window size.
                  */
-                if (free_blocks <= (windowsz/2))
+                if (my_rsv && (free_blocks <= (windowsz/2)))
                         continue;
 
                 brelse(bitmap_bh);
diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
index a78c6b4af060..11a49ce84392 100644
--- a/fs/ext2/dir.c
+++ b/fs/ext2/dir.c
@@ -103,7 +103,7 @@ static int ext2_commit_chunk(struct page *page, loff_t pos, unsigned len)
         return err;
 }
 
-static void ext2_check_page(struct page *page)
+static void ext2_check_page(struct page *page, int quiet)
 {
         struct inode *dir = page->mapping->host;
         struct super_block *sb = dir->i_sb;
@@ -146,10 +146,10 @@ out:
         /* Too bad, we had an error */
 
 Ebadsize:
-        ext2_error(sb, "ext2_check_page",
-                "size of directory #%lu is not a multiple of chunk size",
-                dir->i_ino
-        );
+        if (!quiet)
+                ext2_error(sb, __func__,
+                        "size of directory #%lu is not a multiple "
+                        "of chunk size", dir->i_ino);
         goto fail;
 Eshort:
         error = "rec_len is smaller than minimal";
@@ -166,32 +166,36 @@ Espan:
 Einumber:
         error = "inode out of bounds";
 bad_entry:
-        ext2_error (sb, "ext2_check_page", "bad entry in directory #%lu: %s - "
-                "offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
-                dir->i_ino, error, (page->index<<PAGE_CACHE_SHIFT)+offs,
-                (unsigned long) le32_to_cpu(p->inode),
-                rec_len, p->name_len);
+        if (!quiet)
+                ext2_error(sb, __func__, "bad entry in directory #%lu: : %s - "
+                        "offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
+                        dir->i_ino, error, (page->index<<PAGE_CACHE_SHIFT)+offs,
+                        (unsigned long) le32_to_cpu(p->inode),
+                        rec_len, p->name_len);
         goto fail;
 Eend:
-        p = (ext2_dirent *)(kaddr + offs);
-        ext2_error (sb, "ext2_check_page",
-                "entry in directory #%lu spans the page boundary"
-                "offset=%lu, inode=%lu",
-                dir->i_ino, (page->index<<PAGE_CACHE_SHIFT)+offs,
-                (unsigned long) le32_to_cpu(p->inode));
+        if (!quiet) {
+                p = (ext2_dirent *)(kaddr + offs);
+                ext2_error(sb, "ext2_check_page",
+                        "entry in directory #%lu spans the page boundary"
+                        "offset=%lu, inode=%lu",
+                        dir->i_ino, (page->index<<PAGE_CACHE_SHIFT)+offs,
+                        (unsigned long) le32_to_cpu(p->inode));
+        }
 fail:
         SetPageChecked(page);
         SetPageError(page);
 }
 
-static struct page * ext2_get_page(struct inode *dir, unsigned long n)
+static struct page * ext2_get_page(struct inode *dir, unsigned long n,
+                                   int quiet)
 {
         struct address_space *mapping = dir->i_mapping;
         struct page *page = read_mapping_page(mapping, n, NULL);
         if (!IS_ERR(page)) {
                 kmap(page);
                 if (!PageChecked(page))
-                        ext2_check_page(page);
+                        ext2_check_page(page, quiet);
                 if (PageError(page))
                         goto fail;
         }
@@ -292,7 +296,7 @@ ext2_readdir (struct file * filp, void * dirent, filldir_t filldir)
         for ( ; n < npages; n++, offset = 0) {
                 char *kaddr, *limit;
                 ext2_dirent *de;
-                struct page *page = ext2_get_page(inode, n);
+                struct page *page = ext2_get_page(inode, n, 0);
 
                 if (IS_ERR(page)) {
                         ext2_error(sb, __func__,
@@ -361,6 +365,7 @@ struct ext2_dir_entry_2 * ext2_find_entry (struct inode * dir,
         struct page *page = NULL;
         struct ext2_inode_info *ei = EXT2_I(dir);
         ext2_dirent * de;
+        int dir_has_error = 0;
 
         if (npages == 0)
                 goto out;
@@ -374,7 +379,7 @@ struct ext2_dir_entry_2 * ext2_find_entry (struct inode * dir,
         n = start;
         do {
                 char *kaddr;
-                page = ext2_get_page(dir, n);
+                page = ext2_get_page(dir, n, dir_has_error);
                 if (!IS_ERR(page)) {
                         kaddr = page_address(page);
                         de = (ext2_dirent *) kaddr;
@@ -391,7 +396,9 @@ struct ext2_dir_entry_2 * ext2_find_entry (struct inode * dir,
                                 de = ext2_next_entry(de);
                         }
                         ext2_put_page(page);
-                }
+                } else
+                        dir_has_error = 1;
+
                 if (++n >= npages)
                         n = 0;
                 /* next page is past the blocks we've got */
@@ -414,7 +421,7 @@ found:
 
 struct ext2_dir_entry_2 * ext2_dotdot (struct inode *dir, struct page **p)
 {
-        struct page *page = ext2_get_page(dir, 0);
+        struct page *page = ext2_get_page(dir, 0, 0);
         ext2_dirent *de = NULL;
 
         if (!IS_ERR(page)) {
@@ -487,7 +494,7 @@ int ext2_add_link (struct dentry *dentry, struct inode *inode)
         for (n = 0; n <= npages; n++) {
                 char *dir_end;
 
-                page = ext2_get_page(dir, n);
+                page = ext2_get_page(dir, n, 0);
                 err = PTR_ERR(page);
                 if (IS_ERR(page))
                         goto out;
@@ -655,14 +662,17 @@ int ext2_empty_dir (struct inode * inode)
 {
         struct page *page = NULL;
         unsigned long i, npages = dir_pages(inode);
+        int dir_has_error = 0;
 
         for (i = 0; i < npages; i++) {
                 char *kaddr;
                 ext2_dirent * de;
-                page = ext2_get_page(inode, i);
+                page = ext2_get_page(inode, i, dir_has_error);
 
-                if (IS_ERR(page))
+                if (IS_ERR(page)) {
+                        dir_has_error = 1;
                         continue;
+                }
 
                 kaddr = page_address(page);
                 de = (ext2_dirent *)kaddr;
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 47d88da2d33b..bae998c1e44e 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -133,6 +133,8 @@ extern void ext2_truncate (struct inode *);
 extern int ext2_setattr (struct dentry *, struct iattr *);
 extern void ext2_set_inode_flags(struct inode *inode);
 extern void ext2_get_inode_flags(struct ext2_inode_info *);
+extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+                       u64 start, u64 len);
 int __ext2_write_begin(struct file *file, struct address_space *mapping,
                 loff_t pos, unsigned len, unsigned flags,
                 struct page **pagep, void **fsdata);
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 5f2fa9c36293..45ed07122182 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -86,4 +86,5 @@ const struct inode_operations ext2_file_inode_operations = {
 #endif
         .setattr        = ext2_setattr,
         .permission     = ext2_permission,
+        .fiemap         = ext2_fiemap,
 };
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 991d6dfeb51f..7658b33e2653 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -31,6 +31,7 @@
 #include <linux/writeback.h>
 #include <linux/buffer_head.h>
 #include <linux/mpage.h>
+#include <linux/fiemap.h>
 #include "ext2.h"
 #include "acl.h"
 #include "xip.h"
@@ -704,6 +705,13 @@ int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_
 
 }
 
+int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+                u64 start, u64 len)
+{
+        return generic_block_fiemap(inode, fieinfo, start, len,
+                                    ext2_get_block);
+}
+
 static int ext2_writepage(struct page *page, struct writeback_control *wbc)
 {
         return block_write_full_page(page, ext2_get_block, wbc);
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index fd88c7b43e66..647cd888ac87 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -393,7 +393,7 @@ enum {
         Opt_usrquota, Opt_grpquota, Opt_reservation, Opt_noreservation
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         {Opt_bsd_df, "bsddf"},
         {Opt_minix_df, "minixdf"},
         {Opt_grpid, "grpid"},
diff --git a/fs/ext3/Kconfig b/fs/ext3/Kconfig
new file mode 100644
index 000000000000..8e0cfe44b0fc
--- /dev/null
+++ b/fs/ext3/Kconfig
@@ -0,0 +1,67 @@
+config EXT3_FS
+        tristate "Ext3 journalling file system support"
+        select JBD
+        help
+          This is the journalling version of the Second extended file system
+          (often called ext3), the de facto standard Linux file system
+          (method to organize files on a storage device) for hard disks.
+
+          The journalling code included in this driver means you do not have
+          to run e2fsck (file system checker) on your file systems after a
+          crash.  The journal keeps track of any changes that were being made
+          at the time the system crashed, and can ensure that your file system
+          is consistent without the need for a lengthy check.
+
+          Other than adding the journal to the file system, the on-disk format
+          of ext3 is identical to ext2.  It is possible to freely switch
+          between using the ext3 driver and the ext2 driver, as long as the
+          file system has been cleanly unmounted, or e2fsck is run on the file
+          system.
+
+          To add a journal on an existing ext2 file system or change the
+          behavior of ext3 file systems, you can use the tune2fs utility ("man
+          tune2fs").  To modify attributes of files and directories on ext3
+          file systems, use chattr ("man chattr").  You need to be using
+          e2fsprogs version 1.20 or later in order to create ext3 journals
+          (available at <http://sourceforge.net/projects/e2fsprogs/>).
+
+          To compile this file system support as a module, choose M here: the
+          module will be called ext3.
+
+config EXT3_FS_XATTR
+        bool "Ext3 extended attributes"
+        depends on EXT3_FS
+        default y
+        help
+          Extended attributes are name:value pairs associated with inodes by
+          the kernel or by users (see the attr(5) manual page, or visit
+          <http://acl.bestbits.at/> for details).
+
+          If unsure, say N.
+
+          You need this for POSIX ACL support on ext3.
+
+config EXT3_FS_POSIX_ACL
+        bool "Ext3 POSIX Access Control Lists"
+        depends on EXT3_FS_XATTR
+        select FS_POSIX_ACL
+        help
+          Posix Access Control Lists (ACLs) support permissions for users and
+          groups beyond the owner/group/world scheme.
+
+          To learn more about Access Control Lists, visit the Posix ACLs for
+          Linux website <http://acl.bestbits.at/>.
+
+          If you don't know what Access Control Lists are, say N
+
+config EXT3_FS_SECURITY
+        bool "Ext3 Security Labels"
+        depends on EXT3_FS_XATTR
+        help
+          Security labels support alternative access control models
+          implemented by security modules like SELinux.  This option
+          enables an extended attribute handler for file security
+          labels in the ext3 filesystem.
+
+          If you are not using a security module that requires using
+          extended attributes for file security labels, say N.
diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c
index 92fd0338a6eb..f5b57a2ca35a 100644
--- a/fs/ext3/balloc.c
+++ b/fs/ext3/balloc.c
@@ -1547,6 +1547,7 @@ retry_alloc:
          * turn off reservation for this allocation
          */
         if (my_rsv && (free_blocks < windowsz)
+                && (free_blocks > 0)
                 && (rsv_is_empty(&my_rsv->rsv_window)))
                 my_rsv = NULL;
 
@@ -1585,7 +1586,7 @@ retry_alloc:
                  * free blocks is less than half of the reservation
                  * window size.
                  */
-                if (free_blocks <= (windowsz/2))
+                if (my_rsv && (free_blocks <= (windowsz/2)))
                         continue;
 
                 brelse(bitmap_bh);
diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c
index 2eea96ec78ed..4c82531ea0a8 100644
--- a/fs/ext3/dir.c
+++ b/fs/ext3/dir.c
@@ -102,6 +102,7 @@ static int ext3_readdir(struct file * filp,
         int err;
         struct inode *inode = filp->f_path.dentry->d_inode;
         int ret = 0;
+        int dir_has_error = 0;
 
         sb = inode->i_sb;
 
@@ -148,9 +149,12 @@ static int ext3_readdir(struct file * filp,
                  * of recovering data when there's a bad sector
                  */
                 if (!bh) {
-                        ext3_error (sb, "ext3_readdir",
-                                "directory #%lu contains a hole at offset %lu",
-                                inode->i_ino, (unsigned long)filp->f_pos);
+                        if (!dir_has_error) {
+                                ext3_error(sb, __func__, "directory #%lu "
+                                        "contains a hole at offset %lld",
+                                        inode->i_ino, filp->f_pos);
+                                dir_has_error = 1;
+                        }
                         /* corrupt size?  Maybe no more blocks to read */
                         if (filp->f_pos > inode->i_blocks << 9)
                                 break;
@@ -410,7 +414,7 @@ static int call_filldir(struct file * filp, void * dirent,
                                 get_dtype(sb, fname->file_type));
                 if (error) {
                         filp->f_pos = curr_pos;
-                        info->extra_fname = fname->next;
+                        info->extra_fname = fname;
                         return error;
                 }
                 fname = fname->next;
@@ -449,11 +453,21 @@ static int ext3_dx_readdir(struct file * filp,
          * If there are any leftover names on the hash collision
          * chain, return them first.
          */
-        if (info->extra_fname &&
-            call_filldir(filp, dirent, filldir, info->extra_fname))
-                goto finished;
+        if (info->extra_fname) {
+                if (call_filldir(filp, dirent, filldir, info->extra_fname))
+                        goto finished;
 
-        if (!info->curr_node)
+                info->extra_fname = NULL;
+                info->curr_node = rb_next(info->curr_node);
+                if (!info->curr_node) {
+                        if (info->next_hash == ~0) {
+                                filp->f_pos = EXT3_HTREE_EOF;
+                                goto finished;
+                        }
+                        info->curr_hash = info->next_hash;
+                        info->curr_minor_hash = 0;
+                }
+        } else if (!info->curr_node)
                 info->curr_node = rb_first(&info->root);
 
         while (1) {
diff --git a/fs/ext3/file.c b/fs/ext3/file.c
index acc4913d3019..3be1e0689c9a 100644
--- a/fs/ext3/file.c
+++ b/fs/ext3/file.c
@@ -134,5 +134,6 @@ const struct inode_operations ext3_file_inode_operations = {
         .removexattr    = generic_removexattr,
 #endif
         .permission     = ext3_permission,
+        .fiemap         = ext3_fiemap,
 };
 
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 507d8689b111..f8424ad89971 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -36,6 +36,7 @@
 #include <linux/mpage.h>
 #include <linux/uio.h>
 #include <linux/bio.h>
+#include <linux/fiemap.h>
 #include "xattr.h"
 #include "acl.h"
 
@@ -981,6 +982,13 @@ out:
         return ret;
 }
 
+int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+                u64 start, u64 len)
+{
+        return generic_block_fiemap(inode, fieinfo, start, len,
+                                    ext3_get_block);
+}
+
 /*
  * `handle' can be NULL if create is zero
  */
@@ -1178,6 +1186,13 @@ write_begin_failed:
                 ext3_journal_stop(handle);
                 unlock_page(page);
                 page_cache_release(page);
+                /*
+                 * block_write_begin may have instantiated a few blocks
+                 * outside i_size.  Trim these off again. Don't need
+                 * i_size_read because we hold i_mutex.
+                 */
+                if (pos + len > inode->i_size)
+                        vmtruncate(inode, inode->i_size);
         }
         if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries))
                 goto retry;
diff --git a/fs/ext3/resize.c b/fs/ext3/resize.c
index 77278e947e94..78fdf3836370 100644
--- a/fs/ext3/resize.c
+++ b/fs/ext3/resize.c
@@ -790,7 +790,8 @@ int ext3_group_add(struct super_block *sb, struct ext3_new_group_data *input)
 
         if (reserved_gdb || gdb_off == 0) {
                 if (!EXT3_HAS_COMPAT_FEATURE(sb,
-                                             EXT3_FEATURE_COMPAT_RESIZE_INODE)){
+                                             EXT3_FEATURE_COMPAT_RESIZE_INODE)
+                    || !le16_to_cpu(es->s_reserved_gdt_blocks)) {
                         ext3_warning(sb, __func__,
                                      "No reserved GDT blocks, can't resize");
                         return -EPERM;
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index f38a5afc39a1..3a260af5544d 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -625,6 +625,9 @@ static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs)
         else if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)
                 seq_puts(seq, ",data=writeback");
 
+        if (test_opt(sb, DATA_ERR_ABORT))
+                seq_puts(seq, ",data_err=abort");
+
         ext3_show_quota_options(seq, sb);
 
         return 0;
@@ -754,13 +757,14 @@ enum {
         Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh,
         Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev,
         Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
+        Opt_data_err_abort, Opt_data_err_ignore,
         Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
         Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
         Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota,
         Opt_grpquota
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         {Opt_bsd_df, "bsddf"},
         {Opt_minix_df, "minixdf"},
         {Opt_grpid, "grpid"},
@@ -796,6 +800,8 @@ static match_table_t tokens = {
         {Opt_data_journal, "data=journal"},
         {Opt_data_ordered, "data=ordered"},
         {Opt_data_writeback, "data=writeback"},
+        {Opt_data_err_abort, "data_err=abort"},
+        {Opt_data_err_ignore, "data_err=ignore"},
         {Opt_offusrjquota, "usrjquota="},
         {Opt_usrjquota, "usrjquota=%s"},
         {Opt_offgrpjquota, "grpjquota="},
@@ -1011,6 +1017,12 @@ static int parse_options (char *options, struct super_block *sb,
                                 sbi->s_mount_opt |= data_opt;
                         }
                         break;
+                case Opt_data_err_abort:
+                        set_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
+                        break;
+                case Opt_data_err_ignore:
+                        clear_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
+                        break;
 #ifdef CONFIG_QUOTA
                 case Opt_usrjquota:
                         qtype = USRQUOTA;
@@ -1986,6 +1998,10 @@ static void ext3_init_journal_params(struct super_block *sb, journal_t *journal)
                 journal->j_flags |= JFS_BARRIER;
         else
                 journal->j_flags &= ~JFS_BARRIER;
+        if (test_opt(sb, DATA_ERR_ABORT))
+                journal->j_flags |= JFS_ABORT_ON_SYNCDATA_ERR;
+        else
+                journal->j_flags &= ~JFS_ABORT_ON_SYNCDATA_ERR;
         spin_unlock(&journal->j_state_lock);
 }
 
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
new file mode 100644
index 000000000000..7505482a08fa
--- /dev/null
+++ b/fs/ext4/Kconfig
@@ -0,0 +1,79 @@
+config EXT4_FS
+        tristate "The Extended 4 (ext4) filesystem"
+        select JBD2
+        select CRC16
+        help
+          This is the next generation of the ext3 filesystem.
+
+          Unlike the change from ext2 filesystem to ext3 filesystem,
+          the on-disk format of ext4 is not forwards compatible with
+          ext3; it is based on extent maps and it supports 48-bit
+          physical block numbers.  The ext4 filesystem also supports delayed
+          allocation, persistent preallocation, high resolution time stamps,
+          and a number of other features to improve performance and speed
+          up fsck time.  For more information, please see the web pages at
+          http://ext4.wiki.kernel.org.
+
+          The ext4 filesystem will support mounting an ext3
+          filesystem; while there will be some performance gains from
+          the delayed allocation and inode table readahead, the best
+          performance gains will require enabling ext4 features in the
+          filesystem, or formating a new filesystem as an ext4
+          filesystem initially.
+
+          To compile this file system support as a module, choose M here. The
+          module will be called ext4.
+
+          If unsure, say N.
+
+config EXT4DEV_COMPAT
+        bool "Enable ext4dev compatibility"
+        depends on EXT4_FS
+        help
+          Starting with 2.6.28, the name of the ext4 filesystem was
+          renamed from ext4dev to ext4.  Unfortunately there are some
+          legacy userspace programs (such as klibc's fstype) have
+          "ext4dev" hardcoded.
+
+          To enable backwards compatibility so that systems that are
+          still expecting to mount ext4 filesystems using ext4dev,
+          chose Y here.   This feature will go away by 2.6.31, so
+          please arrange to get your userspace programs fixed!
+
+config EXT4_FS_XATTR
+        bool "Ext4 extended attributes"
+        depends on EXT4_FS
+        default y
+        help
+          Extended attributes are name:value pairs associated with inodes by
+          the kernel or by users (see the attr(5) manual page, or visit
+          <http://acl.bestbits.at/> for details).
+
+          If unsure, say N.
+
+          You need this for POSIX ACL support on ext4.
+
+config EXT4_FS_POSIX_ACL
+        bool "Ext4 POSIX Access Control Lists"
+        depends on EXT4_FS_XATTR
+        select FS_POSIX_ACL
+        help
+          POSIX Access Control Lists (ACLs) support permissions for users and
+          groups beyond the owner/group/world scheme.
+
+          To learn more about Access Control Lists, visit the POSIX ACLs for
+          Linux website <http://acl.bestbits.at/>.
+
+          If you don't know what Access Control Lists are, say N
+
+config EXT4_FS_SECURITY
+        bool "Ext4 Security Labels"
+        depends on EXT4_FS_XATTR
+        help
+          Security labels support alternative access control models
+          implemented by security modules like SELinux.  This option
+          enables an extended attribute handler for file security
+          labels in the ext4 filesystem.
+
+          If you are not using a security module that requires using
+          extended attributes for file security labels, say N.
diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index ac6fa8ca0a2f..a8ff003a00f7 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -2,12 +2,12 @@
 # Makefile for the linux ext4-filesystem routines.
 #
 
-obj-$(CONFIG_EXT4DEV_FS) += ext4dev.o
+obj-$(CONFIG_EXT4_FS) += ext4.o
 
-ext4dev-y       := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \
+ext4-y  := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \
                    ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
                    ext4_jbd2.o migrate.o mballoc.o
 
-ext4dev-$(CONFIG_EXT4DEV_FS_XATTR)      += xattr.o xattr_user.o xattr_trusted.o
-ext4dev-$(CONFIG_EXT4DEV_FS_POSIX_ACL)  += acl.o
-ext4dev-$(CONFIG_EXT4DEV_FS_SECURITY)   += xattr_security.o
+ext4-$(CONFIG_EXT4_FS_XATTR)            += xattr.o xattr_user.o xattr_trusted.o
+ext4-$(CONFIG_EXT4_FS_POSIX_ACL)        += acl.o
+ext4-$(CONFIG_EXT4_FS_SECURITY)         += xattr_security.o
diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h
index cd2b855a07d6..cb45257a246e 100644
--- a/fs/ext4/acl.h
+++ b/fs/ext4/acl.h
@@ -51,18 +51,18 @@ static inline int ext4_acl_count(size_t size)
         }
 }
 
-#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
 
 /* Value for inode->u.ext4_i.i_acl and inode->u.ext4_i.i_default_acl
    if the ACL has not been cached */
 #define EXT4_ACL_NOT_CACHED ((void *)-1)
 
 /* acl.c */
-extern int ext4_permission (struct inode *, int);
-extern int ext4_acl_chmod (struct inode *);
-extern int ext4_init_acl (handle_t *, struct inode *, struct inode *);
+extern int ext4_permission(struct inode *, int);
+extern int ext4_acl_chmod(struct inode *);
+extern int ext4_init_acl(handle_t *, struct inode *, struct inode *);
 
-#else  /* CONFIG_EXT4DEV_FS_POSIX_ACL */
+#else  /* CONFIG_EXT4_FS_POSIX_ACL */
 #include <linux/sched.h>
 #define ext4_permission NULL
 
@@ -77,5 +77,5 @@ ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
 {
         return 0;
 }
-#endif  /* CONFIG_EXT4DEV_FS_POSIX_ACL */
+#endif  /* CONFIG_EXT4_FS_POSIX_ACL */
 
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index e9fa960ba6da..b9821be709bd 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -83,6 +83,7 @@ static int ext4_group_used_meta_blocks(struct super_block *sb,
         }
         return used_blocks;
 }
+
 /* Initializes an uninitialized block bitmap if given, and returns the
  * number of blocks free in the group. */
 unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
@@ -132,7 +133,7 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
                  */
                 group_blocks = ext4_blocks_count(sbi->s_es) -
                         le32_to_cpu(sbi->s_es->s_first_data_block) -
-                        (EXT4_BLOCKS_PER_GROUP(sb) * (sbi->s_groups_count -1));
+                        (EXT4_BLOCKS_PER_GROUP(sb) * (sbi->s_groups_count - 1));
         } else {
                 group_blocks = EXT4_BLOCKS_PER_GROUP(sb);
         }
@@ -200,20 +201,20 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
  * @bh:                 pointer to the buffer head to store the block
  *                      group descriptor
  */
-struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
+struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
                                              ext4_group_t block_group,
-                                             struct buffer_head ** bh)
+                                             struct buffer_head **bh)
 {
         unsigned long group_desc;
         unsigned long offset;
-        struct ext4_group_desc * desc;
+        struct ext4_group_desc *desc;
         struct ext4_sb_info *sbi = EXT4_SB(sb);
 
         if (block_group >= sbi->s_groups_count) {
-                ext4_error (sb, "ext4_get_group_desc",
-                            "block_group >= groups_count - "
-                            "block_group = %lu, groups_count = %lu",
-                            block_group, sbi->s_groups_count);
+                ext4_error(sb, "ext4_get_group_desc",
+                           "block_group >= groups_count - "
+                           "block_group = %lu, groups_count = %lu",
+                           block_group, sbi->s_groups_count);
 
                 return NULL;
         }
@@ -222,10 +223,10 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
         group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb);
         offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1);
         if (!sbi->s_group_desc[group_desc]) {
-                ext4_error (sb, "ext4_get_group_desc",
-                            "Group descriptor not loaded - "
-                            "block_group = %lu, group_desc = %lu, desc = %lu",
-                             block_group, group_desc, offset);
+                ext4_error(sb, "ext4_get_group_desc",
+                           "Group descriptor not loaded - "
+                           "block_group = %lu, group_desc = %lu, desc = %lu",
+                           block_group, group_desc, offset);
                 return NULL;
         }
 
@@ -302,8 +303,8 @@ err_out:
 struct buffer_head *
 ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 {
-        struct ext4_group_desc * desc;
-        struct buffer_head * bh = NULL;
+        struct ext4_group_desc *desc;
+        struct buffer_head *bh = NULL;
         ext4_fsblk_t bitmap_blk;
 
         desc = ext4_get_group_desc(sb, block_group, NULL);
@@ -318,9 +319,11 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
                             block_group, bitmap_blk);
                 return NULL;
         }
-        if (bh_uptodate_or_lock(bh))
+        if (buffer_uptodate(bh) &&
+            !(desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))
                 return bh;
 
+        lock_buffer(bh);
         spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group));
         if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
                 ext4_init_block_bitmap(sb, bh, block_group, desc);
@@ -345,301 +348,6 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
          */
         return bh;
 }
-/*
- * The reservation window structure operations
- * --------------------------------------------
- * Operations include:
- * dump, find, add, remove, is_empty, find_next_reservable_window, etc.
- *
- * We use a red-black tree to represent per-filesystem reservation
- * windows.
- *
- */
-
-/**
- * __rsv_window_dump() -- Dump the filesystem block allocation reservation map
- * @rb_root:            root of per-filesystem reservation rb tree
- * @verbose:            verbose mode
- * @fn:                 function which wishes to dump the reservation map
- *
- * If verbose is turned on, it will print the whole block reservation
- * windows(start, end). Otherwise, it will only print out the "bad" windows,
- * those windows that overlap with their immediate neighbors.
- */
-#if 1
-static void __rsv_window_dump(struct rb_root *root, int verbose,
-                              const char *fn)
-{
-        struct rb_node *n;
-        struct ext4_reserve_window_node *rsv, *prev;
-        int bad;
-
-restart:
-        n = rb_first(root);
-        bad = 0;
-        prev = NULL;
-
-        printk("Block Allocation Reservation Windows Map (%s):\n", fn);
-        while (n) {
-                rsv = rb_entry(n, struct ext4_reserve_window_node, rsv_node);
-                if (verbose)
-                        printk("reservation window 0x%p "
-                               "start:  %llu, end:  %llu\n",
-                               rsv, rsv->rsv_start, rsv->rsv_end);
-                if (rsv->rsv_start && rsv->rsv_start >= rsv->rsv_end) {
-                        printk("Bad reservation %p (start >= end)\n",
-                               rsv);
-                        bad = 1;
-                }
-                if (prev && prev->rsv_end >= rsv->rsv_start) {
-                        printk("Bad reservation %p (prev->end >= start)\n",
-                               rsv);
-                        bad = 1;
-                }
-                if (bad) {
-                        if (!verbose) {
-                                printk("Restarting reservation walk in verbose mode\n");
-                                verbose = 1;
-                                goto restart;
-                        }
-                }
-                n = rb_next(n);
-                prev = rsv;
-        }
-        printk("Window map complete.\n");
-        BUG_ON(bad);
-}
-#define rsv_window_dump(root, verbose) \
-        __rsv_window_dump((root), (verbose), __func__)
-#else
-#define rsv_window_dump(root, verbose) do {} while (0)
-#endif
-
-/**
- * goal_in_my_reservation()
- * @rsv:                inode's reservation window
- * @grp_goal:           given goal block relative to the allocation block group
- * @group:              the current allocation block group
- * @sb:                 filesystem super block
- *
- * Test if the given goal block (group relative) is within the file's
- * own block reservation window range.
- *
- * If the reservation window is outside the goal allocation group, return 0;
- * grp_goal (given goal block) could be -1, which means no specific
- * goal block. In this case, always return 1.
- * If the goal block is within the reservation window, return 1;
- * otherwise, return 0;
- */
-static int
-goal_in_my_reservation(struct ext4_reserve_window *rsv, ext4_grpblk_t grp_goal,
-                        ext4_group_t group, struct super_block *sb)
-{
-        ext4_fsblk_t group_first_block, group_last_block;
-
-        group_first_block = ext4_group_first_block_no(sb, group);
-        group_last_block = group_first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1);
-
-        if ((rsv->_rsv_start > group_last_block) ||
-            (rsv->_rsv_end < group_first_block))
-                return 0;
-        if ((grp_goal >= 0) && ((grp_goal + group_first_block < rsv->_rsv_start)
-                || (grp_goal + group_first_block > rsv->_rsv_end)))
-                return 0;
-        return 1;
-}
-
-/**
- * search_reserve_window()
- * @rb_root:            root of reservation tree
- * @goal:               target allocation block
- *
- * Find the reserved window which includes the goal, or the previous one
- * if the goal is not in any window.
- * Returns NULL if there are no windows or if all windows start after the goal.
- */
-static struct ext4_reserve_window_node *
-search_reserve_window(struct rb_root *root, ext4_fsblk_t goal)
-{
-        struct rb_node *n = root->rb_node;
-        struct ext4_reserve_window_node *rsv;
-
-        if (!n)
-                return NULL;
-
-        do {
-                rsv = rb_entry(n, struct ext4_reserve_window_node, rsv_node);
-
-                if (goal < rsv->rsv_start)
-                        n = n->rb_left;
-                else if (goal > rsv->rsv_end)
-                        n = n->rb_right;
-                else
-                        return rsv;
-        } while (n);
-        /*
-         * We've fallen off the end of the tree: the goal wasn't inside
-         * any particular node.  OK, the previous node must be to one
-         * side of the interval containing the goal.  If it's the RHS,
-         * we need to back up one.
-         */
-        if (rsv->rsv_start > goal) {
-                n = rb_prev(&rsv->rsv_node);
-                rsv = rb_entry(n, struct ext4_reserve_window_node, rsv_node);
-        }
-        return rsv;
-}
-
-/**
- * ext4_rsv_window_add() -- Insert a window to the block reservation rb tree.
- * @sb:                 super block
- * @rsv:                reservation window to add
- *
- * Must be called with rsv_lock hold.
- */
-void ext4_rsv_window_add(struct super_block *sb,
-                    struct ext4_reserve_window_node *rsv)
-{
-        struct rb_root *root = &EXT4_SB(sb)->s_rsv_window_root;
-        struct rb_node *node = &rsv->rsv_node;
-        ext4_fsblk_t start = rsv->rsv_start;
-
-        struct rb_node ** p = &root->rb_node;
-        struct rb_node * parent = NULL;
-        struct ext4_reserve_window_node *this;
-
-        while (*p)
-        {
-                parent = *p;
-                this = rb_entry(parent, struct ext4_reserve_window_node, rsv_node);
-
-                if (start < this->rsv_start)
-                        p = &(*p)->rb_left;
-                else if (start > this->rsv_end)
-                        p = &(*p)->rb_right;
-                else {
-                        rsv_window_dump(root, 1);
-                        BUG();
-                }
-        }
-
-        rb_link_node(node, parent, p);
-        rb_insert_color(node, root);
-}
-
-/**
- * ext4_rsv_window_remove() -- unlink a window from the reservation rb tree
- * @sb:                 super block
- * @rsv:                reservation window to remove
- *
- * Mark the block reservation window as not allocated, and unlink it
- * from the filesystem reservation window rb tree. Must be called with
- * rsv_lock hold.
- */
-static void rsv_window_remove(struct super_block *sb,
-                              struct ext4_reserve_window_node *rsv)
-{
-        rsv->rsv_start = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
-        rsv->rsv_end = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
-        rsv->rsv_alloc_hit = 0;
-        rb_erase(&rsv->rsv_node, &EXT4_SB(sb)->s_rsv_window_root);
-}
-
-/*
- * rsv_is_empty() -- Check if the reservation window is allocated.
- * @rsv:                given reservation window to check
- *
- * returns 1 if the end block is EXT4_RESERVE_WINDOW_NOT_ALLOCATED.
- */
-static inline int rsv_is_empty(struct ext4_reserve_window *rsv)
-{
-        /* a valid reservation end block could not be 0 */
-        return rsv->_rsv_end == EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
-}
-
-/**
- * ext4_init_block_alloc_info()
- * @inode:              file inode structure
- *
- * Allocate and initialize the  reservation window structure, and
- * link the window to the ext4 inode structure at last
- *
- * The reservation window structure is only dynamically allocated
- * and linked to ext4 inode the first time the open file
- * needs a new block. So, before every ext4_new_block(s) call, for
- * regular files, we should check whether the reservation window
- * structure exists or not. In the latter case, this function is called.
- * Fail to do so will result in block reservation being turned off for that
- * open file.
- *
- * This function is called from ext4_get_blocks_handle(), also called
- * when setting the reservation window size through ioctl before the file
- * is open for write (needs block allocation).
- *
- * Needs down_write(i_data_sem) protection prior to call this function.
- */
-void ext4_init_block_alloc_info(struct inode *inode)
-{
-        struct ext4_inode_info *ei = EXT4_I(inode);
-        struct ext4_block_alloc_info *block_i = ei->i_block_alloc_info;
-        struct super_block *sb = inode->i_sb;
-
-        block_i = kmalloc(sizeof(*block_i), GFP_NOFS);
-        if (block_i) {
-                struct ext4_reserve_window_node *rsv = &block_i->rsv_window_node;
-
-                rsv->rsv_start = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
-                rsv->rsv_end = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
-
-                /*
-                 * if filesystem is mounted with NORESERVATION, the goal
-                 * reservation window size is set to zero to indicate
-                 * block reservation is off
-                 */
-                if (!test_opt(sb, RESERVATION))
-                        rsv->rsv_goal_size = 0;
-                else
-                        rsv->rsv_goal_size = EXT4_DEFAULT_RESERVE_BLOCKS;
-                rsv->rsv_alloc_hit = 0;
-                block_i->last_alloc_logical_block = 0;
-                block_i->last_alloc_physical_block = 0;
-        }
-        ei->i_block_alloc_info = block_i;
-}
-
-/**
- * ext4_discard_reservation()
- * @inode:              inode
- *
- * Discard(free) block reservation window on last file close, or truncate
- * or at last iput().
- *
- * It is being called in three cases:
- *      ext4_release_file(): last writer close the file
- *      ext4_clear_inode(): last iput(), when nobody link to this file.
- *      ext4_truncate(): when the block indirect map is about to change.
- *
- */
-void ext4_discard_reservation(struct inode *inode)
-{
-        struct ext4_inode_info *ei = EXT4_I(inode);
-        struct ext4_block_alloc_info *block_i = ei->i_block_alloc_info;
-        struct ext4_reserve_window_node *rsv;
-        spinlock_t *rsv_lock = &EXT4_SB(inode->i_sb)->s_rsv_window_lock;
-
-        ext4_mb_discard_inode_preallocations(inode);
-
-        if (!block_i)
-                return;
-
-        rsv = &block_i->rsv_window_node;
-        if (!rsv_is_empty(&rsv->rsv_window)) {
-                spin_lock(rsv_lock);
-                if (!rsv_is_empty(&rsv->rsv_window))
-                        rsv_window_remove(inode->i_sb, rsv);
-                spin_unlock(rsv_lock);
-        }
-}
 
 /**
  * ext4_free_blocks_sb() -- Free given blocks and update quota
@@ -648,6 +356,13 @@ void ext4_discard_reservation(struct inode *inode)
  * @block:                      start physcial block to free
  * @count:                      number of blocks to free
  * @pdquot_freed_blocks:        pointer to quota
+ *
+ * XXX This function is only used by the on-line resizing code, which
+ * should probably be fixed up to call the mballoc variant.  There
+ * this needs to be cleaned up later; in fact, I'm not convinced this
+ * is 100% correct in the face of the mballoc code.  The online resizing
+ * code needs to be fixed up to more tightly (and correctly) interlock
+ * with the mballoc code.
  */
 void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
                          ext4_fsblk_t block, unsigned long count,
@@ -659,8 +374,8 @@ void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
         ext4_grpblk_t bit;
         unsigned long i;
         unsigned long overflow;
-        struct ext4_group_desc * desc;
-        struct ext4_super_block * es;
+        struct ext4_group_desc *desc;
+        struct ext4_super_block *es;
         struct ext4_sb_info *sbi;
         int err = 0, ret;
         ext4_grpblk_t group_freed;
@@ -671,13 +386,13 @@ void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
         if (block < le32_to_cpu(es->s_first_data_block) ||
             block + count < block ||
             block + count > ext4_blocks_count(es)) {
-                ext4_error (sb, "ext4_free_blocks",
-                            "Freeing blocks not in datazone - "
-                            "block = %llu, count = %lu", block, count);
+                ext4_error(sb, "ext4_free_blocks",
+                           "Freeing blocks not in datazone - "
+                           "block = %llu, count = %lu", block, count);
                 goto error_return;
         }
 
-        ext4_debug ("freeing block(s) %llu-%llu\n", block, block + count - 1);
+        ext4_debug("freeing block(s) %llu-%llu\n", block, block + count - 1);
 
 do_more:
         overflow = 0;
@@ -694,7 +409,7 @@ do_more:
         bitmap_bh = ext4_read_block_bitmap(sb, block_group);
         if (!bitmap_bh)
                 goto error_return;
-        desc = ext4_get_group_desc (sb, block_group, &gd_bh);
+        desc = ext4_get_group_desc(sb, block_group, &gd_bh);
         if (!desc)
                 goto error_return;
 
@@ -703,10 +418,10 @@ do_more:
             in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
             in_range(block + count - 1, ext4_inode_table(sb, desc),
                      sbi->s_itb_per_group)) {
-                ext4_error (sb, "ext4_free_blocks",
-                            "Freeing blocks in system zones - "
-                            "Block = %llu, count = %lu",
-                            block, count);
+                ext4_error(sb, "ext4_free_blocks",
+                           "Freeing blocks in system zones - "
+                           "Block = %llu, count = %lu",
+                           block, count);
                 goto error_return;
         }
 
@@ -848,759 +563,71 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
                         ext4_fsblk_t block, unsigned long count,
                         int metadata)
 {
-        struct super_block * sb;
+        struct super_block *sb;
         unsigned long dquot_freed_blocks;
 
         /* this isn't the right place to decide whether block is metadata
          * inode.c/extents.c knows better, but for safety ... */
-        if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode) ||
-                        ext4_should_journal_data(inode))
+        if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+                metadata = 1;
+
+        /* We need to make sure we don't reuse
+         * block released untill the transaction commit.
+         * writeback mode have weak data consistency so
+         * don't force data as metadata when freeing block
+         * for writeback mode.
+         */
+        if (metadata == 0 && !ext4_should_writeback_data(inode))
                 metadata = 1;
 
         sb = inode->i_sb;
 
-        if (!test_opt(sb, MBALLOC) || !EXT4_SB(sb)->s_group_info)
-                ext4_free_blocks_sb(handle, sb, block, count,
-                                                &dquot_freed_blocks);
-        else
-                ext4_mb_free_blocks(handle, inode, block, count,
-                                                metadata, &dquot_freed_blocks);
+        ext4_mb_free_blocks(handle, inode, block, count,
+                            metadata, &dquot_freed_blocks);
         if (dquot_freed_blocks)
                 DQUOT_FREE_BLOCK(inode, dquot_freed_blocks);
         return;
 }
 
-/**
- * ext4_test_allocatable()
- * @nr:                 given allocation block group
- * @bh:                 bufferhead contains the bitmap of the given block group
- *
- * For ext4 allocations, we must not reuse any blocks which are
- * allocated in the bitmap buffer's "last committed data" copy.  This
- * prevents deletes from freeing up the page for reuse until we have
- * committed the delete transaction.
- *
- * If we didn't do this, then deleting something and reallocating it as
- * data would allow the old block to be overwritten before the
- * transaction committed (because we force data to disk before commit).
- * This would lead to corruption if we crashed between overwriting the
- * data and committing the delete.
- *
- * @@@ We may want to make this allocation behaviour conditional on
- * data-writes at some point, and disable it for metadata allocations or
- * sync-data inodes.
- */
-static int ext4_test_allocatable(ext4_grpblk_t nr, struct buffer_head *bh)
+int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
+                                                s64 nblocks)
 {
-        int ret;
-        struct journal_head *jh = bh2jh(bh);
-
-        if (ext4_test_bit(nr, bh->b_data))
-                return 0;
-
-        jbd_lock_bh_state(bh);
-        if (!jh->b_committed_data)
-                ret = 1;
-        else
-                ret = !ext4_test_bit(nr, jh->b_committed_data);
-        jbd_unlock_bh_state(bh);
-        return ret;
-}
+        s64 free_blocks, dirty_blocks;
+        s64 root_blocks = 0;
+        struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
+        struct percpu_counter *dbc = &sbi->s_dirtyblocks_counter;
 
-/**
- * bitmap_search_next_usable_block()
- * @start:              the starting block (group relative) of the search
- * @bh:                 bufferhead contains the block group bitmap
- * @maxblocks:          the ending block (group relative) of the reservation
- *
- * The bitmap search --- search forward alternately through the actual
- * bitmap on disk and the last-committed copy in journal, until we find a
- * bit free in both bitmaps.
- */
-static ext4_grpblk_t
-bitmap_search_next_usable_block(ext4_grpblk_t start, struct buffer_head *bh,
-                                        ext4_grpblk_t maxblocks)
-{
-        ext4_grpblk_t next;
-        struct journal_head *jh = bh2jh(bh);
-
-        while (start < maxblocks) {
-                next = ext4_find_next_zero_bit(bh->b_data, maxblocks, start);
-                if (next >= maxblocks)
-                        return -1;
-                if (ext4_test_allocatable(next, bh))
-                        return next;
-                jbd_lock_bh_state(bh);
-                if (jh->b_committed_data)
-                        start = ext4_find_next_zero_bit(jh->b_committed_data,
-                                                        maxblocks, next);
-                jbd_unlock_bh_state(bh);
-        }
-        return -1;
-}
+        free_blocks  = percpu_counter_read_positive(fbc);
+        dirty_blocks = percpu_counter_read_positive(dbc);
 
-/**
- * find_next_usable_block()
- * @start:              the starting block (group relative) to find next
- *                      allocatable block in bitmap.
- * @bh:                 bufferhead contains the block group bitmap
- * @maxblocks:          the ending block (group relative) for the search
- *
- * Find an allocatable block in a bitmap.  We honor both the bitmap and
- * its last-committed copy (if that exists), and perform the "most
- * appropriate allocation" algorithm of looking for a free block near
- * the initial goal; then for a free byte somewhere in the bitmap; then
- * for any free bit in the bitmap.
- */
-static ext4_grpblk_t
-find_next_usable_block(ext4_grpblk_t start, struct buffer_head *bh,
-                        ext4_grpblk_t maxblocks)
-{
-        ext4_grpblk_t here, next;
-        char *p, *r;
-
-        if (start > 0) {
-                /*
-                 * The goal was occupied; search forward for a free
-                 * block within the next XX blocks.
-                 *
-                 * end_goal is more or less random, but it has to be
-                 * less than EXT4_BLOCKS_PER_GROUP. Aligning up to the
-                 * next 64-bit boundary is simple..
-                 */
-                ext4_grpblk_t end_goal = (start + 63) & ~63;
-                if (end_goal > maxblocks)
-                        end_goal = maxblocks;
-                here = ext4_find_next_zero_bit(bh->b_data, end_goal, start);
-                if (here < end_goal && ext4_test_allocatable(here, bh))
-                        return here;
-                ext4_debug("Bit not found near goal\n");
-        }
-
-        here = start;
-        if (here < 0)
-                here = 0;
-
-        p = ((char *)bh->b_data) + (here >> 3);
-        r = memscan(p, 0, ((maxblocks + 7) >> 3) - (here >> 3));
-        next = (r - ((char *)bh->b_data)) << 3;
-
-        if (next < maxblocks && next >= start && ext4_test_allocatable(next, bh))
-                return next;
-
-        /*
-         * The bitmap search --- search forward alternately through the actual
-         * bitmap and the last-committed copy until we find a bit free in
-         * both
-         */
-        here = bitmap_search_next_usable_block(here, bh, maxblocks);
-        return here;
-}
-
-/**
- * claim_block()
- * @block:              the free block (group relative) to allocate
- * @bh:                 the bufferhead containts the block group bitmap
- *
- * We think we can allocate this block in this bitmap.  Try to set the bit.
- * If that succeeds then check that nobody has allocated and then freed the
- * block since we saw that is was not marked in b_committed_data.  If it _was_
- * allocated and freed then clear the bit in the bitmap again and return
- * zero (failure).
- */
-static inline int
-claim_block(spinlock_t *lock, ext4_grpblk_t block, struct buffer_head *bh)
-{
-        struct journal_head *jh = bh2jh(bh);
-        int ret;
-
-        if (ext4_set_bit_atomic(lock, block, bh->b_data))
-                return 0;
-        jbd_lock_bh_state(bh);
-        if (jh->b_committed_data && ext4_test_bit(block,jh->b_committed_data)) {
-                ext4_clear_bit_atomic(lock, block, bh->b_data);
-                ret = 0;
-        } else {
-                ret = 1;
-        }
-        jbd_unlock_bh_state(bh);
-        return ret;
-}
-
-/**
- * ext4_try_to_allocate()
- * @sb:                 superblock
- * @handle:             handle to this transaction
- * @group:              given allocation block group
- * @bitmap_bh:          bufferhead holds the block bitmap
- * @grp_goal:           given target block within the group
- * @count:              target number of blocks to allocate
- * @my_rsv:             reservation window
- *
- * Attempt to allocate blocks within a give range. Set the range of allocation
- * first, then find the first free bit(s) from the bitmap (within the range),
- * and at last, allocate the blocks by claiming the found free bit as allocated.
- *
- * To set the range of this allocation:
- *      if there is a reservation window, only try to allocate block(s) from the
- *      file's own reservation window;
- *      Otherwise, the allocation range starts from the give goal block, ends at
- *      the block group's last block.
- *
- * If we failed to allocate the desired block then we may end up crossing to a
- * new bitmap.  In that case we must release write access to the old one via
- * ext4_journal_release_buffer(), else we'll run out of credits.
- */
-static ext4_grpblk_t
-ext4_try_to_allocate(struct super_block *sb, handle_t *handle,
-                        ext4_group_t group, struct buffer_head *bitmap_bh,
-                        ext4_grpblk_t grp_goal, unsigned long *count,
-                        struct ext4_reserve_window *my_rsv)
-{
-        ext4_fsblk_t group_first_block;
-        ext4_grpblk_t start, end;
-        unsigned long num = 0;
-
-        /* we do allocation within the reservation window if we have a window */
-        if (my_rsv) {
-                group_first_block = ext4_group_first_block_no(sb, group);
-                if (my_rsv->_rsv_start >= group_first_block)
-                        start = my_rsv->_rsv_start - group_first_block;
-                else
-                        /* reservation window cross group boundary */
-                        start = 0;
-                end = my_rsv->_rsv_end - group_first_block + 1;
-                if (end > EXT4_BLOCKS_PER_GROUP(sb))
-                        /* reservation window crosses group boundary */
-                        end = EXT4_BLOCKS_PER_GROUP(sb);
-                if ((start <= grp_goal) && (grp_goal < end))
-                        start = grp_goal;
-                else
-                        grp_goal = -1;
-        } else {
-                if (grp_goal > 0)
-                        start = grp_goal;
-                else
-                        start = 0;
-                end = EXT4_BLOCKS_PER_GROUP(sb);
-        }
-
-        BUG_ON(start > EXT4_BLOCKS_PER_GROUP(sb));
-
-repeat:
-        if (grp_goal < 0 || !ext4_test_allocatable(grp_goal, bitmap_bh)) {
-                grp_goal = find_next_usable_block(start, bitmap_bh, end);
-                if (grp_goal < 0)
-                        goto fail_access;
-                if (!my_rsv) {
-                        int i;
-
-                        for (i = 0; i < 7 && grp_goal > start &&
-                                        ext4_test_allocatable(grp_goal - 1,
-                                                                bitmap_bh);
-                                        i++, grp_goal--)
-                                ;
-                }
-        }
-        start = grp_goal;
-
-        if (!claim_block(sb_bgl_lock(EXT4_SB(sb), group),
-                grp_goal, bitmap_bh)) {
-                /*
-                 * The block was allocated by another thread, or it was
-                 * allocated and then freed by another thread
-                 */
-                start++;
-                grp_goal++;
-                if (start >= end)
-                        goto fail_access;
-                goto repeat;
-        }
-        num++;
-        grp_goal++;
-        while (num < *count && grp_goal < end
-                && ext4_test_allocatable(grp_goal, bitmap_bh)
-                && claim_block(sb_bgl_lock(EXT4_SB(sb), group),
-                                grp_goal, bitmap_bh)) {
-                num++;
-                grp_goal++;
-        }
-        *count = num;
-        return grp_goal - num;
-fail_access:
-        *count = num;
-        return -1;
-}
-
-/**
- *      find_next_reservable_window():
- *              find a reservable space within the given range.
- *              It does not allocate the reservation window for now:
- *              alloc_new_reservation() will do the work later.
- *
- *      @search_head: the head of the searching list;
- *              This is not necessarily the list head of the whole filesystem
- *
- *              We have both head and start_block to assist the search
- *              for the reservable space. The list starts from head,
- *              but we will shift to the place where start_block is,
- *              then start from there, when looking for a reservable space.
- *
- *      @size: the target new reservation window size
- *
- *      @group_first_block: the first block we consider to start
- *                      the real search from
- *
- *      @last_block:
- *              the maximum block number that our goal reservable space
- *              could start from. This is normally the last block in this
- *              group. The search will end when we found the start of next
- *              possible reservable space is out of this boundary.
- *              This could handle the cross boundary reservation window
- *              request.
- *
- *      basically we search from the given range, rather than the whole
- *      reservation double linked list, (start_block, last_block)
- *      to find a free region that is of my size and has not
- *      been reserved.
- *
- */
-static int find_next_reservable_window(
-                                struct ext4_reserve_window_node *search_head,
-                                struct ext4_reserve_window_node *my_rsv,
-                                struct super_block * sb,
-                                ext4_fsblk_t start_block,
-                                ext4_fsblk_t last_block)
-{
-        struct rb_node *next;
-        struct ext4_reserve_window_node *rsv, *prev;
-        ext4_fsblk_t cur;
-        int size = my_rsv->rsv_goal_size;
-
-        /* TODO: make the start of the reservation window byte-aligned */
-        /* cur = *start_block & ~7;*/
-        cur = start_block;
-        rsv = search_head;
-        if (!rsv)
-                return -1;
-
-        while (1) {
-                if (cur <= rsv->rsv_end)
-                        cur = rsv->rsv_end + 1;
-
-                /* TODO?
-                 * in the case we could not find a reservable space
-                 * that is what is expected, during the re-search, we could
-                 * remember what's the largest reservable space we could have
-                 * and return that one.
-                 *
-                 * For now it will fail if we could not find the reservable
-                 * space with expected-size (or more)...
-                 */
-                if (cur > last_block)
-                        return -1;              /* fail */
-
-                prev = rsv;
-                next = rb_next(&rsv->rsv_node);
-                rsv = rb_entry(next,struct ext4_reserve_window_node,rsv_node);
+        if (!capable(CAP_SYS_RESOURCE) &&
+                sbi->s_resuid != current->fsuid &&
+                (sbi->s_resgid == 0 || !in_group_p(sbi->s_resgid)))
+                root_blocks = ext4_r_blocks_count(sbi->s_es);
 
-                /*
-                 * Reached the last reservation, we can just append to the
-                 * previous one.
-                 */
-                if (!next)
-                        break;
-
-                if (cur + size <= rsv->rsv_start) {
-                        /*
-                         * Found a reserveable space big enough.  We could
-                         * have a reservation across the group boundary here
-                         */
-                        break;
+        if (free_blocks - (nblocks + root_blocks + dirty_blocks) <
+                                                EXT4_FREEBLOCKS_WATERMARK) {
+                free_blocks  = percpu_counter_sum(fbc);
+                dirty_blocks = percpu_counter_sum(dbc);
+                if (dirty_blocks < 0) {
+                        printk(KERN_CRIT "Dirty block accounting "
+                                        "went wrong %lld\n",
+                                        dirty_blocks);
                 }
         }
-        /*
-         * we come here either :
-         * when we reach the end of the whole list,
-         * and there is empty reservable space after last entry in the list.
-         * append it to the end of the list.
-         *
-         * or we found one reservable space in the middle of the list,
-         * return the reservation window that we could append to.
-         * succeed.
+        /* Check whether we have space after
+         * accounting for current dirty blocks
          */
+        if (free_blocks < ((root_blocks + nblocks) + dirty_blocks))
+                /* we don't have free space */
+                return -ENOSPC;
 
-        if ((prev != my_rsv) && (!rsv_is_empty(&my_rsv->rsv_window)))
-                rsv_window_remove(sb, my_rsv);
-
-        /*
-         * Let's book the whole avaliable window for now.  We will check the
-         * disk bitmap later and then, if there are free blocks then we adjust
-         * the window size if it's larger than requested.
-         * Otherwise, we will remove this node from the tree next time
-         * call find_next_reservable_window.
-         */
-        my_rsv->rsv_start = cur;
-        my_rsv->rsv_end = cur + size - 1;
-        my_rsv->rsv_alloc_hit = 0;
-
-        if (prev != my_rsv)
-                ext4_rsv_window_add(sb, my_rsv);
-
+        /* Add the blocks to nblocks */
+        percpu_counter_add(dbc, nblocks);
         return 0;
 }
 
 /**
- *      alloc_new_reservation()--allocate a new reservation window
- *
- *              To make a new reservation, we search part of the filesystem
- *              reservation list (the list that inside the group). We try to
- *              allocate a new reservation window near the allocation goal,
- *              or the beginning of the group, if there is no goal.
- *
- *              We first find a reservable space after the goal, then from
- *              there, we check the bitmap for the first free block after
- *              it. If there is no free block until the end of group, then the
- *              whole group is full, we failed. Otherwise, check if the free
- *              block is inside the expected reservable space, if so, we
- *              succeed.
- *              If the first free block is outside the reservable space, then
- *              start from the first free block, we search for next available
- *              space, and go on.
- *
- *      on succeed, a new reservation will be found and inserted into the list
- *      It contains at least one free block, and it does not overlap with other
- *      reservation windows.
- *
- *      failed: we failed to find a reservation window in this group
- *
- *      @rsv: the reservation
- *
- *      @grp_goal: The goal (group-relative).  It is where the search for a
- *              free reservable space should start from.
- *              if we have a grp_goal(grp_goal >0 ), then start from there,
- *              no grp_goal(grp_goal = -1), we start from the first block
- *              of the group.
- *
- *      @sb: the super block
- *      @group: the group we are trying to allocate in
- *      @bitmap_bh: the block group block bitmap
- *
- */
-static int alloc_new_reservation(struct ext4_reserve_window_node *my_rsv,
-                ext4_grpblk_t grp_goal, struct super_block *sb,
-                ext4_group_t group, struct buffer_head *bitmap_bh)
-{
-        struct ext4_reserve_window_node *search_head;
-        ext4_fsblk_t group_first_block, group_end_block, start_block;
-        ext4_grpblk_t first_free_block;
-        struct rb_root *fs_rsv_root = &EXT4_SB(sb)->s_rsv_window_root;
-        unsigned long size;
-        int ret;
-        spinlock_t *rsv_lock = &EXT4_SB(sb)->s_rsv_window_lock;
-
-        group_first_block = ext4_group_first_block_no(sb, group);
-        group_end_block = group_first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1);
-
-        if (grp_goal < 0)
-                start_block = group_first_block;
-        else
-                start_block = grp_goal + group_first_block;
-
-        size = my_rsv->rsv_goal_size;
-
-        if (!rsv_is_empty(&my_rsv->rsv_window)) {
-                /*
-                 * if the old reservation is cross group boundary
-                 * and if the goal is inside the old reservation window,
-                 * we will come here when we just failed to allocate from
-                 * the first part of the window. We still have another part
-                 * that belongs to the next group. In this case, there is no
-                 * point to discard our window and try to allocate a new one
-                 * in this group(which will fail). we should
-                 * keep the reservation window, just simply move on.
-                 *
-                 * Maybe we could shift the start block of the reservation
-                 * window to the first block of next group.
-                 */
-
-                if ((my_rsv->rsv_start <= group_end_block) &&
-                                (my_rsv->rsv_end > group_end_block) &&
-                                (start_block >= my_rsv->rsv_start))
-                        return -1;
-
-                if ((my_rsv->rsv_alloc_hit >
-                     (my_rsv->rsv_end - my_rsv->rsv_start + 1) / 2)) {
-                        /*
-                         * if the previously allocation hit ratio is
-                         * greater than 1/2, then we double the size of
-                         * the reservation window the next time,
-                         * otherwise we keep the same size window
-                         */
-                        size = size * 2;
-                        if (size > EXT4_MAX_RESERVE_BLOCKS)
-                                size = EXT4_MAX_RESERVE_BLOCKS;
-                        my_rsv->rsv_goal_size= size;
-                }
-        }
-
-        spin_lock(rsv_lock);
-        /*
-         * shift the search start to the window near the goal block
-         */
-        search_head = search_reserve_window(fs_rsv_root, start_block);
-
-        /*
-         * find_next_reservable_window() simply finds a reservable window
-         * inside the given range(start_block, group_end_block).
-         *
-         * To make sure the reservation window has a free bit inside it, we
-         * need to check the bitmap after we found a reservable window.
-         */
-retry:
-        ret = find_next_reservable_window(search_head, my_rsv, sb,
-                                                start_block, group_end_block);
-
-        if (ret == -1) {
-                if (!rsv_is_empty(&my_rsv->rsv_window))
-                        rsv_window_remove(sb, my_rsv);
-                spin_unlock(rsv_lock);
-                return -1;
-        }
-
-        /*
-         * On success, find_next_reservable_window() returns the
-         * reservation window where there is a reservable space after it.
-         * Before we reserve this reservable space, we need
-         * to make sure there is at least a free block inside this region.
-         *
-         * searching the first free bit on the block bitmap and copy of
-         * last committed bitmap alternatively, until we found a allocatable
-         * block. Search start from the start block of the reservable space
-         * we just found.
-         */
-        spin_unlock(rsv_lock);
-        first_free_block = bitmap_search_next_usable_block(
-                        my_rsv->rsv_start - group_first_block,
-                        bitmap_bh, group_end_block - group_first_block + 1);
-
-        if (first_free_block < 0) {
-                /*
-                 * no free block left on the bitmap, no point
-                 * to reserve the space. return failed.
-                 */
-                spin_lock(rsv_lock);
-                if (!rsv_is_empty(&my_rsv->rsv_window))
-                        rsv_window_remove(sb, my_rsv);
-                spin_unlock(rsv_lock);
-                return -1;              /* failed */
-        }
-
-        start_block = first_free_block + group_first_block;
-        /*
-         * check if the first free block is within the
-         * free space we just reserved
-         */
-        if (start_block >= my_rsv->rsv_start && start_block <= my_rsv->rsv_end)
-                return 0;               /* success */
-        /*
-         * if the first free bit we found is out of the reservable space
-         * continue search for next reservable space,
-         * start from where the free block is,
-         * we also shift the list head to where we stopped last time
-         */
-        search_head = my_rsv;
-        spin_lock(rsv_lock);
-        goto retry;
-}
-
-/**
- * try_to_extend_reservation()
- * @my_rsv:             given reservation window
- * @sb:                 super block
- * @size:               the delta to extend
- *
- * Attempt to expand the reservation window large enough to have
- * required number of free blocks
- *
- * Since ext4_try_to_allocate() will always allocate blocks within
- * the reservation window range, if the window size is too small,
- * multiple blocks allocation has to stop at the end of the reservation
- * window. To make this more efficient, given the total number of
- * blocks needed and the current size of the window, we try to
- * expand the reservation window size if necessary on a best-effort
- * basis before ext4_new_blocks() tries to allocate blocks,
- */
-static void try_to_extend_reservation(struct ext4_reserve_window_node *my_rsv,
-                        struct super_block *sb, int size)
-{
-        struct ext4_reserve_window_node *next_rsv;
-        struct rb_node *next;
-        spinlock_t *rsv_lock = &EXT4_SB(sb)->s_rsv_window_lock;
-
-        if (!spin_trylock(rsv_lock))
-                return;
-
-        next = rb_next(&my_rsv->rsv_node);
-
-        if (!next)
-                my_rsv->rsv_end += size;
-        else {
-                next_rsv = rb_entry(next, struct ext4_reserve_window_node, rsv_node);
-
-                if ((next_rsv->rsv_start - my_rsv->rsv_end - 1) >= size)
-                        my_rsv->rsv_end += size;
-                else
-                        my_rsv->rsv_end = next_rsv->rsv_start - 1;
-        }
-        spin_unlock(rsv_lock);
-}
-
-/**
- * ext4_try_to_allocate_with_rsv()
- * @sb:                 superblock
- * @handle:             handle to this transaction
- * @group:              given allocation block group
- * @bitmap_bh:          bufferhead holds the block bitmap
- * @grp_goal:           given target block within the group
- * @count:              target number of blocks to allocate
- * @my_rsv:             reservation window
- * @errp:               pointer to store the error code
- *
- * This is the main function used to allocate a new block and its reservation
- * window.
- *
- * Each time when a new block allocation is need, first try to allocate from
- * its own reservation.  If it does not have a reservation window, instead of
- * looking for a free bit on bitmap first, then look up the reservation list to
- * see if it is inside somebody else's reservation window, we try to allocate a
- * reservation window for it starting from the goal first. Then do the block
- * allocation within the reservation window.
- *
- * This will avoid keeping on searching the reservation list again and
- * again when somebody is looking for a free block (without
- * reservation), and there are lots of free blocks, but they are all
- * being reserved.
- *
- * We use a red-black tree for the per-filesystem reservation list.
- *
- */
-static ext4_grpblk_t
-ext4_try_to_allocate_with_rsv(struct super_block *sb, handle_t *handle,
-                        ext4_group_t group, struct buffer_head *bitmap_bh,
-                        ext4_grpblk_t grp_goal,
-                        struct ext4_reserve_window_node * my_rsv,
-                        unsigned long *count, int *errp)
-{
-        ext4_fsblk_t group_first_block, group_last_block;
-        ext4_grpblk_t ret = 0;
-        int fatal;
-        unsigned long num = *count;
-
-        *errp = 0;
-
-        /*
-         * Make sure we use undo access for the bitmap, because it is critical
-         * that we do the frozen_data COW on bitmap buffers in all cases even
-         * if the buffer is in BJ_Forget state in the committing transaction.
-         */
-        BUFFER_TRACE(bitmap_bh, "get undo access for new block");
-        fatal = ext4_journal_get_undo_access(handle, bitmap_bh);
-        if (fatal) {
-                *errp = fatal;
-                return -1;
-        }
-
-        /*
-         * we don't deal with reservation when
-         * filesystem is mounted without reservation
-         * or the file is not a regular file
-         * or last attempt to allocate a block with reservation turned on failed
-         */
-        if (my_rsv == NULL ) {
-                ret = ext4_try_to_allocate(sb, handle, group, bitmap_bh,
-                                                grp_goal, count, NULL);
-                goto out;
-        }
-        /*
-         * grp_goal is a group relative block number (if there is a goal)
-         * 0 <= grp_goal < EXT4_BLOCKS_PER_GROUP(sb)
-         * first block is a filesystem wide block number
-         * first block is the block number of the first block in this group
-         */
-        group_first_block = ext4_group_first_block_no(sb, group);
-        group_last_block = group_first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1);
-
-        /*
-         * Basically we will allocate a new block from inode's reservation
-         * window.
-         *
-         * We need to allocate a new reservation window, if:
-         * a) inode does not have a reservation window; or
-         * b) last attempt to allocate a block from existing reservation
-         *    failed; or
-         * c) we come here with a goal and with a reservation window
-         *
-         * We do not need to allocate a new reservation window if we come here
-         * at the beginning with a goal and the goal is inside the window, or
-         * we don't have a goal but already have a reservation window.
-         * then we could go to allocate from the reservation window directly.
-         */
-        while (1) {
-                if (rsv_is_empty(&my_rsv->rsv_window) || (ret < 0) ||
-                        !goal_in_my_reservation(&my_rsv->rsv_window,
-                                                grp_goal, group, sb)) {
-                        if (my_rsv->rsv_goal_size < *count)
-                                my_rsv->rsv_goal_size = *count;
-                        ret = alloc_new_reservation(my_rsv, grp_goal, sb,
-                                                        group, bitmap_bh);
-                        if (ret < 0)
-                                break;                  /* failed */
-
-                        if (!goal_in_my_reservation(&my_rsv->rsv_window,
-                                                        grp_goal, group, sb))
-                                grp_goal = -1;
-                } else if (grp_goal >= 0) {
-                        int curr = my_rsv->rsv_end -
-                                        (grp_goal + group_first_block) + 1;
-
-                        if (curr < *count)
-                                try_to_extend_reservation(my_rsv, sb,
-                                                        *count - curr);
-                }
-
-                if ((my_rsv->rsv_start > group_last_block) ||
-                                (my_rsv->rsv_end < group_first_block)) {
-                        rsv_window_dump(&EXT4_SB(sb)->s_rsv_window_root, 1);
-                        BUG();
-                }
-                ret = ext4_try_to_allocate(sb, handle, group, bitmap_bh,
-                                           grp_goal, &num, &my_rsv->rsv_window);
-                if (ret >= 0) {
-                        my_rsv->rsv_alloc_hit += num;
-                        *count = num;
-                        break;                          /* succeed */
-                }
-                num = *count;
-        }
-out:
-        if (ret >= 0) {
-                BUFFER_TRACE(bitmap_bh, "journal_dirty_metadata for "
-                                        "bitmap block");
-                fatal = ext4_journal_dirty_metadata(handle, bitmap_bh);
-                if (fatal) {
-                        *errp = fatal;
-                        return -1;
-                }
-                return ret;
-        }
-
-        BUFFER_TRACE(bitmap_bh, "journal_release_buffer");
-        ext4_journal_release_buffer(handle, bitmap_bh);
-        return ret;
-}
-
-/**
  * ext4_has_free_blocks()
  * @sbi:        in-core super block structure.
  * @nblocks:    number of neeed blocks
@@ -1610,29 +637,34 @@ out:
  * On success, return nblocks
  */
 ext4_fsblk_t ext4_has_free_blocks(struct ext4_sb_info *sbi,
-                                                ext4_fsblk_t nblocks)
+                                                s64 nblocks)
 {
-        ext4_fsblk_t free_blocks;
-        ext4_fsblk_t root_blocks = 0;
+        s64 free_blocks, dirty_blocks;
+        s64 root_blocks = 0;
+        struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
+        struct percpu_counter *dbc = &sbi->s_dirtyblocks_counter;
 
-        free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
+        free_blocks  = percpu_counter_read_positive(fbc);
+        dirty_blocks = percpu_counter_read_positive(dbc);
 
         if (!capable(CAP_SYS_RESOURCE) &&
                 sbi->s_resuid != current->fsuid &&
                 (sbi->s_resgid == 0 || !in_group_p(sbi->s_resgid)))
                 root_blocks = ext4_r_blocks_count(sbi->s_es);
-#ifdef CONFIG_SMP
-        if (free_blocks - root_blocks < FBC_BATCH)
-                free_blocks =
-                        percpu_counter_sum_and_set(&sbi->s_freeblocks_counter);
-#endif
-        if (free_blocks <= root_blocks)
+
+        if (free_blocks - (nblocks + root_blocks + dirty_blocks) <
+                                                EXT4_FREEBLOCKS_WATERMARK) {
+                free_blocks  = percpu_counter_sum(fbc);
+                dirty_blocks = percpu_counter_sum(dbc);
+        }
+        if (free_blocks <= (root_blocks + dirty_blocks))
                 /* we don't have free space */
                 return 0;
-        if (free_blocks - root_blocks < nblocks)
-                return free_blocks - root_blocks;
+
+        if (free_blocks - (root_blocks + dirty_blocks) < nblocks)
+                return free_blocks - (root_blocks + dirty_blocks);
         return nblocks;
- }
+}
 
 
 /**
@@ -1657,303 +689,6 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries)
         return jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
 }
 
-/**
- * ext4_old_new_blocks() -- core block bitmap based block allocation function
- *
- * @handle:             handle to this transaction
- * @inode:              file inode
- * @goal:               given target block(filesystem wide)
- * @count:              target number of blocks to allocate
- * @errp:               error code
- *
- * ext4_old_new_blocks uses a goal block to assist allocation and look up
- * the block bitmap directly to do block allocation.  It tries to
- * allocate block(s) from the block group contains the goal block first. If
- * that fails, it will try to allocate block(s) from other block groups
- * without any specific goal block.
- *
- * This function is called when -o nomballoc mount option is enabled
- *
- */
-ext4_fsblk_t ext4_old_new_blocks(handle_t *handle, struct inode *inode,
-                        ext4_fsblk_t goal, unsigned long *count, int *errp)
-{
-        struct buffer_head *bitmap_bh = NULL;
-        struct buffer_head *gdp_bh;
-        ext4_group_t group_no;
-        ext4_group_t goal_group;
-        ext4_grpblk_t grp_target_blk;   /* blockgroup relative goal block */
-        ext4_grpblk_t grp_alloc_blk;    /* blockgroup-relative allocated block*/
-        ext4_fsblk_t ret_block;         /* filesyetem-wide allocated block */
-        ext4_group_t bgi;                       /* blockgroup iteration index */
-        int fatal = 0, err;
-        int performed_allocation = 0;
-        ext4_grpblk_t free_blocks;      /* number of free blocks in a group */
-        struct super_block *sb;
-        struct ext4_group_desc *gdp;
-        struct ext4_super_block *es;
-        struct ext4_sb_info *sbi;
-        struct ext4_reserve_window_node *my_rsv = NULL;
-        struct ext4_block_alloc_info *block_i;
-        unsigned short windowsz = 0;
-        ext4_group_t ngroups;
-        unsigned long num = *count;
-
-        sb = inode->i_sb;
-        if (!sb) {
-                *errp = -ENODEV;
-                printk("ext4_new_block: nonexistent device");
-                return 0;
-        }
-
-        sbi = EXT4_SB(sb);
-        if (!EXT4_I(inode)->i_delalloc_reserved_flag) {
-                /*
-                 * With delalloc we already reserved the blocks
-                 */
-                *count = ext4_has_free_blocks(sbi, *count);
-        }
-        if (*count == 0) {
-                *errp = -ENOSPC;
-                return 0;       /*return with ENOSPC error */
-        }
-        num = *count;
-
-        /*
-         * Check quota for allocation of this block.
-         */
-        if (DQUOT_ALLOC_BLOCK(inode, num)) {
-                *errp = -EDQUOT;
-                return 0;
-        }
-
-        sbi = EXT4_SB(sb);
-        es = EXT4_SB(sb)->s_es;
-        ext4_debug("goal=%llu.\n", goal);
-        /*
-         * Allocate a block from reservation only when
-         * filesystem is mounted with reservation(default,-o reservation), and
-         * it's a regular file, and
-         * the desired window size is greater than 0 (One could use ioctl
-         * command EXT4_IOC_SETRSVSZ to set the window size to 0 to turn off
-         * reservation on that particular file)
-         */
-        block_i = EXT4_I(inode)->i_block_alloc_info;
-        if (block_i && ((windowsz = block_i->rsv_window_node.rsv_goal_size) > 0))
-                my_rsv = &block_i->rsv_window_node;
-
-        /*
-         * First, test whether the goal block is free.
-         */
-        if (goal < le32_to_cpu(es->s_first_data_block) ||
-            goal >= ext4_blocks_count(es))
-                goal = le32_to_cpu(es->s_first_data_block);
-        ext4_get_group_no_and_offset(sb, goal, &group_no, &grp_target_blk);
-        goal_group = group_no;
-retry_alloc:
-        gdp = ext4_get_group_desc(sb, group_no, &gdp_bh);
-        if (!gdp)
-                goto io_error;
-
-        free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
-        /*
-         * if there is not enough free blocks to make a new resevation
-         * turn off reservation for this allocation
-         */
-        if (my_rsv && (free_blocks < windowsz)
-                && (rsv_is_empty(&my_rsv->rsv_window)))
-                my_rsv = NULL;
-
-        if (free_blocks > 0) {
-                bitmap_bh = ext4_read_block_bitmap(sb, group_no);
-                if (!bitmap_bh)
-                        goto io_error;
-                grp_alloc_blk = ext4_try_to_allocate_with_rsv(sb, handle,
-                                        group_no, bitmap_bh, grp_target_blk,
-                                        my_rsv, &num, &fatal);
-                if (fatal)
-                        goto out;
-                if (grp_alloc_blk >= 0)
-                        goto allocated;
-        }
-
-        ngroups = EXT4_SB(sb)->s_groups_count;
-        smp_rmb();
-
-        /*
-         * Now search the rest of the groups.  We assume that
-         * group_no and gdp correctly point to the last group visited.
-         */
-        for (bgi = 0; bgi < ngroups; bgi++) {
-                group_no++;
-                if (group_no >= ngroups)
-                        group_no = 0;
-                gdp = ext4_get_group_desc(sb, group_no, &gdp_bh);
-                if (!gdp)
-                        goto io_error;
-                free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
-                /*
-                 * skip this group if the number of
-                 * free blocks is less than half of the reservation
-                 * window size.
-                 */
-                if (free_blocks <= (windowsz/2))
-                        continue;
-
-                brelse(bitmap_bh);
-                bitmap_bh = ext4_read_block_bitmap(sb, group_no);
-                if (!bitmap_bh)
-                        goto io_error;
-                /*
-                 * try to allocate block(s) from this group, without a goal(-1).
-                 */
-                grp_alloc_blk = ext4_try_to_allocate_with_rsv(sb, handle,
-                                        group_no, bitmap_bh, -1, my_rsv,
-                                        &num, &fatal);
-                if (fatal)
-                        goto out;
-                if (grp_alloc_blk >= 0)
-                        goto allocated;
-        }
-        /*
-         * We may end up a bogus ealier ENOSPC error due to
-         * filesystem is "full" of reservations, but
-         * there maybe indeed free blocks avaliable on disk
-         * In this case, we just forget about the reservations
-         * just do block allocation as without reservations.
-         */
-        if (my_rsv) {
-                my_rsv = NULL;
-                windowsz = 0;
-                group_no = goal_group;
-                goto retry_alloc;
-        }
-        /* No space left on the device */
-        *errp = -ENOSPC;
-        goto out;
-
-allocated:
-
-        ext4_debug("using block group %lu(%d)\n",
-                        group_no, gdp->bg_free_blocks_count);
-
-        BUFFER_TRACE(gdp_bh, "get_write_access");
-        fatal = ext4_journal_get_write_access(handle, gdp_bh);
-        if (fatal)
-                goto out;
-
-        ret_block = grp_alloc_blk + ext4_group_first_block_no(sb, group_no);
-
-        if (in_range(ext4_block_bitmap(sb, gdp), ret_block, num) ||
-            in_range(ext4_inode_bitmap(sb, gdp), ret_block, num) ||
-            in_range(ret_block, ext4_inode_table(sb, gdp),
-                     EXT4_SB(sb)->s_itb_per_group) ||
-            in_range(ret_block + num - 1, ext4_inode_table(sb, gdp),
-                     EXT4_SB(sb)->s_itb_per_group)) {
-                ext4_error(sb, "ext4_new_block",
-                            "Allocating block in system zone - "
-                            "blocks from %llu, length %lu",
-                             ret_block, num);
-                /*
-                 * claim_block marked the blocks we allocated
-                 * as in use. So we may want to selectively
-                 * mark some of the blocks as free
-                 */
-                goto retry_alloc;
-        }
-
-        performed_allocation = 1;
-
-#ifdef CONFIG_JBD2_DEBUG
-        {
-                struct buffer_head *debug_bh;
-
-                /* Record bitmap buffer state in the newly allocated block */
-                debug_bh = sb_find_get_block(sb, ret_block);
-                if (debug_bh) {
-                        BUFFER_TRACE(debug_bh, "state when allocated");
-                        BUFFER_TRACE2(debug_bh, bitmap_bh, "bitmap state");
-                        brelse(debug_bh);
-                }
-        }
-        jbd_lock_bh_state(bitmap_bh);
-        spin_lock(sb_bgl_lock(sbi, group_no));
-        if (buffer_jbd(bitmap_bh) && bh2jh(bitmap_bh)->b_committed_data) {
-                int i;
-
-                for (i = 0; i < num; i++) {
-                        if (ext4_test_bit(grp_alloc_blk+i,
-                                        bh2jh(bitmap_bh)->b_committed_data)) {
-                                printk("%s: block was unexpectedly set in "
-                                        "b_committed_data\n", __func__);
-                        }
-                }
-        }
-        ext4_debug("found bit %d\n", grp_alloc_blk);
-        spin_unlock(sb_bgl_lock(sbi, group_no));
-        jbd_unlock_bh_state(bitmap_bh);
-#endif
-
-        if (ret_block + num - 1 >= ext4_blocks_count(es)) {
-                ext4_error(sb, "ext4_new_block",
-                            "block(%llu) >= blocks count(%llu) - "
-                            "block_group = %lu, es == %p ", ret_block,
-                        ext4_blocks_count(es), group_no, es);
-                goto out;
-        }
-
-        /*
-         * It is up to the caller to add the new buffer to a journal
-         * list of some description.  We don't know in advance whether
-         * the caller wants to use it as metadata or data.
-         */
-        spin_lock(sb_bgl_lock(sbi, group_no));
-        if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))
-                gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
-        le16_add_cpu(&gdp->bg_free_blocks_count, -num);
-        gdp->bg_checksum = ext4_group_desc_csum(sbi, group_no, gdp);
-        spin_unlock(sb_bgl_lock(sbi, group_no));
-        if (!EXT4_I(inode)->i_delalloc_reserved_flag)
-                percpu_counter_sub(&sbi->s_freeblocks_counter, num);
-
-        if (sbi->s_log_groups_per_flex) {
-                ext4_group_t flex_group = ext4_flex_group(sbi, group_no);
-                spin_lock(sb_bgl_lock(sbi, flex_group));
-                sbi->s_flex_groups[flex_group].free_blocks -= num;
-                spin_unlock(sb_bgl_lock(sbi, flex_group));
-        }
-
-        BUFFER_TRACE(gdp_bh, "journal_dirty_metadata for group descriptor");
-        err = ext4_journal_dirty_metadata(handle, gdp_bh);
-        if (!fatal)
-                fatal = err;
-
-        sb->s_dirt = 1;
-        if (fatal)
-                goto out;
-
-        *errp = 0;
-        brelse(bitmap_bh);
-        DQUOT_FREE_BLOCK(inode, *count-num);
-        *count = num;
-        return ret_block;
-
-io_error:
-        *errp = -EIO;
-out:
-        if (fatal) {
-                *errp = fatal;
-                ext4_std_error(sb, fatal);
-        }
-        /*
-         * Undo the block allocation
-         */
-        if (!performed_allocation)
-                DQUOT_FREE_BLOCK(inode, *count);
-        brelse(bitmap_bh);
-        return 0;
-}
-
 #define EXT4_META_BLOCK 0x1
 
 static ext4_fsblk_t do_blk_alloc(handle_t *handle, struct inode *inode,
@@ -1963,10 +698,6 @@ static ext4_fsblk_t do_blk_alloc(handle_t *handle, struct inode *inode,
         struct ext4_allocation_request ar;
         ext4_fsblk_t ret;
 
-        if (!test_opt(inode->i_sb, MBALLOC)) {
-                return ext4_old_new_blocks(handle, inode, goal, count, errp);
-        }
-
         memset(&ar, 0, sizeof(ar));
         /* Fill with neighbour allocated blocks */
 
@@ -2008,7 +739,7 @@ ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
         /*
          * Account for the allocated meta blocks
          */
-        if (!(*errp)) {
+        if (!(*errp) && EXT4_I(inode)->i_delalloc_reserved_flag) {
                 spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
                 EXT4_I(inode)->i_allocated_meta_blocks += *count;
                 spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
@@ -2093,10 +824,9 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
                 bitmap_count += x;
         }
         brelse(bitmap_bh);
-        printk("ext4_count_free_blocks: stored = %llu"
-                ", computed = %llu, %llu\n",
-                ext4_free_blocks_count(es),
-                desc_count, bitmap_count);
+        printk(KERN_DEBUG "ext4_count_free_blocks: stored = %llu"
+                ", computed = %llu, %llu\n", ext4_free_blocks_count(es),
+               desc_count, bitmap_count);
         return bitmap_count;
 #else
         desc_count = 0;
@@ -2183,8 +913,9 @@ unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group)
 
         if (!EXT4_HAS_INCOMPAT_FEATURE(sb,EXT4_FEATURE_INCOMPAT_META_BG) ||
                         metagroup < first_meta_bg)
-                return ext4_bg_num_gdb_nometa(sb,group);
+                return ext4_bg_num_gdb_nometa(sb, group);
 
         return ext4_bg_num_gdb_meta(sb,group);
 
 }
+
diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c
index d37ea6750454..0a7a6663c190 100644
--- a/fs/ext4/bitmap.c
+++ b/fs/ext4/bitmap.c
@@ -15,17 +15,17 @@
 
 static const int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0};
 
-unsigned long ext4_count_free (struct buffer_head * map, unsigned int numchars)
+unsigned long ext4_count_free(struct buffer_head *map, unsigned int numchars)
 {
         unsigned int i;
         unsigned long sum = 0;
 
         if (!map)
-                return (0);
+                return 0;
         for (i = 0; i < numchars; i++)
                 sum += nibblemap[map->b_data[i] & 0xf] +
                         nibblemap[(map->b_data[i] >> 4) & 0xf];
-        return (sum);
+        return sum;
 }
 
 #endif  /*  EXT4FS_DEBUG  */
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index ec8e33b45219..3ca6a2b7632d 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -33,10 +33,10 @@ static unsigned char ext4_filetype_table[] = {
 };
 
 static int ext4_readdir(struct file *, void *, filldir_t);
-static int ext4_dx_readdir(struct file * filp,
-                           void * dirent, filldir_t filldir);
-static int ext4_release_dir (struct inode * inode,
-                                struct file * filp);
+static int ext4_dx_readdir(struct file *filp,
+                           void *dirent, filldir_t filldir);
+static int ext4_release_dir(struct inode *inode,
+                                struct file *filp);
 
 const struct file_operations ext4_dir_operations = {
         .llseek         = generic_file_llseek,
@@ -61,12 +61,12 @@ static unsigned char get_dtype(struct super_block *sb, int filetype)
 }
 
 
-int ext4_check_dir_entry (const char * function, struct inode * dir,
-                          struct ext4_dir_entry_2 * de,
-                          struct buffer_head * bh,
-                          unsigned long offset)
+int ext4_check_dir_entry(const char *function, struct inode *dir,
+                         struct ext4_dir_entry_2 *de,
+                         struct buffer_head *bh,
+                         unsigned long offset)
 {
-        const char * error_msg = NULL;
+        const char *error_msg = NULL;
         const int rlen = ext4_rec_len_from_disk(de->rec_len);
 
         if (rlen < EXT4_DIR_REC_LEN(1))
@@ -82,7 +82,7 @@ int ext4_check_dir_entry (const char * function, struct inode * dir,
                 error_msg = "inode out of bounds";
 
         if (error_msg != NULL)
-                ext4_error (dir->i_sb, function,
+                ext4_error(dir->i_sb, function,
                         "bad entry in directory #%lu: %s - "
                         "offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
                         dir->i_ino, error_msg, offset,
@@ -91,8 +91,8 @@ int ext4_check_dir_entry (const char * function, struct inode * dir,
         return error_msg == NULL ? 1 : 0;
 }
 
-static int ext4_readdir(struct file * filp,
-                         void * dirent, filldir_t filldir)
+static int ext4_readdir(struct file *filp,
+                         void *dirent, filldir_t filldir)
 {
         int error = 0;
         unsigned long offset;
@@ -102,6 +102,7 @@ static int ext4_readdir(struct file * filp,
         int err;
         struct inode *inode = filp->f_path.dentry->d_inode;
         int ret = 0;
+        int dir_has_error = 0;
 
         sb = inode->i_sb;
 
@@ -148,9 +149,13 @@ static int ext4_readdir(struct file * filp,
                  * of recovering data when there's a bad sector
                  */
                 if (!bh) {
-                        ext4_error (sb, "ext4_readdir",
-                                "directory #%lu contains a hole at offset %lu",
-                                inode->i_ino, (unsigned long)filp->f_pos);
+                        if (!dir_has_error) {
+                                ext4_error(sb, __func__, "directory #%lu "
+                                           "contains a hole at offset %Lu",
+                                           inode->i_ino,
+                                           (unsigned long long) filp->f_pos);
+                                dir_has_error = 1;
+                        }
                         /* corrupt size?  Maybe no more blocks to read */
                         if (filp->f_pos > inode->i_blocks << 9)
                                 break;
@@ -187,14 +192,14 @@ revalidate:
                 while (!error && filp->f_pos < inode->i_size
                        && offset < sb->s_blocksize) {
                         de = (struct ext4_dir_entry_2 *) (bh->b_data + offset);
-                        if (!ext4_check_dir_entry ("ext4_readdir", inode, de,
-                                                   bh, offset)) {
+                        if (!ext4_check_dir_entry("ext4_readdir", inode, de,
+                                                  bh, offset)) {
                                 /*
                                  * On error, skip the f_pos to the next block
                                  */
                                 filp->f_pos = (filp->f_pos |
                                                 (sb->s_blocksize - 1)) + 1;
-                                brelse (bh);
+                                brelse(bh);
                                 ret = stored;
                                 goto out;
                         }
@@ -218,12 +223,12 @@ revalidate:
                                         break;
                                 if (version != filp->f_version)
                                         goto revalidate;
-                                stored ++;
+                                stored++;
                         }
                         filp->f_pos += ext4_rec_len_from_disk(de->rec_len);
                 }
                 offset = 0;
-                brelse (bh);
+                brelse(bh);
         }
 out:
         return ret;
@@ -290,9 +295,9 @@ static void free_rb_tree_fname(struct rb_root *root)
                 parent = rb_parent(n);
                 fname = rb_entry(n, struct fname, rb_hash);
                 while (fname) {
-                        struct fname * old = fname;
+                        struct fname *old = fname;
                         fname = fname->next;
-                        kfree (old);
+                        kfree(old);
                 }
                 if (!parent)
                         root->rb_node = NULL;
@@ -331,7 +336,7 @@ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
                              struct ext4_dir_entry_2 *dirent)
 {
         struct rb_node **p, *parent = NULL;
-        struct fname * fname, *new_fn;
+        struct fname *fname, *new_fn;
         struct dir_private_info *info;
         int len;
 
@@ -388,19 +393,20 @@ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
  * for all entres on the fname linked list.  (Normally there is only
  * one entry on the linked list, unless there are 62 bit hash collisions.)
  */
-static int call_filldir(struct file * filp, void * dirent,
+static int call_filldir(struct file *filp, void *dirent,
                         filldir_t filldir, struct fname *fname)
 {
         struct dir_private_info *info = filp->private_data;
         loff_t  curr_pos;
         struct inode *inode = filp->f_path.dentry->d_inode;
-        struct super_block * sb;
+        struct super_block *sb;
         int error;
 
         sb = inode->i_sb;
 
         if (!fname) {
-                printk("call_filldir: called with null fname?!?\n");
+                printk(KERN_ERR "ext4: call_filldir: called with "
+                       "null fname?!?\n");
                 return 0;
         }
         curr_pos = hash2pos(fname->hash, fname->minor_hash);
@@ -419,8 +425,8 @@ static int call_filldir(struct file * filp, void * dirent,
         return 0;
 }
 
-static int ext4_dx_readdir(struct file * filp,
-                         void * dirent, filldir_t filldir)
+static int ext4_dx_readdir(struct file *filp,
+                         void *dirent, filldir_t filldir)
 {
         struct dir_private_info *info = filp->private_data;
         struct inode *inode = filp->f_path.dentry->d_inode;
@@ -511,7 +517,7 @@ finished:
         return 0;
 }
 
-static int ext4_release_dir (struct inode * inode, struct file * filp)
+static int ext4_release_dir(struct inode *inode, struct file *filp)
 {
         if (filp->private_data)
                 ext4_htree_free_dir_info(filp->private_data);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 295003241d3d..4880cc3e6727 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -44,9 +44,9 @@
 #ifdef EXT4FS_DEBUG
 #define ext4_debug(f, a...)                                             \
         do {                                                            \
-                printk (KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:",       \
+                printk(KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:",        \
                         __FILE__, __LINE__, __func__);                  \
-                printk (KERN_DEBUG f, ## a);                            \
+                printk(KERN_DEBUG f, ## a);                             \
         } while (0)
 #else
 #define ext4_debug(f, a...)     do {} while (0)
@@ -128,7 +128,7 @@ struct ext4_allocation_request {
 #else
 # define EXT4_BLOCK_SIZE(s)             (EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size)
 #endif
-#define EXT4_ADDR_PER_BLOCK(s)          (EXT4_BLOCK_SIZE(s) / sizeof (__u32))
+#define EXT4_ADDR_PER_BLOCK(s)          (EXT4_BLOCK_SIZE(s) / sizeof(__u32))
 #ifdef __KERNEL__
 # define EXT4_BLOCK_SIZE_BITS(s)        ((s)->s_blocksize_bits)
 #else
@@ -245,7 +245,7 @@ struct flex_groups {
 #define EXT4_RESERVED_FL                0x80000000 /* reserved for ext4 lib */
 
 #define EXT4_FL_USER_VISIBLE            0x000BDFFF /* User visible flags */
-#define EXT4_FL_USER_MODIFIABLE         0x000380FF /* User modifiable flags */
+#define EXT4_FL_USER_MODIFIABLE         0x000B80FF /* User modifiable flags */
 
 /*
  * Inode dynamic state flags
@@ -291,8 +291,6 @@ struct ext4_new_group_data {
 #define EXT4_IOC_SETFLAGS               FS_IOC_SETFLAGS
 #define EXT4_IOC_GETVERSION             _IOR('f', 3, long)
 #define EXT4_IOC_SETVERSION             _IOW('f', 4, long)
-#define EXT4_IOC_GROUP_EXTEND           _IOW('f', 7, unsigned long)
-#define EXT4_IOC_GROUP_ADD              _IOW('f', 8,struct ext4_new_group_input)
 #define EXT4_IOC_GETVERSION_OLD         FS_IOC_GETVERSION
 #define EXT4_IOC_SETVERSION_OLD         FS_IOC_SETVERSION
 #ifdef CONFIG_JBD2_DEBUG
@@ -300,7 +298,10 @@ struct ext4_new_group_data {
 #endif
 #define EXT4_IOC_GETRSVSZ               _IOR('f', 5, long)
 #define EXT4_IOC_SETRSVSZ               _IOW('f', 6, long)
-#define EXT4_IOC_MIGRATE                _IO('f', 7)
+#define EXT4_IOC_GROUP_EXTEND           _IOW('f', 7, unsigned long)
+#define EXT4_IOC_GROUP_ADD              _IOW('f', 8, struct ext4_new_group_input)
+#define EXT4_IOC_MIGRATE                _IO('f', 9)
+ /* note ioctl 11 reserved for filesystem-independent FIEMAP ioctl */
 
 /*
  * ioctl commands in 32 bit emulation
@@ -510,7 +511,6 @@ do {									       \
 /*
  * Mount flags
  */
-#define EXT4_MOUNT_CHECK                0x00001 /* Do mount-time checks */
 #define EXT4_MOUNT_OLDALLOC             0x00002  /* Don't use the new Orlov allocator */
 #define EXT4_MOUNT_GRPID                0x00004 /* Create files with directory's group */
 #define EXT4_MOUNT_DEBUG                0x00008 /* Some debugging messages */
@@ -538,8 +538,9 @@ do {									       \
 #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_MBALLOC              0x4000000 /* Buddy allocation support */
 #define EXT4_MOUNT_DELALLOC             0x8000000 /* Delalloc support */
+#define EXT4_MOUNT_DATA_ERR_ABORT       0x10000000 /* Abort on file data write */
+
 /* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */
 #ifndef _LINUX_EXT2_FS_H
 #define clear_opt(o, opt)               o &= ~EXT4_MOUNT_##opt
@@ -667,7 +668,7 @@ struct ext4_super_block {
 };
 
 #ifdef __KERNEL__
-static inline struct ext4_sb_info * EXT4_SB(struct super_block *sb)
+static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
 {
         return sb->s_fs_info;
 }
@@ -725,11 +726,11 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
  */
 
 #define EXT4_HAS_COMPAT_FEATURE(sb,mask)                        \
-        ( EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask) )
+        (EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask))
 #define EXT4_HAS_RO_COMPAT_FEATURE(sb,mask)                     \
-        ( EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask) )
+        (EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask))
 #define EXT4_HAS_INCOMPAT_FEATURE(sb,mask)                      \
-        ( EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask) )
+        (EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask))
 #define EXT4_SET_COMPAT_FEATURE(sb,mask)                        \
         EXT4_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask)
 #define EXT4_SET_RO_COMPAT_FEATURE(sb,mask)                     \
@@ -789,6 +790,8 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 #define EXT4_DEF_RESUID         0
 #define EXT4_DEF_RESGID         0
 
+#define EXT4_DEF_INODE_READAHEAD_BLKS   32
+
 /*
  * Default mount options
  */
@@ -954,6 +957,24 @@ ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no)
 void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
                         unsigned long *blockgrpp, ext4_grpblk_t *offsetp);
 
+extern struct proc_dir_entry *ext4_proc_root;
+
+#ifdef CONFIG_PROC_FS
+extern const struct file_operations ext4_ui_proc_fops;
+
+#define EXT4_PROC_HANDLER(name, var)                                    \
+do {                                                                    \
+        proc = proc_create_data(name, mode, sbi->s_proc,                \
+                                &ext4_ui_proc_fops, &sbi->s_##var);     \
+        if (proc == NULL) {                                             \
+                printk(KERN_ERR "EXT4-fs: can't create %s\n", name);    \
+                goto err_out;                                           \
+        }                                                               \
+} while (0)
+#else
+#define EXT4_PROC_HANDLER(name, var)
+#endif
+
 /*
  * Function prototypes
  */
@@ -981,23 +1002,20 @@ extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode,
 extern ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
                                         ext4_lblk_t iblock, ext4_fsblk_t goal,
                                         unsigned long *count, int *errp);
-extern ext4_fsblk_t ext4_old_new_blocks(handle_t *handle, struct inode *inode,
-                        ext4_fsblk_t goal, unsigned long *count, int *errp);
+extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi, s64 nblocks);
 extern ext4_fsblk_t ext4_has_free_blocks(struct ext4_sb_info *sbi,
-                                                ext4_fsblk_t nblocks);
-extern void ext4_free_blocks (handle_t *handle, struct inode *inode,
+                                         s64 nblocks);
+extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
                         ext4_fsblk_t block, unsigned long count, int metadata);
-extern void ext4_free_blocks_sb (handle_t *handle, struct super_block *sb,
-                                 ext4_fsblk_t block, unsigned long count,
+extern void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
+                                ext4_fsblk_t block, unsigned long count,
                                 unsigned long *pdquot_freed_blocks);
-extern ext4_fsblk_t ext4_count_free_blocks (struct super_block *);
-extern void ext4_check_blocks_bitmap (struct super_block *);
+extern ext4_fsblk_t ext4_count_free_blocks(struct super_block *);
+extern void ext4_check_blocks_bitmap(struct super_block *);
 extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
                                                     ext4_group_t block_group,
                                                     struct buffer_head ** bh);
 extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
-extern void ext4_init_block_alloc_info(struct inode *);
-extern void ext4_rsv_window_add(struct super_block *sb, struct ext4_reserve_window_node *rsv);
 
 /* dir.c */
 extern int ext4_check_dir_entry(const char *, struct inode *,
@@ -1009,20 +1027,20 @@ extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
 extern void ext4_htree_free_dir_info(struct dir_private_info *p);
 
 /* fsync.c */
-extern int ext4_sync_file (struct file *, struct dentry *, int);
+extern int ext4_sync_file(struct file *, struct dentry *, int);
 
 /* hash.c */
 extern int ext4fs_dirhash(const char *name, int len, struct
                           dx_hash_info *hinfo);
 
 /* ialloc.c */
-extern struct inode * ext4_new_inode (handle_t *, struct inode *, int);
-extern void ext4_free_inode (handle_t *, struct inode *);
-extern struct inode * ext4_orphan_get (struct super_block *, unsigned long);
-extern unsigned long ext4_count_free_inodes (struct super_block *);
-extern unsigned long ext4_count_dirs (struct super_block *);
-extern void ext4_check_inodes_bitmap (struct super_block *);
-extern unsigned long ext4_count_free (struct buffer_head *, unsigned);
+extern struct inode * ext4_new_inode(handle_t *, struct inode *, int);
+extern void ext4_free_inode(handle_t *, struct inode *);
+extern struct inode * ext4_orphan_get(struct super_block *, unsigned long);
+extern unsigned long ext4_count_free_inodes(struct super_block *);
+extern unsigned long ext4_count_dirs(struct super_block *);
+extern void ext4_check_inodes_bitmap(struct super_block *);
+extern unsigned long ext4_count_free(struct buffer_head *, unsigned);
 
 /* mballoc.c */
 extern long ext4_mb_stats;
@@ -1032,7 +1050,7 @@ extern int ext4_mb_release(struct super_block *);
 extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *,
                                 struct ext4_allocation_request *, int *);
 extern int ext4_mb_reserve_blocks(struct super_block *, int);
-extern void ext4_mb_discard_inode_preallocations(struct inode *);
+extern void ext4_discard_preallocations(struct inode *);
 extern int __init init_ext4_mballoc(void);
 extern void exit_ext4_mballoc(void);
 extern void ext4_mb_free_blocks(handle_t *, struct inode *,
@@ -1050,24 +1068,25 @@ struct buffer_head *ext4_getblk(handle_t *, struct inode *,
                                                 ext4_lblk_t, int, int *);
 struct buffer_head *ext4_bread(handle_t *, struct inode *,
                                                 ext4_lblk_t, int, int *);
+int ext4_get_block(struct inode *inode, sector_t iblock,
+                                struct buffer_head *bh_result, int create);
 int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
                                 ext4_lblk_t iblock, unsigned long maxblocks,
                                 struct buffer_head *bh_result,
                                 int create, int extend_disksize);
 
 extern struct inode *ext4_iget(struct super_block *, unsigned long);
-extern int  ext4_write_inode (struct inode *, int);
-extern int  ext4_setattr (struct dentry *, struct iattr *);
+extern int  ext4_write_inode(struct inode *, int);
+extern int  ext4_setattr(struct dentry *, struct iattr *);
 extern int  ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
                                 struct kstat *stat);
-extern void ext4_delete_inode (struct inode *);
-extern int  ext4_sync_inode (handle_t *, struct inode *);
-extern void ext4_discard_reservation (struct inode *);
+extern void ext4_delete_inode(struct inode *);
+extern int  ext4_sync_inode(handle_t *, struct inode *);
 extern void ext4_dirty_inode(struct inode *);
 extern int ext4_change_inode_journal_flag(struct inode *, int);
 extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
 extern int ext4_can_truncate(struct inode *inode);
-extern void ext4_truncate (struct inode *);
+extern void ext4_truncate(struct inode *);
 extern void ext4_set_inode_flags(struct inode *);
 extern void ext4_get_inode_flags(struct ext4_inode_info *);
 extern void ext4_set_aops(struct inode *inode);
@@ -1080,11 +1099,10 @@ extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct page *page);
 
 /* ioctl.c */
 extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
-extern long ext4_compat_ioctl (struct file *, unsigned int, unsigned long);
+extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
 
 /* migrate.c */
-extern int ext4_ext_migrate(struct inode *, struct file *, unsigned int,
-                       unsigned long);
+extern int ext4_ext_migrate(struct inode *);
 /* namei.c */
 extern int ext4_orphan_add(handle_t *, struct inode *);
 extern int ext4_orphan_del(handle_t *, struct inode *);
@@ -1099,14 +1117,14 @@ extern int ext4_group_extend(struct super_block *sb,
                                 ext4_fsblk_t n_blocks_count);
 
 /* super.c */
-extern void ext4_error (struct super_block *, const char *, const char *, ...)
+extern void ext4_error(struct super_block *, const char *, const char *, ...)
         __attribute__ ((format (printf, 3, 4)));
-extern void __ext4_std_error (struct super_block *, const char *, int);
-extern void ext4_abort (struct super_block *, const char *, const char *, ...)
+extern void __ext4_std_error(struct super_block *, const char *, int);
+extern void ext4_abort(struct super_block *, const char *, const char *, ...)
         __attribute__ ((format (printf, 3, 4)));
-extern void ext4_warning (struct super_block *, const char *, const char *, ...)
+extern void ext4_warning(struct super_block *, const char *, const char *, ...)
         __attribute__ ((format (printf, 3, 4)));
-extern void ext4_update_dynamic_rev (struct super_block *sb);
+extern void ext4_update_dynamic_rev(struct super_block *sb);
 extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb,
                                         __u32 compat);
 extern int ext4_update_rocompat_feature(handle_t *handle,
@@ -1179,7 +1197,7 @@ static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size)
 
 static inline
 struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
-                                                        ext4_group_t group)
+                                            ext4_group_t group)
 {
          struct ext4_group_info ***grp_info;
          long indexv, indexh;
@@ -1207,6 +1225,28 @@ do {								\
                 __ext4_std_error((sb), __func__, (errno));      \
 } while (0)
 
+#ifdef CONFIG_SMP
+/* Each CPU can accumulate FBC_BATCH blocks in their local
+ * counters. So we need to make sure we have free blocks more
+ * than FBC_BATCH  * nr_cpu_ids. Also add a window of 4 times.
+ */
+#define EXT4_FREEBLOCKS_WATERMARK (4 * (FBC_BATCH * nr_cpu_ids))
+#else
+#define EXT4_FREEBLOCKS_WATERMARK 0
+#endif
+
+static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
+{
+        /*
+         * XXX: replace with spinlock if seen contended -bzzz
+         */
+        down_write(&EXT4_I(inode)->i_data_sem);
+        if (newsize > EXT4_I(inode)->i_disksize)
+                EXT4_I(inode)->i_disksize = newsize;
+        up_write(&EXT4_I(inode)->i_data_sem);
+        return ;
+}
+
 /*
  * Inodes and files operations
  */
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index d33dc56d6986..bec7ce59fc0d 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -124,6 +124,19 @@ struct ext4_ext_path {
 #define EXT4_EXT_CACHE_GAP      1
 #define EXT4_EXT_CACHE_EXTENT   2
 
+/*
+ * to be called by ext4_ext_walk_space()
+ * negative retcode - error
+ * positive retcode - signal for ext4_ext_walk_space(), see below
+ * callback must return valid extent (passed or newly created)
+ */
+typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *,
+                                        struct ext4_ext_cache *,
+                                        struct ext4_extent *, void *);
+
+#define EXT_CONTINUE   0
+#define EXT_BREAK      1
+#define EXT_REPEAT     2
 
 #define EXT_MAX_BLOCK   0xffffffff
 
@@ -224,6 +237,8 @@ extern int ext4_ext_try_to_merge(struct inode *inode,
                                  struct ext4_extent *);
 extern unsigned int ext4_ext_check_overlap(struct inode *, struct ext4_extent *, struct ext4_ext_path *);
 extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *);
+extern int ext4_ext_walk_space(struct inode *, ext4_lblk_t, ext4_lblk_t,
+                                                        ext_prepare_callback, void *);
 extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t,
                                                         struct ext4_ext_path *);
 extern int ext4_ext_search_left(struct inode *, struct ext4_ext_path *,
diff --git a/fs/ext4/ext4_i.h b/fs/ext4/ext4_i.h
index ef7409f0e7e4..5c124c0ac6d3 100644
--- a/fs/ext4/ext4_i.h
+++ b/fs/ext4/ext4_i.h
@@ -33,38 +33,6 @@ typedef __u32 ext4_lblk_t;
 /* data type for block group number */
 typedef unsigned long ext4_group_t;
 
-struct ext4_reserve_window {
-        ext4_fsblk_t    _rsv_start;     /* First byte reserved */
-        ext4_fsblk_t    _rsv_end;       /* Last byte reserved or 0 */
-};
-
-struct ext4_reserve_window_node {
-        struct rb_node          rsv_node;
-        __u32                   rsv_goal_size;
-        __u32                   rsv_alloc_hit;
-        struct ext4_reserve_window      rsv_window;
-};
-
-struct ext4_block_alloc_info {
-        /* information about reservation window */
-        struct ext4_reserve_window_node rsv_window_node;
-        /*
-         * was i_next_alloc_block in ext4_inode_info
-         * is the logical (file-relative) number of the
-         * most-recently-allocated block in this file.
-         * We use this for detecting linearly ascending allocation requests.
-         */
-        ext4_lblk_t last_alloc_logical_block;
-        /*
-         * Was i_next_alloc_goal in ext4_inode_info
-         * is the *physical* companion to i_next_alloc_block.
-         * it the physical block number of the block which was most-recentl
-         * allocated to this file.  This give us the goal (target) for the next
-         * allocation when we detect linearly ascending requests.
-         */
-        ext4_fsblk_t last_alloc_physical_block;
-};
-
 #define rsv_start rsv_window._rsv_start
 #define rsv_end rsv_window._rsv_end
 
@@ -97,11 +65,8 @@ struct ext4_inode_info {
         ext4_group_t    i_block_group;
         __u32   i_state;                /* Dynamic state flags for ext4 */
 
-        /* block reservation info */
-        struct ext4_block_alloc_info *i_block_alloc_info;
-
         ext4_lblk_t             i_dir_start_lookup;
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
         /*
          * Extended attributes can be read independently of the main file
          * data. Taking i_mutex even when reading would cause contention
@@ -111,7 +76,7 @@ struct ext4_inode_info {
          */
         struct rw_semaphore xattr_sem;
 #endif
-#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
         struct posix_acl        *i_acl;
         struct posix_acl        *i_default_acl;
 #endif
diff --git a/fs/ext4/ext4_sb.h b/fs/ext4/ext4_sb.h
index 6300226d5531..445fde603df8 100644
--- a/fs/ext4/ext4_sb.h
+++ b/fs/ext4/ext4_sb.h
@@ -40,8 +40,8 @@ struct ext4_sb_info {
         unsigned long s_blocks_last;    /* Last seen block count */
         loff_t s_bitmap_maxbytes;       /* max bytes for bitmap files */
         struct buffer_head * s_sbh;     /* Buffer containing the super block */
-        struct ext4_super_block * s_es; /* Pointer to the super block in the buffer */
-        struct buffer_head ** s_group_desc;
+        struct ext4_super_block *s_es;  /* Pointer to the super block in the buffer */
+        struct buffer_head **s_group_desc;
         unsigned long  s_mount_opt;
         ext4_fsblk_t s_sb_block;
         uid_t s_resuid;
@@ -52,6 +52,7 @@ struct ext4_sb_info {
         int s_desc_per_block_bits;
         int s_inode_size;
         int s_first_ino;
+        unsigned int s_inode_readahead_blks;
         spinlock_t s_next_gen_lock;
         u32 s_next_generation;
         u32 s_hash_seed[4];
@@ -59,16 +60,17 @@ struct ext4_sb_info {
         struct percpu_counter s_freeblocks_counter;
         struct percpu_counter s_freeinodes_counter;
         struct percpu_counter s_dirs_counter;
+        struct percpu_counter s_dirtyblocks_counter;
         struct blockgroup_lock s_blockgroup_lock;
+        struct proc_dir_entry *s_proc;
 
         /* root of the per fs reservation window tree */
         spinlock_t s_rsv_window_lock;
         struct rb_root s_rsv_window_root;
-        struct ext4_reserve_window_node s_rsv_window_head;
 
         /* Journaling */
-        struct inode * s_journal_inode;
-        struct journal_s * s_journal;
+        struct inode *s_journal_inode;
+        struct journal_s *s_journal;
         struct list_head s_orphan;
         unsigned long s_commit_interval;
         struct block_device *journal_bdev;
@@ -97,21 +99,18 @@ struct ext4_sb_info {
         struct inode *s_buddy_cache;
         long s_blocks_reserved;
         spinlock_t s_reserve_lock;
-        struct list_head s_active_transaction;
-        struct list_head s_closed_transaction;
-        struct list_head s_committed_transaction;
         spinlock_t s_md_lock;
         tid_t s_last_transaction;
         unsigned short *s_mb_offsets, *s_mb_maxs;
 
         /* tunables */
         unsigned long s_stripe;
-        unsigned long s_mb_stream_request;
-        unsigned long s_mb_max_to_scan;
-        unsigned long s_mb_min_to_scan;
-        unsigned long s_mb_stats;
-        unsigned long s_mb_order2_reqs;
-        unsigned long s_mb_group_prealloc;
+        unsigned int s_mb_stream_request;
+        unsigned int s_mb_max_to_scan;
+        unsigned int s_mb_min_to_scan;
+        unsigned int s_mb_stats;
+        unsigned int s_mb_order2_reqs;
+        unsigned int s_mb_group_prealloc;
         /* where last allocation was done - for stream allocation */
         unsigned long s_mb_last_group;
         unsigned long s_mb_last_start;
@@ -121,7 +120,6 @@ struct ext4_sb_info {
         int s_mb_history_cur;
         int s_mb_history_max;
         int s_mb_history_num;
-        struct proc_dir_entry *s_mb_proc;
         spinlock_t s_mb_history_lock;
         int s_mb_history_filter;
 
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index b24d3c53f20c..ea2ce3c0ae66 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -40,6 +40,7 @@
 #include <linux/slab.h>
 #include <linux/falloc.h>
 #include <asm/uaccess.h>
+#include <linux/fiemap.h>
 #include "ext4_jbd2.h"
 #include "ext4_extents.h"
 
@@ -383,8 +384,8 @@ static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path)
         ext_debug("\n");
 }
 #else
-#define ext4_ext_show_path(inode,path)
-#define ext4_ext_show_leaf(inode,path)
+#define ext4_ext_show_path(inode, path)
+#define ext4_ext_show_leaf(inode, path)
 #endif
 
 void ext4_ext_drop_refs(struct ext4_ext_path *path)
@@ -440,9 +441,10 @@ ext4_ext_binsearch_idx(struct inode *inode,
                 for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ix++) {
                   if (k != 0 &&
                       le32_to_cpu(ix->ei_block) <= le32_to_cpu(ix[-1].ei_block)) {
-                                printk("k=%d, ix=0x%p, first=0x%p\n", k,
-                                        ix, EXT_FIRST_INDEX(eh));
-                                printk("%u <= %u\n",
+                                printk(KERN_DEBUG "k=%d, ix=0x%p, "
+                                       "first=0x%p\n", k,
+                                       ix, EXT_FIRST_INDEX(eh));
+                                printk(KERN_DEBUG "%u <= %u\n",
                                        le32_to_cpu(ix->ei_block),
                                        le32_to_cpu(ix[-1].ei_block));
                         }
@@ -1475,7 +1477,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
                                 struct ext4_ext_path *path,
                                 struct ext4_extent *newext)
 {
-        struct ext4_extent_header * eh;
+        struct ext4_extent_header *eh;
         struct ext4_extent *ex, *fex;
         struct ext4_extent *nearex; /* nearest extent */
         struct ext4_ext_path *npath = NULL;
@@ -1625,6 +1627,113 @@ cleanup:
         return err;
 }
 
+int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block,
+                        ext4_lblk_t num, ext_prepare_callback func,
+                        void *cbdata)
+{
+        struct ext4_ext_path *path = NULL;
+        struct ext4_ext_cache cbex;
+        struct ext4_extent *ex;
+        ext4_lblk_t next, start = 0, end = 0;
+        ext4_lblk_t last = block + num;
+        int depth, exists, err = 0;
+
+        BUG_ON(func == NULL);
+        BUG_ON(inode == NULL);
+
+        while (block < last && block != EXT_MAX_BLOCK) {
+                num = last - block;
+                /* find extent for this block */
+                path = ext4_ext_find_extent(inode, block, path);
+                if (IS_ERR(path)) {
+                        err = PTR_ERR(path);
+                        path = NULL;
+                        break;
+                }
+
+                depth = ext_depth(inode);
+                BUG_ON(path[depth].p_hdr == NULL);
+                ex = path[depth].p_ext;
+                next = ext4_ext_next_allocated_block(path);
+
+                exists = 0;
+                if (!ex) {
+                        /* there is no extent yet, so try to allocate
+                         * all requested space */
+                        start = block;
+                        end = block + num;
+                } else if (le32_to_cpu(ex->ee_block) > block) {
+                        /* need to allocate space before found extent */
+                        start = block;
+                        end = le32_to_cpu(ex->ee_block);
+                        if (block + num < end)
+                                end = block + num;
+                } else if (block >= le32_to_cpu(ex->ee_block)
+                                        + ext4_ext_get_actual_len(ex)) {
+                        /* need to allocate space after found extent */
+                        start = block;
+                        end = block + num;
+                        if (end >= next)
+                                end = next;
+                } else if (block >= le32_to_cpu(ex->ee_block)) {
+                        /*
+                         * some part of requested space is covered
+                         * by found extent
+                         */
+                        start = block;
+                        end = le32_to_cpu(ex->ee_block)
+                                + ext4_ext_get_actual_len(ex);
+                        if (block + num < end)
+                                end = block + num;
+                        exists = 1;
+                } else {
+                        BUG();
+                }
+                BUG_ON(end <= start);
+
+                if (!exists) {
+                        cbex.ec_block = start;
+                        cbex.ec_len = end - start;
+                        cbex.ec_start = 0;
+                        cbex.ec_type = EXT4_EXT_CACHE_GAP;
+                } else {
+                        cbex.ec_block = le32_to_cpu(ex->ee_block);
+                        cbex.ec_len = ext4_ext_get_actual_len(ex);
+                        cbex.ec_start = ext_pblock(ex);
+                        cbex.ec_type = EXT4_EXT_CACHE_EXTENT;
+                }
+
+                BUG_ON(cbex.ec_len == 0);
+                err = func(inode, path, &cbex, ex, cbdata);
+                ext4_ext_drop_refs(path);
+
+                if (err < 0)
+                        break;
+
+                if (err == EXT_REPEAT)
+                        continue;
+                else if (err == EXT_BREAK) {
+                        err = 0;
+                        break;
+                }
+
+                if (ext_depth(inode) != depth) {
+                        /* depth was changed. we have to realloc path */
+                        kfree(path);
+                        path = NULL;
+                }
+
+                block = cbex.ec_block + cbex.ec_len;
+        }
+
+        if (path) {
+                ext4_ext_drop_refs(path);
+                kfree(path);
+        }
+
+        return err;
+}
+
 static void
 ext4_ext_put_in_cache(struct inode *inode, ext4_lblk_t block,
                         __u32 len, ext4_fsblk_t start, int type)
@@ -2142,7 +2251,7 @@ void ext4_ext_init(struct super_block *sb)
          */
 
         if (test_opt(sb, EXTENTS)) {
-                printk("EXT4-fs: file extents enabled");
+                printk(KERN_INFO "EXT4-fs: file extents enabled");
 #ifdef AGGRESSIVE_TEST
                 printk(", aggressive tests");
 #endif
@@ -2696,11 +2805,8 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
                 goto out2;
         }
         /*
-         * Okay, we need to do block allocation.  Lazily initialize the block
-         * allocation info here if necessary.
+         * Okay, we need to do block allocation.
          */
-        if (S_ISREG(inode->i_mode) && (!EXT4_I(inode)->i_block_alloc_info))
-                ext4_init_block_alloc_info(inode);
 
         /* find neighbour allocated blocks */
         ar.lleft = iblock;
@@ -2760,7 +2866,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
                 /* free data blocks we just allocated */
                 /* not a good idea to call discard here directly,
                  * but otherwise we'd need to call it every free() */
-                ext4_mb_discard_inode_preallocations(inode);
+                ext4_discard_preallocations(inode);
                 ext4_free_blocks(handle, inode, ext_pblock(&newex),
                                         ext4_ext_get_actual_len(&newex), 0);
                 goto out2;
@@ -2824,7 +2930,7 @@ void ext4_ext_truncate(struct inode *inode)
         down_write(&EXT4_I(inode)->i_data_sem);
         ext4_ext_invalidate_cache(inode);
 
-        ext4_discard_reservation(inode);
+        ext4_discard_preallocations(inode);
 
         /*
          * TODO: optimization is possible here.
@@ -2877,10 +2983,11 @@ static void ext4_falloc_update_inode(struct inode *inode,
          * Update only when preallocation was requested beyond
          * the file size.
          */
-        if (!(mode & FALLOC_FL_KEEP_SIZE) &&
-                                new_size > i_size_read(inode)) {
-                i_size_write(inode, new_size);
-                EXT4_I(inode)->i_disksize = new_size;
+        if (!(mode & FALLOC_FL_KEEP_SIZE)) {
+                if (new_size > i_size_read(inode))
+                        i_size_write(inode, new_size);
+                if (new_size > EXT4_I(inode)->i_disksize)
+                        ext4_update_i_disksize(inode, new_size);
         }
 
 }
@@ -2972,3 +3079,143 @@ retry:
         mutex_unlock(&inode->i_mutex);
         return ret > 0 ? ret2 : ret;
 }
+
+/*
+ * Callback function called for each extent to gather FIEMAP information.
+ */
+int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
+                       struct ext4_ext_cache *newex, struct ext4_extent *ex,
+                       void *data)
+{
+        struct fiemap_extent_info *fieinfo = data;
+        unsigned long blksize_bits = inode->i_sb->s_blocksize_bits;
+        __u64   logical;
+        __u64   physical;
+        __u64   length;
+        __u32   flags = 0;
+        int     error;
+
+        logical =  (__u64)newex->ec_block << blksize_bits;
+
+        if (newex->ec_type == EXT4_EXT_CACHE_GAP) {
+                pgoff_t offset;
+                struct page *page;
+                struct buffer_head *bh = NULL;
+
+                offset = logical >> PAGE_SHIFT;
+                page = find_get_page(inode->i_mapping, offset);
+                if (!page || !page_has_buffers(page))
+                        return EXT_CONTINUE;
+
+                bh = page_buffers(page);
+
+                if (!bh)
+                        return EXT_CONTINUE;
+
+                if (buffer_delay(bh)) {
+                        flags |= FIEMAP_EXTENT_DELALLOC;
+                        page_cache_release(page);
+                } else {
+                        page_cache_release(page);
+                        return EXT_CONTINUE;
+                }
+        }
+
+        physical = (__u64)newex->ec_start << blksize_bits;
+        length =   (__u64)newex->ec_len << blksize_bits;
+
+        if (ex && ext4_ext_is_uninitialized(ex))
+                flags |= FIEMAP_EXTENT_UNWRITTEN;
+
+        /*
+         * If this extent reaches EXT_MAX_BLOCK, it must be last.
+         *
+         * Or if ext4_ext_next_allocated_block is EXT_MAX_BLOCK,
+         * this also indicates no more allocated blocks.
+         *
+         * XXX this might miss a single-block extent at EXT_MAX_BLOCK
+         */
+        if (logical + length - 1 == EXT_MAX_BLOCK ||
+            ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK)
+                flags |= FIEMAP_EXTENT_LAST;
+
+        error = fiemap_fill_next_extent(fieinfo, logical, physical,
+                                        length, flags);
+        if (error < 0)
+                return error;
+        if (error == 1)
+                return EXT_BREAK;
+
+        return EXT_CONTINUE;
+}
+
+/* fiemap flags we can handle specified here */
+#define EXT4_FIEMAP_FLAGS       (FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR)
+
+int ext4_xattr_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo)
+{
+        __u64 physical = 0;
+        __u64 length;
+        __u32 flags = FIEMAP_EXTENT_LAST;
+        int blockbits = inode->i_sb->s_blocksize_bits;
+        int error = 0;
+
+        /* in-inode? */
+        if (EXT4_I(inode)->i_state & EXT4_STATE_XATTR) {
+                struct ext4_iloc iloc;
+                int offset;     /* offset of xattr in inode */
+
+                error = ext4_get_inode_loc(inode, &iloc);
+                if (error)
+                        return error;
+                physical = iloc.bh->b_blocknr << blockbits;
+                offset = EXT4_GOOD_OLD_INODE_SIZE +
+                                EXT4_I(inode)->i_extra_isize;
+                physical += offset;
+                length = EXT4_SB(inode->i_sb)->s_inode_size - offset;
+                flags |= FIEMAP_EXTENT_DATA_INLINE;
+        } else { /* external block */
+                physical = EXT4_I(inode)->i_file_acl << blockbits;
+                length = inode->i_sb->s_blocksize;
+        }
+
+        if (physical)
+                error = fiemap_fill_next_extent(fieinfo, 0, physical,
+                                                length, flags);
+        return (error < 0 ? error : 0);
+}
+
+int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+                __u64 start, __u64 len)
+{
+        ext4_lblk_t start_blk;
+        ext4_lblk_t len_blks;
+        int error = 0;
+
+        /* fallback to generic here if not in extents fmt */
+        if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
+                return generic_block_fiemap(inode, fieinfo, start, len,
+                        ext4_get_block);
+
+        if (fiemap_check_flags(fieinfo, EXT4_FIEMAP_FLAGS))
+                return -EBADR;
+
+        if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) {
+                error = ext4_xattr_fiemap(inode, fieinfo);
+        } else {
+                start_blk = start >> inode->i_sb->s_blocksize_bits;
+                len_blks = len >> inode->i_sb->s_blocksize_bits;
+
+                /*
+                 * Walk the extent tree gathering extent information.
+                 * ext4_ext_fiemap_cb will push extents back to user.
+                 */
+                down_write(&EXT4_I(inode)->i_data_sem);
+                error = ext4_ext_walk_space(inode, start_blk, len_blks,
+                                          ext4_ext_fiemap_cb, fieinfo);
+                up_write(&EXT4_I(inode)->i_data_sem);
+        }
+
+        return error;
+}
+
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 430eb7978db4..6bd11fba71f7 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -31,14 +31,14 @@
  * from ext4_file_open: open gets called at every open, but release
  * gets called only when /all/ the files are closed.
  */
-static int ext4_release_file (struct inode * inode, struct file * filp)
+static int ext4_release_file(struct inode *inode, struct file *filp)
 {
         /* if we are the last writer on the inode, drop the block reservation */
         if ((filp->f_mode & FMODE_WRITE) &&
                         (atomic_read(&inode->i_writecount) == 1))
         {
                 down_write(&EXT4_I(inode)->i_data_sem);
-                ext4_discard_reservation(inode);
+                ext4_discard_preallocations(inode);
                 up_write(&EXT4_I(inode)->i_data_sem);
         }
         if (is_dx(inode) && filp->private_data)
@@ -140,6 +140,9 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
         return 0;
 }
 
+extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+                __u64 start, __u64 len);
+
 const struct file_operations ext4_file_operations = {
         .llseek         = generic_file_llseek,
         .read           = do_sync_read,
@@ -162,7 +165,7 @@ const struct inode_operations ext4_file_inode_operations = {
         .truncate       = ext4_truncate,
         .setattr        = ext4_setattr,
         .getattr        = ext4_getattr,
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
         .setxattr       = generic_setxattr,
         .getxattr       = generic_getxattr,
         .listxattr      = ext4_listxattr,
@@ -170,5 +173,6 @@ const struct inode_operations ext4_file_inode_operations = {
 #endif
         .permission     = ext4_permission,
         .fallocate      = ext4_fallocate,
+        .fiemap         = ext4_fiemap,
 };
 
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index a45c3737ad31..5afe4370840b 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -28,6 +28,7 @@
 #include <linux/writeback.h>
 #include <linux/jbd2.h>
 #include <linux/blkdev.h>
+#include <linux/marker.h>
 #include "ext4.h"
 #include "ext4_jbd2.h"
 
@@ -43,7 +44,7 @@
  * inode to disk.
  */
 
-int ext4_sync_file(struct file * file, struct dentry *dentry, int datasync)
+int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
 {
         struct inode *inode = dentry->d_inode;
         journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
@@ -51,6 +52,10 @@ int ext4_sync_file(struct file * file, struct dentry *dentry, int datasync)
 
         J_ASSERT(ext4_journal_current_handle() == NULL);
 
+        trace_mark(ext4_sync_file, "dev %s datasync %d ino %ld parent %ld",
+                   inode->i_sb->s_id, datasync, inode->i_ino,
+                   dentry->d_parent->d_inode->i_ino);
+
         /*
          * data=writeback:
          *  The caller's filemap_fdatawrite()/wait will sync the data.
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index 1d6329dbe390..556ca8eba3db 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -27,7 +27,7 @@ static void TEA_transform(__u32 buf[4], __u32 const in[])
                 sum += DELTA;
                 b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b);
                 b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d);
-        } while(--n);
+        } while (--n);
 
         buf[0] += b0;
         buf[1] += b1;
@@ -35,7 +35,7 @@ static void TEA_transform(__u32 buf[4], __u32 const in[])
 
 
 /* The old legacy hash */
-static __u32 dx_hack_hash (const char *name, int len)
+static __u32 dx_hack_hash(const char *name, int len)
 {
         __u32 hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
         while (len--) {
@@ -59,7 +59,7 @@ static void str2hashbuf(const char *msg, int len, __u32 *buf, int num)
         val = pad;
         if (len > num*4)
                 len = num * 4;
-        for (i=0; i < len; i++) {
+        for (i = 0; i < len; i++) {
                 if ((i % 4) == 0)
                         val = pad;
                 val = msg[i] + (val << 8);
@@ -104,7 +104,7 @@ int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 
         /* Check to see if the seed is all zero's */
         if (hinfo->seed) {
-                for (i=0; i < 4; i++) {
+                for (i = 0; i < 4; i++) {
                         if (hinfo->seed[i])
                                 break;
                 }
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index f344834bbf58..fe34d74cfb19 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -115,9 +115,11 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
                             block_group, bitmap_blk);
                 return NULL;
         }
-        if (bh_uptodate_or_lock(bh))
+        if (buffer_uptodate(bh) &&
+            !(desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)))
                 return bh;
 
+        lock_buffer(bh);
         spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group));
         if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
                 ext4_init_inode_bitmap(sb, bh, block_group, desc);
@@ -154,39 +156,40 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
  * though), and then we'd have two inodes sharing the
  * same inode number and space on the harddisk.
  */
-void ext4_free_inode (handle_t *handle, struct inode * inode)
+void ext4_free_inode(handle_t *handle, struct inode *inode)
 {
-        struct super_block * sb = inode->i_sb;
+        struct super_block *sb = inode->i_sb;
         int is_directory;
         unsigned long ino;
         struct buffer_head *bitmap_bh = NULL;
         struct buffer_head *bh2;
         ext4_group_t block_group;
         unsigned long bit;
-        struct ext4_group_desc * gdp;
-        struct ext4_super_block * es;
+        struct ext4_group_desc *gdp;
+        struct ext4_super_block *es;
         struct ext4_sb_info *sbi;
         int fatal = 0, err;
         ext4_group_t flex_group;
 
         if (atomic_read(&inode->i_count) > 1) {
-                printk ("ext4_free_inode: inode has count=%d\n",
-                                        atomic_read(&inode->i_count));
+                printk(KERN_ERR "ext4_free_inode: inode has count=%d\n",
+                       atomic_read(&inode->i_count));
                 return;
         }
         if (inode->i_nlink) {
-                printk ("ext4_free_inode: inode has nlink=%d\n",
-                        inode->i_nlink);
+                printk(KERN_ERR "ext4_free_inode: inode has nlink=%d\n",
+                       inode->i_nlink);
                 return;
         }
         if (!sb) {
-                printk("ext4_free_inode: inode on nonexistent device\n");
+                printk(KERN_ERR "ext4_free_inode: inode on "
+                       "nonexistent device\n");
                 return;
         }
         sbi = EXT4_SB(sb);
 
         ino = inode->i_ino;
-        ext4_debug ("freeing inode %lu\n", ino);
+        ext4_debug("freeing inode %lu\n", ino);
 
         /*
          * Note: we must free any quota before locking the superblock,
@@ -200,12 +203,12 @@ void ext4_free_inode (handle_t *handle, struct inode * inode)
         is_directory = S_ISDIR(inode->i_mode);
 
         /* Do this BEFORE marking the inode not in use or returning an error */
-        clear_inode (inode);
+        clear_inode(inode);
 
         es = EXT4_SB(sb)->s_es;
         if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
-                ext4_error (sb, "ext4_free_inode",
-                            "reserved or nonexistent inode %lu", ino);
+                ext4_error(sb, "ext4_free_inode",
+                           "reserved or nonexistent inode %lu", ino);
                 goto error_return;
         }
         block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
@@ -222,10 +225,10 @@ void ext4_free_inode (handle_t *handle, struct inode * inode)
         /* Ok, now we can actually update the inode bitmaps.. */
         if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
                                         bit, bitmap_bh->b_data))
-                ext4_error (sb, "ext4_free_inode",
-                              "bit already cleared for inode %lu", ino);
+                ext4_error(sb, "ext4_free_inode",
+                           "bit already cleared for inode %lu", ino);
         else {
-                gdp = ext4_get_group_desc (sb, block_group, &bh2);
+                gdp = ext4_get_group_desc(sb, block_group, &bh2);
 
                 BUFFER_TRACE(bh2, "get_write_access");
                 fatal = ext4_journal_get_write_access(handle, bh2);
@@ -287,7 +290,7 @@ static int find_group_dir(struct super_block *sb, struct inode *parent,
         avefreei = freei / ngroups;
 
         for (group = 0; group < ngroups; group++) {
-                desc = ext4_get_group_desc (sb, group, NULL);
+                desc = ext4_get_group_desc(sb, group, NULL);
                 if (!desc || !desc->bg_free_inodes_count)
                         continue;
                 if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
@@ -576,16 +579,16 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
  * For other inodes, search forward from the parent directory's block
  * group to find a free inode.
  */
-struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
+struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
 {
         struct super_block *sb;
         struct buffer_head *bitmap_bh = NULL;
         struct buffer_head *bh2;
         ext4_group_t group = 0;
         unsigned long ino = 0;
-        struct inode * inode;
-        struct ext4_group_desc * gdp = NULL;
-        struct ext4_super_block * es;
+        struct inode *inode;
+        struct ext4_group_desc *gdp = NULL;
+        struct ext4_super_block *es;
         struct ext4_inode_info *ei;
         struct ext4_sb_info *sbi;
         int ret2, err = 0;
@@ -613,7 +616,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
         }
 
         if (S_ISDIR(mode)) {
-                if (test_opt (sb, OLDALLOC))
+                if (test_opt(sb, OLDALLOC))
                         ret2 = find_group_dir(sb, dir, &group);
                 else
                         ret2 = find_group_orlov(sb, dir, &group);
@@ -783,7 +786,7 @@ got:
         }
 
         inode->i_uid = current->fsuid;
-        if (test_opt (sb, GRPID))
+        if (test_opt(sb, GRPID))
                 inode->i_gid = dir->i_gid;
         else if (dir->i_mode & S_ISGID) {
                 inode->i_gid = dir->i_gid;
@@ -816,7 +819,6 @@ got:
                 ei->i_flags &= ~EXT4_DIRSYNC_FL;
         ei->i_file_acl = 0;
         ei->i_dtime = 0;
-        ei->i_block_alloc_info = NULL;
         ei->i_block_group = group;
 
         ext4_set_inode_flags(inode);
@@ -832,7 +834,7 @@ got:
         ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize;
 
         ret = inode;
-        if(DQUOT_ALLOC_INODE(inode)) {
+        if (DQUOT_ALLOC_INODE(inode)) {
                 err = -EDQUOT;
                 goto fail_drop;
         }
@@ -841,7 +843,7 @@ got:
         if (err)
                 goto fail_free_drop;
 
-        err = ext4_init_security(handle,inode, dir);
+        err = ext4_init_security(handle, inode, dir);
         if (err)
                 goto fail_free_drop;
 
@@ -959,7 +961,7 @@ error:
         return ERR_PTR(err);
 }
 
-unsigned long ext4_count_free_inodes (struct super_block * sb)
+unsigned long ext4_count_free_inodes(struct super_block *sb)
 {
         unsigned long desc_count;
         struct ext4_group_desc *gdp;
@@ -974,7 +976,7 @@ unsigned long ext4_count_free_inodes (struct super_block * sb)
         bitmap_count = 0;
         gdp = NULL;
         for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
-                gdp = ext4_get_group_desc (sb, i, NULL);
+                gdp = ext4_get_group_desc(sb, i, NULL);
                 if (!gdp)
                         continue;
                 desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
@@ -989,13 +991,14 @@ unsigned long ext4_count_free_inodes (struct super_block * sb)
                 bitmap_count += x;
         }
         brelse(bitmap_bh);
-        printk("ext4_count_free_inodes: stored = %u, computed = %lu, %lu\n",
-                le32_to_cpu(es->s_free_inodes_count), desc_count, bitmap_count);
+        printk(KERN_DEBUG "ext4_count_free_inodes: "
+               "stored = %u, computed = %lu, %lu\n",
+               le32_to_cpu(es->s_free_inodes_count), desc_count, bitmap_count);
         return desc_count;
 #else
         desc_count = 0;
         for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
-                gdp = ext4_get_group_desc (sb, i, NULL);
+                gdp = ext4_get_group_desc(sb, i, NULL);
                 if (!gdp)
                         continue;
                 desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
@@ -1006,13 +1009,13 @@ unsigned long ext4_count_free_inodes (struct super_block * sb)
 }
 
 /* Called at mount-time, super-block is locked */
-unsigned long ext4_count_dirs (struct super_block * sb)
+unsigned long ext4_count_dirs(struct super_block * sb)
 {
         unsigned long count = 0;
         ext4_group_t i;
 
         for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
-                struct ext4_group_desc *gdp = ext4_get_group_desc (sb, i, NULL);
+                struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL);
                 if (!gdp)
                         continue;
                 count += le16_to_cpu(gdp->bg_used_dirs_count);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 7e91913e325b..8dbf6953845b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -190,7 +190,7 @@ static int ext4_journal_test_restart(handle_t *handle, struct inode *inode)
 /*
  * Called at the last iput() if i_nlink is zero.
  */
-void ext4_delete_inode (struct inode * inode)
+void ext4_delete_inode(struct inode *inode)
 {
         handle_t *handle;
         int err;
@@ -330,11 +330,11 @@ static int ext4_block_to_path(struct inode *inode,
         int final = 0;
 
         if (i_block < 0) {
-                ext4_warning (inode->i_sb, "ext4_block_to_path", "block < 0");
+                ext4_warning(inode->i_sb, "ext4_block_to_path", "block < 0");
         } else if (i_block < direct_blocks) {
                 offsets[n++] = i_block;
                 final = direct_blocks;
-        } else if ( (i_block -= direct_blocks) < indirect_blocks) {
+        } else if ((i_block -= direct_blocks) < indirect_blocks) {
                 offsets[n++] = EXT4_IND_BLOCK;
                 offsets[n++] = i_block;
                 final = ptrs;
@@ -400,14 +400,14 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth,
 
         *err = 0;
         /* i_data is not going away, no lock needed */
-        add_chain (chain, NULL, EXT4_I(inode)->i_data + *offsets);
+        add_chain(chain, NULL, EXT4_I(inode)->i_data + *offsets);
         if (!p->key)
                 goto no_block;
         while (--depth) {
                 bh = sb_bread(sb, le32_to_cpu(p->key));
                 if (!bh)
                         goto failure;
-                add_chain(++p, bh, (__le32*)bh->b_data + *++offsets);
+                add_chain(++p, bh, (__le32 *)bh->b_data + *++offsets);
                 /* Reader: end */
                 if (!p->key)
                         goto no_block;
@@ -443,7 +443,7 @@ no_block:
 static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind)
 {
         struct ext4_inode_info *ei = EXT4_I(inode);
-        __le32 *start = ind->bh ? (__le32*) ind->bh->b_data : ei->i_data;
+        __le32 *start = ind->bh ? (__le32 *) ind->bh->b_data : ei->i_data;
         __le32 *p;
         ext4_fsblk_t bg_start;
         ext4_fsblk_t last_block;
@@ -486,18 +486,9 @@ static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind)
 static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block,
                 Indirect *partial)
 {
-        struct ext4_block_alloc_info *block_i;
-
-        block_i =  EXT4_I(inode)->i_block_alloc_info;
-
         /*
-         * try the heuristic for sequential allocation,
-         * failing that at least try to get decent locality.
+         * XXX need to get goal block from mballoc's data structures
          */
-        if (block_i && (block == block_i->last_alloc_logical_block + 1)
-                && (block_i->last_alloc_physical_block != 0)) {
-                return block_i->last_alloc_physical_block + 1;
-        }
 
         return ext4_find_near(inode, partial);
 }
@@ -630,7 +621,7 @@ allocated:
         *err = 0;
         return ret;
 failed_out:
-        for (i = 0; i <index; i++)
+        for (i = 0; i < index; i++)
                 ext4_free_blocks(handle, inode, new_blocks[i], 1, 0);
         return ret;
 }
@@ -703,7 +694,7 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
                 branch[n].p = (__le32 *) bh->b_data + offsets[n];
                 branch[n].key = cpu_to_le32(new_blocks[n]);
                 *branch[n].p = branch[n].key;
-                if ( n == indirect_blks) {
+                if (n == indirect_blks) {
                         current_block = new_blocks[n];
                         /*
                          * End of chain, update the last new metablock of
@@ -730,7 +721,7 @@ failed:
                 BUFFER_TRACE(branch[i].bh, "call jbd2_journal_forget");
                 ext4_journal_forget(handle, branch[i].bh);
         }
-        for (i = 0; i <indirect_blks; i++)
+        for (i = 0; i < indirect_blks; i++)
                 ext4_free_blocks(handle, inode, new_blocks[i], 1, 0);
 
         ext4_free_blocks(handle, inode, new_blocks[i], num, 0);
@@ -757,10 +748,8 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode,
 {
         int i;
         int err = 0;
-        struct ext4_block_alloc_info *block_i;
         ext4_fsblk_t current_block;
 
-        block_i = EXT4_I(inode)->i_block_alloc_info;
         /*
          * If we're splicing into a [td]indirect block (as opposed to the
          * inode) then we need to get write access to the [td]indirect block
@@ -783,18 +772,7 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode,
         if (num == 0 && blks > 1) {
                 current_block = le32_to_cpu(where->key) + 1;
                 for (i = 1; i < blks; i++)
-                        *(where->p + i ) = cpu_to_le32(current_block++);
-        }
-
-        /*
-         * update the most recently allocated logical & physical block
-         * in i_block_alloc_info, to assist find the proper goal block for next
-         * allocation
-         */
-        if (block_i) {
-                block_i->last_alloc_logical_block = block + blks - 1;
-                block_i->last_alloc_physical_block =
-                                le32_to_cpu(where[num].key) + blks - 1;
+                        *(where->p + i) = cpu_to_le32(current_block++);
         }
 
         /* We are done with atomic stuff, now do the rest of housekeeping */
@@ -914,12 +892,8 @@ int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
                 goto cleanup;
 
         /*
-         * Okay, we need to do block allocation.  Lazily initialize the block
-         * allocation info here if necessary
+         * Okay, we need to do block allocation.
         */
-        if (S_ISREG(inode->i_mode) && (!ei->i_block_alloc_info))
-                ext4_init_block_alloc_info(inode);
-
         goal = ext4_find_goal(inode, iblock, partial);
 
         /* the number of blocks need to allocate for [d,t]indirect blocks */
@@ -1030,19 +1004,20 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used)
         BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
         mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb;
 
-        /* Account for allocated meta_blocks */
-        mdb_free -= EXT4_I(inode)->i_allocated_meta_blocks;
+        if (mdb_free) {
+                /* Account for allocated meta_blocks */
+                mdb_free -= EXT4_I(inode)->i_allocated_meta_blocks;
 
-        /* update fs free blocks counter for truncate case */
-        percpu_counter_add(&sbi->s_freeblocks_counter, mdb_free);
+                /* update fs dirty blocks counter */
+                percpu_counter_sub(&sbi->s_dirtyblocks_counter, mdb_free);
+                EXT4_I(inode)->i_allocated_meta_blocks = 0;
+                EXT4_I(inode)->i_reserved_meta_blocks = mdb;
+        }
 
         /* update per-inode reservations */
         BUG_ON(used  > EXT4_I(inode)->i_reserved_data_blocks);
         EXT4_I(inode)->i_reserved_data_blocks -= used;
 
-        BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
-        EXT4_I(inode)->i_reserved_meta_blocks = mdb;
-        EXT4_I(inode)->i_allocated_meta_blocks = 0;
         spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
 }
 
@@ -1160,8 +1135,8 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
 /* Maximum number of blocks we map for direct IO at once. */
 #define DIO_MAX_BLOCKS 4096
 
-static int ext4_get_block(struct inode *inode, sector_t iblock,
-                        struct buffer_head *bh_result, int create)
+int ext4_get_block(struct inode *inode, sector_t iblock,
+                   struct buffer_head *bh_result, int create)
 {
         handle_t *handle = ext4_journal_current_handle();
         int ret = 0, started = 0;
@@ -1241,7 +1216,7 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
                         BUFFER_TRACE(bh, "call get_create_access");
                         fatal = ext4_journal_get_create_access(handle, bh);
                         if (!fatal && !buffer_uptodate(bh)) {
-                                memset(bh->b_data,0,inode->i_sb->s_blocksize);
+                                memset(bh->b_data, 0, inode->i_sb->s_blocksize);
                                 set_buffer_uptodate(bh);
                         }
                         unlock_buffer(bh);
@@ -1266,7 +1241,7 @@ err:
 struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
                                ext4_lblk_t block, int create, int *err)
 {
-        struct buffer_head * bh;
+        struct buffer_head *bh;
 
         bh = ext4_getblk(handle, inode, block, create, err);
         if (!bh)
@@ -1282,13 +1257,13 @@ struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
         return NULL;
 }
 
-static int walk_page_buffers(   handle_t *handle,
-                                struct buffer_head *head,
-                                unsigned from,
-                                unsigned to,
-                                int *partial,
-                                int (*fn)(      handle_t *handle,
-                                                struct buffer_head *bh))
+static int walk_page_buffers(handle_t *handle,
+                             struct buffer_head *head,
+                             unsigned from,
+                             unsigned to,
+                             int *partial,
+                             int (*fn)(handle_t *handle,
+                                       struct buffer_head *bh))
 {
         struct buffer_head *bh;
         unsigned block_start, block_end;
@@ -1296,9 +1271,9 @@ static int walk_page_buffers(	handle_t *handle,
         int err, ret = 0;
         struct buffer_head *next;
 
-        for (   bh = head, block_start = 0;
-                ret == 0 && (bh != head || !block_start);
-                block_start = block_end, bh = next)
+        for (bh = head, block_start = 0;
+             ret == 0 && (bh != head || !block_start);
+             block_start = block_end, bh = next)
         {
                 next = bh->b_this_page;
                 block_end = block_start + blocksize;
@@ -1351,23 +1326,23 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
                                 loff_t pos, unsigned len, unsigned flags,
                                 struct page **pagep, void **fsdata)
 {
-        struct inode *inode = mapping->host;
+        struct inode *inode = mapping->host;
         int ret, needed_blocks = ext4_writepage_trans_blocks(inode);
         handle_t *handle;
         int retries = 0;
-        struct page *page;
+        struct page *page;
         pgoff_t index;
-        unsigned from, to;
+        unsigned from, to;
 
         index = pos >> PAGE_CACHE_SHIFT;
-        from = pos & (PAGE_CACHE_SIZE - 1);
-        to = from + len;
+        from = pos & (PAGE_CACHE_SIZE - 1);
+        to = from + len;
 
 retry:
-        handle = ext4_journal_start(inode, needed_blocks);
-        if (IS_ERR(handle)) {
-                ret = PTR_ERR(handle);
-                goto out;
+        handle = ext4_journal_start(inode, needed_blocks);
+        if (IS_ERR(handle)) {
+                ret = PTR_ERR(handle);
+                goto out;
         }
 
         page = __grab_cache_page(mapping, index);
@@ -1387,9 +1362,16 @@ retry:
         }
 
         if (ret) {
-                unlock_page(page);
+                unlock_page(page);
                 ext4_journal_stop(handle);
-                page_cache_release(page);
+                page_cache_release(page);
+                /*
+                 * block_write_begin may have instantiated a few blocks
+                 * outside i_size.  Trim these off again. Don't need
+                 * i_size_read because we hold i_mutex.
+                 */
+                if (pos + len > inode->i_size)
+                        vmtruncate(inode, inode->i_size);
         }
 
         if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
@@ -1426,16 +1408,18 @@ static int ext4_ordered_write_end(struct file *file,
         ret = ext4_jbd2_file_inode(handle, inode);
 
         if (ret == 0) {
-                /*
-                 * generic_write_end() will run mark_inode_dirty() if i_size
-                 * changes.  So let's piggyback the i_disksize mark_inode_dirty
-                 * into that.
-                 */
                 loff_t new_i_size;
 
                 new_i_size = pos + copied;
-                if (new_i_size > EXT4_I(inode)->i_disksize)
-                        EXT4_I(inode)->i_disksize = new_i_size;
+                if (new_i_size > EXT4_I(inode)->i_disksize) {
+                        ext4_update_i_disksize(inode, new_i_size);
+                        /* We need to mark inode dirty even if
+                         * new_i_size is less that inode->i_size
+                         * bu greater than i_disksize.(hint delalloc)
+                         */
+                        ext4_mark_inode_dirty(handle, inode);
+                }
+
                 ret2 = generic_write_end(file, mapping, pos, len, copied,
                                                         page, fsdata);
                 copied = ret2;
@@ -1460,8 +1444,14 @@ static int ext4_writeback_write_end(struct file *file,
         loff_t new_i_size;
 
         new_i_size = pos + copied;
-        if (new_i_size > EXT4_I(inode)->i_disksize)
-                EXT4_I(inode)->i_disksize = new_i_size;
+        if (new_i_size > EXT4_I(inode)->i_disksize) {
+                ext4_update_i_disksize(inode, new_i_size);
+                /* We need to mark inode dirty even if
+                 * new_i_size is less that inode->i_size
+                 * bu greater than i_disksize.(hint delalloc)
+                 */
+                ext4_mark_inode_dirty(handle, inode);
+        }
 
         ret2 = generic_write_end(file, mapping, pos, len, copied,
                                                         page, fsdata);
@@ -1486,6 +1476,7 @@ static int ext4_journalled_write_end(struct file *file,
         int ret = 0, ret2;
         int partial = 0;
         unsigned from, to;
+        loff_t new_i_size;
 
         from = pos & (PAGE_CACHE_SIZE - 1);
         to = from + len;
@@ -1500,11 +1491,12 @@ static int ext4_journalled_write_end(struct file *file,
                                 to, &partial, write_end_fn);
         if (!partial)
                 SetPageUptodate(page);
-        if (pos+copied > inode->i_size)
+        new_i_size = pos + copied;
+        if (new_i_size > inode->i_size)
                 i_size_write(inode, pos+copied);
         EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;
-        if (inode->i_size > EXT4_I(inode)->i_disksize) {
-                EXT4_I(inode)->i_disksize = inode->i_size;
+        if (new_i_size > EXT4_I(inode)->i_disksize) {
+                ext4_update_i_disksize(inode, new_i_size);
                 ret2 = ext4_mark_inode_dirty(handle, inode);
                 if (!ret)
                         ret = ret2;
@@ -1521,6 +1513,7 @@ static int ext4_journalled_write_end(struct file *file,
 
 static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
 {
+        int retries = 0;
        struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
        unsigned long md_needed, mdblocks, total = 0;
 
@@ -1529,6 +1522,7 @@ static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
          * in order to allocate nrblocks
          * worse case is one extent per block
          */
+repeat:
         spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
         total = EXT4_I(inode)->i_reserved_data_blocks + nrblocks;
         mdblocks = ext4_calc_metadata_amount(inode, total);
@@ -1537,13 +1531,14 @@ static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
         md_needed = mdblocks - EXT4_I(inode)->i_reserved_meta_blocks;
         total = md_needed + nrblocks;
 
-        if (ext4_has_free_blocks(sbi, total) < total) {
+        if (ext4_claim_free_blocks(sbi, total)) {
                 spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+                if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
+                        yield();
+                        goto repeat;
+                }
                 return -ENOSPC;
         }
-        /* reduce fs free blocks counter */
-        percpu_counter_sub(&sbi->s_freeblocks_counter, total);
-
         EXT4_I(inode)->i_reserved_data_blocks += nrblocks;
         EXT4_I(inode)->i_reserved_meta_blocks = mdblocks;
 
@@ -1585,8 +1580,8 @@ static void ext4_da_release_space(struct inode *inode, int to_free)
 
         release = to_free + mdb_free;
 
-        /* update fs free blocks counter for truncate case */
-        percpu_counter_add(&sbi->s_freeblocks_counter, release);
+        /* update fs dirty blocks counter for truncate case */
+        percpu_counter_sub(&sbi->s_dirtyblocks_counter, release);
 
         /* update per-inode reservations */
         BUG_ON(to_free > EXT4_I(inode)->i_reserved_data_blocks);
@@ -1630,6 +1625,7 @@ struct mpage_da_data {
         struct writeback_control *wbc;
         int io_done;
         long pages_written;
+        int retval;
 };
 
 /*
@@ -1652,6 +1648,7 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd)
         int ret = 0, err, nr_pages, i;
         unsigned long index, end;
         struct pagevec pvec;
+        long pages_skipped;
 
         BUG_ON(mpd->next_page <= mpd->first_page);
         pagevec_init(&pvec, 0);
@@ -1659,20 +1656,30 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd)
         end = mpd->next_page - 1;
 
         while (index <= end) {
-                /* XXX: optimize tail */
-                nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
+                /*
+                 * We can use PAGECACHE_TAG_DIRTY lookup here because
+                 * even though we have cleared the dirty flag on the page
+                 * We still keep the page in the radix tree with tag
+                 * PAGECACHE_TAG_DIRTY. See clear_page_dirty_for_io.
+                 * The PAGECACHE_TAG_DIRTY is cleared in set_page_writeback
+                 * which is called via the below writepage callback.
+                 */
+                nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+                                        PAGECACHE_TAG_DIRTY,
+                                        min(end - index,
+                                        (pgoff_t)PAGEVEC_SIZE-1) + 1);
                 if (nr_pages == 0)
                         break;
                 for (i = 0; i < nr_pages; i++) {
                         struct page *page = pvec.pages[i];
 
-                        index = page->index;
-                        if (index > end)
-                                break;
-                        index++;
-
+                        pages_skipped = mpd->wbc->pages_skipped;
                         err = mapping->a_ops->writepage(page, mpd->wbc);
-                        if (!err)
+                        if (!err && (pages_skipped == mpd->wbc->pages_skipped))
+                                /*
+                                 * have successfully written the page
+                                 * without skipping the same
+                                 */
                                 mpd->pages_written++;
                         /*
                          * In error case, we have to continue because
@@ -1783,6 +1790,57 @@ static inline void __unmap_underlying_blocks(struct inode *inode,
                 unmap_underlying_metadata(bdev, bh->b_blocknr + i);
 }
 
+static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd,
+                                        sector_t logical, long blk_cnt)
+{
+        int nr_pages, i;
+        pgoff_t index, end;
+        struct pagevec pvec;
+        struct inode *inode = mpd->inode;
+        struct address_space *mapping = inode->i_mapping;
+
+        index = logical >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+        end   = (logical + blk_cnt - 1) >>
+                                (PAGE_CACHE_SHIFT - inode->i_blkbits);
+        while (index <= end) {
+                nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
+                if (nr_pages == 0)
+                        break;
+                for (i = 0; i < nr_pages; i++) {
+                        struct page *page = pvec.pages[i];
+                        index = page->index;
+                        if (index > end)
+                                break;
+                        index++;
+
+                        BUG_ON(!PageLocked(page));
+                        BUG_ON(PageWriteback(page));
+                        block_invalidatepage(page, 0);
+                        ClearPageUptodate(page);
+                        unlock_page(page);
+                }
+        }
+        return;
+}
+
+static void ext4_print_free_blocks(struct inode *inode)
+{
+        struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+        printk(KERN_EMERG "Total free blocks count %lld\n",
+                        ext4_count_free_blocks(inode->i_sb));
+        printk(KERN_EMERG "Free/Dirty block details\n");
+        printk(KERN_EMERG "free_blocks=%lld\n",
+                        percpu_counter_sum(&sbi->s_freeblocks_counter));
+        printk(KERN_EMERG "dirty_blocks=%lld\n",
+                        percpu_counter_sum(&sbi->s_dirtyblocks_counter));
+        printk(KERN_EMERG "Block reservation details\n");
+        printk(KERN_EMERG "i_reserved_data_blocks=%lu\n",
+                        EXT4_I(inode)->i_reserved_data_blocks);
+        printk(KERN_EMERG "i_reserved_meta_blocks=%lu\n",
+                        EXT4_I(inode)->i_reserved_meta_blocks);
+        return;
+}
+
 /*
  * mpage_da_map_blocks - go through given space
  *
@@ -1792,32 +1850,69 @@ static inline void __unmap_underlying_blocks(struct inode *inode,
  * The function skips space we know is already mapped to disk blocks.
  *
  */
-static void mpage_da_map_blocks(struct mpage_da_data *mpd)
+static int  mpage_da_map_blocks(struct mpage_da_data *mpd)
 {
         int err = 0;
-        struct buffer_head *lbh = &mpd->lbh;
-        sector_t next = lbh->b_blocknr;
         struct buffer_head new;
+        struct buffer_head *lbh = &mpd->lbh;
+        sector_t next;
 
         /*
          * We consider only non-mapped and non-allocated blocks
          */
         if (buffer_mapped(lbh) && !buffer_delay(lbh))
-                return;
-
+                return 0;
         new.b_state = lbh->b_state;
         new.b_blocknr = 0;
         new.b_size = lbh->b_size;
-
+        next = lbh->b_blocknr;
         /*
          * If we didn't accumulate anything
          * to write simply return
          */
         if (!new.b_size)
-                return;
+                return 0;
         err = mpd->get_block(mpd->inode, next, &new, 1);
-        if (err)
-                return;
+        if (err) {
+
+                /* If get block returns with error
+                 * we simply return. Later writepage
+                 * will redirty the page and writepages
+                 * will find the dirty page again
+                 */
+                if (err == -EAGAIN)
+                        return 0;
+
+                if (err == -ENOSPC &&
+                                ext4_count_free_blocks(mpd->inode->i_sb)) {
+                        mpd->retval = err;
+                        return 0;
+                }
+
+                /*
+                 * get block failure will cause us
+                 * to loop in writepages. Because
+                 * a_ops->writepage won't be able to
+                 * make progress. The page will be redirtied
+                 * by writepage and writepages will again
+                 * try to write the same.
+                 */
+                printk(KERN_EMERG "%s block allocation failed for inode %lu "
+                                  "at logical offset %llu with max blocks "
+                                  "%zd with error %d\n",
+                                  __func__, mpd->inode->i_ino,
+                                  (unsigned long long)next,
+                                  lbh->b_size >> mpd->inode->i_blkbits, err);
+                printk(KERN_EMERG "This should not happen.!! "
+                                        "Data will be lost\n");
+                if (err == -ENOSPC) {
+                        ext4_print_free_blocks(mpd->inode);
+                }
+                /* invlaidate all the pages */
+                ext4_da_block_invalidatepages(mpd, next,
+                                lbh->b_size >> mpd->inode->i_blkbits);
+                return err;
+        }
         BUG_ON(new.b_size == 0);
 
         if (buffer_new(&new))
@@ -1830,7 +1925,7 @@ static void mpage_da_map_blocks(struct mpage_da_data *mpd)
         if (buffer_delay(lbh) || buffer_unwritten(lbh))
                 mpage_put_bnr_to_bhs(mpd, next, &new);
 
-        return;
+        return 0;
 }
 
 #define BH_FLAGS ((1 << BH_Uptodate) | (1 << BH_Mapped) | \
@@ -1899,8 +1994,8 @@ flush_it:
          * We couldn't merge the block to our extent, so we
          * need to flush current  extent and start new one
          */
-        mpage_da_map_blocks(mpd);
-        mpage_da_submit_io(mpd);
+        if (mpage_da_map_blocks(mpd) == 0)
+                mpage_da_submit_io(mpd);
         mpd->io_done = 1;
         return;
 }
@@ -1942,8 +2037,8 @@ static int __mpage_da_writepage(struct page *page,
                  * and start IO on them using writepage()
                  */
                 if (mpd->next_page != mpd->first_page) {
-                        mpage_da_map_blocks(mpd);
-                        mpage_da_submit_io(mpd);
+                        if (mpage_da_map_blocks(mpd) == 0)
+                                mpage_da_submit_io(mpd);
                         /*
                          * skip rest of the page in the page_vec
                          */
@@ -2018,39 +2113,34 @@ static int __mpage_da_writepage(struct page *page,
  */
 static int mpage_da_writepages(struct address_space *mapping,
                                struct writeback_control *wbc,
-                               get_block_t get_block)
+                               struct mpage_da_data *mpd)
 {
-        struct mpage_da_data mpd;
-        long to_write;
         int ret;
 
-        if (!get_block)
+        if (!mpd->get_block)
                 return generic_writepages(mapping, wbc);
 
-        mpd.wbc = wbc;
-        mpd.inode = mapping->host;
-        mpd.lbh.b_size = 0;
-        mpd.lbh.b_state = 0;
-        mpd.lbh.b_blocknr = 0;
-        mpd.first_page = 0;
-        mpd.next_page = 0;
-        mpd.get_block = get_block;
-        mpd.io_done = 0;
-        mpd.pages_written = 0;
-
-        to_write = wbc->nr_to_write;
-
-        ret = write_cache_pages(mapping, wbc, __mpage_da_writepage, &mpd);
+        mpd->lbh.b_size = 0;
+        mpd->lbh.b_state = 0;
+        mpd->lbh.b_blocknr = 0;
+        mpd->first_page = 0;
+        mpd->next_page = 0;
+        mpd->io_done = 0;
+        mpd->pages_written = 0;
+        mpd->retval = 0;
 
+        ret = write_cache_pages(mapping, wbc, __mpage_da_writepage, mpd);
         /*
          * Handle last extent of pages
          */
-        if (!mpd.io_done && mpd.next_page != mpd.first_page) {
-                mpage_da_map_blocks(&mpd);
-                mpage_da_submit_io(&mpd);
-        }
+        if (!mpd->io_done && mpd->next_page != mpd->first_page) {
+                if (mpage_da_map_blocks(mpd) == 0)
+                        mpage_da_submit_io(mpd);
 
-        wbc->nr_to_write = to_write - mpd.pages_written;
+                mpd->io_done = 1;
+                ret = MPAGE_DA_EXTENT_TAIL;
+        }
+        wbc->nr_to_write -= mpd->pages_written;
         return ret;
 }
 
@@ -2103,18 +2193,24 @@ static int ext4_da_get_block_write(struct inode *inode, sector_t iblock,
         handle_t *handle = NULL;
 
         handle = ext4_journal_current_handle();
-        if (!handle) {
-                ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks,
-                                   bh_result, 0, 0, 0);
-                BUG_ON(!ret);
-        } else {
-                ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks,
-                                   bh_result, create, 0, EXT4_DELALLOC_RSVED);
-        }
-
+        BUG_ON(!handle);
+        ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks,
+                        bh_result, create, 0, EXT4_DELALLOC_RSVED);
         if (ret > 0) {
+
                 bh_result->b_size = (ret << inode->i_blkbits);
 
+                if (ext4_should_order_data(inode)) {
+                        int retval;
+                        retval = ext4_jbd2_file_inode(handle, inode);
+                        if (retval)
+                                /*
+                                 * Failed to add inode for ordered
+                                 * mode. Don't update file size
+                                 */
+                                return retval;
+                }
+
                 /*
                  * Update on-disk size along with block allocation
                  * we don't use 'extend_disksize' as size may change
@@ -2124,18 +2220,9 @@ static int ext4_da_get_block_write(struct inode *inode, sector_t iblock,
                 if (disksize > i_size_read(inode))
                         disksize = i_size_read(inode);
                 if (disksize > EXT4_I(inode)->i_disksize) {
-                        /*
-                         * XXX: replace with spinlock if seen contended -bzzz
-                         */
-                        down_write(&EXT4_I(inode)->i_data_sem);
-                        if (disksize > EXT4_I(inode)->i_disksize)
-                                EXT4_I(inode)->i_disksize = disksize;
-                        up_write(&EXT4_I(inode)->i_data_sem);
-
-                        if (EXT4_I(inode)->i_disksize == disksize) {
-                                ret = ext4_mark_inode_dirty(handle, inode);
-                                return ret;
-                        }
+                        ext4_update_i_disksize(inode, disksize);
+                        ret = ext4_mark_inode_dirty(handle, inode);
+                        return ret;
                 }
                 ret = 0;
         }
@@ -2282,11 +2369,14 @@ static int ext4_da_writepages_trans_blocks(struct inode *inode)
 static int ext4_da_writepages(struct address_space *mapping,
                               struct writeback_control *wbc)
 {
+        pgoff_t index;
+        int range_whole = 0;
         handle_t *handle = NULL;
-        loff_t range_start = 0;
+        struct mpage_da_data mpd;
         struct inode *inode = mapping->host;
+        int no_nrwrite_index_update;
+        long pages_written = 0, pages_skipped;
         int needed_blocks, ret = 0, nr_to_writebump = 0;
-        long to_write, pages_skipped = 0;
         struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
 
         /*
@@ -2306,20 +2396,26 @@ static int ext4_da_writepages(struct address_space *mapping,
                 nr_to_writebump = sbi->s_mb_stream_request - wbc->nr_to_write;
                 wbc->nr_to_write = sbi->s_mb_stream_request;
         }
+        if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
+                range_whole = 1;
 
-        if (!wbc->range_cyclic)
-                /*
-                 * If range_cyclic is not set force range_cont
-                 * and save the old writeback_index
-                 */
-                wbc->range_cont = 1;
+        if (wbc->range_cyclic)
+                index = mapping->writeback_index;
+        else
+                index = wbc->range_start >> PAGE_CACHE_SHIFT;
+
+        mpd.wbc = wbc;
+        mpd.inode = mapping->host;
 
-        range_start =  wbc->range_start;
+        /*
+         * we don't want write_cache_pages to update
+         * nr_to_write and writeback_index
+         */
+        no_nrwrite_index_update = wbc->no_nrwrite_index_update;
+        wbc->no_nrwrite_index_update = 1;
         pages_skipped = wbc->pages_skipped;
 
-restart_loop:
-        to_write = wbc->nr_to_write;
-        while (!ret && to_write > 0) {
+        while (!ret && wbc->nr_to_write > 0) {
 
                 /*
                  * we  insert one extent at a time. So we need
@@ -2340,57 +2436,83 @@ restart_loop:
                         dump_stack();
                         goto out_writepages;
                 }
-                if (ext4_should_order_data(inode)) {
-                        /*
-                         * With ordered mode we need to add
-                         * the inode to the journal handl
-                         * when we do block allocation.
-                         */
-                        ret = ext4_jbd2_file_inode(handle, inode);
-                        if (ret) {
-                                ext4_journal_stop(handle);
-                                goto out_writepages;
-                        }
-                }
+                mpd.get_block = ext4_da_get_block_write;
+                ret = mpage_da_writepages(mapping, wbc, &mpd);
 
-                to_write -= wbc->nr_to_write;
-                ret = mpage_da_writepages(mapping, wbc,
-                                          ext4_da_get_block_write);
                 ext4_journal_stop(handle);
-                if (ret == MPAGE_DA_EXTENT_TAIL) {
+
+                if (mpd.retval == -ENOSPC) {
+                        /* commit the transaction which would
+                         * free blocks released in the transaction
+                         * and try again
+                         */
+                        jbd2_journal_force_commit_nested(sbi->s_journal);
+                        wbc->pages_skipped = pages_skipped;
+                        ret = 0;
+                } else if (ret == MPAGE_DA_EXTENT_TAIL) {
                         /*
                          * got one extent now try with
                          * rest of the pages
                          */
-                        to_write += wbc->nr_to_write;
+                        pages_written += mpd.pages_written;
+                        wbc->pages_skipped = pages_skipped;
                         ret = 0;
-                } else if (wbc->nr_to_write) {
+                } else if (wbc->nr_to_write)
                         /*
                          * There is no more writeout needed
                          * or we requested for a noblocking writeout
                          * and we found the device congested
                          */
-                        to_write += wbc->nr_to_write;
                         break;
-                }
-                wbc->nr_to_write = to_write;
-        }
-
-        if (wbc->range_cont && (pages_skipped != wbc->pages_skipped)) {
-                /* We skipped pages in this loop */
-                wbc->range_start = range_start;
-                wbc->nr_to_write = to_write +
-                                wbc->pages_skipped - pages_skipped;
-                wbc->pages_skipped = pages_skipped;
-                goto restart_loop;
         }
+        if (pages_skipped != wbc->pages_skipped)
+                printk(KERN_EMERG "This should not happen leaving %s "
+                                "with nr_to_write = %ld ret = %d\n",
+                                __func__, wbc->nr_to_write, ret);
+
+        /* Update index */
+        index += pages_written;
+        if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
+                /*
+                 * set the writeback_index so that range_cyclic
+                 * mode will write it back later
+                 */
+                mapping->writeback_index = index;
 
 out_writepages:
-        wbc->nr_to_write = to_write - nr_to_writebump;
-        wbc->range_start = range_start;
+        if (!no_nrwrite_index_update)
+                wbc->no_nrwrite_index_update = 0;
+        wbc->nr_to_write -= nr_to_writebump;
         return ret;
 }
 
+#define FALL_BACK_TO_NONDELALLOC 1
+static int ext4_nonda_switch(struct super_block *sb)
+{
+        s64 free_blocks, dirty_blocks;
+        struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+        /*
+         * switch to non delalloc mode if we are running low
+         * on free block. The free block accounting via percpu
+         * counters can get slightly wrong with FBC_BATCH getting
+         * accumulated on each CPU without updating global counters
+         * Delalloc need an accurate free block accounting. So switch
+         * to non delalloc when we are near to error range.
+         */
+        free_blocks  = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
+        dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyblocks_counter);
+        if (2 * free_blocks < 3 * dirty_blocks ||
+                free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) {
+                /*
+                 * free block count is less that 150% of dirty blocks
+                 * or free blocks is less that watermark
+                 */
+                return 1;
+        }
+        return 0;
+}
+
 static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
                                 loff_t pos, unsigned len, unsigned flags,
                                 struct page **pagep, void **fsdata)
@@ -2406,6 +2528,12 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
         from = pos & (PAGE_CACHE_SIZE - 1);
         to = from + len;
 
+        if (ext4_nonda_switch(inode->i_sb)) {
+                *fsdata = (void *)FALL_BACK_TO_NONDELALLOC;
+                return ext4_write_begin(file, mapping, pos,
+                                        len, flags, pagep, fsdata);
+        }
+        *fsdata = (void *)0;
 retry:
         /*
          * With delayed allocation, we don't log the i_disksize update
@@ -2433,6 +2561,13 @@ retry:
                 unlock_page(page);
                 ext4_journal_stop(handle);
                 page_cache_release(page);
+                /*
+                 * block_write_begin may have instantiated a few blocks
+                 * outside i_size.  Trim these off again. Don't need
+                 * i_size_read because we hold i_mutex.
+                 */
+                if (pos + len > inode->i_size)
+                        vmtruncate(inode, inode->i_size);
         }
 
         if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
@@ -2456,7 +2591,7 @@ static int ext4_da_should_update_i_disksize(struct page *page,
         bh = page_buffers(page);
         idx = offset >> inode->i_blkbits;
 
-        for (i=0; i < idx; i++)
+        for (i = 0; i < idx; i++)
                 bh = bh->b_this_page;
 
         if (!buffer_mapped(bh) || (buffer_delay(bh)))
@@ -2474,9 +2609,22 @@ static int ext4_da_write_end(struct file *file,
         handle_t *handle = ext4_journal_current_handle();
         loff_t new_i_size;
         unsigned long start, end;
+        int write_mode = (int)(unsigned long)fsdata;
+
+        if (write_mode == FALL_BACK_TO_NONDELALLOC) {
+                if (ext4_should_order_data(inode)) {
+                        return ext4_ordered_write_end(file, mapping, pos,
+                                        len, copied, page, fsdata);
+                } else if (ext4_should_writeback_data(inode)) {
+                        return ext4_writeback_write_end(file, mapping, pos,
+                                        len, copied, page, fsdata);
+                } else {
+                        BUG();
+                }
+        }
 
         start = pos & (PAGE_CACHE_SIZE - 1);
-        end = start + copied -1;
+        end = start + copied - 1;
 
         /*
          * generic_write_end() will run mark_inode_dirty() if i_size
@@ -2500,6 +2648,11 @@ static int ext4_da_write_end(struct file *file,
                                 EXT4_I(inode)->i_disksize = new_i_size;
                         }
                         up_write(&EXT4_I(inode)->i_data_sem);
+                        /* We need to mark inode dirty even if
+                         * new_i_size is less that inode->i_size
+                         * bu greater than i_disksize.(hint delalloc)
+                         */
+                        ext4_mark_inode_dirty(handle, inode);
                 }
         }
         ret2 = generic_write_end(file, mapping, pos, len, copied,
@@ -2591,7 +2744,7 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
                         return 0;
         }
 
-        return generic_block_bmap(mapping,block,ext4_get_block);
+        return generic_block_bmap(mapping, block, ext4_get_block);
 }
 
 static int bget_one(handle_t *handle, struct buffer_head *bh)
@@ -3197,7 +3350,7 @@ static Indirect *ext4_find_shared(struct inode *inode, int depth,
         if (!partial->key && *partial->p)
                 /* Writer: end */
                 goto no_top;
-        for (p=partial; p>chain && all_zeroes((__le32*)p->bh->b_data,p->p); p--)
+        for (p = partial; (p > chain) && all_zeroes((__le32 *) p->bh->b_data, p->p); p--)
                 ;
         /*
          * OK, we've found the last block that must survive. The rest of our
@@ -3216,7 +3369,7 @@ static Indirect *ext4_find_shared(struct inode *inode, int depth,
         }
         /* Writer: end */
 
-        while(partial > p) {
+        while (partial > p) {
                 brelse(partial->bh);
                 partial--;
         }
@@ -3408,9 +3561,9 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
                         /* This zaps the entire block.  Bottom up. */
                         BUFFER_TRACE(bh, "free child branches");
                         ext4_free_branches(handle, inode, bh,
-                                           (__le32*)bh->b_data,
-                                           (__le32*)bh->b_data + addr_per_block,
-                                           depth);
+                                        (__le32 *) bh->b_data,
+                                        (__le32 *) bh->b_data + addr_per_block,
+                                        depth);
 
                         /*
                          * We've probably journalled the indirect block several
@@ -3578,7 +3731,7 @@ void ext4_truncate(struct inode *inode)
          */
         down_write(&ei->i_data_sem);
 
-        ext4_discard_reservation(inode);
+        ext4_discard_preallocations(inode);
 
         /*
          * The orphan list entry will now protect us from any crash which
@@ -3673,41 +3826,6 @@ out_stop:
         ext4_journal_stop(handle);
 }
 
-static ext4_fsblk_t ext4_get_inode_block(struct super_block *sb,
-                unsigned long ino, struct ext4_iloc *iloc)
-{
-        ext4_group_t block_group;
-        unsigned long offset;
-        ext4_fsblk_t block;
-        struct ext4_group_desc *gdp;
-
-        if (!ext4_valid_inum(sb, ino)) {
-                /*
-                 * This error is already checked for in namei.c unless we are
-                 * looking at an NFS filehandle, in which case no error
-                 * report is needed
-                 */
-                return 0;
-        }
-
-        block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
-        gdp = ext4_get_group_desc(sb, block_group, NULL);
-        if (!gdp)
-                return 0;
-
-        /*
-         * Figure out the offset within the block group inode table
-         */
-        offset = ((ino - 1) % EXT4_INODES_PER_GROUP(sb)) *
-                EXT4_INODE_SIZE(sb);
-        block = ext4_inode_table(sb, gdp) +
-                (offset >> EXT4_BLOCK_SIZE_BITS(sb));
-
-        iloc->block_group = block_group;
-        iloc->offset = offset & (EXT4_BLOCK_SIZE(sb) - 1);
-        return block;
-}
-
 /*
  * ext4_get_inode_loc returns with an extra refcount against the inode's
  * underlying buffer_head on success. If 'in_mem' is true, we have all
@@ -3717,19 +3835,35 @@ static ext4_fsblk_t ext4_get_inode_block(struct super_block *sb,
 static int __ext4_get_inode_loc(struct inode *inode,
                                 struct ext4_iloc *iloc, int in_mem)
 {
-        ext4_fsblk_t block;
-        struct buffer_head *bh;
+        struct ext4_group_desc  *gdp;
+        struct buffer_head      *bh;
+        struct super_block      *sb = inode->i_sb;
+        ext4_fsblk_t            block;
+        int                     inodes_per_block, inode_offset;
+
+        iloc->bh = 0;
+        if (!ext4_valid_inum(sb, inode->i_ino))
+                return -EIO;
 
-        block = ext4_get_inode_block(inode->i_sb, inode->i_ino, iloc);
-        if (!block)
+        iloc->block_group = (inode->i_ino - 1) / EXT4_INODES_PER_GROUP(sb);
+        gdp = ext4_get_group_desc(sb, iloc->block_group, NULL);
+        if (!gdp)
                 return -EIO;
 
-        bh = sb_getblk(inode->i_sb, block);
+        /*
+         * Figure out the offset within the block group inode table
+         */
+        inodes_per_block = (EXT4_BLOCK_SIZE(sb) / EXT4_INODE_SIZE(sb));
+        inode_offset = ((inode->i_ino - 1) %
+                        EXT4_INODES_PER_GROUP(sb));
+        block = ext4_inode_table(sb, gdp) + (inode_offset / inodes_per_block);
+        iloc->offset = (inode_offset % inodes_per_block) * EXT4_INODE_SIZE(sb);
+
+        bh = sb_getblk(sb, block);
         if (!bh) {
-                ext4_error (inode->i_sb, "ext4_get_inode_loc",
-                                "unable to read inode block - "
-                                "inode=%lu, block=%llu",
-                                 inode->i_ino, block);
+                ext4_error(sb, "ext4_get_inode_loc", "unable to read "
+                           "inode block - inode=%lu, block=%llu",
+                           inode->i_ino, block);
                 return -EIO;
         }
         if (!buffer_uptodate(bh)) {
@@ -3757,28 +3891,12 @@ static int __ext4_get_inode_loc(struct inode *inode,
                  */
                 if (in_mem) {
                         struct buffer_head *bitmap_bh;
-                        struct ext4_group_desc *desc;
-                        int inodes_per_buffer;
-                        int inode_offset, i;
-                        ext4_group_t block_group;
-                        int start;
-
-                        block_group = (inode->i_ino - 1) /
-                                        EXT4_INODES_PER_GROUP(inode->i_sb);
-                        inodes_per_buffer = bh->b_size /
-                                EXT4_INODE_SIZE(inode->i_sb);
-                        inode_offset = ((inode->i_ino - 1) %
-                                        EXT4_INODES_PER_GROUP(inode->i_sb));
-                        start = inode_offset & ~(inodes_per_buffer - 1);
+                        int i, start;
 
-                        /* Is the inode bitmap in cache? */
-                        desc = ext4_get_group_desc(inode->i_sb,
-                                                block_group, NULL);
-                        if (!desc)
-                                goto make_io;
+                        start = inode_offset & ~(inodes_per_block - 1);
 
-                        bitmap_bh = sb_getblk(inode->i_sb,
-                                ext4_inode_bitmap(inode->i_sb, desc));
+                        /* Is the inode bitmap in cache? */
+                        bitmap_bh = sb_getblk(sb, ext4_inode_bitmap(sb, gdp));
                         if (!bitmap_bh)
                                 goto make_io;
 
@@ -3791,14 +3909,14 @@ static int __ext4_get_inode_loc(struct inode *inode,
                                 brelse(bitmap_bh);
                                 goto make_io;
                         }
-                        for (i = start; i < start + inodes_per_buffer; i++) {
+                        for (i = start; i < start + inodes_per_block; i++) {
                                 if (i == inode_offset)
                                         continue;
                                 if (ext4_test_bit(i, bitmap_bh->b_data))
                                         break;
                         }
                         brelse(bitmap_bh);
-                        if (i == start + inodes_per_buffer) {
+                        if (i == start + inodes_per_block) {
                                 /* all other inodes are free, so skip I/O */
                                 memset(bh->b_data, 0, bh->b_size);
                                 set_buffer_uptodate(bh);
@@ -3809,6 +3927,36 @@ static int __ext4_get_inode_loc(struct inode *inode,
 
 make_io:
                 /*
+                 * If we need to do any I/O, try to pre-readahead extra
+                 * blocks from the inode table.
+                 */
+                if (EXT4_SB(sb)->s_inode_readahead_blks) {
+                        ext4_fsblk_t b, end, table;
+                        unsigned num;
+
+                        table = ext4_inode_table(sb, gdp);
+                        /* Make sure s_inode_readahead_blks is a power of 2 */
+                        while (EXT4_SB(sb)->s_inode_readahead_blks &
+                               (EXT4_SB(sb)->s_inode_readahead_blks-1))
+                                EXT4_SB(sb)->s_inode_readahead_blks = 
+                                   (EXT4_SB(sb)->s_inode_readahead_blks &
+                                    (EXT4_SB(sb)->s_inode_readahead_blks-1));
+                        b = block & ~(EXT4_SB(sb)->s_inode_readahead_blks-1);
+                        if (table > b)
+                                b = table;
+                        end = b + EXT4_SB(sb)->s_inode_readahead_blks;
+                        num = EXT4_INODES_PER_GROUP(sb);
+                        if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+                                       EXT4_FEATURE_RO_COMPAT_GDT_CSUM))
+                                num -= le16_to_cpu(gdp->bg_itable_unused);
+                        table += num / inodes_per_block;
+                        if (end > table)
+                                end = table;
+                        while (b <= end)
+                                sb_breadahead(sb, b++);
+                }
+
+                /*
                  * There are other valid inodes in the buffer, this inode
                  * has in-inode xattrs, or we don't have this inode in memory.
                  * Read the block from disk.
@@ -3818,10 +3966,9 @@ make_io:
                 submit_bh(READ_META, bh);
                 wait_on_buffer(bh);
                 if (!buffer_uptodate(bh)) {
-                        ext4_error(inode->i_sb, "ext4_get_inode_loc",
-                                        "unable to read inode block - "
-                                        "inode=%lu, block=%llu",
-                                        inode->i_ino, block);
+                        ext4_error(sb, __func__,
+                                   "unable to read inode block - inode=%lu, "
+                                   "block=%llu", inode->i_ino, block);
                         brelse(bh);
                         return -EIO;
                 }
@@ -3913,11 +4060,10 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
                 return inode;
 
         ei = EXT4_I(inode);
-#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
         ei->i_acl = EXT4_ACL_NOT_CACHED;
         ei->i_default_acl = EXT4_ACL_NOT_CACHED;
 #endif
-        ei->i_block_alloc_info = NULL;
 
         ret = __ext4_get_inode_loc(inode, &iloc, 0);
         if (ret < 0)
@@ -3927,7 +4073,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
         inode->i_mode = le16_to_cpu(raw_inode->i_mode);
         inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
         inode->i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low);
-        if(!(test_opt (inode->i_sb, NO_UID32))) {
+        if (!(test_opt(inode->i_sb, NO_UID32))) {
                 inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
                 inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
         }
@@ -3945,7 +4091,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
                 if (inode->i_mode == 0 ||
                     !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) {
                         /* this inode is deleted */
-                        brelse (bh);
+                        brelse(bh);
                         ret = -ESTALE;
                         goto bad_inode;
                 }
@@ -3978,7 +4124,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
                 ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize);
                 if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize >
                     EXT4_INODE_SIZE(inode->i_sb)) {
-                        brelse (bh);
+                        brelse(bh);
                         ret = -EIO;
                         goto bad_inode;
                 }
@@ -4031,7 +4177,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
                         init_special_inode(inode, inode->i_mode,
                            new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
         }
-        brelse (iloc.bh);
+        brelse(iloc.bh);
         ext4_set_inode_flags(inode);
         unlock_new_inode(inode);
         return inode;
@@ -4048,7 +4194,6 @@ static int ext4_inode_blocks_set(handle_t *handle,
         struct inode *inode = &(ei->vfs_inode);
         u64 i_blocks = inode->i_blocks;
         struct super_block *sb = inode->i_sb;
-        int err = 0;
 
         if (i_blocks <= ~0U) {
                 /*
@@ -4058,36 +4203,27 @@ static int ext4_inode_blocks_set(handle_t *handle,
                 raw_inode->i_blocks_lo   = cpu_to_le32(i_blocks);
                 raw_inode->i_blocks_high = 0;
                 ei->i_flags &= ~EXT4_HUGE_FILE_FL;
-        } else if (i_blocks <= 0xffffffffffffULL) {
+                return 0;
+        }
+        if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE))
+                return -EFBIG;
+
+        if (i_blocks <= 0xffffffffffffULL) {
                 /*
                  * i_blocks can be represented in a 48 bit variable
                  * as multiple of 512 bytes
                  */
-                err = ext4_update_rocompat_feature(handle, sb,
-                                            EXT4_FEATURE_RO_COMPAT_HUGE_FILE);
-                if (err)
-                        goto  err_out;
-                /* i_block is stored in the split  48 bit fields */
                 raw_inode->i_blocks_lo   = cpu_to_le32(i_blocks);
                 raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32);
                 ei->i_flags &= ~EXT4_HUGE_FILE_FL;
         } else {
-                /*
-                 * i_blocks should be represented in a 48 bit variable
-                 * as multiple of  file system block size
-                 */
-                err = ext4_update_rocompat_feature(handle, sb,
-                                            EXT4_FEATURE_RO_COMPAT_HUGE_FILE);
-                if (err)
-                        goto  err_out;
                 ei->i_flags |= EXT4_HUGE_FILE_FL;
                 /* i_block is stored in file system block size */
                 i_blocks = i_blocks >> (inode->i_blkbits - 9);
                 raw_inode->i_blocks_lo   = cpu_to_le32(i_blocks);
                 raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32);
         }
-err_out:
-        return err;
+        return 0;
 }
 
 /*
@@ -4113,14 +4249,14 @@ static int ext4_do_update_inode(handle_t *handle,
 
         ext4_get_inode_flags(ei);
         raw_inode->i_mode = cpu_to_le16(inode->i_mode);
-        if(!(test_opt(inode->i_sb, NO_UID32))) {
+        if (!(test_opt(inode->i_sb, NO_UID32))) {
                 raw_inode->i_uid_low = cpu_to_le16(low_16_bits(inode->i_uid));
                 raw_inode->i_gid_low = cpu_to_le16(low_16_bits(inode->i_gid));
 /*
  * Fix up interoperability with old kernels. Otherwise, old inodes get
  * re-used with the upper 16 bits of the uid/gid intact
  */
-                if(!ei->i_dtime) {
+                if (!ei->i_dtime) {
                         raw_inode->i_uid_high =
                                 cpu_to_le16(high_16_bits(inode->i_uid));
                         raw_inode->i_gid_high =
@@ -4208,7 +4344,7 @@ static int ext4_do_update_inode(handle_t *handle,
         ei->i_state &= ~EXT4_STATE_NEW;
 
 out_brelse:
-        brelse (bh);
+        brelse(bh);
         ext4_std_error(inode->i_sb, err);
         return err;
 }
@@ -4811,6 +4947,7 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct page *page)
         loff_t size;
         unsigned long len;
         int ret = -EINVAL;
+        void *fsdata;
         struct file *file = vma->vm_file;
         struct inode *inode = file->f_path.dentry->d_inode;
         struct address_space *mapping = inode->i_mapping;
@@ -4849,11 +4986,11 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct page *page)
          * on the same page though
          */
         ret = mapping->a_ops->write_begin(file, mapping, page_offset(page),
-                        len, AOP_FLAG_UNINTERRUPTIBLE, &page, NULL);
+                        len, AOP_FLAG_UNINTERRUPTIBLE, &page, &fsdata);
         if (ret < 0)
                 goto out_unlock;
         ret = mapping->a_ops->write_end(file, mapping, page_offset(page),
-                        len, len, page, NULL);
+                        len, len, page, fsdata);
         if (ret < 0)
                 goto out_unlock;
         ret = 0;
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 7a6c2f1faba6..dc99b4776d58 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -23,9 +23,8 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
         struct inode *inode = filp->f_dentry->d_inode;
         struct ext4_inode_info *ei = EXT4_I(inode);
         unsigned int flags;
-        unsigned short rsv_window_size;
 
-        ext4_debug ("cmd = %u, arg = %lu\n", cmd, arg);
+        ext4_debug("cmd = %u, arg = %lu\n", cmd, arg);
 
         switch (cmd) {
         case EXT4_IOC_GETFLAGS:
@@ -34,7 +33,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
                 return put_user(flags, (int __user *) arg);
         case EXT4_IOC_SETFLAGS: {
                 handle_t *handle = NULL;
-                int err;
+                int err, migrate = 0;
                 struct ext4_iloc iloc;
                 unsigned int oldflags;
                 unsigned int jflag;
@@ -82,6 +81,17 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
                         if (!capable(CAP_SYS_RESOURCE))
                                 goto flags_out;
                 }
+                if (oldflags & EXT4_EXTENTS_FL) {
+                        /* We don't support clearning extent flags */
+                        if (!(flags & EXT4_EXTENTS_FL)) {
+                                err = -EOPNOTSUPP;
+                                goto flags_out;
+                        }
+                } else if (flags & EXT4_EXTENTS_FL) {
+                        /* migrate the file */
+                        migrate = 1;
+                        flags &= ~EXT4_EXTENTS_FL;
+                }
 
                 handle = ext4_journal_start(inode, 1);
                 if (IS_ERR(handle)) {
@@ -109,6 +119,10 @@ flags_err:
 
                 if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL))
                         err = ext4_change_inode_journal_flag(inode, jflag);
+                if (err)
+                        goto flags_out;
+                if (migrate)
+                        err = ext4_ext_migrate(inode);
 flags_out:
                 mutex_unlock(&inode->i_mutex);
                 mnt_drop_write(filp->f_path.mnt);
@@ -175,53 +189,10 @@ setversion_out:
                         return ret;
                 }
 #endif
-        case EXT4_IOC_GETRSVSZ:
-                if (test_opt(inode->i_sb, RESERVATION)
-                        && S_ISREG(inode->i_mode)
-                        && ei->i_block_alloc_info) {
-                        rsv_window_size = ei->i_block_alloc_info->rsv_window_node.rsv_goal_size;
-                        return put_user(rsv_window_size, (int __user *)arg);
-                }
-                return -ENOTTY;
-        case EXT4_IOC_SETRSVSZ: {
-                int err;
-
-                if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode))
-                        return -ENOTTY;
-
-                if (!is_owner_or_cap(inode))
-                        return -EACCES;
-
-                if (get_user(rsv_window_size, (int __user *)arg))
-                        return -EFAULT;
-
-                err = mnt_want_write(filp->f_path.mnt);
-                if (err)
-                        return err;
-
-                if (rsv_window_size > EXT4_MAX_RESERVE_BLOCKS)
-                        rsv_window_size = EXT4_MAX_RESERVE_BLOCKS;
-
-                /*
-                 * need to allocate reservation structure for this inode
-                 * before set the window size
-                 */
-                down_write(&ei->i_data_sem);
-                if (!ei->i_block_alloc_info)
-                        ext4_init_block_alloc_info(inode);
-
-                if (ei->i_block_alloc_info){
-                        struct ext4_reserve_window_node *rsv = &ei->i_block_alloc_info->rsv_window_node;
-                        rsv->rsv_goal_size = rsv_window_size;
-                }
-                up_write(&ei->i_data_sem);
-                mnt_drop_write(filp->f_path.mnt);
-                return 0;
-        }
         case EXT4_IOC_GROUP_EXTEND: {
                 ext4_fsblk_t n_blocks_count;
                 struct super_block *sb = inode->i_sb;
-                int err;
+                int err, err2;
 
                 if (!capable(CAP_SYS_RESOURCE))
                         return -EPERM;
@@ -235,8 +206,10 @@ setversion_out:
 
                 err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count);
                 jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
-                jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+                err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
                 jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+                if (err == 0)
+                        err = err2;
                 mnt_drop_write(filp->f_path.mnt);
 
                 return err;
@@ -244,7 +217,7 @@ setversion_out:
         case EXT4_IOC_GROUP_ADD: {
                 struct ext4_new_group_data input;
                 struct super_block *sb = inode->i_sb;
-                int err;
+                int err, err2;
 
                 if (!capable(CAP_SYS_RESOURCE))
                         return -EPERM;
@@ -259,15 +232,36 @@ setversion_out:
 
                 err = ext4_group_add(sb, &input);
                 jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
-                jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+                err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
                 jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+                if (err == 0)
+                        err = err2;
                 mnt_drop_write(filp->f_path.mnt);
 
                 return err;
         }
 
         case EXT4_IOC_MIGRATE:
-                return ext4_ext_migrate(inode, filp, cmd, arg);
+        {
+                int err;
+                if (!is_owner_or_cap(inode))
+                        return -EACCES;
+
+                err = mnt_want_write(filp->f_path.mnt);
+                if (err)
+                        return err;
+                /*
+                 * inode_mutex prevent write and truncate on the file.
+                 * Read still goes through. We take i_data_sem in
+                 * ext4_ext_swap_inode_data before we switch the
+                 * inode format to prevent read.
+                 */
+                mutex_lock(&(inode->i_mutex));
+                err = ext4_ext_migrate(inode);
+                mutex_unlock(&(inode->i_mutex));
+                mnt_drop_write(filp->f_path.mnt);
+                return err;
+        }
 
         default:
                 return -ENOTTY;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index e0e3a5eb1ddb..dfe17a134052 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -477,9 +477,10 @@ static void mb_cmp_bitmaps(struct ext4_buddy *e4b, void *bitmap)
                 b2 = (unsigned char *) bitmap;
                 for (i = 0; i < e4b->bd_sb->s_blocksize; i++) {
                         if (b1[i] != b2[i]) {
-                                printk("corruption in group %lu at byte %u(%u):"
-                                       " %x in copy != %x on disk/prealloc\n",
-                                        e4b->bd_group, i, i * 8, b1[i], b2[i]);
+                                printk(KERN_ERR "corruption in group %lu "
+                                       "at byte %u(%u): %x in copy != %x "
+                                       "on disk/prealloc\n",
+                                       e4b->bd_group, i, i * 8, b1[i], b2[i]);
                                 BUG();
                         }
                 }
@@ -533,9 +534,6 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
         void *buddy;
         void *buddy2;
 
-        if (!test_opt(sb, MBALLOC))
-                return 0;
-
         {
                 static int mb_check_counter;
                 if (mb_check_counter++ % 100 != 0)
@@ -784,9 +782,11 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
                 if (bh[i] == NULL)
                         goto out;
 
-                if (bh_uptodate_or_lock(bh[i]))
+                if (buffer_uptodate(bh[i]) &&
+                    !(desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))
                         continue;
 
+                lock_buffer(bh[i]);
                 spin_lock(sb_bgl_lock(EXT4_SB(sb), first_group + i));
                 if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
                         ext4_init_block_bitmap(sb, bh[i],
@@ -2169,9 +2169,10 @@ static void ext4_mb_history_release(struct super_block *sb)
 {
         struct ext4_sb_info *sbi = EXT4_SB(sb);
 
-        remove_proc_entry("mb_groups", sbi->s_mb_proc);
-        remove_proc_entry("mb_history", sbi->s_mb_proc);
-
+        if (sbi->s_proc != NULL) {
+                remove_proc_entry("mb_groups", sbi->s_proc);
+                remove_proc_entry("mb_history", sbi->s_proc);
+        }
         kfree(sbi->s_mb_history);
 }
 
@@ -2180,10 +2181,10 @@ static void ext4_mb_history_init(struct super_block *sb)
         struct ext4_sb_info *sbi = EXT4_SB(sb);
         int i;
 
-        if (sbi->s_mb_proc != NULL) {
-                proc_create_data("mb_history", S_IRUGO, sbi->s_mb_proc,
+        if (sbi->s_proc != NULL) {
+                proc_create_data("mb_history", S_IRUGO, sbi->s_proc,
                                  &ext4_mb_seq_history_fops, sb);
-                proc_create_data("mb_groups", S_IRUGO, sbi->s_mb_proc,
+                proc_create_data("mb_groups", S_IRUGO, sbi->s_proc,
                                  &ext4_mb_seq_groups_fops, sb);
         }
 
@@ -2299,6 +2300,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
         }
 
         INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list);
+        meta_group_info[i]->bb_free_root.rb_node = NULL;;
 
 #ifdef DOUBLE_CHECK
         {
@@ -2485,19 +2487,14 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
         unsigned max;
         int ret;
 
-        if (!test_opt(sb, MBALLOC))
-                return 0;
-
         i = (sb->s_blocksize_bits + 2) * sizeof(unsigned short);
 
         sbi->s_mb_offsets = kmalloc(i, GFP_KERNEL);
         if (sbi->s_mb_offsets == NULL) {
-                clear_opt(sbi->s_mount_opt, MBALLOC);
                 return -ENOMEM;
         }
         sbi->s_mb_maxs = kmalloc(i, GFP_KERNEL);
         if (sbi->s_mb_maxs == NULL) {
-                clear_opt(sbi->s_mount_opt, MBALLOC);
                 kfree(sbi->s_mb_maxs);
                 return -ENOMEM;
         }
@@ -2520,16 +2517,12 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
         /* init file for buddy data */
         ret = ext4_mb_init_backend(sb);
         if (ret != 0) {
-                clear_opt(sbi->s_mount_opt, MBALLOC);
                 kfree(sbi->s_mb_offsets);
                 kfree(sbi->s_mb_maxs);
                 return ret;
         }
 
         spin_lock_init(&sbi->s_md_lock);
-        INIT_LIST_HEAD(&sbi->s_active_transaction);
-        INIT_LIST_HEAD(&sbi->s_closed_transaction);
-        INIT_LIST_HEAD(&sbi->s_committed_transaction);
         spin_lock_init(&sbi->s_bal_lock);
 
         sbi->s_mb_max_to_scan = MB_DEFAULT_MAX_TO_SCAN;
@@ -2540,17 +2533,15 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
         sbi->s_mb_history_filter = EXT4_MB_HISTORY_DEFAULT;
         sbi->s_mb_group_prealloc = MB_DEFAULT_GROUP_PREALLOC;
 
-        i = sizeof(struct ext4_locality_group) * nr_cpu_ids;
-        sbi->s_locality_groups = kmalloc(i, GFP_KERNEL);
+        sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group);
         if (sbi->s_locality_groups == NULL) {
-                clear_opt(sbi->s_mount_opt, MBALLOC);
                 kfree(sbi->s_mb_offsets);
                 kfree(sbi->s_mb_maxs);
                 return -ENOMEM;
         }
-        for (i = 0; i < nr_cpu_ids; i++) {
+        for_each_possible_cpu(i) {
                 struct ext4_locality_group *lg;
-                lg = &sbi->s_locality_groups[i];
+                lg = per_cpu_ptr(sbi->s_locality_groups, i);
                 mutex_init(&lg->lg_mutex);
                 for (j = 0; j < PREALLOC_TB_SIZE; j++)
                         INIT_LIST_HEAD(&lg->lg_prealloc_list[j]);
@@ -2560,7 +2551,9 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
         ext4_mb_init_per_dev_proc(sb);
         ext4_mb_history_init(sb);
 
-        printk("EXT4-fs: mballoc enabled\n");
+        sbi->s_journal->j_commit_callback = release_blocks_on_commit;
+
+        printk(KERN_INFO "EXT4-fs: mballoc enabled\n");
         return 0;
 }
 
@@ -2575,7 +2568,7 @@ static void ext4_mb_cleanup_pa(struct ext4_group_info *grp)
                 pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list);
                 list_del(&pa->pa_group_list);
                 count++;
-                kfree(pa);
+                kmem_cache_free(ext4_pspace_cachep, pa);
         }
         if (count)
                 mb_debug("mballoc: %u PAs left\n", count);
@@ -2589,18 +2582,6 @@ int ext4_mb_release(struct super_block *sb)
         struct ext4_group_info *grinfo;
         struct ext4_sb_info *sbi = EXT4_SB(sb);
 
-        if (!test_opt(sb, MBALLOC))
-                return 0;
-
-        /* release freed, non-committed blocks */
-        spin_lock(&sbi->s_md_lock);
-        list_splice_init(&sbi->s_closed_transaction,
-                        &sbi->s_committed_transaction);
-        list_splice_init(&sbi->s_active_transaction,
-                        &sbi->s_committed_transaction);
-        spin_unlock(&sbi->s_md_lock);
-        ext4_mb_free_committed_blocks(sb);
-
         if (sbi->s_group_info) {
                 for (i = 0; i < sbi->s_groups_count; i++) {
                         grinfo = ext4_get_group_info(sb, i);
@@ -2647,69 +2628,64 @@ int ext4_mb_release(struct super_block *sb)
                                 atomic_read(&sbi->s_mb_discarded));
         }
 
-        kfree(sbi->s_locality_groups);
-
+        free_percpu(sbi->s_locality_groups);
         ext4_mb_history_release(sb);
         ext4_mb_destroy_per_dev_proc(sb);
 
         return 0;
 }
 
-static noinline_for_stack void
-ext4_mb_free_committed_blocks(struct super_block *sb)
+/*
+ * This function is called by the jbd2 layer once the commit has finished,
+ * so we know we can free the blocks that were released with that commit.
+ */
+static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
 {
-        struct ext4_sb_info *sbi = EXT4_SB(sb);
-        int err;
-        int i;
-        int count = 0;
-        int count2 = 0;
-        struct ext4_free_metadata *md;
+        struct super_block *sb = journal->j_private;
         struct ext4_buddy e4b;
+        struct ext4_group_info *db;
+        int err, count = 0, count2 = 0;
+        struct ext4_free_data *entry;
+        ext4_fsblk_t discard_block;
+        struct list_head *l, *ltmp;
 
-        if (list_empty(&sbi->s_committed_transaction))
-                return;
-
-        /* there is committed blocks to be freed yet */
-        do {
-                /* get next array of blocks */
-                md = NULL;
-                spin_lock(&sbi->s_md_lock);
-                if (!list_empty(&sbi->s_committed_transaction)) {
-                        md = list_entry(sbi->s_committed_transaction.next,
-                                        struct ext4_free_metadata, list);
-                        list_del(&md->list);
-                }
-                spin_unlock(&sbi->s_md_lock);
-
-                if (md == NULL)
-                        break;
+        list_for_each_safe(l, ltmp, &txn->t_private_list) {
+                entry = list_entry(l, struct ext4_free_data, list);
 
                 mb_debug("gonna free %u blocks in group %lu (0x%p):",
-                                md->num, md->group, md);
+                         entry->count, entry->group, entry);
 
-                err = ext4_mb_load_buddy(sb, md->group, &e4b);
+                err = ext4_mb_load_buddy(sb, entry->group, &e4b);
                 /* we expect to find existing buddy because it's pinned */
                 BUG_ON(err != 0);
 
+                db = e4b.bd_info;
                 /* there are blocks to put in buddy to make them really free */
-                count += md->num;
+                count += entry->count;
                 count2++;
-                ext4_lock_group(sb, md->group);
-                for (i = 0; i < md->num; i++) {
-                        mb_debug(" %u", md->blocks[i]);
-                        mb_free_blocks(NULL, &e4b, md->blocks[i], 1);
+                ext4_lock_group(sb, entry->group);
+                /* Take it out of per group rb tree */
+                rb_erase(&entry->node, &(db->bb_free_root));
+                mb_free_blocks(NULL, &e4b, entry->start_blk, entry->count);
+
+                if (!db->bb_free_root.rb_node) {
+                        /* No more items in the per group rb tree
+                         * balance refcounts from ext4_mb_free_metadata()
+                         */
+                        page_cache_release(e4b.bd_buddy_page);
+                        page_cache_release(e4b.bd_bitmap_page);
                 }
-                mb_debug("\n");
-                ext4_unlock_group(sb, md->group);
-
-                /* balance refcounts from ext4_mb_free_metadata() */
-                page_cache_release(e4b.bd_buddy_page);
-                page_cache_release(e4b.bd_bitmap_page);
-
-                kfree(md);
+                ext4_unlock_group(sb, entry->group);
+                discard_block = (ext4_fsblk_t) entry->group * EXT4_BLOCKS_PER_GROUP(sb)
+                        + entry->start_blk
+                        + le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
+                trace_mark(ext4_discard_blocks, "dev %s blk %llu count %u", sb->s_id,
+                           (unsigned long long) discard_block, entry->count);
+                sb_issue_discard(sb, discard_block, entry->count);
+
+                kmem_cache_free(ext4_free_ext_cachep, entry);
                 ext4_mb_release_desc(&e4b);
-
-        } while (md);
+        }
 
         mb_debug("freed %u blocks in %u structures\n", count, count2);
 }
@@ -2721,119 +2697,52 @@ ext4_mb_free_committed_blocks(struct super_block *sb)
 #define EXT4_MB_STREAM_REQ              "stream_req"
 #define EXT4_MB_GROUP_PREALLOC          "group_prealloc"
 
-
-
-#define MB_PROC_FOPS(name)                                      \
-static int ext4_mb_##name##_proc_show(struct seq_file *m, void *v)      \
-{                                                               \
-        struct ext4_sb_info *sbi = m->private;                  \
-                                                                \
-        seq_printf(m, "%ld\n", sbi->s_mb_##name);               \
-        return 0;                                               \
-}                                                               \
-                                                                \
-static int ext4_mb_##name##_proc_open(struct inode *inode, struct file *file)\
-{                                                               \
-        return single_open(file, ext4_mb_##name##_proc_show, PDE(inode)->data);\
-}                                                               \
-                                                                \
-static ssize_t ext4_mb_##name##_proc_write(struct file *file,   \
-                const char __user *buf, size_t cnt, loff_t *ppos)       \
-{                                                               \
-        struct ext4_sb_info *sbi = PDE(file->f_path.dentry->d_inode)->data;\
-        char str[32];                                           \
-        long value;                                             \
-        if (cnt >= sizeof(str))                                 \
-                return -EINVAL;                                 \
-        if (copy_from_user(str, buf, cnt))                      \
-                return -EFAULT;                                 \
-        value = simple_strtol(str, NULL, 0);                    \
-        if (value <= 0)                                         \
-                return -ERANGE;                                 \
-        sbi->s_mb_##name = value;                               \
-        return cnt;                                             \
-}                                                               \
-                                                                \
-static const struct file_operations ext4_mb_##name##_proc_fops = {      \
-        .owner          = THIS_MODULE,                          \
-        .open           = ext4_mb_##name##_proc_open,           \
-        .read           = seq_read,                             \
-        .llseek         = seq_lseek,                            \
-        .release        = single_release,                       \
-        .write          = ext4_mb_##name##_proc_write,          \
-};
-
-MB_PROC_FOPS(stats);
-MB_PROC_FOPS(max_to_scan);
-MB_PROC_FOPS(min_to_scan);
-MB_PROC_FOPS(order2_reqs);
-MB_PROC_FOPS(stream_request);
-MB_PROC_FOPS(group_prealloc);
-
-#define MB_PROC_HANDLER(name, var)                                      \
-do {                                                                    \
-        proc = proc_create_data(name, mode, sbi->s_mb_proc,             \
-                                &ext4_mb_##var##_proc_fops, sbi);       \
-        if (proc == NULL) {                                             \
-                printk(KERN_ERR "EXT4-fs: can't to create %s\n", name); \
-                goto err_out;                                           \
-        }                                                               \
-} while (0)
-
 static int ext4_mb_init_per_dev_proc(struct super_block *sb)
 {
+#ifdef CONFIG_PROC_FS
         mode_t mode = S_IFREG | S_IRUGO | S_IWUSR;
         struct ext4_sb_info *sbi = EXT4_SB(sb);
         struct proc_dir_entry *proc;
-        char devname[64];
 
-        if (proc_root_ext4 == NULL) {
-                sbi->s_mb_proc = NULL;
+        if (sbi->s_proc == NULL)
                 return -EINVAL;
-        }
-        bdevname(sb->s_bdev, devname);
-        sbi->s_mb_proc = proc_mkdir(devname, proc_root_ext4);
-
-        MB_PROC_HANDLER(EXT4_MB_STATS_NAME, stats);
-        MB_PROC_HANDLER(EXT4_MB_MAX_TO_SCAN_NAME, max_to_scan);
-        MB_PROC_HANDLER(EXT4_MB_MIN_TO_SCAN_NAME, min_to_scan);
-        MB_PROC_HANDLER(EXT4_MB_ORDER2_REQ, order2_reqs);
-        MB_PROC_HANDLER(EXT4_MB_STREAM_REQ, stream_request);
-        MB_PROC_HANDLER(EXT4_MB_GROUP_PREALLOC, group_prealloc);
 
+        EXT4_PROC_HANDLER(EXT4_MB_STATS_NAME, mb_stats);
+        EXT4_PROC_HANDLER(EXT4_MB_MAX_TO_SCAN_NAME, mb_max_to_scan);
+        EXT4_PROC_HANDLER(EXT4_MB_MIN_TO_SCAN_NAME, mb_min_to_scan);
+        EXT4_PROC_HANDLER(EXT4_MB_ORDER2_REQ, mb_order2_reqs);
+        EXT4_PROC_HANDLER(EXT4_MB_STREAM_REQ, mb_stream_request);
+        EXT4_PROC_HANDLER(EXT4_MB_GROUP_PREALLOC, mb_group_prealloc);
         return 0;
 
 err_out:
-        printk(KERN_ERR "EXT4-fs: Unable to create %s\n", devname);
-        remove_proc_entry(EXT4_MB_GROUP_PREALLOC, sbi->s_mb_proc);
-        remove_proc_entry(EXT4_MB_STREAM_REQ, sbi->s_mb_proc);
-        remove_proc_entry(EXT4_MB_ORDER2_REQ, sbi->s_mb_proc);
-        remove_proc_entry(EXT4_MB_MIN_TO_SCAN_NAME, sbi->s_mb_proc);
-        remove_proc_entry(EXT4_MB_MAX_TO_SCAN_NAME, sbi->s_mb_proc);
-        remove_proc_entry(EXT4_MB_STATS_NAME, sbi->s_mb_proc);
-        remove_proc_entry(devname, proc_root_ext4);
-        sbi->s_mb_proc = NULL;
-
+        remove_proc_entry(EXT4_MB_GROUP_PREALLOC, sbi->s_proc);
+        remove_proc_entry(EXT4_MB_STREAM_REQ, sbi->s_proc);
+        remove_proc_entry(EXT4_MB_ORDER2_REQ, sbi->s_proc);
+        remove_proc_entry(EXT4_MB_MIN_TO_SCAN_NAME, sbi->s_proc);
+        remove_proc_entry(EXT4_MB_MAX_TO_SCAN_NAME, sbi->s_proc);
+        remove_proc_entry(EXT4_MB_STATS_NAME, sbi->s_proc);
         return -ENOMEM;
+#else
+        return 0;
+#endif
 }
 
 static int ext4_mb_destroy_per_dev_proc(struct super_block *sb)
 {
+#ifdef CONFIG_PROC_FS
         struct ext4_sb_info *sbi = EXT4_SB(sb);
-        char devname[64];
 
-        if (sbi->s_mb_proc == NULL)
+        if (sbi->s_proc == NULL)
                 return -EINVAL;
 
-        bdevname(sb->s_bdev, devname);
-        remove_proc_entry(EXT4_MB_GROUP_PREALLOC, sbi->s_mb_proc);
-        remove_proc_entry(EXT4_MB_STREAM_REQ, sbi->s_mb_proc);
-        remove_proc_entry(EXT4_MB_ORDER2_REQ, sbi->s_mb_proc);
-        remove_proc_entry(EXT4_MB_MIN_TO_SCAN_NAME, sbi->s_mb_proc);
-        remove_proc_entry(EXT4_MB_MAX_TO_SCAN_NAME, sbi->s_mb_proc);
-        remove_proc_entry(EXT4_MB_STATS_NAME, sbi->s_mb_proc);
-        remove_proc_entry(devname, proc_root_ext4);
-
+        remove_proc_entry(EXT4_MB_GROUP_PREALLOC, sbi->s_proc);
+        remove_proc_entry(EXT4_MB_STREAM_REQ, sbi->s_proc);
+        remove_proc_entry(EXT4_MB_ORDER2_REQ, sbi->s_proc);
+        remove_proc_entry(EXT4_MB_MIN_TO_SCAN_NAME, sbi->s_proc);
+        remove_proc_entry(EXT4_MB_MAX_TO_SCAN_NAME, sbi->s_proc);
+        remove_proc_entry(EXT4_MB_STATS_NAME, sbi->s_proc);
+#endif
         return 0;
 }
 
@@ -2854,11 +2763,16 @@ int __init init_ext4_mballoc(void)
                 kmem_cache_destroy(ext4_pspace_cachep);
                 return -ENOMEM;
         }
-#ifdef CONFIG_PROC_FS
-        proc_root_ext4 = proc_mkdir("fs/ext4", NULL);
-        if (proc_root_ext4 == NULL)
-                printk(KERN_ERR "EXT4-fs: Unable to create fs/ext4\n");
-#endif
+
+        ext4_free_ext_cachep =
+                kmem_cache_create("ext4_free_block_extents",
+                                     sizeof(struct ext4_free_data),
+                                     0, SLAB_RECLAIM_ACCOUNT, NULL);
+        if (ext4_free_ext_cachep == NULL) {
+                kmem_cache_destroy(ext4_pspace_cachep);
+                kmem_cache_destroy(ext4_ac_cachep);
+                return -ENOMEM;
+        }
         return 0;
 }
 
@@ -2867,9 +2781,7 @@ void exit_ext4_mballoc(void)
         /* XXX: synchronize_rcu(); */
         kmem_cache_destroy(ext4_pspace_cachep);
         kmem_cache_destroy(ext4_ac_cachep);
-#ifdef CONFIG_PROC_FS
-        remove_proc_entry("fs/ext4", NULL);
-#endif
+        kmem_cache_destroy(ext4_free_ext_cachep);
 }
 
 
@@ -2879,7 +2791,7 @@ void exit_ext4_mballoc(void)
  */
 static noinline_for_stack int
 ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
-                                handle_t *handle)
+                                handle_t *handle, unsigned long reserv_blks)
 {
         struct buffer_head *bitmap_bh = NULL;
         struct ext4_super_block *es;
@@ -2968,15 +2880,16 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
         le16_add_cpu(&gdp->bg_free_blocks_count, -ac->ac_b_ex.fe_len);
         gdp->bg_checksum = ext4_group_desc_csum(sbi, ac->ac_b_ex.fe_group, gdp);
         spin_unlock(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group));
-
+        percpu_counter_sub(&sbi->s_freeblocks_counter, ac->ac_b_ex.fe_len);
         /*
-         * free blocks account has already be reduced/reserved
-         * at write_begin() time for delayed allocation
-         * do not double accounting
+         * Now reduce the dirty block count also. Should not go negative
          */
         if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED))
-                percpu_counter_sub(&sbi->s_freeblocks_counter,
-                                        ac->ac_b_ex.fe_len);
+                /* release all the reserved blocks if non delalloc */
+                percpu_counter_sub(&sbi->s_dirtyblocks_counter, reserv_blks);
+        else
+                percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+                                                ac->ac_b_ex.fe_len);
 
         if (sbi->s_log_groups_per_flex) {
                 ext4_group_t flex_group = ext4_flex_group(sbi,
@@ -3884,7 +3797,7 @@ out:
  *
  * FIXME!! Make sure it is valid at all the call sites
  */
-void ext4_mb_discard_inode_preallocations(struct inode *inode)
+void ext4_discard_preallocations(struct inode *inode)
 {
         struct ext4_inode_info *ei = EXT4_I(inode);
         struct super_block *sb = inode->i_sb;
@@ -3896,7 +3809,7 @@ void ext4_mb_discard_inode_preallocations(struct inode *inode)
         struct ext4_buddy e4b;
         int err;
 
-        if (!test_opt(sb, MBALLOC) || !S_ISREG(inode->i_mode)) {
+        if (!S_ISREG(inode->i_mode)) {
                 /*BUG_ON(!list_empty(&ei->i_prealloc_list));*/
                 return;
         }
@@ -4094,8 +4007,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
          * per cpu locality group is to reduce the contention between block
          * request from multiple CPUs.
          */
-        ac->ac_lg = &sbi->s_locality_groups[get_cpu()];
-        put_cpu();
+        ac->ac_lg = per_cpu_ptr(sbi->s_locality_groups, raw_smp_processor_id());
 
         /* we're going to use group allocation */
         ac->ac_flags |= EXT4_MB_HINT_GROUP_ALLOC;
@@ -4369,33 +4281,32 @@ static int ext4_mb_discard_preallocations(struct super_block *sb, int needed)
 ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
                                  struct ext4_allocation_request *ar, int *errp)
 {
+        int freed;
         struct ext4_allocation_context *ac = NULL;
         struct ext4_sb_info *sbi;
         struct super_block *sb;
         ext4_fsblk_t block = 0;
-        int freed;
-        int inquota;
+        unsigned long inquota;
+        unsigned long reserv_blks = 0;
 
         sb = ar->inode->i_sb;
         sbi = EXT4_SB(sb);
 
-        if (!test_opt(sb, MBALLOC)) {
-                block = ext4_old_new_blocks(handle, ar->inode, ar->goal,
-                                            &(ar->len), errp);
-                return block;
-        }
         if (!EXT4_I(ar->inode)->i_delalloc_reserved_flag) {
                 /*
                  * With delalloc we already reserved the blocks
                  */
-                ar->len = ext4_has_free_blocks(sbi, ar->len);
-        }
-
-        if (ar->len == 0) {
-                *errp = -ENOSPC;
-                return 0;
+                while (ar->len && ext4_claim_free_blocks(sbi, ar->len)) {
+                        /* let others to free the space */
+                        yield();
+                        ar->len = ar->len >> 1;
+                }
+                if (!ar->len) {
+                        *errp = -ENOSPC;
+                        return 0;
+                }
+                reserv_blks = ar->len;
         }
-
         while (ar->len && DQUOT_ALLOC_BLOCK(ar->inode, ar->len)) {
                 ar->flags |= EXT4_MB_HINT_NOPREALLOC;
                 ar->len--;
@@ -4416,8 +4327,6 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
                 goto out1;
         }
 
-        ext4_mb_poll_new_transaction(sb, handle);
-
         *errp = ext4_mb_initialize_context(ac, ar);
         if (*errp) {
                 ar->len = 0;
@@ -4441,7 +4350,7 @@ repeat:
         }
 
         if (likely(ac->ac_status == AC_STATUS_FOUND)) {
-                *errp = ext4_mb_mark_diskspace_used(ac, handle);
+                *errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_blks);
                 if (*errp ==  -EAGAIN) {
                         ac->ac_b_ex.fe_group = 0;
                         ac->ac_b_ex.fe_start = 0;
@@ -4476,35 +4385,20 @@ out1:
 
         return block;
 }
-static void ext4_mb_poll_new_transaction(struct super_block *sb,
-                                                handle_t *handle)
-{
-        struct ext4_sb_info *sbi = EXT4_SB(sb);
 
-        if (sbi->s_last_transaction == handle->h_transaction->t_tid)
-                return;
-
-        /* new transaction! time to close last one and free blocks for
-         * committed transaction. we know that only transaction can be
-         * active, so previos transaction can be being logged and we
-         * know that transaction before previous is known to be already
-         * logged. this means that now we may free blocks freed in all
-         * transactions before previous one. hope I'm clear enough ... */
-
-        spin_lock(&sbi->s_md_lock);
-        if (sbi->s_last_transaction != handle->h_transaction->t_tid) {
-                mb_debug("new transaction %lu, old %lu\n",
-                                (unsigned long) handle->h_transaction->t_tid,
-                                (unsigned long) sbi->s_last_transaction);
-                list_splice_init(&sbi->s_closed_transaction,
-                                &sbi->s_committed_transaction);
-                list_splice_init(&sbi->s_active_transaction,
-                                &sbi->s_closed_transaction);
-                sbi->s_last_transaction = handle->h_transaction->t_tid;
-        }
-        spin_unlock(&sbi->s_md_lock);
-
-        ext4_mb_free_committed_blocks(sb);
+/*
+ * We can merge two free data extents only if the physical blocks
+ * are contiguous, AND the extents were freed by the same transaction,
+ * AND the blocks are associated with the same group.
+ */
+static int can_merge(struct ext4_free_data *entry1,
+                        struct ext4_free_data *entry2)
+{
+        if ((entry1->t_tid == entry2->t_tid) &&
+            (entry1->group == entry2->group) &&
+            ((entry1->start_blk + entry1->count) == entry2->start_blk))
+                return 1;
+        return 0;
 }
 
 static noinline_for_stack int
@@ -4514,57 +4408,80 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
         struct ext4_group_info *db = e4b->bd_info;
         struct super_block *sb = e4b->bd_sb;
         struct ext4_sb_info *sbi = EXT4_SB(sb);
-        struct ext4_free_metadata *md;
-        int i;
+        struct ext4_free_data *entry, *new_entry;
+        struct rb_node **n = &db->bb_free_root.rb_node, *node;
+        struct rb_node *parent = NULL, *new_node;
+
 
         BUG_ON(e4b->bd_bitmap_page == NULL);
         BUG_ON(e4b->bd_buddy_page == NULL);
 
+        new_entry  = kmem_cache_alloc(ext4_free_ext_cachep, GFP_NOFS);
+        new_entry->start_blk = block;
+        new_entry->group  = group;
+        new_entry->count = count;
+        new_entry->t_tid = handle->h_transaction->t_tid;
+        new_node = &new_entry->node;
+
         ext4_lock_group(sb, group);
-        for (i = 0; i < count; i++) {
-                md = db->bb_md_cur;
-                if (md && db->bb_tid != handle->h_transaction->t_tid) {
-                        db->bb_md_cur = NULL;
-                        md = NULL;
+        if (!*n) {
+                /* first free block exent. We need to
+                   protect buddy cache from being freed,
+                 * otherwise we'll refresh it from
+                 * on-disk bitmap and lose not-yet-available
+                 * blocks */
+                page_cache_get(e4b->bd_buddy_page);
+                page_cache_get(e4b->bd_bitmap_page);
+        }
+        while (*n) {
+                parent = *n;
+                entry = rb_entry(parent, struct ext4_free_data, node);
+                if (block < entry->start_blk)
+                        n = &(*n)->rb_left;
+                else if (block >= (entry->start_blk + entry->count))
+                        n = &(*n)->rb_right;
+                else {
+                        ext4_error(sb, __func__,
+                            "Double free of blocks %d (%d %d)\n",
+                            block, entry->start_blk, entry->count);
+                        return 0;
                 }
+        }
 
-                if (md == NULL) {
-                        ext4_unlock_group(sb, group);
-                        md = kmalloc(sizeof(*md), GFP_NOFS);
-                        if (md == NULL)
-                                return -ENOMEM;
-                        md->num = 0;
-                        md->group = group;
-
-                        ext4_lock_group(sb, group);
-                        if (db->bb_md_cur == NULL) {
-                                spin_lock(&sbi->s_md_lock);
-                                list_add(&md->list, &sbi->s_active_transaction);
-                                spin_unlock(&sbi->s_md_lock);
-                                /* protect buddy cache from being freed,
-                                 * otherwise we'll refresh it from
-                                 * on-disk bitmap and lose not-yet-available
-                                 * blocks */
-                                page_cache_get(e4b->bd_buddy_page);
-                                page_cache_get(e4b->bd_bitmap_page);
-                                db->bb_md_cur = md;
-                                db->bb_tid = handle->h_transaction->t_tid;
-                                mb_debug("new md 0x%p for group %lu\n",
-                                                md, md->group);
-                        } else {
-                                kfree(md);
-                                md = db->bb_md_cur;
-                        }
+        rb_link_node(new_node, parent, n);
+        rb_insert_color(new_node, &db->bb_free_root);
+
+        /* Now try to see the extent can be merged to left and right */
+        node = rb_prev(new_node);
+        if (node) {
+                entry = rb_entry(node, struct ext4_free_data, node);
+                if (can_merge(entry, new_entry)) {
+                        new_entry->start_blk = entry->start_blk;
+                        new_entry->count += entry->count;
+                        rb_erase(node, &(db->bb_free_root));
+                        spin_lock(&sbi->s_md_lock);
+                        list_del(&entry->list);
+                        spin_unlock(&sbi->s_md_lock);
+                        kmem_cache_free(ext4_free_ext_cachep, entry);
                 }
+        }
 
-                BUG_ON(md->num >= EXT4_BB_MAX_BLOCKS);
-                md->blocks[md->num] = block + i;
-                md->num++;
-                if (md->num == EXT4_BB_MAX_BLOCKS) {
-                        /* no more space, put full container on a sb's list */
-                        db->bb_md_cur = NULL;
+        node = rb_next(new_node);
+        if (node) {
+                entry = rb_entry(node, struct ext4_free_data, node);
+                if (can_merge(new_entry, entry)) {
+                        new_entry->count += entry->count;
+                        rb_erase(node, &(db->bb_free_root));
+                        spin_lock(&sbi->s_md_lock);
+                        list_del(&entry->list);
+                        spin_unlock(&sbi->s_md_lock);
+                        kmem_cache_free(ext4_free_ext_cachep, entry);
                 }
         }
+        /* Add the extent to transaction's private list */
+        spin_lock(&sbi->s_md_lock);
+        list_add(&new_entry->list, &handle->h_transaction->t_private_list);
+        spin_unlock(&sbi->s_md_lock);
         ext4_unlock_group(sb, group);
         return 0;
 }
@@ -4592,8 +4509,6 @@ void ext4_mb_free_blocks(handle_t *handle, struct inode *inode,
 
         *freed = 0;
 
-        ext4_mb_poll_new_transaction(sb, handle);
-
         sbi = EXT4_SB(sb);
         es = EXT4_SB(sb)->s_es;
         if (block < le32_to_cpu(es->s_first_data_block) ||
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index c7c9906c2a75..b5dff1fff1e5 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -18,6 +18,8 @@
 #include <linux/pagemap.h>
 #include <linux/seq_file.h>
 #include <linux/version.h>
+#include <linux/blkdev.h>
+#include <linux/marker.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
 #include "group.h"
@@ -98,23 +100,29 @@
 
 static struct kmem_cache *ext4_pspace_cachep;
 static struct kmem_cache *ext4_ac_cachep;
+static struct kmem_cache *ext4_free_ext_cachep;
 
-#ifdef EXT4_BB_MAX_BLOCKS
-#undef EXT4_BB_MAX_BLOCKS
-#endif
-#define EXT4_BB_MAX_BLOCKS      30
+struct ext4_free_data {
+        /* this links the free block information from group_info */
+        struct rb_node node;
 
-struct ext4_free_metadata {
-        ext4_group_t group;
-        unsigned short num;
-        ext4_grpblk_t  blocks[EXT4_BB_MAX_BLOCKS];
+        /* this links the free block information from ext4_sb_info */
         struct list_head list;
+
+        /* group which free block extent belongs */
+        ext4_group_t group;
+
+        /* free block extent */
+        ext4_grpblk_t start_blk;
+        ext4_grpblk_t count;
+
+        /* transaction which freed this extent */
+        tid_t   t_tid;
 };
 
 struct ext4_group_info {
         unsigned long   bb_state;
-        unsigned long   bb_tid;
-        struct ext4_free_metadata *bb_md_cur;
+        struct rb_root  bb_free_root;
         unsigned short  bb_first_free;
         unsigned short  bb_free;
         unsigned short  bb_fragments;
@@ -257,13 +265,10 @@ static void ext4_mb_store_history(struct ext4_allocation_context *ac);
 
 #define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)
 
-static struct proc_dir_entry *proc_root_ext4;
 struct buffer_head *read_block_bitmap(struct super_block *, ext4_group_t);
 
 static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
                                         ext4_group_t group);
-static void ext4_mb_poll_new_transaction(struct super_block *, handle_t *);
-static void ext4_mb_free_committed_blocks(struct super_block *);
 static void ext4_mb_return_to_preallocation(struct inode *inode,
                                         struct ext4_buddy *e4b, sector_t block,
                                         int count);
@@ -271,6 +276,7 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *,
                         struct super_block *, struct ext4_prealloc_space *pa);
 static int ext4_mb_init_per_dev_proc(struct super_block *sb);
 static int ext4_mb_destroy_per_dev_proc(struct super_block *sb);
+static void release_blocks_on_commit(journal_t *journal, transaction_t *txn);
 
 
 static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index 46fc0b5b12ba..f2a9cf498ecd 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -447,8 +447,7 @@ static int free_ext_block(handle_t *handle, struct inode *inode)
 
 }
 
-int ext4_ext_migrate(struct inode *inode, struct file *filp,
-                                unsigned int cmd, unsigned long arg)
+int ext4_ext_migrate(struct inode *inode)
 {
         handle_t *handle;
         int retval = 0, i;
@@ -516,12 +515,6 @@ int ext4_ext_migrate(struct inode *inode, struct file *filp,
          * when we add extents we extent the journal
          */
         /*
-         * inode_mutex prevent write and truncate on the file. Read still goes
-         * through. We take i_data_sem in ext4_ext_swap_inode_data before we
-         * switch the inode format to prevent read.
-         */
-        mutex_lock(&(inode->i_mutex));
-        /*
          * Even though we take i_mutex we can still cause block allocation
          * via mmap write to holes. If we have allocated new blocks we fail
          * migrate.  New block allocation will clear EXT4_EXT_MIGRATE flag.
@@ -623,7 +616,6 @@ err_out:
         tmp_inode->i_nlink = 0;
 
         ext4_journal_stop(handle);
-        mutex_unlock(&(inode->i_mutex));
 
         if (tmp_inode)
                 iput(tmp_inode);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 387ad98350c3..92db9e945147 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -151,34 +151,36 @@ struct dx_map_entry
 
 static inline ext4_lblk_t dx_get_block(struct dx_entry *entry);
 static void dx_set_block(struct dx_entry *entry, ext4_lblk_t value);
-static inline unsigned dx_get_hash (struct dx_entry *entry);
-static void dx_set_hash (struct dx_entry *entry, unsigned value);
-static unsigned dx_get_count (struct dx_entry *entries);
-static unsigned dx_get_limit (struct dx_entry *entries);
-static void dx_set_count (struct dx_entry *entries, unsigned value);
-static void dx_set_limit (struct dx_entry *entries, unsigned value);
-static unsigned dx_root_limit (struct inode *dir, unsigned infosize);
-static unsigned dx_node_limit (struct inode *dir);
-static struct dx_frame *dx_probe(struct dentry *dentry,
+static inline unsigned dx_get_hash(struct dx_entry *entry);
+static void dx_set_hash(struct dx_entry *entry, unsigned value);
+static unsigned dx_get_count(struct dx_entry *entries);
+static unsigned dx_get_limit(struct dx_entry *entries);
+static void dx_set_count(struct dx_entry *entries, unsigned value);
+static void dx_set_limit(struct dx_entry *entries, unsigned value);
+static unsigned dx_root_limit(struct inode *dir, unsigned infosize);
+static unsigned dx_node_limit(struct inode *dir);
+static struct dx_frame *dx_probe(const struct qstr *d_name,
                                  struct inode *dir,
                                  struct dx_hash_info *hinfo,
                                  struct dx_frame *frame,
                                  int *err);
-static void dx_release (struct dx_frame *frames);
-static int dx_make_map (struct ext4_dir_entry_2 *de, int size,
-                        struct dx_hash_info *hinfo, struct dx_map_entry map[]);
+static void dx_release(struct dx_frame *frames);
+static int dx_make_map(struct ext4_dir_entry_2 *de, int size,
+                       struct dx_hash_info *hinfo, struct dx_map_entry map[]);
 static void dx_sort_map(struct dx_map_entry *map, unsigned count);
-static struct ext4_dir_entry_2 *dx_move_dirents (char *from, char *to,
+static struct ext4_dir_entry_2 *dx_move_dirents(char *from, char *to,
                 struct dx_map_entry *offsets, int count);
-static struct ext4_dir_entry_2* dx_pack_dirents (char *base, int size);
+static struct ext4_dir_entry_2* dx_pack_dirents(char *base, int size);
 static void dx_insert_block(struct dx_frame *frame,
                                         u32 hash, ext4_lblk_t block);
 static int ext4_htree_next_block(struct inode *dir, __u32 hash,
                                  struct dx_frame *frame,
                                  struct dx_frame *frames,
                                  __u32 *start_hash);
-static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry,
-                       struct ext4_dir_entry_2 **res_dir, int *err);
+static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
+                const struct qstr *d_name,
+                struct ext4_dir_entry_2 **res_dir,
+                int *err);
 static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
                              struct inode *inode);
 
@@ -207,44 +209,44 @@ static inline void dx_set_block(struct dx_entry *entry, ext4_lblk_t value)
         entry->block = cpu_to_le32(value);
 }
 
-static inline unsigned dx_get_hash (struct dx_entry *entry)
+static inline unsigned dx_get_hash(struct dx_entry *entry)
 {
         return le32_to_cpu(entry->hash);
 }
 
-static inline void dx_set_hash (struct dx_entry *entry, unsigned value)
+static inline void dx_set_hash(struct dx_entry *entry, unsigned value)
 {
         entry->hash = cpu_to_le32(value);
 }
 
-static inline unsigned dx_get_count (struct dx_entry *entries)
+static inline unsigned dx_get_count(struct dx_entry *entries)
 {
         return le16_to_cpu(((struct dx_countlimit *) entries)->count);
 }
 
-static inline unsigned dx_get_limit (struct dx_entry *entries)
+static inline unsigned dx_get_limit(struct dx_entry *entries)
 {
         return le16_to_cpu(((struct dx_countlimit *) entries)->limit);
 }
 
-static inline void dx_set_count (struct dx_entry *entries, unsigned value)
+static inline void dx_set_count(struct dx_entry *entries, unsigned value)
 {
         ((struct dx_countlimit *) entries)->count = cpu_to_le16(value);
 }
 
-static inline void dx_set_limit (struct dx_entry *entries, unsigned value)
+static inline void dx_set_limit(struct dx_entry *entries, unsigned value)
 {
         ((struct dx_countlimit *) entries)->limit = cpu_to_le16(value);
 }
 
-static inline unsigned dx_root_limit (struct inode *dir, unsigned infosize)
+static inline unsigned dx_root_limit(struct inode *dir, unsigned infosize)
 {
         unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(1) -
                 EXT4_DIR_REC_LEN(2) - infosize;
         return entry_space / sizeof(struct dx_entry);
 }
 
-static inline unsigned dx_node_limit (struct inode *dir)
+static inline unsigned dx_node_limit(struct inode *dir)
 {
         unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0);
         return entry_space / sizeof(struct dx_entry);
@@ -254,12 +256,12 @@ static inline unsigned dx_node_limit (struct inode *dir)
  * Debug
  */
 #ifdef DX_DEBUG
-static void dx_show_index (char * label, struct dx_entry *entries)
+static void dx_show_index(char * label, struct dx_entry *entries)
 {
         int i, n = dx_get_count (entries);
-        printk("%s index ", label);
+        printk(KERN_DEBUG "%s index ", label);
         for (i = 0; i < n; i++) {
-                printk("%x->%lu ", i? dx_get_hash(entries + i) :
+                printk("%x->%lu ", i ? dx_get_hash(entries + i) :
                                 0, (unsigned long)dx_get_block(entries + i));
         }
         printk("\n");
@@ -306,7 +308,7 @@ struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir,
                              struct dx_entry *entries, int levels)
 {
         unsigned blocksize = dir->i_sb->s_blocksize;
-        unsigned count = dx_get_count (entries), names = 0, space = 0, i;
+        unsigned count = dx_get_count(entries), names = 0, space = 0, i;
         unsigned bcount = 0;
         struct buffer_head *bh;
         int err;
@@ -325,11 +327,12 @@ struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir,
                 names += stats.names;
                 space += stats.space;
                 bcount += stats.bcount;
-                brelse (bh);
+                brelse(bh);
         }
         if (bcount)
-                printk("%snames %u, fullness %u (%u%%)\n", levels?"":"   ",
-                        names, space/bcount,(space/bcount)*100/blocksize);
+                printk(KERN_DEBUG "%snames %u, fullness %u (%u%%)\n", 
+                       levels ? "" : "   ", names, space/bcount,
+                       (space/bcount)*100/blocksize);
         return (struct stats) { names, space, bcount};
 }
 #endif /* DX_DEBUG */
@@ -344,7 +347,7 @@ struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir,
  * back to userspace.
  */
 static struct dx_frame *
-dx_probe(struct dentry *dentry, struct inode *dir,
+dx_probe(const struct qstr *d_name, struct inode *dir,
          struct dx_hash_info *hinfo, struct dx_frame *frame_in, int *err)
 {
         unsigned count, indirect;
@@ -355,8 +358,6 @@ dx_probe(struct dentry *dentry, struct inode *dir,
         u32 hash;
 
         frame->bh = NULL;
-        if (dentry)
-                dir = dentry->d_parent->d_inode;
         if (!(bh = ext4_bread (NULL,dir, 0, 0, err)))
                 goto fail;
         root = (struct dx_root *) bh->b_data;
@@ -372,8 +373,8 @@ dx_probe(struct dentry *dentry, struct inode *dir,
         }
         hinfo->hash_version = root->info.hash_version;
         hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed;
-        if (dentry)
-                ext4fs_dirhash(dentry->d_name.name, dentry->d_name.len, hinfo);
+        if (d_name)
+                ext4fs_dirhash(d_name->name, d_name->len, hinfo);
         hash = hinfo->hash;
 
         if (root->info.unused_flags & 1) {
@@ -406,7 +407,7 @@ dx_probe(struct dentry *dentry, struct inode *dir,
                 goto fail;
         }
 
-        dxtrace (printk("Look up %x", hash));
+        dxtrace(printk("Look up %x", hash));
         while (1)
         {
                 count = dx_get_count(entries);
@@ -555,7 +556,7 @@ static int ext4_htree_next_block(struct inode *dir, __u32 hash,
                                       0, &err)))
                         return err; /* Failure */
                 p++;
-                brelse (p->bh);
+                brelse(p->bh);
                 p->bh = bh;
                 p->at = p->entries = ((struct dx_node *) bh->b_data)->entries;
         }
@@ -593,7 +594,7 @@ static int htree_dirblock_to_tree(struct file *dir_file,
                         /* On error, skip the f_pos to the next block. */
                         dir_file->f_pos = (dir_file->f_pos |
                                         (dir->i_sb->s_blocksize - 1)) + 1;
-                        brelse (bh);
+                        brelse(bh);
                         return count;
                 }
                 ext4fs_dirhash(de->name, de->name_len, hinfo);
@@ -635,8 +636,8 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
         int ret, err;
         __u32 hashval;
 
-        dxtrace(printk("In htree_fill_tree, start hash: %x:%x\n", start_hash,
-                       start_minor_hash));
+        dxtrace(printk(KERN_DEBUG "In htree_fill_tree, start hash: %x:%x\n", 
+                       start_hash, start_minor_hash));
         dir = dir_file->f_path.dentry->d_inode;
         if (!(EXT4_I(dir)->i_flags & EXT4_INDEX_FL)) {
                 hinfo.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
@@ -648,7 +649,7 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
         }
         hinfo.hash = start_hash;
         hinfo.minor_hash = 0;
-        frame = dx_probe(NULL, dir_file->f_path.dentry->d_inode, &hinfo, frames, &err);
+        frame = dx_probe(NULL, dir, &hinfo, frames, &err);
         if (!frame)
                 return err;
 
@@ -694,8 +695,8 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
                         break;
         }
         dx_release(frames);
-        dxtrace(printk("Fill tree: returned %d entries, next hash: %x\n",
-                       count, *next_hash));
+        dxtrace(printk(KERN_DEBUG "Fill tree: returned %d entries, "
+                       "next hash: %x\n", count, *next_hash));
         return count;
 errout:
         dx_release(frames);
@@ -802,17 +803,17 @@ static inline int ext4_match (int len, const char * const name,
 /*
  * Returns 0 if not found, -1 on failure, and 1 on success
  */
-static inline int search_dirblock(struct buffer_head * bh,
+static inline int search_dirblock(struct buffer_head *bh,
                                   struct inode *dir,
-                                  struct dentry *dentry,
+                                  const struct qstr *d_name,
                                   unsigned long offset,
                                   struct ext4_dir_entry_2 ** res_dir)
 {
         struct ext4_dir_entry_2 * de;
         char * dlimit;
         int de_len;
-        const char *name = dentry->d_name.name;
-        int namelen = dentry->d_name.len;
+        const char *name = d_name->name;
+        int namelen = d_name->len;
 
         de = (struct ext4_dir_entry_2 *) bh->b_data;
         dlimit = bh->b_data + dir->i_sb->s_blocksize;
@@ -851,12 +852,13 @@ static inline int search_dirblock(struct buffer_head * bh,
  * The returned buffer_head has ->b_count elevated.  The caller is expected
  * to brelse() it when appropriate.
  */
-static struct buffer_head * ext4_find_entry (struct dentry *dentry,
+static struct buffer_head * ext4_find_entry (struct inode *dir,
+                                        const struct qstr *d_name,
                                         struct ext4_dir_entry_2 ** res_dir)
 {
-        struct super_block * sb;
-        struct buffer_head * bh_use[NAMEI_RA_SIZE];
-        struct buffer_head * bh, *ret = NULL;
+        struct super_block *sb;
+        struct buffer_head *bh_use[NAMEI_RA_SIZE];
+        struct buffer_head *bh, *ret = NULL;
         ext4_lblk_t start, block, b;
         int ra_max = 0;         /* Number of bh's in the readahead
                                    buffer, bh_use[] */
@@ -865,16 +867,15 @@ static struct buffer_head * ext4_find_entry (struct dentry *dentry,
         int num = 0;
         ext4_lblk_t  nblocks;
         int i, err;
-        struct inode *dir = dentry->d_parent->d_inode;
         int namelen;
 
         *res_dir = NULL;
         sb = dir->i_sb;
-        namelen = dentry->d_name.len;
+        namelen = d_name->len;
         if (namelen > EXT4_NAME_LEN)
                 return NULL;
         if (is_dx(dir)) {
-                bh = ext4_dx_find_entry(dentry, res_dir, &err);
+                bh = ext4_dx_find_entry(dir, d_name, res_dir, &err);
                 /*
                  * On success, or if the error was file not found,
                  * return.  Otherwise, fall back to doing a search the
@@ -882,7 +883,8 @@ static struct buffer_head * ext4_find_entry (struct dentry *dentry,
                  */
                 if (bh || (err != ERR_BAD_DX_DIR))
                         return bh;
-                dxtrace(printk("ext4_find_entry: dx failed, falling back\n"));
+                dxtrace(printk(KERN_DEBUG "ext4_find_entry: dx failed, "
+                               "falling back\n"));
         }
         nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb);
         start = EXT4_I(dir)->i_dir_start_lookup;
@@ -926,7 +928,7 @@ restart:
                         brelse(bh);
                         goto next;
                 }
-                i = search_dirblock(bh, dir, dentry,
+                i = search_dirblock(bh, dir, d_name,
                             block << EXT4_BLOCK_SIZE_BITS(sb), res_dir);
                 if (i == 1) {
                         EXT4_I(dir)->i_dir_start_lookup = block;
@@ -956,11 +958,11 @@ restart:
 cleanup_and_exit:
         /* Clean up the read-ahead blocks */
         for (; ra_ptr < ra_max; ra_ptr++)
-                brelse (bh_use[ra_ptr]);
+                brelse(bh_use[ra_ptr]);
         return ret;
 }
 
-static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry,
+static struct buffer_head * ext4_dx_find_entry(struct inode *dir, const struct qstr *d_name,
                        struct ext4_dir_entry_2 **res_dir, int *err)
 {
         struct super_block * sb;
@@ -971,14 +973,13 @@ static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry,
         struct buffer_head *bh;
         ext4_lblk_t block;
         int retval;
-        int namelen = dentry->d_name.len;
-        const u8 *name = dentry->d_name.name;
-        struct inode *dir = dentry->d_parent->d_inode;
+        int namelen = d_name->len;
+        const u8 *name = d_name->name;
 
         sb = dir->i_sb;
         /* NFS may look up ".." - look at dx_root directory block */
         if (namelen > 2 || name[0] != '.'||(name[1] != '.' && name[1] != '\0')){
-                if (!(frame = dx_probe(dentry, NULL, &hinfo, frames, err)))
+                if (!(frame = dx_probe(d_name, dir, &hinfo, frames, err)))
                         return NULL;
         } else {
                 frame = frames;
@@ -1010,7 +1011,7 @@ static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry,
                                 return bh;
                         }
                 }
-                brelse (bh);
+                brelse(bh);
                 /* Check to see if we should continue to search */
                 retval = ext4_htree_next_block(dir, hash, frame,
                                                frames, NULL);
@@ -1025,25 +1026,25 @@ static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry,
 
         *err = -ENOENT;
 errout:
-        dxtrace(printk("%s not found\n", name));
+        dxtrace(printk(KERN_DEBUG "%s not found\n", name));
         dx_release (frames);
         return NULL;
 }
 
-static struct dentry *ext4_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
 {
-        struct inode * inode;
-        struct ext4_dir_entry_2 * de;
-        struct buffer_head * bh;
+        struct inode *inode;
+        struct ext4_dir_entry_2 *de;
+        struct buffer_head *bh;
 
         if (dentry->d_name.len > EXT4_NAME_LEN)
                 return ERR_PTR(-ENAMETOOLONG);
 
-        bh = ext4_find_entry(dentry, &de);
+        bh = ext4_find_entry(dir, &dentry->d_name, &de);
         inode = NULL;
         if (bh) {
                 unsigned long ino = le32_to_cpu(de->inode);
-                brelse (bh);
+                brelse(bh);
                 if (!ext4_valid_inum(dir->i_sb, ino)) {
                         ext4_error(dir->i_sb, "ext4_lookup",
                                    "bad inode number: %lu", ino);
@@ -1062,15 +1063,14 @@ struct dentry *ext4_get_parent(struct dentry *child)
         unsigned long ino;
         struct dentry *parent;
         struct inode *inode;
-        struct dentry dotdot;
+        static const struct qstr dotdot = {
+                .name = "..",
+                .len = 2,
+        };
         struct ext4_dir_entry_2 * de;
         struct buffer_head *bh;
 
-        dotdot.d_name.name = "..";
-        dotdot.d_name.len = 2;
-        dotdot.d_parent = child; /* confusing, isn't it! */
-
-        bh = ext4_find_entry(&dotdot, &de);
+        bh = ext4_find_entry(child->d_inode, &dotdot, &de);
         inode = NULL;
         if (!bh)
                 return ERR_PTR(-ENOENT);
@@ -1201,10 +1201,10 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 
         /* create map in the end of data2 block */
         map = (struct dx_map_entry *) (data2 + blocksize);
-        count = dx_make_map ((struct ext4_dir_entry_2 *) data1,
+        count = dx_make_map((struct ext4_dir_entry_2 *) data1,
                              blocksize, hinfo, map);
         map -= count;
-        dx_sort_map (map, count);
+        dx_sort_map(map, count);
         /* Split the existing block in the middle, size-wise */
         size = 0;
         move = 0;
@@ -1225,7 +1225,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 
         /* Fancy dance to stay within two buffers */
         de2 = dx_move_dirents(data1, data2, map + split, count - split);
-        de = dx_pack_dirents(data1,blocksize);
+        de = dx_pack_dirents(data1, blocksize);
         de->rec_len = ext4_rec_len_to_disk(data1 + blocksize - (char *) de);
         de2->rec_len = ext4_rec_len_to_disk(data2 + blocksize - (char *) de2);
         dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data1, blocksize, 1));
@@ -1237,15 +1237,15 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
                 swap(*bh, bh2);
                 de = de2;
         }
-        dx_insert_block (frame, hash2 + continued, newblock);
-        err = ext4_journal_dirty_metadata (handle, bh2);
+        dx_insert_block(frame, hash2 + continued, newblock);
+        err = ext4_journal_dirty_metadata(handle, bh2);
         if (err)
                 goto journal_error;
-        err = ext4_journal_dirty_metadata (handle, frame->bh);
+        err = ext4_journal_dirty_metadata(handle, frame->bh);
         if (err)
                 goto journal_error;
-        brelse (bh2);
-        dxtrace(dx_show_index ("frame", frame->entries));
+        brelse(bh2);
+        dxtrace(dx_show_index("frame", frame->entries));
         return de;
 
 journal_error:
@@ -1271,7 +1271,7 @@ errout:
  */
 static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
                              struct inode *inode, struct ext4_dir_entry_2 *de,
-                             struct buffer_head * bh)
+                             struct buffer_head *bh)
 {
         struct inode    *dir = dentry->d_parent->d_inode;
         const char      *name = dentry->d_name.name;
@@ -1288,11 +1288,11 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
                 while ((char *) de <= top) {
                         if (!ext4_check_dir_entry("ext4_add_entry", dir, de,
                                                   bh, offset)) {
-                                brelse (bh);
+                                brelse(bh);
                                 return -EIO;
                         }
-                        if (ext4_match (namelen, name, de)) {
-                                brelse (bh);
+                        if (ext4_match(namelen, name, de)) {
+                                brelse(bh);
                                 return -EEXIST;
                         }
                         nlen = EXT4_DIR_REC_LEN(de->name_len);
@@ -1329,7 +1329,7 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
         } else
                 de->inode = 0;
         de->name_len = namelen;
-        memcpy (de->name, name, namelen);
+        memcpy(de->name, name, namelen);
         /*
          * XXX shouldn't update any times until successful
          * completion of syscall, but too many callers depend
@@ -1377,7 +1377,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
         struct fake_dirent *fde;
 
         blocksize =  dir->i_sb->s_blocksize;
-        dxtrace(printk("Creating index\n"));
+        dxtrace(printk(KERN_DEBUG "Creating index\n"));
         retval = ext4_journal_get_write_access(handle, bh);
         if (retval) {
                 ext4_std_error(dir->i_sb, retval);
@@ -1386,7 +1386,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
         }
         root = (struct dx_root *) bh->b_data;
 
-        bh2 = ext4_append (handle, dir, &block, &retval);
+        bh2 = ext4_append(handle, dir, &block, &retval);
         if (!(bh2)) {
                 brelse(bh);
                 return retval;
@@ -1412,9 +1412,9 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
         root->info.info_length = sizeof(root->info);
         root->info.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
         entries = root->entries;
-        dx_set_block (entries, 1);
-        dx_set_count (entries, 1);
-        dx_set_limit (entries, dx_root_limit(dir, sizeof(root->info)));
+        dx_set_block(entries, 1);
+        dx_set_count(entries, 1);
+        dx_set_limit(entries, dx_root_limit(dir, sizeof(root->info)));
 
         /* Initialize as for dx_probe */
         hinfo.hash_version = root->info.hash_version;
@@ -1443,14 +1443,14 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
  * may not sleep between calling this and putting something into
  * the entry, as someone else might have used it while you slept.
  */
-static int ext4_add_entry (handle_t *handle, struct dentry *dentry,
-        struct inode *inode)
+static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
+                          struct inode *inode)
 {
         struct inode *dir = dentry->d_parent->d_inode;
         unsigned long offset;
-        struct buffer_head * bh;
+        struct buffer_head *bh;
         struct ext4_dir_entry_2 *de;
-        struct super_block * sb;
+        struct super_block *sb;
         int     retval;
         int     dx_fallback=0;
         unsigned blocksize;
@@ -1500,13 +1500,13 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
         struct dx_frame frames[2], *frame;
         struct dx_entry *entries, *at;
         struct dx_hash_info hinfo;
-        struct buffer_head * bh;
+        struct buffer_head *bh;
         struct inode *dir = dentry->d_parent->d_inode;
-        struct super_block * sb = dir->i_sb;
+        struct super_block *sb = dir->i_sb;
         struct ext4_dir_entry_2 *de;
         int err;
 
-        frame = dx_probe(dentry, NULL, &hinfo, frames, &err);
+        frame = dx_probe(&dentry->d_name, dir, &hinfo, frames, &err);
         if (!frame)
                 return err;
         entries = frame->entries;
@@ -1527,7 +1527,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
         }
 
         /* Block full, should compress but for now just split */
-        dxtrace(printk("using %u of %u node entries\n",
+        dxtrace(printk(KERN_DEBUG "using %u of %u node entries\n",
                        dx_get_count(entries), dx_get_limit(entries)));
         /* Need to split index? */
         if (dx_get_count(entries) == dx_get_limit(entries)) {
@@ -1559,7 +1559,8 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
                 if (levels) {
                         unsigned icount1 = icount/2, icount2 = icount - icount1;
                         unsigned hash2 = dx_get_hash(entries + icount1);
-                        dxtrace(printk("Split index %i/%i\n", icount1, icount2));
+                        dxtrace(printk(KERN_DEBUG "Split index %i/%i\n",
+                                       icount1, icount2));
 
                         BUFFER_TRACE(frame->bh, "get_write_access"); /* index root */
                         err = ext4_journal_get_write_access(handle,
@@ -1567,11 +1568,11 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
                         if (err)
                                 goto journal_error;
 
-                        memcpy ((char *) entries2, (char *) (entries + icount1),
-                                icount2 * sizeof(struct dx_entry));
-                        dx_set_count (entries, icount1);
-                        dx_set_count (entries2, icount2);
-                        dx_set_limit (entries2, dx_node_limit(dir));
+                        memcpy((char *) entries2, (char *) (entries + icount1),
+                               icount2 * sizeof(struct dx_entry));
+                        dx_set_count(entries, icount1);
+                        dx_set_count(entries2, icount2);
+                        dx_set_limit(entries2, dx_node_limit(dir));
 
                         /* Which index block gets the new entry? */
                         if (at - entries >= icount1) {
@@ -1579,16 +1580,17 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
                                 frame->entries = entries = entries2;
                                 swap(frame->bh, bh2);
                         }
-                        dx_insert_block (frames + 0, hash2, newblock);
-                        dxtrace(dx_show_index ("node", frames[1].entries));
-                        dxtrace(dx_show_index ("node",
+                        dx_insert_block(frames + 0, hash2, newblock);
+                        dxtrace(dx_show_index("node", frames[1].entries));
+                        dxtrace(dx_show_index("node",
                                ((struct dx_node *) bh2->b_data)->entries));
                         err = ext4_journal_dirty_metadata(handle, bh2);
                         if (err)
                                 goto journal_error;
                         brelse (bh2);
                 } else {
-                        dxtrace(printk("Creating second level index...\n"));
+                        dxtrace(printk(KERN_DEBUG
+                                       "Creating second level index...\n"));
                         memcpy((char *) entries2, (char *) entries,
                                icount * sizeof(struct dx_entry));
                         dx_set_limit(entries2, dx_node_limit(dir));
@@ -1630,12 +1632,12 @@ cleanup:
  * ext4_delete_entry deletes a directory entry by merging it with the
  * previous entry
  */
-static int ext4_delete_entry (handle_t *handle,
-                              struct inode * dir,
-                              struct ext4_dir_entry_2 * de_del,
-                              struct buffer_head * bh)
+static int ext4_delete_entry(handle_t *handle,
+                             struct inode *dir,
+                             struct ext4_dir_entry_2 *de_del,
+                             struct buffer_head *bh)
 {
-        struct ext4_dir_entry_2 * de, * pde;
+        struct ext4_dir_entry_2 *de, *pde;
         int i;
 
         i = 0;
@@ -1716,11 +1718,11 @@ static int ext4_add_nondir(handle_t *handle,
  * If the create succeeds, we fill in the inode information
  * with d_instantiate().
  */
-static int ext4_create (struct inode * dir, struct dentry * dentry, int mode,
-                struct nameidata *nd)
+static int ext4_create(struct inode *dir, struct dentry *dentry, int mode,
+                       struct nameidata *nd)
 {
         handle_t *handle;
-        struct inode * inode;
+        struct inode *inode;
         int err, retries = 0;
 
 retry:
@@ -1747,8 +1749,8 @@ retry:
         return err;
 }
 
-static int ext4_mknod (struct inode * dir, struct dentry *dentry,
-                        int mode, dev_t rdev)
+static int ext4_mknod(struct inode *dir, struct dentry *dentry,
+                      int mode, dev_t rdev)
 {
         handle_t *handle;
         struct inode *inode;
@@ -1767,11 +1769,11 @@ retry:
         if (IS_DIRSYNC(dir))
                 handle->h_sync = 1;
 
-        inode = ext4_new_inode (handle, dir, mode);
+        inode = ext4_new_inode(handle, dir, mode);
         err = PTR_ERR(inode);
         if (!IS_ERR(inode)) {
                 init_special_inode(inode, inode->i_mode, rdev);
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
                 inode->i_op = &ext4_special_inode_operations;
 #endif
                 err = ext4_add_nondir(handle, dentry, inode);
@@ -1782,12 +1784,12 @@ retry:
         return err;
 }
 
-static int ext4_mkdir(struct inode * dir, struct dentry * dentry, int mode)
+static int ext4_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 {
         handle_t *handle;
-        struct inode * inode;
-        struct buffer_head * dir_block;
-        struct ext4_dir_entry_2 * de;
+        struct inode *inode;
+        struct buffer_head *dir_block;
+        struct ext4_dir_entry_2 *de;
         int err, retries = 0;
 
         if (EXT4_DIR_LINK_MAX(dir))
@@ -1803,7 +1805,7 @@ retry:
         if (IS_DIRSYNC(dir))
                 handle->h_sync = 1;
 
-        inode = ext4_new_inode (handle, dir, S_IFDIR | mode);
+        inode = ext4_new_inode(handle, dir, S_IFDIR | mode);
         err = PTR_ERR(inode);
         if (IS_ERR(inode))
                 goto out_stop;
@@ -1811,7 +1813,7 @@ retry:
         inode->i_op = &ext4_dir_inode_operations;
         inode->i_fop = &ext4_dir_operations;
         inode->i_size = EXT4_I(inode)->i_disksize = inode->i_sb->s_blocksize;
-        dir_block = ext4_bread (handle, inode, 0, 1, &err);
+        dir_block = ext4_bread(handle, inode, 0, 1, &err);
         if (!dir_block)
                 goto out_clear_inode;
         BUFFER_TRACE(dir_block, "get_write_access");
@@ -1820,26 +1822,26 @@ retry:
         de->inode = cpu_to_le32(inode->i_ino);
         de->name_len = 1;
         de->rec_len = ext4_rec_len_to_disk(EXT4_DIR_REC_LEN(de->name_len));
-        strcpy (de->name, ".");
+        strcpy(de->name, ".");
         ext4_set_de_type(dir->i_sb, de, S_IFDIR);
         de = ext4_next_entry(de);
         de->inode = cpu_to_le32(dir->i_ino);
         de->rec_len = ext4_rec_len_to_disk(inode->i_sb->s_blocksize -
                                                 EXT4_DIR_REC_LEN(1));
         de->name_len = 2;
-        strcpy (de->name, "..");
+        strcpy(de->name, "..");
         ext4_set_de_type(dir->i_sb, de, S_IFDIR);
         inode->i_nlink = 2;
         BUFFER_TRACE(dir_block, "call ext4_journal_dirty_metadata");
         ext4_journal_dirty_metadata(handle, dir_block);
-        brelse (dir_block);
+        brelse(dir_block);
         ext4_mark_inode_dirty(handle, inode);
-        err = ext4_add_entry (handle, dentry, inode);
+        err = ext4_add_entry(handle, dentry, inode);
         if (err) {
 out_clear_inode:
                 clear_nlink(inode);
                 ext4_mark_inode_dirty(handle, inode);
-                iput (inode);
+                iput(inode);
                 goto out_stop;
         }
         ext4_inc_count(handle, dir);
@@ -1856,17 +1858,17 @@ out_stop:
 /*
  * routine to check that the specified directory is empty (for rmdir)
  */
-static int empty_dir (struct inode * inode)
+static int empty_dir(struct inode *inode)
 {
         unsigned long offset;
-        struct buffer_head * bh;
-        struct ext4_dir_entry_2 * de, * de1;
-        struct super_block * sb;
+        struct buffer_head *bh;
+        struct ext4_dir_entry_2 *de, *de1;
+        struct super_block *sb;
         int err = 0;
 
         sb = inode->i_sb;
         if (inode->i_size < EXT4_DIR_REC_LEN(1) + EXT4_DIR_REC_LEN(2) ||
-            !(bh = ext4_bread (NULL, inode, 0, 0, &err))) {
+            !(bh = ext4_bread(NULL, inode, 0, 0, &err))) {
                 if (err)
                         ext4_error(inode->i_sb, __func__,
                                    "error %d reading directory #%lu offset 0",
@@ -1881,23 +1883,23 @@ static int empty_dir (struct inode * inode)
         de1 = ext4_next_entry(de);
         if (le32_to_cpu(de->inode) != inode->i_ino ||
                         !le32_to_cpu(de1->inode) ||
-                        strcmp (".", de->name) ||
-                        strcmp ("..", de1->name)) {
-                ext4_warning (inode->i_sb, "empty_dir",
-                              "bad directory (dir #%lu) - no `.' or `..'",
-                              inode->i_ino);
-                brelse (bh);
+                        strcmp(".", de->name) ||
+                        strcmp("..", de1->name)) {
+                ext4_warning(inode->i_sb, "empty_dir",
+                             "bad directory (dir #%lu) - no `.' or `..'",
+                             inode->i_ino);
+                brelse(bh);
                 return 1;
         }
         offset = ext4_rec_len_from_disk(de->rec_len) +
                  ext4_rec_len_from_disk(de1->rec_len);
         de = ext4_next_entry(de1);
-        while (offset < inode->i_size ) {
+        while (offset < inode->i_size) {
                 if (!bh ||
                         (void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
                         err = 0;
-                        brelse (bh);
-                        bh = ext4_bread (NULL, inode,
+                        brelse(bh);
+                        bh = ext4_bread(NULL, inode,
                                 offset >> EXT4_BLOCK_SIZE_BITS(sb), 0, &err);
                         if (!bh) {
                                 if (err)
@@ -1917,13 +1919,13 @@ static int empty_dir (struct inode * inode)
                         continue;
                 }
                 if (le32_to_cpu(de->inode)) {
-                        brelse (bh);
+                        brelse(bh);
                         return 0;
                 }
                 offset += ext4_rec_len_from_disk(de->rec_len);
                 de = ext4_next_entry(de);
         }
-        brelse (bh);
+        brelse(bh);
         return 1;
 }
 
@@ -1954,8 +1956,8 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
          * ->i_nlink. For, say it, character device. Not a regular file,
          * not a directory, not a symlink and ->i_nlink > 0.
          */
-        J_ASSERT ((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-                S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);
+        J_ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+                  S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);
 
         BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
         err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
@@ -2069,12 +2071,12 @@ out_brelse:
         goto out_err;
 }
 
-static int ext4_rmdir (struct inode * dir, struct dentry *dentry)
+static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
 {
         int retval;
-        struct inode * inode;
-        struct buffer_head * bh;
-        struct ext4_dir_entry_2 * de;
+        struct inode *inode;
+        struct buffer_head *bh;
+        struct ext4_dir_entry_2 *de;
         handle_t *handle;
 
         /* Initialize quotas before so that eventual writes go in
@@ -2085,7 +2087,7 @@ static int ext4_rmdir (struct inode * dir, struct dentry *dentry)
                 return PTR_ERR(handle);
 
         retval = -ENOENT;
-        bh = ext4_find_entry (dentry, &de);
+        bh = ext4_find_entry(dir, &dentry->d_name, &de);
         if (!bh)
                 goto end_rmdir;
 
@@ -2099,16 +2101,16 @@ static int ext4_rmdir (struct inode * dir, struct dentry *dentry)
                 goto end_rmdir;
 
         retval = -ENOTEMPTY;
-        if (!empty_dir (inode))
+        if (!empty_dir(inode))
                 goto end_rmdir;
 
         retval = ext4_delete_entry(handle, dir, de, bh);
         if (retval)
                 goto end_rmdir;
         if (!EXT4_DIR_LINK_EMPTY(inode))
-                ext4_warning (inode->i_sb, "ext4_rmdir",
-                              "empty directory has too many links (%d)",
-                              inode->i_nlink);
+                ext4_warning(inode->i_sb, "ext4_rmdir",
+                             "empty directory has too many links (%d)",
+                             inode->i_nlink);
         inode->i_version++;
         clear_nlink(inode);
         /* There's no need to set i_disksize: the fact that i_nlink is
@@ -2124,16 +2126,16 @@ static int ext4_rmdir (struct inode * dir, struct dentry *dentry)
 
 end_rmdir:
         ext4_journal_stop(handle);
-        brelse (bh);
+        brelse(bh);
         return retval;
 }
 
-static int ext4_unlink(struct inode * dir, struct dentry *dentry)
+static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 {
         int retval;
-        struct inode * inode;
-        struct buffer_head * bh;
-        struct ext4_dir_entry_2 * de;
+        struct inode *inode;
+        struct buffer_head *bh;
+        struct ext4_dir_entry_2 *de;
         handle_t *handle;
 
         /* Initialize quotas before so that eventual writes go
@@ -2147,7 +2149,7 @@ static int ext4_unlink(struct inode * dir, struct dentry *dentry)
                 handle->h_sync = 1;
 
         retval = -ENOENT;
-        bh = ext4_find_entry (dentry, &de);
+        bh = ext4_find_entry(dir, &dentry->d_name, &de);
         if (!bh)
                 goto end_unlink;
 
@@ -2158,9 +2160,9 @@ static int ext4_unlink(struct inode * dir, struct dentry *dentry)
                 goto end_unlink;
 
         if (!inode->i_nlink) {
-                ext4_warning (inode->i_sb, "ext4_unlink",
-                              "Deleting nonexistent file (%lu), %d",
-                              inode->i_ino, inode->i_nlink);
+                ext4_warning(inode->i_sb, "ext4_unlink",
+                             "Deleting nonexistent file (%lu), %d",
+                             inode->i_ino, inode->i_nlink);
                 inode->i_nlink = 1;
         }
         retval = ext4_delete_entry(handle, dir, de, bh);
@@ -2178,15 +2180,15 @@ static int ext4_unlink(struct inode * dir, struct dentry *dentry)
 
 end_unlink:
         ext4_journal_stop(handle);
-        brelse (bh);
+        brelse(bh);
         return retval;
 }
 
-static int ext4_symlink (struct inode * dir,
-                struct dentry *dentry, const char * symname)
+static int ext4_symlink(struct inode *dir,
+                        struct dentry *dentry, const char *symname)
 {
         handle_t *handle;
-        struct inode * inode;
+        struct inode *inode;
         int l, err, retries = 0;
 
         l = strlen(symname)+1;
@@ -2203,12 +2205,12 @@ retry:
         if (IS_DIRSYNC(dir))
                 handle->h_sync = 1;
 
-        inode = ext4_new_inode (handle, dir, S_IFLNK|S_IRWXUGO);
+        inode = ext4_new_inode(handle, dir, S_IFLNK|S_IRWXUGO);
         err = PTR_ERR(inode);
         if (IS_ERR(inode))
                 goto out_stop;
 
-        if (l > sizeof (EXT4_I(inode)->i_data)) {
+        if (l > sizeof(EXT4_I(inode)->i_data)) {
                 inode->i_op = &ext4_symlink_inode_operations;
                 ext4_set_aops(inode);
                 /*
@@ -2221,14 +2223,14 @@ retry:
                 if (err) {
                         clear_nlink(inode);
                         ext4_mark_inode_dirty(handle, inode);
-                        iput (inode);
+                        iput(inode);
                         goto out_stop;
                 }
         } else {
                 /* clear the extent format for fast symlink */
                 EXT4_I(inode)->i_flags &= ~EXT4_EXTENTS_FL;
                 inode->i_op = &ext4_fast_symlink_inode_operations;
-                memcpy((char*)&EXT4_I(inode)->i_data,symname,l);
+                memcpy((char *)&EXT4_I(inode)->i_data, symname, l);
                 inode->i_size = l-1;
         }
         EXT4_I(inode)->i_disksize = inode->i_size;
@@ -2240,8 +2242,8 @@ out_stop:
         return err;
 }
 
-static int ext4_link (struct dentry * old_dentry,
-                struct inode * dir, struct dentry *dentry)
+static int ext4_link(struct dentry *old_dentry,
+                     struct inode *dir, struct dentry *dentry)
 {
         handle_t *handle;
         struct inode *inode = old_dentry->d_inode;
@@ -2284,13 +2286,13 @@ retry:
  * Anybody can rename anything with this: the permission checks are left to the
  * higher-level routines.
  */
-static int ext4_rename (struct inode * old_dir, struct dentry *old_dentry,
-                           struct inode * new_dir,struct dentry *new_dentry)
+static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
+                       struct inode *new_dir, struct dentry *new_dentry)
 {
         handle_t *handle;
-        struct inode * old_inode, * new_inode;
-        struct buffer_head * old_bh, * new_bh, * dir_bh;
-        struct ext4_dir_entry_2 * old_de, * new_de;
+        struct inode *old_inode, *new_inode;
+        struct buffer_head *old_bh, *new_bh, *dir_bh;
+        struct ext4_dir_entry_2 *old_de, *new_de;
         int retval;
 
         old_bh = new_bh = dir_bh = NULL;
@@ -2308,7 +2310,7 @@ static int ext4_rename (struct inode * old_dir, struct dentry *old_dentry,
         if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
                 handle->h_sync = 1;
 
-        old_bh = ext4_find_entry (old_dentry, &old_de);
+        old_bh = ext4_find_entry(old_dir, &old_dentry->d_name, &old_de);
         /*
          *  Check for inode number is _not_ due to possible IO errors.
          *  We might rmdir the source, keep it as pwd of some process
@@ -2321,32 +2323,32 @@ static int ext4_rename (struct inode * old_dir, struct dentry *old_dentry,
                 goto end_rename;
 
         new_inode = new_dentry->d_inode;
-        new_bh = ext4_find_entry (new_dentry, &new_de);
+        new_bh = ext4_find_entry(new_dir, &new_dentry->d_name, &new_de);
         if (new_bh) {
                 if (!new_inode) {
-                        brelse (new_bh);
+                        brelse(new_bh);
                         new_bh = NULL;
                 }
         }
         if (S_ISDIR(old_inode->i_mode)) {
                 if (new_inode) {
                         retval = -ENOTEMPTY;
-                        if (!empty_dir (new_inode))
+                        if (!empty_dir(new_inode))
                                 goto end_rename;
                 }
                 retval = -EIO;
-                dir_bh = ext4_bread (handle, old_inode, 0, 0, &retval);
+                dir_bh = ext4_bread(handle, old_inode, 0, 0, &retval);
                 if (!dir_bh)
                         goto end_rename;
                 if (le32_to_cpu(PARENT_INO(dir_bh->b_data)) != old_dir->i_ino)
                         goto end_rename;
                 retval = -EMLINK;
-                if (!new_inode && new_dir!=old_dir &&
+                if (!new_inode && new_dir != old_dir &&
                                 new_dir->i_nlink >= EXT4_LINK_MAX)
                         goto end_rename;
         }
         if (!new_bh) {
-                retval = ext4_add_entry (handle, new_dentry, old_inode);
+                retval = ext4_add_entry(handle, new_dentry, old_inode);
                 if (retval)
                         goto end_rename;
         } else {
@@ -2388,7 +2390,7 @@ static int ext4_rename (struct inode * old_dir, struct dentry *old_dentry,
                 struct buffer_head *old_bh2;
                 struct ext4_dir_entry_2 *old_de2;
 
-                old_bh2 = ext4_find_entry(old_dentry, &old_de2);
+                old_bh2 = ext4_find_entry(old_dir, &old_dentry->d_name, &old_de2);
                 if (old_bh2) {
                         retval = ext4_delete_entry(handle, old_dir,
                                                    old_de2, old_bh2);
@@ -2433,9 +2435,9 @@ static int ext4_rename (struct inode * old_dir, struct dentry *old_dentry,
         retval = 0;
 
 end_rename:
-        brelse (dir_bh);
-        brelse (old_bh);
-        brelse (new_bh);
+        brelse(dir_bh);
+        brelse(old_bh);
+        brelse(new_bh);
         ext4_journal_stop(handle);
         return retval;
 }
@@ -2454,7 +2456,7 @@ const struct inode_operations ext4_dir_inode_operations = {
         .mknod          = ext4_mknod,
         .rename         = ext4_rename,
         .setattr        = ext4_setattr,
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
         .setxattr       = generic_setxattr,
         .getxattr       = generic_getxattr,
         .listxattr      = ext4_listxattr,
@@ -2465,7 +2467,7 @@ const struct inode_operations ext4_dir_inode_operations = {
 
 const struct inode_operations ext4_special_inode_operations = {
         .setattr        = ext4_setattr,
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
         .setxattr       = generic_setxattr,
         .getxattr       = generic_getxattr,
         .listxattr      = ext4_listxattr,
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index b3d35604ea18..b6ec1843a015 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -416,8 +416,8 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
                        "EXT4-fs: ext4_add_new_gdb: adding group block %lu\n",
                        gdb_num);
 
-        /*
-         * If we are not using the primary superblock/GDT copy don't resize,
+        /*
+         * If we are not using the primary superblock/GDT copy don't resize,
          * because the user tools have no way of handling this.  Probably a
          * bad time to do it anyways.
          */
@@ -870,11 +870,10 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
          * We can allocate memory for mb_alloc based on the new group
          * descriptor
          */
-        if (test_opt(sb, MBALLOC)) {
-                err = ext4_mb_add_more_groupinfo(sb, input->group, gdp);
-                if (err)
-                        goto exit_journal;
-        }
+        err = ext4_mb_add_more_groupinfo(sb, input->group, gdp);
+        if (err)
+                goto exit_journal;
+
         /*
          * Make the new blocks and inodes valid next.  We do this before
          * increasing the group count so that once the group is enabled,
@@ -929,6 +928,15 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
         percpu_counter_add(&sbi->s_freeinodes_counter,
                            EXT4_INODES_PER_GROUP(sb));
 
+        if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
+                ext4_group_t flex_group;
+                flex_group = ext4_flex_group(sbi, input->group);
+                sbi->s_flex_groups[flex_group].free_blocks +=
+                        input->free_blocks_count;
+                sbi->s_flex_groups[flex_group].free_inodes +=
+                        EXT4_INODES_PER_GROUP(sb);
+        }
+
         ext4_journal_dirty_metadata(handle, sbi->s_sbh);
         sb->s_dirt = 1;
 
@@ -964,7 +972,7 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
         ext4_group_t o_groups_count;
         ext4_grpblk_t last;
         ext4_grpblk_t add;
-        struct buffer_head * bh;
+        struct buffer_head *bh;
         handle_t *handle;
         int err;
         unsigned long freed_blocks;
@@ -1077,8 +1085,15 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
         /*
          * Mark mballoc pages as not up to date so that they will be updated
          * next time they are loaded by ext4_mb_load_buddy.
+         *
+         * XXX Bad, Bad, BAD!!!  We should not be overloading the
+         * Uptodate flag, particularly on thte bitmap bh, as way of
+         * hinting to ext4_mb_load_buddy() that it needs to be
+         * overloaded.  A user could take a LVM snapshot, then do an
+         * on-line fsck, and clear the uptodate flag, and this would
+         * not be a bug in userspace, but a bug in the kernel.  FIXME!!!
          */
-        if (test_opt(sb, MBALLOC)) {
+        {
                 struct ext4_sb_info *sbi = EXT4_SB(sb);
                 struct inode *inode = sbi->s_buddy_cache;
                 int blocks_per_page;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 566344b926b7..9b2b2bc4ec17 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -34,6 +34,8 @@
 #include <linux/namei.h>
 #include <linux/quotaops.h>
 #include <linux/seq_file.h>
+#include <linux/proc_fs.h>
+#include <linux/marker.h>
 #include <linux/log2.h>
 #include <linux/crc16.h>
 #include <asm/uaccess.h>
@@ -45,6 +47,8 @@
 #include "namei.h"
 #include "group.h"
 
+struct proc_dir_entry *ext4_proc_root;
+
 static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
                              unsigned long journal_devnum);
 static int ext4_create_journal(struct super_block *, struct ext4_super_block *,
@@ -370,66 +374,6 @@ void ext4_update_dynamic_rev(struct super_block *sb)
          */
 }
 
-int ext4_update_compat_feature(handle_t *handle,
-                                        struct super_block *sb, __u32 compat)
-{
-        int err = 0;
-        if (!EXT4_HAS_COMPAT_FEATURE(sb, compat)) {
-                err = ext4_journal_get_write_access(handle,
-                                EXT4_SB(sb)->s_sbh);
-                if (err)
-                        return err;
-                EXT4_SET_COMPAT_FEATURE(sb, compat);
-                sb->s_dirt = 1;
-                handle->h_sync = 1;
-                BUFFER_TRACE(EXT4_SB(sb)->s_sbh,
-                                        "call ext4_journal_dirty_met adata");
-                err = ext4_journal_dirty_metadata(handle,
-                                EXT4_SB(sb)->s_sbh);
-        }
-        return err;
-}
-
-int ext4_update_rocompat_feature(handle_t *handle,
-                                        struct super_block *sb, __u32 rocompat)
-{
-        int err = 0;
-        if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, rocompat)) {
-                err = ext4_journal_get_write_access(handle,
-                                EXT4_SB(sb)->s_sbh);
-                if (err)
-                        return err;
-                EXT4_SET_RO_COMPAT_FEATURE(sb, rocompat);
-                sb->s_dirt = 1;
-                handle->h_sync = 1;
-                BUFFER_TRACE(EXT4_SB(sb)->s_sbh,
-                                        "call ext4_journal_dirty_met adata");
-                err = ext4_journal_dirty_metadata(handle,
-                                EXT4_SB(sb)->s_sbh);
-        }
-        return err;
-}
-
-int ext4_update_incompat_feature(handle_t *handle,
-                                        struct super_block *sb, __u32 incompat)
-{
-        int err = 0;
-        if (!EXT4_HAS_INCOMPAT_FEATURE(sb, incompat)) {
-                err = ext4_journal_get_write_access(handle,
-                                EXT4_SB(sb)->s_sbh);
-                if (err)
-                        return err;
-                EXT4_SET_INCOMPAT_FEATURE(sb, incompat);
-                sb->s_dirt = 1;
-                handle->h_sync = 1;
-                BUFFER_TRACE(EXT4_SB(sb)->s_sbh,
-                                        "call ext4_journal_dirty_met adata");
-                err = ext4_journal_dirty_metadata(handle,
-                                EXT4_SB(sb)->s_sbh);
-        }
-        return err;
-}
-
 /*
  * Open the external journal device
  */
@@ -503,15 +447,18 @@ static void ext4_put_super(struct super_block *sb)
         ext4_mb_release(sb);
         ext4_ext_release(sb);
         ext4_xattr_put_super(sb);
-        jbd2_journal_destroy(sbi->s_journal);
+        if (jbd2_journal_destroy(sbi->s_journal) < 0)
+                ext4_abort(sb, __func__, "Couldn't clean up the journal");
         sbi->s_journal = NULL;
         if (!(sb->s_flags & MS_RDONLY)) {
                 EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
                 es->s_state = cpu_to_le16(sbi->s_mount_state);
-                BUFFER_TRACE(sbi->s_sbh, "marking dirty");
-                mark_buffer_dirty(sbi->s_sbh);
                 ext4_commit_super(sb, es, 1);
         }
+        if (sbi->s_proc) {
+                remove_proc_entry("inode_readahead_blks", sbi->s_proc);
+                remove_proc_entry(sb->s_id, ext4_proc_root);
+        }
 
         for (i = 0; i < sbi->s_gdb_count; i++)
                 brelse(sbi->s_group_desc[i]);
@@ -520,6 +467,7 @@ static void ext4_put_super(struct super_block *sb)
         percpu_counter_destroy(&sbi->s_freeblocks_counter);
         percpu_counter_destroy(&sbi->s_freeinodes_counter);
         percpu_counter_destroy(&sbi->s_dirs_counter);
+        percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
         brelse(sbi->s_sbh);
 #ifdef CONFIG_QUOTA
         for (i = 0; i < MAXQUOTAS; i++)
@@ -562,11 +510,10 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
         ei = kmem_cache_alloc(ext4_inode_cachep, GFP_NOFS);
         if (!ei)
                 return NULL;
-#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
         ei->i_acl = EXT4_ACL_NOT_CACHED;
         ei->i_default_acl = EXT4_ACL_NOT_CACHED;
 #endif
-        ei->i_block_alloc_info = NULL;
         ei->vfs_inode.i_version = 1;
         ei->vfs_inode.i_data.writeback_index = 0;
         memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache));
@@ -599,7 +546,7 @@ static void init_once(void *foo)
         struct ext4_inode_info *ei = (struct ext4_inode_info *) foo;
 
         INIT_LIST_HEAD(&ei->i_orphan);
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
         init_rwsem(&ei->xattr_sem);
 #endif
         init_rwsem(&ei->i_data_sem);
@@ -625,8 +572,7 @@ static void destroy_inodecache(void)
 
 static void ext4_clear_inode(struct inode *inode)
 {
-        struct ext4_block_alloc_info *rsv = EXT4_I(inode)->i_block_alloc_info;
-#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
         if (EXT4_I(inode)->i_acl &&
                         EXT4_I(inode)->i_acl != EXT4_ACL_NOT_CACHED) {
                 posix_acl_release(EXT4_I(inode)->i_acl);
@@ -638,10 +584,7 @@ static void ext4_clear_inode(struct inode *inode)
                 EXT4_I(inode)->i_default_acl = EXT4_ACL_NOT_CACHED;
         }
 #endif
-        ext4_discard_reservation(inode);
-        EXT4_I(inode)->i_block_alloc_info = NULL;
-        if (unlikely(rsv))
-                kfree(rsv);
+        ext4_discard_preallocations(inode);
         jbd2_journal_release_jbd_inode(EXT4_SB(inode->i_sb)->s_journal,
                                        &EXT4_I(inode)->jinode);
 }
@@ -654,7 +597,7 @@ static inline void ext4_show_quota_options(struct seq_file *seq,
 
         if (sbi->s_jquota_fmt)
                 seq_printf(seq, ",jqfmt=%s",
-                (sbi->s_jquota_fmt == QFMT_VFS_OLD) ? "vfsold": "vfsv0");
+                (sbi->s_jquota_fmt == QFMT_VFS_OLD) ? "vfsold" : "vfsv0");
 
         if (sbi->s_qf_names[USRQUOTA])
                 seq_printf(seq, ",usrjquota=%s", sbi->s_qf_names[USRQUOTA]);
@@ -718,7 +661,7 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
                 seq_puts(seq, ",debug");
         if (test_opt(sb, OLDALLOC))
                 seq_puts(seq, ",oldalloc");
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
         if (test_opt(sb, XATTR_USER) &&
                 !(def_mount_opts & EXT4_DEFM_XATTR_USER))
                 seq_puts(seq, ",user_xattr");
@@ -727,7 +670,7 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
                 seq_puts(seq, ",nouser_xattr");
         }
 #endif
-#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
         if (test_opt(sb, POSIX_ACL) && !(def_mount_opts & EXT4_DEFM_ACL))
                 seq_puts(seq, ",acl");
         if (!test_opt(sb, POSIX_ACL) && (def_mount_opts & EXT4_DEFM_ACL))
@@ -752,8 +695,6 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
                 seq_puts(seq, ",nobh");
         if (!test_opt(sb, EXTENTS))
                 seq_puts(seq, ",noextents");
-        if (!test_opt(sb, MBALLOC))
-                seq_puts(seq, ",nomballoc");
         if (test_opt(sb, I_VERSION))
                 seq_puts(seq, ",i_version");
         if (!test_opt(sb, DELALLOC))
@@ -773,6 +714,13 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
         else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
                 seq_puts(seq, ",data=writeback");
 
+        if (sbi->s_inode_readahead_blks != EXT4_DEF_INODE_READAHEAD_BLKS)
+                seq_printf(seq, ",inode_readahead_blks=%u",
+                           sbi->s_inode_readahead_blks);
+
+        if (test_opt(sb, DATA_ERR_ABORT))
+                seq_puts(seq, ",data_err=abort");
+
         ext4_show_quota_options(seq, sb);
         return 0;
 }
@@ -822,7 +770,7 @@ static struct dentry *ext4_fh_to_parent(struct super_block *sb, struct fid *fid,
 }
 
 #ifdef CONFIG_QUOTA
-#define QTYPE2NAME(t) ((t) == USRQUOTA?"user":"group")
+#define QTYPE2NAME(t) ((t) == USRQUOTA ? "user" : "group")
 #define QTYPE2MOPT(on, t) ((t) == USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA))
 
 static int ext4_dquot_initialize(struct inode *inode, int type);
@@ -896,20 +844,22 @@ static const struct export_operations ext4_export_ops = {
 enum {
         Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid,
         Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, Opt_err_ro,
-        Opt_nouid32, Opt_nocheck, Opt_debug, Opt_oldalloc, Opt_orlov,
+        Opt_nouid32, Opt_debug, Opt_oldalloc, Opt_orlov,
         Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
         Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh,
         Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev,
         Opt_journal_checksum, Opt_journal_async_commit,
         Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
+        Opt_data_err_abort, Opt_data_err_ignore,
         Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
         Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
         Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota,
         Opt_grpquota, Opt_extents, Opt_noextents, Opt_i_version,
-        Opt_mballoc, Opt_nomballoc, Opt_stripe, Opt_delalloc, Opt_nodelalloc,
+        Opt_stripe, Opt_delalloc, Opt_nodelalloc,
+        Opt_inode_readahead_blks
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         {Opt_bsd_df, "bsddf"},
         {Opt_minix_df, "minixdf"},
         {Opt_grpid, "grpid"},
@@ -923,8 +873,6 @@ static match_table_t tokens = {
         {Opt_err_panic, "errors=panic"},
         {Opt_err_ro, "errors=remount-ro"},
         {Opt_nouid32, "nouid32"},
-        {Opt_nocheck, "nocheck"},
-        {Opt_nocheck, "check=none"},
         {Opt_debug, "debug"},
         {Opt_oldalloc, "oldalloc"},
         {Opt_orlov, "orlov"},
@@ -947,6 +895,8 @@ static match_table_t tokens = {
         {Opt_data_journal, "data=journal"},
         {Opt_data_ordered, "data=ordered"},
         {Opt_data_writeback, "data=writeback"},
+        {Opt_data_err_abort, "data_err=abort"},
+        {Opt_data_err_ignore, "data_err=ignore"},
         {Opt_offusrjquota, "usrjquota="},
         {Opt_usrjquota, "usrjquota=%s"},
         {Opt_offgrpjquota, "grpjquota="},
@@ -961,12 +911,11 @@ static match_table_t tokens = {
         {Opt_extents, "extents"},
         {Opt_noextents, "noextents"},
         {Opt_i_version, "i_version"},
-        {Opt_mballoc, "mballoc"},
-        {Opt_nomballoc, "nomballoc"},
         {Opt_stripe, "stripe=%u"},
         {Opt_resize, "resize"},
         {Opt_delalloc, "delalloc"},
         {Opt_nodelalloc, "nodelalloc"},
+        {Opt_inode_readahead_blks, "inode_readahead_blks=%u"},
         {Opt_err, NULL},
 };
 
@@ -981,7 +930,7 @@ static ext4_fsblk_t get_sb_block(void **data)
         /*todo: use simple_strtoll with >32bit ext4 */
         sb_block = simple_strtoul(options, &options, 0);
         if (*options && *options != ',') {
-                printk("EXT4-fs: Invalid sb specification: %s\n",
+                printk(KERN_ERR "EXT4-fs: Invalid sb specification: %s\n",
                        (char *) *data);
                 return 1;
         }
@@ -1060,9 +1009,6 @@ static int parse_options(char *options, struct super_block *sb,
                 case Opt_nouid32:
                         set_opt(sbi->s_mount_opt, NO_UID32);
                         break;
-                case Opt_nocheck:
-                        clear_opt(sbi->s_mount_opt, CHECK);
-                        break;
                 case Opt_debug:
                         set_opt(sbi->s_mount_opt, DEBUG);
                         break;
@@ -1072,7 +1018,7 @@ static int parse_options(char *options, struct super_block *sb,
                 case Opt_orlov:
                         clear_opt(sbi->s_mount_opt, OLDALLOC);
                         break;
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
                 case Opt_user_xattr:
                         set_opt(sbi->s_mount_opt, XATTR_USER);
                         break;
@@ -1082,10 +1028,11 @@ static int parse_options(char *options, struct super_block *sb,
 #else
                 case Opt_user_xattr:
                 case Opt_nouser_xattr:
-                        printk("EXT4 (no)user_xattr options not supported\n");
+                        printk(KERN_ERR "EXT4 (no)user_xattr options "
+                               "not supported\n");
                         break;
 #endif
-#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
                 case Opt_acl:
                         set_opt(sbi->s_mount_opt, POSIX_ACL);
                         break;
@@ -1095,7 +1042,8 @@ static int parse_options(char *options, struct super_block *sb,
 #else
                 case Opt_acl:
                 case Opt_noacl:
-                        printk("EXT4 (no)acl options not supported\n");
+                        printk(KERN_ERR "EXT4 (no)acl options "
+                               "not supported\n");
                         break;
 #endif
                 case Opt_reservation:
@@ -1178,6 +1126,12 @@ static int parse_options(char *options, struct super_block *sb,
                                 sbi->s_mount_opt |= data_opt;
                         }
                         break;
+                case Opt_data_err_abort:
+                        set_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
+                        break;
+                case Opt_data_err_ignore:
+                        clear_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
+                        break;
 #ifdef CONFIG_QUOTA
                 case Opt_usrjquota:
                         qtype = USRQUOTA;
@@ -1189,8 +1143,8 @@ set_qf_name:
                              sb_any_quota_suspended(sb)) &&
                             !sbi->s_qf_names[qtype]) {
                                 printk(KERN_ERR
-                                        "EXT4-fs: Cannot change journaled "
-                                        "quota options when quota turned on.\n");
+                                       "EXT4-fs: Cannot change journaled "
+                                       "quota options when quota turned on.\n");
                                 return 0;
                         }
                         qname = match_strdup(&args[0]);
@@ -1357,12 +1311,6 @@ set_qf_format:
                 case Opt_nodelalloc:
                         clear_opt(sbi->s_mount_opt, DELALLOC);
                         break;
-                case Opt_mballoc:
-                        set_opt(sbi->s_mount_opt, MBALLOC);
-                        break;
-                case Opt_nomballoc:
-                        clear_opt(sbi->s_mount_opt, MBALLOC);
-                        break;
                 case Opt_stripe:
                         if (match_int(&args[0], &option))
                                 return 0;
@@ -1373,6 +1321,13 @@ set_qf_format:
                 case Opt_delalloc:
                         set_opt(sbi->s_mount_opt, DELALLOC);
                         break;
+                case Opt_inode_readahead_blks:
+                        if (match_int(&args[0], &option))
+                                return 0;
+                        if (option < 0 || option > (1 << 30))
+                                return 0;
+                        sbi->s_inode_readahead_blks = option;
+                        break;
                 default:
                         printk(KERN_ERR
                                "EXT4-fs: Unrecognized mount option \"%s\" "
@@ -1473,15 +1428,9 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
                         EXT4_INODES_PER_GROUP(sb),
                         sbi->s_mount_opt);
 
-        printk(KERN_INFO "EXT4 FS on %s, ", sb->s_id);
-        if (EXT4_SB(sb)->s_journal->j_inode == NULL) {
-                char b[BDEVNAME_SIZE];
-
-                printk("external journal on %s\n",
-                        bdevname(EXT4_SB(sb)->s_journal->j_dev, b));
-        } else {
-                printk("internal journal\n");
-        }
+        printk(KERN_INFO "EXT4 FS on %s, %s journal on %s\n",
+               sb->s_id, EXT4_SB(sb)->s_journal->j_inode ? "internal" :
+               "external", EXT4_SB(sb)->s_journal->j_devname);
         return res;
 }
 
@@ -1504,8 +1453,11 @@ static int ext4_fill_flex_info(struct super_block *sb)
         sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
         groups_per_flex = 1 << sbi->s_log_groups_per_flex;
 
-        flex_group_count = (sbi->s_groups_count + groups_per_flex - 1) /
-                groups_per_flex;
+        /* We allocate both existing and potentially added groups */
+        flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) +
+                            ((sbi->s_es->s_reserved_gdt_blocks +1 ) <<
+                              EXT4_DESC_PER_BLOCK_BITS(sb))) /
+                           groups_per_flex;
         sbi->s_flex_groups = kzalloc(flex_group_count *
                                      sizeof(struct flex_groups), GFP_KERNEL);
         if (sbi->s_flex_groups == NULL) {
@@ -1584,7 +1536,7 @@ static int ext4_check_descriptors(struct super_block *sb)
         if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
                 flexbg_flag = 1;
 
-        ext4_debug ("Checking group descriptors");
+        ext4_debug("Checking group descriptors");
 
         for (i = 0; i < sbi->s_groups_count; i++) {
                 struct ext4_group_desc *gdp = ext4_get_group_desc(sb, i, NULL);
@@ -1599,14 +1551,14 @@ static int ext4_check_descriptors(struct super_block *sb)
                 if (block_bitmap < first_block || block_bitmap > last_block) {
                         printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
                                "Block bitmap for group %lu not in group "
-                               "(block %llu)!", i, block_bitmap);
+                               "(block %llu)!\n", i, block_bitmap);
                         return 0;
                 }
                 inode_bitmap = ext4_inode_bitmap(sb, gdp);
                 if (inode_bitmap < first_block || inode_bitmap > last_block) {
                         printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
                                "Inode bitmap for group %lu not in group "
-                               "(block %llu)!", i, inode_bitmap);
+                               "(block %llu)!\n", i, inode_bitmap);
                         return 0;
                 }
                 inode_table = ext4_inode_table(sb, gdp);
@@ -1614,7 +1566,7 @@ static int ext4_check_descriptors(struct super_block *sb)
                     inode_table + sbi->s_itb_per_group - 1 > last_block) {
                         printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
                                "Inode table for group %lu not in group "
-                               "(block %llu)!", i, inode_table);
+                               "(block %llu)!\n", i, inode_table);
                         return 0;
                 }
                 spin_lock(sb_bgl_lock(sbi, i));
@@ -1623,8 +1575,10 @@ static int ext4_check_descriptors(struct super_block *sb)
                                "Checksum for group %lu failed (%u!=%u)\n",
                                i, le16_to_cpu(ext4_group_desc_csum(sbi, i,
                                gdp)), le16_to_cpu(gdp->bg_checksum));
-                        if (!(sb->s_flags & MS_RDONLY))
+                        if (!(sb->s_flags & MS_RDONLY)) {
+                                spin_unlock(sb_bgl_lock(sbi, i));
                                 return 0;
+                        }
                 }
                 spin_unlock(sb_bgl_lock(sbi, i));
                 if (!flexbg_flag)
@@ -1714,9 +1668,9 @@ static void ext4_orphan_cleanup(struct super_block *sb,
                 DQUOT_INIT(inode);
                 if (inode->i_nlink) {
                         printk(KERN_DEBUG
-                                "%s: truncating inode %lu to %Ld bytes\n",
+                                "%s: truncating inode %lu to %lld bytes\n",
                                 __func__, inode->i_ino, inode->i_size);
-                        jbd_debug(2, "truncating inode %lu to %Ld bytes\n",
+                        jbd_debug(2, "truncating inode %lu to %lld bytes\n",
                                   inode->i_ino, inode->i_size);
                         ext4_truncate(inode);
                         nr_truncates++;
@@ -1757,13 +1711,13 @@ static void ext4_orphan_cleanup(struct super_block *sb,
  *
  * Note, this does *not* consider any metadata overhead for vfs i_blocks.
  */
-static loff_t ext4_max_size(int blkbits)
+static loff_t ext4_max_size(int blkbits, int has_huge_files)
 {
         loff_t res;
         loff_t upper_limit = MAX_LFS_FILESIZE;
 
         /* small i_blocks in vfs inode? */
-        if (sizeof(blkcnt_t) < sizeof(u64)) {
+        if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) {
                 /*
                  * CONFIG_LSF is not enabled implies the inode
                  * i_block represent total blocks in 512 bytes
@@ -1793,7 +1747,7 @@ static loff_t ext4_max_size(int blkbits)
  * block limit, and also a limit of (2^48 - 1) 512-byte sectors in i_blocks.
  * We need to be 1 filesystem block less than the 2^48 sector limit.
  */
-static loff_t ext4_max_bitmap_size(int bits)
+static loff_t ext4_max_bitmap_size(int bits, int has_huge_files)
 {
         loff_t res = EXT4_NDIR_BLOCKS;
         int meta_blocks;
@@ -1806,11 +1760,11 @@ static loff_t ext4_max_bitmap_size(int bits)
          * total number of  512 bytes blocks of the file
          */
 
-        if (sizeof(blkcnt_t) < sizeof(u64)) {
+        if (!has_huge_files || sizeof(blkcnt_t) < sizeof(u64)) {
                 /*
-                 * CONFIG_LSF is not enabled implies the inode
-                 * i_block represent total blocks in 512 bytes
-                 * 32 == size of vfs inode i_blocks * 8
+                 * !has_huge_files or CONFIG_LSF is not enabled
+                 * implies the inode i_block represent total blocks in
+                 * 512 bytes 32 == size of vfs inode i_blocks * 8
                  */
                 upper_limit = (1LL << 32) - 1;
 
@@ -1914,11 +1868,12 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
         unsigned long journal_devnum = 0;
         unsigned long def_mount_opts;
         struct inode *root;
+        char *cp;
         int ret = -EINVAL;
         int blocksize;
         int db_count;
         int i;
-        int needs_recovery;
+        int needs_recovery, has_huge_files;
         __le32 features;
         __u64 blocks_count;
         int err;
@@ -1930,10 +1885,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
         sbi->s_mount_opt = 0;
         sbi->s_resuid = EXT4_DEF_RESUID;
         sbi->s_resgid = EXT4_DEF_RESGID;
+        sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;
         sbi->s_sb_block = sb_block;
 
         unlock_kernel();
 
+        /* Cleanup superblock name */
+        for (cp = sb->s_id; (cp = strchr(cp, '/'));)
+                *cp = '!';
+
         blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE);
         if (!blocksize) {
                 printk(KERN_ERR "EXT4-fs: unable to set blocksize\n");
@@ -1973,11 +1933,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
                 set_opt(sbi->s_mount_opt, GRPID);
         if (def_mount_opts & EXT4_DEFM_UID16)
                 set_opt(sbi->s_mount_opt, NO_UID32);
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
         if (def_mount_opts & EXT4_DEFM_XATTR_USER)
                 set_opt(sbi->s_mount_opt, XATTR_USER);
 #endif
-#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
         if (def_mount_opts & EXT4_DEFM_ACL)
                 set_opt(sbi->s_mount_opt, POSIX_ACL);
 #endif
@@ -2012,11 +1972,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
                 ext4_warning(sb, __func__,
                         "extents feature not enabled on this filesystem, "
                         "use tune2fs.\n");
-        /*
-         * turn on mballoc code by default in ext4 filesystem
-         * Use -o nomballoc to turn it off
-         */
-        set_opt(sbi->s_mount_opt, MBALLOC);
 
         /*
          * enable delayed allocation by default
@@ -2041,16 +1996,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
                        "running e2fsck is recommended\n");
 
         /*
-         * Since ext4 is still considered development code, we require
-         * that the TEST_FILESYS flag in s->flags be set.
-         */
-        if (!(le32_to_cpu(es->s_flags) & EXT2_FLAGS_TEST_FILESYS)) {
-                printk(KERN_WARNING "EXT4-fs: %s: not marked "
-                       "OK to use with test code.\n", sb->s_id);
-                goto failed_mount;
-        }
-
-        /*
          * Check feature flags regardless of the revision level, since we
          * previously didn't change the revision level when setting the flags,
          * so there is a chance incompat flags are set on a rev 0 filesystem.
@@ -2069,7 +2014,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
                        sb->s_id, le32_to_cpu(features));
                 goto failed_mount;
         }
-        if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE)) {
+        has_huge_files = EXT4_HAS_RO_COMPAT_FEATURE(sb,
+                                    EXT4_FEATURE_RO_COMPAT_HUGE_FILE);
+        if (has_huge_files) {
                 /*
                  * Large file size enabled file system can only be
                  * mount if kernel is build with CONFIG_LSF
@@ -2119,8 +2066,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
                 }
         }
 
-        sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits);
-        sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits);
+        sbi->s_bitmap_maxbytes = ext4_max_bitmap_size(sb->s_blocksize_bits,
+                                                      has_huge_files);
+        sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits, has_huge_files);
 
         if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) {
                 sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE;
@@ -2219,6 +2167,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
                 goto failed_mount;
         }
 
+#ifdef CONFIG_PROC_FS
+        if (ext4_proc_root)
+                sbi->s_proc = proc_mkdir(sb->s_id, ext4_proc_root);
+
+        if (sbi->s_proc)
+                proc_create_data("inode_readahead_blks", 0644, sbi->s_proc,
+                                 &ext4_ui_proc_fops,
+                                 &sbi->s_inode_readahead_blks);
+#endif
+
         bgl_lock_init(&sbi->s_blockgroup_lock);
 
         for (i = 0; i < db_count; i++) {
@@ -2257,24 +2215,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
                 err = percpu_counter_init(&sbi->s_dirs_counter,
                                 ext4_count_dirs(sb));
         }
+        if (!err) {
+                err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
+        }
         if (err) {
                 printk(KERN_ERR "EXT4-fs: insufficient memory\n");
                 goto failed_mount3;
         }
 
-        /* per fileystem reservation list head & lock */
-        spin_lock_init(&sbi->s_rsv_window_lock);
-        sbi->s_rsv_window_root = RB_ROOT;
-        /* Add a single, static dummy reservation to the start of the
-         * reservation window list --- it gives us a placeholder for
-         * append-at-start-of-list which makes the allocation logic
-         * _much_ simpler. */
-        sbi->s_rsv_window_head.rsv_start = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
-        sbi->s_rsv_window_head.rsv_end = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
-        sbi->s_rsv_window_head.rsv_alloc_hit = 0;
-        sbi->s_rsv_window_head.rsv_goal_size = 0;
-        ext4_rsv_window_add(sb, &sbi->s_rsv_window_head);
-
         sbi->s_stripe = ext4_get_stripe_size(sbi);
 
         /*
@@ -2444,6 +2392,21 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
                         "available.\n");
         }
 
+        if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
+                printk(KERN_WARNING "EXT4-fs: Ignoring delalloc option - "
+                                "requested data journaling mode\n");
+                clear_opt(sbi->s_mount_opt, DELALLOC);
+        } else if (test_opt(sb, DELALLOC))
+                printk(KERN_INFO "EXT4-fs: delayed allocation enabled\n");
+
+        ext4_ext_init(sb);
+        err = ext4_mb_init(sb, needs_recovery);
+        if (err) {
+                printk(KERN_ERR "EXT4-fs: failed to initalize mballoc (%d)\n",
+                       err);
+                goto failed_mount4;
+        }
+
         /*
          * akpm: core read_super() calls in here with the superblock locked.
          * That deadlocks, because orphan cleanup needs to lock the superblock
@@ -2463,16 +2426,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
                test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA ? "ordered":
                "writeback");
 
-        if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
-                printk(KERN_WARNING "EXT4-fs: Ignoring delalloc option - "
-                                "requested data journaling mode\n");
-                clear_opt(sbi->s_mount_opt, DELALLOC);
-        } else if (test_opt(sb, DELALLOC))
-                printk(KERN_INFO "EXT4-fs: delayed allocation enabled\n");
-
-        ext4_ext_init(sb);
-        ext4_mb_init(sb, needs_recovery);
-
         lock_kernel();
         return 0;
 
@@ -2489,11 +2442,16 @@ failed_mount3:
         percpu_counter_destroy(&sbi->s_freeblocks_counter);
         percpu_counter_destroy(&sbi->s_freeinodes_counter);
         percpu_counter_destroy(&sbi->s_dirs_counter);
+        percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
 failed_mount2:
         for (i = 0; i < db_count; i++)
                 brelse(sbi->s_group_desc[i]);
         kfree(sbi->s_group_desc);
 failed_mount:
+        if (sbi->s_proc) {
+                remove_proc_entry("inode_readahead_blks", sbi->s_proc);
+                remove_proc_entry(sb->s_id, ext4_proc_root);
+        }
 #ifdef CONFIG_QUOTA
         for (i = 0; i < MAXQUOTAS; i++)
                 kfree(sbi->s_qf_names[i]);
@@ -2527,6 +2485,10 @@ static void ext4_init_journal_params(struct super_block *sb, journal_t *journal)
                 journal->j_flags |= JBD2_BARRIER;
         else
                 journal->j_flags &= ~JBD2_BARRIER;
+        if (test_opt(sb, DATA_ERR_ABORT))
+                journal->j_flags |= JBD2_ABORT_ON_SYNCDATA_ERR;
+        else
+                journal->j_flags &= ~JBD2_ABORT_ON_SYNCDATA_ERR;
         spin_unlock(&journal->j_state_lock);
 }
 
@@ -2552,7 +2514,7 @@ static journal_t *ext4_get_journal(struct super_block *sb,
                 return NULL;
         }
 
-        jbd_debug(2, "Journal inode found at %p: %Ld bytes\n",
+        jbd_debug(2, "Journal inode found at %p: %lld bytes\n",
                   journal_inode, journal_inode->i_size);
         if (!S_ISREG(journal_inode->i_mode)) {
                 printk(KERN_ERR "EXT4-fs: invalid journal inode.\n");
@@ -2715,6 +2677,11 @@ static int ext4_load_journal(struct super_block *sb,
                         return -EINVAL;
         }
 
+        if (journal->j_flags & JBD2_BARRIER)
+                printk(KERN_INFO "EXT4-fs: barriers enabled\n");
+        else
+                printk(KERN_INFO "EXT4-fs: barriers disabled\n");
+
         if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) {
                 err = jbd2_journal_update_format(journal);
                 if (err)  {
@@ -2799,13 +2766,34 @@ static void ext4_commit_super(struct super_block *sb,
 
         if (!sbh)
                 return;
+        if (buffer_write_io_error(sbh)) {
+                /*
+                 * Oh, dear.  A previous attempt to write the
+                 * superblock failed.  This could happen because the
+                 * USB device was yanked out.  Or it could happen to
+                 * be a transient write error and maybe the block will
+                 * be remapped.  Nothing we can do but to retry the
+                 * write and hope for the best.
+                 */
+                printk(KERN_ERR "ext4: previous I/O error to "
+                       "superblock detected for %s.\n", sb->s_id);
+                clear_buffer_write_io_error(sbh);
+                set_buffer_uptodate(sbh);
+        }
         es->s_wtime = cpu_to_le32(get_seconds());
         ext4_free_blocks_count_set(es, ext4_count_free_blocks(sb));
         es->s_free_inodes_count = cpu_to_le32(ext4_count_free_inodes(sb));
         BUFFER_TRACE(sbh, "marking dirty");
         mark_buffer_dirty(sbh);
-        if (sync)
+        if (sync) {
                 sync_dirty_buffer(sbh);
+                if (buffer_write_io_error(sbh)) {
+                        printk(KERN_ERR "ext4: I/O error while writing "
+                               "superblock for %s.\n", sb->s_id);
+                        clear_buffer_write_io_error(sbh);
+                        set_buffer_uptodate(sbh);
+                }
+        }
 }
 
 
@@ -2820,7 +2808,9 @@ static void ext4_mark_recovery_complete(struct super_block *sb,
         journal_t *journal = EXT4_SB(sb)->s_journal;
 
         jbd2_journal_lock_updates(journal);
-        jbd2_journal_flush(journal);
+        if (jbd2_journal_flush(journal) < 0)
+                goto out;
+
         lock_super(sb);
         if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER) &&
             sb->s_flags & MS_RDONLY) {
@@ -2829,6 +2819,8 @@ static void ext4_mark_recovery_complete(struct super_block *sb,
                 ext4_commit_super(sb, es, 1);
         }
         unlock_super(sb);
+
+out:
         jbd2_journal_unlock_updates(journal);
 }
 
@@ -2907,6 +2899,7 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
 {
         tid_t target;
 
+        trace_mark(ext4_sync_fs, "dev %s wait %d", sb->s_id, wait);
         sb->s_dirt = 0;
         if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, &target)) {
                 if (wait)
@@ -2928,7 +2921,13 @@ static void ext4_write_super_lockfs(struct super_block *sb)
 
                 /* Now we set up the journal barrier. */
                 jbd2_journal_lock_updates(journal);
-                jbd2_journal_flush(journal);
+
+                /*
+                 * We don't want to clear needs_recovery flag when we failed
+                 * to flush the journal.
+                 */
+                if (jbd2_journal_flush(journal) < 0)
+                        return;
 
                 /* Journal blocked and flushed, clear needs_recovery flag. */
                 EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
@@ -3162,7 +3161,8 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
         buf->f_type = EXT4_SUPER_MAGIC;
         buf->f_bsize = sb->s_blocksize;
         buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last;
-        buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter);
+        buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) -
+                       percpu_counter_sum_positive(&sbi->s_dirtyblocks_counter);
         ext4_free_blocks_count_set(es, buf->f_bfree);
         buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
         if (buf->f_bfree < ext4_r_blocks_count(es))
@@ -3367,8 +3367,12 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
                  * otherwise be livelocked...
                  */
                 jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
-                jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+                err = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
                 jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+                if (err) {
+                        path_put(&nd.path);
+                        return err;
+                }
         }
 
         err = vfs_quota_on_path(sb, type, format_id, &nd.path);
@@ -3432,7 +3436,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
         handle_t *handle = journal_current_handle();
 
         if (!handle) {
-                printk(KERN_WARNING "EXT4-fs: Quota write (off=%Lu, len=%Lu)"
+                printk(KERN_WARNING "EXT4-fs: Quota write (off=%llu, len=%llu)"
                         " cancelled because transaction is not started.\n",
                         (unsigned long long)off, (unsigned long long)len);
                 return -EIO;
@@ -3493,18 +3497,82 @@ static int ext4_get_sb(struct file_system_type *fs_type,
         return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super, mnt);
 }
 
+#ifdef CONFIG_PROC_FS
+static int ext4_ui_proc_show(struct seq_file *m, void *v)
+{
+        unsigned int *p = m->private;
+
+        seq_printf(m, "%u\n", *p);
+        return 0;
+}
+
+static int ext4_ui_proc_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, ext4_ui_proc_show, PDE(inode)->data);
+}
+
+static ssize_t ext4_ui_proc_write(struct file *file, const char __user *buf,
+                               size_t cnt, loff_t *ppos)
+{
+        unsigned int *p = PDE(file->f_path.dentry->d_inode)->data;
+        char str[32];
+        unsigned long value;
+
+        if (cnt >= sizeof(str))
+                return -EINVAL;
+        if (copy_from_user(str, buf, cnt))
+                return -EFAULT;
+        value = simple_strtol(str, NULL, 0);
+        if (value < 0)
+                return -ERANGE;
+        *p = value;
+        return cnt;
+}
+
+const struct file_operations ext4_ui_proc_fops = {
+        .owner          = THIS_MODULE,
+        .open           = ext4_ui_proc_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+        .write          = ext4_ui_proc_write,
+};
+#endif
+
+static struct file_system_type ext4_fs_type = {
+        .owner          = THIS_MODULE,
+        .name           = "ext4",
+        .get_sb         = ext4_get_sb,
+        .kill_sb        = kill_block_super,
+        .fs_flags       = FS_REQUIRES_DEV,
+};
+
+#ifdef CONFIG_EXT4DEV_COMPAT
+static int ext4dev_get_sb(struct file_system_type *fs_type,
+        int flags, const char *dev_name, void *data, struct vfsmount *mnt)
+{
+        printk(KERN_WARNING "EXT4-fs: Update your userspace programs "
+               "to mount using ext4\n");
+        printk(KERN_WARNING "EXT4-fs: ext4dev backwards compatibility "
+               "will go away by 2.6.31\n");
+        return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super, mnt);
+}
+
 static struct file_system_type ext4dev_fs_type = {
         .owner          = THIS_MODULE,
         .name           = "ext4dev",
-        .get_sb         = ext4_get_sb,
+        .get_sb         = ext4dev_get_sb,
         .kill_sb        = kill_block_super,
         .fs_flags       = FS_REQUIRES_DEV,
 };
+MODULE_ALIAS("ext4dev");
+#endif
 
 static int __init init_ext4_fs(void)
 {
         int err;
 
+        ext4_proc_root = proc_mkdir("fs/ext4", NULL);
         err = init_ext4_mballoc();
         if (err)
                 return err;
@@ -3515,9 +3583,16 @@ static int __init init_ext4_fs(void)
         err = init_inodecache();
         if (err)
                 goto out1;
-        err = register_filesystem(&ext4dev_fs_type);
+        err = register_filesystem(&ext4_fs_type);
         if (err)
                 goto out;
+#ifdef CONFIG_EXT4DEV_COMPAT
+        err = register_filesystem(&ext4dev_fs_type);
+        if (err) {
+                unregister_filesystem(&ext4_fs_type);
+                goto out;
+        }
+#endif
         return 0;
 out:
         destroy_inodecache();
@@ -3530,10 +3605,14 @@ out2:
 
 static void __exit exit_ext4_fs(void)
 {
+        unregister_filesystem(&ext4_fs_type);
+#ifdef CONFIG_EXT4DEV_COMPAT
         unregister_filesystem(&ext4dev_fs_type);
+#endif
         destroy_inodecache();
         exit_ext4_xattr();
         exit_ext4_mballoc();
+        remove_proc_entry("fs/ext4", NULL);
 }
 
 MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c
index e9178643dc01..00740cb32be3 100644
--- a/fs/ext4/symlink.c
+++ b/fs/ext4/symlink.c
@@ -23,10 +23,10 @@
 #include "ext4.h"
 #include "xattr.h"
 
-static void * ext4_follow_link(struct dentry *dentry, struct nameidata *nd)
+static void *ext4_follow_link(struct dentry *dentry, struct nameidata *nd)
 {
         struct ext4_inode_info *ei = EXT4_I(dentry->d_inode);
-        nd_set_link(nd, (char*)ei->i_data);
+        nd_set_link(nd, (char *) ei->i_data);
         return NULL;
 }
 
@@ -34,7 +34,7 @@ const struct inode_operations ext4_symlink_inode_operations = {
         .readlink       = generic_readlink,
         .follow_link    = page_follow_link_light,
         .put_link       = page_put_link,
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
         .setxattr       = generic_setxattr,
         .getxattr       = generic_getxattr,
         .listxattr      = ext4_listxattr,
@@ -45,7 +45,7 @@ const struct inode_operations ext4_symlink_inode_operations = {
 const struct inode_operations ext4_fast_symlink_inode_operations = {
         .readlink       = generic_readlink,
         .follow_link    = ext4_follow_link,
-#ifdef CONFIG_EXT4DEV_FS_XATTR
+#ifdef CONFIG_EXT4_FS_XATTR
         .setxattr       = generic_setxattr,
         .getxattr       = generic_getxattr,
         .listxattr      = ext4_listxattr,
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 8954208b4893..80626d516fee 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -99,12 +99,12 @@ static struct mb_cache *ext4_xattr_cache;
 
 static struct xattr_handler *ext4_xattr_handler_map[] = {
         [EXT4_XATTR_INDEX_USER]              = &ext4_xattr_user_handler,
-#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
         [EXT4_XATTR_INDEX_POSIX_ACL_ACCESS]  = &ext4_xattr_acl_access_handler,
         [EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT] = &ext4_xattr_acl_default_handler,
 #endif
         [EXT4_XATTR_INDEX_TRUSTED]           = &ext4_xattr_trusted_handler,
-#ifdef CONFIG_EXT4DEV_FS_SECURITY
+#ifdef CONFIG_EXT4_FS_SECURITY
         [EXT4_XATTR_INDEX_SECURITY]          = &ext4_xattr_security_handler,
 #endif
 };
@@ -112,11 +112,11 @@ static struct xattr_handler *ext4_xattr_handler_map[] = {
 struct xattr_handler *ext4_xattr_handlers[] = {
         &ext4_xattr_user_handler,
         &ext4_xattr_trusted_handler,
-#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
         &ext4_xattr_acl_access_handler,
         &ext4_xattr_acl_default_handler,
 #endif
-#ifdef CONFIG_EXT4DEV_FS_SECURITY
+#ifdef CONFIG_EXT4_FS_SECURITY
         &ext4_xattr_security_handler,
 #endif
         NULL
@@ -959,6 +959,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
         struct ext4_xattr_block_find bs = {
                 .s = { .not_found = -ENODATA, },
         };
+        unsigned long no_expand;
         int error;
 
         if (!name)
@@ -966,6 +967,9 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
         if (strlen(name) > 255)
                 return -ERANGE;
         down_write(&EXT4_I(inode)->xattr_sem);
+        no_expand = EXT4_I(inode)->i_state & EXT4_STATE_NO_EXPAND;
+        EXT4_I(inode)->i_state |= EXT4_STATE_NO_EXPAND;
+
         error = ext4_get_inode_loc(inode, &is.iloc);
         if (error)
                 goto cleanup;
@@ -1042,6 +1046,8 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 cleanup:
         brelse(is.iloc.bh);
         brelse(bs.bh);
+        if (no_expand == 0)
+                EXT4_I(inode)->i_state &= ~EXT4_STATE_NO_EXPAND;
         up_write(&EXT4_I(inode)->xattr_sem);
         return error;
 }
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index 5992fe979bb9..8ede88b18c29 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -51,8 +51,8 @@ struct ext4_xattr_entry {
         (((name_len) + EXT4_XATTR_ROUND + \
         sizeof(struct ext4_xattr_entry)) & ~EXT4_XATTR_ROUND)
 #define EXT4_XATTR_NEXT(entry) \
-        ( (struct ext4_xattr_entry *)( \
-          (char *)(entry) + EXT4_XATTR_LEN((entry)->e_name_len)) )
+        ((struct ext4_xattr_entry *)( \
+         (char *)(entry) + EXT4_XATTR_LEN((entry)->e_name_len)))
 #define EXT4_XATTR_SIZE(size) \
         (((size) + EXT4_XATTR_ROUND) & ~EXT4_XATTR_ROUND)
 
@@ -63,7 +63,7 @@ struct ext4_xattr_entry {
                 EXT4_I(inode)->i_extra_isize))
 #define IFIRST(hdr) ((struct ext4_xattr_entry *)((hdr)+1))
 
-# ifdef CONFIG_EXT4DEV_FS_XATTR
+# ifdef CONFIG_EXT4_FS_XATTR
 
 extern struct xattr_handler ext4_xattr_user_handler;
 extern struct xattr_handler ext4_xattr_trusted_handler;
@@ -88,7 +88,7 @@ extern void exit_ext4_xattr(void);
 
 extern struct xattr_handler *ext4_xattr_handlers[];
 
-# else  /* CONFIG_EXT4DEV_FS_XATTR */
+# else  /* CONFIG_EXT4_FS_XATTR */
 
 static inline int
 ext4_xattr_get(struct inode *inode, int name_index, const char *name,
@@ -141,9 +141,9 @@ ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
 
 #define ext4_xattr_handlers     NULL
 
-# endif  /* CONFIG_EXT4DEV_FS_XATTR */
+# endif  /* CONFIG_EXT4_FS_XATTR */
 
-#ifdef CONFIG_EXT4DEV_FS_SECURITY
+#ifdef CONFIG_EXT4_FS_SECURITY
 extern int ext4_init_security(handle_t *handle, struct inode *inode,
                                 struct inode *dir);
 #else
diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c
index 302e95c4af7e..fb98b3d847ed 100644
--- a/fs/fat/fatent.c
+++ b/fs/fat/fatent.c
@@ -6,6 +6,7 @@
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/msdos_fs.h>
+#include <linux/blkdev.h>
 
 struct fatent_operations {
         void (*ent_blocknr)(struct super_block *, int, int *, sector_t *);
@@ -535,6 +536,7 @@ int fat_free_clusters(struct inode *inode, int cluster)
         struct fat_entry fatent;
         struct buffer_head *bhs[MAX_BUF_PER_PAGE];
         int i, err, nr_bhs;
+        int first_cl = cluster;
 
         nr_bhs = 0;
         fatent_init(&fatent);
@@ -551,6 +553,18 @@ int fat_free_clusters(struct inode *inode, int cluster)
                         goto error;
                 }
 
+                /* 
+                 * Issue discard for the sectors we no longer care about,
+                 * batching contiguous clusters into one request
+                 */
+                if (cluster != fatent.entry + 1) {
+                        int nr_clus = fatent.entry - first_cl + 1;
+
+                        sb_issue_discard(sb, fat_clus_to_blknr(sbi, first_cl),
+                                         nr_clus * sbi->sec_per_clus);
+                        first_cl = cluster;
+                }
+
                 ops->ent_put(&fatent, FAT_ENT_FREE);
                 if (sbi->free_clusters != -1) {
                         sbi->free_clusters++;
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 80ff3381fa21..d12cdf2a0406 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -855,7 +855,7 @@ enum {
         Opt_obsolate, Opt_flush, Opt_tz_utc, Opt_err,
 };
 
-static match_table_t fat_tokens = {
+static const match_table_t fat_tokens = {
         {Opt_check_r, "check=relaxed"},
         {Opt_check_s, "check=strict"},
         {Opt_check_n, "check=normal"},
@@ -890,14 +890,14 @@ static match_table_t fat_tokens = {
         {Opt_tz_utc, "tz=UTC"},
         {Opt_err, NULL},
 };
-static match_table_t msdos_tokens = {
+static const match_table_t msdos_tokens = {
         {Opt_nodots, "nodots"},
         {Opt_nodots, "dotsOK=no"},
         {Opt_dots, "dots"},
         {Opt_dots, "dotsOK=yes"},
         {Opt_err, NULL}
 };
-static match_table_t vfat_tokens = {
+static const match_table_t vfat_tokens = {
         {Opt_charset, "iocharset=%s"},
         {Opt_shortname_lower, "shortname=lower"},
         {Opt_shortname_win95, "shortname=win95"},
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 25adfc3c693a..d0ff0b8cf309 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -8,7 +8,7 @@
  * pages against inodes.  ie: data writeback.  Writeout of the
  * inode itself is not handled here.
  *
- * 10Apr2002    akpm@zip.com.au
+ * 10Apr2002    Andrew Morton
  *              Split out of fs/inode.c
  *              Additions for address_space-based writeback
  */
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 2bada6bbc317..34930a964b82 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -101,6 +101,8 @@ void fuse_finish_open(struct inode *inode, struct file *file,
                 file->f_op = &fuse_direct_io_file_operations;
         if (!(outarg->open_flags & FOPEN_KEEP_CACHE))
                 invalidate_inode_pages2(inode->i_mapping);
+        if (outarg->open_flags & FOPEN_NONSEEKABLE)
+                nonseekable_open(inode, file);
         ff->fh = outarg->fh;
         file->private_data = fuse_file_get(ff);
 }
@@ -1448,6 +1450,9 @@ static loff_t fuse_file_llseek(struct file *file, loff_t offset, int origin)
         mutex_lock(&inode->i_mutex);
         switch (origin) {
         case SEEK_END:
+                retval = fuse_update_attributes(inode, NULL, file, NULL);
+                if (retval)
+                        return retval;
                 offset += i_size_read(inode);
                 break;
         case SEEK_CUR:
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 3a876076bdd1..35accfdd747f 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -6,6 +6,9 @@
   See the file COPYING.
 */
 
+#ifndef _FS_FUSE_I_H
+#define _FS_FUSE_I_H
+
 #include <linux/fuse.h>
 #include <linux/fs.h>
 #include <linux/mount.h>
@@ -655,3 +658,5 @@ void fuse_set_nowrite(struct inode *inode);
 void fuse_release_nowrite(struct inode *inode);
 
 u64 fuse_get_attr_version(struct fuse_conn *fc);
+
+#endif /* _FS_FUSE_I_H */
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index d2249f174e20..54b1f0e1ef58 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -354,7 +354,7 @@ enum {
         OPT_ERR
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         {OPT_FD,                        "fd=%u"},
         {OPT_ROOTMODE,                  "rootmode=%o"},
         {OPT_USER_ID,                   "user_id=%u"},
@@ -865,7 +865,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
         if (is_bdev) {
                 fc->destroy_req = fuse_request_alloc();
                 if (!fc->destroy_req)
-                        goto err_put_root;
+                        goto err_free_init_req;
         }
 
         mutex_lock(&fuse_mutex);
@@ -895,6 +895,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 
  err_unlock:
         mutex_unlock(&fuse_mutex);
+ err_free_init_req:
         fuse_request_free(init_req);
  err_put_root:
         dput(root_dentry);
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 13391e546616..c962283d4e7f 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1265,6 +1265,8 @@ static void blocking_cb(struct gfs2_sbd *sdp, struct lm_lockname *name,
         holdtime = gl->gl_tchange + gl->gl_ops->go_min_hold_time;
         if (time_before(now, holdtime))
                 delay = holdtime - now;
+        if (test_bit(GLF_REPLY_PENDING, &gl->gl_flags))
+                delay = gl->gl_ops->go_min_hold_time;
 
         spin_lock(&gl->gl_spin);
         handle_callback(gl, state, 1, delay);
@@ -1578,8 +1580,6 @@ static const char *hflags2str(char *buf, unsigned flags, unsigned long iflags)
                 *p++ = 'a';
         if (flags & GL_EXACT)
                 *p++ = 'E';
-        if (flags & GL_ATIME)
-                *p++ = 'a';
         if (flags & GL_NOCACHE)
                 *p++ = 'c';
         if (test_bit(HIF_HOLDER, &iflags))
@@ -1816,15 +1816,17 @@ restart:
         if (gl) {
                 gi->gl = hlist_entry(gl->gl_list.next,
                                      struct gfs2_glock, gl_list);
-                if (gi->gl)
-                        gfs2_glock_hold(gi->gl);
+        } else {
+                gi->gl = hlist_entry(gl_hash_table[gi->hash].hb_list.first,
+                                     struct gfs2_glock, gl_list);
         }
+        if (gi->gl)
+                gfs2_glock_hold(gi->gl);
         read_unlock(gl_lock_addr(gi->hash));
         if (gl)
                 gfs2_glock_put(gl);
-        if (gl && gi->gl == NULL)
-                gi->hash++;
         while (gi->gl == NULL) {
+                gi->hash++;
                 if (gi->hash >= GFS2_GL_HASH_SIZE)
                         return 1;
                 read_lock(gl_lock_addr(gi->hash));
@@ -1833,7 +1835,6 @@ restart:
                 if (gi->gl)
                         gfs2_glock_hold(gi->gl);
                 read_unlock(gl_lock_addr(gi->hash));
-                gi->hash++;
         }
 
         if (gi->sdp != gi->gl->gl_sbd)
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index 971d92af70fc..695c6b193611 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -24,7 +24,6 @@
 #define GL_ASYNC                0x00000040
 #define GL_EXACT                0x00000080
 #define GL_SKIP                 0x00000100
-#define GL_ATIME                0x00000200
 #define GL_NOCACHE              0x00000400
 
 #define GLR_TRYFAILED           13
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 448697a5c462..f566ec1b4e8e 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -386,20 +386,21 @@ struct gfs2_statfs_change_host {
 #define GFS2_DATA_ORDERED       2
 
 struct gfs2_args {
-        char ar_lockproto[GFS2_LOCKNAME_LEN]; /* Name of the Lock Protocol */
-        char ar_locktable[GFS2_LOCKNAME_LEN]; /* Name of the Lock Table */
-        char ar_hostdata[GFS2_LOCKNAME_LEN]; /* Host specific data */
-        int ar_spectator; /* Don't get a journal because we're always RO */
-        int ar_ignore_local_fs; /* Don't optimize even if local_fs is 1 */
-        int ar_localflocks; /* Let the VFS do flock|fcntl locks for us */
-        int ar_localcaching; /* Local-style caching (dangerous on multihost) */
-        int ar_debug; /* Oops on errors instead of trying to be graceful */
-        int ar_upgrade; /* Upgrade ondisk/multihost format */
-        unsigned int ar_num_glockd; /* Number of glockd threads */
-        int ar_posix_acl; /* Enable posix acls */
-        int ar_quota; /* off/account/on */
-        int ar_suiddir; /* suiddir support */
-        int ar_data; /* ordered/writeback */
+        char ar_lockproto[GFS2_LOCKNAME_LEN];   /* Name of the Lock Protocol */
+        char ar_locktable[GFS2_LOCKNAME_LEN];   /* Name of the Lock Table */
+        char ar_hostdata[GFS2_LOCKNAME_LEN];    /* Host specific data */
+        unsigned int ar_spectator:1;            /* Don't get a journal */
+        unsigned int ar_ignore_local_fs:1;      /* Ignore optimisations */
+        unsigned int ar_localflocks:1;          /* Let the VFS do flock|fcntl */
+        unsigned int ar_localcaching:1;         /* Local caching */
+        unsigned int ar_debug:1;                /* Oops on errors */
+        unsigned int ar_upgrade:1;              /* Upgrade ondisk format */
+        unsigned int ar_posix_acl:1;            /* Enable posix acls */
+        unsigned int ar_quota:2;                /* off/account/on */
+        unsigned int ar_suiddir:1;              /* suiddir support */
+        unsigned int ar_data:2;                 /* ordered/writeback */
+        unsigned int ar_meta:1;                 /* mount metafs */
+        unsigned int ar_num_glockd;             /* Number of glockd threads */
 };
 
 struct gfs2_tune {
@@ -419,7 +420,6 @@ struct gfs2_tune {
         unsigned int gt_quota_scale_den; /* Denominator */
         unsigned int gt_quota_cache_secs;
         unsigned int gt_quota_quantum; /* Secs between syncs to quota file */
-        unsigned int gt_atime_quantum; /* Min secs between atime updates */
         unsigned int gt_new_files_jdata;
         unsigned int gt_max_readahead; /* Max bytes to read-ahead from disk */
         unsigned int gt_stall_secs; /* Detects trouble! */
@@ -432,7 +432,7 @@ enum {
         SDF_JOURNAL_CHECKED     = 0,
         SDF_JOURNAL_LIVE        = 1,
         SDF_SHUTDOWN            = 2,
-        SDF_NOATIME             = 3,
+        SDF_NOBARRIERS          = 3,
 };
 
 #define GFS2_FSNAME_LEN         256
@@ -461,7 +461,6 @@ struct gfs2_sb_host {
 
 struct gfs2_sbd {
         struct super_block *sd_vfs;
-        struct super_block *sd_vfs_meta;
         struct kobject sd_kobj;
         unsigned long sd_flags; /* SDF_... */
         struct gfs2_sb_host sd_sb;
@@ -499,7 +498,9 @@ struct gfs2_sbd {
 
         /* Inode Stuff */
 
-        struct inode *sd_master_dir;
+        struct dentry *sd_master_dir;
+        struct dentry *sd_root_dir;
+
         struct inode *sd_jindex;
         struct inode *sd_inum_inode;
         struct inode *sd_statfs_inode;
@@ -634,7 +635,6 @@ struct gfs2_sbd {
         /* Debugging crud */
 
         unsigned long sd_last_warning;
-        struct vfsmount *sd_gfs2mnt;
         struct dentry *debugfs_dir;    /* debugfs directory */
         struct dentry *debugfs_dentry_glocks; /* for debugfs */
 };
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 8b0806a32948..7cee695fa441 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -18,6 +18,7 @@
 #include <linux/crc32.h>
 #include <linux/lm_interface.h>
 #include <linux/security.h>
+#include <linux/time.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -249,6 +250,7 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
 {
         struct gfs2_dinode_host *di = &ip->i_di;
         const struct gfs2_dinode *str = buf;
+        struct timespec atime;
         u16 height, depth;
 
         if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr)))
@@ -275,8 +277,10 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
         di->di_size = be64_to_cpu(str->di_size);
         i_size_write(&ip->i_inode, di->di_size);
         gfs2_set_inode_blocks(&ip->i_inode, be64_to_cpu(str->di_blocks));
-        ip->i_inode.i_atime.tv_sec = be64_to_cpu(str->di_atime);
-        ip->i_inode.i_atime.tv_nsec = be32_to_cpu(str->di_atime_nsec);
+        atime.tv_sec = be64_to_cpu(str->di_atime);
+        atime.tv_nsec = be32_to_cpu(str->di_atime_nsec);
+        if (timespec_compare(&ip->i_inode.i_atime, &atime) < 0)
+                ip->i_inode.i_atime = atime;
         ip->i_inode.i_mtime.tv_sec = be64_to_cpu(str->di_mtime);
         ip->i_inode.i_mtime.tv_nsec = be32_to_cpu(str->di_mtime_nsec);
         ip->i_inode.i_ctime.tv_sec = be64_to_cpu(str->di_ctime);
@@ -1033,13 +1037,11 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
 
         if (bh)
                 brelse(bh);
-        if (!inode)
-                return ERR_PTR(-ENOMEM);
         return inode;
 
 fail_gunlock2:
         gfs2_glock_dq_uninit(ghs + 1);
-        if (inode)
+        if (inode && !IS_ERR(inode))
                 iput(inode);
 fail_gunlock:
         gfs2_glock_dq(ghs);
@@ -1140,54 +1142,6 @@ int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
         return 0;
 }
 
-/*
- * gfs2_ok_to_move - check if it's ok to move a directory to another directory
- * @this: move this
- * @to: to here
- *
- * Follow @to back to the root and make sure we don't encounter @this
- * Assumes we already hold the rename lock.
- *
- * Returns: errno
- */
-
-int gfs2_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to)
-{
-        struct inode *dir = &to->i_inode;
-        struct super_block *sb = dir->i_sb;
-        struct inode *tmp;
-        struct qstr dotdot;
-        int error = 0;
-
-        gfs2_str2qstr(&dotdot, "..");
-
-        igrab(dir);
-
-        for (;;) {
-                if (dir == &this->i_inode) {
-                        error = -EINVAL;
-                        break;
-                }
-                if (dir == sb->s_root->d_inode) {
-                        error = 0;
-                        break;
-                }
-
-                tmp = gfs2_lookupi(dir, &dotdot, 1);
-                if (IS_ERR(tmp)) {
-                        error = PTR_ERR(tmp);
-                        break;
-                }
-
-                iput(dir);
-                dir = tmp;
-        }
-
-        iput(dir);
-
-        return error;
-}
-
 /**
  * gfs2_readlinki - return the contents of a symlink
  * @ip: the symlink's inode
@@ -1207,8 +1161,8 @@ int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len)
         unsigned int x;
         int error;
 
-        gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &i_gh);
-        error = gfs2_glock_nq_atime(&i_gh);
+        gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh);
+        error = gfs2_glock_nq(&i_gh);
         if (error) {
                 gfs2_holder_uninit(&i_gh);
                 return error;
@@ -1243,101 +1197,6 @@ out:
         return error;
 }
 
-/**
- * gfs2_glock_nq_atime - Acquire a hold on an inode's glock, and
- *       conditionally update the inode's atime
- * @gh: the holder to acquire
- *
- * Tests atime (access time) for gfs2_read, gfs2_readdir and gfs2_mmap
- * Update if the difference between the current time and the inode's current
- * atime is greater than an interval specified at mount.
- *
- * Returns: errno
- */
-
-int gfs2_glock_nq_atime(struct gfs2_holder *gh)
-{
-        struct gfs2_glock *gl = gh->gh_gl;
-        struct gfs2_sbd *sdp = gl->gl_sbd;
-        struct gfs2_inode *ip = gl->gl_object;
-        s64 quantum = gfs2_tune_get(sdp, gt_atime_quantum);
-        unsigned int state;
-        int flags;
-        int error;
-        struct timespec tv = CURRENT_TIME;
-
-        if (gfs2_assert_warn(sdp, gh->gh_flags & GL_ATIME) ||
-            gfs2_assert_warn(sdp, !(gh->gh_flags & GL_ASYNC)) ||
-            gfs2_assert_warn(sdp, gl->gl_ops == &gfs2_inode_glops))
-                return -EINVAL;
-
-        state = gh->gh_state;
-        flags = gh->gh_flags;
-
-        error = gfs2_glock_nq(gh);
-        if (error)
-                return error;
-
-        if (test_bit(SDF_NOATIME, &sdp->sd_flags) ||
-            (sdp->sd_vfs->s_flags & MS_RDONLY))
-                return 0;
-
-        if (tv.tv_sec - ip->i_inode.i_atime.tv_sec >= quantum) {
-                gfs2_glock_dq(gh);
-                gfs2_holder_reinit(LM_ST_EXCLUSIVE, gh->gh_flags & ~LM_FLAG_ANY,
-                                   gh);
-                error = gfs2_glock_nq(gh);
-                if (error)
-                        return error;
-
-                /* Verify that atime hasn't been updated while we were
-                   trying to get exclusive lock. */
-
-                tv = CURRENT_TIME;
-                if (tv.tv_sec - ip->i_inode.i_atime.tv_sec >= quantum) {
-                        struct buffer_head *dibh;
-                        struct gfs2_dinode *di;
-
-                        error = gfs2_trans_begin(sdp, RES_DINODE, 0);
-                        if (error == -EROFS)
-                                return 0;
-                        if (error)
-                                goto fail;
-
-                        error = gfs2_meta_inode_buffer(ip, &dibh);
-                        if (error)
-                                goto fail_end_trans;
-
-                        ip->i_inode.i_atime = tv;
-
-                        gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-                        di = (struct gfs2_dinode *)dibh->b_data;
-                        di->di_atime = cpu_to_be64(ip->i_inode.i_atime.tv_sec);
-                        di->di_atime_nsec = cpu_to_be32(ip->i_inode.i_atime.tv_nsec);
-                        brelse(dibh);
-
-                        gfs2_trans_end(sdp);
-                }
-
-                /* If someone else has asked for the glock,
-                   unlock and let them have it. Then reacquire
-                   in the original state. */
-                if (gfs2_glock_is_blocking(gl)) {
-                        gfs2_glock_dq(gh);
-                        gfs2_holder_reinit(state, flags, gh);
-                        return gfs2_glock_nq(gh);
-                }
-        }
-
-        return 0;
-
-fail_end_trans:
-        gfs2_trans_end(sdp);
-fail:
-        gfs2_glock_dq(gh);
-        return error;
-}
-
 static int
 __gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
 {
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index 58f9607d6a86..2d43f69610a0 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -91,9 +91,7 @@ int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name,
 int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
                    const struct gfs2_inode *ip);
 int gfs2_permission(struct inode *inode, int mask);
-int gfs2_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to);
 int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len);
-int gfs2_glock_nq_atime(struct gfs2_holder *gh);
 int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr);
 struct inode *gfs2_lookup_simple(struct inode *dip, const char *name);
 void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf);
diff --git a/fs/gfs2/locking/dlm/mount.c b/fs/gfs2/locking/dlm/mount.c
index 09d78c216f48..0c4cbe6c8285 100644
--- a/fs/gfs2/locking/dlm/mount.c
+++ b/fs/gfs2/locking/dlm/mount.c
@@ -144,7 +144,8 @@ static int gdlm_mount(char *table_name, char *host_data,
 
         error = dlm_new_lockspace(ls->fsname, strlen(ls->fsname),
                                   &ls->dlm_lockspace,
-                                  DLM_LSFL_FS | (nodir ? DLM_LSFL_NODIR : 0),
+                                  DLM_LSFL_FS | DLM_LSFL_NEWEXCL |
+                                  (nodir ? DLM_LSFL_NODIR : 0),
                                   GDLM_LVB_SIZE);
         if (error) {
                 log_error("dlm_new_lockspace error %d", error);
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 6c6af9f5e3ab..ad305854bdc6 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -18,6 +18,7 @@
 #include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/freezer.h>
+#include <linux/bio.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -584,7 +585,6 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
         memset(bh->b_data, 0, bh->b_size);
         set_buffer_uptodate(bh);
         clear_buffer_dirty(bh);
-        unlock_buffer(bh);
 
         gfs2_ail1_empty(sdp, 0);
         tail = current_tail(sdp);
@@ -601,8 +601,23 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
         hash = gfs2_disk_hash(bh->b_data, sizeof(struct gfs2_log_header));
         lh->lh_hash = cpu_to_be32(hash);
 
-        set_buffer_dirty(bh);
-        if (sync_dirty_buffer(bh))
+        bh->b_end_io = end_buffer_write_sync;
+        if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags))
+                goto skip_barrier;
+        get_bh(bh);
+        submit_bh(WRITE_BARRIER | (1 << BIO_RW_META), bh);
+        wait_on_buffer(bh);
+        if (buffer_eopnotsupp(bh)) {
+                clear_buffer_eopnotsupp(bh);
+                set_buffer_uptodate(bh);
+                set_bit(SDF_NOBARRIERS, &sdp->sd_flags);
+                lock_buffer(bh);
+skip_barrier:
+                get_bh(bh);
+                submit_bh(WRITE_SYNC | (1 << BIO_RW_META), bh);
+                wait_on_buffer(bh);
+        }
+        if (!buffer_uptodate(bh))
                 gfs2_io_error_bh(sdp, bh);
         brelse(bh);
 
diff --git a/fs/gfs2/mount.c b/fs/gfs2/mount.c
index b941f9f9f958..f96eb90a2cfa 100644
--- a/fs/gfs2/mount.c
+++ b/fs/gfs2/mount.c
@@ -42,10 +42,11 @@ enum {
         Opt_nosuiddir,
         Opt_data_writeback,
         Opt_data_ordered,
+        Opt_meta,
         Opt_err,
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         {Opt_lockproto, "lockproto=%s"},
         {Opt_locktable, "locktable=%s"},
         {Opt_hostdata, "hostdata=%s"},
@@ -66,6 +67,7 @@ static match_table_t tokens = {
         {Opt_nosuiddir, "nosuiddir"},
         {Opt_data_writeback, "data=writeback"},
         {Opt_data_ordered, "data=ordered"},
+        {Opt_meta, "meta"},
         {Opt_err, NULL}
 };
 
@@ -239,6 +241,11 @@ int gfs2_mount_args(struct gfs2_sbd *sdp, char *data_arg, int remount)
                 case Opt_data_ordered:
                         args->ar_data = GFS2_DATA_ORDERED;
                         break;
+                case Opt_meta:
+                        if (remount && args->ar_meta != 1)
+                                goto cant_remount;
+                        args->ar_meta = 1;
+                        break;
                 case Opt_err:
                 default:
                         fs_info(sdp, "unknown option: %s\n", o);
diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c
index e64a1b04117a..27563816e1c5 100644
--- a/fs/gfs2/ops_address.c
+++ b/fs/gfs2/ops_address.c
@@ -512,8 +512,8 @@ static int gfs2_readpage(struct file *file, struct page *page)
         int error;
 
         unlock_page(page);
-        gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &gh);
-        error = gfs2_glock_nq_atime(&gh);
+        gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+        error = gfs2_glock_nq(&gh);
         if (unlikely(error))
                 goto out;
         error = AOP_TRUNCATED_PAGE;
@@ -594,8 +594,8 @@ static int gfs2_readpages(struct file *file, struct address_space *mapping,
         struct gfs2_holder gh;
         int ret;
 
-        gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &gh);
-        ret = gfs2_glock_nq_atime(&gh);
+        gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+        ret = gfs2_glock_nq(&gh);
         if (unlikely(ret))
                 goto out_uninit;
         if (!gfs2_is_stuffed(ip))
@@ -636,8 +636,8 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping,
         unsigned to = from + len;
         struct page *page;
 
-        gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_ATIME, &ip->i_gh);
-        error = gfs2_glock_nq_atime(&ip->i_gh);
+        gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
+        error = gfs2_glock_nq(&ip->i_gh);
         if (unlikely(error))
                 goto out_uninit;
 
@@ -975,7 +975,7 @@ static int gfs2_ok_for_dio(struct gfs2_inode *ip, int rw, loff_t offset)
         if (gfs2_is_stuffed(ip))
                 return 0;
 
-        if (offset > i_size_read(&ip->i_inode))
+        if (offset >= i_size_read(&ip->i_inode))
                 return 0;
         return 1;
 }
@@ -1000,8 +1000,8 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
          * unfortunately have the option of only flushing a range like
          * the VFS does.
          */
-        gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, GL_ATIME, &gh);
-        rv = gfs2_glock_nq_atime(&gh);
+        gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, &gh);
+        rv = gfs2_glock_nq(&gh);
         if (rv)
                 return rv;
         rv = gfs2_ok_for_dio(ip, rw, offset);
diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/ops_file.c
index e9a366d4411c..3a747f8e2188 100644
--- a/fs/gfs2/ops_file.c
+++ b/fs/gfs2/ops_file.c
@@ -89,8 +89,8 @@ static int gfs2_readdir(struct file *file, void *dirent, filldir_t filldir)
         u64 offset = file->f_pos;
         int error;
 
-        gfs2_holder_init(dip->i_gl, LM_ST_SHARED, GL_ATIME, &d_gh);
-        error = gfs2_glock_nq_atime(&d_gh);
+        gfs2_holder_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
+        error = gfs2_glock_nq(&d_gh);
         if (error) {
                 gfs2_holder_uninit(&d_gh);
                 return error;
@@ -153,8 +153,8 @@ static int gfs2_get_flags(struct file *filp, u32 __user *ptr)
         int error;
         u32 fsflags;
 
-        gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &gh);
-        error = gfs2_glock_nq_atime(&gh);
+        gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+        error = gfs2_glock_nq(&gh);
         if (error)
                 return error;
 
@@ -351,8 +351,8 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct page *page)
         struct gfs2_alloc *al;
         int ret;
 
-        gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_ATIME, &gh);
-        ret = gfs2_glock_nq_atime(&gh);
+        gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+        ret = gfs2_glock_nq(&gh);
         if (ret)
                 goto out;
 
@@ -434,8 +434,8 @@ static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
         struct gfs2_holder i_gh;
         int error;
 
-        gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &i_gh);
-        error = gfs2_glock_nq_atime(&i_gh);
+        gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh);
+        error = gfs2_glock_nq(&i_gh);
         if (error) {
                 gfs2_holder_uninit(&i_gh);
                 return error;
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index b4d1d6490633..b117fcf2c4f5 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -40,6 +40,44 @@
 #define DO 0
 #define UNDO 1
 
+static const u32 gfs2_old_fs_formats[] = {
+        0
+};
+
+static const u32 gfs2_old_multihost_formats[] = {
+        0
+};
+
+/**
+ * gfs2_tune_init - Fill a gfs2_tune structure with default values
+ * @gt: tune
+ *
+ */
+
+static void gfs2_tune_init(struct gfs2_tune *gt)
+{
+        spin_lock_init(&gt->gt_spin);
+
+        gt->gt_demote_secs = 300;
+        gt->gt_incore_log_blocks = 1024;
+        gt->gt_log_flush_secs = 60;
+        gt->gt_recoverd_secs = 60;
+        gt->gt_logd_secs = 1;
+        gt->gt_quotad_secs = 5;
+        gt->gt_quota_simul_sync = 64;
+        gt->gt_quota_warn_period = 10;
+        gt->gt_quota_scale_num = 1;
+        gt->gt_quota_scale_den = 1;
+        gt->gt_quota_cache_secs = 300;
+        gt->gt_quota_quantum = 60;
+        gt->gt_new_files_jdata = 0;
+        gt->gt_max_readahead = 1 << 18;
+        gt->gt_stall_secs = 600;
+        gt->gt_complain_secs = 10;
+        gt->gt_statfs_quantum = 30;
+        gt->gt_statfs_slow = 0;
+}
+
 static struct gfs2_sbd *init_sbd(struct super_block *sb)
 {
         struct gfs2_sbd *sdp;
@@ -96,21 +134,271 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
         return sdp;
 }
 
-static void init_vfs(struct super_block *sb, unsigned noatime)
+
+/**
+ * gfs2_check_sb - Check superblock
+ * @sdp: the filesystem
+ * @sb: The superblock
+ * @silent: Don't print a message if the check fails
+ *
+ * Checks the version code of the FS is one that we understand how to
+ * read and that the sizes of the various on-disk structures have not
+ * changed.
+ */
+
+static int gfs2_check_sb(struct gfs2_sbd *sdp, struct gfs2_sb_host *sb, int silent)
 {
-        struct gfs2_sbd *sdp = sb->s_fs_info;
+        unsigned int x;
 
-        sb->s_magic = GFS2_MAGIC;
-        sb->s_op = &gfs2_super_ops;
-        sb->s_export_op = &gfs2_export_ops;
-        sb->s_time_gran = 1;
-        sb->s_maxbytes = MAX_LFS_FILESIZE;
+        if (sb->sb_magic != GFS2_MAGIC ||
+            sb->sb_type != GFS2_METATYPE_SB) {
+                if (!silent)
+                        printk(KERN_WARNING "GFS2: not a GFS2 filesystem\n");
+                return -EINVAL;
+        }
+
+        /*  If format numbers match exactly, we're done.  */
+
+        if (sb->sb_fs_format == GFS2_FORMAT_FS &&
+            sb->sb_multihost_format == GFS2_FORMAT_MULTI)
+                return 0;
+
+        if (sb->sb_fs_format != GFS2_FORMAT_FS) {
+                for (x = 0; gfs2_old_fs_formats[x]; x++)
+                        if (gfs2_old_fs_formats[x] == sb->sb_fs_format)
+                                break;
+
+                if (!gfs2_old_fs_formats[x]) {
+                        printk(KERN_WARNING
+                               "GFS2: code version (%u, %u) is incompatible "
+                               "with ondisk format (%u, %u)\n",
+                               GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
+                               sb->sb_fs_format, sb->sb_multihost_format);
+                        printk(KERN_WARNING
+                               "GFS2: I don't know how to upgrade this FS\n");
+                        return -EINVAL;
+                }
+        }
+
+        if (sb->sb_multihost_format != GFS2_FORMAT_MULTI) {
+                for (x = 0; gfs2_old_multihost_formats[x]; x++)
+                        if (gfs2_old_multihost_formats[x] ==
+                            sb->sb_multihost_format)
+                                break;
+
+                if (!gfs2_old_multihost_formats[x]) {
+                        printk(KERN_WARNING
+                               "GFS2: code version (%u, %u) is incompatible "
+                               "with ondisk format (%u, %u)\n",
+                               GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
+                               sb->sb_fs_format, sb->sb_multihost_format);
+                        printk(KERN_WARNING
+                               "GFS2: I don't know how to upgrade this FS\n");
+                        return -EINVAL;
+                }
+        }
+
+        if (!sdp->sd_args.ar_upgrade) {
+                printk(KERN_WARNING
+                       "GFS2: code version (%u, %u) is incompatible "
+                       "with ondisk format (%u, %u)\n",
+                       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
+                       sb->sb_fs_format, sb->sb_multihost_format);
+                printk(KERN_INFO
+                       "GFS2: Use the \"upgrade\" mount option to upgrade "
+                       "the FS\n");
+                printk(KERN_INFO "GFS2: See the manual for more details\n");
+                return -EINVAL;
+        }
+
+        return 0;
+}
+
+static void end_bio_io_page(struct bio *bio, int error)
+{
+        struct page *page = bio->bi_private;
 
-        if (sb->s_flags & (MS_NOATIME | MS_NODIRATIME))
-                set_bit(noatime, &sdp->sd_flags);
+        if (!error)
+                SetPageUptodate(page);
+        else
+                printk(KERN_WARNING "gfs2: error %d reading superblock\n", error);
+        unlock_page(page);
+}
+
+static void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf)
+{
+        const struct gfs2_sb *str = buf;
+
+        sb->sb_magic = be32_to_cpu(str->sb_header.mh_magic);
+        sb->sb_type = be32_to_cpu(str->sb_header.mh_type);
+        sb->sb_format = be32_to_cpu(str->sb_header.mh_format);
+        sb->sb_fs_format = be32_to_cpu(str->sb_fs_format);
+        sb->sb_multihost_format = be32_to_cpu(str->sb_multihost_format);
+        sb->sb_bsize = be32_to_cpu(str->sb_bsize);
+        sb->sb_bsize_shift = be32_to_cpu(str->sb_bsize_shift);
+        sb->sb_master_dir.no_addr = be64_to_cpu(str->sb_master_dir.no_addr);
+        sb->sb_master_dir.no_formal_ino = be64_to_cpu(str->sb_master_dir.no_formal_ino);
+        sb->sb_root_dir.no_addr = be64_to_cpu(str->sb_root_dir.no_addr);
+        sb->sb_root_dir.no_formal_ino = be64_to_cpu(str->sb_root_dir.no_formal_ino);
+
+        memcpy(sb->sb_lockproto, str->sb_lockproto, GFS2_LOCKNAME_LEN);
+        memcpy(sb->sb_locktable, str->sb_locktable, GFS2_LOCKNAME_LEN);
+}
+
+/**
+ * gfs2_read_super - Read the gfs2 super block from disk
+ * @sdp: The GFS2 super block
+ * @sector: The location of the super block
+ * @error: The error code to return
+ *
+ * This uses the bio functions to read the super block from disk
+ * because we want to be 100% sure that we never read cached data.
+ * A super block is read twice only during each GFS2 mount and is
+ * never written to by the filesystem. The first time its read no
+ * locks are held, and the only details which are looked at are those
+ * relating to the locking protocol. Once locking is up and working,
+ * the sb is read again under the lock to establish the location of
+ * the master directory (contains pointers to journals etc) and the
+ * root directory.
+ *
+ * Returns: 0 on success or error
+ */
+
+static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector)
+{
+        struct super_block *sb = sdp->sd_vfs;
+        struct gfs2_sb *p;
+        struct page *page;
+        struct bio *bio;
+
+        page = alloc_page(GFP_NOFS);
+        if (unlikely(!page))
+                return -ENOBUFS;
+
+        ClearPageUptodate(page);
+        ClearPageDirty(page);
+        lock_page(page);
+
+        bio = bio_alloc(GFP_NOFS, 1);
+        if (unlikely(!bio)) {
+                __free_page(page);
+                return -ENOBUFS;
+        }
 
-        /* Don't let the VFS update atimes.  GFS2 handles this itself. */
-        sb->s_flags |= MS_NOATIME | MS_NODIRATIME;
+        bio->bi_sector = sector * (sb->s_blocksize >> 9);
+        bio->bi_bdev = sb->s_bdev;
+        bio_add_page(bio, page, PAGE_SIZE, 0);
+
+        bio->bi_end_io = end_bio_io_page;
+        bio->bi_private = page;
+        submit_bio(READ_SYNC | (1 << BIO_RW_META), bio);
+        wait_on_page_locked(page);
+        bio_put(bio);
+        if (!PageUptodate(page)) {
+                __free_page(page);
+                return -EIO;
+        }
+        p = kmap(page);
+        gfs2_sb_in(&sdp->sd_sb, p);
+        kunmap(page);
+        __free_page(page);
+        return 0;
+}
+/**
+ * gfs2_read_sb - Read super block
+ * @sdp: The GFS2 superblock
+ * @gl: the glock for the superblock (assumed to be held)
+ * @silent: Don't print message if mount fails
+ *
+ */
+
+static int gfs2_read_sb(struct gfs2_sbd *sdp, struct gfs2_glock *gl, int silent)
+{
+        u32 hash_blocks, ind_blocks, leaf_blocks;
+        u32 tmp_blocks;
+        unsigned int x;
+        int error;
+
+        error = gfs2_read_super(sdp, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift);
+        if (error) {
+                if (!silent)
+                        fs_err(sdp, "can't read superblock\n");
+                return error;
+        }
+
+        error = gfs2_check_sb(sdp, &sdp->sd_sb, silent);
+        if (error)
+                return error;
+
+        sdp->sd_fsb2bb_shift = sdp->sd_sb.sb_bsize_shift -
+                               GFS2_BASIC_BLOCK_SHIFT;
+        sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift;
+        sdp->sd_diptrs = (sdp->sd_sb.sb_bsize -
+                          sizeof(struct gfs2_dinode)) / sizeof(u64);
+        sdp->sd_inptrs = (sdp->sd_sb.sb_bsize -
+                          sizeof(struct gfs2_meta_header)) / sizeof(u64);
+        sdp->sd_jbsize = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header);
+        sdp->sd_hash_bsize = sdp->sd_sb.sb_bsize / 2;
+        sdp->sd_hash_bsize_shift = sdp->sd_sb.sb_bsize_shift - 1;
+        sdp->sd_hash_ptrs = sdp->sd_hash_bsize / sizeof(u64);
+        sdp->sd_qc_per_block = (sdp->sd_sb.sb_bsize -
+                                sizeof(struct gfs2_meta_header)) /
+                                sizeof(struct gfs2_quota_change);
+
+        /* Compute maximum reservation required to add a entry to a directory */
+
+        hash_blocks = DIV_ROUND_UP(sizeof(u64) * (1 << GFS2_DIR_MAX_DEPTH),
+                             sdp->sd_jbsize);
+
+        ind_blocks = 0;
+        for (tmp_blocks = hash_blocks; tmp_blocks > sdp->sd_diptrs;) {
+                tmp_blocks = DIV_ROUND_UP(tmp_blocks, sdp->sd_inptrs);
+                ind_blocks += tmp_blocks;
+        }
+
+        leaf_blocks = 2 + GFS2_DIR_MAX_DEPTH;
+
+        sdp->sd_max_dirres = hash_blocks + ind_blocks + leaf_blocks;
+
+        sdp->sd_heightsize[0] = sdp->sd_sb.sb_bsize -
+                                sizeof(struct gfs2_dinode);
+        sdp->sd_heightsize[1] = sdp->sd_sb.sb_bsize * sdp->sd_diptrs;
+        for (x = 2;; x++) {
+                u64 space, d;
+                u32 m;
+
+                space = sdp->sd_heightsize[x - 1] * sdp->sd_inptrs;
+                d = space;
+                m = do_div(d, sdp->sd_inptrs);
+
+                if (d != sdp->sd_heightsize[x - 1] || m)
+                        break;
+                sdp->sd_heightsize[x] = space;
+        }
+        sdp->sd_max_height = x;
+        sdp->sd_heightsize[x] = ~0;
+        gfs2_assert(sdp, sdp->sd_max_height <= GFS2_MAX_META_HEIGHT);
+
+        sdp->sd_jheightsize[0] = sdp->sd_sb.sb_bsize -
+                                 sizeof(struct gfs2_dinode);
+        sdp->sd_jheightsize[1] = sdp->sd_jbsize * sdp->sd_diptrs;
+        for (x = 2;; x++) {
+                u64 space, d;
+                u32 m;
+
+                space = sdp->sd_jheightsize[x - 1] * sdp->sd_inptrs;
+                d = space;
+                m = do_div(d, sdp->sd_inptrs);
+
+                if (d != sdp->sd_jheightsize[x - 1] || m)
+                        break;
+                sdp->sd_jheightsize[x] = space;
+        }
+        sdp->sd_max_jheight = x;
+        sdp->sd_jheightsize[x] = ~0;
+        gfs2_assert(sdp, sdp->sd_max_jheight <= GFS2_MAX_META_HEIGHT);
+
+        return 0;
 }
 
 static int init_names(struct gfs2_sbd *sdp, int silent)
@@ -224,51 +512,59 @@ fail:
         return error;
 }
 
-static inline struct inode *gfs2_lookup_root(struct super_block *sb,
-                                             u64 no_addr)
+static int gfs2_lookup_root(struct super_block *sb, struct dentry **dptr,
+                            u64 no_addr, const char *name)
 {
-        return gfs2_inode_lookup(sb, DT_DIR, no_addr, 0, 0);
+        struct gfs2_sbd *sdp = sb->s_fs_info;
+        struct dentry *dentry;
+        struct inode *inode;
+
+        inode = gfs2_inode_lookup(sb, DT_DIR, no_addr, 0, 0);
+        if (IS_ERR(inode)) {
+                fs_err(sdp, "can't read in %s inode: %ld\n", name, PTR_ERR(inode));
+                return PTR_ERR(inode);
+        }
+        dentry = d_alloc_root(inode);
+        if (!dentry) {
+                fs_err(sdp, "can't alloc %s dentry\n", name);
+                iput(inode);
+                return -ENOMEM;
+        }
+        dentry->d_op = &gfs2_dops;
+        *dptr = dentry;
+        return 0;
 }
 
-static int init_sb(struct gfs2_sbd *sdp, int silent, int undo)
+static int init_sb(struct gfs2_sbd *sdp, int silent)
 {
         struct super_block *sb = sdp->sd_vfs;
         struct gfs2_holder sb_gh;
         u64 no_addr;
-        struct inode *inode;
-        int error = 0;
+        int ret;
 
-        if (undo) {
-                if (sb->s_root) {
-                        dput(sb->s_root);
-                        sb->s_root = NULL;
-                }
-                return 0;
+        ret = gfs2_glock_nq_num(sdp, GFS2_SB_LOCK, &gfs2_meta_glops,
+                                LM_ST_SHARED, 0, &sb_gh);
+        if (ret) {
+                fs_err(sdp, "can't acquire superblock glock: %d\n", ret);
+                return ret;
         }
 
-        error = gfs2_glock_nq_num(sdp, GFS2_SB_LOCK, &gfs2_meta_glops,
-                                 LM_ST_SHARED, 0, &sb_gh);
-        if (error) {
-                fs_err(sdp, "can't acquire superblock glock: %d\n", error);
-                return error;
-        }
-
-        error = gfs2_read_sb(sdp, sb_gh.gh_gl, silent);
-        if (error) {
-                fs_err(sdp, "can't read superblock: %d\n", error);
+        ret = gfs2_read_sb(sdp, sb_gh.gh_gl, silent);
+        if (ret) {
+                fs_err(sdp, "can't read superblock: %d\n", ret);
                 goto out;
         }
 
         /* Set up the buffer cache and SB for real */
         if (sdp->sd_sb.sb_bsize < bdev_hardsect_size(sb->s_bdev)) {
-                error = -EINVAL;
+                ret = -EINVAL;
                 fs_err(sdp, "FS block size (%u) is too small for device "
                        "block size (%u)\n",
                        sdp->sd_sb.sb_bsize, bdev_hardsect_size(sb->s_bdev));
                 goto out;
         }
         if (sdp->sd_sb.sb_bsize > PAGE_SIZE) {
-                error = -EINVAL;
+                ret = -EINVAL;
                 fs_err(sdp, "FS block size (%u) is too big for machine "
                        "page size (%u)\n",
                        sdp->sd_sb.sb_bsize, (unsigned int)PAGE_SIZE);
@@ -278,26 +574,21 @@ static int init_sb(struct gfs2_sbd *sdp, int silent, int undo)
 
         /* Get the root inode */
         no_addr = sdp->sd_sb.sb_root_dir.no_addr;
-        if (sb->s_type == &gfs2meta_fs_type)
-                no_addr = sdp->sd_sb.sb_master_dir.no_addr;
-        inode = gfs2_lookup_root(sb, no_addr);
-        if (IS_ERR(inode)) {
-                error = PTR_ERR(inode);
-                fs_err(sdp, "can't read in root inode: %d\n", error);
+        ret = gfs2_lookup_root(sb, &sdp->sd_root_dir, no_addr, "root");
+        if (ret)
                 goto out;
-        }
 
-        sb->s_root = d_alloc_root(inode);
-        if (!sb->s_root) {
-                fs_err(sdp, "can't get root dentry\n");
-                error = -ENOMEM;
-                iput(inode);
-        } else
-                sb->s_root->d_op = &gfs2_dops;
-        
+        /* Get the master inode */
+        no_addr = sdp->sd_sb.sb_master_dir.no_addr;
+        ret = gfs2_lookup_root(sb, &sdp->sd_master_dir, no_addr, "master");
+        if (ret) {
+                dput(sdp->sd_root_dir);
+                goto out;
+        }
+        sb->s_root = dget(sdp->sd_args.ar_meta ? sdp->sd_master_dir : sdp->sd_root_dir);
 out:
         gfs2_glock_dq_uninit(&sb_gh);
-        return error;
+        return ret;
 }
 
 /**
@@ -372,6 +663,7 @@ static void gfs2_lm_others_may_mount(struct gfs2_sbd *sdp)
 
 static int init_journal(struct gfs2_sbd *sdp, int undo)
 {
+        struct inode *master = sdp->sd_master_dir->d_inode;
         struct gfs2_holder ji_gh;
         struct task_struct *p;
         struct gfs2_inode *ip;
@@ -383,7 +675,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
                 goto fail_recoverd;
         }
 
-        sdp->sd_jindex = gfs2_lookup_simple(sdp->sd_master_dir, "jindex");
+        sdp->sd_jindex = gfs2_lookup_simple(master, "jindex");
         if (IS_ERR(sdp->sd_jindex)) {
                 fs_err(sdp, "can't lookup journal index: %d\n", error);
                 return PTR_ERR(sdp->sd_jindex);
@@ -506,25 +798,17 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo)
 {
         int error = 0;
         struct gfs2_inode *ip;
-        struct inode *inode;
+        struct inode *master = sdp->sd_master_dir->d_inode;
 
         if (undo)
                 goto fail_qinode;
 
-        inode = gfs2_lookup_root(sdp->sd_vfs, sdp->sd_sb.sb_master_dir.no_addr);
-        if (IS_ERR(inode)) {
-                error = PTR_ERR(inode);
-                fs_err(sdp, "can't read in master directory: %d\n", error);
-                goto fail;
-        }
-        sdp->sd_master_dir = inode;
-
         error = init_journal(sdp, undo);
         if (error)
-                goto fail_master;
+                goto fail;
 
         /* Read in the master inode number inode */
-        sdp->sd_inum_inode = gfs2_lookup_simple(sdp->sd_master_dir, "inum");
+        sdp->sd_inum_inode = gfs2_lookup_simple(master, "inum");
         if (IS_ERR(sdp->sd_inum_inode)) {
                 error = PTR_ERR(sdp->sd_inum_inode);
                 fs_err(sdp, "can't read in inum inode: %d\n", error);
@@ -533,7 +817,7 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo)
 
 
         /* Read in the master statfs inode */
-        sdp->sd_statfs_inode = gfs2_lookup_simple(sdp->sd_master_dir, "statfs");
+        sdp->sd_statfs_inode = gfs2_lookup_simple(master, "statfs");
         if (IS_ERR(sdp->sd_statfs_inode)) {
                 error = PTR_ERR(sdp->sd_statfs_inode);
                 fs_err(sdp, "can't read in statfs inode: %d\n", error);
@@ -541,7 +825,7 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo)
         }
 
         /* Read in the resource index inode */
-        sdp->sd_rindex = gfs2_lookup_simple(sdp->sd_master_dir, "rindex");
+        sdp->sd_rindex = gfs2_lookup_simple(master, "rindex");
         if (IS_ERR(sdp->sd_rindex)) {
                 error = PTR_ERR(sdp->sd_rindex);
                 fs_err(sdp, "can't get resource index inode: %d\n", error);
@@ -552,7 +836,7 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo)
         sdp->sd_rindex_uptodate = 0;
 
         /* Read in the quota inode */
-        sdp->sd_quota_inode = gfs2_lookup_simple(sdp->sd_master_dir, "quota");
+        sdp->sd_quota_inode = gfs2_lookup_simple(master, "quota");
         if (IS_ERR(sdp->sd_quota_inode)) {
                 error = PTR_ERR(sdp->sd_quota_inode);
                 fs_err(sdp, "can't get quota file inode: %d\n", error);
@@ -571,8 +855,6 @@ fail_inum:
         iput(sdp->sd_inum_inode);
 fail_journal:
         init_journal(sdp, UNDO);
-fail_master:
-        iput(sdp->sd_master_dir);
 fail:
         return error;
 }
@@ -583,6 +865,7 @@ static int init_per_node(struct gfs2_sbd *sdp, int undo)
         char buf[30];
         int error = 0;
         struct gfs2_inode *ip;
+        struct inode *master = sdp->sd_master_dir->d_inode;
 
         if (sdp->sd_args.ar_spectator)
                 return 0;
@@ -590,7 +873,7 @@ static int init_per_node(struct gfs2_sbd *sdp, int undo)
         if (undo)
                 goto fail_qc_gh;
 
-        pn = gfs2_lookup_simple(sdp->sd_master_dir, "per_node");
+        pn = gfs2_lookup_simple(master, "per_node");
         if (IS_ERR(pn)) {
                 error = PTR_ERR(pn);
                 fs_err(sdp, "can't find per_node directory: %d\n", error);
@@ -800,7 +1083,11 @@ static int fill_super(struct super_block *sb, void *data, int silent)
                 goto fail;
         }
 
-        init_vfs(sb, SDF_NOATIME);
+        sb->s_magic = GFS2_MAGIC;
+        sb->s_op = &gfs2_super_ops;
+        sb->s_export_op = &gfs2_export_ops;
+        sb->s_time_gran = 1;
+        sb->s_maxbytes = MAX_LFS_FILESIZE;
 
         /* Set up the buffer cache and fill in some fake block size values
            to allow us to read-in the on-disk superblock. */
@@ -828,7 +1115,7 @@ static int fill_super(struct super_block *sb, void *data, int silent)
         if (error)
                 goto fail_lm;
 
-        error = init_sb(sdp, silent, DO);
+        error = init_sb(sdp, silent);
         if (error)
                 goto fail_locking;
 
@@ -869,7 +1156,11 @@ fail_per_node:
 fail_inodes:
         init_inodes(sdp, UNDO);
 fail_sb:
-        init_sb(sdp, 0, UNDO);
+        if (sdp->sd_root_dir)
+                dput(sdp->sd_root_dir);
+        if (sdp->sd_master_dir)
+                dput(sdp->sd_master_dir);
+        sb->s_root = NULL;
 fail_locking:
         init_locking(sdp, &mount_gh, UNDO);
 fail_lm:
@@ -887,151 +1178,63 @@ fail:
 }
 
 static int gfs2_get_sb(struct file_system_type *fs_type, int flags,
-                const char *dev_name, void *data, struct vfsmount *mnt)
+                       const char *dev_name, void *data, struct vfsmount *mnt)
 {
-        struct super_block *sb;
-        struct gfs2_sbd *sdp;
-        int error = get_sb_bdev(fs_type, flags, dev_name, data, fill_super, mnt);
-        if (error)
-                goto out;
-        sb = mnt->mnt_sb;
-        sdp = sb->s_fs_info;
-        sdp->sd_gfs2mnt = mnt;
-out:
-        return error;
+        return get_sb_bdev(fs_type, flags, dev_name, data, fill_super, mnt);
 }
 
-static int fill_super_meta(struct super_block *sb, struct super_block *new,
-                           void *data, int silent)
+static struct super_block *get_gfs2_sb(const char *dev_name)
 {
-        struct gfs2_sbd *sdp = sb->s_fs_info;
-        struct inode *inode;
-        int error = 0;
-
-        new->s_fs_info = sdp;
-        sdp->sd_vfs_meta = sb;
-
-        init_vfs(new, SDF_NOATIME);
-
-        /* Get the master inode */
-        inode = igrab(sdp->sd_master_dir);
-
-        new->s_root = d_alloc_root(inode);
-        if (!new->s_root) {
-                fs_err(sdp, "can't get root dentry\n");
-                error = -ENOMEM;
-                iput(inode);
-        } else
-                new->s_root->d_op = &gfs2_dops;
-
-        return error;
-}
-
-static int set_bdev_super(struct super_block *s, void *data)
-{
-        s->s_bdev = data;
-        s->s_dev = s->s_bdev->bd_dev;
-        return 0;
-}
-
-static int test_bdev_super(struct super_block *s, void *data)
-{
-        return s->s_bdev == data;
-}
-
-static struct super_block* get_gfs2_sb(const char *dev_name)
-{
-        struct kstat stat;
+        struct super_block *sb;
         struct nameidata nd;
-        struct super_block *sb = NULL, *s;
         int error;
 
         error = path_lookup(dev_name, LOOKUP_FOLLOW, &nd);
         if (error) {
-                printk(KERN_WARNING "GFS2: path_lookup on %s returned error\n",
-                       dev_name);
-                goto out;
-        }
-        error = vfs_getattr(nd.path.mnt, nd.path.dentry, &stat);
-
-        list_for_each_entry(s, &gfs2_fs_type.fs_supers, s_instances) {
-                if ((S_ISBLK(stat.mode) && s->s_dev == stat.rdev) ||
-                    (S_ISDIR(stat.mode) &&
-                     s == nd.path.dentry->d_inode->i_sb)) {
-                        sb = s;
-                        goto free_nd;
-                }
+                printk(KERN_WARNING "GFS2: path_lookup on %s returned error %d\n",
+                       dev_name, error);
+                return NULL;
         }
-
-        printk(KERN_WARNING "GFS2: Unrecognized block device or "
-               "mount point %s\n", dev_name);
-
-free_nd:
+        sb = nd.path.dentry->d_inode->i_sb;
+        if (sb && (sb->s_type == &gfs2_fs_type))
+                atomic_inc(&sb->s_active);
+        else
+                sb = NULL;
         path_put(&nd.path);
-out:
         return sb;
 }
 
 static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags,
                             const char *dev_name, void *data, struct vfsmount *mnt)
 {
-        int error = 0;
-        struct super_block *sb = NULL, *new;
+        struct super_block *sb = NULL;
         struct gfs2_sbd *sdp;
 
         sb = get_gfs2_sb(dev_name);
         if (!sb) {
                 printk(KERN_WARNING "GFS2: gfs2 mount does not exist\n");
-                error = -ENOENT;
-                goto error;
+                return -ENOENT;
         }
         sdp = sb->s_fs_info;
-        if (sdp->sd_vfs_meta) {
-                printk(KERN_WARNING "GFS2: gfs2meta mount already exists\n");
-                error = -EBUSY;
-                goto error;
-        }
-        down(&sb->s_bdev->bd_mount_sem);
-        new = sget(fs_type, test_bdev_super, set_bdev_super, sb->s_bdev);
-        up(&sb->s_bdev->bd_mount_sem);
-        if (IS_ERR(new)) {
-                error = PTR_ERR(new);
-                goto error;
-        }
-        new->s_flags = flags;
-        strlcpy(new->s_id, sb->s_id, sizeof(new->s_id));
-        sb_set_blocksize(new, sb->s_blocksize);
-        error = fill_super_meta(sb, new, data, flags & MS_SILENT ? 1 : 0);
-        if (error) {
-                up_write(&new->s_umount);
-                deactivate_super(new);
-                goto error;
-        }
-
-        new->s_flags |= MS_ACTIVE;
-
-        /* Grab a reference to the gfs2 mount point */
-        atomic_inc(&sdp->sd_gfs2mnt->mnt_count);
-        return simple_set_mnt(mnt, new);
-error:
-        return error;
+        mnt->mnt_sb = sb;
+        mnt->mnt_root = dget(sdp->sd_master_dir);
+        return 0;
 }
 
 static void gfs2_kill_sb(struct super_block *sb)
 {
-        if (sb->s_fs_info) {
-                gfs2_delete_debugfs_file(sb->s_fs_info);
-                gfs2_meta_syncfs(sb->s_fs_info);
+        struct gfs2_sbd *sdp = sb->s_fs_info;
+        if (sdp) {
+                gfs2_meta_syncfs(sdp);
+                dput(sdp->sd_root_dir);
+                dput(sdp->sd_master_dir);
+                sdp->sd_root_dir = NULL;
+                sdp->sd_master_dir = NULL;
         }
+        shrink_dcache_sb(sb);
         kill_block_super(sb);
-}
-
-static void gfs2_kill_sb_meta(struct super_block *sb)
-{
-        struct gfs2_sbd *sdp = sb->s_fs_info;
-        generic_shutdown_super(sb);
-        sdp->sd_vfs_meta = NULL;
-        atomic_dec(&sdp->sd_gfs2mnt->mnt_count);
+        if (sdp)
+                gfs2_delete_debugfs_file(sdp);
 }
 
 struct file_system_type gfs2_fs_type = {
@@ -1046,7 +1249,6 @@ struct file_system_type gfs2meta_fs_type = {
         .name = "gfs2meta",
         .fs_flags = FS_REQUIRES_DEV,
         .get_sb = gfs2_get_sb_meta,
-        .kill_sb = gfs2_kill_sb_meta,
         .owner = THIS_MODULE,
 };
 
diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index e2c62f73a778..534e1e2c65ca 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -159,9 +159,13 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
         gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
         gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + 1);
 
-        error = gfs2_glock_nq_m(2, ghs);
+        error = gfs2_glock_nq(ghs); /* parent */
         if (error)
-                goto out;
+                goto out_parent;
+
+        error = gfs2_glock_nq(ghs + 1); /* child */
+        if (error)
+                goto out_child;
 
         error = gfs2_permission(dir, MAY_WRITE | MAY_EXEC);
         if (error)
@@ -245,8 +249,10 @@ out_alloc:
         if (alloc_required)
                 gfs2_alloc_put(dip);
 out_gunlock:
-        gfs2_glock_dq_m(2, ghs);
-out:
+        gfs2_glock_dq(ghs + 1);
+out_child:
+        gfs2_glock_dq(ghs);
+out_parent:
         gfs2_holder_uninit(ghs);
         gfs2_holder_uninit(ghs + 1);
         if (!error) {
@@ -302,7 +308,7 @@ static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
 
         error = gfs2_unlink_ok(dip, &dentry->d_name, ip);
         if (error)
-                goto out_rgrp;
+                goto out_gunlock;
 
         error = gfs2_trans_begin(sdp, 2*RES_DINODE + RES_LEAF + RES_RG_BIT, 0);
         if (error)
@@ -316,6 +322,7 @@ static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
 
 out_end_trans:
         gfs2_trans_end(sdp);
+out_gunlock:
         gfs2_glock_dq(ghs + 2);
 out_rgrp:
         gfs2_holder_uninit(ghs + 2);
@@ -485,7 +492,6 @@ static int gfs2_rmdir(struct inode *dir, struct dentry *dentry)
         struct gfs2_holder ri_gh;
         int error;
 
-
         error = gfs2_rindex_hold(sdp, &ri_gh);
         if (error)
                 return error;
@@ -495,9 +501,17 @@ static int gfs2_rmdir(struct inode *dir, struct dentry *dentry)
         rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
         gfs2_holder_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + 2);
 
-        error = gfs2_glock_nq_m(3, ghs);
+        error = gfs2_glock_nq(ghs); /* parent */
         if (error)
-                goto out;
+                goto out_parent;
+
+        error = gfs2_glock_nq(ghs + 1); /* child */
+        if (error)
+                goto out_child;
+
+        error = gfs2_glock_nq(ghs + 2); /* rgrp */
+        if (error)
+                goto out_rgrp;
 
         error = gfs2_unlink_ok(dip, &dentry->d_name, ip);
         if (error)
@@ -523,11 +537,15 @@ static int gfs2_rmdir(struct inode *dir, struct dentry *dentry)
         gfs2_trans_end(sdp);
 
 out_gunlock:
-        gfs2_glock_dq_m(3, ghs);
-out:
-        gfs2_holder_uninit(ghs);
-        gfs2_holder_uninit(ghs + 1);
+        gfs2_glock_dq(ghs + 2);
+out_rgrp:
         gfs2_holder_uninit(ghs + 2);
+        gfs2_glock_dq(ghs + 1);
+out_child:
+        gfs2_holder_uninit(ghs + 1);
+        gfs2_glock_dq(ghs);
+out_parent:
+        gfs2_holder_uninit(ghs);
         gfs2_glock_dq_uninit(&ri_gh);
         return error;
 }
@@ -571,6 +589,54 @@ static int gfs2_mknod(struct inode *dir, struct dentry *dentry, int mode,
         return 0;
 }
 
+/*
+ * gfs2_ok_to_move - check if it's ok to move a directory to another directory
+ * @this: move this
+ * @to: to here
+ *
+ * Follow @to back to the root and make sure we don't encounter @this
+ * Assumes we already hold the rename lock.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to)
+{
+        struct inode *dir = &to->i_inode;
+        struct super_block *sb = dir->i_sb;
+        struct inode *tmp;
+        struct qstr dotdot;
+        int error = 0;
+
+        gfs2_str2qstr(&dotdot, "..");
+
+        igrab(dir);
+
+        for (;;) {
+                if (dir == &this->i_inode) {
+                        error = -EINVAL;
+                        break;
+                }
+                if (dir == sb->s_root->d_inode) {
+                        error = 0;
+                        break;
+                }
+
+                tmp = gfs2_lookupi(dir, &dotdot, 1);
+                if (IS_ERR(tmp)) {
+                        error = PTR_ERR(tmp);
+                        break;
+                }
+
+                iput(dir);
+                dir = tmp;
+        }
+
+        iput(dir);
+
+        return error;
+}
+
 /**
  * gfs2_rename - Rename a file
  * @odir: Parent directory of old file name
@@ -589,7 +655,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
         struct gfs2_inode *ip = GFS2_I(odentry->d_inode);
         struct gfs2_inode *nip = NULL;
         struct gfs2_sbd *sdp = GFS2_SB(odir);
-        struct gfs2_holder ghs[5], r_gh;
+        struct gfs2_holder ghs[5], r_gh = { .gh_gl = NULL, };
         struct gfs2_rgrpd *nrgd;
         unsigned int num_gh;
         int dir_rename = 0;
@@ -603,19 +669,20 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
                         return 0;
         }
 
-        /* Make sure we aren't trying to move a dirctory into it's subdir */
-
-        if (S_ISDIR(ip->i_inode.i_mode) && odip != ndip) {
-                dir_rename = 1;
 
-                error = gfs2_glock_nq_init(sdp->sd_rename_gl, LM_ST_EXCLUSIVE, 0,
-                                           &r_gh);
+        if (odip != ndip) {
+                error = gfs2_glock_nq_init(sdp->sd_rename_gl, LM_ST_EXCLUSIVE,
+                                           0, &r_gh);
                 if (error)
                         goto out;
 
-                error = gfs2_ok_to_move(ip, ndip);
-                if (error)
-                        goto out_gunlock_r;
+                if (S_ISDIR(ip->i_inode.i_mode)) {
+                        dir_rename = 1;
+                        /* don't move a dirctory into it's subdir */
+                        error = gfs2_ok_to_move(ip, ndip);
+                        if (error)
+                                goto out_gunlock_r;
+                }
         }
 
         num_gh = 1;
@@ -639,9 +706,11 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
                         gfs2_holder_init(nrgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh++);
         }
 
-        error = gfs2_glock_nq_m(num_gh, ghs);
-        if (error)
-                goto out_uninit;
+        for (x = 0; x < num_gh; x++) {
+                error = gfs2_glock_nq(ghs + x);
+                if (error)
+                        goto out_gunlock;
+        }
 
         /* Check out the old directory */
 
@@ -804,12 +873,12 @@ out_alloc:
         if (alloc_required)
                 gfs2_alloc_put(ndip);
 out_gunlock:
-        gfs2_glock_dq_m(num_gh, ghs);
-out_uninit:
-        for (x = 0; x < num_gh; x++)
+        while (x--) {
+                gfs2_glock_dq(ghs + x);
                 gfs2_holder_uninit(ghs + x);
+        }
 out_gunlock_r:
-        if (dir_rename)
+        if (r_gh.gh_gl)
                 gfs2_glock_dq_uninit(&r_gh);
 out:
         return error;
diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c
index f66ea0f7a356..d5355d9b5926 100644
--- a/fs/gfs2/ops_super.c
+++ b/fs/gfs2/ops_super.c
@@ -20,6 +20,7 @@
 #include <linux/gfs2_ondisk.h>
 #include <linux/crc32.h>
 #include <linux/lm_interface.h>
+#include <linux/time.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -38,6 +39,7 @@
 #include "dir.h"
 #include "eattr.h"
 #include "bmap.h"
+#include "meta_io.h"
 
 /**
  * gfs2_write_inode - Make sure the inode is stable on the disk
@@ -50,16 +52,74 @@
 static int gfs2_write_inode(struct inode *inode, int sync)
 {
         struct gfs2_inode *ip = GFS2_I(inode);
-
-        /* Check this is a "normal" inode */
-        if (test_bit(GIF_USER, &ip->i_flags)) {
-                if (current->flags & PF_MEMALLOC)
-                        return 0;
-                if (sync)
-                        gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
+        struct gfs2_sbd *sdp = GFS2_SB(inode);
+        struct gfs2_holder gh;
+        struct buffer_head *bh;
+        struct timespec atime;
+        struct gfs2_dinode *di;
+        int ret = 0;
+
+        /* Check this is a "normal" inode, etc */
+        if (!test_bit(GIF_USER, &ip->i_flags) ||
+            (current->flags & PF_MEMALLOC))
+                return 0;
+        ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+        if (ret)
+                goto do_flush;
+        ret = gfs2_trans_begin(sdp, RES_DINODE, 0);
+        if (ret)
+                goto do_unlock;
+        ret = gfs2_meta_inode_buffer(ip, &bh);
+        if (ret == 0) {
+                di = (struct gfs2_dinode *)bh->b_data;
+                atime.tv_sec = be64_to_cpu(di->di_atime);
+                atime.tv_nsec = be32_to_cpu(di->di_atime_nsec);
+                if (timespec_compare(&inode->i_atime, &atime) > 0) {
+                        gfs2_trans_add_bh(ip->i_gl, bh, 1);
+                        gfs2_dinode_out(ip, bh->b_data);
+                }
+                brelse(bh);
         }
+        gfs2_trans_end(sdp);
+do_unlock:
+        gfs2_glock_dq_uninit(&gh);
+do_flush:
+        if (sync != 0)
+                gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
+        return ret;
+}
 
-        return 0;
+/**
+ * gfs2_make_fs_ro - Turn a Read-Write FS into a Read-Only one
+ * @sdp: the filesystem
+ *
+ * Returns: errno
+ */
+
+static int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
+{
+        struct gfs2_holder t_gh;
+        int error;
+
+        gfs2_quota_sync(sdp);
+        gfs2_statfs_sync(sdp);
+
+        error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, GL_NOCACHE,
+                                   &t_gh);
+        if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+                return error;
+
+        gfs2_meta_syncfs(sdp);
+        gfs2_log_shutdown(sdp);
+
+        clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
+
+        if (t_gh.gh_gl)
+                gfs2_glock_dq_uninit(&t_gh);
+
+        gfs2_quota_cleanup(sdp);
+
+        return error;
 }
 
 /**
@@ -73,12 +133,6 @@ static void gfs2_put_super(struct super_block *sb)
         struct gfs2_sbd *sdp = sb->s_fs_info;
         int error;
 
-        if (!sdp)
-                return;
-
-        if (!strncmp(sb->s_type->name, "gfs2meta", 8))
-                return; /* Nothing to do */
-
         /*  Unfreeze the filesystem, if we need to  */
 
         mutex_lock(&sdp->sd_freeze_lock);
@@ -101,7 +155,6 @@ static void gfs2_put_super(struct super_block *sb)
 
         /*  Release stuff  */
 
-        iput(sdp->sd_master_dir);
         iput(sdp->sd_jindex);
         iput(sdp->sd_inum_inode);
         iput(sdp->sd_statfs_inode);
@@ -152,6 +205,7 @@ static void gfs2_write_super(struct super_block *sb)
  *
  * Flushes the log to disk.
  */
+
 static int gfs2_sync_fs(struct super_block *sb, int wait)
 {
         sb->s_dirt = 0;
@@ -270,14 +324,6 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
                 }
         }
 
-        if (*flags & (MS_NOATIME | MS_NODIRATIME))
-                set_bit(SDF_NOATIME, &sdp->sd_flags);
-        else
-                clear_bit(SDF_NOATIME, &sdp->sd_flags);
-
-        /* Don't let the VFS update atimes.  GFS2 handles this itself. */
-        *flags |= MS_NOATIME | MS_NODIRATIME;
-
         return error;
 }
 
@@ -295,6 +341,7 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
  * inode's blocks, or alternatively pass the baton on to another
  * node for later deallocation.
  */
+
 static void gfs2_drop_inode(struct inode *inode)
 {
         struct gfs2_inode *ip = GFS2_I(inode);
@@ -333,6 +380,16 @@ static void gfs2_clear_inode(struct inode *inode)
         }
 }
 
+static int is_ancestor(const struct dentry *d1, const struct dentry *d2)
+{
+        do {
+                if (d1 == d2)
+                        return 1;
+                d1 = d1->d_parent;
+        } while (!IS_ROOT(d1));
+        return 0;
+}
+
 /**
  * gfs2_show_options - Show mount options for /proc/mounts
  * @s: seq_file structure
@@ -346,6 +403,8 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
         struct gfs2_sbd *sdp = mnt->mnt_sb->s_fs_info;
         struct gfs2_args *args = &sdp->sd_args;
 
+        if (is_ancestor(mnt->mnt_root, sdp->sd_master_dir))
+                seq_printf(s, ",meta");
         if (args->ar_lockproto[0])
                 seq_printf(s, ",lockproto=%s", args->ar_lockproto);
         if (args->ar_locktable[0])
@@ -414,6 +473,7 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
  * conversion on the iopen lock, but we can change that later. This
  * is safe, just less efficient.
  */
+
 static void gfs2_delete_inode(struct inode *inode)
 {
         struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
@@ -478,8 +538,6 @@ out:
         clear_inode(inode);
 }
 
-
-
 static struct inode *gfs2_alloc_inode(struct super_block *sb)
 {
         struct gfs2_inode *ip;
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index ca831991cbc2..c3ba3d9d0aac 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -33,313 +33,6 @@
 #include "trans.h"
 #include "util.h"
 
-static const u32 gfs2_old_fs_formats[] = {
-        0
-};
-
-static const u32 gfs2_old_multihost_formats[] = {
-        0
-};
-
-/**
- * gfs2_tune_init - Fill a gfs2_tune structure with default values
- * @gt: tune
- *
- */
-
-void gfs2_tune_init(struct gfs2_tune *gt)
-{
-        spin_lock_init(&gt->gt_spin);
-
-        gt->gt_demote_secs = 300;
-        gt->gt_incore_log_blocks = 1024;
-        gt->gt_log_flush_secs = 60;
-        gt->gt_recoverd_secs = 60;
-        gt->gt_logd_secs = 1;
-        gt->gt_quotad_secs = 5;
-        gt->gt_quota_simul_sync = 64;
-        gt->gt_quota_warn_period = 10;
-        gt->gt_quota_scale_num = 1;
-        gt->gt_quota_scale_den = 1;
-        gt->gt_quota_cache_secs = 300;
-        gt->gt_quota_quantum = 60;
-        gt->gt_atime_quantum = 3600;
-        gt->gt_new_files_jdata = 0;
-        gt->gt_max_readahead = 1 << 18;
-        gt->gt_stall_secs = 600;
-        gt->gt_complain_secs = 10;
-        gt->gt_statfs_quantum = 30;
-        gt->gt_statfs_slow = 0;
-}
-
-/**
- * gfs2_check_sb - Check superblock
- * @sdp: the filesystem
- * @sb: The superblock
- * @silent: Don't print a message if the check fails
- *
- * Checks the version code of the FS is one that we understand how to
- * read and that the sizes of the various on-disk structures have not
- * changed.
- */
-
-int gfs2_check_sb(struct gfs2_sbd *sdp, struct gfs2_sb_host *sb, int silent)
-{
-        unsigned int x;
-
-        if (sb->sb_magic != GFS2_MAGIC ||
-            sb->sb_type != GFS2_METATYPE_SB) {
-                if (!silent)
-                        printk(KERN_WARNING "GFS2: not a GFS2 filesystem\n");
-                return -EINVAL;
-        }
-
-        /*  If format numbers match exactly, we're done.  */
-
-        if (sb->sb_fs_format == GFS2_FORMAT_FS &&
-            sb->sb_multihost_format == GFS2_FORMAT_MULTI)
-                return 0;
-
-        if (sb->sb_fs_format != GFS2_FORMAT_FS) {
-                for (x = 0; gfs2_old_fs_formats[x]; x++)
-                        if (gfs2_old_fs_formats[x] == sb->sb_fs_format)
-                                break;
-
-                if (!gfs2_old_fs_formats[x]) {
-                        printk(KERN_WARNING
-                               "GFS2: code version (%u, %u) is incompatible "
-                               "with ondisk format (%u, %u)\n",
-                               GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
-                               sb->sb_fs_format, sb->sb_multihost_format);
-                        printk(KERN_WARNING
-                               "GFS2: I don't know how to upgrade this FS\n");
-                        return -EINVAL;
-                }
-        }
-
-        if (sb->sb_multihost_format != GFS2_FORMAT_MULTI) {
-                for (x = 0; gfs2_old_multihost_formats[x]; x++)
-                        if (gfs2_old_multihost_formats[x] ==
-                            sb->sb_multihost_format)
-                                break;
-
-                if (!gfs2_old_multihost_formats[x]) {
-                        printk(KERN_WARNING
-                               "GFS2: code version (%u, %u) is incompatible "
-                               "with ondisk format (%u, %u)\n",
-                               GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
-                               sb->sb_fs_format, sb->sb_multihost_format);
-                        printk(KERN_WARNING
-                               "GFS2: I don't know how to upgrade this FS\n");
-                        return -EINVAL;
-                }
-        }
-
-        if (!sdp->sd_args.ar_upgrade) {
-                printk(KERN_WARNING
-                       "GFS2: code version (%u, %u) is incompatible "
-                       "with ondisk format (%u, %u)\n",
-                       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
-                       sb->sb_fs_format, sb->sb_multihost_format);
-                printk(KERN_INFO
-                       "GFS2: Use the \"upgrade\" mount option to upgrade "
-                       "the FS\n");
-                printk(KERN_INFO "GFS2: See the manual for more details\n");
-                return -EINVAL;
-        }
-
-        return 0;
-}
-
-
-static void end_bio_io_page(struct bio *bio, int error)
-{
-        struct page *page = bio->bi_private;
-
-        if (!error)
-                SetPageUptodate(page);
-        else
-                printk(KERN_WARNING "gfs2: error %d reading superblock\n", error);
-        unlock_page(page);
-}
-
-static void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf)
-{
-        const struct gfs2_sb *str = buf;
-
-        sb->sb_magic = be32_to_cpu(str->sb_header.mh_magic);
-        sb->sb_type = be32_to_cpu(str->sb_header.mh_type);
-        sb->sb_format = be32_to_cpu(str->sb_header.mh_format);
-        sb->sb_fs_format = be32_to_cpu(str->sb_fs_format);
-        sb->sb_multihost_format = be32_to_cpu(str->sb_multihost_format);
-        sb->sb_bsize = be32_to_cpu(str->sb_bsize);
-        sb->sb_bsize_shift = be32_to_cpu(str->sb_bsize_shift);
-        sb->sb_master_dir.no_addr = be64_to_cpu(str->sb_master_dir.no_addr);
-        sb->sb_master_dir.no_formal_ino = be64_to_cpu(str->sb_master_dir.no_formal_ino);
-        sb->sb_root_dir.no_addr = be64_to_cpu(str->sb_root_dir.no_addr);
-        sb->sb_root_dir.no_formal_ino = be64_to_cpu(str->sb_root_dir.no_formal_ino);
-
-        memcpy(sb->sb_lockproto, str->sb_lockproto, GFS2_LOCKNAME_LEN);
-        memcpy(sb->sb_locktable, str->sb_locktable, GFS2_LOCKNAME_LEN);
-}
-
-/**
- * gfs2_read_super - Read the gfs2 super block from disk
- * @sdp: The GFS2 super block
- * @sector: The location of the super block
- * @error: The error code to return
- *
- * This uses the bio functions to read the super block from disk
- * because we want to be 100% sure that we never read cached data.
- * A super block is read twice only during each GFS2 mount and is
- * never written to by the filesystem. The first time its read no
- * locks are held, and the only details which are looked at are those
- * relating to the locking protocol. Once locking is up and working,
- * the sb is read again under the lock to establish the location of
- * the master directory (contains pointers to journals etc) and the
- * root directory.
- *
- * Returns: 0 on success or error
- */
-
-int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector)
-{
-        struct super_block *sb = sdp->sd_vfs;
-        struct gfs2_sb *p;
-        struct page *page;
-        struct bio *bio;
-
-        page = alloc_page(GFP_NOFS);
-        if (unlikely(!page))
-                return -ENOBUFS;
-
-        ClearPageUptodate(page);
-        ClearPageDirty(page);
-        lock_page(page);
-
-        bio = bio_alloc(GFP_NOFS, 1);
-        if (unlikely(!bio)) {
-                __free_page(page);
-                return -ENOBUFS;
-        }
-
-        bio->bi_sector = sector * (sb->s_blocksize >> 9);
-        bio->bi_bdev = sb->s_bdev;
-        bio_add_page(bio, page, PAGE_SIZE, 0);
-
-        bio->bi_end_io = end_bio_io_page;
-        bio->bi_private = page;
-        submit_bio(READ_SYNC | (1 << BIO_RW_META), bio);
-        wait_on_page_locked(page);
-        bio_put(bio);
-        if (!PageUptodate(page)) {
-                __free_page(page);
-                return -EIO;
-        }
-        p = kmap(page);
-        gfs2_sb_in(&sdp->sd_sb, p);
-        kunmap(page);
-        __free_page(page);
-        return 0;
-}
-
-/**
- * gfs2_read_sb - Read super block
- * @sdp: The GFS2 superblock
- * @gl: the glock for the superblock (assumed to be held)
- * @silent: Don't print message if mount fails
- *
- */
-
-int gfs2_read_sb(struct gfs2_sbd *sdp, struct gfs2_glock *gl, int silent)
-{
-        u32 hash_blocks, ind_blocks, leaf_blocks;
-        u32 tmp_blocks;
-        unsigned int x;
-        int error;
-
-        error = gfs2_read_super(sdp, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift);
-        if (error) {
-                if (!silent)
-                        fs_err(sdp, "can't read superblock\n");
-                return error;
-        }
-
-        error = gfs2_check_sb(sdp, &sdp->sd_sb, silent);
-        if (error)
-                return error;
-
-        sdp->sd_fsb2bb_shift = sdp->sd_sb.sb_bsize_shift -
-                               GFS2_BASIC_BLOCK_SHIFT;
-        sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift;
-        sdp->sd_diptrs = (sdp->sd_sb.sb_bsize -
-                          sizeof(struct gfs2_dinode)) / sizeof(u64);
-        sdp->sd_inptrs = (sdp->sd_sb.sb_bsize -
-                          sizeof(struct gfs2_meta_header)) / sizeof(u64);
-        sdp->sd_jbsize = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header);
-        sdp->sd_hash_bsize = sdp->sd_sb.sb_bsize / 2;
-        sdp->sd_hash_bsize_shift = sdp->sd_sb.sb_bsize_shift - 1;
-        sdp->sd_hash_ptrs = sdp->sd_hash_bsize / sizeof(u64);
-        sdp->sd_qc_per_block = (sdp->sd_sb.sb_bsize -
-                                sizeof(struct gfs2_meta_header)) /
-                                sizeof(struct gfs2_quota_change);
-
-        /* Compute maximum reservation required to add a entry to a directory */
-
-        hash_blocks = DIV_ROUND_UP(sizeof(u64) * (1 << GFS2_DIR_MAX_DEPTH),
-                             sdp->sd_jbsize);
-
-        ind_blocks = 0;
-        for (tmp_blocks = hash_blocks; tmp_blocks > sdp->sd_diptrs;) {
-                tmp_blocks = DIV_ROUND_UP(tmp_blocks, sdp->sd_inptrs);
-                ind_blocks += tmp_blocks;
-        }
-
-        leaf_blocks = 2 + GFS2_DIR_MAX_DEPTH;
-
-        sdp->sd_max_dirres = hash_blocks + ind_blocks + leaf_blocks;
-
-        sdp->sd_heightsize[0] = sdp->sd_sb.sb_bsize -
-                                sizeof(struct gfs2_dinode);
-        sdp->sd_heightsize[1] = sdp->sd_sb.sb_bsize * sdp->sd_diptrs;
-        for (x = 2;; x++) {
-                u64 space, d;
-                u32 m;
-
-                space = sdp->sd_heightsize[x - 1] * sdp->sd_inptrs;
-                d = space;
-                m = do_div(d, sdp->sd_inptrs);
-
-                if (d != sdp->sd_heightsize[x - 1] || m)
-                        break;
-                sdp->sd_heightsize[x] = space;
-        }
-        sdp->sd_max_height = x;
-        sdp->sd_heightsize[x] = ~0;
-        gfs2_assert(sdp, sdp->sd_max_height <= GFS2_MAX_META_HEIGHT);
-
-        sdp->sd_jheightsize[0] = sdp->sd_sb.sb_bsize -
-                                 sizeof(struct gfs2_dinode);
-        sdp->sd_jheightsize[1] = sdp->sd_jbsize * sdp->sd_diptrs;
-        for (x = 2;; x++) {
-                u64 space, d;
-                u32 m;
-
-                space = sdp->sd_jheightsize[x - 1] * sdp->sd_inptrs;
-                d = space;
-                m = do_div(d, sdp->sd_inptrs);
-
-                if (d != sdp->sd_jheightsize[x - 1] || m)
-                        break;
-                sdp->sd_jheightsize[x] = space;
-        }
-        sdp->sd_max_jheight = x;
-        sdp->sd_jheightsize[x] = ~0;
-        gfs2_assert(sdp, sdp->sd_max_jheight <= GFS2_MAX_META_HEIGHT);
-
-        return 0;
-}
-
 /**
  * gfs2_jindex_hold - Grab a lock on the jindex
  * @sdp: The GFS2 superblock
@@ -581,39 +274,6 @@ fail:
         return error;
 }
 
-/**
- * gfs2_make_fs_ro - Turn a Read-Write FS into a Read-Only one
- * @sdp: the filesystem
- *
- * Returns: errno
- */
-
-int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
-{
-        struct gfs2_holder t_gh;
-        int error;
-
-        gfs2_quota_sync(sdp);
-        gfs2_statfs_sync(sdp);
-
-        error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, GL_NOCACHE,
-                                   &t_gh);
-        if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
-                return error;
-
-        gfs2_meta_syncfs(sdp);
-        gfs2_log_shutdown(sdp);
-
-        clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
-
-        if (t_gh.gh_gl)
-                gfs2_glock_dq_uninit(&t_gh);
-
-        gfs2_quota_cleanup(sdp);
-
-        return error;
-}
-
 static void gfs2_statfs_change_in(struct gfs2_statfs_change_host *sc, const void *buf)
 {
         const struct gfs2_statfs_change *str = buf;
diff --git a/fs/gfs2/super.h b/fs/gfs2/super.h
index 44361ecc44f7..50a4c9b1215e 100644
--- a/fs/gfs2/super.h
+++ b/fs/gfs2/super.h
@@ -12,11 +12,6 @@
 
 #include "incore.h"
 
-void gfs2_tune_init(struct gfs2_tune *gt);
-
-int gfs2_check_sb(struct gfs2_sbd *sdp, struct gfs2_sb_host *sb, int silent);
-int gfs2_read_sb(struct gfs2_sbd *sdp, struct gfs2_glock *gl, int silent);
-int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector);
 void gfs2_lm_unmount(struct gfs2_sbd *sdp);
 
 static inline unsigned int gfs2_jindex_size(struct gfs2_sbd *sdp)
@@ -40,7 +35,6 @@ int gfs2_lookup_in_master_dir(struct gfs2_sbd *sdp, char *filename,
                               struct gfs2_inode **ipp);
 
 int gfs2_make_fs_rw(struct gfs2_sbd *sdp);
-int gfs2_make_fs_ro(struct gfs2_sbd *sdp);
 
 int gfs2_statfs_init(struct gfs2_sbd *sdp);
 void gfs2_statfs_change(struct gfs2_sbd *sdp,
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index 74846559fc3f..7e1879f1a02c 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -269,14 +269,6 @@ ARGS_ATTR(quota,           "%u\n");
 ARGS_ATTR(suiddir,         "%d\n");
 ARGS_ATTR(data,            "%d\n");
 
-/* one oddball doesn't fit the macro mold */
-static ssize_t noatime_show(struct gfs2_sbd *sdp, char *buf)
-{
-        return snprintf(buf, PAGE_SIZE, "%d\n",
-                        !!test_bit(SDF_NOATIME, &sdp->sd_flags));
-}
-static struct args_attr args_attr_noatime = __ATTR_RO(noatime);
-
 static struct attribute *args_attrs[] = {
         &args_attr_lockproto.attr,
         &args_attr_locktable.attr,
@@ -292,7 +284,6 @@ static struct attribute *args_attrs[] = {
         &args_attr_quota.attr,
         &args_attr_suiddir.attr,
         &args_attr_data.attr,
-        &args_attr_noatime.attr,
         NULL,
 };
 
@@ -407,7 +398,6 @@ TUNE_ATTR(incore_log_blocks, 0);
 TUNE_ATTR(log_flush_secs, 0);
 TUNE_ATTR(quota_warn_period, 0);
 TUNE_ATTR(quota_quantum, 0);
-TUNE_ATTR(atime_quantum, 0);
 TUNE_ATTR(max_readahead, 0);
 TUNE_ATTR(complain_secs, 0);
 TUNE_ATTR(statfs_slow, 0);
@@ -427,7 +417,6 @@ static struct attribute *tune_attrs[] = {
         &tune_attr_log_flush_secs.attr,
         &tune_attr_quota_warn_period.attr,
         &tune_attr_quota_quantum.attr,
-        &tune_attr_atime_quantum.attr,
         &tune_attr_max_readahead.attr,
         &tune_attr_complain_secs.attr,
         &tune_attr_statfs_slow.attr,
diff --git a/fs/hfs/catalog.c b/fs/hfs/catalog.c
index ba851576ebb1..6d98f116ca03 100644
--- a/fs/hfs/catalog.c
+++ b/fs/hfs/catalog.c
@@ -190,6 +190,10 @@ int hfs_cat_find_brec(struct super_block *sb, u32 cnid,
 
         fd->search_key->cat.ParID = rec.thread.ParID;
         len = fd->search_key->cat.CName.len = rec.thread.CName.len;
+        if (len > HFS_NAMELEN) {
+                printk(KERN_ERR "hfs: bad catalog namelength\n");
+                return -EIO;
+        }
         memcpy(fd->search_key->cat.CName.name, rec.thread.CName.name, len);
         return hfs_brec_find(fd);
 }
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index 4abb1047c689..3c7c7637719c 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -173,7 +173,7 @@ enum {
         opt_err
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         { opt_uid, "uid=%u" },
         { opt_gid, "gid=%u" },
         { opt_umask, "umask=%o" },
diff --git a/fs/hfsplus/bitmap.c b/fs/hfsplus/bitmap.c
index d128a25b74d2..ea30afc2a03c 100644
--- a/fs/hfsplus/bitmap.c
+++ b/fs/hfsplus/bitmap.c
@@ -32,6 +32,10 @@ int hfsplus_block_allocate(struct super_block *sb, u32 size, u32 offset, u32 *ma
         mutex_lock(&HFSPLUS_SB(sb).alloc_file->i_mutex);
         mapping = HFSPLUS_SB(sb).alloc_file->i_mapping;
         page = read_mapping_page(mapping, offset / PAGE_CACHE_BITS, NULL);
+        if (IS_ERR(page)) {
+                start = size;
+                goto out;
+        }
         pptr = kmap(page);
         curr = pptr + (offset & (PAGE_CACHE_BITS - 1)) / 32;
         i = offset % 32;
@@ -73,6 +77,10 @@ int hfsplus_block_allocate(struct super_block *sb, u32 size, u32 offset, u32 *ma
                         break;
                 page = read_mapping_page(mapping, offset / PAGE_CACHE_BITS,
                                          NULL);
+                if (IS_ERR(page)) {
+                        start = size;
+                        goto out;
+                }
                 curr = pptr = kmap(page);
                 if ((size ^ offset) / PAGE_CACHE_BITS)
                         end = pptr + PAGE_CACHE_BITS / 32;
@@ -120,6 +128,10 @@ found:
                 offset += PAGE_CACHE_BITS;
                 page = read_mapping_page(mapping, offset / PAGE_CACHE_BITS,
                                          NULL);
+                if (IS_ERR(page)) {
+                        start = size;
+                        goto out;
+                }
                 pptr = kmap(page);
                 curr = pptr;
                 end = pptr + PAGE_CACHE_BITS / 32;
diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c
index ba117c445e78..f6874acb2cf2 100644
--- a/fs/hfsplus/catalog.c
+++ b/fs/hfsplus/catalog.c
@@ -168,6 +168,11 @@ int hfsplus_find_cat(struct super_block *sb, u32 cnid,
                 return -EIO;
         }
 
+        if (be16_to_cpu(tmp.thread.nodeName.length) > 255) {
+                printk(KERN_ERR "hfs: catalog name length corrupted\n");
+                return -EIO;
+        }
+
         hfsplus_cat_build_key_uni(fd->search_key, be32_to_cpu(tmp.thread.parentID),
                                  &tmp.thread.nodeName);
         return hfs_brec_find(fd);
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index fec8f61227ff..0022eec63cda 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -199,6 +199,9 @@ int hfsplus_get_block(struct inode *inode, sector_t iblock,
                 goto done;
         }
 
+        if (inode->i_ino == HFSPLUS_EXT_CNID)
+                return -EIO;
+
         mutex_lock(&HFSPLUS_I(inode).extents_lock);
         res = hfsplus_ext_read_extent(inode, ablock);
         if (!res) {
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index b085d64a2b67..963be644297a 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -254,6 +254,8 @@ static int hfsplus_file_open(struct inode *inode, struct file *file)
 {
         if (HFSPLUS_IS_RSRC(inode))
                 inode = HFSPLUS_I(inode).rsrc_inode;
+        if (!(file->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS)
+                return -EOVERFLOW;
         atomic_inc(&HFSPLUS_I(inode).opencnt);
         return 0;
 }
diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c
index 9997cbf8beb5..9699c56d323f 100644
--- a/fs/hfsplus/options.c
+++ b/fs/hfsplus/options.c
@@ -25,7 +25,7 @@ enum {
         opt_force, opt_err
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         { opt_creator, "creator=%s" },
         { opt_type, "type=%s" },
         { opt_umask, "umask=%o" },
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index e834e578c93f..eb74531a0a8e 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -356,7 +356,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
         } 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)) {
+        } 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;
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index b8ae9c90ada0..29ad461d568f 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -215,7 +215,7 @@ enum {
         Opt_timeshift, Opt_err,
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         {Opt_help, "help"},
         {Opt_uid, "uid=%u"},
         {Opt_gid, "gid=%u"},
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 3f58923fb39b..61edc701b0e6 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -57,7 +57,7 @@ enum {
         Opt_err,
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         {Opt_size,      "size=%s"},
         {Opt_nr_inodes, "nr_inodes=%s"},
         {Opt_mode,      "mode=%o"},
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 7db32b3382d3..d152856c371b 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -13,9 +13,14 @@
 #include <linux/security.h>
 #include <linux/module.h>
 #include <linux/uaccess.h>
+#include <linux/writeback.h>
+#include <linux/buffer_head.h>
 
 #include <asm/ioctls.h>
 
+/* So that the fiemap access checks can't overflow on 32 bit machines. */
+#define FIEMAP_MAX_EXTENTS      (UINT_MAX / sizeof(struct fiemap_extent))
+
 /**
  * vfs_ioctl - call filesystem specific ioctl methods
  * @filp:       open file to invoke ioctl method on
@@ -71,6 +76,276 @@ static int ioctl_fibmap(struct file *filp, int __user *p)
         return put_user(res, p);
 }
 
+/**
+ * fiemap_fill_next_extent - Fiemap helper function
+ * @fieinfo:    Fiemap context passed into ->fiemap
+ * @logical:    Extent logical start offset, in bytes
+ * @phys:       Extent physical start offset, in bytes
+ * @len:        Extent length, in bytes
+ * @flags:      FIEMAP_EXTENT flags that describe this extent
+ *
+ * Called from file system ->fiemap callback. Will populate extent
+ * info as passed in via arguments and copy to user memory. On
+ * success, extent count on fieinfo is incremented.
+ *
+ * Returns 0 on success, -errno on error, 1 if this was the last
+ * extent that will fit in user array.
+ */
+#define SET_UNKNOWN_FLAGS       (FIEMAP_EXTENT_DELALLOC)
+#define SET_NO_UNMOUNTED_IO_FLAGS       (FIEMAP_EXTENT_DATA_ENCRYPTED)
+#define SET_NOT_ALIGNED_FLAGS   (FIEMAP_EXTENT_DATA_TAIL|FIEMAP_EXTENT_DATA_INLINE)
+int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical,
+                            u64 phys, u64 len, u32 flags)
+{
+        struct fiemap_extent extent;
+        struct fiemap_extent *dest = fieinfo->fi_extents_start;
+
+        /* only count the extents */
+        if (fieinfo->fi_extents_max == 0) {
+                fieinfo->fi_extents_mapped++;
+                return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
+        }
+
+        if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max)
+                return 1;
+
+        if (flags & SET_UNKNOWN_FLAGS)
+                flags |= FIEMAP_EXTENT_UNKNOWN;
+        if (flags & SET_NO_UNMOUNTED_IO_FLAGS)
+                flags |= FIEMAP_EXTENT_ENCODED;
+        if (flags & SET_NOT_ALIGNED_FLAGS)
+                flags |= FIEMAP_EXTENT_NOT_ALIGNED;
+
+        memset(&extent, 0, sizeof(extent));
+        extent.fe_logical = logical;
+        extent.fe_physical = phys;
+        extent.fe_length = len;
+        extent.fe_flags = flags;
+
+        dest += fieinfo->fi_extents_mapped;
+        if (copy_to_user(dest, &extent, sizeof(extent)))
+                return -EFAULT;
+
+        fieinfo->fi_extents_mapped++;
+        if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max)
+                return 1;
+        return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
+}
+EXPORT_SYMBOL(fiemap_fill_next_extent);
+
+/**
+ * fiemap_check_flags - check validity of requested flags for fiemap
+ * @fieinfo:    Fiemap context passed into ->fiemap
+ * @fs_flags:   Set of fiemap flags that the file system understands
+ *
+ * Called from file system ->fiemap callback. This will compute the
+ * intersection of valid fiemap flags and those that the fs supports. That
+ * value is then compared against the user supplied flags. In case of bad user
+ * flags, the invalid values will be written into the fieinfo structure, and
+ * -EBADR is returned, which tells ioctl_fiemap() to return those values to
+ * userspace. For this reason, a return code of -EBADR should be preserved.
+ *
+ * Returns 0 on success, -EBADR on bad flags.
+ */
+int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags)
+{
+        u32 incompat_flags;
+
+        incompat_flags = fieinfo->fi_flags & ~(FIEMAP_FLAGS_COMPAT & fs_flags);
+        if (incompat_flags) {
+                fieinfo->fi_flags = incompat_flags;
+                return -EBADR;
+        }
+        return 0;
+}
+EXPORT_SYMBOL(fiemap_check_flags);
+
+static int fiemap_check_ranges(struct super_block *sb,
+                               u64 start, u64 len, u64 *new_len)
+{
+        *new_len = len;
+
+        if (len == 0)
+                return -EINVAL;
+
+        if (start > sb->s_maxbytes)
+                return -EFBIG;
+
+        /*
+         * Shrink request scope to what the fs can actually handle.
+         */
+        if ((len > sb->s_maxbytes) ||
+            (sb->s_maxbytes - len) < start)
+                *new_len = sb->s_maxbytes - start;
+
+        return 0;
+}
+
+static int ioctl_fiemap(struct file *filp, unsigned long arg)
+{
+        struct fiemap fiemap;
+        struct fiemap_extent_info fieinfo = { 0, };
+        struct inode *inode = filp->f_path.dentry->d_inode;
+        struct super_block *sb = inode->i_sb;
+        u64 len;
+        int error;
+
+        if (!inode->i_op->fiemap)
+                return -EOPNOTSUPP;
+
+        if (copy_from_user(&fiemap, (struct fiemap __user *)arg,
+                           sizeof(struct fiemap)))
+                return -EFAULT;
+
+        if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS)
+                return -EINVAL;
+
+        error = fiemap_check_ranges(sb, fiemap.fm_start, fiemap.fm_length,
+                                    &len);
+        if (error)
+                return error;
+
+        fieinfo.fi_flags = fiemap.fm_flags;
+        fieinfo.fi_extents_max = fiemap.fm_extent_count;
+        fieinfo.fi_extents_start = (struct fiemap_extent *)(arg + sizeof(fiemap));
+
+        if (fiemap.fm_extent_count != 0 &&
+            !access_ok(VERIFY_WRITE, fieinfo.fi_extents_start,
+                       fieinfo.fi_extents_max * sizeof(struct fiemap_extent)))
+                return -EFAULT;
+
+        if (fieinfo.fi_flags & FIEMAP_FLAG_SYNC)
+                filemap_write_and_wait(inode->i_mapping);
+
+        error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, len);
+        fiemap.fm_flags = fieinfo.fi_flags;
+        fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped;
+        if (copy_to_user((char *)arg, &fiemap, sizeof(fiemap)))
+                error = -EFAULT;
+
+        return error;
+}
+
+#ifdef CONFIG_BLOCK
+
+#define blk_to_logical(inode, blk) (blk << (inode)->i_blkbits)
+#define logical_to_blk(inode, offset) (offset >> (inode)->i_blkbits);
+
+/*
+ * @inode - the inode to map
+ * @arg - the pointer to userspace where we copy everything to
+ * @get_block - the fs's get_block function
+ *
+ * This does FIEMAP for block based inodes.  Basically it will just loop
+ * through get_block until we hit the number of extents we want to map, or we
+ * go past the end of the file and hit a hole.
+ *
+ * If it is possible to have data blocks beyond a hole past @inode->i_size, then
+ * please do not use this function, it will stop at the first unmapped block
+ * beyond i_size
+ */
+int generic_block_fiemap(struct inode *inode,
+                         struct fiemap_extent_info *fieinfo, u64 start,
+                         u64 len, get_block_t *get_block)
+{
+        struct buffer_head tmp;
+        unsigned int start_blk;
+        long long length = 0, map_len = 0;
+        u64 logical = 0, phys = 0, size = 0;
+        u32 flags = FIEMAP_EXTENT_MERGED;
+        int ret = 0;
+
+        if ((ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC)))
+                return ret;
+
+        start_blk = logical_to_blk(inode, start);
+
+        /* guard against change */
+        mutex_lock(&inode->i_mutex);
+
+        length = (long long)min_t(u64, len, i_size_read(inode));
+        map_len = length;
+
+        do {
+                /*
+                 * we set b_size to the total size we want so it will map as
+                 * many contiguous blocks as possible at once
+                 */
+                memset(&tmp, 0, sizeof(struct buffer_head));
+                tmp.b_size = map_len;
+
+                ret = get_block(inode, start_blk, &tmp, 0);
+                if (ret)
+                        break;
+
+                /* HOLE */
+                if (!buffer_mapped(&tmp)) {
+                        /*
+                         * first hole after going past the EOF, this is our
+                         * last extent
+                         */
+                        if (length <= 0) {
+                                flags = FIEMAP_EXTENT_MERGED|FIEMAP_EXTENT_LAST;
+                                ret = fiemap_fill_next_extent(fieinfo, logical,
+                                                              phys, size,
+                                                              flags);
+                                break;
+                        }
+
+                        length -= blk_to_logical(inode, 1);
+
+                        /* if we have holes up to/past EOF then we're done */
+                        if (length <= 0)
+                                break;
+
+                        start_blk++;
+                } else {
+                        if (length <= 0 && size) {
+                                ret = fiemap_fill_next_extent(fieinfo, logical,
+                                                              phys, size,
+                                                              flags);
+                                if (ret)
+                                        break;
+                        }
+
+                        logical = blk_to_logical(inode, start_blk);
+                        phys = blk_to_logical(inode, tmp.b_blocknr);
+                        size = tmp.b_size;
+                        flags = FIEMAP_EXTENT_MERGED;
+
+                        length -= tmp.b_size;
+                        start_blk += logical_to_blk(inode, size);
+
+                        /*
+                         * if we are past the EOF we need to loop again to see
+                         * if there is a hole so we can mark this extent as the
+                         * last one, and if not keep mapping things until we
+                         * find a hole, or we run out of slots in the extent
+                         * array
+                         */
+                        if (length <= 0)
+                                continue;
+
+                        ret = fiemap_fill_next_extent(fieinfo, logical, phys,
+                                                      size, flags);
+                        if (ret)
+                                break;
+                }
+                cond_resched();
+        } while (1);
+
+        mutex_unlock(&inode->i_mutex);
+
+        /* if ret is 1 then we just hit the end of the extent array */
+        if (ret == 1)
+                ret = 0;
+
+        return ret;
+}
+EXPORT_SYMBOL(generic_block_fiemap);
+
+#endif  /*  CONFIG_BLOCK  */
+
 static int file_ioctl(struct file *filp, unsigned int cmd,
                 unsigned long arg)
 {
@@ -80,6 +355,8 @@ static int file_ioctl(struct file *filp, unsigned int cmd,
         switch (cmd) {
         case FIBMAP:
                 return ioctl_fibmap(filp, p);
+        case FS_IOC_FIEMAP:
+                return ioctl_fiemap(filp, arg);
         case FIGETBSZ:
                 return put_user(inode->i_sb->s_blocksize, p);
         case FIONREAD:
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 26948a6033b6..3f8af0f1505b 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -310,7 +310,7 @@ enum {
         Opt_nocompress, Opt_hide, Opt_showassoc, Opt_dmode,
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         {Opt_norock, "norock"},
         {Opt_nojoliet, "nojoliet"},
         {Opt_unhide, "unhide"},
diff --git a/fs/jbd/Kconfig b/fs/jbd/Kconfig
new file mode 100644
index 000000000000..4e28beeed157
--- /dev/null
+++ b/fs/jbd/Kconfig
@@ -0,0 +1,30 @@
+config JBD
+        tristate
+        help
+          This is a generic journalling layer for block devices.  It is
+          currently used by the ext3 file system, but it could also be
+          used to add journal support to other file systems or block
+          devices such as RAID or LVM.
+
+          If you are using the ext3 file system, you need to say Y here.
+          If you are not using ext3 then you will probably want to say N.
+
+          To compile this device as a module, choose M here: the module will be
+          called jbd.  If you are compiling ext3 into the kernel, you
+          cannot compile this code as a module.
+
+config JBD_DEBUG
+        bool "JBD (ext3) debugging support"
+        depends on JBD && DEBUG_FS
+        help
+          If you are using the ext3 journaled file system (or potentially any
+          other file system/device using JBD), this option allows you to
+          enable debugging output while the system is running, in order to
+          help track down any problems you are having.  By default the
+          debugging output will be turned off.
+
+          If you select Y here, then you will be able to turn on debugging
+          with "echo N > /sys/kernel/debug/jbd/jbd-debug", where N is a
+          number between 1 and 5, the higher the number, the more debugging
+          output is generated.  To turn debugging off again, do
+          "echo 0 > /sys/kernel/debug/jbd/jbd-debug".
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index ae08c057e751..25719d902c51 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -482,6 +482,8 @@ void journal_commit_transaction(journal_t *journal)
                 printk(KERN_WARNING
                         "JBD: Detected IO errors while flushing file data "
                         "on %s\n", bdevname(journal->j_fs_dev, b));
+                if (journal->j_flags & JFS_ABORT_ON_SYNCDATA_ERR)
+                        journal_abort(journal, err);
                 err = 0;
         }
 
@@ -518,9 +520,10 @@ void journal_commit_transaction(journal_t *journal)
                 jh = commit_transaction->t_buffers;
 
                 /* If we're in abort mode, we just un-journal the buffer and
-                   release it for background writing. */
+                   release it. */
 
                 if (is_journal_aborted(journal)) {
+                        clear_buffer_jbddirty(jh2bh(jh));
                         JBUFFER_TRACE(jh, "journal is aborting: refile");
                         journal_refile_buffer(journal, jh);
                         /* If that was the last one, we need to clean up
@@ -762,6 +765,9 @@ wait_for_iobuf:
                 /* AKPM: bforget here */
         }
 
+        if (err)
+                journal_abort(journal, err);
+
         jbd_debug(3, "JBD: commit phase 6\n");
 
         if (journal_write_commit_record(journal, commit_transaction))
@@ -852,6 +858,8 @@ restart_loop:
                 if (buffer_jbddirty(bh)) {
                         JBUFFER_TRACE(jh, "add to new checkpointing trans");
                         __journal_insert_checkpoint(jh, commit_transaction);
+                        if (is_journal_aborted(journal))
+                                clear_buffer_jbddirty(bh);
                         JBUFFER_TRACE(jh, "refile for checkpoint writeback");
                         __journal_refile_buffer(jh);
                         jbd_unlock_bh_state(bh);
diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c
index 0540ca27a446..d15cd6e7251e 100644
--- a/fs/jbd/transaction.c
+++ b/fs/jbd/transaction.c
@@ -954,9 +954,10 @@ int journal_dirty_data(handle_t *handle, struct buffer_head *bh)
         journal_t *journal = handle->h_transaction->t_journal;
         int need_brelse = 0;
         struct journal_head *jh;
+        int ret = 0;
 
         if (is_handle_aborted(handle))
-                return 0;
+                return ret;
 
         jh = journal_add_journal_head(bh);
         JBUFFER_TRACE(jh, "entry");
@@ -1067,7 +1068,16 @@ int journal_dirty_data(handle_t *handle, struct buffer_head *bh)
                                    time if it is redirtied */
                         }
 
-                        /* journal_clean_data_list() may have got there first */
+                        /*
+                         * We cannot remove the buffer with io error from the
+                         * committing transaction, because otherwise it would
+                         * miss the error and the commit would not abort.
+                         */
+                        if (unlikely(!buffer_uptodate(bh))) {
+                                ret = -EIO;
+                                goto no_journal;
+                        }
+
                         if (jh->b_transaction != NULL) {
                                 JBUFFER_TRACE(jh, "unfile from commit");
                                 __journal_temp_unlink_buffer(jh);
@@ -1108,7 +1118,7 @@ no_journal:
         }
         JBUFFER_TRACE(jh, "exit");
         journal_put_journal_head(jh);
-        return 0;
+        return ret;
 }
 
 /**
diff --git a/fs/jbd2/Kconfig b/fs/jbd2/Kconfig
new file mode 100644
index 000000000000..f32f346f4b0a
--- /dev/null
+++ b/fs/jbd2/Kconfig
@@ -0,0 +1,33 @@
+config JBD2
+        tristate
+        select CRC32
+        help
+          This is a generic journaling layer for block devices that support
+          both 32-bit and 64-bit block numbers.  It is currently used by
+          the ext4 and OCFS2 filesystems, but it could also be used to add
+          journal support to other file systems or block devices such
+          as RAID or LVM.
+
+          If you are using ext4 or OCFS2, you need to say Y here.
+          If you are not using ext4 or OCFS2 then you will
+          probably want to say N.
+
+          To compile this device as a module, choose M here. The module will be
+          called jbd2.  If you are compiling ext4 or OCFS2 into the kernel,
+          you cannot compile this code as a module.
+
+config JBD2_DEBUG
+        bool "JBD2 (ext4) debugging support"
+        depends on JBD2 && DEBUG_FS
+        help
+          If you are using the ext4 journaled file system (or
+          potentially any other filesystem/device using JBD2), this option
+          allows you to enable debugging output while the system is running,
+          in order to help track down any problems you are having.
+          By default, the debugging output will be turned off.
+
+          If you select Y here, then you will be able to turn on debugging
+          with "echo N > /sys/kernel/debug/jbd2/jbd2-debug", where N is a
+          number between 1 and 5. The higher the number, the more debugging
+          output is generated.  To turn debugging off again, do
+          "echo 0 > /sys/kernel/debug/jbd2/jbd2-debug".
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 91389c8aee8a..9203c3332f17 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -20,6 +20,7 @@
 #include <linux/time.h>
 #include <linux/fs.h>
 #include <linux/jbd2.h>
+#include <linux/marker.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
 
@@ -93,7 +94,8 @@ static int __try_to_free_cp_buf(struct journal_head *jh)
         int ret = 0;
         struct buffer_head *bh = jh2bh(jh);
 
-        if (jh->b_jlist == BJ_None && !buffer_locked(bh) && !buffer_dirty(bh)) {
+        if (jh->b_jlist == BJ_None && !buffer_locked(bh) &&
+            !buffer_dirty(bh) && !buffer_write_io_error(bh)) {
                 JBUFFER_TRACE(jh, "remove from checkpoint list");
                 ret = __jbd2_journal_remove_checkpoint(jh) + 1;
                 jbd_unlock_bh_state(bh);
@@ -126,14 +128,29 @@ void __jbd2_log_wait_for_space(journal_t *journal)
 
                 /*
                  * Test again, another process may have checkpointed while we
-                 * were waiting for the checkpoint lock
+                 * were waiting for the checkpoint lock. If there are no
+                 * outstanding transactions there is nothing to checkpoint and
+                 * we can't make progress. Abort the journal in this case.
                  */
                 spin_lock(&journal->j_state_lock);
+                spin_lock(&journal->j_list_lock);
                 nblocks = jbd_space_needed(journal);
                 if (__jbd2_log_space_left(journal) < nblocks) {
+                        int chkpt = journal->j_checkpoint_transactions != NULL;
+
+                        spin_unlock(&journal->j_list_lock);
                         spin_unlock(&journal->j_state_lock);
-                        jbd2_log_do_checkpoint(journal);
+                        if (chkpt) {
+                                jbd2_log_do_checkpoint(journal);
+                        } else {
+                                printk(KERN_ERR "%s: no transactions\n",
+                                       __func__);
+                                jbd2_journal_abort(journal, 0);
+                        }
+
                         spin_lock(&journal->j_state_lock);
+                } else {
+                        spin_unlock(&journal->j_list_lock);
                 }
                 mutex_unlock(&journal->j_checkpoint_mutex);
         }
@@ -160,21 +177,25 @@ static void jbd_sync_bh(journal_t *journal, struct buffer_head *bh)
  * buffers. Note that we take the buffers in the opposite ordering
  * from the one in which they were submitted for IO.
  *
+ * Return 0 on success, and return <0 if some buffers have failed
+ * to be written out.
+ *
  * Called with j_list_lock held.
  */
-static void __wait_cp_io(journal_t *journal, transaction_t *transaction)
+static int __wait_cp_io(journal_t *journal, transaction_t *transaction)
 {
         struct journal_head *jh;
         struct buffer_head *bh;
         tid_t this_tid;
         int released = 0;
+        int ret = 0;
 
         this_tid = transaction->t_tid;
 restart:
         /* Did somebody clean up the transaction in the meanwhile? */
         if (journal->j_checkpoint_transactions != transaction ||
                         transaction->t_tid != this_tid)
-                return;
+                return ret;
         while (!released && transaction->t_checkpoint_io_list) {
                 jh = transaction->t_checkpoint_io_list;
                 bh = jh2bh(jh);
@@ -194,6 +215,9 @@ restart:
                         spin_lock(&journal->j_list_lock);
                         goto restart;
                 }
+                if (unlikely(buffer_write_io_error(bh)))
+                        ret = -EIO;
+
                 /*
                  * Now in whatever state the buffer currently is, we know that
                  * it has been written out and so we can drop it from the list
@@ -203,6 +227,8 @@ restart:
                 jbd2_journal_remove_journal_head(bh);
                 __brelse(bh);
         }
+
+        return ret;
 }
 
 #define NR_BATCH        64
@@ -226,7 +252,8 @@ __flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count)
  * Try to flush one buffer from the checkpoint list to disk.
  *
  * Return 1 if something happened which requires us to abort the current
- * scan of the checkpoint list.
+ * scan of the checkpoint list.  Return <0 if the buffer has failed to
+ * be written out.
  *
  * Called with j_list_lock held and drops it if 1 is returned
  * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it
@@ -258,6 +285,9 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
                 jbd2_log_wait_commit(journal, tid);
                 ret = 1;
         } else if (!buffer_dirty(bh)) {
+                ret = 1;
+                if (unlikely(buffer_write_io_error(bh)))
+                        ret = -EIO;
                 J_ASSERT_JH(jh, !buffer_jbddirty(bh));
                 BUFFER_TRACE(bh, "remove from checkpoint");
                 __jbd2_journal_remove_checkpoint(jh);
@@ -265,7 +295,6 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
                 jbd_unlock_bh_state(bh);
                 jbd2_journal_remove_journal_head(bh);
                 __brelse(bh);
-                ret = 1;
         } else {
                 /*
                  * Important: we are about to write the buffer, and
@@ -298,6 +327,7 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
  * to disk. We submit larger chunks of data at once.
  *
  * The journal should be locked before calling this function.
+ * Called with j_checkpoint_mutex held.
  */
 int jbd2_log_do_checkpoint(journal_t *journal)
 {
@@ -313,6 +343,8 @@ int jbd2_log_do_checkpoint(journal_t *journal)
          * journal straight away.
          */
         result = jbd2_cleanup_journal_tail(journal);
+        trace_mark(jbd2_checkpoint, "dev %s need_checkpoint %d",
+                   journal->j_devname, result);
         jbd_debug(1, "cleanup_journal_tail returned %d\n", result);
         if (result <= 0)
                 return result;
@@ -321,6 +353,7 @@ int jbd2_log_do_checkpoint(journal_t *journal)
          * OK, we need to start writing disk blocks.  Take one transaction
          * and write it.
          */
+        result = 0;
         spin_lock(&journal->j_list_lock);
         if (!journal->j_checkpoint_transactions)
                 goto out;
@@ -339,7 +372,7 @@ restart:
                 int batch_count = 0;
                 struct buffer_head *bhs[NR_BATCH];
                 struct journal_head *jh;
-                int retry = 0;
+                int retry = 0, err;
 
                 while (!retry && transaction->t_checkpoint_list) {
                         struct buffer_head *bh;
@@ -353,6 +386,8 @@ restart:
                         }
                         retry = __process_buffer(journal, jh, bhs, &batch_count,
                                                  transaction);
+                        if (retry < 0 && !result)
+                                result = retry;
                         if (!retry && (need_resched() ||
                                 spin_needbreak(&journal->j_list_lock))) {
                                 spin_unlock(&journal->j_list_lock);
@@ -377,14 +412,18 @@ restart:
                  * Now we have cleaned up the first transaction's checkpoint
                  * list. Let's clean up the second one
                  */
-                __wait_cp_io(journal, transaction);
+                err = __wait_cp_io(journal, transaction);
+                if (!result)
+                        result = err;
         }
 out:
         spin_unlock(&journal->j_list_lock);
-        result = jbd2_cleanup_journal_tail(journal);
         if (result < 0)
-                return result;
-        return 0;
+                jbd2_journal_abort(journal, result);
+        else
+                result = jbd2_cleanup_journal_tail(journal);
+
+        return (result < 0) ? result : 0;
 }
 
 /*
@@ -400,8 +439,9 @@ out:
  * This is the only part of the journaling code which really needs to be
  * aware of transaction aborts.  Checkpointing involves writing to the
  * main filesystem area rather than to the journal, so it can proceed
- * even in abort state, but we must not update the journal superblock if
- * we have an abort error outstanding.
+ * even in abort state, but we must not update the super block if
+ * checkpointing may have failed.  Otherwise, we would lose some metadata
+ * buffers which should be written-back to the filesystem.
  */
 
 int jbd2_cleanup_journal_tail(journal_t *journal)
@@ -410,6 +450,9 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
         tid_t           first_tid;
         unsigned long   blocknr, freed;
 
+        if (is_journal_aborted(journal))
+                return 1;
+
         /* OK, work out the oldest transaction remaining in the log, and
          * the log block it starts at.
          *
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index f2ad061e95ec..8b119e16aa36 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -16,6 +16,7 @@
 #include <linux/time.h>
 #include <linux/fs.h>
 #include <linux/jbd2.h>
+#include <linux/marker.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
@@ -126,8 +127,7 @@ static int journal_submit_commit_record(journal_t *journal,
 
         JBUFFER_TRACE(descriptor, "submit commit block");
         lock_buffer(bh);
-        get_bh(bh);
-        set_buffer_dirty(bh);
+        clear_buffer_dirty(bh);
         set_buffer_uptodate(bh);
         bh->b_end_io = journal_end_buffer_io_sync;
 
@@ -147,12 +147,9 @@ static int journal_submit_commit_record(journal_t *journal,
          * to remember if we sent a barrier request
          */
         if (ret == -EOPNOTSUPP && barrier_done) {
-                char b[BDEVNAME_SIZE];
-
                 printk(KERN_WARNING
-                        "JBD: barrier-based sync failed on %s - "
-                        "disabling barriers\n",
-                        bdevname(journal->j_dev, b));
+                       "JBD: barrier-based sync failed on %s - "
+                       "disabling barriers\n", journal->j_devname);
                 spin_lock(&journal->j_state_lock);
                 journal->j_flags &= ~JBD2_BARRIER;
                 spin_unlock(&journal->j_state_lock);
@@ -160,7 +157,7 @@ static int journal_submit_commit_record(journal_t *journal,
                 /* And try again, without the barrier */
                 lock_buffer(bh);
                 set_buffer_uptodate(bh);
-                set_buffer_dirty(bh);
+                clear_buffer_dirty(bh);
                 ret = submit_bh(WRITE, bh);
         }
         *cbh = bh;
@@ -371,6 +368,8 @@ void jbd2_journal_commit_transaction(journal_t *journal)
         commit_transaction = journal->j_running_transaction;
         J_ASSERT(commit_transaction->t_state == T_RUNNING);
 
+        trace_mark(jbd2_start_commit, "dev %s transaction %d",
+                   journal->j_devname, commit_transaction->t_tid);
         jbd_debug(1, "JBD: starting commit of transaction %d\n",
                         commit_transaction->t_tid);
 
@@ -505,9 +504,10 @@ void jbd2_journal_commit_transaction(journal_t *journal)
                 jh = commit_transaction->t_buffers;
 
                 /* If we're in abort mode, we just un-journal the buffer and
-                   release it for background writing. */
+                   release it. */
 
                 if (is_journal_aborted(journal)) {
+                        clear_buffer_jbddirty(jh2bh(jh));
                         JBUFFER_TRACE(jh, "journal is aborting: refile");
                         jbd2_journal_refile_buffer(journal, jh);
                         /* If that was the last one, we need to clean up
@@ -681,11 +681,11 @@ start_journal_io:
          */
         err = journal_finish_inode_data_buffers(journal, commit_transaction);
         if (err) {
-                char b[BDEVNAME_SIZE];
-
                 printk(KERN_WARNING
                         "JBD2: Detected IO errors while flushing file data "
-                        "on %s\n", bdevname(journal->j_fs_dev, b));
+                       "on %s\n", journal->j_devname);
+                if (journal->j_flags & JBD2_ABORT_ON_SYNCDATA_ERR)
+                        jbd2_journal_abort(journal, err);
                 err = 0;
         }
 
@@ -786,6 +786,9 @@ wait_for_iobuf:
                 /* AKPM: bforget here */
         }
 
+        if (err)
+                jbd2_journal_abort(journal, err);
+
         jbd_debug(3, "JBD: commit phase 5\n");
 
         if (!JBD2_HAS_INCOMPAT_FEATURE(journal,
@@ -884,6 +887,8 @@ restart_loop:
                 if (buffer_jbddirty(bh)) {
                         JBUFFER_TRACE(jh, "add to new checkpointing trans");
                         __jbd2_journal_insert_checkpoint(jh, commit_transaction);
+                        if (is_journal_aborted(journal))
+                                clear_buffer_jbddirty(bh);
                         JBUFFER_TRACE(jh, "refile for checkpoint writeback");
                         __jbd2_journal_refile_buffer(jh);
                         jbd_unlock_bh_state(bh);
@@ -990,6 +995,12 @@ restart_loop:
         }
         spin_unlock(&journal->j_list_lock);
 
+        if (journal->j_commit_callback)
+                journal->j_commit_callback(journal, commit_transaction);
+
+        trace_mark(jbd2_end_commit, "dev %s transaction %d head %d",
+                   journal->j_devname, commit_transaction->t_tid,
+                   journal->j_tail_sequence);
         jbd_debug(1, "JBD: commit %d complete, head %d\n",
                   journal->j_commit_sequence, journal->j_tail_sequence);
 
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 8207a01c4edb..783de118de92 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -597,13 +597,9 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr,
                 if (ret)
                         *retp = ret;
                 else {
-                        char b[BDEVNAME_SIZE];
-
                         printk(KERN_ALERT "%s: journal block not found "
                                         "at offset %lu on %s\n",
-                                __func__,
-                                blocknr,
-                                bdevname(journal->j_dev, b));
+                               __func__, blocknr, journal->j_devname);
                         err = -EIO;
                         __journal_abort_soft(journal, err);
                 }
@@ -901,10 +897,7 @@ static struct proc_dir_entry *proc_jbd2_stats;
 
 static void jbd2_stats_proc_init(journal_t *journal)
 {
-        char name[BDEVNAME_SIZE];
-
-        bdevname(journal->j_dev, name);
-        journal->j_proc_entry = proc_mkdir(name, proc_jbd2_stats);
+        journal->j_proc_entry = proc_mkdir(journal->j_devname, proc_jbd2_stats);
         if (journal->j_proc_entry) {
                 proc_create_data("history", S_IRUGO, journal->j_proc_entry,
                                  &jbd2_seq_history_fops, journal);
@@ -915,12 +908,9 @@ static void jbd2_stats_proc_init(journal_t *journal)
 
 static void jbd2_stats_proc_exit(journal_t *journal)
 {
-        char name[BDEVNAME_SIZE];
-
-        bdevname(journal->j_dev, name);
         remove_proc_entry("info", journal->j_proc_entry);
         remove_proc_entry("history", journal->j_proc_entry);
-        remove_proc_entry(name, proc_jbd2_stats);
+        remove_proc_entry(journal->j_devname, proc_jbd2_stats);
 }
 
 static void journal_init_stats(journal_t *journal)
@@ -1018,6 +1008,7 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev,
 {
         journal_t *journal = journal_init_common();
         struct buffer_head *bh;
+        char *p;
         int n;
 
         if (!journal)
@@ -1039,6 +1030,10 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev,
         journal->j_fs_dev = fs_dev;
         journal->j_blk_offset = start;
         journal->j_maxlen = len;
+        bdevname(journal->j_dev, journal->j_devname);
+        p = journal->j_devname;
+        while ((p = strchr(p, '/')))
+                *p = '!';
         jbd2_stats_proc_init(journal);
 
         bh = __getblk(journal->j_dev, start, journal->j_blocksize);
@@ -1061,6 +1056,7 @@ journal_t * jbd2_journal_init_inode (struct inode *inode)
 {
         struct buffer_head *bh;
         journal_t *journal = journal_init_common();
+        char *p;
         int err;
         int n;
         unsigned long long blocknr;
@@ -1070,6 +1066,12 @@ journal_t * jbd2_journal_init_inode (struct inode *inode)
 
         journal->j_dev = journal->j_fs_dev = inode->i_sb->s_bdev;
         journal->j_inode = inode;
+        bdevname(journal->j_dev, journal->j_devname);
+        p = journal->j_devname;
+        while ((p = strchr(p, '/')))
+                *p = '!';
+        p = journal->j_devname + strlen(journal->j_devname);
+        sprintf(p, ":%lu", journal->j_inode->i_ino);
         jbd_debug(1,
                   "journal %p: inode %s/%ld, size %Ld, bits %d, blksize %ld\n",
                   journal, inode->i_sb->s_id, inode->i_ino,
@@ -1253,6 +1255,22 @@ void jbd2_journal_update_superblock(journal_t *journal, int wait)
                 goto out;
         }
 
+        if (buffer_write_io_error(bh)) {
+                /*
+                 * Oh, dear.  A previous attempt to write the journal
+                 * superblock failed.  This could happen because the
+                 * USB device was yanked out.  Or it could happen to
+                 * be a transient write error and maybe the block will
+                 * be remapped.  Nothing we can do but to retry the
+                 * write and hope for the best.
+                 */
+                printk(KERN_ERR "JBD2: previous I/O error detected "
+                       "for journal superblock update for %s.\n",
+                       journal->j_devname);
+                clear_buffer_write_io_error(bh);
+                set_buffer_uptodate(bh);
+        }
+
         spin_lock(&journal->j_state_lock);
         jbd_debug(1,"JBD: updating superblock (start %ld, seq %d, errno %d)\n",
                   journal->j_tail, journal->j_tail_sequence, journal->j_errno);
@@ -1264,9 +1282,16 @@ void jbd2_journal_update_superblock(journal_t *journal, int wait)
 
         BUFFER_TRACE(bh, "marking dirty");
         mark_buffer_dirty(bh);
-        if (wait)
+        if (wait) {
                 sync_dirty_buffer(bh);
-        else
+                if (buffer_write_io_error(bh)) {
+                        printk(KERN_ERR "JBD2: I/O error detected "
+                               "when updating journal superblock for %s.\n",
+                               journal->j_devname);
+                        clear_buffer_write_io_error(bh);
+                        set_buffer_uptodate(bh);
+                }
+        } else
                 ll_rw_block(SWRITE, 1, &bh);
 
 out:
@@ -1426,9 +1451,12 @@ recovery_error:
  *
  * Release a journal_t structure once it is no longer in use by the
  * journaled object.
+ * Return <0 if we couldn't clean up the journal.
  */
-void jbd2_journal_destroy(journal_t *journal)
+int jbd2_journal_destroy(journal_t *journal)
 {
+        int err = 0;
+
         /* Wait for the commit thread to wake up and die. */
         journal_kill_thread(journal);
 
@@ -1451,11 +1479,16 @@ void jbd2_journal_destroy(journal_t *journal)
         J_ASSERT(journal->j_checkpoint_transactions == NULL);
         spin_unlock(&journal->j_list_lock);
 
-        /* We can now mark the journal as empty. */
-        journal->j_tail = 0;
-        journal->j_tail_sequence = ++journal->j_transaction_sequence;
         if (journal->j_sb_buffer) {
-                jbd2_journal_update_superblock(journal, 1);
+                if (!is_journal_aborted(journal)) {
+                        /* We can now mark the journal as empty. */
+                        journal->j_tail = 0;
+                        journal->j_tail_sequence =
+                                ++journal->j_transaction_sequence;
+                        jbd2_journal_update_superblock(journal, 1);
+                } else {
+                        err = -EIO;
+                }
                 brelse(journal->j_sb_buffer);
         }
 
@@ -1467,6 +1500,8 @@ void jbd2_journal_destroy(journal_t *journal)
                 jbd2_journal_destroy_revoke(journal);
         kfree(journal->j_wbuf);
         kfree(journal);
+
+        return err;
 }
 
 
@@ -1692,10 +1727,16 @@ int jbd2_journal_flush(journal_t *journal)
         spin_lock(&journal->j_list_lock);
         while (!err && journal->j_checkpoint_transactions != NULL) {
                 spin_unlock(&journal->j_list_lock);
+                mutex_lock(&journal->j_checkpoint_mutex);
                 err = jbd2_log_do_checkpoint(journal);
+                mutex_unlock(&journal->j_checkpoint_mutex);
                 spin_lock(&journal->j_list_lock);
         }
         spin_unlock(&journal->j_list_lock);
+
+        if (is_journal_aborted(journal))
+                return -EIO;
+
         jbd2_cleanup_journal_tail(journal);
 
         /* Finally, mark the journal as really needing no recovery.
@@ -1717,7 +1758,7 @@ int jbd2_journal_flush(journal_t *journal)
         J_ASSERT(journal->j_head == journal->j_tail);
         J_ASSERT(journal->j_tail_sequence == journal->j_transaction_sequence);
         spin_unlock(&journal->j_state_lock);
-        return err;
+        return 0;
 }
 
 /**
@@ -1761,23 +1802,6 @@ int jbd2_journal_wipe(journal_t *journal, int write)
 }
 
 /*
- * journal_dev_name: format a character string to describe on what
- * device this journal is present.
- */
-
-static const char *journal_dev_name(journal_t *journal, char *buffer)
-{
-        struct block_device *bdev;
-
-        if (journal->j_inode)
-                bdev = journal->j_inode->i_sb->s_bdev;
-        else
-                bdev = journal->j_dev;
-
-        return bdevname(bdev, buffer);
-}
-
-/*
  * Journal abort has very specific semantics, which we describe
  * for journal abort.
  *
@@ -1793,13 +1817,12 @@ static const char *journal_dev_name(journal_t *journal, char *buffer)
 void __jbd2_journal_abort_hard(journal_t *journal)
 {
         transaction_t *transaction;
-        char b[BDEVNAME_SIZE];
 
         if (journal->j_flags & JBD2_ABORT)
                 return;
 
         printk(KERN_ERR "Aborting journal on device %s.\n",
-                journal_dev_name(journal, b));
+               journal->j_devname);
 
         spin_lock(&journal->j_state_lock);
         journal->j_flags |= JBD2_ABORT;
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 058f50f65b76..73063285b13f 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -225,7 +225,7 @@ do {									\
  */
 int jbd2_journal_recover(journal_t *journal)
 {
-        int                     err;
+        int                     err, err2;
         journal_superblock_t *  sb;
 
         struct recovery_info    info;
@@ -263,7 +263,10 @@ int jbd2_journal_recover(journal_t *journal)
         journal->j_transaction_sequence = ++info.end_transaction;
 
         jbd2_journal_clear_revoke(journal);
-        sync_blockdev(journal->j_fs_dev);
+        err2 = sync_blockdev(journal->j_fs_dev);
+        if (!err)
+                err = err2;
+
         return err;
 }
 
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index e5d540588fa9..39b7805a599a 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -52,6 +52,7 @@ jbd2_get_transaction(journal_t *journal, transaction_t *transaction)
         transaction->t_expires = jiffies + journal->j_commit_interval;
         spin_lock_init(&transaction->t_handle_lock);
         INIT_LIST_HEAD(&transaction->t_inode_list);
+        INIT_LIST_HEAD(&transaction->t_private_list);
 
         /* Set up the commit timer for the new transaction. */
         journal->j_commit_timer.expires = round_jiffies(transaction->t_expires);
diff --git a/fs/jffs2/Kconfig b/fs/jffs2/Kconfig
new file mode 100644
index 000000000000..6ae169cd8faa
--- /dev/null
+++ b/fs/jffs2/Kconfig
@@ -0,0 +1,188 @@
+config JFFS2_FS
+        tristate "Journalling Flash File System v2 (JFFS2) support"
+        select CRC32
+        depends on MTD
+        help
+          JFFS2 is the second generation of the Journalling Flash File System
+          for use on diskless embedded devices. It provides improved wear
+          levelling, compression and support for hard links. You cannot use
+          this on normal block devices, only on 'MTD' devices.
+
+          Further information on the design and implementation of JFFS2 is
+          available at <http://sources.redhat.com/jffs2/>.
+
+config JFFS2_FS_DEBUG
+        int "JFFS2 debugging verbosity (0 = quiet, 2 = noisy)"
+        depends on JFFS2_FS
+        default "0"
+        help
+          This controls the amount of debugging messages produced by the JFFS2
+          code. Set it to zero for use in production systems. For evaluation,
+          testing and debugging, it's advisable to set it to one. This will
+          enable a few assertions and will print debugging messages at the
+          KERN_DEBUG loglevel, where they won't normally be visible. Level 2
+          is unlikely to be useful - it enables extra debugging in certain
+          areas which at one point needed debugging, but when the bugs were
+          located and fixed, the detailed messages were relegated to level 2.
+
+          If reporting bugs, please try to have available a full dump of the
+          messages at debug level 1 while the misbehaviour was occurring.
+
+config JFFS2_FS_WRITEBUFFER
+        bool "JFFS2 write-buffering support"
+        depends on JFFS2_FS
+        default y
+        help
+          This enables the write-buffering support in JFFS2.
+
+          This functionality is required to support JFFS2 on the following
+          types of flash devices:
+            - NAND flash
+            - NOR flash with transparent ECC
+            - DataFlash
+
+config JFFS2_FS_WBUF_VERIFY
+        bool "Verify JFFS2 write-buffer reads"
+        depends on JFFS2_FS_WRITEBUFFER
+        default n
+        help
+          This causes JFFS2 to read back every page written through the
+          write-buffer, and check for errors.
+
+config JFFS2_SUMMARY
+        bool "JFFS2 summary support (EXPERIMENTAL)"
+        depends on JFFS2_FS && EXPERIMENTAL
+        default n
+        help
+          This feature makes it possible to use summary information
+          for faster filesystem mount.
+
+          The summary information can be inserted into a filesystem image
+          by the utility 'sumtool'.
+
+          If unsure, say 'N'.
+
+config JFFS2_FS_XATTR
+        bool "JFFS2 XATTR support (EXPERIMENTAL)"
+        depends on JFFS2_FS && EXPERIMENTAL
+        default n
+        help
+          Extended attributes are name:value pairs associated with inodes by
+          the kernel or by users (see the attr(5) manual page, or visit
+          <http://acl.bestbits.at/> for details).
+
+          If unsure, say N.
+
+config JFFS2_FS_POSIX_ACL
+        bool "JFFS2 POSIX Access Control Lists"
+        depends on JFFS2_FS_XATTR
+        default y
+        select FS_POSIX_ACL
+        help
+          Posix Access Control Lists (ACLs) support permissions for users and
+          groups beyond the owner/group/world scheme.
+
+          To learn more about Access Control Lists, visit the Posix ACLs for
+          Linux website <http://acl.bestbits.at/>.
+
+          If you don't know what Access Control Lists are, say N
+
+config JFFS2_FS_SECURITY
+        bool "JFFS2 Security Labels"
+        depends on JFFS2_FS_XATTR
+        default y
+        help
+          Security labels support alternative access control models
+          implemented by security modules like SELinux.  This option
+          enables an extended attribute handler for file security
+          labels in the jffs2 filesystem.
+
+          If you are not using a security module that requires using
+          extended attributes for file security labels, say N.
+
+config JFFS2_COMPRESSION_OPTIONS
+        bool "Advanced compression options for JFFS2"
+        depends on JFFS2_FS
+        default n
+        help
+          Enabling this option allows you to explicitly choose which
+          compression modules, if any, are enabled in JFFS2. Removing
+          compressors can mean you cannot read existing file systems,
+          and enabling experimental compressors can mean that you
+          write a file system which cannot be read by a standard kernel.
+
+          If unsure, you should _definitely_ say 'N'.
+
+config JFFS2_ZLIB
+        bool "JFFS2 ZLIB compression support" if JFFS2_COMPRESSION_OPTIONS
+        select ZLIB_INFLATE
+        select ZLIB_DEFLATE
+        depends on JFFS2_FS
+        default y
+        help
+          Zlib is designed to be a free, general-purpose, legally unencumbered,
+          lossless data-compression library for use on virtually any computer
+          hardware and operating system. See <http://www.gzip.org/zlib/> for
+          further information.
+
+          Say 'Y' if unsure.
+
+config JFFS2_LZO
+        bool "JFFS2 LZO compression support" if JFFS2_COMPRESSION_OPTIONS
+        select LZO_COMPRESS
+        select LZO_DECOMPRESS
+        depends on JFFS2_FS
+        default n
+        help
+          minilzo-based compression. Generally works better than Zlib.
+
+          This feature was added in July, 2007. Say 'N' if you need
+          compatibility with older bootloaders or kernels.
+
+config JFFS2_RTIME
+        bool "JFFS2 RTIME compression support" if JFFS2_COMPRESSION_OPTIONS
+        depends on JFFS2_FS
+        default y
+        help
+          Rtime does manage to recompress already-compressed data. Say 'Y' if unsure.
+
+config JFFS2_RUBIN
+        bool "JFFS2 RUBIN compression support" if JFFS2_COMPRESSION_OPTIONS
+        depends on JFFS2_FS
+        default n
+        help
+          RUBINMIPS and DYNRUBIN compressors. Say 'N' if unsure.
+
+choice
+        prompt "JFFS2 default compression mode" if JFFS2_COMPRESSION_OPTIONS
+        default JFFS2_CMODE_PRIORITY
+        depends on JFFS2_FS
+        help
+          You can set here the default compression mode of JFFS2 from
+          the available compression modes. Don't touch if unsure.
+
+config JFFS2_CMODE_NONE
+        bool "no compression"
+        help
+          Uses no compression.
+
+config JFFS2_CMODE_PRIORITY
+        bool "priority"
+        help
+          Tries the compressors in a predefined order and chooses the first
+          successful one.
+
+config JFFS2_CMODE_SIZE
+        bool "size (EXPERIMENTAL)"
+        help
+          Tries all compressors and chooses the one which has the smallest
+          result.
+
+config JFFS2_CMODE_FAVOURLZO
+        bool "Favour LZO"
+        help
+          Tries all compressors and chooses the one which has the smallest
+          result but gives some preference to LZO (which has faster
+          decompression) at the expense of size.
+
+endchoice
diff --git a/fs/jffs2/compr.c b/fs/jffs2/compr.c
index 86739ee53b37..f25e70c1b51c 100644
--- a/fs/jffs2/compr.c
+++ b/fs/jffs2/compr.c
@@ -53,8 +53,8 @@ static int jffs2_is_best_compression(struct jffs2_compressor *this,
 }
 
 /* jffs2_compress:
- * @data: Pointer to uncompressed data
- * @cdata: Pointer to returned pointer to buffer for compressed data
+ * @data_in: Pointer to uncompressed data
+ * @cpage_out: Pointer to returned pointer to buffer for compressed data
  * @datalen: On entry, holds the amount of data available for compression.
  *      On exit, expected to hold the amount of data actually compressed.
  * @cdatalen: On entry, holds the amount of space available for compressed
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index cd219ef55254..b1aaae823a52 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -311,7 +311,7 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char
         /* FIXME: If you care. We'd need to use frags for the target
            if it grows much more than this */
         if (targetlen > 254)
-                return -EINVAL;
+                return -ENAMETOOLONG;
 
         ri = jffs2_alloc_raw_inode();
 
diff --git a/fs/jffs2/erase.c b/fs/jffs2/erase.c
index dddb2a6c9e2c..259461b910af 100644
--- a/fs/jffs2/erase.c
+++ b/fs/jffs2/erase.c
@@ -68,7 +68,7 @@ static void jffs2_erase_block(struct jffs2_sb_info *c,
         instr->len = c->sector_size;
         instr->callback = jffs2_erase_callback;
         instr->priv = (unsigned long)(&instr[1]);
-        instr->fail_addr = 0xffffffff;
+        instr->fail_addr = MTD_FAIL_ADDR_UNKNOWN;
 
         ((struct erase_priv_struct *)instr->priv)->jeb = jeb;
         ((struct erase_priv_struct *)instr->priv)->c = c;
@@ -175,7 +175,7 @@ static void jffs2_erase_failed(struct jffs2_sb_info *c, struct jffs2_eraseblock
 {
         /* For NAND, if the failure did not occur at the device level for a
            specific physical page, don't bother updating the bad block table. */
-        if (jffs2_cleanmarker_oob(c) && (bad_offset != 0xffffffff)) {
+        if (jffs2_cleanmarker_oob(c) && (bad_offset != MTD_FAIL_ADDR_UNKNOWN)) {
                 /* We had a device-level failure to erase.  Let's see if we've
                    failed too many times. */
                 if (!jffs2_write_nand_badblock(c, jeb, bad_offset)) {
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index 086c43830221..249305d65d5b 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -207,6 +207,8 @@ int jffs2_statfs(struct dentry *dentry, struct kstatfs *buf)
         buf->f_files = 0;
         buf->f_ffree = 0;
         buf->f_namelen = JFFS2_MAX_NAME_LEN;
+        buf->f_fsid.val[0] = JFFS2_SUPER_MAGIC;
+        buf->f_fsid.val[1] = c->mtd->index;
 
         spin_lock(&c->erase_completion_lock);
         avail = c->dirty_size + c->free_size;
@@ -440,14 +442,14 @@ struct inode *jffs2_new_inode (struct inode *dir_i, int mode, struct jffs2_raw_i
 
         memset(ri, 0, sizeof(*ri));
         /* Set OS-specific defaults for new inodes */
-        ri->uid = cpu_to_je16(current->fsuid);
+        ri->uid = cpu_to_je16(current_fsuid());
 
         if (dir_i->i_mode & S_ISGID) {
                 ri->gid = cpu_to_je16(dir_i->i_gid);
                 if (S_ISDIR(mode))
                         mode |= S_ISGID;
         } else {
-                ri->gid = cpu_to_je16(current->fsgid);
+                ri->gid = cpu_to_je16(current_fsgid());
         }
 
         /* POSIX ACLs have to be processed now, at least partly.
diff --git a/fs/jffs2/nodemgmt.c b/fs/jffs2/nodemgmt.c
index a9bf9603c1ba..0875b60b4bf7 100644
--- a/fs/jffs2/nodemgmt.c
+++ b/fs/jffs2/nodemgmt.c
@@ -261,6 +261,10 @@ static int jffs2_find_nextblock(struct jffs2_sb_info *c)
 
         jffs2_sum_reset_collected(c->summary); /* reset collected summary */
 
+        /* adjust write buffer offset, else we get a non contiguous write bug */
+        if (!(c->wbuf_ofs % c->sector_size) && !c->wbuf_len)
+                c->wbuf_ofs = 0xffffffff;
+
         D1(printk(KERN_DEBUG "jffs2_find_nextblock(): new nextblock = 0x%08x\n", c->nextblock->offset));
 
         return 0;
diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c
index 0e78b00035e4..d9a721e6db70 100644
--- a/fs/jffs2/wbuf.c
+++ b/fs/jffs2/wbuf.c
@@ -679,10 +679,7 @@ static int __jffs2_flush_wbuf(struct jffs2_sb_info *c, int pad)
 
         memset(c->wbuf,0xff,c->wbuf_pagesize);
         /* adjust write buffer offset, else we get a non contiguous write bug */
-        if (SECTOR_ADDR(c->wbuf_ofs) == SECTOR_ADDR(c->wbuf_ofs+c->wbuf_pagesize))
-                c->wbuf_ofs += c->wbuf_pagesize;
-        else
-                c->wbuf_ofs = 0xffffffff;
+        c->wbuf_ofs += c->wbuf_pagesize;
         c->wbuf_len = 0;
         return 0;
 }
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 3630718be395..0dae345e481b 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -199,7 +199,7 @@ enum {
         Opt_usrquota, Opt_grpquota, Opt_uid, Opt_gid, Opt_umask
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         {Opt_integrity, "integrity"},
         {Opt_nointegrity, "nointegrity"},
         {Opt_iocharset, "iocharset=%s"},
diff --git a/fs/lockd/Makefile b/fs/lockd/Makefile
index 7725a0a9a555..97f6073ab339 100644
--- a/fs/lockd/Makefile
+++ b/fs/lockd/Makefile
@@ -5,6 +5,6 @@
 obj-$(CONFIG_LOCKD) += lockd.o
 
 lockd-objs-y := clntlock.o clntproc.o host.o svc.o svclock.o svcshare.o \
-                svcproc.o svcsubs.o mon.o xdr.o
+                svcproc.o svcsubs.o mon.o xdr.o grace.o
 lockd-objs-$(CONFIG_LOCKD_V4) += xdr4.o svc4proc.o
 lockd-objs                    := $(lockd-objs-y)
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index 0b45fd3a4bfd..8307dd64bf46 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -54,14 +54,13 @@ struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init)
         u32 nlm_version = (nlm_init->nfs_version == 2) ? 1 : 4;
         int status;
 
-        status = lockd_up(nlm_init->protocol);
+        status = lockd_up();
         if (status < 0)
                 return ERR_PTR(status);
 
-        host = nlmclnt_lookup_host((struct sockaddr_in *)nlm_init->address,
+        host = nlmclnt_lookup_host(nlm_init->address, nlm_init->addrlen,
                                    nlm_init->protocol, nlm_version,
-                                   nlm_init->hostname,
-                                   strlen(nlm_init->hostname));
+                                   nlm_init->hostname);
         if (host == NULL) {
                 lockd_down();
                 return ERR_PTR(-ENOLCK);
@@ -142,7 +141,7 @@ int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout)
 /*
  * The server lockd has called us back to tell us the lock was granted
  */
-__be32 nlmclnt_grant(const struct sockaddr_in *addr, const struct nlm_lock *lock)
+__be32 nlmclnt_grant(const struct sockaddr *addr, const struct nlm_lock *lock)
 {
         const struct file_lock *fl = &lock->fl;
         const struct nfs_fh *fh = &lock->fh;
@@ -166,7 +165,7 @@ __be32 nlmclnt_grant(const struct sockaddr_in *addr, const struct nlm_lock *lock
                  */
                 if (fl_blocked->fl_u.nfs_fl.owner->pid != lock->svid)
                         continue;
-                if (!nlm_cmp_addr(&block->b_host->h_addr, addr))
+                if (!nlm_cmp_addr(nlm_addr(block->b_host), addr))
                         continue;
                 if (nfs_compare_fh(NFS_FH(fl_blocked->fl_file->f_path.dentry->d_inode) ,fh) != 0)
                         continue;
@@ -216,7 +215,7 @@ reclaimer(void *ptr)
         /* This one ensures that our parent doesn't terminate while the
          * reclaim is in progress */
         lock_kernel();
-        lockd_up(0); /* note: this cannot fail as lockd is already running */
+        lockd_up();     /* note: this cannot fail as lockd is already running */
 
         dprintk("lockd: reclaiming locks for host %s\n", host->h_name);
 
diff --git a/fs/lockd/grace.c b/fs/lockd/grace.c
new file mode 100644
index 000000000000..183cc1f0af1c
--- /dev/null
+++ b/fs/lockd/grace.c
@@ -0,0 +1,59 @@
+/*
+ * Common code for control of lockd and nfsv4 grace periods.
+ */
+
+#include <linux/module.h>
+#include <linux/lockd/bind.h>
+
+static LIST_HEAD(grace_list);
+static DEFINE_SPINLOCK(grace_lock);
+
+/**
+ * locks_start_grace
+ * @lm: who this grace period is for
+ *
+ * A grace period is a period during which locks should not be given
+ * out.  Currently grace periods are only enforced by the two lock
+ * managers (lockd and nfsd), using the locks_in_grace() function to
+ * check when they are in a grace period.
+ *
+ * This function is called to start a grace period.
+ */
+void locks_start_grace(struct lock_manager *lm)
+{
+        spin_lock(&grace_lock);
+        list_add(&lm->list, &grace_list);
+        spin_unlock(&grace_lock);
+}
+EXPORT_SYMBOL_GPL(locks_start_grace);
+
+/**
+ * locks_end_grace
+ * @lm: who this grace period is for
+ *
+ * Call this function to state that the given lock manager is ready to
+ * resume regular locking.  The grace period will not end until all lock
+ * managers that called locks_start_grace() also call locks_end_grace().
+ * Note that callers count on it being safe to call this more than once,
+ * and the second call should be a no-op.
+ */
+void locks_end_grace(struct lock_manager *lm)
+{
+        spin_lock(&grace_lock);
+        list_del_init(&lm->list);
+        spin_unlock(&grace_lock);
+}
+EXPORT_SYMBOL_GPL(locks_end_grace);
+
+/**
+ * locks_in_grace
+ *
+ * Lock managers call this function to determine when it is OK for them
+ * to answer ordinary lock requests, and when they should accept only
+ * lock reclaims.
+ */
+int locks_in_grace(void)
+{
+        return !list_empty(&grace_list);
+}
+EXPORT_SYMBOL_GPL(locks_in_grace);
diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index a17664c7eacc..9fd8889097b7 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -11,16 +11,17 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/in.h>
+#include <linux/in6.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/lockd/lockd.h>
 #include <linux/lockd/sm_inter.h>
 #include <linux/mutex.h>
 
+#include <net/ipv6.h>
 
 #define NLMDBG_FACILITY         NLMDBG_HOSTCACHE
 #define NLM_HOST_NRHASH         32
-#define NLM_ADDRHASH(addr)      (ntohl(addr) & (NLM_HOST_NRHASH-1))
 #define NLM_HOST_REBIND         (60 * HZ)
 #define NLM_HOST_EXPIRE         (300 * HZ)
 #define NLM_HOST_COLLECT        (120 * HZ)
@@ -30,42 +31,115 @@ static unsigned long		next_gc;
 static int                      nrhosts;
 static DEFINE_MUTEX(nlm_host_mutex);
 
-
 static void                     nlm_gc_hosts(void);
-static struct nsm_handle *      __nsm_find(const struct sockaddr_in *,
-                                        const char *, unsigned int, int);
-static struct nsm_handle *      nsm_find(const struct sockaddr_in *sin,
-                                         const char *hostname,
-                                         unsigned int hostname_len);
+static struct nsm_handle        *nsm_find(const struct sockaddr *sap,
+                                                const size_t salen,
+                                                const char *hostname,
+                                                const size_t hostname_len,
+                                                const int create);
+
+struct nlm_lookup_host_info {
+        const int               server;         /* search for server|client */
+        const struct sockaddr   *sap;           /* address to search for */
+        const size_t            salen;          /* it's length */
+        const unsigned short    protocol;       /* transport to search for*/
+        const u32               version;        /* NLM version to search for */
+        const char              *hostname;      /* remote's hostname */
+        const size_t            hostname_len;   /* it's length */
+        const struct sockaddr   *src_sap;       /* our address (optional) */
+        const size_t            src_len;        /* it's length */
+};
+
+/*
+ * Hash function must work well on big- and little-endian platforms
+ */
+static unsigned int __nlm_hash32(const __be32 n)
+{
+        unsigned int hash = (__force u32)n ^ ((__force u32)n >> 16);
+        return hash ^ (hash >> 8);
+}
+
+static unsigned int __nlm_hash_addr4(const struct sockaddr *sap)
+{
+        const struct sockaddr_in *sin = (struct sockaddr_in *)sap;
+        return __nlm_hash32(sin->sin_addr.s_addr);
+}
+
+static unsigned int __nlm_hash_addr6(const struct sockaddr *sap)
+{
+        const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
+        const struct in6_addr addr = sin6->sin6_addr;
+        return __nlm_hash32(addr.s6_addr32[0]) ^
+               __nlm_hash32(addr.s6_addr32[1]) ^
+               __nlm_hash32(addr.s6_addr32[2]) ^
+               __nlm_hash32(addr.s6_addr32[3]);
+}
+
+static unsigned int nlm_hash_address(const struct sockaddr *sap)
+{
+        unsigned int hash;
+
+        switch (sap->sa_family) {
+        case AF_INET:
+                hash = __nlm_hash_addr4(sap);
+                break;
+        case AF_INET6:
+                hash = __nlm_hash_addr6(sap);
+                break;
+        default:
+                hash = 0;
+        }
+        return hash & (NLM_HOST_NRHASH - 1);
+}
+
+static void nlm_clear_port(struct sockaddr *sap)
+{
+        switch (sap->sa_family) {
+        case AF_INET:
+                ((struct sockaddr_in *)sap)->sin_port = 0;
+                break;
+        case AF_INET6:
+                ((struct sockaddr_in6 *)sap)->sin6_port = 0;
+                break;
+        }
+}
+
+static void nlm_display_address(const struct sockaddr *sap,
+                                char *buf, const size_t len)
+{
+        const struct sockaddr_in *sin = (struct sockaddr_in *)sap;
+        const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
+
+        switch (sap->sa_family) {
+        case AF_UNSPEC:
+                snprintf(buf, len, "unspecified");
+                break;
+        case AF_INET:
+                snprintf(buf, len, NIPQUAD_FMT, NIPQUAD(sin->sin_addr.s_addr));
+                break;
+        case AF_INET6:
+                if (ipv6_addr_v4mapped(&sin6->sin6_addr))
+                        snprintf(buf, len, NIPQUAD_FMT,
+                                 NIPQUAD(sin6->sin6_addr.s6_addr32[3]));
+                else
+                        snprintf(buf, len, NIP6_FMT, NIP6(sin6->sin6_addr));
+                break;
+        default:
+                snprintf(buf, len, "unsupported address family");
+                break;
+        }
+}
 
 /*
  * Common host lookup routine for server & client
  */
-static struct nlm_host *nlm_lookup_host(int server,
-                                        const struct sockaddr_in *sin,
-                                        int proto, u32 version,
-                                        const char *hostname,
-                                        unsigned int hostname_len,
-                                        const struct sockaddr_in *ssin)
+static struct nlm_host *nlm_lookup_host(struct nlm_lookup_host_info *ni)
 {
         struct hlist_head *chain;
         struct hlist_node *pos;
         struct nlm_host *host;
         struct nsm_handle *nsm = NULL;
-        int             hash;
-
-        dprintk("lockd: nlm_lookup_host("NIPQUAD_FMT"->"NIPQUAD_FMT
-                        ", p=%d, v=%u, my role=%s, name=%.*s)\n",
-                        NIPQUAD(ssin->sin_addr.s_addr),
-                        NIPQUAD(sin->sin_addr.s_addr), proto, version,
-                        server? "server" : "client",
-                        hostname_len,
-                        hostname? hostname : "<none>");
 
-
-        hash = NLM_ADDRHASH(sin->sin_addr.s_addr);
-
-        /* Lock hash table */
         mutex_lock(&nlm_host_mutex);
 
         if (time_after_eq(jiffies, next_gc))
@@ -78,22 +152,22 @@ static struct nlm_host *nlm_lookup_host(int server,
          * different NLM rpc_clients into one single nlm_host object.
          * This would allow us to have one nlm_host per address.
          */
-        chain = &nlm_hosts[hash];
+        chain = &nlm_hosts[nlm_hash_address(ni->sap)];
         hlist_for_each_entry(host, pos, chain, h_hash) {
-                if (!nlm_cmp_addr(&host->h_addr, sin))
+                if (!nlm_cmp_addr(nlm_addr(host), ni->sap))
                         continue;
 
                 /* See if we have an NSM handle for this client */
                 if (!nsm)
                         nsm = host->h_nsmhandle;
 
-                if (host->h_proto != proto)
+                if (host->h_proto != ni->protocol)
                         continue;
-                if (host->h_version != version)
+                if (host->h_version != ni->version)
                         continue;
-                if (host->h_server != server)
+                if (host->h_server != ni->server)
                         continue;
-                if (!nlm_cmp_addr(&host->h_saddr, ssin))
+                if (!nlm_cmp_addr(nlm_srcaddr(host), ni->src_sap))
                         continue;
 
                 /* Move to head of hash chain. */
@@ -101,30 +175,41 @@ static struct nlm_host *nlm_lookup_host(int server,
                 hlist_add_head(&host->h_hash, chain);
 
                 nlm_get_host(host);
+                dprintk("lockd: nlm_lookup_host found host %s (%s)\n",
+                                host->h_name, host->h_addrbuf);
                 goto out;
         }
-        if (nsm)
-                atomic_inc(&nsm->sm_count);
-
-        host = NULL;
 
-        /* Sadly, the host isn't in our hash table yet. See if
-         * we have an NSM handle for it. If not, create one.
+        /*
+         * The host wasn't in our hash table.  If we don't
+         * have an NSM handle for it yet, create one.
          */
-        if (!nsm && !(nsm = nsm_find(sin, hostname, hostname_len)))
-                goto out;
+        if (nsm)
+                atomic_inc(&nsm->sm_count);
+        else {
+                host = NULL;
+                nsm = nsm_find(ni->sap, ni->salen,
+                                ni->hostname, ni->hostname_len, 1);
+                if (!nsm) {
+                        dprintk("lockd: nlm_lookup_host failed; "
+                                "no nsm handle\n");
+                        goto out;
+                }
+        }
 
         host = kzalloc(sizeof(*host), GFP_KERNEL);
         if (!host) {
                 nsm_release(nsm);
+                dprintk("lockd: nlm_lookup_host failed; no memory\n");
                 goto out;
         }
         host->h_name       = nsm->sm_name;
-        host->h_addr       = *sin;
-        host->h_addr.sin_port = 0;      /* ouch! */
-        host->h_saddr      = *ssin;
-        host->h_version    = version;
-        host->h_proto      = proto;
+        memcpy(nlm_addr(host), ni->sap, ni->salen);
+        host->h_addrlen = ni->salen;
+        nlm_clear_port(nlm_addr(host));
+        memcpy(nlm_srcaddr(host), ni->src_sap, ni->src_len);
+        host->h_version    = ni->version;
+        host->h_proto      = ni->protocol;
         host->h_rpcclnt    = NULL;
         mutex_init(&host->h_mutex);
         host->h_nextrebind = jiffies + NLM_HOST_REBIND;
@@ -135,7 +220,7 @@ static struct nlm_host *nlm_lookup_host(int server,
         host->h_state      = 0;                 /* pseudo NSM state */
         host->h_nsmstate   = 0;                 /* real NSM state */
         host->h_nsmhandle  = nsm;
-        host->h_server     = server;
+        host->h_server     = ni->server;
         hlist_add_head(&host->h_hash, chain);
         INIT_LIST_HEAD(&host->h_lockowners);
         spin_lock_init(&host->h_lock);
@@ -143,6 +228,15 @@ static struct nlm_host *nlm_lookup_host(int server,
         INIT_LIST_HEAD(&host->h_reclaim);
 
         nrhosts++;
+
+        nlm_display_address((struct sockaddr *)&host->h_addr,
+                                host->h_addrbuf, sizeof(host->h_addrbuf));
+        nlm_display_address((struct sockaddr *)&host->h_srcaddr,
+                                host->h_srcaddrbuf, sizeof(host->h_srcaddrbuf));
+
+        dprintk("lockd: nlm_lookup_host created host %s\n",
+                        host->h_name);
+
 out:
         mutex_unlock(&nlm_host_mutex);
         return host;
@@ -170,33 +264,103 @@ nlm_destroy_host(struct nlm_host *host)
         kfree(host);
 }
 
-/*
- * Find an NLM server handle in the cache. If there is none, create it.
+/**
+ * nlmclnt_lookup_host - Find an NLM host handle matching a remote server
+ * @sap: network address of server
+ * @salen: length of server address
+ * @protocol: transport protocol to use
+ * @version: NLM protocol version
+ * @hostname: '\0'-terminated hostname of server
+ *
+ * Returns an nlm_host structure that matches the passed-in
+ * [server address, transport protocol, NLM version, server hostname].
+ * If one doesn't already exist in the host cache, a new handle is
+ * created and returned.
  */
-struct nlm_host *nlmclnt_lookup_host(const struct sockaddr_in *sin,
-                                     int proto, u32 version,
-                                     const char *hostname,
-                                     unsigned int hostname_len)
+struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap,
+                                     const size_t salen,
+                                     const unsigned short protocol,
+                                     const u32 version, const char *hostname)
 {
-        struct sockaddr_in ssin = {0};
-
-        return nlm_lookup_host(0, sin, proto, version,
-                               hostname, hostname_len, &ssin);
+        const struct sockaddr source = {
+                .sa_family      = AF_UNSPEC,
+        };
+        struct nlm_lookup_host_info ni = {
+                .server         = 0,
+                .sap            = sap,
+                .salen          = salen,
+                .protocol       = protocol,
+                .version        = version,
+                .hostname       = hostname,
+                .hostname_len   = strlen(hostname),
+                .src_sap        = &source,
+                .src_len        = sizeof(source),
+        };
+
+        dprintk("lockd: %s(host='%s', vers=%u, proto=%s)\n", __func__,
+                        (hostname ? hostname : "<none>"), version,
+                        (protocol == IPPROTO_UDP ? "udp" : "tcp"));
+
+        return nlm_lookup_host(&ni);
 }
 
-/*
- * Find an NLM client handle in the cache. If there is none, create it.
+/**
+ * nlmsvc_lookup_host - Find an NLM host handle matching a remote client
+ * @rqstp: incoming NLM request
+ * @hostname: name of client host
+ * @hostname_len: length of client hostname
+ *
+ * Returns an nlm_host structure that matches the [client address,
+ * transport protocol, NLM version, client hostname] of the passed-in
+ * NLM request.  If one doesn't already exist in the host cache, a
+ * new handle is created and returned.
+ *
+ * Before possibly creating a new nlm_host, construct a sockaddr
+ * for a specific source address in case the local system has
+ * multiple network addresses.  The family of the address in
+ * rq_daddr is guaranteed to be the same as the family of the
+ * address in rq_addr, so it's safe to use the same family for
+ * the source address.
  */
-struct nlm_host *
-nlmsvc_lookup_host(struct svc_rqst *rqstp,
-                        const char *hostname, unsigned int hostname_len)
+struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp,
+                                    const char *hostname,
+                                    const size_t hostname_len)
 {
-        struct sockaddr_in ssin = {0};
+        struct sockaddr_in sin = {
+                .sin_family     = AF_INET,
+        };
+        struct sockaddr_in6 sin6 = {
+                .sin6_family    = AF_INET6,
+        };
+        struct nlm_lookup_host_info ni = {
+                .server         = 1,
+                .sap            = svc_addr(rqstp),
+                .salen          = rqstp->rq_addrlen,
+                .protocol       = rqstp->rq_prot,
+                .version        = rqstp->rq_vers,
+                .hostname       = hostname,
+                .hostname_len   = hostname_len,
+                .src_len        = rqstp->rq_addrlen,
+        };
+
+        dprintk("lockd: %s(host='%*s', vers=%u, proto=%s)\n", __func__,
+                        (int)hostname_len, hostname, rqstp->rq_vers,
+                        (rqstp->rq_prot == IPPROTO_UDP ? "udp" : "tcp"));
+
+        switch (ni.sap->sa_family) {
+        case AF_INET:
+                sin.sin_addr.s_addr = rqstp->rq_daddr.addr.s_addr;
+                ni.src_sap = (struct sockaddr *)&sin;
+                break;
+        case AF_INET6:
+                ipv6_addr_copy(&sin6.sin6_addr, &rqstp->rq_daddr.addr6);
+                ni.src_sap = (struct sockaddr *)&sin6;
+                break;
+        default:
+                return NULL;
+        }
 
-        ssin.sin_addr = rqstp->rq_daddr.addr;
-        return nlm_lookup_host(1, svc_addr_in(rqstp),
-                               rqstp->rq_prot, rqstp->rq_vers,
-                               hostname, hostname_len, &ssin);
+        return nlm_lookup_host(&ni);
 }
 
 /*
@@ -207,9 +371,8 @@ nlm_bind_host(struct nlm_host *host)
 {
         struct rpc_clnt *clnt;
 
-        dprintk("lockd: nlm_bind_host("NIPQUAD_FMT"->"NIPQUAD_FMT")\n",
-                        NIPQUAD(host->h_saddr.sin_addr),
-                        NIPQUAD(host->h_addr.sin_addr));
+        dprintk("lockd: nlm_bind_host %s (%s), my addr=%s\n",
+                        host->h_name, host->h_addrbuf, host->h_srcaddrbuf);
 
         /* Lock host handle */
         mutex_lock(&host->h_mutex);
@@ -221,7 +384,7 @@ nlm_bind_host(struct nlm_host *host)
                 if (time_after_eq(jiffies, host->h_nextrebind)) {
                         rpc_force_rebind(clnt);
                         host->h_nextrebind = jiffies + NLM_HOST_REBIND;
-                        dprintk("lockd: next rebind in %ld jiffies\n",
+                        dprintk("lockd: next rebind in %lu jiffies\n",
                                         host->h_nextrebind - jiffies);
                 }
         } else {
@@ -234,9 +397,9 @@ nlm_bind_host(struct nlm_host *host)
                 };
                 struct rpc_create_args args = {
                         .protocol       = host->h_proto,
-                        .address        = (struct sockaddr *)&host->h_addr,
-                        .addrsize       = sizeof(host->h_addr),
-                        .saddress       = (struct sockaddr *)&host->h_saddr,
+                        .address        = nlm_addr(host),
+                        .addrsize       = host->h_addrlen,
+                        .saddress       = nlm_srcaddr(host),
                         .timeout        = &timeparms,
                         .servername     = host->h_name,
                         .program        = &nlm_program,
@@ -324,12 +487,16 @@ void nlm_host_rebooted(const struct sockaddr_in *sin,
         struct nsm_handle *nsm;
         struct nlm_host *host;
 
-        dprintk("lockd: nlm_host_rebooted(%s, %u.%u.%u.%u)\n",
-                        hostname, NIPQUAD(sin->sin_addr));
-
-        /* Find the NSM handle for this peer */
-        if (!(nsm = __nsm_find(sin, hostname, hostname_len, 0)))
+        nsm = nsm_find((struct sockaddr *)sin, sizeof(*sin),
+                        hostname, hostname_len, 0);
+        if (nsm == NULL) {
+                dprintk("lockd: never saw rebooted peer '%.*s' before\n",
+                                hostname_len, hostname);
                 return;
+        }
+
+        dprintk("lockd: nlm_host_rebooted(%.*s, %s)\n",
+                        hostname_len, hostname, nsm->sm_addrbuf);
 
         /* When reclaiming locks on this peer, make sure that
          * we set up a new notification */
@@ -461,22 +628,23 @@ nlm_gc_hosts(void)
 static LIST_HEAD(nsm_handles);
 static DEFINE_SPINLOCK(nsm_lock);
 
-static struct nsm_handle *
-__nsm_find(const struct sockaddr_in *sin,
-                const char *hostname, unsigned int hostname_len,
-                int create)
+static struct nsm_handle *nsm_find(const struct sockaddr *sap,
+                                   const size_t salen,
+                                   const char *hostname,
+                                   const size_t hostname_len,
+                                   const int create)
 {
         struct nsm_handle *nsm = NULL;
         struct nsm_handle *pos;
 
-        if (!sin)
+        if (!sap)
                 return NULL;
 
         if (hostname && memchr(hostname, '/', hostname_len) != NULL) {
                 if (printk_ratelimit()) {
                         printk(KERN_WARNING "Invalid hostname \"%.*s\" "
                                             "in NFS lock request\n",
-                                hostname_len, hostname);
+                                (int)hostname_len, hostname);
                 }
                 return NULL;
         }
@@ -489,7 +657,7 @@ retry:
                         if (strlen(pos->sm_name) != hostname_len
                          || memcmp(pos->sm_name, hostname, hostname_len))
                                 continue;
-                } else if (!nlm_cmp_addr(&pos->sm_addr, sin))
+                } else if (!nlm_cmp_addr(nsm_addr(pos), sap))
                         continue;
                 atomic_inc(&pos->sm_count);
                 kfree(nsm);
@@ -509,10 +677,13 @@ retry:
         if (nsm == NULL)
                 return NULL;
 
-        nsm->sm_addr = *sin;
+        memcpy(nsm_addr(nsm), sap, salen);
+        nsm->sm_addrlen = salen;
         nsm->sm_name = (char *) (nsm + 1);
         memcpy(nsm->sm_name, hostname, hostname_len);
         nsm->sm_name[hostname_len] = '\0';
+        nlm_display_address((struct sockaddr *)&nsm->sm_addr,
+                                nsm->sm_addrbuf, sizeof(nsm->sm_addrbuf));
         atomic_set(&nsm->sm_count, 1);
         goto retry;
 
@@ -521,13 +692,6 @@ found:
         return nsm;
 }
 
-static struct nsm_handle *
-nsm_find(const struct sockaddr_in *sin, const char *hostname,
-         unsigned int hostname_len)
-{
-        return __nsm_find(sin, hostname, hostname_len, 1);
-}
-
 /*
  * Release an NSM handle
  */
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index e4d563543b11..4e7e958e8f67 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -51,7 +51,7 @@ nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res)
 
         memset(&args, 0, sizeof(args));
         args.mon_name = nsm->sm_name;
-        args.addr = nsm->sm_addr.sin_addr.s_addr;
+        args.addr = nsm_addr_in(nsm)->sin_addr.s_addr;
         args.prog = NLM_PROGRAM;
         args.vers = 3;
         args.proc = NLMPROC_NSM_NOTIFY;
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 5bd9bf0fa9df..c631a83931ce 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -51,7 +51,6 @@ static DEFINE_MUTEX(nlmsvc_mutex);
 static unsigned int             nlmsvc_users;
 static struct task_struct       *nlmsvc_task;
 static struct svc_rqst          *nlmsvc_rqst;
-int                             nlmsvc_grace_period;
 unsigned long                   nlmsvc_timeout;
 
 /*
@@ -85,27 +84,23 @@ static unsigned long get_lockd_grace_period(void)
                 return nlm_timeout * 5 * HZ;
 }
 
-unsigned long get_nfs_grace_period(void)
-{
-        unsigned long lockdgrace = get_lockd_grace_period();
-        unsigned long nfsdgrace = 0;
-
-        if (nlmsvc_ops)
-                nfsdgrace = nlmsvc_ops->get_grace_period();
-
-        return max(lockdgrace, nfsdgrace);
-}
-EXPORT_SYMBOL(get_nfs_grace_period);
+static struct lock_manager lockd_manager = {
+};
 
-static unsigned long set_grace_period(void)
+static void grace_ender(struct work_struct *not_used)
 {
-        nlmsvc_grace_period = 1;
-        return get_nfs_grace_period() + jiffies;
+        locks_end_grace(&lockd_manager);
 }
 
-static inline void clear_grace_period(void)
+static DECLARE_DELAYED_WORK(grace_period_end, grace_ender);
+
+static void set_grace_period(void)
 {
-        nlmsvc_grace_period = 0;
+        unsigned long grace_period = get_lockd_grace_period();
+
+        locks_start_grace(&lockd_manager);
+        cancel_delayed_work_sync(&grace_period_end);
+        schedule_delayed_work(&grace_period_end, grace_period);
 }
 
 /*
@@ -116,7 +111,6 @@ lockd(void *vrqstp)
 {
         int             err = 0, preverr = 0;
         struct svc_rqst *rqstp = vrqstp;
-        unsigned long grace_period_expire;
 
         /* try_to_freeze() is called from svc_recv() */
         set_freezable();
@@ -139,7 +133,7 @@ lockd(void *vrqstp)
                 nlm_timeout = LOCKD_DFLT_TIMEO;
         nlmsvc_timeout = nlm_timeout * HZ;
 
-        grace_period_expire = set_grace_period();
+        set_grace_period();
 
         /*
          * The main request loop. We don't terminate until the last
@@ -153,21 +147,12 @@ lockd(void *vrqstp)
                         flush_signals(current);
                         if (nlmsvc_ops) {
                                 nlmsvc_invalidate_all();
-                                grace_period_expire = set_grace_period();
+                                set_grace_period();
                         }
                         continue;
                 }
 
-                /*
-                 * Retry any blocked locks that have been notified by
-                 * the VFS. Don't do this during grace period.
-                 * (Theoretically, there shouldn't even be blocked locks
-                 * during grace period).
-                 */
-                if (!nlmsvc_grace_period) {
-                        timeout = nlmsvc_retry_blocked();
-                } else if (time_before(grace_period_expire, jiffies))
-                        clear_grace_period();
+                timeout = nlmsvc_retry_blocked();
 
                 /*
                  * Find a socket with data available and call its
@@ -195,6 +180,7 @@ lockd(void *vrqstp)
                 svc_process(rqstp);
         }
         flush_signals(current);
+        cancel_delayed_work_sync(&grace_period_end);
         if (nlmsvc_ops)
                 nlmsvc_invalidate_all();
         nlm_shutdown_hosts();
@@ -203,25 +189,28 @@ lockd(void *vrqstp)
 }
 
 /*
- * Make any sockets that are needed but not present.
- * If nlm_udpport or nlm_tcpport were set as module
- * options, make those sockets unconditionally
+ * Ensure there are active UDP and TCP listeners for lockd.
+ *
+ * Even if we have only TCP NFS mounts and/or TCP NFSDs, some
+ * local services (such as rpc.statd) still require UDP, and
+ * some NFS servers do not yet support NLM over TCP.
+ *
+ * Returns zero if all listeners are available; otherwise a
+ * negative errno value is returned.
  */
-static int make_socks(struct svc_serv *serv, int proto)
+static int make_socks(struct svc_serv *serv)
 {
         static int warned;
         struct svc_xprt *xprt;
         int err = 0;
 
-        if (proto == IPPROTO_UDP || nlm_udpport) {
-                xprt = svc_find_xprt(serv, "udp", 0, 0);
-                if (!xprt)
-                        err = svc_create_xprt(serv, "udp", nlm_udpport,
-                                              SVC_SOCK_DEFAULTS);
-                else
-                        svc_xprt_put(xprt);
-        }
-        if (err >= 0 && (proto == IPPROTO_TCP || nlm_tcpport)) {
+        xprt = svc_find_xprt(serv, "udp", 0, 0);
+        if (!xprt)
+                err = svc_create_xprt(serv, "udp", nlm_udpport,
+                                      SVC_SOCK_DEFAULTS);
+        else
+                svc_xprt_put(xprt);
+        if (err >= 0) {
                 xprt = svc_find_xprt(serv, "tcp", 0, 0);
                 if (!xprt)
                         err = svc_create_xprt(serv, "tcp", nlm_tcpport,
@@ -241,8 +230,7 @@ static int make_socks(struct svc_serv *serv, int proto)
 /*
  * Bring up the lockd process if it's not already up.
  */
-int
-lockd_up(int proto) /* Maybe add a 'family' option when IPv6 is supported ?? */
+int lockd_up(void)
 {
         struct svc_serv *serv;
         int             error = 0;
@@ -251,11 +239,8 @@ lockd_up(int proto) /* Maybe add a 'family' option when IPv6 is supported ?? */
         /*
          * Check whether we're already up and running.
          */
-        if (nlmsvc_rqst) {
-                if (proto)
-                        error = make_socks(nlmsvc_rqst->rq_server, proto);
+        if (nlmsvc_rqst)
                 goto out;
-        }
 
         /*
          * Sanity check: if there's no pid,
@@ -266,13 +251,14 @@ lockd_up(int proto) /* Maybe add a 'family' option when IPv6 is supported ?? */
                         "lockd_up: no pid, %d users??\n", nlmsvc_users);
 
         error = -ENOMEM;
-        serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, NULL);
+        serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, AF_INET, NULL);
         if (!serv) {
                 printk(KERN_WARNING "lockd_up: create service failed\n");
                 goto out;
         }
 
-        if ((error = make_socks(serv, proto)) < 0)
+        error = make_socks(serv);
+        if (error < 0)
                 goto destroy_and_out;
 
         /*
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index 4a714f64515b..014f6ce48172 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -88,12 +88,6 @@ nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp,
         dprintk("lockd: TEST4        called\n");
         resp->cookie = argp->cookie;
 
-        /* Don't accept test requests during grace period */
-        if (nlmsvc_grace_period) {
-                resp->status = nlm_lck_denied_grace_period;
-                return rc;
-        }
-
         /* Obtain client and file */
         if ((resp->status = nlm4svc_retrieve_args(rqstp, argp, &host, &file)))
                 return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
@@ -122,12 +116,6 @@ nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
 
         resp->cookie = argp->cookie;
 
-        /* Don't accept new lock requests during grace period */
-        if (nlmsvc_grace_period && !argp->reclaim) {
-                resp->status = nlm_lck_denied_grace_period;
-                return rc;
-        }
-
         /* Obtain client and file */
         if ((resp->status = nlm4svc_retrieve_args(rqstp, argp, &host, &file)))
                 return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
@@ -146,7 +134,8 @@ nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
 
         /* Now try to lock the file */
         resp->status = nlmsvc_lock(rqstp, file, host, &argp->lock,
-                                        argp->block, &argp->cookie);
+                                        argp->block, &argp->cookie,
+                                        argp->reclaim);
         if (resp->status == nlm_drop_reply)
                 rc = rpc_drop_reply;
         else
@@ -169,7 +158,7 @@ nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp,
         resp->cookie = argp->cookie;
 
         /* Don't accept requests during grace period */
-        if (nlmsvc_grace_period) {
+        if (locks_in_grace()) {
                 resp->status = nlm_lck_denied_grace_period;
                 return rpc_success;
         }
@@ -202,7 +191,7 @@ nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp,
         resp->cookie = argp->cookie;
 
         /* Don't accept new lock requests during grace period */
-        if (nlmsvc_grace_period) {
+        if (locks_in_grace()) {
                 resp->status = nlm_lck_denied_grace_period;
                 return rpc_success;
         }
@@ -231,7 +220,7 @@ nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp,
         resp->cookie = argp->cookie;
 
         dprintk("lockd: GRANTED       called\n");
-        resp->status = nlmclnt_grant(svc_addr_in(rqstp), &argp->lock);
+        resp->status = nlmclnt_grant(svc_addr(rqstp), &argp->lock);
         dprintk("lockd: GRANTED       status %d\n", ntohl(resp->status));
         return rpc_success;
 }
@@ -341,7 +330,7 @@ nlm4svc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp,
         resp->cookie = argp->cookie;
 
         /* Don't accept new lock requests during grace period */
-        if (nlmsvc_grace_period && !argp->reclaim) {
+        if (locks_in_grace() && !argp->reclaim) {
                 resp->status = nlm_lck_denied_grace_period;
                 return rpc_success;
         }
@@ -374,7 +363,7 @@ nlm4svc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp,
         resp->cookie = argp->cookie;
 
         /* Don't accept requests during grace period */
-        if (nlmsvc_grace_period) {
+        if (locks_in_grace()) {
                 resp->status = nlm_lck_denied_grace_period;
                 return rpc_success;
         }
@@ -432,11 +421,9 @@ nlm4svc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
 {
         struct sockaddr_in      saddr;
 
-        memcpy(&saddr, svc_addr_in(rqstp), sizeof(saddr));
-
         dprintk("lockd: SM_NOTIFY     called\n");
-        if (saddr.sin_addr.s_addr != htonl(INADDR_LOOPBACK)
-         || ntohs(saddr.sin_port) >= 1024) {
+
+        if (!nlm_privileged_requester(rqstp)) {
                 char buf[RPC_MAX_ADDRBUFLEN];
                 printk(KERN_WARNING "lockd: rejected NSM callback from %s\n",
                                 svc_print_addr(rqstp, buf, sizeof(buf)));
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index cf0d5c2c318d..6063a8e4b9f3 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -360,7 +360,7 @@ nlmsvc_defer_lock_rqst(struct svc_rqst *rqstp, struct nlm_block *block)
 __be32
 nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
             struct nlm_host *host, struct nlm_lock *lock, int wait,
-            struct nlm_cookie *cookie)
+            struct nlm_cookie *cookie, int reclaim)
 {
         struct nlm_block        *block = NULL;
         int                     error;
@@ -406,6 +406,15 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
                 goto out;
         }
 
+        if (locks_in_grace() && !reclaim) {
+                ret = nlm_lck_denied_grace_period;
+                goto out;
+        }
+        if (reclaim && !locks_in_grace()) {
+                ret = nlm_lck_denied_grace_period;
+                goto out;
+        }
+
         if (!wait)
                 lock->fl.fl_flags &= ~FL_SLEEP;
         error = vfs_lock_file(file->f_file, F_SETLK, &lock->fl, NULL);
@@ -502,6 +511,10 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
                 goto out;
         }
 
+        if (locks_in_grace()) {
+                ret = nlm_lck_denied_grace_period;
+                goto out;
+        }
         error = vfs_test_lock(file->f_file, &lock->fl);
         if (error == FILE_LOCK_DEFERRED) {
                 ret = nlmsvc_defer_lock_rqst(rqstp, block);
@@ -582,6 +595,9 @@ nlmsvc_cancel_blocked(struct nlm_file *file, struct nlm_lock *lock)
                                 (long long)lock->fl.fl_start,
                                 (long long)lock->fl.fl_end);
 
+        if (locks_in_grace())
+                return nlm_lck_denied_grace_period;
+
         mutex_lock(&file->f_mutex);
         block = nlmsvc_lookup_block(file, lock);
         mutex_unlock(&file->f_mutex);
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index 76262c1986f2..548b0bb2b84d 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -117,12 +117,6 @@ nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp,
         dprintk("lockd: TEST          called\n");
         resp->cookie = argp->cookie;
 
-        /* Don't accept test requests during grace period */
-        if (nlmsvc_grace_period) {
-                resp->status = nlm_lck_denied_grace_period;
-                return rc;
-        }
-
         /* Obtain client and file */
         if ((resp->status = nlmsvc_retrieve_args(rqstp, argp, &host, &file)))
                 return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
@@ -152,12 +146,6 @@ nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
 
         resp->cookie = argp->cookie;
 
-        /* Don't accept new lock requests during grace period */
-        if (nlmsvc_grace_period && !argp->reclaim) {
-                resp->status = nlm_lck_denied_grace_period;
-                return rc;
-        }
-
         /* Obtain client and file */
         if ((resp->status = nlmsvc_retrieve_args(rqstp, argp, &host, &file)))
                 return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
@@ -176,7 +164,8 @@ nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
 
         /* Now try to lock the file */
         resp->status = cast_status(nlmsvc_lock(rqstp, file, host, &argp->lock,
-                                               argp->block, &argp->cookie));
+                                               argp->block, &argp->cookie,
+                                               argp->reclaim));
         if (resp->status == nlm_drop_reply)
                 rc = rpc_drop_reply;
         else
@@ -199,7 +188,7 @@ nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp,
         resp->cookie = argp->cookie;
 
         /* Don't accept requests during grace period */
-        if (nlmsvc_grace_period) {
+        if (locks_in_grace()) {
                 resp->status = nlm_lck_denied_grace_period;
                 return rpc_success;
         }
@@ -232,7 +221,7 @@ nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp,
         resp->cookie = argp->cookie;
 
         /* Don't accept new lock requests during grace period */
-        if (nlmsvc_grace_period) {
+        if (locks_in_grace()) {
                 resp->status = nlm_lck_denied_grace_period;
                 return rpc_success;
         }
@@ -261,7 +250,7 @@ nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp,
         resp->cookie = argp->cookie;
 
         dprintk("lockd: GRANTED       called\n");
-        resp->status = nlmclnt_grant(svc_addr_in(rqstp), &argp->lock);
+        resp->status = nlmclnt_grant(svc_addr(rqstp), &argp->lock);
         dprintk("lockd: GRANTED       status %d\n", ntohl(resp->status));
         return rpc_success;
 }
@@ -373,7 +362,7 @@ nlmsvc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp,
         resp->cookie = argp->cookie;
 
         /* Don't accept new lock requests during grace period */
-        if (nlmsvc_grace_period && !argp->reclaim) {
+        if (locks_in_grace() && !argp->reclaim) {
                 resp->status = nlm_lck_denied_grace_period;
                 return rpc_success;
         }
@@ -406,7 +395,7 @@ nlmsvc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp,
         resp->cookie = argp->cookie;
 
         /* Don't accept requests during grace period */
-        if (nlmsvc_grace_period) {
+        if (locks_in_grace()) {
                 resp->status = nlm_lck_denied_grace_period;
                 return rpc_success;
         }
@@ -464,11 +453,9 @@ nlmsvc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
 {
         struct sockaddr_in      saddr;
 
-        memcpy(&saddr, svc_addr_in(rqstp), sizeof(saddr));
-
         dprintk("lockd: SM_NOTIFY     called\n");
-        if (saddr.sin_addr.s_addr != htonl(INADDR_LOOPBACK)
-         || ntohs(saddr.sin_port) >= 1024) {
+
+        if (!nlm_privileged_requester(rqstp)) {
                 char buf[RPC_MAX_ADDRBUFLEN];
                 printk(KERN_WARNING "lockd: rejected NSM callback from %s\n",
                                 svc_print_addr(rqstp, buf, sizeof(buf)));
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index 198b4e55b373..34c2766e27c7 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -418,7 +418,7 @@ EXPORT_SYMBOL_GPL(nlmsvc_unlock_all_by_sb);
 static int
 nlmsvc_match_ip(void *datap, struct nlm_host *host)
 {
-        return nlm_cmp_addr(&host->h_saddr, datap);
+        return nlm_cmp_addr(nlm_srcaddr(host), datap);
 }
 
 /**
diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c
index 3e459e18cc31..1f226290c67c 100644
--- a/fs/lockd/xdr.c
+++ b/fs/lockd/xdr.c
@@ -351,8 +351,6 @@ nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp)
         argp->state = ntohl(*p++);
         /* Preserve the address in network byte order */
         argp->addr = *p++;
-        argp->vers = *p++;
-        argp->proto = *p++;
         return xdr_argsize_check(rqstp, p);
 }
 
diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c
index 43ff9397e6c6..50c493a8ad8e 100644
--- a/fs/lockd/xdr4.c
+++ b/fs/lockd/xdr4.c
@@ -358,8 +358,6 @@ nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp
         argp->state = ntohl(*p++);
         /* Preserve the address in network byte order */
         argp->addr  = *p++;
-        argp->vers  = *p++;
-        argp->proto = *p++;
         return xdr_argsize_check(rqstp, p);
 }
 
diff --git a/fs/mpage.c b/fs/mpage.c
index dbcc7af76a15..552b80b3facc 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -6,7 +6,7 @@
  * Contains functions related to preparing and submitting BIOs which contain
  * multiple pagecache pages.
  *
- * 15May2002    akpm@zip.com.au
+ * 15May2002    Andrew Morton
  *              Initial version
  * 27Jun2002    axboe@suse.de
  *              use bio_add_page() to build bio's just the right size
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index f447f4b4476c..c2e9cfd9e5a4 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -40,6 +40,16 @@ unsigned short nfs_callback_tcpport;
 static const int nfs_set_port_min = 0;
 static const int nfs_set_port_max = 65535;
 
+/*
+ * If the kernel has IPv6 support available, always listen for
+ * both AF_INET and AF_INET6 requests.
+ */
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+static const sa_family_t        nfs_callback_family = AF_INET6;
+#else
+static const sa_family_t        nfs_callback_family = AF_INET;
+#endif
+
 static int param_set_port(const char *val, struct kernel_param *kp)
 {
         char *endp;
@@ -105,7 +115,8 @@ int nfs_callback_up(void)
         mutex_lock(&nfs_callback_mutex);
         if (nfs_callback_info.users++ || nfs_callback_info.task != NULL)
                 goto out;
-        serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, NULL);
+        serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE,
+                                nfs_callback_family, NULL);
         ret = -ENOMEM;
         if (!serv)
                 goto out_err;
@@ -115,7 +126,8 @@ int nfs_callback_up(void)
         if (ret <= 0)
                 goto out_err;
         nfs_callback_tcpport = ret;
-        dprintk("Callback port = 0x%x\n", nfs_callback_tcpport);
+        dprintk("NFS: Callback listener port = %u (af %u)\n",
+                        nfs_callback_tcpport, nfs_callback_family);
 
         nfs_callback_info.rqst = svc_prepare_thread(serv, &serv->sv_pools[0]);
         if (IS_ERR(nfs_callback_info.rqst)) {
@@ -148,8 +160,8 @@ out:
         mutex_unlock(&nfs_callback_mutex);
         return ret;
 out_err:
-        dprintk("Couldn't create callback socket or server thread; err = %d\n",
-                ret);
+        dprintk("NFS: Couldn't create callback socket or server thread; "
+                "err = %d\n", ret);
         nfs_callback_info.users--;
         goto out;
 }
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 5ee23e7058b3..7547600b6174 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -675,7 +675,7 @@ static int nfs_init_server(struct nfs_server *server,
         server->nfs_client = clp;
 
         /* Initialise the client representation from the mount data */
-        server->flags = data->flags & NFS_MOUNT_FLAGMASK;
+        server->flags = data->flags;
 
         if (data->rsize)
                 server->rsize = nfs_block_size(data->rsize, NULL);
@@ -850,7 +850,6 @@ static struct nfs_server *nfs_alloc_server(void)
         INIT_LIST_HEAD(&server->client_link);
         INIT_LIST_HEAD(&server->master_link);
 
-        init_waitqueue_head(&server->active_wq);
         atomic_set(&server->active, 0);
 
         server->io_stats = nfs_alloc_iostats();
@@ -1073,7 +1072,7 @@ static int nfs4_init_server(struct nfs_server *server,
                 goto error;
 
         /* Initialise the client representation from the mount data */
-        server->flags = data->flags & NFS_MOUNT_FLAGMASK;
+        server->flags = data->flags;
         server->caps |= NFS_CAP_ATOMIC_OPEN;
 
         if (data->rsize)
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 74f92b717f78..efdba2e802d7 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -156,6 +156,7 @@ typedef struct {
         decode_dirent_t decode;
         int             plus;
         unsigned long   timestamp;
+        unsigned long   gencount;
         int             timestamp_valid;
 } nfs_readdir_descriptor_t;
 
@@ -177,7 +178,7 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page *page)
         struct file     *file = desc->file;
         struct inode    *inode = file->f_path.dentry->d_inode;
         struct rpc_cred *cred = nfs_file_cred(file);
-        unsigned long   timestamp;
+        unsigned long   timestamp, gencount;
         int             error;
 
         dfprintk(DIRCACHE, "NFS: %s: reading cookie %Lu into page %lu\n",
@@ -186,6 +187,7 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page *page)
 
  again:
         timestamp = jiffies;
+        gencount = nfs_inc_attr_generation_counter();
         error = NFS_PROTO(inode)->readdir(file->f_path.dentry, cred, desc->entry->cookie, page,
                                           NFS_SERVER(inode)->dtsize, desc->plus);
         if (error < 0) {
@@ -199,6 +201,7 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page *page)
                 goto error;
         }
         desc->timestamp = timestamp;
+        desc->gencount = gencount;
         desc->timestamp_valid = 1;
         SetPageUptodate(page);
         /* Ensure consistent page alignment of the data.
@@ -224,9 +227,10 @@ int dir_decode(nfs_readdir_descriptor_t *desc)
         if (IS_ERR(p))
                 return PTR_ERR(p);
         desc->ptr = p;
-        if (desc->timestamp_valid)
+        if (desc->timestamp_valid) {
                 desc->entry->fattr->time_start = desc->timestamp;
-        else
+                desc->entry->fattr->gencount = desc->gencount;
+        } else
                 desc->entry->fattr->valid &= ~NFS_ATTR_FATTR;
         return 0;
 }
@@ -471,7 +475,7 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent,
         struct rpc_cred *cred = nfs_file_cred(file);
         struct page     *page = NULL;
         int             status;
-        unsigned long   timestamp;
+        unsigned long   timestamp, gencount;
 
         dfprintk(DIRCACHE, "NFS: uncached_readdir() searching for cookie %Lu\n",
                         (unsigned long long)*desc->dir_cookie);
@@ -482,6 +486,7 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent,
                 goto out;
         }
         timestamp = jiffies;
+        gencount = nfs_inc_attr_generation_counter();
         status = NFS_PROTO(inode)->readdir(file->f_path.dentry, cred,
                                                 *desc->dir_cookie, page,
                                                 NFS_SERVER(inode)->dtsize,
@@ -490,6 +495,7 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent,
         desc->ptr = kmap(page);         /* matching kunmap in nfs_do_filldir */
         if (status >= 0) {
                 desc->timestamp = timestamp;
+                desc->gencount = gencount;
                 desc->timestamp_valid = 1;
                 if ((status = dir_decode(desc)) == 0)
                         desc->entry->prev_cookie = *desc->dir_cookie;
@@ -655,7 +661,7 @@ static int nfs_fsync_dir(struct file *filp, struct dentry *dentry, int datasync)
  */
 void nfs_force_lookup_revalidate(struct inode *dir)
 {
-        NFS_I(dir)->cache_change_attribute = jiffies;
+        NFS_I(dir)->cache_change_attribute++;
 }
 
 /*
@@ -667,6 +673,8 @@ static int nfs_check_verifier(struct inode *dir, struct dentry *dentry)
 {
         if (IS_ROOT(dentry))
                 return 1;
+        if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONE)
+                return 0;
         if (!nfs_verify_change_attribute(dir, dentry->d_time))
                 return 0;
         /* Revalidate nfsi->cache_change_attribute before we declare a match */
@@ -750,6 +758,8 @@ int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry,
         /* Don't revalidate a negative dentry if we're creating a new file */
         if (nd != NULL && nfs_lookup_check_intent(nd, LOOKUP_CREATE) != 0)
                 return 0;
+        if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG)
+                return 1;
         return !nfs_check_verifier(dir, dentry);
 }
 
@@ -1507,7 +1517,7 @@ static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *sym
         if (!add_to_page_cache(page, dentry->d_inode->i_mapping, 0,
                                                         GFP_KERNEL)) {
                 pagevec_add(&lru_pvec, page);
-                pagevec_lru_add(&lru_pvec);
+                pagevec_lru_add_file(&lru_pvec);
                 SetPageUptodate(page);
                 unlock_page(page);
         } else
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 78460657f5cb..d319b49f8f06 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -188,13 +188,16 @@ static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
         /* origin == SEEK_END => we must revalidate the cached file length */
         if (origin == SEEK_END) {
                 struct inode *inode = filp->f_mapping->host;
+
                 int retval = nfs_revalidate_file_size(inode, filp);
                 if (retval < 0)
                         return (loff_t)retval;
-        }
-        lock_kernel();  /* BKL needed? */
-        loff = generic_file_llseek_unlocked(filp, offset, origin);
-        unlock_kernel();
+
+                spin_lock(&inode->i_lock);
+                loff = generic_file_llseek_unlocked(filp, offset, origin);
+                spin_unlock(&inode->i_lock);
+        } else
+                loff = generic_file_llseek_unlocked(filp, offset, origin);
         return loff;
 }
 
@@ -699,13 +702,6 @@ static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
                         filp->f_path.dentry->d_name.name,
                         fl->fl_type, fl->fl_flags);
 
-        /*
-         * No BSD flocks over NFS allowed.
-         * Note: we could try to fake a POSIX lock request here by
-         * using ((u32) filp | 0x80000000) or some such as the pid.
-         * Not sure whether that would be unique, though, or whether
-         * that would break in other places.
-         */
         if (!(fl->fl_flags & FL_FLOCK))
                 return -ENOLCK;
 
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 52daefa2f521..b9195c02a863 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -305,8 +305,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
                         init_special_inode(inode, inode->i_mode, fattr->rdev);
 
                 nfsi->read_cache_jiffies = fattr->time_start;
-                nfsi->last_updated = now;
-                nfsi->cache_change_attribute = now;
+                nfsi->attr_gencount = fattr->gencount;
                 inode->i_atime = fattr->atime;
                 inode->i_mtime = fattr->mtime;
                 inode->i_ctime = fattr->ctime;
@@ -453,6 +452,7 @@ out_big:
 void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr)
 {
         if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0) {
+                spin_lock(&inode->i_lock);
                 if ((attr->ia_valid & ATTR_MODE) != 0) {
                         int mode = attr->ia_mode & S_IALLUGO;
                         mode |= inode->i_mode & ~S_IALLUGO;
@@ -462,7 +462,6 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr)
                         inode->i_uid = attr->ia_uid;
                 if ((attr->ia_valid & ATTR_GID) != 0)
                         inode->i_gid = attr->ia_gid;
-                spin_lock(&inode->i_lock);
                 NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
                 spin_unlock(&inode->i_lock);
         }
@@ -472,37 +471,6 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr)
         }
 }
 
-static int nfs_wait_schedule(void *word)
-{
-        if (signal_pending(current))
-                return -ERESTARTSYS;
-        schedule();
-        return 0;
-}
-
-/*
- * Wait for the inode to get unlocked.
- */
-static int nfs_wait_on_inode(struct inode *inode)
-{
-        struct nfs_inode *nfsi = NFS_I(inode);
-        int error;
-
-        error = wait_on_bit_lock(&nfsi->flags, NFS_INO_REVALIDATING,
-                                        nfs_wait_schedule, TASK_KILLABLE);
-
-        return error;
-}
-
-static void nfs_wake_up_inode(struct inode *inode)
-{
-        struct nfs_inode *nfsi = NFS_I(inode);
-
-        clear_bit(NFS_INO_REVALIDATING, &nfsi->flags);
-        smp_mb__after_clear_bit();
-        wake_up_bit(&nfsi->flags, NFS_INO_REVALIDATING);
-}
-
 int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 {
         struct inode *inode = dentry->d_inode;
@@ -697,20 +665,15 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
         dfprintk(PAGECACHE, "NFS: revalidating (%s/%Ld)\n",
                 inode->i_sb->s_id, (long long)NFS_FILEID(inode));
 
-        nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE);
         if (is_bad_inode(inode))
-                goto out_nowait;
+                goto out;
         if (NFS_STALE(inode))
-                goto out_nowait;
-
-        status = nfs_wait_on_inode(inode);
-        if (status < 0)
                 goto out;
 
-        status = -ESTALE;
         if (NFS_STALE(inode))
                 goto out;
 
+        nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE);
         status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), &fattr);
         if (status != 0) {
                 dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Ld) getattr failed, error=%d\n",
@@ -724,16 +687,13 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
                 goto out;
         }
 
-        spin_lock(&inode->i_lock);
-        status = nfs_update_inode(inode, &fattr);
+        status = nfs_refresh_inode(inode, &fattr);
         if (status) {
-                spin_unlock(&inode->i_lock);
                 dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Ld) refresh failed, error=%d\n",
                          inode->i_sb->s_id,
                          (long long)NFS_FILEID(inode), status);
                 goto out;
         }
-        spin_unlock(&inode->i_lock);
 
         if (nfsi->cache_validity & NFS_INO_INVALID_ACL)
                 nfs_zap_acl_cache(inode);
@@ -743,9 +703,6 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
                 (long long)NFS_FILEID(inode));
 
  out:
-        nfs_wake_up_inode(inode);
-
- out_nowait:
         return status;
 }
 
@@ -908,9 +865,6 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
                 return -EIO;
         }
 
-        /* Do atomic weak cache consistency updates */
-        nfs_wcc_update_inode(inode, fattr);
-
         if ((fattr->valid & NFS_ATTR_FATTR_V4) != 0 &&
                         nfsi->change_attr != fattr->change_attr)
                 invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
@@ -939,15 +893,81 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
 
         if (invalid != 0)
                 nfsi->cache_validity |= invalid;
-        else
-                nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR
-                                | NFS_INO_INVALID_ATIME
-                                | NFS_INO_REVAL_PAGECACHE);
 
         nfsi->read_cache_jiffies = fattr->time_start;
         return 0;
 }
 
+static int nfs_ctime_need_update(const struct inode *inode, const struct nfs_fattr *fattr)
+{
+        return timespec_compare(&fattr->ctime, &inode->i_ctime) > 0;
+}
+
+static int nfs_size_need_update(const struct inode *inode, const struct nfs_fattr *fattr)
+{
+        return nfs_size_to_loff_t(fattr->size) > i_size_read(inode);
+}
+
+static unsigned long nfs_attr_generation_counter;
+
+static unsigned long nfs_read_attr_generation_counter(void)
+{
+        smp_rmb();
+        return nfs_attr_generation_counter;
+}
+
+unsigned long nfs_inc_attr_generation_counter(void)
+{
+        unsigned long ret;
+        smp_rmb();
+        ret = ++nfs_attr_generation_counter;
+        smp_wmb();
+        return ret;
+}
+
+void nfs_fattr_init(struct nfs_fattr *fattr)
+{
+        fattr->valid = 0;
+        fattr->time_start = jiffies;
+        fattr->gencount = nfs_inc_attr_generation_counter();
+}
+
+/**
+ * nfs_inode_attrs_need_update - check if the inode attributes need updating
+ * @inode - pointer to inode
+ * @fattr - attributes
+ *
+ * Attempt to divine whether or not an RPC call reply carrying stale
+ * attributes got scheduled after another call carrying updated ones.
+ *
+ * To do so, the function first assumes that a more recent ctime means
+ * that the attributes in fattr are newer, however it also attempt to
+ * catch the case where ctime either didn't change, or went backwards
+ * (if someone reset the clock on the server) by looking at whether
+ * or not this RPC call was started after the inode was last updated.
+ * Note also the check for wraparound of 'attr_gencount'
+ *
+ * The function returns 'true' if it thinks the attributes in 'fattr' are
+ * more recent than the ones cached in the inode.
+ *
+ */
+static int nfs_inode_attrs_need_update(const struct inode *inode, const struct nfs_fattr *fattr)
+{
+        const struct nfs_inode *nfsi = NFS_I(inode);
+
+        return ((long)fattr->gencount - (long)nfsi->attr_gencount) > 0 ||
+                nfs_ctime_need_update(inode, fattr) ||
+                nfs_size_need_update(inode, fattr) ||
+                ((long)nfsi->attr_gencount - (long)nfs_read_attr_generation_counter() > 0);
+}
+
+static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr)
+{
+        if (nfs_inode_attrs_need_update(inode, fattr))
+                return nfs_update_inode(inode, fattr);
+        return nfs_check_inode_attributes(inode, fattr);
+}
+
 /**
  * nfs_refresh_inode - try to update the inode attribute cache
  * @inode - pointer to inode
@@ -960,21 +980,28 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
  */
 int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr)
 {
-        struct nfs_inode *nfsi = NFS_I(inode);
         int status;
 
         if ((fattr->valid & NFS_ATTR_FATTR) == 0)
                 return 0;
         spin_lock(&inode->i_lock);
-        if (time_after(fattr->time_start, nfsi->last_updated))
-                status = nfs_update_inode(inode, fattr);
-        else
-                status = nfs_check_inode_attributes(inode, fattr);
-
+        status = nfs_refresh_inode_locked(inode, fattr);
         spin_unlock(&inode->i_lock);
         return status;
 }
 
+static int nfs_post_op_update_inode_locked(struct inode *inode, struct nfs_fattr *fattr)
+{
+        struct nfs_inode *nfsi = NFS_I(inode);
+
+        nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
+        if (S_ISDIR(inode->i_mode))
+                nfsi->cache_validity |= NFS_INO_INVALID_DATA;
+        if ((fattr->valid & NFS_ATTR_FATTR) == 0)
+                return 0;
+        return nfs_refresh_inode_locked(inode, fattr);
+}
+
 /**
  * nfs_post_op_update_inode - try to update the inode attribute cache
  * @inode - pointer to inode
@@ -991,14 +1018,12 @@ int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr)
  */
 int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 {
-        struct nfs_inode *nfsi = NFS_I(inode);
+        int status;
 
         spin_lock(&inode->i_lock);
-        nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
-        if (S_ISDIR(inode->i_mode))
-                nfsi->cache_validity |= NFS_INO_INVALID_DATA;
+        status = nfs_post_op_update_inode_locked(inode, fattr);
         spin_unlock(&inode->i_lock);
-        return nfs_refresh_inode(inode, fattr);
+        return status;
 }
 
 /**
@@ -1014,6 +1039,15 @@ int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr)
  */
 int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr)
 {
+        int status;
+
+        spin_lock(&inode->i_lock);
+        /* Don't do a WCC update if these attributes are already stale */
+        if ((fattr->valid & NFS_ATTR_FATTR) == 0 ||
+                        !nfs_inode_attrs_need_update(inode, fattr)) {
+                fattr->valid &= ~(NFS_ATTR_WCC_V4|NFS_ATTR_WCC);
+                goto out_noforce;
+        }
         if ((fattr->valid & NFS_ATTR_FATTR_V4) != 0 &&
                         (fattr->valid & NFS_ATTR_WCC_V4) == 0) {
                 fattr->pre_change_attr = NFS_I(inode)->change_attr;
@@ -1026,7 +1060,10 @@ int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fa
                 fattr->pre_size = i_size_read(inode);
                 fattr->valid |= NFS_ATTR_WCC;
         }
-        return nfs_post_op_update_inode(inode, fattr);
+out_noforce:
+        status = nfs_post_op_update_inode_locked(inode, fattr);
+        spin_unlock(&inode->i_lock);
+        return status;
 }
 
 /*
@@ -1092,7 +1129,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
                 }
                 /* If ctime has changed we should definitely clear access+acl caches */
                 if (!timespec_equal(&inode->i_ctime, &fattr->ctime))
-                        invalid |= NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
+                        invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
         } else if (nfsi->change_attr != fattr->change_attr) {
                 dprintk("NFS: change_attr change on server for file %s/%ld\n",
                                 inode->i_sb->s_id, inode->i_ino);
@@ -1126,6 +1163,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
             inode->i_gid != fattr->gid)
                 invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
 
+        if (inode->i_nlink != fattr->nlink)
+                invalid |= NFS_INO_INVALID_ATTR;
+
         inode->i_mode = fattr->mode;
         inode->i_nlink = fattr->nlink;
         inode->i_uid = fattr->uid;
@@ -1145,18 +1185,13 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
                 nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
                 nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
                 nfsi->attrtimeo_timestamp = now;
-                nfsi->last_updated = now;
+                nfsi->attr_gencount = nfs_inc_attr_generation_counter();
         } else {
                 if (!time_in_range(now, nfsi->attrtimeo_timestamp, nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) {
                         if ((nfsi->attrtimeo <<= 1) > NFS_MAXATTRTIMEO(inode))
                                 nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode);
                         nfsi->attrtimeo_timestamp = now;
                 }
-                /*
-                 * Avoid jiffy wraparound issues with nfsi->last_updated
-                 */
-                if (!time_in_range(nfsi->last_updated, nfsi->read_cache_jiffies, now))
-                        nfsi->last_updated = nfsi->read_cache_jiffies;
         }
         invalid &= ~NFS_INO_INVALID_ATTR;
         /* Don't invalidate the data if we were to blame */
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 24241fcbb98d..d212ee41caf2 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -153,6 +153,7 @@ extern void nfs4_clear_inode(struct inode *);
 void nfs_zap_acl_cache(struct inode *inode);
 
 /* super.c */
+void nfs_parse_ip_address(char *, size_t, struct sockaddr *, size_t *);
 extern struct file_system_type nfs_xdev_fs_type;
 #ifdef CONFIG_NFS_V4
 extern struct file_system_type nfs4_xdev_fs_type;
@@ -163,8 +164,8 @@ extern struct rpc_stat nfs_rpcstat;
 
 extern int __init register_nfs_fs(void);
 extern void __exit unregister_nfs_fs(void);
-extern void nfs_sb_active(struct nfs_server *server);
-extern void nfs_sb_deactive(struct nfs_server *server);
+extern void nfs_sb_active(struct super_block *sb);
+extern void nfs_sb_deactive(struct super_block *sb);
 
 /* namespace.c */
 extern char *nfs_path(const char *base,
@@ -276,3 +277,23 @@ unsigned int nfs_page_array_len(unsigned int base, size_t len)
                 PAGE_SIZE - 1) >> PAGE_SHIFT;
 }
 
+#define IPV6_SCOPE_DELIMITER    '%'
+
+/*
+ * Set the port number in an address.  Be agnostic about the address
+ * family.
+ */
+static inline void nfs_set_port(struct sockaddr *sap, unsigned short port)
+{
+        struct sockaddr_in *ap = (struct sockaddr_in *)sap;
+        struct sockaddr_in6 *ap6 = (struct sockaddr_in6 *)sap;
+
+        switch (sap->sa_family) {
+        case AF_INET:
+                ap->sin_port = htons(port);
+                break;
+        case AF_INET6:
+                ap6->sin6_port = htons(port);
+                break;
+        }
+}
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index 779d2eb649c5..086a6830d785 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -14,6 +14,7 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/sched.h>
 #include <linux/nfs_fs.h>
+#include "internal.h"
 
 #ifdef RPC_DEBUG
 # define NFSDBG_FACILITY        NFSDBG_MOUNT
@@ -98,7 +99,7 @@ out_call_err:
 
 out_mnt_err:
         dprintk("NFS: MNT server returned result %d\n", result.status);
-        status = -EACCES;
+        status = nfs_stat_to_errno(result.status);
         goto out;
 }
 
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 66df08dd1caf..64a288ee046d 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -105,7 +105,10 @@ static void * nfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
 
         dprintk("--> nfs_follow_mountpoint()\n");
 
-        BUG_ON(IS_ROOT(dentry));
+        err = -ESTALE;
+        if (IS_ROOT(dentry))
+                goto out_err;
+
         dprintk("%s: enter\n", __func__);
         dput(nd->path.dentry);
         nd->path.dentry = dget(dentry);
@@ -189,7 +192,7 @@ static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server,
                                            struct nfs_clone_mount *mountdata)
 {
 #ifdef CONFIG_NFS_V4
-        struct vfsmount *mnt = NULL;
+        struct vfsmount *mnt = ERR_PTR(-EINVAL);
         switch (server->nfs_client->rpc_ops->version) {
                 case 2:
                 case 3:
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 423842f51ac9..cef62557c87d 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -229,6 +229,7 @@ struct posix_acl *nfs3_proc_getacl(struct inode *inode, int type)
 
         dprintk("NFS call getacl\n");
         msg.rpc_proc = &server->client_acl->cl_procinfo[ACLPROC3_GETACL];
+        nfs_fattr_init(&fattr);
         status = rpc_call_sync(server->client_acl, &msg, 0);
         dprintk("NFS reply getacl: %d\n", status);
 
@@ -322,6 +323,7 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 
         dprintk("NFS call setacl\n");
         msg.rpc_proc = &server->client_acl->cl_procinfo[ACLPROC3_SETACL];
+        nfs_fattr_init(&fattr);
         status = rpc_call_sync(server->client_acl, &msg, 0);
         nfs_access_zap_cache(inode);
         nfs_zap_acl_cache(inode);
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 1e750e4574a9..c55be7a7679e 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -699,7 +699,7 @@ nfs3_proc_statfs(struct nfs_server *server, struct nfs_fh *fhandle,
 }
 
 static int
-nfs3_proc_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle,
+do_proc_fsinfo(struct rpc_clnt *client, struct nfs_fh *fhandle,
                  struct nfs_fsinfo *info)
 {
         struct rpc_message msg = {
@@ -711,11 +711,27 @@ nfs3_proc_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle,
 
         dprintk("NFS call  fsinfo\n");
         nfs_fattr_init(info->fattr);
-        status = rpc_call_sync(server->nfs_client->cl_rpcclient, &msg, 0);
+        status = rpc_call_sync(client, &msg, 0);
         dprintk("NFS reply fsinfo: %d\n", status);
         return status;
 }
 
+/*
+ * Bare-bones access to fsinfo: this is for nfs_get_root/nfs_get_sb via
+ * nfs_create_server
+ */
+static int
+nfs3_proc_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle,
+                   struct nfs_fsinfo *info)
+{
+        int     status;
+
+        status = do_proc_fsinfo(server->client, fhandle, info);
+        if (status && server->nfs_client->cl_rpcclient != server->client)
+                status = do_proc_fsinfo(server->nfs_client->cl_rpcclient, fhandle, info);
+        return status;
+}
+
 static int
 nfs3_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
                    struct nfs_pathconf *info)
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index b112857301f7..30befc39b3c6 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -93,21 +93,52 @@ static int nfs4_validate_fspath(const struct vfsmount *mnt_parent,
         return 0;
 }
 
-/*
- * Check if the string represents a "valid" IPv4 address
- */
-static inline int valid_ipaddr4(const char *buf)
+static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
+                                     char *page, char *page2,
+                                     const struct nfs4_fs_location *location)
 {
-        int rc, count, in[4];
-
-        rc = sscanf(buf, "%d.%d.%d.%d", &in[0], &in[1], &in[2], &in[3]);
-        if (rc != 4)
-                return -EINVAL;
-        for (count = 0; count < 4; count++) {
-                if (in[count] > 255)
-                        return -EINVAL;
+        struct vfsmount *mnt = ERR_PTR(-ENOENT);
+        char *mnt_path;
+        int page2len;
+        unsigned int s;
+
+        mnt_path = nfs4_pathname_string(&location->rootpath, page2, PAGE_SIZE);
+        if (IS_ERR(mnt_path))
+                return mnt;
+        mountdata->mnt_path = mnt_path;
+        page2 += strlen(mnt_path) + 1;
+        page2len = PAGE_SIZE - strlen(mnt_path) - 1;
+
+        for (s = 0; s < location->nservers; s++) {
+                const struct nfs4_string *buf = &location->servers[s];
+                struct sockaddr_storage addr;
+
+                if (buf->len <= 0 || buf->len >= PAGE_SIZE)
+                        continue;
+
+                mountdata->addr = (struct sockaddr *)&addr;
+
+                if (memchr(buf->data, IPV6_SCOPE_DELIMITER, buf->len))
+                        continue;
+                nfs_parse_ip_address(buf->data, buf->len,
+                                mountdata->addr, &mountdata->addrlen);
+                if (mountdata->addr->sa_family == AF_UNSPEC)
+                        continue;
+                nfs_set_port(mountdata->addr, NFS_PORT);
+
+                strncpy(page2, buf->data, page2len);
+                page2[page2len] = '\0';
+                mountdata->hostname = page2;
+
+                snprintf(page, PAGE_SIZE, "%s:%s",
+                                mountdata->hostname,
+                                mountdata->mnt_path);
+
+                mnt = vfs_kern_mount(&nfs4_referral_fs_type, 0, page, mountdata);
+                if (!IS_ERR(mnt))
+                        break;
         }
-        return 0;
+        return mnt;
 }
 
 /**
@@ -128,7 +159,6 @@ static struct vfsmount *nfs_follow_referral(const struct vfsmount *mnt_parent,
                 .authflavor = NFS_SB(mnt_parent->mnt_sb)->client->cl_auth->au_flavor,
         };
         char *page = NULL, *page2 = NULL;
-        unsigned int s;
         int loc, error;
 
         if (locations == NULL || locations->nlocations <= 0)
@@ -152,53 +182,16 @@ static struct vfsmount *nfs_follow_referral(const struct vfsmount *mnt_parent,
                 goto out;
         }
 
-        loc = 0;
-        while (loc < locations->nlocations && IS_ERR(mnt)) {
+        for (loc = 0; loc < locations->nlocations; loc++) {
                 const struct nfs4_fs_location *location = &locations->locations[loc];
-                char *mnt_path;
 
                 if (location == NULL || location->nservers <= 0 ||
-                    location->rootpath.ncomponents == 0) {
-                        loc++;
+                    location->rootpath.ncomponents == 0)
                         continue;
-                }
 
-                mnt_path = nfs4_pathname_string(&location->rootpath, page2, PAGE_SIZE);
-                if (IS_ERR(mnt_path)) {
-                        loc++;
-                        continue;
-                }
-                mountdata.mnt_path = mnt_path;
-
-                s = 0;
-                while (s < location->nservers) {
-                        struct sockaddr_in addr = {
-                                .sin_family     = AF_INET,
-                                .sin_port       = htons(NFS_PORT),
-                        };
-
-                        if (location->servers[s].len <= 0 ||
-                            valid_ipaddr4(location->servers[s].data) < 0) {
-                                s++;
-                                continue;
-                        }
-
-                        mountdata.hostname = location->servers[s].data;
-                        addr.sin_addr.s_addr = in_aton(mountdata.hostname),
-                        mountdata.addr = (struct sockaddr *)&addr;
-                        mountdata.addrlen = sizeof(addr);
-
-                        snprintf(page, PAGE_SIZE, "%s:%s",
-                                        mountdata.hostname,
-                                        mountdata.mnt_path);
-
-                        mnt = vfs_kern_mount(&nfs4_referral_fs_type, 0, page, &mountdata);
-                        if (!IS_ERR(mnt)) {
-                                break;
-                        }
-                        s++;
-                }
-                loc++;
+                mnt = try_location(&mountdata, page, page2, location);
+                if (!IS_ERR(mnt))
+                        break;
         }
 
 out:
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index c910413eaeca..83e700a2b0c0 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1659,8 +1659,10 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
                 struct nfs_open_context *ctx;
 
                 ctx = nfs_file_open_context(sattr->ia_file);
-                cred = ctx->cred;
-                state = ctx->state;
+                if (ctx) {
+                        cred = ctx->cred;
+                        state = ctx->state;
+                }
         }
 
         status = nfs4_do_setattr(inode, cred, fattr, sattr, state);
diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c
index 46763d1cd397..8478fc25daee 100644
--- a/fs/nfs/nfsroot.c
+++ b/fs/nfs/nfsroot.c
@@ -127,7 +127,7 @@ enum {
         Opt_err
 };
 
-static match_table_t __initdata tokens = {
+static match_table_t __initconst tokens = {
         {Opt_port, "port=%u"},
         {Opt_rsize, "rsize=%u"},
         {Opt_wsize, "wsize=%u"},
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index 4dbb84df1b68..193465210d7c 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -65,14 +65,20 @@ nfs_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
 
         dprintk("%s: call getattr\n", __func__);
         nfs_fattr_init(fattr);
-        status = rpc_call_sync(server->nfs_client->cl_rpcclient, &msg, 0);
+        status = rpc_call_sync(server->client, &msg, 0);
+        /* Retry with default authentication if different */
+        if (status && server->nfs_client->cl_rpcclient != server->client)
+                status = rpc_call_sync(server->nfs_client->cl_rpcclient, &msg, 0);
         dprintk("%s: reply getattr: %d\n", __func__, status);
         if (status)
                 return status;
         dprintk("%s: call statfs\n", __func__);
         msg.rpc_proc = &nfs_procedures[NFSPROC_STATFS];
         msg.rpc_resp = &fsinfo;
-        status = rpc_call_sync(server->nfs_client->cl_rpcclient, &msg, 0);
+        status = rpc_call_sync(server->client, &msg, 0);
+        /* Retry with default authentication if different */
+        if (status && server->nfs_client->cl_rpcclient != server->client)
+                status = rpc_call_sync(server->nfs_client->cl_rpcclient, &msg, 0);
         dprintk("%s: reply statfs: %d\n", __func__, status);
         if (status)
                 return status;
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index e9b20173fef3..a3b0061dfd45 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -91,6 +91,7 @@ enum {
         /* Mount options that take string arguments */
         Opt_sec, Opt_proto, Opt_mountproto, Opt_mounthost,
         Opt_addr, Opt_mountaddr, Opt_clientaddr,
+        Opt_lookupcache,
 
         /* Special mount options */
         Opt_userspace, Opt_deprecated, Opt_sloppy,
@@ -98,7 +99,7 @@ enum {
         Opt_err
 };
 
-static match_table_t nfs_mount_option_tokens = {
+static const match_table_t nfs_mount_option_tokens = {
         { Opt_userspace, "bg" },
         { Opt_userspace, "fg" },
         { Opt_userspace, "retry=%s" },
@@ -154,6 +155,8 @@ static match_table_t nfs_mount_option_tokens = {
         { Opt_mounthost, "mounthost=%s" },
         { Opt_mountaddr, "mountaddr=%s" },
 
+        { Opt_lookupcache, "lookupcache=%s" },
+
         { Opt_err, NULL }
 };
 
@@ -163,7 +166,7 @@ enum {
         Opt_xprt_err
 };
 
-static match_table_t nfs_xprt_protocol_tokens = {
+static const match_table_t nfs_xprt_protocol_tokens = {
         { Opt_xprt_udp, "udp" },
         { Opt_xprt_tcp, "tcp" },
         { Opt_xprt_rdma, "rdma" },
@@ -180,7 +183,7 @@ enum {
         Opt_sec_err
 };
 
-static match_table_t nfs_secflavor_tokens = {
+static const match_table_t nfs_secflavor_tokens = {
         { Opt_sec_none, "none" },
         { Opt_sec_none, "null" },
         { Opt_sec_sys, "sys" },
@@ -200,6 +203,22 @@ static match_table_t nfs_secflavor_tokens = {
         { Opt_sec_err, NULL }
 };
 
+enum {
+        Opt_lookupcache_all, Opt_lookupcache_positive,
+        Opt_lookupcache_none,
+
+        Opt_lookupcache_err
+};
+
+static match_table_t nfs_lookupcache_tokens = {
+        { Opt_lookupcache_all, "all" },
+        { Opt_lookupcache_positive, "pos" },
+        { Opt_lookupcache_positive, "positive" },
+        { Opt_lookupcache_none, "none" },
+
+        { Opt_lookupcache_err, NULL }
+};
+
 
 static void nfs_umount_begin(struct super_block *);
 static int  nfs_statfs(struct dentry *, struct kstatfs *);
@@ -209,7 +228,6 @@ static int nfs_get_sb(struct file_system_type *, int, const char *, void *, stru
 static int nfs_xdev_get_sb(struct file_system_type *fs_type,
                 int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
 static void nfs_kill_super(struct super_block *);
-static void nfs_put_super(struct super_block *);
 static int nfs_remount(struct super_block *sb, int *flags, char *raw_data);
 
 static struct file_system_type nfs_fs_type = {
@@ -232,7 +250,6 @@ static const struct super_operations nfs_sops = {
         .alloc_inode    = nfs_alloc_inode,
         .destroy_inode  = nfs_destroy_inode,
         .write_inode    = nfs_write_inode,
-        .put_super      = nfs_put_super,
         .statfs         = nfs_statfs,
         .clear_inode    = nfs_clear_inode,
         .umount_begin   = nfs_umount_begin,
@@ -337,26 +354,20 @@ void __exit unregister_nfs_fs(void)
         unregister_filesystem(&nfs_fs_type);
 }
 
-void nfs_sb_active(struct nfs_server *server)
+void nfs_sb_active(struct super_block *sb)
 {
-        atomic_inc(&server->active);
-}
+        struct nfs_server *server = NFS_SB(sb);
 
-void nfs_sb_deactive(struct nfs_server *server)
-{
-        if (atomic_dec_and_test(&server->active))
-                wake_up(&server->active_wq);
+        if (atomic_inc_return(&server->active) == 1)
+                atomic_inc(&sb->s_active);
 }
 
-static void nfs_put_super(struct super_block *sb)
+void nfs_sb_deactive(struct super_block *sb)
 {
         struct nfs_server *server = NFS_SB(sb);
-        /*
-         * Make sure there are no outstanding ops to this server.
-         * If so, wait for them to finish before allowing the
-         * unmount to continue.
-         */
-        wait_event(server->active_wq, atomic_read(&server->active) == 0);
+
+        if (atomic_dec_and_test(&server->active))
+                deactivate_super(sb);
 }
 
 /*
@@ -664,25 +675,6 @@ static void nfs_umount_begin(struct super_block *sb)
 }
 
 /*
- * Set the port number in an address.  Be agnostic about the address family.
- */
-static void nfs_set_port(struct sockaddr *sap, unsigned short port)
-{
-        switch (sap->sa_family) {
-        case AF_INET: {
-                struct sockaddr_in *ap = (struct sockaddr_in *)sap;
-                ap->sin_port = htons(port);
-                break;
-        }
-        case AF_INET6: {
-                struct sockaddr_in6 *ap = (struct sockaddr_in6 *)sap;
-                ap->sin6_port = htons(port);
-                break;
-        }
-        }
-}
-
-/*
  * Sanity-check a server address provided by the mount command.
  *
  * Address family must be initialized, and address must not be
@@ -724,20 +716,22 @@ static void nfs_parse_ipv4_address(char *string, size_t str_len,
         *addr_len = 0;
 }
 
-#define IPV6_SCOPE_DELIMITER    '%'
-
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-static void nfs_parse_ipv6_scope_id(const char *string, const size_t str_len,
-                                    const char *delim,
-                                    struct sockaddr_in6 *sin6)
+static int nfs_parse_ipv6_scope_id(const char *string, const size_t str_len,
+                                   const char *delim,
+                                   struct sockaddr_in6 *sin6)
 {
         char *p;
         size_t len;
 
-        if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL))
-                return ;
+        if ((string + str_len) == delim)
+                return 1;
+
         if (*delim != IPV6_SCOPE_DELIMITER)
-                return;
+                return 0;
+
+        if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL))
+                return 0;
 
         len = (string + str_len) - delim - 1;
         p = kstrndup(delim + 1, len, GFP_KERNEL);
@@ -750,14 +744,20 @@ static void nfs_parse_ipv6_scope_id(const char *string, const size_t str_len,
                         scope_id = dev->ifindex;
                         dev_put(dev);
                 } else {
-                        /* scope_id is set to zero on error */
-                        strict_strtoul(p, 10, &scope_id);
+                        if (strict_strtoul(p, 10, &scope_id) == 0) {
+                                kfree(p);
+                                return 0;
+                        }
                 }
 
                 kfree(p);
+
                 sin6->sin6_scope_id = scope_id;
                 dfprintk(MOUNT, "NFS: IPv6 scope ID = %lu\n", scope_id);
+                return 1;
         }
+
+        return 0;
 }
 
 static void nfs_parse_ipv6_address(char *string, size_t str_len,
@@ -773,9 +773,11 @@ static void nfs_parse_ipv6_address(char *string, size_t str_len,
 
                 sin6->sin6_family = AF_INET6;
                 *addr_len = sizeof(*sin6);
-                if (in6_pton(string, str_len, addr, IPV6_SCOPE_DELIMITER, &delim)) {
-                        nfs_parse_ipv6_scope_id(string, str_len, delim, sin6);
-                        return;
+                if (in6_pton(string, str_len, addr,
+                                        IPV6_SCOPE_DELIMITER, &delim) != 0) {
+                        if (nfs_parse_ipv6_scope_id(string, str_len,
+                                                        delim, sin6) != 0)
+                                return;
                 }
         }
 
@@ -798,7 +800,7 @@ static void nfs_parse_ipv6_address(char *string, size_t str_len,
  * If there is a problem constructing the new sockaddr, set the address
  * family to AF_UNSPEC.
  */
-static void nfs_parse_ip_address(char *string, size_t str_len,
+void nfs_parse_ip_address(char *string, size_t str_len,
                                  struct sockaddr *sap, size_t *addr_len)
 {
         unsigned int i, colons;
@@ -1258,6 +1260,30 @@ static int nfs_parse_mount_options(char *raw,
                                              &mnt->mount_server.addrlen);
                         kfree(string);
                         break;
+                case Opt_lookupcache:
+                        string = match_strdup(args);
+                        if (string == NULL)
+                                goto out_nomem;
+                        token = match_token(string,
+                                        nfs_lookupcache_tokens, args);
+                        kfree(string);
+                        switch (token) {
+                                case Opt_lookupcache_all:
+                                        mnt->flags &= ~(NFS_MOUNT_LOOKUP_CACHE_NONEG|NFS_MOUNT_LOOKUP_CACHE_NONE);
+                                        break;
+                                case Opt_lookupcache_positive:
+                                        mnt->flags &= ~NFS_MOUNT_LOOKUP_CACHE_NONE;
+                                        mnt->flags |= NFS_MOUNT_LOOKUP_CACHE_NONEG;
+                                        break;
+                                case Opt_lookupcache_none:
+                                        mnt->flags |= NFS_MOUNT_LOOKUP_CACHE_NONEG|NFS_MOUNT_LOOKUP_CACHE_NONE;
+                                        break;
+                                default:
+                                        errors++;
+                                        dfprintk(MOUNT, "NFS:   invalid "
+                                                        "lookupcache argument\n");
+                        };
+                        break;
 
                 /*
                  * Special options
@@ -1558,7 +1584,7 @@ static int nfs_validate_mount_data(void *options,
                  * Translate to nfs_parsed_mount_data, which nfs_fill_super
                  * can deal with.
                  */
-                args->flags             = data->flags;
+                args->flags             = data->flags & NFS_MOUNT_FLAGMASK;
                 args->rsize             = data->rsize;
                 args->wsize             = data->wsize;
                 args->timeo             = data->timeo;
@@ -2433,7 +2459,7 @@ static int nfs4_xdev_get_sb(struct file_system_type *fs_type, int flags,
                 compare_super = NULL;
 
         /* Get a superblock - note that we may end up sharing one that already exists */
-        s = sget(&nfs_fs_type, compare_super, nfs_set_super, &sb_mntdata);
+        s = sget(&nfs4_fs_type, compare_super, nfs_set_super, &sb_mntdata);
         if (IS_ERR(s)) {
                 error = PTR_ERR(s);
                 goto out_err_nosb;
@@ -2518,7 +2544,7 @@ static int nfs4_referral_get_sb(struct file_system_type *fs_type, int flags,
                 compare_super = NULL;
 
         /* Get a superblock - note that we may end up sharing one that already exists */
-        s = sget(&nfs_fs_type, compare_super, nfs_set_super, &sb_mntdata);
+        s = sget(&nfs4_fs_type, compare_super, nfs_set_super, &sb_mntdata);
         if (IS_ERR(s)) {
                 error = PTR_ERR(s);
                 goto out_err_nosb;
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index f089e5839d7d..ecc295347775 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -99,7 +99,7 @@ static void nfs_async_unlink_release(void *calldata)
 
         nfs_dec_sillycount(data->dir);
         nfs_free_unlinkdata(data);
-        nfs_sb_deactive(NFS_SB(sb));
+        nfs_sb_deactive(sb);
 }
 
 static const struct rpc_call_ops nfs_unlink_ops = {
@@ -118,6 +118,7 @@ static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct n
                 .rpc_message = &msg,
                 .callback_ops = &nfs_unlink_ops,
                 .callback_data = data,
+                .workqueue = nfsiod_workqueue,
                 .flags = RPC_TASK_ASYNC,
         };
         struct rpc_task *task;
@@ -149,7 +150,7 @@ static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct n
                 nfs_dec_sillycount(dir);
                 return 0;
         }
-        nfs_sb_active(NFS_SERVER(dir));
+        nfs_sb_active(dir->i_sb);
         data->args.fh = NFS_FH(dir);
         nfs_fattr_init(&data->res.dir_attr);
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 3229e217c773..9f9845859fc1 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1427,8 +1427,9 @@ static int nfs_write_mapping(struct address_space *mapping, int how)
                 .bdi = mapping->backing_dev_info,
                 .sync_mode = WB_SYNC_NONE,
                 .nr_to_write = LONG_MAX,
+                .range_start = 0,
+                .range_end = LLONG_MAX,
                 .for_writepages = 1,
-                .range_cyclic = 1,
         };
         int ret;
 
diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c
index 15c6faeec77c..b2786a5f9afe 100644
--- a/fs/nfsd/lockd.c
+++ b/fs/nfsd/lockd.c
@@ -70,7 +70,6 @@ nlm_fclose(struct file *filp)
 static struct nlmsvc_binding    nfsd_nlm_ops = {
         .fopen          = nlm_fopen,            /* open file for locking */
         .fclose         = nlm_fclose,           /* close file */
-        .get_grace_period = get_nfs4_grace_period,
 };
 
 void
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 4d617ea28cfc..9dbd2eb91281 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -63,7 +63,8 @@ nfsd3_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle  *argp,
                 SVCFH_fmt(&argp->fh));
 
         fh_copy(&resp->fh, &argp->fh);
-        nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP);
+        nfserr = fh_verify(rqstp, &resp->fh, 0,
+                        NFSD_MAY_NOP | NFSD_MAY_BYPASS_GSS_ON_ROOT);
         if (nfserr)
                 RETURN_STATUS(nfserr);
 
@@ -530,7 +531,7 @@ nfsd3_proc_fsstat(struct svc_rqst * rqstp, struct nfsd_fhandle    *argp,
         dprintk("nfsd: FSSTAT(3)   %s\n",
                                 SVCFH_fmt(&argp->fh));
 
-        nfserr = nfsd_statfs(rqstp, &argp->fh, &resp->stats);
+        nfserr = nfsd_statfs(rqstp, &argp->fh, &resp->stats, 0);
         fh_put(&argp->fh);
         RETURN_STATUS(nfserr);
 }
@@ -558,7 +559,8 @@ nfsd3_proc_fsinfo(struct svc_rqst * rqstp, struct nfsd_fhandle    *argp,
         resp->f_maxfilesize = ~(u32) 0;
         resp->f_properties = NFS3_FSF_DEFAULT;
 
-        nfserr = fh_verify(rqstp, &argp->fh, 0, NFSD_MAY_NOP);
+        nfserr = fh_verify(rqstp, &argp->fh, 0,
+                        NFSD_MAY_NOP | NFSD_MAY_BYPASS_GSS_ON_ROOT);
 
         /* Check special features of the file system. May request
          * different read/write sizes for file systems known to have
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 702fa577aa6e..094747a1227c 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -225,7 +225,8 @@ encode_cb_recall(struct xdr_stream *xdr, struct nfs4_cb_recall *cb_rec)
 
         RESERVE_SPACE(12+sizeof(cb_rec->cbr_stateid) + len);
         WRITE32(OP_CB_RECALL);
-        WRITEMEM(&cb_rec->cbr_stateid, sizeof(stateid_t));
+        WRITE32(cb_rec->cbr_stateid.si_generation);
+        WRITEMEM(&cb_rec->cbr_stateid.si_opaque, sizeof(stateid_opaque_t));
         WRITE32(cb_rec->cbr_trunc);
         WRITE32(len);
         WRITEMEM(cb_rec->cbr_fhval, len);
@@ -379,6 +380,7 @@ static int do_probe_callback(void *data)
                 .addrsize       = sizeof(addr),
                 .timeout        = &timeparms,
                 .program        = &cb_program,
+                .prognumber     = cb->cb_prog,
                 .version        = nfs_cb_version[1]->number,
                 .authflavor     = RPC_AUTH_UNIX, /* XXX: need AUTH_GSS... */
                 .flags          = (RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_QUIET),
@@ -396,9 +398,6 @@ static int do_probe_callback(void *data)
         addr.sin_port = htons(cb->cb_port);
         addr.sin_addr.s_addr = htonl(cb->cb_addr);
 
-        /* Initialize rpc_stat */
-        memset(args.program->stats, 0, sizeof(struct rpc_stat));
-
         /* Create RPC client */
         client = rpc_create(&args);
         if (IS_ERR(client)) {
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index e5b51ffafc6c..669461e291ae 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -201,10 +201,10 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
         /* Openowner is now set, so sequence id will get bumped.  Now we need
          * these checks before we do any creates: */
         status = nfserr_grace;
-        if (nfs4_in_grace() && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
+        if (locks_in_grace() && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
                 goto out;
         status = nfserr_no_grace;
-        if (!nfs4_in_grace() && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
+        if (!locks_in_grace() && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
                 goto out;
 
         switch (open->op_claim_type) {
@@ -575,7 +575,7 @@ nfsd4_remove(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 {
         __be32 status;
 
-        if (nfs4_in_grace())
+        if (locks_in_grace())
                 return nfserr_grace;
         status = nfsd_unlink(rqstp, &cstate->current_fh, 0,
                              remove->rm_name, remove->rm_namelen);
@@ -596,7 +596,7 @@ nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
         if (!cstate->save_fh.fh_dentry)
                 return status;
-        if (nfs4_in_grace() && !(cstate->save_fh.fh_export->ex_flags
+        if (locks_in_grace() && !(cstate->save_fh.fh_export->ex_flags
                                         & NFSEXP_NOSUBTREECHECK))
                 return nfserr_grace;
         status = nfsd_rename(rqstp, &cstate->save_fh, rename->rn_sname,
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 1578d7a2667e..0cc7ff5d5ab5 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -61,7 +61,6 @@
 static time_t lease_time = 90;     /* default lease time */
 static time_t user_lease_time = 90;
 static time_t boot_time;
-static int in_grace = 1;
 static u32 current_ownerid = 1;
 static u32 current_fileid = 1;
 static u32 current_delegid = 1;
@@ -1640,7 +1639,7 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_sta
                 case NFS4_OPEN_CLAIM_NULL:
                         /* Let's not give out any delegations till everyone's
                          * had the chance to reclaim theirs.... */
-                        if (nfs4_in_grace())
+                        if (locks_in_grace())
                                 goto out;
                         if (!atomic_read(&cb->cb_set) || !sop->so_confirmed)
                                 goto out;
@@ -1816,12 +1815,15 @@ out:
         return status;
 }
 
+struct lock_manager nfsd4_manager = {
+};
+
 static void
-end_grace(void)
+nfsd4_end_grace(void)
 {
         dprintk("NFSD: end of grace period\n");
         nfsd4_recdir_purge_old();
-        in_grace = 0;
+        locks_end_grace(&nfsd4_manager);
 }
 
 static time_t
@@ -1838,8 +1840,8 @@ nfs4_laundromat(void)
         nfs4_lock_state();
 
         dprintk("NFSD: laundromat service - starting\n");
-        if (in_grace)
-                end_grace();
+        if (locks_in_grace())
+                nfsd4_end_grace();
         list_for_each_safe(pos, next, &client_lru) {
                 clp = list_entry(pos, struct nfs4_client, cl_lru);
                 if (time_after((unsigned long)clp->cl_time, (unsigned long)cutoff)) {
@@ -1974,7 +1976,7 @@ check_special_stateids(svc_fh *current_fh, stateid_t *stateid, int flags)
                 return nfserr_bad_stateid;
         else if (ONE_STATEID(stateid) && (flags & RD_STATE))
                 return nfs_ok;
-        else if (nfs4_in_grace()) {
+        else if (locks_in_grace()) {
                 /* Answer in remaining cases depends on existance of
                  * conflicting state; so we must wait out the grace period. */
                 return nfserr_grace;
@@ -1993,7 +1995,7 @@ check_special_stateids(svc_fh *current_fh, stateid_t *stateid, int flags)
 static inline int
 io_during_grace_disallowed(struct inode *inode, int flags)
 {
-        return nfs4_in_grace() && (flags & (RD_STATE | WR_STATE))
+        return locks_in_grace() && (flags & (RD_STATE | WR_STATE))
                 && mandatory_lock(inode);
 }
 
@@ -2693,10 +2695,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
         filp = lock_stp->st_vfs_file;
 
         status = nfserr_grace;
-        if (nfs4_in_grace() && !lock->lk_reclaim)
+        if (locks_in_grace() && !lock->lk_reclaim)
                 goto out;
         status = nfserr_no_grace;
-        if (!nfs4_in_grace() && lock->lk_reclaim)
+        if (!locks_in_grace() && lock->lk_reclaim)
                 goto out;
 
         locks_init_lock(&file_lock);
@@ -2779,7 +2781,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
         int error;
         __be32 status;
 
-        if (nfs4_in_grace())
+        if (locks_in_grace())
                 return nfserr_grace;
 
         if (check_lock_length(lockt->lt_offset, lockt->lt_length))
@@ -3192,9 +3194,9 @@ __nfs4_state_start(void)
         unsigned long grace_time;
 
         boot_time = get_seconds();
-        grace_time = get_nfs_grace_period();
+        grace_time = get_nfs4_grace_period();
         lease_time = user_lease_time;
-        in_grace = 1;
+        locks_start_grace(&nfsd4_manager);
         printk(KERN_INFO "NFSD: starting %ld-second grace period\n",
                grace_time/HZ);
         laundry_wq = create_singlethread_workqueue("nfsd4");
@@ -3213,12 +3215,6 @@ nfs4_state_start(void)
         return;
 }
 
-int
-nfs4_in_grace(void)
-{
-        return in_grace;
-}
-
 time_t
 nfs4_lease_time(void)
 {
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 14ba4d9b2859..afcdf4b76843 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -413,6 +413,18 @@ out_nfserr:
 }
 
 static __be32
+nfsd4_decode_stateid(struct nfsd4_compoundargs *argp, stateid_t *sid)
+{
+        DECODE_HEAD;
+
+        READ_BUF(sizeof(stateid_t));
+        READ32(sid->si_generation);
+        COPYMEM(&sid->si_opaque, sizeof(stateid_opaque_t));
+
+        DECODE_TAIL;
+}
+
+static __be32
 nfsd4_decode_access(struct nfsd4_compoundargs *argp, struct nfsd4_access *access)
 {
         DECODE_HEAD;
@@ -429,10 +441,9 @@ nfsd4_decode_close(struct nfsd4_compoundargs *argp, struct nfsd4_close *close)
         DECODE_HEAD;
 
         close->cl_stateowner = NULL;
-        READ_BUF(4 + sizeof(stateid_t));
+        READ_BUF(4);
         READ32(close->cl_seqid);
-        READ32(close->cl_stateid.si_generation);
-        COPYMEM(&close->cl_stateid.si_opaque, sizeof(stateid_opaque_t));
+        return nfsd4_decode_stateid(argp, &close->cl_stateid);
 
         DECODE_TAIL;
 }
@@ -493,13 +504,7 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create
 static inline __be32
 nfsd4_decode_delegreturn(struct nfsd4_compoundargs *argp, struct nfsd4_delegreturn *dr)
 {
-        DECODE_HEAD;
-
-        READ_BUF(sizeof(stateid_t));
-        READ32(dr->dr_stateid.si_generation);
-        COPYMEM(&dr->dr_stateid.si_opaque, sizeof(stateid_opaque_t));
-
-        DECODE_TAIL;
+        return nfsd4_decode_stateid(argp, &dr->dr_stateid);
 }
 
 static inline __be32
@@ -542,20 +547,22 @@ nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock)
         READ32(lock->lk_is_new);
 
         if (lock->lk_is_new) {
-                READ_BUF(36);
+                READ_BUF(4);
                 READ32(lock->lk_new_open_seqid);
-                READ32(lock->lk_new_open_stateid.si_generation);
-
-                COPYMEM(&lock->lk_new_open_stateid.si_opaque, sizeof(stateid_opaque_t));
+                status = nfsd4_decode_stateid(argp, &lock->lk_new_open_stateid);
+                if (status)
+                        return status;
+                READ_BUF(8 + sizeof(clientid_t));
                 READ32(lock->lk_new_lock_seqid);
                 COPYMEM(&lock->lk_new_clientid, sizeof(clientid_t));
                 READ32(lock->lk_new_owner.len);
                 READ_BUF(lock->lk_new_owner.len);
                 READMEM(lock->lk_new_owner.data, lock->lk_new_owner.len);
         } else {
-                READ_BUF(20);
-                READ32(lock->lk_old_lock_stateid.si_generation);
-                COPYMEM(&lock->lk_old_lock_stateid.si_opaque, sizeof(stateid_opaque_t));
+                status = nfsd4_decode_stateid(argp, &lock->lk_old_lock_stateid);
+                if (status)
+                        return status;
+                READ_BUF(4);
                 READ32(lock->lk_old_lock_seqid);
         }
 
@@ -587,13 +594,15 @@ nfsd4_decode_locku(struct nfsd4_compoundargs *argp, struct nfsd4_locku *locku)
         DECODE_HEAD;
 
         locku->lu_stateowner = NULL;
-        READ_BUF(24 + sizeof(stateid_t));
+        READ_BUF(8);
         READ32(locku->lu_type);
         if ((locku->lu_type < NFS4_READ_LT) || (locku->lu_type > NFS4_WRITEW_LT))
                 goto xdr_error;
         READ32(locku->lu_seqid);
-        READ32(locku->lu_stateid.si_generation);
-        COPYMEM(&locku->lu_stateid.si_opaque, sizeof(stateid_opaque_t));
+        status = nfsd4_decode_stateid(argp, &locku->lu_stateid);
+        if (status)
+                return status;
+        READ_BUF(16);
         READ64(locku->lu_offset);
         READ64(locku->lu_length);
 
@@ -678,8 +687,10 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
                 READ32(open->op_delegate_type);
                 break;
         case NFS4_OPEN_CLAIM_DELEGATE_CUR:
-                READ_BUF(sizeof(stateid_t) + 4);
-                COPYMEM(&open->op_delegate_stateid, sizeof(stateid_t));
+                status = nfsd4_decode_stateid(argp, &open->op_delegate_stateid);
+                if (status)
+                        return status;
+                READ_BUF(4);
                 READ32(open->op_fname.len);
                 READ_BUF(open->op_fname.len);
                 SAVEMEM(open->op_fname.data, open->op_fname.len);
@@ -699,9 +710,10 @@ nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_open_con
         DECODE_HEAD;
                     
         open_conf->oc_stateowner = NULL;
-        READ_BUF(4 + sizeof(stateid_t));
-        READ32(open_conf->oc_req_stateid.si_generation);
-        COPYMEM(&open_conf->oc_req_stateid.si_opaque, sizeof(stateid_opaque_t));
+        status = nfsd4_decode_stateid(argp, &open_conf->oc_req_stateid);
+        if (status)
+                return status;
+        READ_BUF(4);
         READ32(open_conf->oc_seqid);
                                                         
         DECODE_TAIL;
@@ -713,9 +725,10 @@ nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, struct nfsd4_open_d
         DECODE_HEAD;
                     
         open_down->od_stateowner = NULL;
-        READ_BUF(12 + sizeof(stateid_t));
-        READ32(open_down->od_stateid.si_generation);
-        COPYMEM(&open_down->od_stateid.si_opaque, sizeof(stateid_opaque_t));
+        status = nfsd4_decode_stateid(argp, &open_down->od_stateid);
+        if (status)
+                return status;
+        READ_BUF(12);
         READ32(open_down->od_seqid);
         READ32(open_down->od_share_access);
         READ32(open_down->od_share_deny);
@@ -743,9 +756,10 @@ nfsd4_decode_read(struct nfsd4_compoundargs *argp, struct nfsd4_read *read)
 {
         DECODE_HEAD;
 
-        READ_BUF(sizeof(stateid_t) + 12);
-        READ32(read->rd_stateid.si_generation);
-        COPYMEM(&read->rd_stateid.si_opaque, sizeof(stateid_opaque_t));
+        status = nfsd4_decode_stateid(argp, &read->rd_stateid);
+        if (status)
+                return status;
+        READ_BUF(12);
         READ64(read->rd_offset);
         READ32(read->rd_length);
 
@@ -834,15 +848,13 @@ nfsd4_decode_secinfo(struct nfsd4_compoundargs *argp,
 static __be32
 nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, struct nfsd4_setattr *setattr)
 {
-        DECODE_HEAD;
-
-        READ_BUF(sizeof(stateid_t));
-        READ32(setattr->sa_stateid.si_generation);
-        COPYMEM(&setattr->sa_stateid.si_opaque, sizeof(stateid_opaque_t));
-        if ((status = nfsd4_decode_fattr(argp, setattr->sa_bmval, &setattr->sa_iattr, &setattr->sa_acl)))
-                goto out;
+        __be32 status;
 
-        DECODE_TAIL;
+        status = nfsd4_decode_stateid(argp, &setattr->sa_stateid);
+        if (status)
+                return status;
+        return nfsd4_decode_fattr(argp, setattr->sa_bmval,
+                                  &setattr->sa_iattr, &setattr->sa_acl);
 }
 
 static __be32
@@ -927,9 +939,10 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write)
         int len;
         DECODE_HEAD;
 
-        READ_BUF(sizeof(stateid_opaque_t) + 20);
-        READ32(write->wr_stateid.si_generation);
-        COPYMEM(&write->wr_stateid.si_opaque, sizeof(stateid_opaque_t));
+        status = nfsd4_decode_stateid(argp, &write->wr_stateid);
+        if (status)
+                return status;
+        READ_BUF(16);
         READ64(write->wr_offset);
         READ32(write->wr_stable_how);
         if (write->wr_stable_how > 2)
@@ -1183,7 +1196,6 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
  * Header routine to setup seqid operation replay cache
  */
 #define ENCODE_SEQID_OP_HEAD                                    \
-        __be32 *p;                                              \
         __be32 *save;                                           \
                                                                 \
         save = resp->p;
@@ -1950,6 +1962,17 @@ fail:
         return -EINVAL;
 }
 
+static void
+nfsd4_encode_stateid(struct nfsd4_compoundres *resp, stateid_t *sid)
+{
+        ENCODE_HEAD;
+
+        RESERVE_SPACE(sizeof(stateid_t));
+        WRITE32(sid->si_generation);
+        WRITEMEM(&sid->si_opaque, sizeof(stateid_opaque_t));
+        ADJUST_ARGS();
+}
+
 static __be32
 nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_access *access)
 {
@@ -1969,12 +1992,9 @@ nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_c
 {
         ENCODE_SEQID_OP_HEAD;
 
-        if (!nfserr) {
-                RESERVE_SPACE(sizeof(stateid_t));
-                WRITE32(close->cl_stateid.si_generation);
-                WRITEMEM(&close->cl_stateid.si_opaque, sizeof(stateid_opaque_t));
-                ADJUST_ARGS();
-        }
+        if (!nfserr)
+                nfsd4_encode_stateid(resp, &close->cl_stateid);
+
         ENCODE_SEQID_OP_TAIL(close->cl_stateowner);
         return nfserr;
 }
@@ -2074,12 +2094,9 @@ nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lo
 {
         ENCODE_SEQID_OP_HEAD;
 
-        if (!nfserr) {
-                RESERVE_SPACE(4 + sizeof(stateid_t));
-                WRITE32(lock->lk_resp_stateid.si_generation);
-                WRITEMEM(&lock->lk_resp_stateid.si_opaque, sizeof(stateid_opaque_t));
-                ADJUST_ARGS();
-        } else if (nfserr == nfserr_denied)
+        if (!nfserr)
+                nfsd4_encode_stateid(resp, &lock->lk_resp_stateid);
+        else if (nfserr == nfserr_denied)
                 nfsd4_encode_lock_denied(resp, &lock->lk_denied);
 
         ENCODE_SEQID_OP_TAIL(lock->lk_replay_owner);
@@ -2099,13 +2116,9 @@ nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l
 {
         ENCODE_SEQID_OP_HEAD;
 
-        if (!nfserr) {
-                RESERVE_SPACE(sizeof(stateid_t));
-                WRITE32(locku->lu_stateid.si_generation);
-                WRITEMEM(&locku->lu_stateid.si_opaque, sizeof(stateid_opaque_t));
-                ADJUST_ARGS();
-        }
-                                        
+        if (!nfserr)
+                nfsd4_encode_stateid(resp, &locku->lu_stateid);
+
         ENCODE_SEQID_OP_TAIL(locku->lu_stateowner);
         return nfserr;
 }
@@ -2128,14 +2141,14 @@ nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_li
 static __be32
 nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open *open)
 {
+        ENCODE_HEAD;
         ENCODE_SEQID_OP_HEAD;
 
         if (nfserr)
                 goto out;
 
-        RESERVE_SPACE(36 + sizeof(stateid_t));
-        WRITE32(open->op_stateid.si_generation);
-        WRITEMEM(&open->op_stateid.si_opaque, sizeof(stateid_opaque_t));
+        nfsd4_encode_stateid(resp, &open->op_stateid);
+        RESERVE_SPACE(40);
         WRITECINFO(open->op_cinfo);
         WRITE32(open->op_rflags);
         WRITE32(2);
@@ -2148,8 +2161,8 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op
         case NFS4_OPEN_DELEGATE_NONE:
                 break;
         case NFS4_OPEN_DELEGATE_READ:
-                RESERVE_SPACE(20 + sizeof(stateid_t));
-                WRITEMEM(&open->op_delegate_stateid, sizeof(stateid_t));
+                nfsd4_encode_stateid(resp, &open->op_delegate_stateid);
+                RESERVE_SPACE(20);
                 WRITE32(open->op_recall);
 
                 /*
@@ -2162,8 +2175,8 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op
                 ADJUST_ARGS();
                 break;
         case NFS4_OPEN_DELEGATE_WRITE:
-                RESERVE_SPACE(32 + sizeof(stateid_t));
-                WRITEMEM(&open->op_delegate_stateid, sizeof(stateid_t));
+                nfsd4_encode_stateid(resp, &open->op_delegate_stateid);
+                RESERVE_SPACE(32);
                 WRITE32(0);
 
                 /*
@@ -2195,13 +2208,9 @@ static __be32
 nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_confirm *oc)
 {
         ENCODE_SEQID_OP_HEAD;
-                                        
-        if (!nfserr) {
-                RESERVE_SPACE(sizeof(stateid_t));
-                WRITE32(oc->oc_resp_stateid.si_generation);
-                WRITEMEM(&oc->oc_resp_stateid.si_opaque, sizeof(stateid_opaque_t));
-                ADJUST_ARGS();
-        }
+
+        if (!nfserr)
+                nfsd4_encode_stateid(resp, &oc->oc_resp_stateid);
 
         ENCODE_SEQID_OP_TAIL(oc->oc_stateowner);
         return nfserr;
@@ -2211,13 +2220,9 @@ static __be32
 nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_downgrade *od)
 {
         ENCODE_SEQID_OP_HEAD;
-                                        
-        if (!nfserr) {
-                RESERVE_SPACE(sizeof(stateid_t));
-                WRITE32(od->od_stateid.si_generation);
-                WRITEMEM(&od->od_stateid.si_opaque, sizeof(stateid_opaque_t));
-                ADJUST_ARGS();
-        }
+
+        if (!nfserr)
+                nfsd4_encode_stateid(resp, &od->od_stateid);
 
         ENCODE_SEQID_OP_TAIL(od->od_stateowner);
         return nfserr;
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index c53e65f8f3a2..97543df58242 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -614,10 +614,9 @@ static ssize_t __write_ports(struct file *file, char *buf, size_t size)
                         return -EINVAL;
                 err = nfsd_create_serv();
                 if (!err) {
-                        int proto = 0;
-                        err = svc_addsock(nfsd_serv, fd, buf, &proto);
+                        err = svc_addsock(nfsd_serv, fd, buf);
                         if (err >= 0) {
-                                err = lockd_up(proto);
+                                err = lockd_up();
                                 if (err < 0)
                                         svc_sock_names(buf+strlen(buf)+1, nfsd_serv, buf);
                         }
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index ea37c96f0445..cd25d91895a1 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -302,17 +302,27 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access)
         if (error)
                 goto out;
 
-        if (!(access & NFSD_MAY_LOCK)) {
-                /*
-                 * pseudoflavor restrictions are not enforced on NLM,
-                 * which clients virtually always use auth_sys for,
-                 * even while using RPCSEC_GSS for NFS.
-                 */
-                error = check_nfsd_access(exp, rqstp);
-                if (error)
-                        goto out;
-        }
+        /*
+         * pseudoflavor restrictions are not enforced on NLM,
+         * which clients virtually always use auth_sys for,
+         * even while using RPCSEC_GSS for NFS.
+         */
+        if (access & NFSD_MAY_LOCK)
+                goto skip_pseudoflavor_check;
+        /*
+         * Clients may expect to be able to use auth_sys during mount,
+         * even if they use gss for everything else; see section 2.3.2
+         * of rfc 2623.
+         */
+        if (access & NFSD_MAY_BYPASS_GSS_ON_ROOT
+                        && exp->ex_path.dentry == dentry)
+                goto skip_pseudoflavor_check;
+
+        error = check_nfsd_access(exp, rqstp);
+        if (error)
+                goto out;
 
+skip_pseudoflavor_check:
         /* Finally, check access permissions. */
         error = nfsd_permission(rqstp, exp, dentry, access);
 
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 0766f95d236a..5cffeca7acef 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -65,7 +65,8 @@ nfsd_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle  *argp,
         dprintk("nfsd: GETATTR  %s\n", SVCFH_fmt(&argp->fh));
 
         fh_copy(&resp->fh, &argp->fh);
-        nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP);
+        nfserr = fh_verify(rqstp, &resp->fh, 0,
+                        NFSD_MAY_NOP | NFSD_MAY_BYPASS_GSS_ON_ROOT);
         return nfsd_return_attrs(nfserr, resp);
 }
 
@@ -521,7 +522,8 @@ nfsd_proc_statfs(struct svc_rqst * rqstp, struct nfsd_fhandle   *argp,
 
         dprintk("nfsd: STATFS   %s\n", SVCFH_fmt(&argp->fh));
 
-        nfserr = nfsd_statfs(rqstp, &argp->fh, &resp->stats);
+        nfserr = nfsd_statfs(rqstp, &argp->fh, &resp->stats,
+                        NFSD_MAY_BYPASS_GSS_ON_ROOT);
         fh_put(&argp->fh);
         return nfserr;
 }
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 80292ff5e924..59eeb46f82c5 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -229,6 +229,7 @@ int nfsd_create_serv(void)
 
         atomic_set(&nfsd_busy, 0);
         nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize,
+                                      AF_INET,
                                       nfsd_last_thread, nfsd, THIS_MODULE);
         if (nfsd_serv == NULL)
                 err = -ENOMEM;
@@ -243,25 +244,20 @@ static int nfsd_init_socks(int port)
         if (!list_empty(&nfsd_serv->sv_permsocks))
                 return 0;
 
-        error = lockd_up(IPPROTO_UDP);
-        if (error >= 0) {
-                error = svc_create_xprt(nfsd_serv, "udp", port,
+        error = svc_create_xprt(nfsd_serv, "udp", port,
                                         SVC_SOCK_DEFAULTS);
-                if (error < 0)
-                        lockd_down();
-        }
         if (error < 0)
                 return error;
 
-        error = lockd_up(IPPROTO_TCP);
-        if (error >= 0) {
-                error = svc_create_xprt(nfsd_serv, "tcp", port,
+        error = svc_create_xprt(nfsd_serv, "tcp", port,
                                         SVC_SOCK_DEFAULTS);
-                if (error < 0)
-                        lockd_down();
-        }
         if (error < 0)
                 return error;
+
+        error = lockd_up();
+        if (error < 0)
+                return error;
+
         return 0;
 }
 
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 18060bed5267..aa1d0d6489a1 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -83,7 +83,6 @@ struct raparm_hbucket {
         spinlock_t              pb_lock;
 } ____cacheline_aligned_in_smp;
 
-static struct raparms *         raparml;
 #define RAPARM_HASH_BITS        4
 #define RAPARM_HASH_SIZE        (1<<RAPARM_HASH_BITS)
 #define RAPARM_HASH_MASK        (RAPARM_HASH_SIZE-1)
@@ -1866,9 +1865,9 @@ out:
  * N.B. After this call fhp needs an fh_put
  */
 __be32
-nfsd_statfs(struct svc_rqst *rqstp, struct svc_fh *fhp, struct kstatfs *stat)
+nfsd_statfs(struct svc_rqst *rqstp, struct svc_fh *fhp, struct kstatfs *stat, int access)
 {
-        __be32 err = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP);
+        __be32 err = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP | access);
         if (!err && vfs_statfs(fhp->fh_dentry,stat))
                 err = nfserr_io;
         return err;
@@ -1966,11 +1965,20 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
 void
 nfsd_racache_shutdown(void)
 {
-        if (!raparml)
-                return;
+        struct raparms *raparm, *last_raparm;
+        unsigned int i;
+
         dprintk("nfsd: freeing readahead buffers.\n");
-        kfree(raparml);
-        raparml = NULL;
+
+        for (i = 0; i < RAPARM_HASH_SIZE; i++) {
+                raparm = raparm_hash[i].pb_head;
+                while(raparm) {
+                        last_raparm = raparm;
+                        raparm = raparm->p_next;
+                        kfree(last_raparm);
+                }
+                raparm_hash[i].pb_head = NULL;
+        }
 }
 /*
  * Initialize readahead param cache
@@ -1981,35 +1989,38 @@ nfsd_racache_init(int cache_size)
         int     i;
         int     j = 0;
         int     nperbucket;
+        struct raparms **raparm = NULL;
 
 
-        if (raparml)
+        if (raparm_hash[0].pb_head)
                 return 0;
-        if (cache_size < 2*RAPARM_HASH_SIZE)
-                cache_size = 2*RAPARM_HASH_SIZE;
-        raparml = kcalloc(cache_size, sizeof(struct raparms), GFP_KERNEL);
-
-        if (!raparml) {
-                printk(KERN_WARNING
-                        "nfsd: Could not allocate memory read-ahead cache.\n");
-                return -ENOMEM;
-        }
+        nperbucket = DIV_ROUND_UP(cache_size, RAPARM_HASH_SIZE);
+        if (nperbucket < 2)
+                nperbucket = 2;
+        cache_size = nperbucket * RAPARM_HASH_SIZE;
 
         dprintk("nfsd: allocating %d readahead buffers.\n", cache_size);
-        for (i = 0 ; i < RAPARM_HASH_SIZE ; i++) {
-                raparm_hash[i].pb_head = NULL;
+
+        for (i = 0; i < RAPARM_HASH_SIZE; i++) {
                 spin_lock_init(&raparm_hash[i].pb_lock);
-        }
-        nperbucket = DIV_ROUND_UP(cache_size, RAPARM_HASH_SIZE);
-        for (i = 0; i < cache_size - 1; i++) {
-                if (i % nperbucket == 0)
-                        raparm_hash[j++].pb_head = raparml + i;
-                if (i % nperbucket < nperbucket-1)
-                        raparml[i].p_next = raparml + i + 1;
+
+                raparm = &raparm_hash[i].pb_head;
+                for (j = 0; j < nperbucket; j++) {
+                        *raparm = kzalloc(sizeof(struct raparms), GFP_KERNEL);
+                        if (!*raparm)
+                                goto out_nomem;
+                        raparm = &(*raparm)->p_next;
+                }
+                *raparm = NULL;
         }
 
         nfsdstats.ra_size = cache_size;
         return 0;
+
+out_nomem:
+        dprintk("nfsd: kmalloc failed, freeing readahead buffers\n");
+        nfsd_racache_shutdown();
+        return -ENOMEM;
 }
 
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
diff --git a/fs/nls/nls_base.c b/fs/nls/nls_base.c
index 64965e1c21c4..9b0efdad8910 100644
--- a/fs/nls/nls_base.c
+++ b/fs/nls/nls_base.c
@@ -13,9 +13,7 @@
 #include <linux/nls.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
-#ifdef CONFIG_KMOD
 #include <linux/kmod.h>
-#endif
 #include <linux/spinlock.h>
 
 static struct nls_table default_table;
@@ -215,24 +213,7 @@ static struct nls_table *find_nls(char *charset)
 
 struct nls_table *load_nls(char *charset)
 {
-        struct nls_table *nls;
-#ifdef CONFIG_KMOD
-        int ret;
-#endif
-
-        nls = find_nls(charset);
-        if (nls)
-                return nls;
-
-#ifdef CONFIG_KMOD
-        ret = request_module("nls_%s", charset);
-        if (ret != 0) {
-                printk("Unable to load NLS charset %s\n", charset);
-                return NULL;
-        }
-        nls = find_nls(charset);
-#endif
-        return nls;
+        return try_then_request_module(find_nls(charset), "nls_%s", charset);
 }
 
 void unload_nls(struct nls_table *nls)
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index d020866d4232..3140a4429af1 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -439,7 +439,7 @@ static inline int __ntfs_grab_cache_pages(struct address_space *mapping,
                         pages[nr] = *cached_page;
                         page_cache_get(*cached_page);
                         if (unlikely(!pagevec_add(lru_pvec, *cached_page)))
-                                __pagevec_lru_add(lru_pvec);
+                                __pagevec_lru_add_file(lru_pvec);
                         *cached_page = NULL;
                 }
                 index++;
@@ -2084,7 +2084,7 @@ err_out:
                                                 OSYNC_METADATA|OSYNC_DATA);
                 }
         }
-        pagevec_lru_add(&lru_pvec);
+        pagevec_lru_add_file(&lru_pvec);
         ntfs_debug("Done.  Returning %s (written 0x%lx, status %li).",
                         written ? "written" : "status", (unsigned long)written,
                         (long)status);
diff --git a/fs/ocfs2/Makefile b/fs/ocfs2/Makefile
index f6956de56fdb..589dcdfdfe3c 100644
--- a/fs/ocfs2/Makefile
+++ b/fs/ocfs2/Makefile
@@ -34,7 +34,8 @@ ocfs2-objs := \
         symlink.o               \
         sysfile.o               \
         uptodate.o              \
-        ver.o
+        ver.o                   \
+        xattr.o
 
 ocfs2_stackglue-objs := stackglue.o
 ocfs2_stack_o2cb-objs := stack_o2cb.o
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 10bfb466e068..0cc2deb9394c 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -49,6 +49,340 @@
 
 #include "buffer_head_io.h"
 
+
+/*
+ * Operations for a specific extent tree type.
+ *
+ * To implement an on-disk btree (extent tree) type in ocfs2, add
+ * an ocfs2_extent_tree_operations structure and the matching
+ * ocfs2_init_<thingy>_extent_tree() function.  That's pretty much it
+ * for the allocation portion of the extent tree.
+ */
+struct ocfs2_extent_tree_operations {
+        /*
+         * last_eb_blk is the block number of the right most leaf extent
+         * block.  Most on-disk structures containing an extent tree store
+         * this value for fast access.  The ->eo_set_last_eb_blk() and
+         * ->eo_get_last_eb_blk() operations access this value.  They are
+         *  both required.
+         */
+        void (*eo_set_last_eb_blk)(struct ocfs2_extent_tree *et,
+                                   u64 blkno);
+        u64 (*eo_get_last_eb_blk)(struct ocfs2_extent_tree *et);
+
+        /*
+         * The on-disk structure usually keeps track of how many total
+         * clusters are stored in this extent tree.  This function updates
+         * that value.  new_clusters is the delta, and must be
+         * added to the total.  Required.
+         */
+        void (*eo_update_clusters)(struct inode *inode,
+                                   struct ocfs2_extent_tree *et,
+                                   u32 new_clusters);
+
+        /*
+         * If ->eo_insert_check() exists, it is called before rec is
+         * inserted into the extent tree.  It is optional.
+         */
+        int (*eo_insert_check)(struct inode *inode,
+                               struct ocfs2_extent_tree *et,
+                               struct ocfs2_extent_rec *rec);
+        int (*eo_sanity_check)(struct inode *inode, struct ocfs2_extent_tree *et);
+
+        /*
+         * --------------------------------------------------------------
+         * The remaining are internal to ocfs2_extent_tree and don't have
+         * accessor functions
+         */
+
+        /*
+         * ->eo_fill_root_el() takes et->et_object and sets et->et_root_el.
+         * It is required.
+         */
+        void (*eo_fill_root_el)(struct ocfs2_extent_tree *et);
+
+        /*
+         * ->eo_fill_max_leaf_clusters sets et->et_max_leaf_clusters if
+         * it exists.  If it does not, et->et_max_leaf_clusters is set
+         * to 0 (unlimited).  Optional.
+         */
+        void (*eo_fill_max_leaf_clusters)(struct inode *inode,
+                                          struct ocfs2_extent_tree *et);
+};
+
+
+/*
+ * Pre-declare ocfs2_dinode_et_ops so we can use it as a sanity check
+ * in the methods.
+ */
+static u64 ocfs2_dinode_get_last_eb_blk(struct ocfs2_extent_tree *et);
+static void ocfs2_dinode_set_last_eb_blk(struct ocfs2_extent_tree *et,
+                                         u64 blkno);
+static void ocfs2_dinode_update_clusters(struct inode *inode,
+                                         struct ocfs2_extent_tree *et,
+                                         u32 clusters);
+static int ocfs2_dinode_insert_check(struct inode *inode,
+                                     struct ocfs2_extent_tree *et,
+                                     struct ocfs2_extent_rec *rec);
+static int ocfs2_dinode_sanity_check(struct inode *inode,
+                                     struct ocfs2_extent_tree *et);
+static void ocfs2_dinode_fill_root_el(struct ocfs2_extent_tree *et);
+static struct ocfs2_extent_tree_operations ocfs2_dinode_et_ops = {
+        .eo_set_last_eb_blk     = ocfs2_dinode_set_last_eb_blk,
+        .eo_get_last_eb_blk     = ocfs2_dinode_get_last_eb_blk,
+        .eo_update_clusters     = ocfs2_dinode_update_clusters,
+        .eo_insert_check        = ocfs2_dinode_insert_check,
+        .eo_sanity_check        = ocfs2_dinode_sanity_check,
+        .eo_fill_root_el        = ocfs2_dinode_fill_root_el,
+};
+
+static void ocfs2_dinode_set_last_eb_blk(struct ocfs2_extent_tree *et,
+                                         u64 blkno)
+{
+        struct ocfs2_dinode *di = et->et_object;
+
+        BUG_ON(et->et_ops != &ocfs2_dinode_et_ops);
+        di->i_last_eb_blk = cpu_to_le64(blkno);
+}
+
+static u64 ocfs2_dinode_get_last_eb_blk(struct ocfs2_extent_tree *et)
+{
+        struct ocfs2_dinode *di = et->et_object;
+
+        BUG_ON(et->et_ops != &ocfs2_dinode_et_ops);
+        return le64_to_cpu(di->i_last_eb_blk);
+}
+
+static void ocfs2_dinode_update_clusters(struct inode *inode,
+                                         struct ocfs2_extent_tree *et,
+                                         u32 clusters)
+{
+        struct ocfs2_dinode *di = et->et_object;
+
+        le32_add_cpu(&di->i_clusters, clusters);
+        spin_lock(&OCFS2_I(inode)->ip_lock);
+        OCFS2_I(inode)->ip_clusters = le32_to_cpu(di->i_clusters);
+        spin_unlock(&OCFS2_I(inode)->ip_lock);
+}
+
+static int ocfs2_dinode_insert_check(struct inode *inode,
+                                     struct ocfs2_extent_tree *et,
+                                     struct ocfs2_extent_rec *rec)
+{
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+        BUG_ON(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL);
+        mlog_bug_on_msg(!ocfs2_sparse_alloc(osb) &&
+                        (OCFS2_I(inode)->ip_clusters != rec->e_cpos),
+                        "Device %s, asking for sparse allocation: inode %llu, "
+                        "cpos %u, clusters %u\n",
+                        osb->dev_str,
+                        (unsigned long long)OCFS2_I(inode)->ip_blkno,
+                        rec->e_cpos,
+                        OCFS2_I(inode)->ip_clusters);
+
+        return 0;
+}
+
+static int ocfs2_dinode_sanity_check(struct inode *inode,
+                                     struct ocfs2_extent_tree *et)
+{
+        int ret = 0;
+        struct ocfs2_dinode *di;
+
+        BUG_ON(et->et_ops != &ocfs2_dinode_et_ops);
+
+        di = et->et_object;
+        if (!OCFS2_IS_VALID_DINODE(di)) {
+                ret = -EIO;
+                ocfs2_error(inode->i_sb,
+                        "Inode %llu has invalid path root",
+                        (unsigned long long)OCFS2_I(inode)->ip_blkno);
+        }
+
+        return ret;
+}
+
+static void ocfs2_dinode_fill_root_el(struct ocfs2_extent_tree *et)
+{
+        struct ocfs2_dinode *di = et->et_object;
+
+        et->et_root_el = &di->id2.i_list;
+}
+
+
+static void ocfs2_xattr_value_fill_root_el(struct ocfs2_extent_tree *et)
+{
+        struct ocfs2_xattr_value_root *xv = et->et_object;
+
+        et->et_root_el = &xv->xr_list;
+}
+
+static void ocfs2_xattr_value_set_last_eb_blk(struct ocfs2_extent_tree *et,
+                                              u64 blkno)
+{
+        struct ocfs2_xattr_value_root *xv =
+                (struct ocfs2_xattr_value_root *)et->et_object;
+
+        xv->xr_last_eb_blk = cpu_to_le64(blkno);
+}
+
+static u64 ocfs2_xattr_value_get_last_eb_blk(struct ocfs2_extent_tree *et)
+{
+        struct ocfs2_xattr_value_root *xv =
+                (struct ocfs2_xattr_value_root *) et->et_object;
+
+        return le64_to_cpu(xv->xr_last_eb_blk);
+}
+
+static void ocfs2_xattr_value_update_clusters(struct inode *inode,
+                                              struct ocfs2_extent_tree *et,
+                                              u32 clusters)
+{
+        struct ocfs2_xattr_value_root *xv =
+                (struct ocfs2_xattr_value_root *)et->et_object;
+
+        le32_add_cpu(&xv->xr_clusters, clusters);
+}
+
+static struct ocfs2_extent_tree_operations ocfs2_xattr_value_et_ops = {
+        .eo_set_last_eb_blk     = ocfs2_xattr_value_set_last_eb_blk,
+        .eo_get_last_eb_blk     = ocfs2_xattr_value_get_last_eb_blk,
+        .eo_update_clusters     = ocfs2_xattr_value_update_clusters,
+        .eo_fill_root_el        = ocfs2_xattr_value_fill_root_el,
+};
+
+static void ocfs2_xattr_tree_fill_root_el(struct ocfs2_extent_tree *et)
+{
+        struct ocfs2_xattr_block *xb = et->et_object;
+
+        et->et_root_el = &xb->xb_attrs.xb_root.xt_list;
+}
+
+static void ocfs2_xattr_tree_fill_max_leaf_clusters(struct inode *inode,
+                                                    struct ocfs2_extent_tree *et)
+{
+        et->et_max_leaf_clusters =
+                ocfs2_clusters_for_bytes(inode->i_sb,
+                                         OCFS2_MAX_XATTR_TREE_LEAF_SIZE);
+}
+
+static void ocfs2_xattr_tree_set_last_eb_blk(struct ocfs2_extent_tree *et,
+                                             u64 blkno)
+{
+        struct ocfs2_xattr_block *xb = et->et_object;
+        struct ocfs2_xattr_tree_root *xt = &xb->xb_attrs.xb_root;
+
+        xt->xt_last_eb_blk = cpu_to_le64(blkno);
+}
+
+static u64 ocfs2_xattr_tree_get_last_eb_blk(struct ocfs2_extent_tree *et)
+{
+        struct ocfs2_xattr_block *xb = et->et_object;
+        struct ocfs2_xattr_tree_root *xt = &xb->xb_attrs.xb_root;
+
+        return le64_to_cpu(xt->xt_last_eb_blk);
+}
+
+static void ocfs2_xattr_tree_update_clusters(struct inode *inode,
+                                             struct ocfs2_extent_tree *et,
+                                             u32 clusters)
+{
+        struct ocfs2_xattr_block *xb = et->et_object;
+
+        le32_add_cpu(&xb->xb_attrs.xb_root.xt_clusters, clusters);
+}
+
+static struct ocfs2_extent_tree_operations ocfs2_xattr_tree_et_ops = {
+        .eo_set_last_eb_blk     = ocfs2_xattr_tree_set_last_eb_blk,
+        .eo_get_last_eb_blk     = ocfs2_xattr_tree_get_last_eb_blk,
+        .eo_update_clusters     = ocfs2_xattr_tree_update_clusters,
+        .eo_fill_root_el        = ocfs2_xattr_tree_fill_root_el,
+        .eo_fill_max_leaf_clusters = ocfs2_xattr_tree_fill_max_leaf_clusters,
+};
+
+static void __ocfs2_init_extent_tree(struct ocfs2_extent_tree *et,
+                                     struct inode *inode,
+                                     struct buffer_head *bh,
+                                     void *obj,
+                                     struct ocfs2_extent_tree_operations *ops)
+{
+        et->et_ops = ops;
+        et->et_root_bh = bh;
+        if (!obj)
+                obj = (void *)bh->b_data;
+        et->et_object = obj;
+
+        et->et_ops->eo_fill_root_el(et);
+        if (!et->et_ops->eo_fill_max_leaf_clusters)
+                et->et_max_leaf_clusters = 0;
+        else
+                et->et_ops->eo_fill_max_leaf_clusters(inode, et);
+}
+
+void ocfs2_init_dinode_extent_tree(struct ocfs2_extent_tree *et,
+                                   struct inode *inode,
+                                   struct buffer_head *bh)
+{
+        __ocfs2_init_extent_tree(et, inode, bh, NULL, &ocfs2_dinode_et_ops);
+}
+
+void ocfs2_init_xattr_tree_extent_tree(struct ocfs2_extent_tree *et,
+                                       struct inode *inode,
+                                       struct buffer_head *bh)
+{
+        __ocfs2_init_extent_tree(et, inode, bh, NULL,
+                                 &ocfs2_xattr_tree_et_ops);
+}
+
+void ocfs2_init_xattr_value_extent_tree(struct ocfs2_extent_tree *et,
+                                        struct inode *inode,
+                                        struct buffer_head *bh,
+                                        struct ocfs2_xattr_value_root *xv)
+{
+        __ocfs2_init_extent_tree(et, inode, bh, xv,
+                                 &ocfs2_xattr_value_et_ops);
+}
+
+static inline void ocfs2_et_set_last_eb_blk(struct ocfs2_extent_tree *et,
+                                            u64 new_last_eb_blk)
+{
+        et->et_ops->eo_set_last_eb_blk(et, new_last_eb_blk);
+}
+
+static inline u64 ocfs2_et_get_last_eb_blk(struct ocfs2_extent_tree *et)
+{
+        return et->et_ops->eo_get_last_eb_blk(et);
+}
+
+static inline void ocfs2_et_update_clusters(struct inode *inode,
+                                            struct ocfs2_extent_tree *et,
+                                            u32 clusters)
+{
+        et->et_ops->eo_update_clusters(inode, et, clusters);
+}
+
+static inline int ocfs2_et_insert_check(struct inode *inode,
+                                        struct ocfs2_extent_tree *et,
+                                        struct ocfs2_extent_rec *rec)
+{
+        int ret = 0;
+
+        if (et->et_ops->eo_insert_check)
+                ret = et->et_ops->eo_insert_check(inode, et, rec);
+        return ret;
+}
+
+static inline int ocfs2_et_sanity_check(struct inode *inode,
+                                        struct ocfs2_extent_tree *et)
+{
+        int ret = 0;
+
+        if (et->et_ops->eo_sanity_check)
+                ret = et->et_ops->eo_sanity_check(inode, et);
+        return ret;
+}
+
 static void ocfs2_free_truncate_context(struct ocfs2_truncate_context *tc);
 static int ocfs2_cache_extent_block_free(struct ocfs2_cached_dealloc_ctxt *ctxt,
                                          struct ocfs2_extent_block *eb);
@@ -205,17 +539,6 @@ static struct ocfs2_path *ocfs2_new_path(struct buffer_head *root_bh,
 }
 
 /*
- * Allocate and initialize a new path based on a disk inode tree.
- */
-static struct ocfs2_path *ocfs2_new_inode_path(struct buffer_head *di_bh)
-{
-        struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
-        struct ocfs2_extent_list *el = &di->id2.i_list;
-
-        return ocfs2_new_path(di_bh, el);
-}
-
-/*
  * Convenience function to journal all components in a path.
  */
 static int ocfs2_journal_access_path(struct inode *inode, handle_t *handle,
@@ -368,39 +691,35 @@ struct ocfs2_merge_ctxt {
  */
 int ocfs2_num_free_extents(struct ocfs2_super *osb,
                            struct inode *inode,
-                           struct ocfs2_dinode *fe)
+                           struct ocfs2_extent_tree *et)
 {
         int retval;
-        struct ocfs2_extent_list *el;
+        struct ocfs2_extent_list *el = NULL;
         struct ocfs2_extent_block *eb;
         struct buffer_head *eb_bh = NULL;
+        u64 last_eb_blk = 0;
 
         mlog_entry_void();
 
-        if (!OCFS2_IS_VALID_DINODE(fe)) {
-                OCFS2_RO_ON_INVALID_DINODE(inode->i_sb, fe);
-                retval = -EIO;
-                goto bail;
-        }
+        el = et->et_root_el;
+        last_eb_blk = ocfs2_et_get_last_eb_blk(et);
 
-        if (fe->i_last_eb_blk) {
-                retval = ocfs2_read_block(osb, le64_to_cpu(fe->i_last_eb_blk),
-                                          &eb_bh, OCFS2_BH_CACHED, inode);
+        if (last_eb_blk) {
+                retval = ocfs2_read_block(inode, last_eb_blk,
+                                          &eb_bh);
                 if (retval < 0) {
                         mlog_errno(retval);
                         goto bail;
                 }
                 eb = (struct ocfs2_extent_block *) eb_bh->b_data;
                 el = &eb->h_list;
-        } else
-                el = &fe->id2.i_list;
+        }
 
         BUG_ON(el->l_tree_depth != 0);
 
         retval = le16_to_cpu(el->l_count) - le16_to_cpu(el->l_next_free_rec);
 bail:
-        if (eb_bh)
-                brelse(eb_bh);
+        brelse(eb_bh);
 
         mlog_exit(retval);
         return retval;
@@ -486,8 +805,7 @@ static int ocfs2_create_new_meta_bhs(struct ocfs2_super *osb,
 bail:
         if (status < 0) {
                 for(i = 0; i < wanted; i++) {
-                        if (bhs[i])
-                                brelse(bhs[i]);
+                        brelse(bhs[i]);
                         bhs[i] = NULL;
                 }
         }
@@ -531,7 +849,7 @@ static inline u32 ocfs2_sum_rightmost_rec(struct ocfs2_extent_list  *el)
 static int ocfs2_add_branch(struct ocfs2_super *osb,
                             handle_t *handle,
                             struct inode *inode,
-                            struct buffer_head *fe_bh,
+                            struct ocfs2_extent_tree *et,
                             struct buffer_head *eb_bh,
                             struct buffer_head **last_eb_bh,
                             struct ocfs2_alloc_context *meta_ac)
@@ -540,7 +858,6 @@ static int ocfs2_add_branch(struct ocfs2_super *osb,
         u64 next_blkno, new_last_eb_blk;
         struct buffer_head *bh;
         struct buffer_head **new_eb_bhs = NULL;
-        struct ocfs2_dinode *fe;
         struct ocfs2_extent_block *eb;
         struct ocfs2_extent_list  *eb_el;
         struct ocfs2_extent_list  *el;
@@ -550,13 +867,11 @@ static int ocfs2_add_branch(struct ocfs2_super *osb,
 
         BUG_ON(!last_eb_bh || !*last_eb_bh);
 
-        fe = (struct ocfs2_dinode *) fe_bh->b_data;
-
         if (eb_bh) {
                 eb = (struct ocfs2_extent_block *) eb_bh->b_data;
                 el = &eb->h_list;
         } else
-                el = &fe->id2.i_list;
+                el = et->et_root_el;
 
         /* we never add a branch to a leaf. */
         BUG_ON(!el->l_tree_depth);
@@ -646,7 +961,7 @@ static int ocfs2_add_branch(struct ocfs2_super *osb,
                 mlog_errno(status);
                 goto bail;
         }
-        status = ocfs2_journal_access(handle, inode, fe_bh,
+        status = ocfs2_journal_access(handle, inode, et->et_root_bh,
                                       OCFS2_JOURNAL_ACCESS_WRITE);
         if (status < 0) {
                 mlog_errno(status);
@@ -662,7 +977,7 @@ static int ocfs2_add_branch(struct ocfs2_super *osb,
         }
 
         /* Link the new branch into the rest of the tree (el will
-         * either be on the fe, or the extent block passed in. */
+         * either be on the root_bh, or the extent block passed in. */
         i = le16_to_cpu(el->l_next_free_rec);
         el->l_recs[i].e_blkno = cpu_to_le64(next_blkno);
         el->l_recs[i].e_cpos = cpu_to_le32(new_cpos);
@@ -671,7 +986,7 @@ static int ocfs2_add_branch(struct ocfs2_super *osb,
 
         /* fe needs a new last extent block pointer, as does the
          * next_leaf on the previously last-extent-block. */
-        fe->i_last_eb_blk = cpu_to_le64(new_last_eb_blk);
+        ocfs2_et_set_last_eb_blk(et, new_last_eb_blk);
 
         eb = (struct ocfs2_extent_block *) (*last_eb_bh)->b_data;
         eb->h_next_leaf_blk = cpu_to_le64(new_last_eb_blk);
@@ -679,7 +994,7 @@ static int ocfs2_add_branch(struct ocfs2_super *osb,
         status = ocfs2_journal_dirty(handle, *last_eb_bh);
         if (status < 0)
                 mlog_errno(status);
-        status = ocfs2_journal_dirty(handle, fe_bh);
+        status = ocfs2_journal_dirty(handle, et->et_root_bh);
         if (status < 0)
                 mlog_errno(status);
         if (eb_bh) {
@@ -700,8 +1015,7 @@ static int ocfs2_add_branch(struct ocfs2_super *osb,
 bail:
         if (new_eb_bhs) {
                 for (i = 0; i < new_blocks; i++)
-                        if (new_eb_bhs[i])
-                                brelse(new_eb_bhs[i]);
+                        brelse(new_eb_bhs[i]);
                 kfree(new_eb_bhs);
         }
 
@@ -717,16 +1031,15 @@ bail:
 static int ocfs2_shift_tree_depth(struct ocfs2_super *osb,
                                   handle_t *handle,
                                   struct inode *inode,
-                                  struct buffer_head *fe_bh,
+                                  struct ocfs2_extent_tree *et,
                                   struct ocfs2_alloc_context *meta_ac,
                                   struct buffer_head **ret_new_eb_bh)
 {
         int status, i;
         u32 new_clusters;
         struct buffer_head *new_eb_bh = NULL;
-        struct ocfs2_dinode *fe;
         struct ocfs2_extent_block *eb;
-        struct ocfs2_extent_list  *fe_el;
+        struct ocfs2_extent_list  *root_el;
         struct ocfs2_extent_list  *eb_el;
 
         mlog_entry_void();
@@ -746,8 +1059,7 @@ static int ocfs2_shift_tree_depth(struct ocfs2_super *osb,
         }
 
         eb_el = &eb->h_list;
-        fe = (struct ocfs2_dinode *) fe_bh->b_data;
-        fe_el = &fe->id2.i_list;
+        root_el = et->et_root_el;
 
         status = ocfs2_journal_access(handle, inode, new_eb_bh,
                                       OCFS2_JOURNAL_ACCESS_CREATE);
@@ -756,11 +1068,11 @@ static int ocfs2_shift_tree_depth(struct ocfs2_super *osb,
                 goto bail;
         }
 
-        /* copy the fe data into the new extent block */
-        eb_el->l_tree_depth = fe_el->l_tree_depth;
-        eb_el->l_next_free_rec = fe_el->l_next_free_rec;
-        for(i = 0; i < le16_to_cpu(fe_el->l_next_free_rec); i++)
-                eb_el->l_recs[i] = fe_el->l_recs[i];
+        /* copy the root extent list data into the new extent block */
+        eb_el->l_tree_depth = root_el->l_tree_depth;
+        eb_el->l_next_free_rec = root_el->l_next_free_rec;
+        for (i = 0; i < le16_to_cpu(root_el->l_next_free_rec); i++)
+                eb_el->l_recs[i] = root_el->l_recs[i];
 
         status = ocfs2_journal_dirty(handle, new_eb_bh);
         if (status < 0) {
@@ -768,7 +1080,7 @@ static int ocfs2_shift_tree_depth(struct ocfs2_super *osb,
                 goto bail;
         }
 
-        status = ocfs2_journal_access(handle, inode, fe_bh,
+        status = ocfs2_journal_access(handle, inode, et->et_root_bh,
                                       OCFS2_JOURNAL_ACCESS_WRITE);
         if (status < 0) {
                 mlog_errno(status);
@@ -777,21 +1089,21 @@ static int ocfs2_shift_tree_depth(struct ocfs2_super *osb,
 
         new_clusters = ocfs2_sum_rightmost_rec(eb_el);
 
-        /* update fe now */
-        le16_add_cpu(&fe_el->l_tree_depth, 1);
-        fe_el->l_recs[0].e_cpos = 0;
-        fe_el->l_recs[0].e_blkno = eb->h_blkno;
-        fe_el->l_recs[0].e_int_clusters = cpu_to_le32(new_clusters);
-        for(i = 1; i < le16_to_cpu(fe_el->l_next_free_rec); i++)
-                memset(&fe_el->l_recs[i], 0, sizeof(struct ocfs2_extent_rec));
-        fe_el->l_next_free_rec = cpu_to_le16(1);
+        /* update root_bh now */
+        le16_add_cpu(&root_el->l_tree_depth, 1);
+        root_el->l_recs[0].e_cpos = 0;
+        root_el->l_recs[0].e_blkno = eb->h_blkno;
+        root_el->l_recs[0].e_int_clusters = cpu_to_le32(new_clusters);
+        for (i = 1; i < le16_to_cpu(root_el->l_next_free_rec); i++)
+                memset(&root_el->l_recs[i], 0, sizeof(struct ocfs2_extent_rec));
+        root_el->l_next_free_rec = cpu_to_le16(1);
 
         /* If this is our 1st tree depth shift, then last_eb_blk
          * becomes the allocated extent block */
-        if (fe_el->l_tree_depth == cpu_to_le16(1))
-                fe->i_last_eb_blk = eb->h_blkno;
+        if (root_el->l_tree_depth == cpu_to_le16(1))
+                ocfs2_et_set_last_eb_blk(et, le64_to_cpu(eb->h_blkno));
 
-        status = ocfs2_journal_dirty(handle, fe_bh);
+        status = ocfs2_journal_dirty(handle, et->et_root_bh);
         if (status < 0) {
                 mlog_errno(status);
                 goto bail;
@@ -801,8 +1113,7 @@ static int ocfs2_shift_tree_depth(struct ocfs2_super *osb,
         new_eb_bh = NULL;
         status = 0;
 bail:
-        if (new_eb_bh)
-                brelse(new_eb_bh);
+        brelse(new_eb_bh);
 
         mlog_exit(status);
         return status;
@@ -817,22 +1128,21 @@ bail:
  * 1) a lowest extent block is found, then we pass it back in
  *    *lowest_eb_bh and return '0'
  *
- * 2) the search fails to find anything, but the dinode has room. We
+ * 2) the search fails to find anything, but the root_el has room. We
  *    pass NULL back in *lowest_eb_bh, but still return '0'
  *
- * 3) the search fails to find anything AND the dinode is full, in
+ * 3) the search fails to find anything AND the root_el is full, in
  *    which case we return > 0
  *
  * return status < 0 indicates an error.
  */
 static int ocfs2_find_branch_target(struct ocfs2_super *osb,
                                     struct inode *inode,
-                                    struct buffer_head *fe_bh,
+                                    struct ocfs2_extent_tree *et,
                                     struct buffer_head **target_bh)
 {
         int status = 0, i;
         u64 blkno;
-        struct ocfs2_dinode *fe;
         struct ocfs2_extent_block *eb;
         struct ocfs2_extent_list  *el;
         struct buffer_head *bh = NULL;
@@ -842,8 +1152,7 @@ static int ocfs2_find_branch_target(struct ocfs2_super *osb,
 
         *target_bh = NULL;
 
-        fe = (struct ocfs2_dinode *) fe_bh->b_data;
-        el = &fe->id2.i_list;
+        el = et->et_root_el;
 
         while(le16_to_cpu(el->l_tree_depth) > 1) {
                 if (le16_to_cpu(el->l_next_free_rec) == 0) {
@@ -864,13 +1173,10 @@ static int ocfs2_find_branch_target(struct ocfs2_super *osb,
                         goto bail;
                 }
 
-                if (bh) {
-                        brelse(bh);
-                        bh = NULL;
-                }
+                brelse(bh);
+                bh = NULL;
 
-                status = ocfs2_read_block(osb, blkno, &bh, OCFS2_BH_CACHED,
-                                          inode);
+                status = ocfs2_read_block(inode, blkno, &bh);
                 if (status < 0) {
                         mlog_errno(status);
                         goto bail;
@@ -886,8 +1192,7 @@ static int ocfs2_find_branch_target(struct ocfs2_super *osb,
 
                 if (le16_to_cpu(el->l_next_free_rec) <
                     le16_to_cpu(el->l_count)) {
-                        if (lowest_bh)
-                                brelse(lowest_bh);
+                        brelse(lowest_bh);
                         lowest_bh = bh;
                         get_bh(lowest_bh);
                 }
@@ -895,14 +1200,13 @@ static int ocfs2_find_branch_target(struct ocfs2_super *osb,
 
         /* If we didn't find one and the fe doesn't have any room,
          * then return '1' */
-        if (!lowest_bh
-            && (fe->id2.i_list.l_next_free_rec == fe->id2.i_list.l_count))
+        el = et->et_root_el;
+        if (!lowest_bh && (el->l_next_free_rec == el->l_count))
                 status = 1;
 
         *target_bh = lowest_bh;
 bail:
-        if (bh)
-                brelse(bh);
+        brelse(bh);
 
         mlog_exit(status);
         return status;
@@ -919,19 +1223,19 @@ bail:
  * *last_eb_bh will be updated by ocfs2_add_branch().
  */
 static int ocfs2_grow_tree(struct inode *inode, handle_t *handle,
-                           struct buffer_head *di_bh, int *final_depth,
+                           struct ocfs2_extent_tree *et, int *final_depth,
                            struct buffer_head **last_eb_bh,
                            struct ocfs2_alloc_context *meta_ac)
 {
         int ret, shift;
-        struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
-        int depth = le16_to_cpu(di->id2.i_list.l_tree_depth);
+        struct ocfs2_extent_list *el = et->et_root_el;
+        int depth = le16_to_cpu(el->l_tree_depth);
         struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
         struct buffer_head *bh = NULL;
 
         BUG_ON(meta_ac == NULL);
 
-        shift = ocfs2_find_branch_target(osb, inode, di_bh, &bh);
+        shift = ocfs2_find_branch_target(osb, inode, et, &bh);
         if (shift < 0) {
                 ret = shift;
                 mlog_errno(ret);
@@ -948,7 +1252,7 @@ static int ocfs2_grow_tree(struct inode *inode, handle_t *handle,
                 /* ocfs2_shift_tree_depth will return us a buffer with
                  * the new extent block (so we can pass that to
                  * ocfs2_add_branch). */
-                ret = ocfs2_shift_tree_depth(osb, handle, inode, di_bh,
+                ret = ocfs2_shift_tree_depth(osb, handle, inode, et,
                                              meta_ac, &bh);
                 if (ret < 0) {
                         mlog_errno(ret);
@@ -975,7 +1279,7 @@ static int ocfs2_grow_tree(struct inode *inode, handle_t *handle,
         /* call ocfs2_add_branch to add the final part of the tree with
          * the new data. */
         mlog(0, "add branch. bh = %p\n", bh);
-        ret = ocfs2_add_branch(osb, handle, inode, di_bh, bh, last_eb_bh,
+        ret = ocfs2_add_branch(osb, handle, inode, et, bh, last_eb_bh,
                                meta_ac);
         if (ret < 0) {
                 mlog_errno(ret);
@@ -990,15 +1294,6 @@ out:
 }
 
 /*
- * This is only valid for leaf nodes, which are the only ones that can
- * have empty extents anyway.
- */
-static inline int ocfs2_is_empty_extent(struct ocfs2_extent_rec *rec)
-{
-        return !rec->e_leaf_clusters;
-}
-
-/*
  * This function will discard the rightmost extent record.
  */
 static void ocfs2_shift_records_right(struct ocfs2_extent_list *el)
@@ -1245,8 +1540,7 @@ static int __ocfs2_find_path(struct inode *inode,
 
                 brelse(bh);
                 bh = NULL;
-                ret = ocfs2_read_block(OCFS2_SB(inode->i_sb), blkno,
-                                       &bh, OCFS2_BH_CACHED, inode);
+                ret = ocfs2_read_block(inode, blkno, &bh);
                 if (ret) {
                         mlog_errno(ret);
                         goto out;
@@ -2067,11 +2361,11 @@ static int ocfs2_rotate_subtree_left(struct inode *inode, handle_t *handle,
                                      struct ocfs2_path *right_path,
                                      int subtree_index,
                                      struct ocfs2_cached_dealloc_ctxt *dealloc,
-                                     int *deleted)
+                                     int *deleted,
+                                     struct ocfs2_extent_tree *et)
 {
         int ret, i, del_right_subtree = 0, right_has_empty = 0;
-        struct buffer_head *root_bh, *di_bh = path_root_bh(right_path);
-        struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
+        struct buffer_head *root_bh, *et_root_bh = path_root_bh(right_path);
         struct ocfs2_extent_list *right_leaf_el, *left_leaf_el;
         struct ocfs2_extent_block *eb;
 
@@ -2123,7 +2417,7 @@ static int ocfs2_rotate_subtree_left(struct inode *inode, handle_t *handle,
                  * We have to update i_last_eb_blk during the meta
                  * data delete.
                  */
-                ret = ocfs2_journal_access(handle, inode, di_bh,
+                ret = ocfs2_journal_access(handle, inode, et_root_bh,
                                            OCFS2_JOURNAL_ACCESS_WRITE);
                 if (ret) {
                         mlog_errno(ret);
@@ -2198,7 +2492,7 @@ static int ocfs2_rotate_subtree_left(struct inode *inode, handle_t *handle,
                 ocfs2_update_edge_lengths(inode, handle, left_path);
 
                 eb = (struct ocfs2_extent_block *)path_leaf_bh(left_path)->b_data;
-                di->i_last_eb_blk = eb->h_blkno;
+                ocfs2_et_set_last_eb_blk(et, le64_to_cpu(eb->h_blkno));
 
                 /*
                  * Removal of the extent in the left leaf was skipped
@@ -2208,7 +2502,7 @@ static int ocfs2_rotate_subtree_left(struct inode *inode, handle_t *handle,
                 if (right_has_empty)
                         ocfs2_remove_empty_extent(left_leaf_el);
 
-                ret = ocfs2_journal_dirty(handle, di_bh);
+                ret = ocfs2_journal_dirty(handle, et_root_bh);
                 if (ret)
                         mlog_errno(ret);
 
@@ -2331,7 +2625,8 @@ static int __ocfs2_rotate_tree_left(struct inode *inode,
                                     handle_t *handle, int orig_credits,
                                     struct ocfs2_path *path,
                                     struct ocfs2_cached_dealloc_ctxt *dealloc,
-                                    struct ocfs2_path **empty_extent_path)
+                                    struct ocfs2_path **empty_extent_path,
+                                    struct ocfs2_extent_tree *et)
 {
         int ret, subtree_root, deleted;
         u32 right_cpos;
@@ -2404,7 +2699,7 @@ static int __ocfs2_rotate_tree_left(struct inode *inode,
 
                 ret = ocfs2_rotate_subtree_left(inode, handle, left_path,
                                                 right_path, subtree_root,
-                                                dealloc, &deleted);
+                                                dealloc, &deleted, et);
                 if (ret == -EAGAIN) {
                         /*
                          * The rotation has to temporarily stop due to
@@ -2447,29 +2742,20 @@ out:
 }
 
 static int ocfs2_remove_rightmost_path(struct inode *inode, handle_t *handle,
-                                       struct ocfs2_path *path,
-                                       struct ocfs2_cached_dealloc_ctxt *dealloc)
+                                struct ocfs2_path *path,
+                                struct ocfs2_cached_dealloc_ctxt *dealloc,
+                                struct ocfs2_extent_tree *et)
 {
         int ret, subtree_index;
         u32 cpos;
         struct ocfs2_path *left_path = NULL;
-        struct ocfs2_dinode *di;
         struct ocfs2_extent_block *eb;
         struct ocfs2_extent_list *el;
 
-        /*
-         * XXX: This code assumes that the root is an inode, which is
-         * true for now but may change as tree code gets generic.
-         */
-        di = (struct ocfs2_dinode *)path_root_bh(path)->b_data;
-        if (!OCFS2_IS_VALID_DINODE(di)) {
-                ret = -EIO;
-                ocfs2_error(inode->i_sb,
-                            "Inode %llu has invalid path root",
-                            (unsigned long long)OCFS2_I(inode)->ip_blkno);
-                goto out;
-        }
 
+        ret = ocfs2_et_sanity_check(inode, et);
+        if (ret)
+                goto out;
         /*
          * There's two ways we handle this depending on
          * whether path is the only existing one.
@@ -2526,7 +2812,7 @@ static int ocfs2_remove_rightmost_path(struct inode *inode, handle_t *handle,
                 ocfs2_update_edge_lengths(inode, handle, left_path);
 
                 eb = (struct ocfs2_extent_block *)path_leaf_bh(left_path)->b_data;
-                di->i_last_eb_blk = eb->h_blkno;
+                ocfs2_et_set_last_eb_blk(et, le64_to_cpu(eb->h_blkno));
         } else {
                 /*
                  * 'path' is also the leftmost path which
@@ -2537,12 +2823,12 @@ static int ocfs2_remove_rightmost_path(struct inode *inode, handle_t *handle,
                  */
                 ocfs2_unlink_path(inode, handle, dealloc, path, 1);
 
-                el = &di->id2.i_list;
+                el = et->et_root_el;
                 el->l_tree_depth = 0;
                 el->l_next_free_rec = 0;
                 memset(&el->l_recs[0], 0, sizeof(struct ocfs2_extent_rec));
 
-                di->i_last_eb_blk = 0;
+                ocfs2_et_set_last_eb_blk(et, 0);
         }
 
         ocfs2_journal_dirty(handle, path_root_bh(path));
@@ -2570,7 +2856,8 @@ out:
  */
 static int ocfs2_rotate_tree_left(struct inode *inode, handle_t *handle,
                                   struct ocfs2_path *path,
-                                  struct ocfs2_cached_dealloc_ctxt *dealloc)
+                                  struct ocfs2_cached_dealloc_ctxt *dealloc,
+                                  struct ocfs2_extent_tree *et)
 {
         int ret, orig_credits = handle->h_buffer_credits;
         struct ocfs2_path *tmp_path = NULL, *restart_path = NULL;
@@ -2584,7 +2871,7 @@ static int ocfs2_rotate_tree_left(struct inode *inode, handle_t *handle,
         if (path->p_tree_depth == 0) {
 rightmost_no_delete:
                 /*
-                 * In-inode extents. This is trivially handled, so do
+                 * Inline extents. This is trivially handled, so do
                  * it up front.
                  */
                 ret = ocfs2_rotate_rightmost_leaf_left(inode, handle,
@@ -2638,7 +2925,7 @@ rightmost_no_delete:
                  */
 
                 ret = ocfs2_remove_rightmost_path(inode, handle, path,
-                                                  dealloc);
+                                                  dealloc, et);
                 if (ret)
                         mlog_errno(ret);
                 goto out;
@@ -2650,7 +2937,7 @@ rightmost_no_delete:
          */
 try_rotate:
         ret = __ocfs2_rotate_tree_left(inode, handle, orig_credits, path,
-                                       dealloc, &restart_path);
+                                       dealloc, &restart_path, et);
         if (ret && ret != -EAGAIN) {
                 mlog_errno(ret);
                 goto out;
@@ -2662,7 +2949,7 @@ try_rotate:
 
                 ret = __ocfs2_rotate_tree_left(inode, handle, orig_credits,
                                                tmp_path, dealloc,
-                                               &restart_path);
+                                               &restart_path, et);
                 if (ret && ret != -EAGAIN) {
                         mlog_errno(ret);
                         goto out;
@@ -2948,6 +3235,7 @@ static int ocfs2_merge_rec_left(struct inode *inode,
                                 handle_t *handle,
                                 struct ocfs2_extent_rec *split_rec,
                                 struct ocfs2_cached_dealloc_ctxt *dealloc,
+                                struct ocfs2_extent_tree *et,
                                 int index)
 {
         int ret, i, subtree_index = 0, has_empty_extent = 0;
@@ -3068,7 +3356,8 @@ static int ocfs2_merge_rec_left(struct inode *inode,
                     le16_to_cpu(el->l_next_free_rec) == 1) {
 
                         ret = ocfs2_remove_rightmost_path(inode, handle,
-                                                          right_path, dealloc);
+                                                          right_path,
+                                                          dealloc, et);
                         if (ret) {
                                 mlog_errno(ret);
                                 goto out;
@@ -3095,7 +3384,8 @@ static int ocfs2_try_to_merge_extent(struct inode *inode,
                                      int split_index,
                                      struct ocfs2_extent_rec *split_rec,
                                      struct ocfs2_cached_dealloc_ctxt *dealloc,
-                                     struct ocfs2_merge_ctxt *ctxt)
+                                     struct ocfs2_merge_ctxt *ctxt,
+                                     struct ocfs2_extent_tree *et)
 
 {
         int ret = 0;
@@ -3113,7 +3403,7 @@ static int ocfs2_try_to_merge_extent(struct inode *inode,
                  * illegal.
                  */
                 ret = ocfs2_rotate_tree_left(inode, handle, path,
-                                             dealloc);
+                                             dealloc, et);
                 if (ret) {
                         mlog_errno(ret);
                         goto out;
@@ -3156,7 +3446,8 @@ static int ocfs2_try_to_merge_extent(struct inode *inode,
                 BUG_ON(!ocfs2_is_empty_extent(&el->l_recs[0]));
 
                 /* The merge left us with an empty extent, remove it. */
-                ret = ocfs2_rotate_tree_left(inode, handle, path, dealloc);
+                ret = ocfs2_rotate_tree_left(inode, handle, path,
+                                             dealloc, et);
                 if (ret) {
                         mlog_errno(ret);
                         goto out;
@@ -3170,7 +3461,7 @@ static int ocfs2_try_to_merge_extent(struct inode *inode,
                  */
                 ret = ocfs2_merge_rec_left(inode, path,
                                            handle, rec,
-                                           dealloc,
+                                           dealloc, et,
                                            split_index);
 
                 if (ret) {
@@ -3179,7 +3470,7 @@ static int ocfs2_try_to_merge_extent(struct inode *inode,
                 }
 
                 ret = ocfs2_rotate_tree_left(inode, handle, path,
-                                             dealloc);
+                                             dealloc, et);
                 /*
                  * Error from this last rotate is not critical, so
                  * print but don't bubble it up.
@@ -3199,7 +3490,7 @@ static int ocfs2_try_to_merge_extent(struct inode *inode,
                         ret = ocfs2_merge_rec_left(inode,
                                                    path,
                                                    handle, split_rec,
-                                                   dealloc,
+                                                   dealloc, et,
                                                    split_index);
                         if (ret) {
                                 mlog_errno(ret);
@@ -3222,7 +3513,7 @@ static int ocfs2_try_to_merge_extent(struct inode *inode,
                          * our leaf. Try to rotate it away.
                          */
                         ret = ocfs2_rotate_tree_left(inode, handle, path,
-                                                     dealloc);
+                                                     dealloc, et);
                         if (ret)
                                 mlog_errno(ret);
                         ret = 0;
@@ -3356,16 +3647,6 @@ rotate:
         ocfs2_rotate_leaf(el, insert_rec);
 }
 
-static inline void ocfs2_update_dinode_clusters(struct inode *inode,
-                                                struct ocfs2_dinode *di,
-                                                u32 clusters)
-{
-        le32_add_cpu(&di->i_clusters, clusters);
-        spin_lock(&OCFS2_I(inode)->ip_lock);
-        OCFS2_I(inode)->ip_clusters = le32_to_cpu(di->i_clusters);
-        spin_unlock(&OCFS2_I(inode)->ip_lock);
-}
-
 static void ocfs2_adjust_rightmost_records(struct inode *inode,
                                            handle_t *handle,
                                            struct ocfs2_path *path,
@@ -3567,8 +3848,8 @@ static void ocfs2_split_record(struct inode *inode,
 }
 
 /*
- * This function only does inserts on an allocation b-tree. For dinode
- * lists, ocfs2_insert_at_leaf() is called directly.
+ * This function only does inserts on an allocation b-tree. For tree
+ * depth = 0, ocfs2_insert_at_leaf() is called directly.
  *
  * right_path is the path we want to do the actual insert
  * in. left_path should only be passed in if we need to update that
@@ -3665,7 +3946,7 @@ out:
 
 static int ocfs2_do_insert_extent(struct inode *inode,
                                   handle_t *handle,
-                                  struct buffer_head *di_bh,
+                                  struct ocfs2_extent_tree *et,
                                   struct ocfs2_extent_rec *insert_rec,
                                   struct ocfs2_insert_type *type)
 {
@@ -3673,13 +3954,11 @@ static int ocfs2_do_insert_extent(struct inode *inode,
         u32 cpos;
         struct ocfs2_path *right_path = NULL;
         struct ocfs2_path *left_path = NULL;
-        struct ocfs2_dinode *di;
         struct ocfs2_extent_list *el;
 
-        di = (struct ocfs2_dinode *) di_bh->b_data;
-        el = &di->id2.i_list;
+        el = et->et_root_el;
 
-        ret = ocfs2_journal_access(handle, inode, di_bh,
+        ret = ocfs2_journal_access(handle, inode, et->et_root_bh,
                                    OCFS2_JOURNAL_ACCESS_WRITE);
         if (ret) {
                 mlog_errno(ret);
@@ -3691,7 +3970,7 @@ static int ocfs2_do_insert_extent(struct inode *inode,
                 goto out_update_clusters;
         }
 
-        right_path = ocfs2_new_inode_path(di_bh);
+        right_path = ocfs2_new_path(et->et_root_bh, et->et_root_el);
         if (!right_path) {
                 ret = -ENOMEM;
                 mlog_errno(ret);
@@ -3741,7 +4020,7 @@ static int ocfs2_do_insert_extent(struct inode *inode,
                  * ocfs2_rotate_tree_right() might have extended the
                  * transaction without re-journaling our tree root.
                  */
-                ret = ocfs2_journal_access(handle, inode, di_bh,
+                ret = ocfs2_journal_access(handle, inode, et->et_root_bh,
                                            OCFS2_JOURNAL_ACCESS_WRITE);
                 if (ret) {
                         mlog_errno(ret);
@@ -3766,10 +4045,10 @@ static int ocfs2_do_insert_extent(struct inode *inode,
 
 out_update_clusters:
         if (type->ins_split == SPLIT_NONE)
-                ocfs2_update_dinode_clusters(inode, di,
-                                             le16_to_cpu(insert_rec->e_leaf_clusters));
+                ocfs2_et_update_clusters(inode, et,
+                                         le16_to_cpu(insert_rec->e_leaf_clusters));
 
-        ret = ocfs2_journal_dirty(handle, di_bh);
+        ret = ocfs2_journal_dirty(handle, et->et_root_bh);
         if (ret)
                 mlog_errno(ret);
 
@@ -3899,7 +4178,8 @@ out:
 static void ocfs2_figure_contig_type(struct inode *inode,
                                      struct ocfs2_insert_type *insert,
                                      struct ocfs2_extent_list *el,
-                                     struct ocfs2_extent_rec *insert_rec)
+                                     struct ocfs2_extent_rec *insert_rec,
+                                     struct ocfs2_extent_tree *et)
 {
         int i;
         enum ocfs2_contig_type contig_type = CONTIG_NONE;
@@ -3915,6 +4195,21 @@ static void ocfs2_figure_contig_type(struct inode *inode,
                 }
         }
         insert->ins_contig = contig_type;
+
+        if (insert->ins_contig != CONTIG_NONE) {
+                struct ocfs2_extent_rec *rec =
+                                &el->l_recs[insert->ins_contig_index];
+                unsigned int len = le16_to_cpu(rec->e_leaf_clusters) +
+                                   le16_to_cpu(insert_rec->e_leaf_clusters);
+
+                /*
+                 * Caller might want us to limit the size of extents, don't
+                 * calculate contiguousness if we might exceed that limit.
+                 */
+                if (et->et_max_leaf_clusters &&
+                    (len > et->et_max_leaf_clusters))
+                        insert->ins_contig = CONTIG_NONE;
+        }
 }
 
 /*
@@ -3923,8 +4218,8 @@ static void ocfs2_figure_contig_type(struct inode *inode,
  * ocfs2_figure_appending_type() will figure out whether we'll have to
  * insert at the tail of the rightmost leaf.
  *
- * This should also work against the dinode list for tree's with 0
- * depth. If we consider the dinode list to be the rightmost leaf node
+ * This should also work against the root extent list for tree's with 0
+ * depth. If we consider the root extent list to be the rightmost leaf node
  * then the logic here makes sense.
  */
 static void ocfs2_figure_appending_type(struct ocfs2_insert_type *insert,
@@ -3975,14 +4270,13 @@ set_tail_append:
  * structure.
  */
 static int ocfs2_figure_insert_type(struct inode *inode,
-                                    struct buffer_head *di_bh,
+                                    struct ocfs2_extent_tree *et,
                                     struct buffer_head **last_eb_bh,
                                     struct ocfs2_extent_rec *insert_rec,
                                     int *free_records,
                                     struct ocfs2_insert_type *insert)
 {
         int ret;
-        struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
         struct ocfs2_extent_block *eb;
         struct ocfs2_extent_list *el;
         struct ocfs2_path *path = NULL;
@@ -3990,7 +4284,7 @@ static int ocfs2_figure_insert_type(struct inode *inode,
 
         insert->ins_split = SPLIT_NONE;
 
-        el = &di->id2.i_list;
+        el = et->et_root_el;
         insert->ins_tree_depth = le16_to_cpu(el->l_tree_depth);
 
         if (el->l_tree_depth) {
@@ -4000,9 +4294,7 @@ static int ocfs2_figure_insert_type(struct inode *inode,
                  * ocfs2_figure_insert_type() and ocfs2_add_branch()
                  * may want it later.
                  */
-                ret = ocfs2_read_block(OCFS2_SB(inode->i_sb),
-                                       le64_to_cpu(di->i_last_eb_blk), &bh,
-                                       OCFS2_BH_CACHED, inode);
+                ret = ocfs2_read_block(inode, ocfs2_et_get_last_eb_blk(et), &bh);
                 if (ret) {
                         mlog_exit(ret);
                         goto out;
@@ -4023,12 +4315,12 @@ static int ocfs2_figure_insert_type(struct inode *inode,
                 le16_to_cpu(el->l_next_free_rec);
 
         if (!insert->ins_tree_depth) {
-                ocfs2_figure_contig_type(inode, insert, el, insert_rec);
+                ocfs2_figure_contig_type(inode, insert, el, insert_rec, et);
                 ocfs2_figure_appending_type(insert, el, insert_rec);
                 return 0;
         }
 
-        path = ocfs2_new_inode_path(di_bh);
+        path = ocfs2_new_path(et->et_root_bh, et->et_root_el);
         if (!path) {
                 ret = -ENOMEM;
                 mlog_errno(ret);
@@ -4057,7 +4349,7 @@ static int ocfs2_figure_insert_type(struct inode *inode,
          *     into two types of appends: simple record append, or a
          *     rotate inside the tail leaf.
          */
-        ocfs2_figure_contig_type(inode, insert, el, insert_rec);
+        ocfs2_figure_contig_type(inode, insert, el, insert_rec, et);
 
         /*
          * The insert code isn't quite ready to deal with all cases of
@@ -4078,7 +4370,8 @@ static int ocfs2_figure_insert_type(struct inode *inode,
          * the case that we're doing a tail append, so maybe we can
          * take advantage of that information somehow.
          */
-        if (le64_to_cpu(di->i_last_eb_blk) == path_leaf_bh(path)->b_blocknr) {
+        if (ocfs2_et_get_last_eb_blk(et) ==
+            path_leaf_bh(path)->b_blocknr) {
                 /*
                  * Ok, ocfs2_find_path() returned us the rightmost
                  * tree path. This might be an appending insert. There are
@@ -4108,7 +4401,7 @@ out:
 int ocfs2_insert_extent(struct ocfs2_super *osb,
                         handle_t *handle,
                         struct inode *inode,
-                        struct buffer_head *fe_bh,
+                        struct ocfs2_extent_tree *et,
                         u32 cpos,
                         u64 start_blk,
                         u32 new_clusters,
@@ -4121,26 +4414,21 @@ int ocfs2_insert_extent(struct ocfs2_super *osb,
         struct ocfs2_insert_type insert = {0, };
         struct ocfs2_extent_rec rec;
 
-        BUG_ON(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL);
-
         mlog(0, "add %u clusters at position %u to inode %llu\n",
              new_clusters, cpos, (unsigned long long)OCFS2_I(inode)->ip_blkno);
 
-        mlog_bug_on_msg(!ocfs2_sparse_alloc(osb) &&
-                        (OCFS2_I(inode)->ip_clusters != cpos),
-                        "Device %s, asking for sparse allocation: inode %llu, "
-                        "cpos %u, clusters %u\n",
-                        osb->dev_str,
-                        (unsigned long long)OCFS2_I(inode)->ip_blkno, cpos,
-                        OCFS2_I(inode)->ip_clusters);
-
         memset(&rec, 0, sizeof(rec));
         rec.e_cpos = cpu_to_le32(cpos);
         rec.e_blkno = cpu_to_le64(start_blk);
         rec.e_leaf_clusters = cpu_to_le16(new_clusters);
         rec.e_flags = flags;
+        status = ocfs2_et_insert_check(inode, et, &rec);
+        if (status) {
+                mlog_errno(status);
+                goto bail;
+        }
 
-        status = ocfs2_figure_insert_type(inode, fe_bh, &last_eb_bh, &rec,
+        status = ocfs2_figure_insert_type(inode, et, &last_eb_bh, &rec,
                                           &free_records, &insert);
         if (status < 0) {
                 mlog_errno(status);
@@ -4154,7 +4442,7 @@ int ocfs2_insert_extent(struct ocfs2_super *osb,
              free_records, insert.ins_tree_depth);
 
         if (insert.ins_contig == CONTIG_NONE && free_records == 0) {
-                status = ocfs2_grow_tree(inode, handle, fe_bh,
+                status = ocfs2_grow_tree(inode, handle, et,
                                          &insert.ins_tree_depth, &last_eb_bh,
                                          meta_ac);
                 if (status) {
@@ -4164,17 +4452,124 @@ int ocfs2_insert_extent(struct ocfs2_super *osb,
         }
 
         /* Finally, we can add clusters. This might rotate the tree for us. */
-        status = ocfs2_do_insert_extent(inode, handle, fe_bh, &rec, &insert);
+        status = ocfs2_do_insert_extent(inode, handle, et, &rec, &insert);
         if (status < 0)
                 mlog_errno(status);
-        else
+        else if (et->et_ops == &ocfs2_dinode_et_ops)
                 ocfs2_extent_map_insert_rec(inode, &rec);
 
 bail:
-        if (last_eb_bh)
-                brelse(last_eb_bh);
+        brelse(last_eb_bh);
+
+        mlog_exit(status);
+        return status;
+}
+
+/*
+ * Allcate and add clusters into the extent b-tree.
+ * The new clusters(clusters_to_add) will be inserted at logical_offset.
+ * The extent b-tree's root is specified by et, and
+ * it is not limited to the file storage. Any extent tree can use this
+ * function if it implements the proper ocfs2_extent_tree.
+ */
+int ocfs2_add_clusters_in_btree(struct ocfs2_super *osb,
+                                struct inode *inode,
+                                u32 *logical_offset,
+                                u32 clusters_to_add,
+                                int mark_unwritten,
+                                struct ocfs2_extent_tree *et,
+                                handle_t *handle,
+                                struct ocfs2_alloc_context *data_ac,
+                                struct ocfs2_alloc_context *meta_ac,
+                                enum ocfs2_alloc_restarted *reason_ret)
+{
+        int status = 0;
+        int free_extents;
+        enum ocfs2_alloc_restarted reason = RESTART_NONE;
+        u32 bit_off, num_bits;
+        u64 block;
+        u8 flags = 0;
+
+        BUG_ON(!clusters_to_add);
+
+        if (mark_unwritten)
+                flags = OCFS2_EXT_UNWRITTEN;
+
+        free_extents = ocfs2_num_free_extents(osb, inode, et);
+        if (free_extents < 0) {
+                status = free_extents;
+                mlog_errno(status);
+                goto leave;
+        }
+
+        /* there are two cases which could cause us to EAGAIN in the
+         * we-need-more-metadata case:
+         * 1) we haven't reserved *any*
+         * 2) we are so fragmented, we've needed to add metadata too
+         *    many times. */
+        if (!free_extents && !meta_ac) {
+                mlog(0, "we haven't reserved any metadata!\n");
+                status = -EAGAIN;
+                reason = RESTART_META;
+                goto leave;
+        } else if ((!free_extents)
+                   && (ocfs2_alloc_context_bits_left(meta_ac)
+                       < ocfs2_extend_meta_needed(et->et_root_el))) {
+                mlog(0, "filesystem is really fragmented...\n");
+                status = -EAGAIN;
+                reason = RESTART_META;
+                goto leave;
+        }
+
+        status = __ocfs2_claim_clusters(osb, handle, data_ac, 1,
+                                        clusters_to_add, &bit_off, &num_bits);
+        if (status < 0) {
+                if (status != -ENOSPC)
+                        mlog_errno(status);
+                goto leave;
+        }
 
+        BUG_ON(num_bits > clusters_to_add);
+
+        /* reserve our write early -- insert_extent may update the inode */
+        status = ocfs2_journal_access(handle, inode, et->et_root_bh,
+                                      OCFS2_JOURNAL_ACCESS_WRITE);
+        if (status < 0) {
+                mlog_errno(status);
+                goto leave;
+        }
+
+        block = ocfs2_clusters_to_blocks(osb->sb, bit_off);
+        mlog(0, "Allocating %u clusters at block %u for inode %llu\n",
+             num_bits, bit_off, (unsigned long long)OCFS2_I(inode)->ip_blkno);
+        status = ocfs2_insert_extent(osb, handle, inode, et,
+                                     *logical_offset, block,
+                                     num_bits, flags, meta_ac);
+        if (status < 0) {
+                mlog_errno(status);
+                goto leave;
+        }
+
+        status = ocfs2_journal_dirty(handle, et->et_root_bh);
+        if (status < 0) {
+                mlog_errno(status);
+                goto leave;
+        }
+
+        clusters_to_add -= num_bits;
+        *logical_offset += num_bits;
+
+        if (clusters_to_add) {
+                mlog(0, "need to alloc once more, wanted = %u\n",
+                     clusters_to_add);
+                status = -EAGAIN;
+                reason = RESTART_TRANS;
+        }
+
+leave:
         mlog_exit(status);
+        if (reason_ret)
+                *reason_ret = reason;
         return status;
 }
 
@@ -4201,7 +4596,7 @@ static void ocfs2_make_right_split_rec(struct super_block *sb,
 static int ocfs2_split_and_insert(struct inode *inode,
                                   handle_t *handle,
                                   struct ocfs2_path *path,
-                                  struct buffer_head *di_bh,
+                                  struct ocfs2_extent_tree *et,
                                   struct buffer_head **last_eb_bh,
                                   int split_index,
                                   struct ocfs2_extent_rec *orig_split_rec,
@@ -4215,7 +4610,6 @@ static int ocfs2_split_and_insert(struct inode *inode,
         struct ocfs2_extent_rec split_rec = *orig_split_rec;
         struct ocfs2_insert_type insert;
         struct ocfs2_extent_block *eb;
-        struct ocfs2_dinode *di;
 
 leftright:
         /*
@@ -4224,8 +4618,7 @@ leftright:
          */
         rec = path_leaf_el(path)->l_recs[split_index];
 
-        di = (struct ocfs2_dinode *)di_bh->b_data;
-        rightmost_el = &di->id2.i_list;
+        rightmost_el = et->et_root_el;
 
         depth = le16_to_cpu(rightmost_el->l_tree_depth);
         if (depth) {
@@ -4236,8 +4629,8 @@ leftright:
 
         if (le16_to_cpu(rightmost_el->l_next_free_rec) ==
             le16_to_cpu(rightmost_el->l_count)) {
-                ret = ocfs2_grow_tree(inode, handle, di_bh, &depth, last_eb_bh,
-                                      meta_ac);
+                ret = ocfs2_grow_tree(inode, handle, et,
+                                      &depth, last_eb_bh, meta_ac);
                 if (ret) {
                         mlog_errno(ret);
                         goto out;
@@ -4274,8 +4667,7 @@ leftright:
                 do_leftright = 1;
         }
 
-        ret = ocfs2_do_insert_extent(inode, handle, di_bh, &split_rec,
-                                     &insert);
+        ret = ocfs2_do_insert_extent(inode, handle, et, &split_rec, &insert);
         if (ret) {
                 mlog_errno(ret);
                 goto out;
@@ -4317,8 +4709,9 @@ out:
  * of the tree is required. All other cases will degrade into a less
  * optimal tree layout.
  *
- * last_eb_bh should be the rightmost leaf block for any inode with a
- * btree. Since a split may grow the tree or a merge might shrink it, the caller cannot trust the contents of that buffer after this call.
+ * last_eb_bh should be the rightmost leaf block for any extent
+ * btree. Since a split may grow the tree or a merge might shrink it,
+ * the caller cannot trust the contents of that buffer after this call.
  *
  * This code is optimized for readability - several passes might be
  * made over certain portions of the tree. All of those blocks will
@@ -4326,7 +4719,7 @@ out:
  * extra overhead is not expressed in terms of disk reads.
  */
 static int __ocfs2_mark_extent_written(struct inode *inode,
-                                       struct buffer_head *di_bh,
+                                       struct ocfs2_extent_tree *et,
                                        handle_t *handle,
                                        struct ocfs2_path *path,
                                        int split_index,
@@ -4366,11 +4759,9 @@ static int __ocfs2_mark_extent_written(struct inode *inode,
          */
         if (path->p_tree_depth) {
                 struct ocfs2_extent_block *eb;
-                struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
 
-                ret = ocfs2_read_block(OCFS2_SB(inode->i_sb),
-                                       le64_to_cpu(di->i_last_eb_blk),
-                                       &last_eb_bh, OCFS2_BH_CACHED, inode);
+                ret = ocfs2_read_block(inode, ocfs2_et_get_last_eb_blk(et),
+                                       &last_eb_bh);
                 if (ret) {
                         mlog_exit(ret);
                         goto out;
@@ -4403,7 +4794,7 @@ static int __ocfs2_mark_extent_written(struct inode *inode,
                 if (ctxt.c_split_covers_rec)
                         el->l_recs[split_index] = *split_rec;
                 else
-                        ret = ocfs2_split_and_insert(inode, handle, path, di_bh,
+                        ret = ocfs2_split_and_insert(inode, handle, path, et,
                                                      &last_eb_bh, split_index,
                                                      split_rec, meta_ac);
                 if (ret)
@@ -4411,7 +4802,7 @@ static int __ocfs2_mark_extent_written(struct inode *inode,
         } else {
                 ret = ocfs2_try_to_merge_extent(inode, handle, path,
                                                 split_index, split_rec,
-                                                dealloc, &ctxt);
+                                                dealloc, &ctxt, et);
                 if (ret)
                         mlog_errno(ret);
         }
@@ -4429,7 +4820,8 @@ out:
  *
  * The caller is responsible for passing down meta_ac if we'll need it.
  */
-int ocfs2_mark_extent_written(struct inode *inode, struct buffer_head *di_bh,
+int ocfs2_mark_extent_written(struct inode *inode,
+                              struct ocfs2_extent_tree *et,
                               handle_t *handle, u32 cpos, u32 len, u32 phys,
                               struct ocfs2_alloc_context *meta_ac,
                               struct ocfs2_cached_dealloc_ctxt *dealloc)
@@ -4455,10 +4847,14 @@ int ocfs2_mark_extent_written(struct inode *inode, struct buffer_head *di_bh,
         /*
          * XXX: This should be fixed up so that we just re-insert the
          * next extent records.
+         *
+         * XXX: This is a hack on the extent tree, maybe it should be
+         * an op?
          */
-        ocfs2_extent_map_trunc(inode, 0);
+        if (et->et_ops == &ocfs2_dinode_et_ops)
+                ocfs2_extent_map_trunc(inode, 0);
 
-        left_path = ocfs2_new_inode_path(di_bh);
+        left_path = ocfs2_new_path(et->et_root_bh, et->et_root_el);
         if (!left_path) {
                 ret = -ENOMEM;
                 mlog_errno(ret);
@@ -4489,8 +4885,9 @@ int ocfs2_mark_extent_written(struct inode *inode, struct buffer_head *di_bh,
         split_rec.e_flags = path_leaf_el(left_path)->l_recs[index].e_flags;
         split_rec.e_flags &= ~OCFS2_EXT_UNWRITTEN;
 
-        ret = __ocfs2_mark_extent_written(inode, di_bh, handle, left_path,
-                                          index, &split_rec, meta_ac, dealloc);
+        ret = __ocfs2_mark_extent_written(inode, et, handle, left_path,
+                                          index, &split_rec, meta_ac,
+                                          dealloc);
         if (ret)
                 mlog_errno(ret);
 
@@ -4499,13 +4896,12 @@ out:
         return ret;
 }
 
-static int ocfs2_split_tree(struct inode *inode, struct buffer_head *di_bh,
+static int ocfs2_split_tree(struct inode *inode, struct ocfs2_extent_tree *et,
                             handle_t *handle, struct ocfs2_path *path,
                             int index, u32 new_range,
                             struct ocfs2_alloc_context *meta_ac)
 {
         int ret, depth, credits = handle->h_buffer_credits;
-        struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
         struct buffer_head *last_eb_bh = NULL;
         struct ocfs2_extent_block *eb;
         struct ocfs2_extent_list *rightmost_el, *el;
@@ -4522,9 +4918,8 @@ static int ocfs2_split_tree(struct inode *inode, struct buffer_head *di_bh,
 
         depth = path->p_tree_depth;
         if (depth > 0) {
-                ret = ocfs2_read_block(OCFS2_SB(inode->i_sb),
-                                       le64_to_cpu(di->i_last_eb_blk),
-                                       &last_eb_bh, OCFS2_BH_CACHED, inode);
+                ret = ocfs2_read_block(inode, ocfs2_et_get_last_eb_blk(et),
+                                       &last_eb_bh);
                 if (ret < 0) {
                         mlog_errno(ret);
                         goto out;
@@ -4535,7 +4930,8 @@ static int ocfs2_split_tree(struct inode *inode, struct buffer_head *di_bh,
         } else
                 rightmost_el = path_leaf_el(path);
 
-        credits += path->p_tree_depth + ocfs2_extend_meta_needed(di);
+        credits += path->p_tree_depth +
+                   ocfs2_extend_meta_needed(et->et_root_el);
         ret = ocfs2_extend_trans(handle, credits);
         if (ret) {
                 mlog_errno(ret);
@@ -4544,7 +4940,7 @@ static int ocfs2_split_tree(struct inode *inode, struct buffer_head *di_bh,
 
         if (le16_to_cpu(rightmost_el->l_next_free_rec) ==
             le16_to_cpu(rightmost_el->l_count)) {
-                ret = ocfs2_grow_tree(inode, handle, di_bh, &depth, &last_eb_bh,
+                ret = ocfs2_grow_tree(inode, handle, et, &depth, &last_eb_bh,
                                       meta_ac);
                 if (ret) {
                         mlog_errno(ret);
@@ -4558,7 +4954,7 @@ static int ocfs2_split_tree(struct inode *inode, struct buffer_head *di_bh,
         insert.ins_split = SPLIT_RIGHT;
         insert.ins_tree_depth = depth;
 
-        ret = ocfs2_do_insert_extent(inode, handle, di_bh, &split_rec, &insert);
+        ret = ocfs2_do_insert_extent(inode, handle, et, &split_rec, &insert);
         if (ret)
                 mlog_errno(ret);
 
@@ -4570,7 +4966,8 @@ out:
 static int ocfs2_truncate_rec(struct inode *inode, handle_t *handle,
                               struct ocfs2_path *path, int index,
                               struct ocfs2_cached_dealloc_ctxt *dealloc,
-                              u32 cpos, u32 len)
+                              u32 cpos, u32 len,
+                              struct ocfs2_extent_tree *et)
 {
         int ret;
         u32 left_cpos, rec_range, trunc_range;
@@ -4582,7 +4979,7 @@ static int ocfs2_truncate_rec(struct inode *inode, handle_t *handle,
         struct ocfs2_extent_block *eb;
 
         if (ocfs2_is_empty_extent(&el->l_recs[0]) && index > 0) {
-                ret = ocfs2_rotate_tree_left(inode, handle, path, dealloc);
+                ret = ocfs2_rotate_tree_left(inode, handle, path, dealloc, et);
                 if (ret) {
                         mlog_errno(ret);
                         goto out;
@@ -4713,7 +5110,7 @@ static int ocfs2_truncate_rec(struct inode *inode, handle_t *handle,
 
         ocfs2_journal_dirty(handle, path_leaf_bh(path));
 
-        ret = ocfs2_rotate_tree_left(inode, handle, path, dealloc);
+        ret = ocfs2_rotate_tree_left(inode, handle, path, dealloc, et);
         if (ret) {
                 mlog_errno(ret);
                 goto out;
@@ -4724,7 +5121,8 @@ out:
         return ret;
 }
 
-int ocfs2_remove_extent(struct inode *inode, struct buffer_head *di_bh,
+int ocfs2_remove_extent(struct inode *inode,
+                        struct ocfs2_extent_tree *et,
                         u32 cpos, u32 len, handle_t *handle,
                         struct ocfs2_alloc_context *meta_ac,
                         struct ocfs2_cached_dealloc_ctxt *dealloc)
@@ -4733,11 +5131,11 @@ int ocfs2_remove_extent(struct inode *inode, struct buffer_head *di_bh,
         u32 rec_range, trunc_range;
         struct ocfs2_extent_rec *rec;
         struct ocfs2_extent_list *el;
-        struct ocfs2_path *path;
+        struct ocfs2_path *path = NULL;
 
         ocfs2_extent_map_trunc(inode, 0);
 
-        path = ocfs2_new_inode_path(di_bh);
+        path = ocfs2_new_path(et->et_root_bh, et->et_root_el);
         if (!path) {
                 ret = -ENOMEM;
                 mlog_errno(ret);
@@ -4790,13 +5188,13 @@ int ocfs2_remove_extent(struct inode *inode, struct buffer_head *di_bh,
 
         if (le32_to_cpu(rec->e_cpos) == cpos || rec_range == trunc_range) {
                 ret = ocfs2_truncate_rec(inode, handle, path, index, dealloc,
-                                         cpos, len);
+                                         cpos, len, et);
                 if (ret) {
                         mlog_errno(ret);
                         goto out;
                 }
         } else {
-                ret = ocfs2_split_tree(inode, di_bh, handle, path, index,
+                ret = ocfs2_split_tree(inode, et, handle, path, index,
                                        trunc_range, meta_ac);
                 if (ret) {
                         mlog_errno(ret);
@@ -4845,7 +5243,7 @@ int ocfs2_remove_extent(struct inode *inode, struct buffer_head *di_bh,
                 }
 
                 ret = ocfs2_truncate_rec(inode, handle, path, index, dealloc,
-                                         cpos, len);
+                                         cpos, len, et);
                 if (ret) {
                         mlog_errno(ret);
                         goto out;
@@ -5188,8 +5586,7 @@ static int ocfs2_get_truncate_log_info(struct ocfs2_super *osb,
                 goto bail;
         }
 
-        status = ocfs2_read_block(osb, OCFS2_I(inode)->ip_blkno, &bh,
-                                  OCFS2_BH_CACHED, inode);
+        status = ocfs2_read_block(inode, OCFS2_I(inode)->ip_blkno, &bh);
         if (status < 0) {
                 iput(inode);
                 mlog_errno(status);
@@ -5264,8 +5661,7 @@ int ocfs2_begin_truncate_log_recovery(struct ocfs2_super *osb,
 bail:
         if (tl_inode)
                 iput(tl_inode);
-        if (tl_bh)
-                brelse(tl_bh);
+        brelse(tl_bh);
 
         if (status < 0 && (*tl_copy)) {
                 kfree(*tl_copy);
@@ -6008,20 +6404,13 @@ bail:
         return status;
 }
 
-static int ocfs2_writeback_zero_func(handle_t *handle, struct buffer_head *bh)
+static int ocfs2_zero_func(handle_t *handle, struct buffer_head *bh)
 {
         set_buffer_uptodate(bh);
         mark_buffer_dirty(bh);
         return 0;
 }
 
-static int ocfs2_ordered_zero_func(handle_t *handle, struct buffer_head *bh)
-{
-        set_buffer_uptodate(bh);
-        mark_buffer_dirty(bh);
-        return ocfs2_journal_dirty_data(handle, bh);
-}
-
 static void ocfs2_map_and_dirty_page(struct inode *inode, handle_t *handle,
                                      unsigned int from, unsigned int to,
                                      struct page *page, int zero, u64 *phys)
@@ -6040,17 +6429,18 @@ static void ocfs2_map_and_dirty_page(struct inode *inode, handle_t *handle,
          * here if they aren't - ocfs2_map_page_blocks()
          * might've skipped some
          */
-        if (ocfs2_should_order_data(inode)) {
-                ret = walk_page_buffers(handle,
-                                        page_buffers(page),
-                                        from, to, &partial,
-                                        ocfs2_ordered_zero_func);
-                if (ret < 0)
-                        mlog_errno(ret);
-        } else {
+        ret = walk_page_buffers(handle, page_buffers(page),
+                                from, to, &partial,
+                                ocfs2_zero_func);
+        if (ret < 0)
+                mlog_errno(ret);
+        else if (ocfs2_should_order_data(inode)) {
+                ret = ocfs2_jbd2_file_inode(handle, inode);
+#ifdef CONFIG_OCFS2_COMPAT_JBD
                 ret = walk_page_buffers(handle, page_buffers(page),
                                         from, to, &partial,
-                                        ocfs2_writeback_zero_func);
+                                        ocfs2_journal_dirty_data);
+#endif
                 if (ret < 0)
                         mlog_errno(ret);
         }
@@ -6215,20 +6605,29 @@ out:
         return ret;
 }
 
-static void ocfs2_zero_dinode_id2(struct inode *inode, struct ocfs2_dinode *di)
+static void ocfs2_zero_dinode_id2_with_xattr(struct inode *inode,
+                                             struct ocfs2_dinode *di)
 {
         unsigned int blocksize = 1 << inode->i_sb->s_blocksize_bits;
+        unsigned int xattrsize = le16_to_cpu(di->i_xattr_inline_size);
 
-        memset(&di->id2, 0, blocksize - offsetof(struct ocfs2_dinode, id2));
+        if (le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_XATTR_FL)
+                memset(&di->id2, 0, blocksize -
+                                    offsetof(struct ocfs2_dinode, id2) -
+                                    xattrsize);
+        else
+                memset(&di->id2, 0, blocksize -
+                                    offsetof(struct ocfs2_dinode, id2));
 }
 
 void ocfs2_dinode_new_extent_list(struct inode *inode,
                                   struct ocfs2_dinode *di)
 {
-        ocfs2_zero_dinode_id2(inode, di);
+        ocfs2_zero_dinode_id2_with_xattr(inode, di);
         di->id2.i_list.l_tree_depth = 0;
         di->id2.i_list.l_next_free_rec = 0;
-        di->id2.i_list.l_count = cpu_to_le16(ocfs2_extent_recs_per_inode(inode->i_sb));
+        di->id2.i_list.l_count = cpu_to_le16(
+                ocfs2_extent_recs_per_inode_with_xattr(inode->i_sb, di));
 }
 
 void ocfs2_set_inode_data_inline(struct inode *inode, struct ocfs2_dinode *di)
@@ -6245,9 +6644,10 @@ void ocfs2_set_inode_data_inline(struct inode *inode, struct ocfs2_dinode *di)
          * We clear the entire i_data structure here so that all
          * fields can be properly initialized.
          */
-        ocfs2_zero_dinode_id2(inode, di);
+        ocfs2_zero_dinode_id2_with_xattr(inode, di);
 
-        idata->id_count = cpu_to_le16(ocfs2_max_inline_data(inode->i_sb));
+        idata->id_count = cpu_to_le16(
+                        ocfs2_max_inline_data_with_xattr(inode->i_sb, di));
 }
 
 int ocfs2_convert_inline_data_to_extents(struct inode *inode,
@@ -6262,6 +6662,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
         struct ocfs2_alloc_context *data_ac = NULL;
         struct page **pages = NULL;
         loff_t end = osb->s_clustersize;
+        struct ocfs2_extent_tree et;
 
         has_data = i_size_read(inode) ? 1 : 0;
 
@@ -6361,7 +6762,8 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
                  * this proves to be false, we could always re-build
                  * the in-inode data from our pages.
                  */
-                ret = ocfs2_insert_extent(osb, handle, inode, di_bh,
+                ocfs2_init_dinode_extent_tree(&et, inode, di_bh);
+                ret = ocfs2_insert_extent(osb, handle, inode, &et,
                                           0, block, 1, 0, NULL);
                 if (ret) {
                         mlog_errno(ret);
@@ -6404,13 +6806,14 @@ int ocfs2_commit_truncate(struct ocfs2_super *osb,
         handle_t *handle = NULL;
         struct inode *tl_inode = osb->osb_tl_inode;
         struct ocfs2_path *path = NULL;
+        struct ocfs2_dinode *di = (struct ocfs2_dinode *)fe_bh->b_data;
 
         mlog_entry_void();
 
         new_highest_cpos = ocfs2_clusters_for_bytes(osb->sb,
                                                      i_size_read(inode));
 
-        path = ocfs2_new_inode_path(fe_bh);
+        path = ocfs2_new_path(fe_bh, &di->id2.i_list);
         if (!path) {
                 status = -ENOMEM;
                 mlog_errno(status);
@@ -6581,8 +6984,8 @@ int ocfs2_prepare_truncate(struct ocfs2_super *osb,
         ocfs2_init_dealloc_ctxt(&(*tc)->tc_dealloc);
 
         if (fe->id2.i_list.l_tree_depth) {
-                status = ocfs2_read_block(osb, le64_to_cpu(fe->i_last_eb_blk),
-                                          &last_eb_bh, OCFS2_BH_CACHED, inode);
+                status = ocfs2_read_block(inode, le64_to_cpu(fe->i_last_eb_blk),
+                                          &last_eb_bh);
                 if (status < 0) {
                         mlog_errno(status);
                         goto bail;
@@ -6695,8 +7098,7 @@ static void ocfs2_free_truncate_context(struct ocfs2_truncate_context *tc)
                 mlog(ML_NOTICE,
                      "Truncate completion has non-empty dealloc context\n");
 
-        if (tc->tc_last_eb_bh)
-                brelse(tc->tc_last_eb_bh);
+        brelse(tc->tc_last_eb_bh);
 
         kfree(tc);
 }
diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h
index 42ff94bd8011..70257c84cfbe 100644
--- a/fs/ocfs2/alloc.h
+++ b/fs/ocfs2/alloc.h
@@ -26,30 +26,102 @@
 #ifndef OCFS2_ALLOC_H
 #define OCFS2_ALLOC_H
 
+
+/*
+ * For xattr tree leaf, we limit the leaf byte size to be 64K.
+ */
+#define OCFS2_MAX_XATTR_TREE_LEAF_SIZE 65536
+
+/*
+ * ocfs2_extent_tree and ocfs2_extent_tree_operations are used to abstract
+ * the b-tree operations in ocfs2. Now all the b-tree operations are not
+ * limited to ocfs2_dinode only. Any data which need to allocate clusters
+ * to store can use b-tree. And it only needs to implement its ocfs2_extent_tree
+ * and operation.
+ *
+ * ocfs2_extent_tree becomes the first-class object for extent tree
+ * manipulation.  Callers of the alloc.c code need to fill it via one of
+ * the ocfs2_init_*_extent_tree() operations below.
+ *
+ * ocfs2_extent_tree contains info for the root of the b-tree, it must have a
+ * root ocfs2_extent_list and a root_bh so that they can be used in the b-tree
+ * functions.
+ * ocfs2_extent_tree_operations abstract the normal operations we do for
+ * the root of extent b-tree.
+ */
+struct ocfs2_extent_tree_operations;
+struct ocfs2_extent_tree {
+        struct ocfs2_extent_tree_operations     *et_ops;
+        struct buffer_head                      *et_root_bh;
+        struct ocfs2_extent_list                *et_root_el;
+        void                                    *et_object;
+        unsigned int                            et_max_leaf_clusters;
+};
+
+/*
+ * ocfs2_init_*_extent_tree() will fill an ocfs2_extent_tree from the
+ * specified object buffer.
+ */
+void ocfs2_init_dinode_extent_tree(struct ocfs2_extent_tree *et,
+                                   struct inode *inode,
+                                   struct buffer_head *bh);
+void ocfs2_init_xattr_tree_extent_tree(struct ocfs2_extent_tree *et,
+                                       struct inode *inode,
+                                       struct buffer_head *bh);
+void ocfs2_init_xattr_value_extent_tree(struct ocfs2_extent_tree *et,
+                                        struct inode *inode,
+                                        struct buffer_head *bh,
+                                        struct ocfs2_xattr_value_root *xv);
+
 struct ocfs2_alloc_context;
 int ocfs2_insert_extent(struct ocfs2_super *osb,
                         handle_t *handle,
                         struct inode *inode,
-                        struct buffer_head *fe_bh,
+                        struct ocfs2_extent_tree *et,
                         u32 cpos,
                         u64 start_blk,
                         u32 new_clusters,
                         u8 flags,
                         struct ocfs2_alloc_context *meta_ac);
+
+enum ocfs2_alloc_restarted {
+        RESTART_NONE = 0,
+        RESTART_TRANS,
+        RESTART_META
+};
+int ocfs2_add_clusters_in_btree(struct ocfs2_super *osb,
+                                struct inode *inode,
+                                u32 *logical_offset,
+                                u32 clusters_to_add,
+                                int mark_unwritten,
+                                struct ocfs2_extent_tree *et,
+                                handle_t *handle,
+                                struct ocfs2_alloc_context *data_ac,
+                                struct ocfs2_alloc_context *meta_ac,
+                                enum ocfs2_alloc_restarted *reason_ret);
 struct ocfs2_cached_dealloc_ctxt;
-int ocfs2_mark_extent_written(struct inode *inode, struct buffer_head *di_bh,
+int ocfs2_mark_extent_written(struct inode *inode,
+                              struct ocfs2_extent_tree *et,
                               handle_t *handle, u32 cpos, u32 len, u32 phys,
                               struct ocfs2_alloc_context *meta_ac,
                               struct ocfs2_cached_dealloc_ctxt *dealloc);
-int ocfs2_remove_extent(struct inode *inode, struct buffer_head *di_bh,
+int ocfs2_remove_extent(struct inode *inode,
+                        struct ocfs2_extent_tree *et,
                         u32 cpos, u32 len, handle_t *handle,
                         struct ocfs2_alloc_context *meta_ac,
                         struct ocfs2_cached_dealloc_ctxt *dealloc);
 int ocfs2_num_free_extents(struct ocfs2_super *osb,
                            struct inode *inode,
-                           struct ocfs2_dinode *fe);
-/* how many new metadata chunks would an allocation need at maximum? */
-static inline int ocfs2_extend_meta_needed(struct ocfs2_dinode *fe)
+                           struct ocfs2_extent_tree *et);
+
+/*
+ * how many new metadata chunks would an allocation need at maximum?
+ *
+ * Please note that the caller must make sure that root_el is the root
+ * of extent tree. So for an inode, it should be &fe->id2.i_list. Otherwise
+ * the result may be wrong.
+ */
+static inline int ocfs2_extend_meta_needed(struct ocfs2_extent_list *root_el)
 {
         /*
          * Rather than do all the work of determining how much we need
@@ -59,7 +131,7 @@ static inline int ocfs2_extend_meta_needed(struct ocfs2_dinode *fe)
          * new tree_depth==0 extent_block, and one block at the new
          * top-of-the tree.
          */
-        return le16_to_cpu(fe->id2.i_list.l_tree_depth) + 2;
+        return le16_to_cpu(root_el->l_tree_depth) + 2;
 }
 
 void ocfs2_dinode_new_extent_list(struct inode *inode, struct ocfs2_dinode *di);
@@ -146,4 +218,13 @@ static inline unsigned int ocfs2_rec_clusters(struct ocfs2_extent_list *el,
                 return le16_to_cpu(rec->e_leaf_clusters);
 }
 
+/*
+ * This is only valid for leaf nodes, which are the only ones that can
+ * have empty extents anyway.
+ */
+static inline int ocfs2_is_empty_extent(struct ocfs2_extent_rec *rec)
+{
+        return !rec->e_leaf_clusters;
+}
+
 #endif /* OCFS2_ALLOC_H */
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index a53da1466277..c22543b33420 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -68,9 +68,7 @@ static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
                 goto bail;
         }
 
-        status = ocfs2_read_block(OCFS2_SB(inode->i_sb),
-                                  OCFS2_I(inode)->ip_blkno,
-                                  &bh, OCFS2_BH_CACHED, inode);
+        status = ocfs2_read_block(inode, OCFS2_I(inode)->ip_blkno, &bh);
         if (status < 0) {
                 mlog_errno(status);
                 goto bail;
@@ -128,8 +126,7 @@ static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
         err = 0;
 
 bail:
-        if (bh)
-                brelse(bh);
+        brelse(bh);
 
         mlog_exit(err);
         return err;
@@ -261,13 +258,11 @@ static int ocfs2_readpage_inline(struct inode *inode, struct page *page)
 {
         int ret;
         struct buffer_head *di_bh = NULL;
-        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
         BUG_ON(!PageLocked(page));
         BUG_ON(!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL));
 
-        ret = ocfs2_read_block(osb, OCFS2_I(inode)->ip_blkno, &di_bh,
-                               OCFS2_BH_CACHED, inode);
+        ret = ocfs2_read_block(inode, OCFS2_I(inode)->ip_blkno, &di_bh);
         if (ret) {
                 mlog_errno(ret);
                 goto out;
@@ -485,11 +480,14 @@ handle_t *ocfs2_start_walk_page_trans(struct inode *inode,
         }
 
         if (ocfs2_should_order_data(inode)) {
+                ret = ocfs2_jbd2_file_inode(handle, inode);
+#ifdef CONFIG_OCFS2_COMPAT_JBD
                 ret = walk_page_buffers(handle,
                                         page_buffers(page),
                                         from, to, NULL,
                                         ocfs2_journal_dirty_data);
-                if (ret < 0) 
+#endif
+                if (ret < 0)
                         mlog_errno(ret);
         }
 out:
@@ -669,7 +667,7 @@ static void ocfs2_invalidatepage(struct page *page, unsigned long offset)
 {
         journal_t *journal = OCFS2_SB(page->mapping->host->i_sb)->journal->j_journal;
 
-        journal_invalidatepage(journal, page, offset);
+        jbd2_journal_invalidatepage(journal, page, offset);
 }
 
 static int ocfs2_releasepage(struct page *page, gfp_t wait)
@@ -678,7 +676,7 @@ static int ocfs2_releasepage(struct page *page, gfp_t wait)
 
         if (!page_has_buffers(page))
                 return 0;
-        return journal_try_to_free_buffers(journal, page, wait);
+        return jbd2_journal_try_to_free_buffers(journal, page, wait);
 }
 
 static ssize_t ocfs2_direct_IO(int rw,
@@ -1074,11 +1072,15 @@ static void ocfs2_write_failure(struct inode *inode,
                 tmppage = wc->w_pages[i];
 
                 if (page_has_buffers(tmppage)) {
-                        if (ocfs2_should_order_data(inode))
+                        if (ocfs2_should_order_data(inode)) {
+                                ocfs2_jbd2_file_inode(wc->w_handle, inode);
+#ifdef CONFIG_OCFS2_COMPAT_JBD
                                 walk_page_buffers(wc->w_handle,
                                                   page_buffers(tmppage),
                                                   from, to, NULL,
                                                   ocfs2_journal_dirty_data);
+#endif
+                        }
 
                         block_commit_write(tmppage, from, to);
                 }
@@ -1242,6 +1244,7 @@ static int ocfs2_write_cluster(struct address_space *mapping,
         int ret, i, new, should_zero = 0;
         u64 v_blkno, p_blkno;
         struct inode *inode = mapping->host;
+        struct ocfs2_extent_tree et;
 
         new = phys == 0 ? 1 : 0;
         if (new || unwritten)
@@ -1255,10 +1258,10 @@ static int ocfs2_write_cluster(struct address_space *mapping,
                  * any additional semaphores or cluster locks.
                  */
                 tmp_pos = cpos;
-                ret = ocfs2_do_extend_allocation(OCFS2_SB(inode->i_sb), inode,
-                                                 &tmp_pos, 1, 0, wc->w_di_bh,
-                                                 wc->w_handle, data_ac,
-                                                 meta_ac, NULL);
+                ret = ocfs2_add_inode_data(OCFS2_SB(inode->i_sb), inode,
+                                           &tmp_pos, 1, 0, wc->w_di_bh,
+                                           wc->w_handle, data_ac,
+                                           meta_ac, NULL);
                 /*
                  * This shouldn't happen because we must have already
                  * calculated the correct meta data allocation required. The
@@ -1276,7 +1279,8 @@ static int ocfs2_write_cluster(struct address_space *mapping,
                         goto out;
                 }
         } else if (unwritten) {
-                ret = ocfs2_mark_extent_written(inode, wc->w_di_bh,
+                ocfs2_init_dinode_extent_tree(&et, inode, wc->w_di_bh);
+                ret = ocfs2_mark_extent_written(inode, &et,
                                                 wc->w_handle, cpos, 1, phys,
                                                 meta_ac, &wc->w_dealloc);
                 if (ret < 0) {
@@ -1665,6 +1669,7 @@ int ocfs2_write_begin_nolock(struct address_space *mapping,
         struct ocfs2_alloc_context *data_ac = NULL;
         struct ocfs2_alloc_context *meta_ac = NULL;
         handle_t *handle;
+        struct ocfs2_extent_tree et;
 
         ret = ocfs2_alloc_write_ctxt(&wc, osb, pos, len, di_bh);
         if (ret) {
@@ -1712,14 +1717,23 @@ int ocfs2_write_begin_nolock(struct address_space *mapping,
                  * ocfs2_lock_allocators(). It greatly over-estimates
                  * the work to be done.
                  */
-                ret = ocfs2_lock_allocators(inode, di, clusters_to_alloc,
-                                            extents_to_split, &data_ac, &meta_ac);
+                mlog(0, "extend inode %llu, i_size = %lld, di->i_clusters = %u,"
+                     " clusters_to_add = %u, extents_to_split = %u\n",
+                     (unsigned long long)OCFS2_I(inode)->ip_blkno,
+                     (long long)i_size_read(inode), le32_to_cpu(di->i_clusters),
+                     clusters_to_alloc, extents_to_split);
+
+                ocfs2_init_dinode_extent_tree(&et, inode, wc->w_di_bh);
+                ret = ocfs2_lock_allocators(inode, &et,
+                                            clusters_to_alloc, extents_to_split,
+                                            &data_ac, &meta_ac);
                 if (ret) {
                         mlog_errno(ret);
                         goto out;
                 }
 
-                credits = ocfs2_calc_extend_credits(inode->i_sb, di,
+                credits = ocfs2_calc_extend_credits(inode->i_sb,
+                                                    &di->id2.i_list,
                                                     clusters_to_alloc);
 
         }
@@ -1905,11 +1919,15 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
                 }
 
                 if (page_has_buffers(tmppage)) {
-                        if (ocfs2_should_order_data(inode))
+                        if (ocfs2_should_order_data(inode)) {
+                                ocfs2_jbd2_file_inode(wc->w_handle, inode);
+#ifdef CONFIG_OCFS2_COMPAT_JBD
                                 walk_page_buffers(wc->w_handle,
                                                   page_buffers(tmppage),
                                                   from, to, NULL,
                                                   ocfs2_journal_dirty_data);
+#endif
+                        }
                         block_commit_write(tmppage, from, to);
                 }
         }
diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index f136639f5b41..7e947c672469 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -66,7 +66,7 @@ int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh,
         /* remove from dirty list before I/O. */
         clear_buffer_dirty(bh);
 
-        get_bh(bh); /* for end_buffer_write_sync() */                   
+        get_bh(bh); /* for end_buffer_write_sync() */
         bh->b_end_io = end_buffer_write_sync;
         submit_bh(WRITE, bh);
 
@@ -88,22 +88,103 @@ out:
         return ret;
 }
 
-int ocfs2_read_blocks(struct ocfs2_super *osb, u64 block, int nr,
-                      struct buffer_head *bhs[], int flags,
-                      struct inode *inode)
+int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
+                           unsigned int nr, struct buffer_head *bhs[])
+{
+        int status = 0;
+        unsigned int i;
+        struct buffer_head *bh;
+
+        if (!nr) {
+                mlog(ML_BH_IO, "No buffers will be read!\n");
+                goto bail;
+        }
+
+        for (i = 0 ; i < nr ; i++) {
+                if (bhs[i] == NULL) {
+                        bhs[i] = sb_getblk(osb->sb, block++);
+                        if (bhs[i] == NULL) {
+                                status = -EIO;
+                                mlog_errno(status);
+                                goto bail;
+                        }
+                }
+                bh = bhs[i];
+
+                if (buffer_jbd(bh)) {
+                        mlog(ML_ERROR,
+                             "trying to sync read a jbd "
+                             "managed bh (blocknr = %llu), skipping\n",
+                             (unsigned long long)bh->b_blocknr);
+                        continue;
+                }
+
+                if (buffer_dirty(bh)) {
+                        /* This should probably be a BUG, or
+                         * at least return an error. */
+                        mlog(ML_ERROR,
+                             "trying to sync read a dirty "
+                             "buffer! (blocknr = %llu), skipping\n",
+                             (unsigned long long)bh->b_blocknr);
+                        continue;
+                }
+
+                lock_buffer(bh);
+                if (buffer_jbd(bh)) {
+                        mlog(ML_ERROR,
+                             "block %llu had the JBD bit set "
+                             "while I was in lock_buffer!",
+                             (unsigned long long)bh->b_blocknr);
+                        BUG();
+                }
+
+                clear_buffer_uptodate(bh);
+                get_bh(bh); /* for end_buffer_read_sync() */
+                bh->b_end_io = end_buffer_read_sync;
+                submit_bh(READ, bh);
+        }
+
+        for (i = nr; i > 0; i--) {
+                bh = bhs[i - 1];
+
+                if (buffer_jbd(bh)) {
+                        mlog(ML_ERROR,
+                             "the journal got the buffer while it was "
+                             "locked for io! (blocknr = %llu)\n",
+                             (unsigned long long)bh->b_blocknr);
+                        BUG();
+                }
+
+                wait_on_buffer(bh);
+                if (!buffer_uptodate(bh)) {
+                        /* Status won't be cleared from here on out,
+                         * so we can safely record this and loop back
+                         * to cleanup the other buffers. */
+                        status = -EIO;
+                        put_bh(bh);
+                        bhs[i - 1] = NULL;
+                }
+        }
+
+bail:
+        return status;
+}
+
+int ocfs2_read_blocks(struct inode *inode, u64 block, int nr,
+                      struct buffer_head *bhs[], int flags)
 {
         int status = 0;
-        struct super_block *sb;
         int i, ignore_cache = 0;
         struct buffer_head *bh;
 
-        mlog_entry("(block=(%llu), nr=(%d), flags=%d, inode=%p)\n",
-                   (unsigned long long)block, nr, flags, inode);
+        mlog_entry("(inode=%p, block=(%llu), nr=(%d), flags=%d)\n",
+                   inode, (unsigned long long)block, nr, flags);
 
+        BUG_ON(!inode);
         BUG_ON((flags & OCFS2_BH_READAHEAD) &&
-               (!inode || !(flags & OCFS2_BH_CACHED)));
+               (flags & OCFS2_BH_IGNORE_CACHE));
 
-        if (osb == NULL || osb->sb == NULL || bhs == NULL) {
+        if (bhs == NULL) {
                 status = -EINVAL;
                 mlog_errno(status);
                 goto bail;
@@ -122,26 +203,19 @@ int ocfs2_read_blocks(struct ocfs2_super *osb, u64 block, int nr,
                 goto bail;
         }
 
-        sb = osb->sb;
-
-        if (flags & OCFS2_BH_CACHED && !inode)
-                flags &= ~OCFS2_BH_CACHED;
-
-        if (inode)
-                mutex_lock(&OCFS2_I(inode)->ip_io_mutex);
+        mutex_lock(&OCFS2_I(inode)->ip_io_mutex);
         for (i = 0 ; i < nr ; i++) {
                 if (bhs[i] == NULL) {
-                        bhs[i] = sb_getblk(sb, block++);
+                        bhs[i] = sb_getblk(inode->i_sb, block++);
                         if (bhs[i] == NULL) {
-                                if (inode)
-                                        mutex_unlock(&OCFS2_I(inode)->ip_io_mutex);
+                                mutex_unlock(&OCFS2_I(inode)->ip_io_mutex);
                                 status = -EIO;
                                 mlog_errno(status);
                                 goto bail;
                         }
                 }
                 bh = bhs[i];
-                ignore_cache = 0;
+                ignore_cache = (flags & OCFS2_BH_IGNORE_CACHE);
 
                 /* There are three read-ahead cases here which we need to
                  * be concerned with. All three assume a buffer has
@@ -167,26 +241,27 @@ int ocfs2_read_blocks(struct ocfs2_super *osb, u64 block, int nr,
                  *    before our is-it-in-flight check.
                  */
 
-                if (flags & OCFS2_BH_CACHED &&
-                    !ocfs2_buffer_uptodate(inode, bh)) {
+                if (!ignore_cache && !ocfs2_buffer_uptodate(inode, bh)) {
                         mlog(ML_UPTODATE,
                              "bh (%llu), inode %llu not uptodate\n",
                              (unsigned long long)bh->b_blocknr,
                              (unsigned long long)OCFS2_I(inode)->ip_blkno);
+                        /* We're using ignore_cache here to say
+                         * "go to disk" */
                         ignore_cache = 1;
                 }
 
                 /* XXX: Can we ever get this and *not* have the cached
                  * flag set? */
                 if (buffer_jbd(bh)) {
-                        if (!(flags & OCFS2_BH_CACHED) || ignore_cache)
+                        if (ignore_cache)
                                 mlog(ML_BH_IO, "trying to sync read a jbd "
                                                "managed bh (blocknr = %llu)\n",
                                      (unsigned long long)bh->b_blocknr);
                         continue;
                 }
 
-                if (!(flags & OCFS2_BH_CACHED) || ignore_cache) {
+                if (ignore_cache) {
                         if (buffer_dirty(bh)) {
                                 /* This should probably be a BUG, or
                                  * at least return an error. */
@@ -221,7 +296,7 @@ int ocfs2_read_blocks(struct ocfs2_super *osb, u64 block, int nr,
                          * previously read-ahead buffer may have
                          * completed I/O while we were waiting for the
                          * buffer lock. */
-                        if ((flags & OCFS2_BH_CACHED)
+                        if (!(flags & OCFS2_BH_IGNORE_CACHE)
                             && !(flags & OCFS2_BH_READAHEAD)
                             && ocfs2_buffer_uptodate(inode, bh)) {
                                 unlock_buffer(bh);
@@ -265,15 +340,14 @@ int ocfs2_read_blocks(struct ocfs2_super *osb, u64 block, int nr,
                 /* Always set the buffer in the cache, even if it was
                  * a forced read, or read-ahead which hasn't yet
                  * completed. */
-                if (inode)
-                        ocfs2_set_buffer_uptodate(inode, bh);
+                ocfs2_set_buffer_uptodate(inode, bh);
         }
-        if (inode)
-                mutex_unlock(&OCFS2_I(inode)->ip_io_mutex);
+        mutex_unlock(&OCFS2_I(inode)->ip_io_mutex);
 
         mlog(ML_BH_IO, "block=(%llu), nr=(%d), cached=%s, flags=0x%x\n", 
              (unsigned long long)block, nr,
-             (!(flags & OCFS2_BH_CACHED) || ignore_cache) ? "no" : "yes", flags);
+             ((flags & OCFS2_BH_IGNORE_CACHE) || ignore_cache) ? "no" : "yes",
+             flags);
 
 bail:
 
diff --git a/fs/ocfs2/buffer_head_io.h b/fs/ocfs2/buffer_head_io.h
index c2e78614c3e5..75e1dcb1ade7 100644
--- a/fs/ocfs2/buffer_head_io.h
+++ b/fs/ocfs2/buffer_head_io.h
@@ -31,31 +31,29 @@
 void ocfs2_end_buffer_io_sync(struct buffer_head *bh,
                              int uptodate);
 
-static inline int ocfs2_read_block(struct ocfs2_super          *osb,
+static inline int ocfs2_read_block(struct inode        *inode,
                                    u64                  off,
-                                   struct buffer_head **bh,
-                                   int                  flags,
-                                   struct inode        *inode);
+                                   struct buffer_head **bh);
 
 int ocfs2_write_block(struct ocfs2_super          *osb,
                       struct buffer_head  *bh,
                       struct inode        *inode);
-int ocfs2_read_blocks(struct ocfs2_super          *osb,
+int ocfs2_read_blocks(struct inode        *inode,
                       u64                  block,
                       int                  nr,
                       struct buffer_head  *bhs[],
-                      int                  flags,
-                      struct inode        *inode);
+                      int                  flags);
+int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
+                           unsigned int nr, struct buffer_head *bhs[]);
 
 int ocfs2_write_super_or_backup(struct ocfs2_super *osb,
                                 struct buffer_head *bh);
 
-#define OCFS2_BH_CACHED            1
+#define OCFS2_BH_IGNORE_CACHE      1
 #define OCFS2_BH_READAHEAD         8
 
-static inline int ocfs2_read_block(struct ocfs2_super * osb, u64 off,
-                                   struct buffer_head **bh, int flags,
-                                   struct inode *inode)
+static inline int ocfs2_read_block(struct inode *inode, u64 off,
+                                   struct buffer_head **bh)
 {
         int status = 0;
 
@@ -65,8 +63,7 @@ static inline int ocfs2_read_block(struct ocfs2_super * osb, u64 off,
                 goto bail;
         }
 
-        status = ocfs2_read_blocks(osb, off, 1, bh,
-                                   flags, inode);
+        status = ocfs2_read_blocks(inode, off, 1, bh, 0);
 
 bail:
         return status;
diff --git a/fs/ocfs2/cluster/masklog.c b/fs/ocfs2/cluster/masklog.c
index 23c732f27529..d8a0cb92cef6 100644
--- a/fs/ocfs2/cluster/masklog.c
+++ b/fs/ocfs2/cluster/masklog.c
@@ -109,6 +109,7 @@ static struct mlog_attribute mlog_attrs[MLOG_MAX_BITS] = {
         define_mask(CONN),
         define_mask(QUORUM),
         define_mask(EXPORT),
+        define_mask(XATTR),
         define_mask(ERROR),
         define_mask(NOTICE),
         define_mask(KTHREAD),
diff --git a/fs/ocfs2/cluster/masklog.h b/fs/ocfs2/cluster/masklog.h
index 597e064bb94f..57670c680471 100644
--- a/fs/ocfs2/cluster/masklog.h
+++ b/fs/ocfs2/cluster/masklog.h
@@ -112,6 +112,7 @@
 #define ML_CONN         0x0000000004000000ULL /* net connection management */
 #define ML_QUORUM       0x0000000008000000ULL /* net connection quorum */
 #define ML_EXPORT       0x0000000010000000ULL /* ocfs2 export operations */
+#define ML_XATTR        0x0000000020000000ULL /* ocfs2 extended attributes */
 /* 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 */
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index 9cce563fd627..026e6eb85187 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -82,6 +82,49 @@ static int ocfs2_do_extend_dir(struct super_block *sb,
                                struct ocfs2_alloc_context *meta_ac,
                                struct buffer_head **new_bh);
 
+static struct buffer_head *ocfs2_bread(struct inode *inode,
+                                       int block, int *err, int reada)
+{
+        struct buffer_head *bh = NULL;
+        int tmperr;
+        u64 p_blkno;
+        int readflags = 0;
+
+        if (reada)
+                readflags |= OCFS2_BH_READAHEAD;
+
+        if (((u64)block << inode->i_sb->s_blocksize_bits) >=
+            i_size_read(inode)) {
+                BUG_ON(!reada);
+                return NULL;
+        }
+
+        down_read(&OCFS2_I(inode)->ip_alloc_sem);
+        tmperr = ocfs2_extent_map_get_blocks(inode, block, &p_blkno, NULL,
+                                             NULL);
+        up_read(&OCFS2_I(inode)->ip_alloc_sem);
+        if (tmperr < 0) {
+                mlog_errno(tmperr);
+                goto fail;
+        }
+
+        tmperr = ocfs2_read_blocks(inode, p_blkno, 1, &bh, readflags);
+        if (tmperr < 0)
+                goto fail;
+
+        tmperr = 0;
+
+        *err = 0;
+        return bh;
+
+fail:
+        brelse(bh);
+        bh = NULL;
+
+        *err = -EIO;
+        return NULL;
+}
+
 /*
  * bh passed here can be an inode block or a dir data block, depending
  * on the inode inline data flag.
@@ -188,8 +231,7 @@ static struct buffer_head *ocfs2_find_entry_id(const char *name,
         struct ocfs2_dinode *di;
         struct ocfs2_inline_data *data;
 
-        ret = ocfs2_read_block(OCFS2_SB(dir->i_sb), OCFS2_I(dir)->ip_blkno,
-                               &di_bh, OCFS2_BH_CACHED, dir);
+        ret = ocfs2_read_block(dir, OCFS2_I(dir)->ip_blkno, &di_bh);
         if (ret) {
                 mlog_errno(ret);
                 goto out;
@@ -260,14 +302,13 @@ restart:
                 }
                 if ((bh = bh_use[ra_ptr++]) == NULL)
                         goto next;
-                wait_on_buffer(bh);
-                if (!buffer_uptodate(bh)) {
-                        /* read error, skip block & hope for the best */
+                if (ocfs2_read_block(dir, block, &bh)) {
+                        /* read error, skip block & hope for the best.
+                         * ocfs2_read_block() has released the bh. */
                         ocfs2_error(dir->i_sb, "reading directory %llu, "
                                     "offset %lu\n",
                                     (unsigned long long)OCFS2_I(dir)->ip_blkno,
                                     block);
-                        brelse(bh);
                         goto next;
                 }
                 i = ocfs2_search_dirblock(bh, dir, name, namelen,
@@ -417,8 +458,7 @@ static inline int ocfs2_delete_entry_id(handle_t *handle,
         struct ocfs2_dinode *di;
         struct ocfs2_inline_data *data;
 
-        ret = ocfs2_read_block(OCFS2_SB(dir->i_sb), OCFS2_I(dir)->ip_blkno,
-                               &di_bh, OCFS2_BH_CACHED, dir);
+        ret = ocfs2_read_block(dir, OCFS2_I(dir)->ip_blkno, &di_bh);
         if (ret) {
                 mlog_errno(ret);
                 goto out;
@@ -596,8 +636,7 @@ static int ocfs2_dir_foreach_blk_id(struct inode *inode,
         struct ocfs2_inline_data *data;
         struct ocfs2_dir_entry *de;
 
-        ret = ocfs2_read_block(OCFS2_SB(inode->i_sb), OCFS2_I(inode)->ip_blkno,
-                               &di_bh, OCFS2_BH_CACHED, inode);
+        ret = ocfs2_read_block(inode, OCFS2_I(inode)->ip_blkno, &di_bh);
         if (ret) {
                 mlog(ML_ERROR, "Unable to read inode block for dir %llu\n",
                      (unsigned long long)OCFS2_I(inode)->ip_blkno);
@@ -716,8 +755,7 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode,
                         for (i = ra_sectors >> (sb->s_blocksize_bits - 9);
                              i > 0; i--) {
                                 tmp = ocfs2_bread(inode, ++blk, &err, 1);
-                                if (tmp)
-                                        brelse(tmp);
+                                brelse(tmp);
                         }
                         last_ra_blk = blk;
                         ra_sectors = 8;
@@ -899,10 +937,8 @@ int ocfs2_find_files_on_disk(const char *name,
 leave:
         if (status < 0) {
                 *dirent = NULL;
-                if (*dirent_bh) {
-                        brelse(*dirent_bh);
-                        *dirent_bh = NULL;
-                }
+                brelse(*dirent_bh);
+                *dirent_bh = NULL;
         }
 
         mlog_exit(status);
@@ -951,8 +987,7 @@ int ocfs2_check_dir_for_entry(struct inode *dir,
 
         ret = 0;
 bail:
-        if (dirent_bh)
-                brelse(dirent_bh);
+        brelse(dirent_bh);
 
         mlog_exit(ret);
         return ret;
@@ -1127,8 +1162,7 @@ static int ocfs2_fill_new_dir_el(struct ocfs2_super *osb,
 
         status = 0;
 bail:
-        if (new_bh)
-                brelse(new_bh);
+        brelse(new_bh);
 
         mlog_exit(status);
         return status;
@@ -1192,6 +1226,9 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh,
         struct buffer_head *dirdata_bh = NULL;
         struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
         handle_t *handle;
+        struct ocfs2_extent_tree et;
+
+        ocfs2_init_dinode_extent_tree(&et, dir, di_bh);
 
         alloc = ocfs2_clusters_for_bytes(sb, bytes);
 
@@ -1305,8 +1342,8 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh,
          * This should never fail as our extent list is empty and all
          * related blocks have been journaled already.
          */
-        ret = ocfs2_insert_extent(osb, handle, dir, di_bh, 0, blkno, len, 0,
-                                  NULL);
+        ret = ocfs2_insert_extent(osb, handle, dir, &et, 0, blkno, len,
+                                  0, NULL);
         if (ret) {
                 mlog_errno(ret);
                 goto out_commit;
@@ -1337,8 +1374,8 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh,
                 }
                 blkno = ocfs2_clusters_to_blocks(dir->i_sb, bit_off);
 
-                ret = ocfs2_insert_extent(osb, handle, dir, di_bh, 1, blkno,
-                                          len, 0, NULL);
+                ret = ocfs2_insert_extent(osb, handle, dir, &et, 1,
+                                          blkno, len, 0, NULL);
                 if (ret) {
                         mlog_errno(ret);
                         goto out_commit;
@@ -1383,9 +1420,9 @@ static int ocfs2_do_extend_dir(struct super_block *sb,
         if (extend) {
                 u32 offset = OCFS2_I(dir)->ip_clusters;
 
-                status = ocfs2_do_extend_allocation(OCFS2_SB(sb), dir, &offset,
-                                                    1, 0, parent_fe_bh, handle,
-                                                    data_ac, meta_ac, NULL);
+                status = ocfs2_add_inode_data(OCFS2_SB(sb), dir, &offset,
+                                              1, 0, parent_fe_bh, handle,
+                                              data_ac, meta_ac, NULL);
                 BUG_ON(status == -EAGAIN);
                 if (status < 0) {
                         mlog_errno(status);
@@ -1430,12 +1467,14 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb,
         int credits, num_free_extents, drop_alloc_sem = 0;
         loff_t dir_i_size;
         struct ocfs2_dinode *fe = (struct ocfs2_dinode *) parent_fe_bh->b_data;
+        struct ocfs2_extent_list *el = &fe->id2.i_list;
         struct ocfs2_alloc_context *data_ac = NULL;
         struct ocfs2_alloc_context *meta_ac = NULL;
         handle_t *handle = NULL;
         struct buffer_head *new_bh = NULL;
         struct ocfs2_dir_entry * de;
         struct super_block *sb = osb->sb;
+        struct ocfs2_extent_tree et;
 
         mlog_entry_void();
 
@@ -1479,7 +1518,8 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb,
         spin_lock(&OCFS2_I(dir)->ip_lock);
         if (dir_i_size == ocfs2_clusters_to_bytes(sb, OCFS2_I(dir)->ip_clusters)) {
                 spin_unlock(&OCFS2_I(dir)->ip_lock);
-                num_free_extents = ocfs2_num_free_extents(osb, dir, fe);
+                ocfs2_init_dinode_extent_tree(&et, dir, parent_fe_bh);
+                num_free_extents = ocfs2_num_free_extents(osb, dir, &et);
                 if (num_free_extents < 0) {
                         status = num_free_extents;
                         mlog_errno(status);
@@ -1487,7 +1527,7 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb,
                 }
 
                 if (!num_free_extents) {
-                        status = ocfs2_reserve_new_metadata(osb, fe, &meta_ac);
+                        status = ocfs2_reserve_new_metadata(osb, el, &meta_ac);
                         if (status < 0) {
                                 if (status != -ENOSPC)
                                         mlog_errno(status);
@@ -1502,7 +1542,7 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb,
                         goto bail;
                 }
 
-                credits = ocfs2_calc_extend_credits(sb, fe, 1);
+                credits = ocfs2_calc_extend_credits(sb, el, 1);
         } else {
                 spin_unlock(&OCFS2_I(dir)->ip_lock);
                 credits = OCFS2_SIMPLE_DIR_EXTEND_CREDITS;
@@ -1568,8 +1608,7 @@ bail:
         if (meta_ac)
                 ocfs2_free_alloc_context(meta_ac);
 
-        if (new_bh)
-                brelse(new_bh);
+        brelse(new_bh);
 
         mlog_exit(status);
         return status;
@@ -1696,8 +1735,7 @@ static int ocfs2_find_dir_space_el(struct inode *dir, const char *name,
 
         status = 0;
 bail:
-        if (bh)
-                brelse(bh);
+        brelse(bh);
 
         mlog_exit(status);
         return status;
@@ -1756,7 +1794,6 @@ int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb,
         *ret_de_bh = bh;
         bh = NULL;
 out:
-        if (bh)
-                brelse(bh);
+        brelse(bh);
         return ret;
 }
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index eae3d643a5e4..ec684426034b 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -2024,8 +2024,7 @@ static int ocfs2_inode_lock_update(struct inode *inode,
         } else {
                 /* Boo, we have to go to disk. */
                 /* read bh, cast, ocfs2_refresh_inode */
-                status = ocfs2_read_block(OCFS2_SB(inode->i_sb), oi->ip_blkno,
-                                          bh, OCFS2_BH_CACHED, inode);
+                status = ocfs2_read_block(inode, oi->ip_blkno, bh);
                 if (status < 0) {
                         mlog_errno(status);
                         goto bail_refresh;
@@ -2086,11 +2085,7 @@ static int ocfs2_assign_bh(struct inode *inode,
                 return 0;
         }
 
-        status = ocfs2_read_block(OCFS2_SB(inode->i_sb),
-                                  OCFS2_I(inode)->ip_blkno,
-                                  ret_bh,
-                                  OCFS2_BH_CACHED,
-                                  inode);
+        status = ocfs2_read_block(inode, OCFS2_I(inode)->ip_blkno, ret_bh);
         if (status < 0)
                 mlog_errno(status);
 
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index c58668a326fe..2baedac58234 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -25,6 +25,7 @@
 #include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/types.h>
+#include <linux/fiemap.h>
 
 #define MLOG_MASK_PREFIX ML_EXTENT_MAP
 #include <cluster/masklog.h>
@@ -32,6 +33,7 @@
 #include "ocfs2.h"
 
 #include "alloc.h"
+#include "dlmglue.h"
 #include "extent_map.h"
 #include "inode.h"
 #include "super.h"
@@ -282,6 +284,50 @@ out:
                 kfree(new_emi);
 }
 
+static int ocfs2_last_eb_is_empty(struct inode *inode,
+                                  struct ocfs2_dinode *di)
+{
+        int ret, next_free;
+        u64 last_eb_blk = le64_to_cpu(di->i_last_eb_blk);
+        struct buffer_head *eb_bh = NULL;
+        struct ocfs2_extent_block *eb;
+        struct ocfs2_extent_list *el;
+
+        ret = ocfs2_read_block(inode, last_eb_blk, &eb_bh);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        eb = (struct ocfs2_extent_block *) eb_bh->b_data;
+        el = &eb->h_list;
+
+        if (!OCFS2_IS_VALID_EXTENT_BLOCK(eb)) {
+                ret = -EROFS;
+                OCFS2_RO_ON_INVALID_EXTENT_BLOCK(inode->i_sb, eb);
+                goto out;
+        }
+
+        if (el->l_tree_depth) {
+                ocfs2_error(inode->i_sb,
+                            "Inode %lu has non zero tree depth in "
+                            "leaf block %llu\n", inode->i_ino,
+                            (unsigned long long)eb_bh->b_blocknr);
+                ret = -EROFS;
+                goto out;
+        }
+
+        next_free = le16_to_cpu(el->l_next_free_rec);
+
+        if (next_free == 0 ||
+            (next_free == 1 && ocfs2_is_empty_extent(&el->l_recs[0])))
+                ret = 1;
+
+out:
+        brelse(eb_bh);
+        return ret;
+}
+
 /*
  * Return the 1st index within el which contains an extent start
  * larger than v_cluster.
@@ -335,9 +381,9 @@ static int ocfs2_figure_hole_clusters(struct inode *inode,
                 if (le64_to_cpu(eb->h_next_leaf_blk) == 0ULL)
                         goto no_more_extents;
 
-                ret = ocfs2_read_block(OCFS2_SB(inode->i_sb),
+                ret = ocfs2_read_block(inode,
                                        le64_to_cpu(eb->h_next_leaf_blk),
-                                       &next_eb_bh, OCFS2_BH_CACHED, inode);
+                                       &next_eb_bh);
                 if (ret) {
                         mlog_errno(ret);
                         goto out;
@@ -373,42 +419,28 @@ out:
         return ret;
 }
 
-int ocfs2_get_clusters(struct inode *inode, u32 v_cluster,
-                       u32 *p_cluster, u32 *num_clusters,
-                       unsigned int *extent_flags)
+static int ocfs2_get_clusters_nocache(struct inode *inode,
+                                      struct buffer_head *di_bh,
+                                      u32 v_cluster, unsigned int *hole_len,
+                                      struct ocfs2_extent_rec *ret_rec,
+                                      unsigned int *is_last)
 {
-        int ret, i;
-        unsigned int flags = 0;
-        struct buffer_head *di_bh = NULL;
-        struct buffer_head *eb_bh = NULL;
+        int i, ret, tree_height, len;
         struct ocfs2_dinode *di;
-        struct ocfs2_extent_block *eb;
+        struct ocfs2_extent_block *uninitialized_var(eb);
         struct ocfs2_extent_list *el;
         struct ocfs2_extent_rec *rec;
-        u32 coff;
-
-        if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
-                ret = -ERANGE;
-                mlog_errno(ret);
-                goto out;
-        }
-
-        ret = ocfs2_extent_map_lookup(inode, v_cluster, p_cluster,
-                                      num_clusters, extent_flags);
-        if (ret == 0)
-                goto out;
+        struct buffer_head *eb_bh = NULL;
 
-        ret = ocfs2_read_block(OCFS2_SB(inode->i_sb), OCFS2_I(inode)->ip_blkno,
-                               &di_bh, OCFS2_BH_CACHED, inode);
-        if (ret) {
-                mlog_errno(ret);
-                goto out;
-        }
+        memset(ret_rec, 0, sizeof(*ret_rec));
+        if (is_last)
+                *is_last = 0;
 
         di = (struct ocfs2_dinode *) di_bh->b_data;
         el = &di->id2.i_list;
+        tree_height = le16_to_cpu(el->l_tree_depth);
 
-        if (el->l_tree_depth) {
+        if (tree_height > 0) {
                 ret = ocfs2_find_leaf(inode, el, v_cluster, &eb_bh);
                 if (ret) {
                         mlog_errno(ret);
@@ -431,46 +463,202 @@ int ocfs2_get_clusters(struct inode *inode, u32 v_cluster,
         i = ocfs2_search_extent_list(el, v_cluster);
         if (i == -1) {
                 /*
-                 * A hole was found. Return some canned values that
-                 * callers can key on. If asked for, num_clusters will
-                 * be populated with the size of the hole.
+                 * Holes can be larger than the maximum size of an
+                 * extent, so we return their lengths in a seperate
+                 * field.
                  */
-                *p_cluster = 0;
-                if (num_clusters) {
+                if (hole_len) {
                         ret = ocfs2_figure_hole_clusters(inode, el, eb_bh,
-                                                         v_cluster,
-                                                         num_clusters);
+                                                         v_cluster, &len);
                         if (ret) {
                                 mlog_errno(ret);
                                 goto out;
                         }
+
+                        *hole_len = len;
+                }
+                goto out_hole;
+        }
+
+        rec = &el->l_recs[i];
+
+        BUG_ON(v_cluster < le32_to_cpu(rec->e_cpos));
+
+        if (!rec->e_blkno) {
+                ocfs2_error(inode->i_sb, "Inode %lu has bad extent "
+                            "record (%u, %u, 0)", inode->i_ino,
+                            le32_to_cpu(rec->e_cpos),
+                            ocfs2_rec_clusters(el, rec));
+                ret = -EROFS;
+                goto out;
+        }
+
+        *ret_rec = *rec;
+
+        /*
+         * Checking for last extent is potentially expensive - we
+         * might have to look at the next leaf over to see if it's
+         * empty.
+         *
+         * The first two checks are to see whether the caller even
+         * cares for this information, and if the extent is at least
+         * the last in it's list.
+         *
+         * If those hold true, then the extent is last if any of the
+         * additional conditions hold true:
+         *  - Extent list is in-inode
+         *  - Extent list is right-most
+         *  - Extent list is 2nd to rightmost, with empty right-most
+         */
+        if (is_last) {
+                if (i == (le16_to_cpu(el->l_next_free_rec) - 1)) {
+                        if (tree_height == 0)
+                                *is_last = 1;
+                        else if (eb->h_blkno == di->i_last_eb_blk)
+                                *is_last = 1;
+                        else if (eb->h_next_leaf_blk == di->i_last_eb_blk) {
+                                ret = ocfs2_last_eb_is_empty(inode, di);
+                                if (ret < 0) {
+                                        mlog_errno(ret);
+                                        goto out;
+                                }
+                                if (ret == 1)
+                                        *is_last = 1;
+                        }
+                }
+        }
+
+out_hole:
+        ret = 0;
+out:
+        brelse(eb_bh);
+        return ret;
+}
+
+static void ocfs2_relative_extent_offsets(struct super_block *sb,
+                                          u32 v_cluster,
+                                          struct ocfs2_extent_rec *rec,
+                                          u32 *p_cluster, u32 *num_clusters)
+
+{
+        u32 coff = v_cluster - le32_to_cpu(rec->e_cpos);
+
+        *p_cluster = ocfs2_blocks_to_clusters(sb, le64_to_cpu(rec->e_blkno));
+        *p_cluster = *p_cluster + coff;
+
+        if (num_clusters)
+                *num_clusters = le16_to_cpu(rec->e_leaf_clusters) - coff;
+}
+
+int ocfs2_xattr_get_clusters(struct inode *inode, u32 v_cluster,
+                             u32 *p_cluster, u32 *num_clusters,
+                             struct ocfs2_extent_list *el)
+{
+        int ret = 0, i;
+        struct buffer_head *eb_bh = NULL;
+        struct ocfs2_extent_block *eb;
+        struct ocfs2_extent_rec *rec;
+        u32 coff;
+
+        if (el->l_tree_depth) {
+                ret = ocfs2_find_leaf(inode, el, v_cluster, &eb_bh);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
                 }
+
+                eb = (struct ocfs2_extent_block *) eb_bh->b_data;
+                el = &eb->h_list;
+
+                if (el->l_tree_depth) {
+                        ocfs2_error(inode->i_sb,
+                                    "Inode %lu has non zero tree depth in "
+                                    "xattr leaf block %llu\n", inode->i_ino,
+                                    (unsigned long long)eb_bh->b_blocknr);
+                        ret = -EROFS;
+                        goto out;
+                }
+        }
+
+        i = ocfs2_search_extent_list(el, v_cluster);
+        if (i == -1) {
+                ret = -EROFS;
+                mlog_errno(ret);
+                goto out;
         } else {
                 rec = &el->l_recs[i];
-
                 BUG_ON(v_cluster < le32_to_cpu(rec->e_cpos));
 
                 if (!rec->e_blkno) {
                         ocfs2_error(inode->i_sb, "Inode %lu has bad extent "
-                                    "record (%u, %u, 0)", inode->i_ino,
+                                    "record (%u, %u, 0) in xattr", inode->i_ino,
                                     le32_to_cpu(rec->e_cpos),
                                     ocfs2_rec_clusters(el, rec));
                         ret = -EROFS;
                         goto out;
                 }
-
                 coff = v_cluster - le32_to_cpu(rec->e_cpos);
-
                 *p_cluster = ocfs2_blocks_to_clusters(inode->i_sb,
                                                     le64_to_cpu(rec->e_blkno));
                 *p_cluster = *p_cluster + coff;
-
                 if (num_clusters)
                         *num_clusters = ocfs2_rec_clusters(el, rec) - coff;
+        }
+out:
+        if (eb_bh)
+                brelse(eb_bh);
+        return ret;
+}
+
+int ocfs2_get_clusters(struct inode *inode, u32 v_cluster,
+                       u32 *p_cluster, u32 *num_clusters,
+                       unsigned int *extent_flags)
+{
+        int ret;
+        unsigned int uninitialized_var(hole_len), flags = 0;
+        struct buffer_head *di_bh = NULL;
+        struct ocfs2_extent_rec rec;
+
+        if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+                ret = -ERANGE;
+                mlog_errno(ret);
+                goto out;
+        }
+
+        ret = ocfs2_extent_map_lookup(inode, v_cluster, p_cluster,
+                                      num_clusters, extent_flags);
+        if (ret == 0)
+                goto out;
+
+        ret = ocfs2_read_block(inode, OCFS2_I(inode)->ip_blkno, &di_bh);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
 
-                flags = rec->e_flags;
+        ret = ocfs2_get_clusters_nocache(inode, di_bh, v_cluster, &hole_len,
+                                         &rec, NULL);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        if (rec.e_blkno == 0ULL) {
+                /*
+                 * A hole was found. Return some canned values that
+                 * callers can key on. If asked for, num_clusters will
+                 * be populated with the size of the hole.
+                 */
+                *p_cluster = 0;
+                if (num_clusters) {
+                        *num_clusters = hole_len;
+                }
+        } else {
+                ocfs2_relative_extent_offsets(inode->i_sb, v_cluster, &rec,
+                                              p_cluster, num_clusters);
+                flags = rec.e_flags;
 
-                ocfs2_extent_map_insert_rec(inode, rec);
+                ocfs2_extent_map_insert_rec(inode, &rec);
         }
 
         if (extent_flags)
@@ -478,7 +666,6 @@ int ocfs2_get_clusters(struct inode *inode, u32 v_cluster,
 
 out:
         brelse(di_bh);
-        brelse(eb_bh);
         return ret;
 }
 
@@ -521,3 +708,114 @@ int ocfs2_extent_map_get_blocks(struct inode *inode, u64 v_blkno, u64 *p_blkno,
 out:
         return ret;
 }
+
+static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh,
+                               struct fiemap_extent_info *fieinfo,
+                               u64 map_start)
+{
+        int ret;
+        unsigned int id_count;
+        struct ocfs2_dinode *di;
+        u64 phys;
+        u32 flags = FIEMAP_EXTENT_DATA_INLINE|FIEMAP_EXTENT_LAST;
+        struct ocfs2_inode_info *oi = OCFS2_I(inode);
+
+        di = (struct ocfs2_dinode *)di_bh->b_data;
+        id_count = le16_to_cpu(di->id2.i_data.id_count);
+
+        if (map_start < id_count) {
+                phys = oi->ip_blkno << inode->i_sb->s_blocksize_bits;
+                phys += offsetof(struct ocfs2_dinode, id2.i_data.id_data);
+
+                ret = fiemap_fill_next_extent(fieinfo, 0, phys, id_count,
+                                              flags);
+                if (ret < 0)
+                        return ret;
+        }
+
+        return 0;
+}
+
+#define OCFS2_FIEMAP_FLAGS      (FIEMAP_FLAG_SYNC)
+
+int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+                 u64 map_start, u64 map_len)
+{
+        int ret, is_last;
+        u32 mapping_end, cpos;
+        unsigned int hole_size;
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+        u64 len_bytes, phys_bytes, virt_bytes;
+        struct buffer_head *di_bh = NULL;
+        struct ocfs2_extent_rec rec;
+
+        ret = fiemap_check_flags(fieinfo, OCFS2_FIEMAP_FLAGS);
+        if (ret)
+                return ret;
+
+        ret = ocfs2_inode_lock(inode, &di_bh, 0);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        down_read(&OCFS2_I(inode)->ip_alloc_sem);
+
+        /*
+         * Handle inline-data separately.
+         */
+        if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+                ret = ocfs2_fiemap_inline(inode, di_bh, fieinfo, map_start);
+                goto out_unlock;
+        }
+
+        cpos = map_start >> osb->s_clustersize_bits;
+        mapping_end = ocfs2_clusters_for_bytes(inode->i_sb,
+                                               map_start + map_len);
+        mapping_end -= cpos;
+        is_last = 0;
+        while (cpos < mapping_end && !is_last) {
+                u32 fe_flags;
+
+                ret = ocfs2_get_clusters_nocache(inode, di_bh, cpos,
+                                                 &hole_size, &rec, &is_last);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+
+                if (rec.e_blkno == 0ULL) {
+                        cpos += hole_size;
+                        continue;
+                }
+
+                fe_flags = 0;
+                if (rec.e_flags & OCFS2_EXT_UNWRITTEN)
+                        fe_flags |= FIEMAP_EXTENT_UNWRITTEN;
+                if (is_last)
+                        fe_flags |= FIEMAP_EXTENT_LAST;
+                len_bytes = (u64)le16_to_cpu(rec.e_leaf_clusters) << osb->s_clustersize_bits;
+                phys_bytes = le64_to_cpu(rec.e_blkno) << osb->sb->s_blocksize_bits;
+                virt_bytes = (u64)le32_to_cpu(rec.e_cpos) << osb->s_clustersize_bits;
+
+                ret = fiemap_fill_next_extent(fieinfo, virt_bytes, phys_bytes,
+                                              len_bytes, fe_flags);
+                if (ret)
+                        break;
+
+                cpos = le32_to_cpu(rec.e_cpos)+ le16_to_cpu(rec.e_leaf_clusters);
+        }
+
+        if (ret > 0)
+                ret = 0;
+
+out_unlock:
+        brelse(di_bh);
+
+        up_read(&OCFS2_I(inode)->ip_alloc_sem);
+
+        ocfs2_inode_unlock(inode, 0);
+out:
+
+        return ret;
+}
diff --git a/fs/ocfs2/extent_map.h b/fs/ocfs2/extent_map.h
index de91e3e41a22..1c4aa8b06f34 100644
--- a/fs/ocfs2/extent_map.h
+++ b/fs/ocfs2/extent_map.h
@@ -50,4 +50,11 @@ int ocfs2_get_clusters(struct inode *inode, u32 v_cluster, u32 *p_cluster,
 int ocfs2_extent_map_get_blocks(struct inode *inode, u64 v_blkno, u64 *p_blkno,
                                 u64 *ret_count, unsigned int *extent_flags);
 
+int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+                 u64 map_start, u64 map_len);
+
+int ocfs2_xattr_get_clusters(struct inode *inode, u32 v_cluster,
+                             u32 *p_cluster, u32 *num_clusters,
+                             struct ocfs2_extent_list *el);
+
 #endif  /* _EXTENT_MAP_H */
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index ec2ed15c3daa..8d3225a78073 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -55,6 +55,7 @@
 #include "mmap.h"
 #include "suballoc.h"
 #include "super.h"
+#include "xattr.h"
 
 #include "buffer_head_io.h"
 
@@ -184,7 +185,7 @@ static int ocfs2_sync_file(struct file *file,
                 goto bail;
 
         journal = osb->journal->j_journal;
-        err = journal_force_commit(journal);
+        err = jbd2_journal_force_commit(journal);
 
 bail:
         mlog_exit(err);
@@ -488,7 +489,7 @@ bail:
 }
 
 /*
- * extend allocation only here.
+ * extend file allocation only here.
  * we'll update all the disk stuff, and oip->alloc_size
  *
  * expect stuff to be locked, a transaction started and enough data /
@@ -497,189 +498,25 @@ bail:
  * Will return -EAGAIN, and a reason if a restart is needed.
  * If passed in, *reason will always be set, even in error.
  */
-int ocfs2_do_extend_allocation(struct ocfs2_super *osb,
-                               struct inode *inode,
-                               u32 *logical_offset,
-                               u32 clusters_to_add,
-                               int mark_unwritten,
-                               struct buffer_head *fe_bh,
-                               handle_t *handle,
-                               struct ocfs2_alloc_context *data_ac,
-                               struct ocfs2_alloc_context *meta_ac,
-                               enum ocfs2_alloc_restarted *reason_ret)
+int ocfs2_add_inode_data(struct ocfs2_super *osb,
+                         struct inode *inode,
+                         u32 *logical_offset,
+                         u32 clusters_to_add,
+                         int mark_unwritten,
+                         struct buffer_head *fe_bh,
+                         handle_t *handle,
+                         struct ocfs2_alloc_context *data_ac,
+                         struct ocfs2_alloc_context *meta_ac,
+                         enum ocfs2_alloc_restarted *reason_ret)
 {
-        int status = 0;
-        int free_extents;
-        struct ocfs2_dinode *fe = (struct ocfs2_dinode *) fe_bh->b_data;
-        enum ocfs2_alloc_restarted reason = RESTART_NONE;
-        u32 bit_off, num_bits;
-        u64 block;
-        u8 flags = 0;
-
-        BUG_ON(!clusters_to_add);
-
-        if (mark_unwritten)
-                flags = OCFS2_EXT_UNWRITTEN;
-
-        free_extents = ocfs2_num_free_extents(osb, inode, fe);
-        if (free_extents < 0) {
-                status = free_extents;
-                mlog_errno(status);
-                goto leave;
-        }
-
-        /* there are two cases which could cause us to EAGAIN in the
-         * we-need-more-metadata case:
-         * 1) we haven't reserved *any*
-         * 2) we are so fragmented, we've needed to add metadata too
-         *    many times. */
-        if (!free_extents && !meta_ac) {
-                mlog(0, "we haven't reserved any metadata!\n");
-                status = -EAGAIN;
-                reason = RESTART_META;
-                goto leave;
-        } else if ((!free_extents)
-                   && (ocfs2_alloc_context_bits_left(meta_ac)
-                       < ocfs2_extend_meta_needed(fe))) {
-                mlog(0, "filesystem is really fragmented...\n");
-                status = -EAGAIN;
-                reason = RESTART_META;
-                goto leave;
-        }
-
-        status = __ocfs2_claim_clusters(osb, handle, data_ac, 1,
-                                        clusters_to_add, &bit_off, &num_bits);
-        if (status < 0) {
-                if (status != -ENOSPC)
-                        mlog_errno(status);
-                goto leave;
-        }
-
-        BUG_ON(num_bits > clusters_to_add);
-
-        /* reserve our write early -- insert_extent may update the inode */
-        status = ocfs2_journal_access(handle, inode, fe_bh,
-                                      OCFS2_JOURNAL_ACCESS_WRITE);
-        if (status < 0) {
-                mlog_errno(status);
-                goto leave;
-        }
-
-        block = ocfs2_clusters_to_blocks(osb->sb, bit_off);
-        mlog(0, "Allocating %u clusters at block %u for inode %llu\n",
-             num_bits, bit_off, (unsigned long long)OCFS2_I(inode)->ip_blkno);
-        status = ocfs2_insert_extent(osb, handle, inode, fe_bh,
-                                     *logical_offset, block, num_bits,
-                                     flags, meta_ac);
-        if (status < 0) {
-                mlog_errno(status);
-                goto leave;
-        }
-
-        status = ocfs2_journal_dirty(handle, fe_bh);
-        if (status < 0) {
-                mlog_errno(status);
-                goto leave;
-        }
-
-        clusters_to_add -= num_bits;
-        *logical_offset += num_bits;
-
-        if (clusters_to_add) {
-                mlog(0, "need to alloc once more, clusters = %u, wanted = "
-                     "%u\n", fe->i_clusters, clusters_to_add);
-                status = -EAGAIN;
-                reason = RESTART_TRANS;
-        }
-
-leave:
-        mlog_exit(status);
-        if (reason_ret)
-                *reason_ret = reason;
-        return status;
-}
-
-/*
- * For a given allocation, determine which allocators will need to be
- * accessed, and lock them, reserving the appropriate number of bits.
- *
- * Sparse file systems call this from ocfs2_write_begin_nolock()
- * and ocfs2_allocate_unwritten_extents().
- *
- * File systems which don't support holes call this from
- * ocfs2_extend_allocation().
- */
-int ocfs2_lock_allocators(struct inode *inode, struct ocfs2_dinode *di,
-                          u32 clusters_to_add, u32 extents_to_split,
-                          struct ocfs2_alloc_context **data_ac,
-                          struct ocfs2_alloc_context **meta_ac)
-{
-        int ret = 0, num_free_extents;
-        unsigned int max_recs_needed = clusters_to_add + 2 * extents_to_split;
-        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
-
-        *meta_ac = NULL;
-        if (data_ac)
-                *data_ac = NULL;
-
-        BUG_ON(clusters_to_add != 0 && data_ac == NULL);
-
-        mlog(0, "extend inode %llu, i_size = %lld, di->i_clusters = %u, "
-             "clusters_to_add = %u, extents_to_split = %u\n",
-             (unsigned long long)OCFS2_I(inode)->ip_blkno, (long long)i_size_read(inode),
-             le32_to_cpu(di->i_clusters), clusters_to_add, extents_to_split);
-
-        num_free_extents = ocfs2_num_free_extents(osb, inode, di);
-        if (num_free_extents < 0) {
-                ret = num_free_extents;
-                mlog_errno(ret);
-                goto out;
-        }
-
-        /*
-         * Sparse allocation file systems need to be more conservative
-         * with reserving room for expansion - the actual allocation
-         * happens while we've got a journal handle open so re-taking
-         * a cluster lock (because we ran out of room for another
-         * extent) will violate ordering rules.
-         *
-         * Most of the time we'll only be seeing this 1 cluster at a time
-         * anyway.
-         *
-         * Always lock for any unwritten extents - we might want to
-         * add blocks during a split.
-         */
-        if (!num_free_extents ||
-            (ocfs2_sparse_alloc(osb) && num_free_extents < max_recs_needed)) {
-                ret = ocfs2_reserve_new_metadata(osb, di, meta_ac);
-                if (ret < 0) {
-                        if (ret != -ENOSPC)
-                                mlog_errno(ret);
-                        goto out;
-                }
-        }
-
-        if (clusters_to_add == 0)
-                goto out;
-
-        ret = ocfs2_reserve_clusters(osb, clusters_to_add, data_ac);
-        if (ret < 0) {
-                if (ret != -ENOSPC)
-                        mlog_errno(ret);
-                goto out;
-        }
-
-out:
-        if (ret) {
-                if (*meta_ac) {
-                        ocfs2_free_alloc_context(*meta_ac);
-                        *meta_ac = NULL;
-                }
+        int ret;
+        struct ocfs2_extent_tree et;
 
-                /*
-                 * We cannot have an error and a non null *data_ac.
-                 */
-        }
+        ocfs2_init_dinode_extent_tree(&et, inode, fe_bh);
+        ret = ocfs2_add_clusters_in_btree(osb, inode, logical_offset,
+                                           clusters_to_add, mark_unwritten,
+                                           &et, handle,
+                                           data_ac, meta_ac, reason_ret);
 
         return ret;
 }
@@ -698,6 +535,7 @@ static int __ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
         struct ocfs2_alloc_context *meta_ac = NULL;
         enum ocfs2_alloc_restarted why;
         struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+        struct ocfs2_extent_tree et;
 
         mlog_entry("(clusters_to_add = %u)\n", clusters_to_add);
 
@@ -707,8 +545,7 @@ static int __ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
          */
         BUG_ON(mark_unwritten && !ocfs2_sparse_alloc(osb));
 
-        status = ocfs2_read_block(osb, OCFS2_I(inode)->ip_blkno, &bh,
-                                  OCFS2_BH_CACHED, inode);
+        status = ocfs2_read_block(inode, OCFS2_I(inode)->ip_blkno, &bh);
         if (status < 0) {
                 mlog_errno(status);
                 goto leave;
@@ -724,14 +561,21 @@ static int __ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
 restart_all:
         BUG_ON(le32_to_cpu(fe->i_clusters) != OCFS2_I(inode)->ip_clusters);
 
-        status = ocfs2_lock_allocators(inode, fe, clusters_to_add, 0, &data_ac,
-                                       &meta_ac);
+        mlog(0, "extend inode %llu, i_size = %lld, di->i_clusters = %u, "
+             "clusters_to_add = %u\n",
+             (unsigned long long)OCFS2_I(inode)->ip_blkno,
+             (long long)i_size_read(inode), le32_to_cpu(fe->i_clusters),
+             clusters_to_add);
+        ocfs2_init_dinode_extent_tree(&et, inode, bh);
+        status = ocfs2_lock_allocators(inode, &et, clusters_to_add, 0,
+                                       &data_ac, &meta_ac);
         if (status) {
                 mlog_errno(status);
                 goto leave;
         }
 
-        credits = ocfs2_calc_extend_credits(osb->sb, fe, clusters_to_add);
+        credits = ocfs2_calc_extend_credits(osb->sb, &fe->id2.i_list,
+                                            clusters_to_add);
         handle = ocfs2_start_trans(osb, credits);
         if (IS_ERR(handle)) {
                 status = PTR_ERR(handle);
@@ -753,16 +597,16 @@ restarted_transaction:
 
         prev_clusters = OCFS2_I(inode)->ip_clusters;
 
-        status = ocfs2_do_extend_allocation(osb,
-                                            inode,
-                                            &logical_start,
-                                            clusters_to_add,
-                                            mark_unwritten,
-                                            bh,
-                                            handle,
-                                            data_ac,
-                                            meta_ac,
-                                            &why);
+        status = ocfs2_add_inode_data(osb,
+                                      inode,
+                                      &logical_start,
+                                      clusters_to_add,
+                                      mark_unwritten,
+                                      bh,
+                                      handle,
+                                      data_ac,
+                                      meta_ac,
+                                      &why);
         if ((status < 0) && (status != -EAGAIN)) {
                 if (status != -ENOSPC)
                         mlog_errno(status);
@@ -789,7 +633,7 @@ restarted_transaction:
                         mlog(0, "restarting transaction.\n");
                         /* TODO: This can be more intelligent. */
                         credits = ocfs2_calc_extend_credits(osb->sb,
-                                                            fe,
+                                                            &fe->id2.i_list,
                                                             clusters_to_add);
                         status = ocfs2_extend_trans(handle, credits);
                         if (status < 0) {
@@ -826,10 +670,8 @@ leave:
                 restart_func = 0;
                 goto restart_all;
         }
-        if (bh) {
-                brelse(bh);
-                bh = NULL;
-        }
+        brelse(bh);
+        bh = NULL;
 
         mlog_exit(status);
         return status;
@@ -1096,9 +938,15 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
                         goto bail_unlock;
                 }
 
-                if (i_size_read(inode) > attr->ia_size)
+                if (i_size_read(inode) > attr->ia_size) {
+                        if (ocfs2_should_order_data(inode)) {
+                                status = ocfs2_begin_ordered_truncate(inode,
+                                                                      attr->ia_size);
+                                if (status)
+                                        goto bail_unlock;
+                        }
                         status = ocfs2_truncate_file(inode, bh, attr->ia_size);
-                else
+                } else
                         status = ocfs2_extend_file(inode, bh, attr->ia_size);
                 if (status < 0) {
                         if (status != -ENOSPC)
@@ -1140,8 +988,7 @@ bail_unlock_rw:
         if (size_change)
                 ocfs2_rw_unlock(inode, 1);
 bail:
-        if (bh)
-                brelse(bh);
+        brelse(bh);
 
         mlog_exit(status);
         return status;
@@ -1284,8 +1131,7 @@ static int ocfs2_write_remove_suid(struct inode *inode)
         struct buffer_head *bh = NULL;
         struct ocfs2_inode_info *oi = OCFS2_I(inode);
 
-        ret = ocfs2_read_block(OCFS2_SB(inode->i_sb),
-                               oi->ip_blkno, &bh, OCFS2_BH_CACHED, inode);
+        ret = ocfs2_read_block(inode, oi->ip_blkno, &bh);
         if (ret < 0) {
                 mlog_errno(ret);
                 goto out;
@@ -1311,9 +1157,8 @@ static int ocfs2_allocate_unwritten_extents(struct inode *inode,
         struct buffer_head *di_bh = NULL;
 
         if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
-                ret = ocfs2_read_block(OCFS2_SB(inode->i_sb),
-                                       OCFS2_I(inode)->ip_blkno, &di_bh,
-                                       OCFS2_BH_CACHED, inode);
+                ret = ocfs2_read_block(inode, OCFS2_I(inode)->ip_blkno,
+                                       &di_bh);
                 if (ret) {
                         mlog_errno(ret);
                         goto out;
@@ -1394,8 +1239,11 @@ static int __ocfs2_remove_inode_range(struct inode *inode,
         handle_t *handle;
         struct ocfs2_alloc_context *meta_ac = NULL;
         struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
+        struct ocfs2_extent_tree et;
 
-        ret = ocfs2_lock_allocators(inode, di, 0, 1, NULL, &meta_ac);
+        ocfs2_init_dinode_extent_tree(&et, inode, di_bh);
+
+        ret = ocfs2_lock_allocators(inode, &et, 0, 1, NULL, &meta_ac);
         if (ret) {
                 mlog_errno(ret);
                 return ret;
@@ -1425,7 +1273,7 @@ static int __ocfs2_remove_inode_range(struct inode *inode,
                 goto out;
         }
 
-        ret = ocfs2_remove_extent(inode, di_bh, cpos, len, handle, meta_ac,
+        ret = ocfs2_remove_extent(inode, &et, cpos, len, handle, meta_ac,
                                   dealloc);
         if (ret) {
                 mlog_errno(ret);
@@ -2040,7 +1888,7 @@ out_dio:
                  */
                 if (old_size != i_size_read(inode) ||
                     old_clusters != OCFS2_I(inode)->ip_clusters) {
-                        ret = journal_force_commit(osb->journal->j_journal);
+                        ret = jbd2_journal_force_commit(osb->journal->j_journal);
                         if (ret < 0)
                                 written = ret;
                 }
@@ -2227,7 +2075,12 @@ const struct inode_operations ocfs2_file_iops = {
         .setattr        = ocfs2_setattr,
         .getattr        = ocfs2_getattr,
         .permission     = ocfs2_permission,
+        .setxattr       = generic_setxattr,
+        .getxattr       = generic_getxattr,
+        .listxattr      = ocfs2_listxattr,
+        .removexattr    = generic_removexattr,
         .fallocate      = ocfs2_fallocate,
+        .fiemap         = ocfs2_fiemap,
 };
 
 const struct inode_operations ocfs2_special_file_iops = {
@@ -2236,6 +2089,10 @@ const struct inode_operations ocfs2_special_file_iops = {
         .permission     = ocfs2_permission,
 };
 
+/*
+ * Other than ->lock, keep ocfs2_fops and ocfs2_dops in sync with
+ * ocfs2_fops_no_plocks and ocfs2_dops_no_plocks!
+ */
 const struct file_operations ocfs2_fops = {
         .llseek         = generic_file_llseek,
         .read           = do_sync_read,
@@ -2250,6 +2107,7 @@ const struct file_operations ocfs2_fops = {
 #ifdef CONFIG_COMPAT
         .compat_ioctl   = ocfs2_compat_ioctl,
 #endif
+        .lock           = ocfs2_lock,
         .flock          = ocfs2_flock,
         .splice_read    = ocfs2_file_splice_read,
         .splice_write   = ocfs2_file_splice_write,
@@ -2266,5 +2124,51 @@ const struct file_operations ocfs2_dops = {
 #ifdef CONFIG_COMPAT
         .compat_ioctl   = ocfs2_compat_ioctl,
 #endif
+        .lock           = ocfs2_lock,
+        .flock          = ocfs2_flock,
+};
+
+/*
+ * POSIX-lockless variants of our file_operations.
+ *
+ * These will be used if the underlying cluster stack does not support
+ * posix file locking, if the user passes the "localflocks" mount
+ * option, or if we have a local-only fs.
+ *
+ * ocfs2_flock is in here because all stacks handle UNIX file locks,
+ * so we still want it in the case of no stack support for
+ * plocks. Internally, it will do the right thing when asked to ignore
+ * the cluster.
+ */
+const struct file_operations ocfs2_fops_no_plocks = {
+        .llseek         = generic_file_llseek,
+        .read           = do_sync_read,
+        .write          = do_sync_write,
+        .mmap           = ocfs2_mmap,
+        .fsync          = ocfs2_sync_file,
+        .release        = ocfs2_file_release,
+        .open           = ocfs2_file_open,
+        .aio_read       = ocfs2_file_aio_read,
+        .aio_write      = ocfs2_file_aio_write,
+        .unlocked_ioctl = ocfs2_ioctl,
+#ifdef CONFIG_COMPAT
+        .compat_ioctl   = ocfs2_compat_ioctl,
+#endif
+        .flock          = ocfs2_flock,
+        .splice_read    = ocfs2_file_splice_read,
+        .splice_write   = ocfs2_file_splice_write,
+};
+
+const struct file_operations ocfs2_dops_no_plocks = {
+        .llseek         = generic_file_llseek,
+        .read           = generic_read_dir,
+        .readdir        = ocfs2_readdir,
+        .fsync          = ocfs2_sync_file,
+        .release        = ocfs2_dir_release,
+        .open           = ocfs2_dir_open,
+        .unlocked_ioctl = ocfs2_ioctl,
+#ifdef CONFIG_COMPAT
+        .compat_ioctl   = ocfs2_compat_ioctl,
+#endif
         .flock          = ocfs2_flock,
 };
diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h
index 1e27b4d017ea..e92382cbca5f 100644
--- a/fs/ocfs2/file.h
+++ b/fs/ocfs2/file.h
@@ -28,9 +28,12 @@
 
 extern const struct file_operations ocfs2_fops;
 extern const struct file_operations ocfs2_dops;
+extern const struct file_operations ocfs2_fops_no_plocks;
+extern const struct file_operations ocfs2_dops_no_plocks;
 extern const struct inode_operations ocfs2_file_iops;
 extern const struct inode_operations ocfs2_special_file_iops;
 struct ocfs2_alloc_context;
+enum ocfs2_alloc_restarted;
 
 struct ocfs2_file_private {
         struct file             *fp_file;
@@ -38,27 +41,18 @@ struct ocfs2_file_private {
         struct ocfs2_lock_res   fp_flock;
 };
 
-enum ocfs2_alloc_restarted {
-        RESTART_NONE = 0,
-        RESTART_TRANS,
-        RESTART_META
-};
-int ocfs2_do_extend_allocation(struct ocfs2_super *osb,
-                               struct inode *inode,
-                               u32 *logical_offset,
-                               u32 clusters_to_add,
-                               int mark_unwritten,
-                               struct buffer_head *fe_bh,
-                               handle_t *handle,
-                               struct ocfs2_alloc_context *data_ac,
-                               struct ocfs2_alloc_context *meta_ac,
-                               enum ocfs2_alloc_restarted *reason_ret);
+int ocfs2_add_inode_data(struct ocfs2_super *osb,
+                         struct inode *inode,
+                         u32 *logical_offset,
+                         u32 clusters_to_add,
+                         int mark_unwritten,
+                         struct buffer_head *fe_bh,
+                         handle_t *handle,
+                         struct ocfs2_alloc_context *data_ac,
+                         struct ocfs2_alloc_context *meta_ac,
+                         enum ocfs2_alloc_restarted *reason_ret);
 int ocfs2_extend_no_holes(struct inode *inode, u64 new_i_size,
                           u64 zero_to);
-int ocfs2_lock_allocators(struct inode *inode, struct ocfs2_dinode *di,
-                          u32 clusters_to_add, u32 extents_to_split,
-                          struct ocfs2_alloc_context **data_ac,
-                          struct ocfs2_alloc_context **meta_ac);
 int ocfs2_setattr(struct dentry *dentry, struct iattr *attr);
 int ocfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
                   struct kstat *stat);
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 7e9e4c79aec7..4903688f72a9 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -49,6 +49,7 @@
 #include "symlink.h"
 #include "sysfile.h"
 #include "uptodate.h"
+#include "xattr.h"
 
 #include "buffer_head_io.h"
 
@@ -219,6 +220,7 @@ int ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe,
         struct super_block *sb;
         struct ocfs2_super *osb;
         int status = -EINVAL;
+        int use_plocks = 1;
 
         mlog_entry("(0x%p, size:%llu)\n", inode,
                    (unsigned long long)le64_to_cpu(fe->i_size));
@@ -226,6 +228,10 @@ int ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe,
         sb = inode->i_sb;
         osb = OCFS2_SB(sb);
 
+        if ((osb->s_mount_opt & OCFS2_MOUNT_LOCALFLOCKS) ||
+            ocfs2_mount_local(osb) || !ocfs2_stack_supports_plocks())
+                use_plocks = 0;
+
         /* this means that read_inode cannot create a superblock inode
          * today.  change if needed. */
         if (!OCFS2_IS_VALID_DINODE(fe) ||
@@ -295,13 +301,19 @@ int ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe,
 
         switch (inode->i_mode & S_IFMT) {
             case S_IFREG:
-                    inode->i_fop = &ocfs2_fops;
+                    if (use_plocks)
+                            inode->i_fop = &ocfs2_fops;
+                    else
+                            inode->i_fop = &ocfs2_fops_no_plocks;
                     inode->i_op = &ocfs2_file_iops;
                     i_size_write(inode, le64_to_cpu(fe->i_size));
                     break;
             case S_IFDIR:
                     inode->i_op = &ocfs2_dir_iops;
-                    inode->i_fop = &ocfs2_dops;
+                    if (use_plocks)
+                            inode->i_fop = &ocfs2_dops;
+                    else
+                            inode->i_fop = &ocfs2_dops_no_plocks;
                     i_size_write(inode, le64_to_cpu(fe->i_size));
                     break;
             case S_IFLNK:
@@ -448,8 +460,11 @@ static int ocfs2_read_locked_inode(struct inode *inode,
                 }
         }
 
-        status = ocfs2_read_block(osb, args->fi_blkno, &bh, 0,
-                                  can_lock ? inode : NULL);
+        if (can_lock)
+                status = ocfs2_read_blocks(inode, args->fi_blkno, 1, &bh,
+                                           OCFS2_BH_IGNORE_CACHE);
+        else
+                status = ocfs2_read_blocks_sync(osb, args->fi_blkno, 1, &bh);
         if (status < 0) {
                 mlog_errno(status);
                 goto bail;
@@ -522,6 +537,9 @@ static int ocfs2_truncate_for_delete(struct ocfs2_super *osb,
          * data and fast symlinks.
          */
         if (fe->i_clusters) {
+                if (ocfs2_should_order_data(inode))
+                        ocfs2_begin_ordered_truncate(inode, 0);
+
                 handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
                 if (IS_ERR(handle)) {
                         status = PTR_ERR(handle);
@@ -730,6 +748,13 @@ static int ocfs2_wipe_inode(struct inode *inode,
                 goto bail_unlock_dir;
         }
 
+        /*Free extended attribute resources associated with this inode.*/
+        status = ocfs2_xattr_remove(inode, di_bh);
+        if (status < 0) {
+                mlog_errno(status);
+                goto bail_unlock_dir;
+        }
+
         status = ocfs2_remove_inode(inode, di_bh, orphan_dir_inode,
                                     orphan_dir_bh);
         if (status < 0)
@@ -1081,6 +1106,8 @@ void ocfs2_clear_inode(struct inode *inode)
         oi->ip_last_trans = 0;
         oi->ip_dir_start_lookup = 0;
         oi->ip_blkno = 0ULL;
+        jbd2_journal_release_jbd_inode(OCFS2_SB(inode->i_sb)->journal->j_journal,
+                                       &oi->ip_jinode);
 
 bail:
         mlog_exit_void();
@@ -1107,58 +1134,6 @@ void ocfs2_drop_inode(struct inode *inode)
 }
 
 /*
- * TODO: this should probably be merged into ocfs2_get_block
- *
- * However, you now need to pay attention to the cont_prepare_write()
- * stuff in ocfs2_get_block (that is, ocfs2_get_block pretty much
- * expects never to extend).
- */
-struct buffer_head *ocfs2_bread(struct inode *inode,
-                                int block, int *err, int reada)
-{
-        struct buffer_head *bh = NULL;
-        int tmperr;
-        u64 p_blkno;
-        int readflags = OCFS2_BH_CACHED;
-
-        if (reada)
-                readflags |= OCFS2_BH_READAHEAD;
-
-        if (((u64)block << inode->i_sb->s_blocksize_bits) >=
-            i_size_read(inode)) {
-                BUG_ON(!reada);
-                return NULL;
-        }
-
-        down_read(&OCFS2_I(inode)->ip_alloc_sem);
-        tmperr = ocfs2_extent_map_get_blocks(inode, block, &p_blkno, NULL,
-                                             NULL);
-        up_read(&OCFS2_I(inode)->ip_alloc_sem);
-        if (tmperr < 0) {
-                mlog_errno(tmperr);
-                goto fail;
-        }
-
-        tmperr = ocfs2_read_block(OCFS2_SB(inode->i_sb), p_blkno, &bh,
-                                  readflags, inode);
-        if (tmperr < 0)
-                goto fail;
-
-        tmperr = 0;
-
-        *err = 0;
-        return bh;
-
-fail:
-        if (bh) {
-                brelse(bh);
-                bh = NULL;
-        }
-        *err = -EIO;
-        return NULL;
-}
-
-/*
  * This is called from our getattr.
  */
 int ocfs2_inode_revalidate(struct dentry *dentry)
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index 390a85596aa0..2f37af9bcc4a 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -40,6 +40,9 @@ struct ocfs2_inode_info
         /* protects allocation changes on this inode. */
         struct rw_semaphore             ip_alloc_sem;
 
+        /* protects extended attribute changes on this inode */
+        struct rw_semaphore             ip_xattr_sem;
+
         /* These fields are protected by ip_lock */
         spinlock_t                      ip_lock;
         u32                             ip_open_count;
@@ -68,6 +71,7 @@ struct ocfs2_inode_info
         struct ocfs2_extent_map         ip_extent_map;
 
         struct inode                    vfs_inode;
+        struct jbd2_inode               ip_jinode;
 };
 
 /*
@@ -113,8 +117,6 @@ extern struct kmem_cache *ocfs2_inode_cache;
 
 extern const struct address_space_operations ocfs2_aops;
 
-struct buffer_head *ocfs2_bread(struct inode *inode, int block,
-                                int *err, int reada);
 void ocfs2_clear_inode(struct inode *inode);
 void ocfs2_delete_inode(struct inode *inode);
 void ocfs2_drop_inode(struct inode *inode);
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 7b142f0ce995..9fcd36dcc9a0 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -102,8 +102,7 @@ bail_unlock:
 bail:
         mutex_unlock(&inode->i_mutex);
 
-        if (bh)
-                brelse(bh);
+        brelse(bh);
 
         mlog_exit(status);
         return status;
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index c47bc2a809c2..81e40677eecb 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -215,9 +215,9 @@ static int ocfs2_commit_cache(struct ocfs2_super *osb)
                 goto finally;
         }
 
-        journal_lock_updates(journal->j_journal);
-        status = journal_flush(journal->j_journal);
-        journal_unlock_updates(journal->j_journal);
+        jbd2_journal_lock_updates(journal->j_journal);
+        status = jbd2_journal_flush(journal->j_journal);
+        jbd2_journal_unlock_updates(journal->j_journal);
         if (status < 0) {
                 up_write(&journal->j_trans_barrier);
                 mlog_errno(status);
@@ -264,7 +264,7 @@ handle_t *ocfs2_start_trans(struct ocfs2_super *osb, int max_buffs)
 
         down_read(&osb->journal->j_trans_barrier);
 
-        handle = journal_start(journal, max_buffs);
+        handle = jbd2_journal_start(journal, max_buffs);
         if (IS_ERR(handle)) {
                 up_read(&osb->journal->j_trans_barrier);
 
@@ -290,7 +290,7 @@ int ocfs2_commit_trans(struct ocfs2_super *osb,
 
         BUG_ON(!handle);
 
-        ret = journal_stop(handle);
+        ret = jbd2_journal_stop(handle);
         if (ret < 0)
                 mlog_errno(ret);
 
@@ -304,7 +304,7 @@ int ocfs2_commit_trans(struct ocfs2_super *osb,
  * transaction. extend_trans will either extend the current handle by
  * nblocks, or commit it and start a new one with nblocks credits.
  *
- * This might call journal_restart() which will commit dirty buffers
+ * This might call jbd2_journal_restart() which will commit dirty buffers
  * and then restart the transaction. Before calling
  * ocfs2_extend_trans(), any changed blocks should have been
  * dirtied. After calling it, all blocks which need to be changed must
@@ -332,7 +332,7 @@ int ocfs2_extend_trans(handle_t *handle, int nblocks)
 #ifdef CONFIG_OCFS2_DEBUG_FS
         status = 1;
 #else
-        status = journal_extend(handle, nblocks);
+        status = jbd2_journal_extend(handle, nblocks);
         if (status < 0) {
                 mlog_errno(status);
                 goto bail;
@@ -340,8 +340,10 @@ int ocfs2_extend_trans(handle_t *handle, int nblocks)
 #endif
 
         if (status > 0) {
-                mlog(0, "journal_extend failed, trying journal_restart\n");
-                status = journal_restart(handle, nblocks);
+                mlog(0,
+                     "jbd2_journal_extend failed, trying "
+                     "jbd2_journal_restart\n");
+                status = jbd2_journal_restart(handle, nblocks);
                 if (status < 0) {
                         mlog_errno(status);
                         goto bail;
@@ -393,11 +395,11 @@ int ocfs2_journal_access(handle_t *handle,
         switch (type) {
         case OCFS2_JOURNAL_ACCESS_CREATE:
         case OCFS2_JOURNAL_ACCESS_WRITE:
-                status = journal_get_write_access(handle, bh);
+                status = jbd2_journal_get_write_access(handle, bh);
                 break;
 
         case OCFS2_JOURNAL_ACCESS_UNDO:
-                status = journal_get_undo_access(handle, bh);
+                status = jbd2_journal_get_undo_access(handle, bh);
                 break;
 
         default:
@@ -422,7 +424,7 @@ int ocfs2_journal_dirty(handle_t *handle,
         mlog_entry("(bh->b_blocknr=%llu)\n",
                    (unsigned long long)bh->b_blocknr);
 
-        status = journal_dirty_metadata(handle, bh);
+        status = jbd2_journal_dirty_metadata(handle, bh);
         if (status < 0)
                 mlog(ML_ERROR, "Could not dirty metadata buffer. "
                      "(bh->b_blocknr=%llu)\n",
@@ -432,6 +434,7 @@ int ocfs2_journal_dirty(handle_t *handle,
         return status;
 }
 
+#ifdef CONFIG_OCFS2_COMPAT_JBD
 int ocfs2_journal_dirty_data(handle_t *handle,
                              struct buffer_head *bh)
 {
@@ -443,8 +446,9 @@ int ocfs2_journal_dirty_data(handle_t *handle,
 
         return err;
 }
+#endif
 
-#define OCFS2_DEFAULT_COMMIT_INTERVAL   (HZ * JBD_DEFAULT_MAX_COMMIT_AGE)
+#define OCFS2_DEFAULT_COMMIT_INTERVAL   (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE)
 
 void ocfs2_set_journal_params(struct ocfs2_super *osb)
 {
@@ -457,9 +461,9 @@ void ocfs2_set_journal_params(struct ocfs2_super *osb)
         spin_lock(&journal->j_state_lock);
         journal->j_commit_interval = commit_interval;
         if (osb->s_mount_opt & OCFS2_MOUNT_BARRIER)
-                journal->j_flags |= JFS_BARRIER;
+                journal->j_flags |= JBD2_BARRIER;
         else
-                journal->j_flags &= ~JFS_BARRIER;
+                journal->j_flags &= ~JBD2_BARRIER;
         spin_unlock(&journal->j_state_lock);
 }
 
@@ -524,14 +528,14 @@ int ocfs2_journal_init(struct ocfs2_journal *journal, int *dirty)
         mlog(0, "inode->ip_clusters = %u\n", OCFS2_I(inode)->ip_clusters);
 
         /* call the kernels journal init function now */
-        j_journal = journal_init_inode(inode);
+        j_journal = jbd2_journal_init_inode(inode);
         if (j_journal == NULL) {
                 mlog(ML_ERROR, "Linux journal layer error\n");
                 status = -EINVAL;
                 goto done;
         }
 
-        mlog(0, "Returned from journal_init_inode\n");
+        mlog(0, "Returned from jbd2_journal_init_inode\n");
         mlog(0, "j_journal->j_maxlen = %u\n", j_journal->j_maxlen);
 
         *dirty = (le32_to_cpu(di->id1.journal1.ij_flags) &
@@ -550,8 +554,7 @@ done:
         if (status < 0) {
                 if (inode_lock)
                         ocfs2_inode_unlock(inode, 1);
-                if (bh != NULL)
-                        brelse(bh);
+                brelse(bh);
                 if (inode) {
                         OCFS2_I(inode)->ip_open_count--;
                         iput(inode);
@@ -639,7 +642,7 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb)
         if (journal->j_state != OCFS2_JOURNAL_LOADED)
                 goto done;
 
-        /* need to inc inode use count as journal_destroy will iput. */
+        /* need to inc inode use count - jbd2_journal_destroy will iput. */
         if (!igrab(inode))
                 BUG();
 
@@ -668,9 +671,9 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb)
         BUG_ON(atomic_read(&(osb->journal->j_num_trans)) != 0);
 
         if (ocfs2_mount_local(osb)) {
-                journal_lock_updates(journal->j_journal);
-                status = journal_flush(journal->j_journal);
-                journal_unlock_updates(journal->j_journal);
+                jbd2_journal_lock_updates(journal->j_journal);
+                status = jbd2_journal_flush(journal->j_journal);
+                jbd2_journal_unlock_updates(journal->j_journal);
                 if (status < 0)
                         mlog_errno(status);
         }
@@ -686,7 +689,7 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb)
         }
 
         /* Shutdown the kernel journal system */
-        journal_destroy(journal->j_journal);
+        jbd2_journal_destroy(journal->j_journal);
 
         OCFS2_I(inode)->ip_open_count--;
 
@@ -711,15 +714,15 @@ static void ocfs2_clear_journal_error(struct super_block *sb,
 {
         int olderr;
 
-        olderr = journal_errno(journal);
+        olderr = jbd2_journal_errno(journal);
         if (olderr) {
                 mlog(ML_ERROR, "File system error %d recorded in "
                      "journal %u.\n", olderr, slot);
                 mlog(ML_ERROR, "File system on device %s needs checking.\n",
                      sb->s_id);
 
-                journal_ack_err(journal);
-                journal_clear_err(journal);
+                jbd2_journal_ack_err(journal);
+                jbd2_journal_clear_err(journal);
         }
 }
 
@@ -734,7 +737,7 @@ int ocfs2_journal_load(struct ocfs2_journal *journal, int local, int replayed)
 
         osb = journal->j_osb;
 
-        status = journal_load(journal->j_journal);
+        status = jbd2_journal_load(journal->j_journal);
         if (status < 0) {
                 mlog(ML_ERROR, "Failed to load journal!\n");
                 goto done;
@@ -778,7 +781,7 @@ int ocfs2_journal_wipe(struct ocfs2_journal *journal, int full)
 
         BUG_ON(!journal);
 
-        status = journal_wipe(journal->j_journal, full);
+        status = jbd2_journal_wipe(journal->j_journal, full);
         if (status < 0) {
                 mlog_errno(status);
                 goto bail;
@@ -847,9 +850,8 @@ static int ocfs2_force_read_journal(struct inode *inode)
 
                 /* We are reading journal data which should not
                  * be put in the uptodate cache */
-                status = ocfs2_read_blocks(OCFS2_SB(inode->i_sb),
-                                           p_blkno, p_blocks, bhs, 0,
-                                           NULL);
+                status = ocfs2_read_blocks_sync(OCFS2_SB(inode->i_sb),
+                                                p_blkno, p_blocks, bhs);
                 if (status < 0) {
                         mlog_errno(status);
                         goto bail;
@@ -865,8 +867,7 @@ static int ocfs2_force_read_journal(struct inode *inode)
 
 bail:
         for(i = 0; i < CONCURRENT_JOURNAL_FILL; i++)
-                if (bhs[i])
-                        brelse(bhs[i]);
+                brelse(bhs[i]);
         mlog_exit(status);
         return status;
 }
@@ -1133,7 +1134,8 @@ static int ocfs2_read_journal_inode(struct ocfs2_super *osb,
         }
         SET_INODE_JOURNAL(inode);
 
-        status = ocfs2_read_block(osb, OCFS2_I(inode)->ip_blkno, bh, 0, inode);
+        status = ocfs2_read_blocks(inode, OCFS2_I(inode)->ip_blkno, 1, bh,
+                                   OCFS2_BH_IGNORE_CACHE);
         if (status < 0) {
                 mlog_errno(status);
                 goto bail;
@@ -1229,19 +1231,19 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb,
         }
 
         mlog(0, "calling journal_init_inode\n");
-        journal = journal_init_inode(inode);
+        journal = jbd2_journal_init_inode(inode);
         if (journal == NULL) {
                 mlog(ML_ERROR, "Linux journal layer error\n");
                 status = -EIO;
                 goto done;
         }
 
-        status = journal_load(journal);
+        status = jbd2_journal_load(journal);
         if (status < 0) {
                 mlog_errno(status);
                 if (!igrab(inode))
                         BUG();
-                journal_destroy(journal);
+                jbd2_journal_destroy(journal);
                 goto done;
         }
 
@@ -1249,9 +1251,9 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb,
 
         /* wipe the journal */
         mlog(0, "flushing the journal.\n");
-        journal_lock_updates(journal);
-        status = journal_flush(journal);
-        journal_unlock_updates(journal);
+        jbd2_journal_lock_updates(journal);
+        status = jbd2_journal_flush(journal);
+        jbd2_journal_unlock_updates(journal);
         if (status < 0)
                 mlog_errno(status);
 
@@ -1272,7 +1274,7 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb,
         if (!igrab(inode))
                 BUG();
 
-        journal_destroy(journal);
+        jbd2_journal_destroy(journal);
 
 done:
         /* drop the lock on this nodes journal */
@@ -1282,8 +1284,7 @@ done:
         if (inode)
                 iput(inode);
 
-        if (bh)
-                brelse(bh);
+        brelse(bh);
 
         mlog_exit(status);
         return status;
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 2178ebffa05f..d4d14e9a3cea 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -27,7 +27,12 @@
 #define OCFS2_JOURNAL_H
 
 #include <linux/fs.h>
-#include <linux/jbd.h>
+#ifndef CONFIG_OCFS2_COMPAT_JBD
+# include <linux/jbd2.h>
+#else
+# include <linux/jbd.h>
+# include "ocfs2_jbd_compat.h"
+#endif
 
 enum ocfs2_journal_state {
         OCFS2_JOURNAL_FREE = 0,
@@ -215,8 +220,8 @@ static inline void ocfs2_checkpoint_inode(struct inode *inode)
  *                          buffer. Will have to call ocfs2_journal_dirty once
  *                          we've actually dirtied it. Type is one of . or .
  *  ocfs2_journal_dirty    - Mark a journalled buffer as having dirty data.
- *  ocfs2_journal_dirty_data - Indicate that a data buffer should go out before
- *                             the current handle commits.
+ *  ocfs2_jbd2_file_inode  - Mark an inode so that its data goes out before
+ *                           the current handle commits.
  */
 
 /* You must always start_trans with a number of buffs > 0, but it's
@@ -268,8 +273,10 @@ int                  ocfs2_journal_access(handle_t *handle,
  */
 int                  ocfs2_journal_dirty(handle_t *handle,
                                          struct buffer_head *bh);
+#ifdef CONFIG_OCFS2_COMPAT_JBD
 int                  ocfs2_journal_dirty_data(handle_t *handle,
                                               struct buffer_head *bh);
+#endif
 
 /*
  *  Credit Macros:
@@ -283,6 +290,9 @@ int                  ocfs2_journal_dirty_data(handle_t *handle,
 /* simple file updates like chmod, etc. */
 #define OCFS2_INODE_UPDATE_CREDITS 1
 
+/* extended attribute block update */
+#define OCFS2_XATTR_BLOCK_UPDATE_CREDITS 1
+
 /* group extend. inode update and last group update. */
 #define OCFS2_GROUP_EXTEND_CREDITS      (OCFS2_INODE_UPDATE_CREDITS + 1)
 
@@ -340,11 +350,23 @@ int                  ocfs2_journal_dirty_data(handle_t *handle,
 #define OCFS2_RENAME_CREDITS (3 * OCFS2_INODE_UPDATE_CREDITS + 3              \
                              + OCFS2_UNLINK_CREDITS)
 
+/* global bitmap dinode, group desc., relinked group,
+ * suballocator dinode, group desc., relinked group,
+ * dinode, xattr block */
+#define OCFS2_XATTR_BLOCK_CREATE_CREDITS (OCFS2_SUBALLOC_ALLOC * 2 + \
+                                          + OCFS2_INODE_UPDATE_CREDITS \
+                                          + OCFS2_XATTR_BLOCK_UPDATE_CREDITS)
+
+/*
+ * Please note that the caller must make sure that root_el is the root
+ * of extent tree. So for an inode, it should be &fe->id2.i_list. Otherwise
+ * the result may be wrong.
+ */
 static inline int ocfs2_calc_extend_credits(struct super_block *sb,
-                                            struct ocfs2_dinode *fe,
+                                            struct ocfs2_extent_list *root_el,
                                             u32 bits_wanted)
 {
-        int bitmap_blocks, sysfile_bitmap_blocks, dinode_blocks;
+        int bitmap_blocks, sysfile_bitmap_blocks, extent_blocks;
 
         /* bitmap dinode, group desc. + relinked group. */
         bitmap_blocks = OCFS2_SUBALLOC_ALLOC;
@@ -355,16 +377,16 @@ static inline int ocfs2_calc_extend_credits(struct super_block *sb,
          * however many metadata chunks needed * a remaining suballoc
          * alloc. */
         sysfile_bitmap_blocks = 1 +
-                (OCFS2_SUBALLOC_ALLOC - 1) * ocfs2_extend_meta_needed(fe);
+                (OCFS2_SUBALLOC_ALLOC - 1) * ocfs2_extend_meta_needed(root_el);
 
         /* this does not include *new* metadata blocks, which are
-         * accounted for in sysfile_bitmap_blocks. fe +
+         * accounted for in sysfile_bitmap_blocks. root_el +
          * prev. last_eb_blk + blocks along edge of tree.
          * calc_symlink_credits passes because we just need 1
          * credit for the dinode there. */
-        dinode_blocks = 1 + 1 + le16_to_cpu(fe->id2.i_list.l_tree_depth);
+        extent_blocks = 1 + 1 + le16_to_cpu(root_el->l_tree_depth);
 
-        return bitmap_blocks + sysfile_bitmap_blocks + dinode_blocks;
+        return bitmap_blocks + sysfile_bitmap_blocks + extent_blocks;
 }
 
 static inline int ocfs2_calc_symlink_credits(struct super_block *sb)
@@ -415,4 +437,16 @@ static inline int ocfs2_calc_tree_trunc_credits(struct super_block *sb,
         return credits;
 }
 
+static inline int ocfs2_jbd2_file_inode(handle_t *handle, struct inode *inode)
+{
+        return jbd2_journal_file_inode(handle, &OCFS2_I(inode)->ip_jinode);
+}
+
+static inline int ocfs2_begin_ordered_truncate(struct inode *inode,
+                                               loff_t new_size)
+{
+        return jbd2_journal_begin_ordered_truncate(&OCFS2_I(inode)->ip_jinode,
+                                                   new_size);
+}
+
 #endif /* OCFS2_JOURNAL_H */
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index 28e492e4ec88..687b28713c32 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/bitops.h>
+#include <linux/debugfs.h>
 
 #define MLOG_MASK_PREFIX ML_DISK_ALLOC
 #include <cluster/masklog.h>
@@ -47,8 +48,6 @@
 
 #define OCFS2_LOCAL_ALLOC(dinode)       (&((dinode)->id2.i_lab))
 
-static inline int ocfs2_local_alloc_window_bits(struct ocfs2_super *osb);
-
 static u32 ocfs2_local_alloc_count_bits(struct ocfs2_dinode *alloc);
 
 static int ocfs2_local_alloc_find_clear_bits(struct ocfs2_super *osb,
@@ -75,24 +74,129 @@ static int ocfs2_local_alloc_new_window(struct ocfs2_super *osb,
 static int ocfs2_local_alloc_slide_window(struct ocfs2_super *osb,
                                           struct inode *local_alloc_inode);
 
-static inline int ocfs2_local_alloc_window_bits(struct ocfs2_super *osb)
+#ifdef CONFIG_OCFS2_FS_STATS
+
+static int ocfs2_la_debug_open(struct inode *inode, struct file *file)
+{
+        file->private_data = inode->i_private;
+        return 0;
+}
+
+#define LA_DEBUG_BUF_SZ PAGE_CACHE_SIZE
+#define LA_DEBUG_VER    1
+static ssize_t ocfs2_la_debug_read(struct file *file, char __user *userbuf,
+                                   size_t count, loff_t *ppos)
+{
+        static DEFINE_MUTEX(la_debug_mutex);
+        struct ocfs2_super *osb = file->private_data;
+        int written, ret;
+        char *buf = osb->local_alloc_debug_buf;
+
+        mutex_lock(&la_debug_mutex);
+        memset(buf, 0, LA_DEBUG_BUF_SZ);
+
+        written = snprintf(buf, LA_DEBUG_BUF_SZ,
+                           "0x%x\t0x%llx\t%u\t%u\t0x%x\n",
+                           LA_DEBUG_VER,
+                           (unsigned long long)osb->la_last_gd,
+                           osb->local_alloc_default_bits,
+                           osb->local_alloc_bits, osb->local_alloc_state);
+
+        ret = simple_read_from_buffer(userbuf, count, ppos, buf, written);
+
+        mutex_unlock(&la_debug_mutex);
+        return ret;
+}
+
+static const struct file_operations ocfs2_la_debug_fops = {
+        .open =         ocfs2_la_debug_open,
+        .read =         ocfs2_la_debug_read,
+};
+
+static void ocfs2_init_la_debug(struct ocfs2_super *osb)
+{
+        osb->local_alloc_debug_buf = kmalloc(LA_DEBUG_BUF_SZ, GFP_NOFS);
+        if (!osb->local_alloc_debug_buf)
+                return;
+
+        osb->local_alloc_debug = debugfs_create_file("local_alloc_stats",
+                                                     S_IFREG|S_IRUSR,
+                                                     osb->osb_debug_root,
+                                                     osb,
+                                                     &ocfs2_la_debug_fops);
+        if (!osb->local_alloc_debug) {
+                kfree(osb->local_alloc_debug_buf);
+                osb->local_alloc_debug_buf = NULL;
+        }
+}
+
+static void ocfs2_shutdown_la_debug(struct ocfs2_super *osb)
+{
+        if (osb->local_alloc_debug)
+                debugfs_remove(osb->local_alloc_debug);
+
+        if (osb->local_alloc_debug_buf)
+                kfree(osb->local_alloc_debug_buf);
+
+        osb->local_alloc_debug_buf = NULL;
+        osb->local_alloc_debug = NULL;
+}
+#else   /* CONFIG_OCFS2_FS_STATS */
+static void ocfs2_init_la_debug(struct ocfs2_super *osb)
+{
+        return;
+}
+static void ocfs2_shutdown_la_debug(struct ocfs2_super *osb)
+{
+        return;
+}
+#endif
+
+static inline int ocfs2_la_state_enabled(struct ocfs2_super *osb)
 {
-        BUG_ON(osb->s_clustersize_bits > 20);
+        return (osb->local_alloc_state == OCFS2_LA_THROTTLED ||
+                osb->local_alloc_state == OCFS2_LA_ENABLED);
+}
 
-        /* Size local alloc windows by the megabyte */
-        return osb->local_alloc_size << (20 - osb->s_clustersize_bits);
+void ocfs2_local_alloc_seen_free_bits(struct ocfs2_super *osb,
+                                      unsigned int num_clusters)
+{
+        spin_lock(&osb->osb_lock);
+        if (osb->local_alloc_state == OCFS2_LA_DISABLED ||
+            osb->local_alloc_state == OCFS2_LA_THROTTLED)
+                if (num_clusters >= osb->local_alloc_default_bits) {
+                        cancel_delayed_work(&osb->la_enable_wq);
+                        osb->local_alloc_state = OCFS2_LA_ENABLED;
+                }
+        spin_unlock(&osb->osb_lock);
+}
+
+void ocfs2_la_enable_worker(struct work_struct *work)
+{
+        struct ocfs2_super *osb =
+                container_of(work, struct ocfs2_super,
+                             la_enable_wq.work);
+        spin_lock(&osb->osb_lock);
+        osb->local_alloc_state = OCFS2_LA_ENABLED;
+        spin_unlock(&osb->osb_lock);
 }
 
 /*
  * Tell us whether a given allocation should use the local alloc
  * file. Otherwise, it has to go to the main bitmap.
+ *
+ * This function does semi-dirty reads of local alloc size and state!
+ * This is ok however, as the values are re-checked once under mutex.
  */
 int ocfs2_alloc_should_use_local(struct ocfs2_super *osb, u64 bits)
 {
-        int la_bits = ocfs2_local_alloc_window_bits(osb);
         int ret = 0;
+        int la_bits;
+
+        spin_lock(&osb->osb_lock);
+        la_bits = osb->local_alloc_bits;
 
-        if (osb->local_alloc_state != OCFS2_LA_ENABLED)
+        if (!ocfs2_la_state_enabled(osb))
                 goto bail;
 
         /* la_bits should be at least twice the size (in clusters) of
@@ -106,6 +210,7 @@ int ocfs2_alloc_should_use_local(struct ocfs2_super *osb, u64 bits)
 bail:
         mlog(0, "state=%d, bits=%llu, la_bits=%d, ret=%d\n",
              osb->local_alloc_state, (unsigned long long)bits, la_bits, ret);
+        spin_unlock(&osb->osb_lock);
         return ret;
 }
 
@@ -120,14 +225,18 @@ int ocfs2_load_local_alloc(struct ocfs2_super *osb)
 
         mlog_entry_void();
 
-        if (osb->local_alloc_size == 0)
+        ocfs2_init_la_debug(osb);
+
+        if (osb->local_alloc_bits == 0)
                 goto bail;
 
-        if (ocfs2_local_alloc_window_bits(osb) >= osb->bitmap_cpg) {
+        if (osb->local_alloc_bits >= osb->bitmap_cpg) {
                 mlog(ML_NOTICE, "Requested local alloc window %d is larger "
                      "than max possible %u. Using defaults.\n",
-                     ocfs2_local_alloc_window_bits(osb), (osb->bitmap_cpg - 1));
-                osb->local_alloc_size = OCFS2_DEFAULT_LOCAL_ALLOC_SIZE;
+                     osb->local_alloc_bits, (osb->bitmap_cpg - 1));
+                osb->local_alloc_bits =
+                        ocfs2_megabytes_to_clusters(osb->sb,
+                                                    OCFS2_DEFAULT_LOCAL_ALLOC_SIZE);
         }
 
         /* read the alloc off disk */
@@ -139,8 +248,8 @@ int ocfs2_load_local_alloc(struct ocfs2_super *osb)
                 goto bail;
         }
 
-        status = ocfs2_read_block(osb, OCFS2_I(inode)->ip_blkno,
-                                  &alloc_bh, 0, inode);
+        status = ocfs2_read_blocks(inode, OCFS2_I(inode)->ip_blkno, 1,
+                                   &alloc_bh, OCFS2_BH_IGNORE_CACHE);
         if (status < 0) {
                 mlog_errno(status);
                 goto bail;
@@ -185,13 +294,14 @@ int ocfs2_load_local_alloc(struct ocfs2_super *osb)
 
 bail:
         if (status < 0)
-                if (alloc_bh)
-                        brelse(alloc_bh);
+                brelse(alloc_bh);
         if (inode)
                 iput(inode);
 
-        mlog(0, "Local alloc window bits = %d\n",
-             ocfs2_local_alloc_window_bits(osb));
+        if (status < 0)
+                ocfs2_shutdown_la_debug(osb);
+
+        mlog(0, "Local alloc window bits = %d\n", osb->local_alloc_bits);
 
         mlog_exit(status);
         return status;
@@ -217,6 +327,11 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb)
 
         mlog_entry_void();
 
+        cancel_delayed_work(&osb->la_enable_wq);
+        flush_workqueue(ocfs2_wq);
+
+        ocfs2_shutdown_la_debug(osb);
+
         if (osb->local_alloc_state == OCFS2_LA_UNUSED)
                 goto out;
 
@@ -295,8 +410,7 @@ out_commit:
         ocfs2_commit_trans(osb, handle);
 
 out_unlock:
-        if (main_bm_bh)
-                brelse(main_bm_bh);
+        brelse(main_bm_bh);
 
         ocfs2_inode_unlock(main_bm_inode, 1);
 
@@ -345,8 +459,8 @@ int ocfs2_begin_local_alloc_recovery(struct ocfs2_super *osb,
 
         mutex_lock(&inode->i_mutex);
 
-        status = ocfs2_read_block(osb, OCFS2_I(inode)->ip_blkno,
-                                  &alloc_bh, 0, inode);
+        status = ocfs2_read_blocks(inode, OCFS2_I(inode)->ip_blkno, 1,
+                                   &alloc_bh, OCFS2_BH_IGNORE_CACHE);
         if (status < 0) {
                 mlog_errno(status);
                 goto bail;
@@ -372,8 +486,7 @@ bail:
                 *alloc_copy = NULL;
         }
 
-        if (alloc_bh)
-                brelse(alloc_bh);
+        brelse(alloc_bh);
 
         if (inode) {
                 mutex_unlock(&inode->i_mutex);
@@ -441,8 +554,7 @@ out_unlock:
 out_mutex:
         mutex_unlock(&main_bm_inode->i_mutex);
 
-        if (main_bm_bh)
-                brelse(main_bm_bh);
+        brelse(main_bm_bh);
 
         iput(main_bm_inode);
 
@@ -453,8 +565,48 @@ out:
         return status;
 }
 
+/* Check to see if the local alloc window is within ac->ac_max_block */
+static int ocfs2_local_alloc_in_range(struct inode *inode,
+                                      struct ocfs2_alloc_context *ac,
+                                      u32 bits_wanted)
+{
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+        struct ocfs2_dinode *alloc;
+        struct ocfs2_local_alloc *la;
+        int start;
+        u64 block_off;
+
+        if (!ac->ac_max_block)
+                return 1;
+
+        alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data;
+        la = OCFS2_LOCAL_ALLOC(alloc);
+
+        start = ocfs2_local_alloc_find_clear_bits(osb, alloc, bits_wanted);
+        if (start == -1) {
+                mlog_errno(-ENOSPC);
+                return 0;
+        }
+
+        /*
+         * Converting (bm_off + start + bits_wanted) to blocks gives us
+         * the blkno just past our actual allocation.  This is perfect
+         * to compare with ac_max_block.
+         */
+        block_off = ocfs2_clusters_to_blocks(inode->i_sb,
+                                             le32_to_cpu(la->la_bm_off) +
+                                             start + bits_wanted);
+        mlog(0, "Checking %llu against %llu\n",
+             (unsigned long long)block_off,
+             (unsigned long long)ac->ac_max_block);
+        if (block_off > ac->ac_max_block)
+                return 0;
+
+        return 1;
+}
+
 /*
- * make sure we've got at least bitswanted contiguous bits in the
+ * make sure we've got at least bits_wanted contiguous bits in the
  * local alloc. You lose them when you drop i_mutex.
  *
  * We will add ourselves to the transaction passed in, but may start
@@ -485,16 +637,18 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
 
         mutex_lock(&local_alloc_inode->i_mutex);
 
-        if (osb->local_alloc_state != OCFS2_LA_ENABLED) {
-                status = -ENOSPC;
-                goto bail;
-        }
-
-        if (bits_wanted > ocfs2_local_alloc_window_bits(osb)) {
-                mlog(0, "Asking for more than my max window size!\n");
+        /*
+         * We must double check state and allocator bits because
+         * another process may have changed them while holding i_mutex.
+         */
+        spin_lock(&osb->osb_lock);
+        if (!ocfs2_la_state_enabled(osb) ||
+            (bits_wanted > osb->local_alloc_bits)) {
+                spin_unlock(&osb->osb_lock);
                 status = -ENOSPC;
                 goto bail;
         }
+        spin_unlock(&osb->osb_lock);
 
         alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data;
 
@@ -522,6 +676,36 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
                                 mlog_errno(status);
                         goto bail;
                 }
+
+                /*
+                 * Under certain conditions, the window slide code
+                 * might have reduced the number of bits available or
+                 * disabled the the local alloc entirely. Re-check
+                 * here and return -ENOSPC if necessary.
+                 */
+                status = -ENOSPC;
+                if (!ocfs2_la_state_enabled(osb))
+                        goto bail;
+
+                free_bits = le32_to_cpu(alloc->id1.bitmap1.i_total) -
+                        le32_to_cpu(alloc->id1.bitmap1.i_used);
+                if (bits_wanted > free_bits)
+                        goto bail;
+        }
+
+        if (ac->ac_max_block)
+                mlog(0, "Calling in_range for max block %llu\n",
+                     (unsigned long long)ac->ac_max_block);
+
+        if (!ocfs2_local_alloc_in_range(local_alloc_inode, ac,
+                                        bits_wanted)) {
+                /*
+                 * The window is outside ac->ac_max_block.
+                 * This errno tells the caller to keep localalloc enabled
+                 * but to get the allocation from the main bitmap.
+                 */
+                status = -EFBIG;
+                goto bail;
         }
 
         ac->ac_inode = local_alloc_inode;
@@ -789,6 +973,85 @@ bail:
         return status;
 }
 
+enum ocfs2_la_event {
+        OCFS2_LA_EVENT_SLIDE,           /* Normal window slide. */
+        OCFS2_LA_EVENT_FRAGMENTED,      /* The global bitmap has
+                                         * enough bits theoretically
+                                         * free, but a contiguous
+                                         * allocation could not be
+                                         * found. */
+        OCFS2_LA_EVENT_ENOSPC,          /* Global bitmap doesn't have
+                                         * enough bits free to satisfy
+                                         * our request. */
+};
+#define OCFS2_LA_ENABLE_INTERVAL (30 * HZ)
+/*
+ * Given an event, calculate the size of our next local alloc window.
+ *
+ * This should always be called under i_mutex of the local alloc inode
+ * so that local alloc disabling doesn't race with processes trying to
+ * use the allocator.
+ *
+ * Returns the state which the local alloc was left in. This value can
+ * be ignored by some paths.
+ */
+static int ocfs2_recalc_la_window(struct ocfs2_super *osb,
+                                  enum ocfs2_la_event event)
+{
+        unsigned int bits;
+        int state;
+
+        spin_lock(&osb->osb_lock);
+        if (osb->local_alloc_state == OCFS2_LA_DISABLED) {
+                WARN_ON_ONCE(osb->local_alloc_state == OCFS2_LA_DISABLED);
+                goto out_unlock;
+        }
+
+        /*
+         * ENOSPC and fragmentation are treated similarly for now.
+         */
+        if (event == OCFS2_LA_EVENT_ENOSPC ||
+            event == OCFS2_LA_EVENT_FRAGMENTED) {
+                /*
+                 * We ran out of contiguous space in the primary
+                 * bitmap. Drastically reduce the number of bits used
+                 * by local alloc until we have to disable it.
+                 */
+                bits = osb->local_alloc_bits >> 1;
+                if (bits > ocfs2_megabytes_to_clusters(osb->sb, 1)) {
+                        /*
+                         * By setting state to THROTTLED, we'll keep
+                         * the number of local alloc bits used down
+                         * until an event occurs which would give us
+                         * reason to assume the bitmap situation might
+                         * have changed.
+                         */
+                        osb->local_alloc_state = OCFS2_LA_THROTTLED;
+                        osb->local_alloc_bits = bits;
+                } else {
+                        osb->local_alloc_state = OCFS2_LA_DISABLED;
+                }
+                queue_delayed_work(ocfs2_wq, &osb->la_enable_wq,
+                                   OCFS2_LA_ENABLE_INTERVAL);
+                goto out_unlock;
+        }
+
+        /*
+         * Don't increase the size of the local alloc window until we
+         * know we might be able to fulfill the request. Otherwise, we
+         * risk bouncing around the global bitmap during periods of
+         * low space.
+         */
+        if (osb->local_alloc_state != OCFS2_LA_THROTTLED)
+                osb->local_alloc_bits = osb->local_alloc_default_bits;
+
+out_unlock:
+        state = osb->local_alloc_state;
+        spin_unlock(&osb->osb_lock);
+
+        return state;
+}
+
 static int ocfs2_local_alloc_reserve_for_window(struct ocfs2_super *osb,
                                                 struct ocfs2_alloc_context **ac,
                                                 struct inode **bitmap_inode,
@@ -803,12 +1066,21 @@ static int ocfs2_local_alloc_reserve_for_window(struct ocfs2_super *osb,
                 goto bail;
         }
 
-        (*ac)->ac_bits_wanted = ocfs2_local_alloc_window_bits(osb);
+retry_enospc:
+        (*ac)->ac_bits_wanted = osb->local_alloc_bits;
 
         status = ocfs2_reserve_cluster_bitmap_bits(osb, *ac);
+        if (status == -ENOSPC) {
+                if (ocfs2_recalc_la_window(osb, OCFS2_LA_EVENT_ENOSPC) ==
+                    OCFS2_LA_DISABLED)
+                        goto bail;
+
+                ocfs2_free_ac_resource(*ac);
+                memset(*ac, 0, sizeof(struct ocfs2_alloc_context));
+                goto retry_enospc;
+        }
         if (status < 0) {
-                if (status != -ENOSPC)
-                        mlog_errno(status);
+                mlog_errno(status);
                 goto bail;
         }
 
@@ -849,7 +1121,7 @@ static int ocfs2_local_alloc_new_window(struct ocfs2_super *osb,
                      "one\n");
 
         mlog(0, "Allocating %u clusters for a new window.\n",
-             ocfs2_local_alloc_window_bits(osb));
+             osb->local_alloc_bits);
 
         /* Instruct the allocation code to try the most recently used
          * cluster group. We'll re-record the group used this pass
@@ -859,9 +1131,36 @@ static int ocfs2_local_alloc_new_window(struct ocfs2_super *osb,
         /* we used the generic suballoc reserve function, but we set
          * everything up nicely, so there's no reason why we can't use
          * the more specific cluster api to claim bits. */
-        status = ocfs2_claim_clusters(osb, handle, ac,
-                                      ocfs2_local_alloc_window_bits(osb),
+        status = ocfs2_claim_clusters(osb, handle, ac, osb->local_alloc_bits,
                                       &cluster_off, &cluster_count);
+        if (status == -ENOSPC) {
+retry_enospc:
+                /*
+                 * Note: We could also try syncing the journal here to
+                 * allow use of any free bits which the current
+                 * transaction can't give us access to. --Mark
+                 */
+                if (ocfs2_recalc_la_window(osb, OCFS2_LA_EVENT_FRAGMENTED) ==
+                    OCFS2_LA_DISABLED)
+                        goto bail;
+
+                status = ocfs2_claim_clusters(osb, handle, ac,
+                                              osb->local_alloc_bits,
+                                              &cluster_off,
+                                              &cluster_count);
+                if (status == -ENOSPC)
+                        goto retry_enospc;
+                /*
+                 * We only shrunk the *minimum* number of in our
+                 * request - it's entirely possible that the allocator
+                 * might give us more than we asked for.
+                 */
+                if (status == 0) {
+                        spin_lock(&osb->osb_lock);
+                        osb->local_alloc_bits = cluster_count;
+                        spin_unlock(&osb->osb_lock);
+                }
+        }
         if (status < 0) {
                 if (status != -ENOSPC)
                         mlog_errno(status);
@@ -905,6 +1204,8 @@ static int ocfs2_local_alloc_slide_window(struct ocfs2_super *osb,
 
         mlog_entry_void();
 
+        ocfs2_recalc_la_window(osb, OCFS2_LA_EVENT_SLIDE);
+
         /* This will lock the main bitmap for us. */
         status = ocfs2_local_alloc_reserve_for_window(osb,
                                                       &ac,
@@ -976,8 +1277,7 @@ bail:
         if (handle)
                 ocfs2_commit_trans(osb, handle);
 
-        if (main_bm_bh)
-                brelse(main_bm_bh);
+        brelse(main_bm_bh);
 
         if (main_bm_inode)
                 iput(main_bm_inode);
diff --git a/fs/ocfs2/localalloc.h b/fs/ocfs2/localalloc.h
index 3f76631e110c..ac5ea9f86653 100644
--- a/fs/ocfs2/localalloc.h
+++ b/fs/ocfs2/localalloc.h
@@ -52,4 +52,8 @@ int ocfs2_claim_local_alloc_bits(struct ocfs2_super *osb,
                                  u32 *bit_off,
                                  u32 *num_bits);
 
+void ocfs2_local_alloc_seen_free_bits(struct ocfs2_super *osb,
+                                      unsigned int num_clusters);
+void ocfs2_la_enable_worker(struct work_struct *work);
+
 #endif /* OCFS2_LOCALALLOC_H */
diff --git a/fs/ocfs2/locks.c b/fs/ocfs2/locks.c
index 203f87143877..544ac6245175 100644
--- a/fs/ocfs2/locks.c
+++ b/fs/ocfs2/locks.c
@@ -24,6 +24,7 @@
  */
 
 #include <linux/fs.h>
+#include <linux/fcntl.h>
 
 #define MLOG_MASK_PREFIX ML_INODE
 #include <cluster/masklog.h>
@@ -32,6 +33,7 @@
 
 #include "dlmglue.h"
 #include "file.h"
+#include "inode.h"
 #include "locks.h"
 
 static int ocfs2_do_flock(struct file *file, struct inode *inode,
@@ -123,3 +125,16 @@ int ocfs2_flock(struct file *file, int cmd, struct file_lock *fl)
         else
                 return ocfs2_do_flock(file, inode, cmd, fl);
 }
+
+int ocfs2_lock(struct file *file, int cmd, struct file_lock *fl)
+{
+        struct inode *inode = file->f_mapping->host;
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+        if (!(fl->fl_flags & FL_POSIX))
+                return -ENOLCK;
+        if (__mandatory_lock(inode))
+                return -ENOLCK;
+
+        return ocfs2_plock(osb->cconn, OCFS2_I(inode)->ip_blkno, file, cmd, fl);
+}
diff --git a/fs/ocfs2/locks.h b/fs/ocfs2/locks.h
index 9743ef2324ec..496d488b271f 100644
--- a/fs/ocfs2/locks.h
+++ b/fs/ocfs2/locks.h
@@ -27,5 +27,6 @@
 #define OCFS2_LOCKS_H
 
 int ocfs2_flock(struct file *file, int cmd, struct file_lock *fl);
+int ocfs2_lock(struct file *file, int cmd, struct file_lock *fl);
 
 #endif /* OCFS2_LOCKS_H */
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index d5d808fe0140..485a6aa0ad39 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -60,6 +60,7 @@
 #include "symlink.h"
 #include "sysfile.h"
 #include "uptodate.h"
+#include "xattr.h"
 
 #include "buffer_head_io.h"
 
@@ -327,14 +328,9 @@ leave:
         if (status == -ENOSPC)
                 mlog(0, "Disk is full\n");
 
-        if (new_fe_bh)
-                brelse(new_fe_bh);
-
-        if (de_bh)
-                brelse(de_bh);
-
-        if (parent_fe_bh)
-                brelse(parent_fe_bh);
+        brelse(new_fe_bh);
+        brelse(de_bh);
+        brelse(parent_fe_bh);
 
         if ((status < 0) && inode)
                 iput(inode);
@@ -647,12 +643,9 @@ out_unlock_inode:
 out:
         ocfs2_inode_unlock(dir, 1);
 
-        if (de_bh)
-                brelse(de_bh);
-        if (fe_bh)
-                brelse(fe_bh);
-        if (parent_fe_bh)
-                brelse(parent_fe_bh);
+        brelse(de_bh);
+        brelse(fe_bh);
+        brelse(parent_fe_bh);
 
         mlog_exit(err);
 
@@ -851,17 +844,10 @@ leave:
                 iput(orphan_dir);
         }
 
-        if (fe_bh)
-                brelse(fe_bh);
-
-        if (dirent_bh)
-                brelse(dirent_bh);
-
-        if (parent_node_bh)
-                brelse(parent_node_bh);
-
-        if (orphan_entry_bh)
-                brelse(orphan_entry_bh);
+        brelse(fe_bh);
+        brelse(dirent_bh);
+        brelse(parent_node_bh);
+        brelse(orphan_entry_bh);
 
         mlog_exit(status);
 
@@ -1372,24 +1358,15 @@ bail:
 
         if (new_inode)
                 iput(new_inode);
-        if (newfe_bh)
-                brelse(newfe_bh);
-        if (old_inode_bh)
-                brelse(old_inode_bh);
-        if (old_dir_bh)
-                brelse(old_dir_bh);
-        if (new_dir_bh)
-                brelse(new_dir_bh);
-        if (new_de_bh)
-                brelse(new_de_bh);
-        if (old_de_bh)
-                brelse(old_de_bh);
-        if (old_inode_de_bh)
-                brelse(old_inode_de_bh);
-        if (orphan_entry_bh)
-                brelse(orphan_entry_bh);
-        if (insert_entry_bh)
-                brelse(insert_entry_bh);
+        brelse(newfe_bh);
+        brelse(old_inode_bh);
+        brelse(old_dir_bh);
+        brelse(new_dir_bh);
+        brelse(new_de_bh);
+        brelse(old_de_bh);
+        brelse(old_inode_de_bh);
+        brelse(orphan_entry_bh);
+        brelse(insert_entry_bh);
 
         mlog_exit(status);
 
@@ -1492,8 +1469,7 @@ bail:
 
         if (bhs) {
                 for(i = 0; i < blocks; i++)
-                        if (bhs[i])
-                                brelse(bhs[i]);
+                        brelse(bhs[i]);
                 kfree(bhs);
         }
 
@@ -1598,10 +1574,10 @@ static int ocfs2_symlink(struct inode *dir,
                 u32 offset = 0;
 
                 inode->i_op = &ocfs2_symlink_inode_operations;
-                status = ocfs2_do_extend_allocation(osb, inode, &offset, 1, 0,
-                                                    new_fe_bh,
-                                                    handle, data_ac, NULL,
-                                                    NULL);
+                status = ocfs2_add_inode_data(osb, inode, &offset, 1, 0,
+                                              new_fe_bh,
+                                              handle, data_ac, NULL,
+                                              NULL);
                 if (status < 0) {
                         if (status != -ENOSPC && status != -EINTR) {
                                 mlog(ML_ERROR,
@@ -1659,12 +1635,9 @@ bail:
 
         ocfs2_inode_unlock(dir, 1);
 
-        if (new_fe_bh)
-                brelse(new_fe_bh);
-        if (parent_fe_bh)
-                brelse(parent_fe_bh);
-        if (de_bh)
-                brelse(de_bh);
+        brelse(new_fe_bh);
+        brelse(parent_fe_bh);
+        brelse(de_bh);
         if (inode_ac)
                 ocfs2_free_alloc_context(inode_ac);
         if (data_ac)
@@ -1759,8 +1732,7 @@ leave:
                 iput(orphan_dir_inode);
         }
 
-        if (orphan_dir_bh)
-                brelse(orphan_dir_bh);
+        brelse(orphan_dir_bh);
 
         mlog_exit(status);
         return status;
@@ -1780,10 +1752,9 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb,
 
         mlog_entry("(inode->i_ino = %lu)\n", inode->i_ino);
 
-        status = ocfs2_read_block(osb,
+        status = ocfs2_read_block(orphan_dir_inode,
                                   OCFS2_I(orphan_dir_inode)->ip_blkno,
-                                  &orphan_dir_bh, OCFS2_BH_CACHED,
-                                  orphan_dir_inode);
+                                  &orphan_dir_bh);
         if (status < 0) {
                 mlog_errno(status);
                 goto leave;
@@ -1829,8 +1800,7 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb,
              (unsigned long long)OCFS2_I(inode)->ip_blkno, osb->slot_num);
 
 leave:
-        if (orphan_dir_bh)
-                brelse(orphan_dir_bh);
+        brelse(orphan_dir_bh);
 
         mlog_exit(status);
         return status;
@@ -1898,8 +1868,7 @@ int ocfs2_orphan_del(struct ocfs2_super *osb,
         }
 
 leave:
-        if (target_de_bh)
-                brelse(target_de_bh);
+        brelse(target_de_bh);
 
         mlog_exit(status);
         return status;
@@ -1918,4 +1887,8 @@ const struct inode_operations ocfs2_dir_iops = {
         .setattr        = ocfs2_setattr,
         .getattr        = ocfs2_getattr,
         .permission     = ocfs2_permission,
+        .setxattr       = generic_setxattr,
+        .getxattr       = generic_getxattr,
+        .listxattr      = ocfs2_listxattr,
+        .removexattr    = generic_removexattr,
 };
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 7f625f2b1117..a21a465490c4 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -34,7 +34,12 @@
 #include <linux/workqueue.h>
 #include <linux/kref.h>
 #include <linux/mutex.h>
-#include <linux/jbd.h>
+#ifndef CONFIG_OCFS2_COMPAT_JBD
+# include <linux/jbd2.h>
+#else
+# include <linux/jbd.h>
+# include "ocfs2_jbd_compat.h"
+#endif
 
 /* For union ocfs2_dlm_lksb */
 #include "stackglue.h"
@@ -171,9 +176,13 @@ struct ocfs2_alloc_stats
 
 enum ocfs2_local_alloc_state
 {
-        OCFS2_LA_UNUSED = 0,
-        OCFS2_LA_ENABLED,
-        OCFS2_LA_DISABLED
+        OCFS2_LA_UNUSED = 0,    /* Local alloc will never be used for
+                                 * this mountpoint. */
+        OCFS2_LA_ENABLED,       /* Local alloc is in use. */
+        OCFS2_LA_THROTTLED,     /* Local alloc is in use, but number
+                                 * of bits has been reduced. */
+        OCFS2_LA_DISABLED       /* Local alloc has temporarily been
+                                 * disabled. */
 };
 
 enum ocfs2_mount_options
@@ -184,6 +193,8 @@ enum ocfs2_mount_options
         OCFS2_MOUNT_ERRORS_PANIC = 1 << 3, /* Panic on errors */
         OCFS2_MOUNT_DATA_WRITEBACK = 1 << 4, /* No data ordering */
         OCFS2_MOUNT_LOCALFLOCKS = 1 << 5, /* No cluster aware user file locks */
+        OCFS2_MOUNT_NOUSERXATTR = 1 << 6, /* No user xattr */
+        OCFS2_MOUNT_INODE64 = 1 << 7,   /* Allow inode numbers > 2^32 */
 };
 
 #define OCFS2_OSB_SOFT_RO       0x0001
@@ -214,6 +225,7 @@ struct ocfs2_super
         u32 bitmap_cpg;
         u8 *uuid;
         char *uuid_str;
+        u32 uuid_hash;
         u8 *vol_label;
         u64 first_cluster_group_blkno;
         u32 fs_generation;
@@ -241,6 +253,7 @@ struct ocfs2_super
         int s_sectsize_bits;
         int s_clustersize;
         int s_clustersize_bits;
+        unsigned int s_xattr_inline_size;
 
         atomic_t vol_state;
         struct mutex recovery_lock;
@@ -252,11 +265,27 @@ struct ocfs2_super
         struct ocfs2_journal *journal;
         unsigned long osb_commit_interval;
 
-        int local_alloc_size;
-        enum ocfs2_local_alloc_state local_alloc_state;
+        struct delayed_work             la_enable_wq;
+
+        /*
+         * Must hold local alloc i_mutex and osb->osb_lock to change
+         * local_alloc_bits. Reads can be done under either lock.
+         */
+        unsigned int local_alloc_bits;
+        unsigned int local_alloc_default_bits;
+
+        enum ocfs2_local_alloc_state local_alloc_state; /* protected
+                                                         * by osb_lock */
+
         struct buffer_head *local_alloc_bh;
+
         u64 la_last_gd;
 
+#ifdef CONFIG_OCFS2_FS_STATS
+        struct dentry *local_alloc_debug;
+        char *local_alloc_debug_buf;
+#endif
+
         /* Next two fields are for local node slot recovery during
          * mount. */
         int dirty;
@@ -340,6 +369,13 @@ static inline int ocfs2_supports_inline_data(struct ocfs2_super *osb)
         return 0;
 }
 
+static inline int ocfs2_supports_xattr(struct ocfs2_super *osb)
+{
+        if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_XATTR)
+                return 1;
+        return 0;
+}
+
 /* set / clear functions because cluster events can make these happen
  * in parallel so we want the transitions to be atomic. this also
  * means that any future flags osb_flags must be protected by spinlock
@@ -554,6 +590,14 @@ static inline unsigned int ocfs2_pages_per_cluster(struct super_block *sb)
         return pages_per_cluster;
 }
 
+static inline unsigned int ocfs2_megabytes_to_clusters(struct super_block *sb,
+                                                       unsigned int megs)
+{
+        BUILD_BUG_ON(OCFS2_MAX_CLUSTERSIZE > 1048576);
+
+        return megs << (20 - OCFS2_SB(sb)->s_clustersize_bits);
+}
+
 static inline void ocfs2_init_inode_steal_slot(struct ocfs2_super *osb)
 {
         spin_lock(&osb->osb_lock);
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 4f619850ccf7..f24ce3d3f956 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -64,6 +64,7 @@
 #define OCFS2_INODE_SIGNATURE           "INODE01"
 #define OCFS2_EXTENT_BLOCK_SIGNATURE    "EXBLK01"
 #define OCFS2_GROUP_DESC_SIGNATURE      "GROUP01"
+#define OCFS2_XATTR_BLOCK_SIGNATURE     "XATTR01"
 
 /* Compatibility flags */
 #define OCFS2_HAS_COMPAT_FEATURE(sb,mask)                       \
@@ -90,7 +91,8 @@
                                          | OCFS2_FEATURE_INCOMPAT_SPARSE_ALLOC \
                                          | OCFS2_FEATURE_INCOMPAT_INLINE_DATA \
                                          | OCFS2_FEATURE_INCOMPAT_EXTENDED_SLOT_MAP \
-                                         | OCFS2_FEATURE_INCOMPAT_USERSPACE_STACK)
+                                         | OCFS2_FEATURE_INCOMPAT_USERSPACE_STACK \
+                                         | OCFS2_FEATURE_INCOMPAT_XATTR)
 #define OCFS2_FEATURE_RO_COMPAT_SUPP    OCFS2_FEATURE_RO_COMPAT_UNWRITTEN
 
 /*
@@ -127,10 +129,6 @@
 /* Support for data packed into inode blocks */
 #define OCFS2_FEATURE_INCOMPAT_INLINE_DATA      0x0040
 
-/* Support for the extended slot map */
-#define OCFS2_FEATURE_INCOMPAT_EXTENDED_SLOT_MAP 0x100
-
-
 /*
  * Support for alternate, userspace cluster stacks.  If set, the superblock
  * field s_cluster_info contains a tag for the alternate stack in use as
@@ -142,6 +140,12 @@
  */
 #define OCFS2_FEATURE_INCOMPAT_USERSPACE_STACK  0x0080
 
+/* Support for the extended slot map */
+#define OCFS2_FEATURE_INCOMPAT_EXTENDED_SLOT_MAP 0x100
+
+/* Support for extended attributes */
+#define OCFS2_FEATURE_INCOMPAT_XATTR            0x0200
+
 /*
  * backup superblock flag is used to indicate that this volume
  * has backup superblocks.
@@ -299,6 +303,12 @@ struct ocfs2_new_group_input {
  */
 #define OCFS2_DEFAULT_LOCAL_ALLOC_SIZE  8
 
+/*
+ * Inline extended attribute size (in bytes)
+ * The value chosen should be aligned to 16 byte boundaries.
+ */
+#define OCFS2_MIN_XATTR_INLINE_SIZE     256
+
 struct ocfs2_system_inode_info {
         char    *si_name;
         int     si_iflags;
@@ -563,7 +573,7 @@ struct ocfs2_super_block {
 /*40*/  __le16 s_max_slots;             /* Max number of simultaneous mounts
                                            before tunefs required */
         __le16 s_tunefs_flag;
-        __le32 s_reserved1;
+        __le32 s_uuid_hash;             /* hash value of uuid */
         __le64 s_first_cluster_group;   /* Block offset of 1st cluster
                                          * group header */
 /*50*/  __u8  s_label[OCFS2_MAX_VOL_LABEL_LEN]; /* Label for mounting, etc. */
@@ -571,7 +581,11 @@ struct ocfs2_super_block {
 /*A0*/  struct ocfs2_cluster_info s_cluster_info; /* Selected userspace
                                                      stack.  Only valid
                                                      with INCOMPAT flag. */
-/*B8*/  __le64 s_reserved2[17];         /* Fill out superblock */
+/*B8*/  __le16 s_xattr_inline_size;     /* extended attribute inline size
+                                           for this fs*/
+        __le16 s_reserved0;
+        __le32 s_reserved1;
+/*C0*/  __le64 s_reserved2[16];         /* Fill out superblock */
 /*140*/
 
         /*
@@ -621,7 +635,8 @@ struct ocfs2_dinode {
                                            belongs to */
         __le16 i_suballoc_bit;          /* Bit offset in suballocator
                                            block group */
-/*10*/  __le32 i_reserved0;
+/*10*/  __le16 i_reserved0;
+        __le16 i_xattr_inline_size;
         __le32 i_clusters;              /* Cluster count */
         __le32 i_uid;                   /* Owner UID */
         __le32 i_gid;                   /* Owning GID */
@@ -640,11 +655,12 @@ struct ocfs2_dinode {
         __le32 i_atime_nsec;
         __le32 i_ctime_nsec;
         __le32 i_mtime_nsec;
-        __le32 i_attr;
+/*70*/  __le32 i_attr;
         __le16 i_orphaned_slot;         /* Only valid when OCFS2_ORPHANED_FL
                                            was set in i_flags */
         __le16 i_dyn_features;
-/*70*/  __le64 i_reserved2[8];
+        __le64 i_xattr_loc;
+/*80*/  __le64 i_reserved2[7];
 /*B8*/  union {
                 __le64 i_pad1;          /* Generic way to refer to this
                                            64bit union */
@@ -715,6 +731,136 @@ struct ocfs2_group_desc
 /*40*/  __u8    bg_bitmap[0];
 };
 
+/*
+ * On disk extended attribute structure for OCFS2.
+ */
+
+/*
+ * ocfs2_xattr_entry indicates one extend attribute.
+ *
+ * Note that it can be stored in inode, one block or one xattr bucket.
+ */
+struct ocfs2_xattr_entry {
+        __le32  xe_name_hash;    /* hash value of xattr prefix+suffix. */
+        __le16  xe_name_offset;  /* byte offset from the 1st etnry in the local
+                                    local xattr storage(inode, xattr block or
+                                    xattr bucket). */
+        __u8    xe_name_len;     /* xattr name len, does't include prefix. */
+        __u8    xe_type;         /* the low 7 bits indicates the name prefix's
+                                  * type and the highest 1 bits indicate whether
+                                  * the EA is stored in the local storage. */
+        __le64  xe_value_size;   /* real xattr value length. */
+};
+
+/*
+ * On disk structure for xattr header.
+ *
+ * One ocfs2_xattr_header describes how many ocfs2_xattr_entry records in
+ * the local xattr storage.
+ */
+struct ocfs2_xattr_header {
+        __le16  xh_count;                       /* contains the count of how
+                                                   many records are in the
+                                                   local xattr storage. */
+        __le16  xh_free_start;                  /* current offset for storing
+                                                   xattr. */
+        __le16  xh_name_value_len;              /* total length of name/value
+                                                   length in this bucket. */
+        __le16  xh_num_buckets;                 /* bucket nums in one extent
+                                                   record, only valid in the
+                                                   first bucket. */
+        __le64  xh_csum;
+        struct ocfs2_xattr_entry xh_entries[0]; /* xattr entry list. */
+};
+
+/*
+ * On disk structure for xattr value root.
+ *
+ * It is used when one extended attribute's size is larger, and we will save it
+ * in an outside cluster. It will stored in a b-tree like file content.
+ */
+struct ocfs2_xattr_value_root {
+/*00*/  __le32  xr_clusters;              /* clusters covered by xattr value. */
+        __le32  xr_reserved0;
+        __le64  xr_last_eb_blk;           /* Pointer to last extent block */
+/*10*/  struct ocfs2_extent_list xr_list; /* Extent record list */
+};
+
+/*
+ * On disk structure for xattr tree root.
+ *
+ * It is used when there are too many extended attributes for one file. These
+ * attributes will be organized and stored in an indexed-btree.
+ */
+struct ocfs2_xattr_tree_root {
+/*00*/  __le32  xt_clusters;              /* clusters covered by xattr. */
+        __le32  xt_reserved0;
+        __le64  xt_last_eb_blk;           /* Pointer to last extent block */
+/*10*/  struct ocfs2_extent_list xt_list; /* Extent record list */
+};
+
+#define OCFS2_XATTR_INDEXED     0x1
+#define OCFS2_HASH_SHIFT        5
+#define OCFS2_XATTR_ROUND       3
+#define OCFS2_XATTR_SIZE(size)  (((size) + OCFS2_XATTR_ROUND) & \
+                                ~(OCFS2_XATTR_ROUND))
+
+#define OCFS2_XATTR_BUCKET_SIZE                 4096
+#define OCFS2_XATTR_MAX_BLOCKS_PER_BUCKET       (OCFS2_XATTR_BUCKET_SIZE \
+                                                 / OCFS2_MIN_BLOCKSIZE)
+
+/*
+ * On disk structure for xattr block.
+ */
+struct ocfs2_xattr_block {
+/*00*/  __u8    xb_signature[8];     /* Signature for verification */
+        __le16  xb_suballoc_slot;    /* Slot suballocator this
+                                        block belongs to. */
+        __le16  xb_suballoc_bit;     /* Bit offset in suballocator
+                                        block group */
+        __le32  xb_fs_generation;    /* Must match super block */
+/*10*/  __le64  xb_blkno;            /* Offset on disk, in blocks */
+        __le64  xb_csum;
+/*20*/  __le16  xb_flags;            /* Indicates whether this block contains
+                                        real xattr or a xattr tree. */
+        __le16  xb_reserved0;
+        __le32  xb_reserved1;
+        __le64  xb_reserved2;
+/*30*/  union {
+                struct ocfs2_xattr_header xb_header; /* xattr header if this
+                                                        block contains xattr */
+                struct ocfs2_xattr_tree_root xb_root;/* xattr tree root if this
+                                                        block cotains xattr
+                                                        tree. */
+        } xb_attrs;
+};
+
+#define OCFS2_XATTR_ENTRY_LOCAL         0x80
+#define OCFS2_XATTR_TYPE_MASK           0x7F
+static inline void ocfs2_xattr_set_local(struct ocfs2_xattr_entry *xe,
+                                         int local)
+{
+        if (local)
+                xe->xe_type |= OCFS2_XATTR_ENTRY_LOCAL;
+        else
+                xe->xe_type &= ~OCFS2_XATTR_ENTRY_LOCAL;
+}
+
+static inline int ocfs2_xattr_is_local(struct ocfs2_xattr_entry *xe)
+{
+        return xe->xe_type & OCFS2_XATTR_ENTRY_LOCAL;
+}
+
+static inline void ocfs2_xattr_set_type(struct ocfs2_xattr_entry *xe, int type)
+{
+        xe->xe_type |= type & OCFS2_XATTR_TYPE_MASK;
+}
+
+static inline int ocfs2_xattr_get_type(struct ocfs2_xattr_entry *xe)
+{
+        return xe->xe_type & OCFS2_XATTR_TYPE_MASK;
+}
+
 #ifdef __KERNEL__
 static inline int ocfs2_fast_symlink_chars(struct super_block *sb)
 {
@@ -728,6 +874,20 @@ static inline int ocfs2_max_inline_data(struct super_block *sb)
                 offsetof(struct ocfs2_dinode, id2.i_data.id_data);
 }
 
+static inline int ocfs2_max_inline_data_with_xattr(struct super_block *sb,
+                                                   struct ocfs2_dinode *di)
+{
+        unsigned int xattrsize = le16_to_cpu(di->i_xattr_inline_size);
+
+        if (le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_XATTR_FL)
+                return sb->s_blocksize -
+                        offsetof(struct ocfs2_dinode, id2.i_data.id_data) -
+                        xattrsize;
+        else
+                return sb->s_blocksize -
+                        offsetof(struct ocfs2_dinode, id2.i_data.id_data);
+}
+
 static inline int ocfs2_extent_recs_per_inode(struct super_block *sb)
 {
         int size;
@@ -738,6 +898,24 @@ static inline int ocfs2_extent_recs_per_inode(struct super_block *sb)
         return size / sizeof(struct ocfs2_extent_rec);
 }
 
+static inline int ocfs2_extent_recs_per_inode_with_xattr(
+                                                struct super_block *sb,
+                                                struct ocfs2_dinode *di)
+{
+        int size;
+        unsigned int xattrsize = le16_to_cpu(di->i_xattr_inline_size);
+
+        if (le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_XATTR_FL)
+                size = sb->s_blocksize -
+                        offsetof(struct ocfs2_dinode, id2.i_list.l_recs) -
+                        xattrsize;
+        else
+                size = sb->s_blocksize -
+                        offsetof(struct ocfs2_dinode, id2.i_list.l_recs);
+
+        return size / sizeof(struct ocfs2_extent_rec);
+}
+
 static inline int ocfs2_chain_recs_per_inode(struct super_block *sb)
 {
         int size;
@@ -801,6 +979,17 @@ static inline u64 ocfs2_backup_super_blkno(struct super_block *sb, int index)
         return 0;
 
 }
+
+static inline u16 ocfs2_xattr_recs_per_xb(struct super_block *sb)
+{
+        int size;
+
+        size = sb->s_blocksize -
+                offsetof(struct ocfs2_xattr_block,
+                         xb_attrs.xb_root.xt_list.l_recs);
+
+        return size / sizeof(struct ocfs2_extent_rec);
+}
 #else
 static inline int ocfs2_fast_symlink_chars(int blocksize)
 {
@@ -884,6 +1073,17 @@ static inline uint64_t ocfs2_backup_super_blkno(int blocksize, int index)
 
         return 0;
 }
+
+static inline int ocfs2_xattr_recs_per_xb(int blocksize)
+{
+        int size;
+
+        size = blocksize -
+                offsetof(struct ocfs2_xattr_block,
+                         xb_attrs.xb_root.xt_list.l_recs);
+
+        return size / sizeof(struct ocfs2_extent_rec);
+}
 #endif  /* __KERNEL__ */
 
 
diff --git a/fs/ocfs2/ocfs2_jbd_compat.h b/fs/ocfs2/ocfs2_jbd_compat.h
new file mode 100644
index 000000000000..b91c78f8f558
--- /dev/null
+++ b/fs/ocfs2/ocfs2_jbd_compat.h
@@ -0,0 +1,82 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * ocfs2_jbd_compat.h
+ *
+ * Compatibility defines for JBD.
+ *
+ * Copyright (C) 2008 Oracle.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef OCFS2_JBD_COMPAT_H
+#define OCFS2_JBD_COMPAT_H
+
+#ifndef CONFIG_OCFS2_COMPAT_JBD
+# error Should not have been included
+#endif
+
+struct jbd2_inode {
+        unsigned int dummy;
+};
+
+#define JBD2_BARRIER                    JFS_BARRIER
+#define JBD2_DEFAULT_MAX_COMMIT_AGE     JBD_DEFAULT_MAX_COMMIT_AGE
+
+#define jbd2_journal_ack_err                    journal_ack_err
+#define jbd2_journal_clear_err                  journal_clear_err
+#define jbd2_journal_destroy                    journal_destroy
+#define jbd2_journal_dirty_metadata             journal_dirty_metadata
+#define jbd2_journal_errno                      journal_errno
+#define jbd2_journal_extend                     journal_extend
+#define jbd2_journal_flush                      journal_flush
+#define jbd2_journal_force_commit               journal_force_commit
+#define jbd2_journal_get_write_access           journal_get_write_access
+#define jbd2_journal_get_undo_access            journal_get_undo_access
+#define jbd2_journal_init_inode                 journal_init_inode
+#define jbd2_journal_invalidatepage             journal_invalidatepage
+#define jbd2_journal_load                       journal_load
+#define jbd2_journal_lock_updates               journal_lock_updates
+#define jbd2_journal_restart                    journal_restart
+#define jbd2_journal_start                      journal_start
+#define jbd2_journal_start_commit               journal_start_commit
+#define jbd2_journal_stop                       journal_stop
+#define jbd2_journal_try_to_free_buffers        journal_try_to_free_buffers
+#define jbd2_journal_unlock_updates             journal_unlock_updates
+#define jbd2_journal_wipe                       journal_wipe
+#define jbd2_log_wait_commit                    log_wait_commit
+
+static inline int jbd2_journal_file_inode(handle_t *handle,
+                                          struct jbd2_inode *inode)
+{
+        return 0;
+}
+
+static inline int jbd2_journal_begin_ordered_truncate(struct jbd2_inode *inode,
+                                                      loff_t new_size)
+{
+        return 0;
+}
+
+static inline void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode,
+                                               struct inode *inode)
+{
+        return;
+}
+
+static inline void jbd2_journal_release_jbd_inode(journal_t *journal,
+                                                  struct jbd2_inode *jinode)
+{
+        return;
+}
+
+
+#endif  /* OCFS2_JBD_COMPAT_H */
diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c
index 8166968e9015..ffd48db229a7 100644
--- a/fs/ocfs2/resize.c
+++ b/fs/ocfs2/resize.c
@@ -200,7 +200,7 @@ static int update_backups(struct inode * inode, u32 clusters, char *data)
                 if (cluster > clusters)
                         break;
 
-                ret = ocfs2_read_block(osb, blkno, &backup, 0, NULL);
+                ret = ocfs2_read_blocks_sync(osb, blkno, 1, &backup);
                 if (ret < 0) {
                         mlog_errno(ret);
                         break;
@@ -236,8 +236,8 @@ static void ocfs2_update_super_and_backups(struct inode *inode,
          * update the superblock last.
          * It doesn't matter if the write failed.
          */
-        ret = ocfs2_read_block(osb, OCFS2_SUPER_BLOCK_BLKNO,
-                               &super_bh, 0, NULL);
+        ret = ocfs2_read_blocks_sync(osb, OCFS2_SUPER_BLOCK_BLKNO, 1,
+                                     &super_bh);
         if (ret < 0) {
                 mlog_errno(ret);
                 goto out;
@@ -332,8 +332,7 @@ int ocfs2_group_extend(struct inode * inode, int new_clusters)
         lgd_blkno = ocfs2_which_cluster_group(main_bm_inode,
                                               first_new_cluster - 1);
 
-        ret = ocfs2_read_block(osb, lgd_blkno, &group_bh, OCFS2_BH_CACHED,
-                               main_bm_inode);
+        ret = ocfs2_read_block(main_bm_inode, lgd_blkno, &group_bh);
         if (ret < 0) {
                 mlog_errno(ret);
                 goto out_unlock;
@@ -540,7 +539,7 @@ int ocfs2_group_add(struct inode *inode, struct ocfs2_new_group_input *input)
                 goto out_unlock;
         }
 
-        ret = ocfs2_read_block(osb, input->group, &group_bh, 0, NULL);
+        ret = ocfs2_read_blocks_sync(osb, input->group, 1, &group_bh);
         if (ret < 0) {
                 mlog(ML_ERROR, "Can't read the group descriptor # %llu "
                      "from the device.", (unsigned long long)input->group);
diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c
index bb5ff8939bf1..bdda2d8f8508 100644
--- a/fs/ocfs2/slot_map.c
+++ b/fs/ocfs2/slot_map.c
@@ -150,8 +150,8 @@ int ocfs2_refresh_slot_info(struct ocfs2_super *osb)
          * be !NULL.  Thus, ocfs2_read_blocks() will ignore blocknr.  If
          * this is not true, the read of -1 (UINT64_MAX) will fail.
          */
-        ret = ocfs2_read_blocks(osb, -1, si->si_blocks, si->si_bh, 0,
-                                si->si_inode);
+        ret = ocfs2_read_blocks(si->si_inode, -1, si->si_blocks, si->si_bh,
+                                OCFS2_BH_IGNORE_CACHE);
         if (ret == 0) {
                 spin_lock(&osb->osb_lock);
                 ocfs2_update_slot_info(si);
@@ -404,7 +404,8 @@ static int ocfs2_map_slot_buffers(struct ocfs2_super *osb,
                      (unsigned long long)blkno);
 
                 bh = NULL;  /* Acquire a fresh bh */
-                status = ocfs2_read_block(osb, blkno, &bh, 0, si->si_inode);
+                status = ocfs2_read_blocks(si->si_inode, blkno, 1, &bh,
+                                           OCFS2_BH_IGNORE_CACHE);
                 if (status < 0) {
                         mlog_errno(status);
                         goto bail;
diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index 353fc35c6748..faec2d879357 100644
--- a/fs/ocfs2/stack_user.c
+++ b/fs/ocfs2/stack_user.c
@@ -28,6 +28,7 @@
 #include "ocfs2.h"  /* For struct ocfs2_lock_res */
 #include "stackglue.h"
 
+#include <linux/dlm_plock.h>
 
 /*
  * The control protocol starts with a handshake.  Until the handshake
@@ -746,6 +747,37 @@ static void user_dlm_dump_lksb(union ocfs2_dlm_lksb *lksb)
 {
 }
 
+static int user_plock(struct ocfs2_cluster_connection *conn,
+                      u64 ino,
+                      struct file *file,
+                      int cmd,
+                      struct file_lock *fl)
+{
+        /*
+         * This more or less just demuxes the plock request into any
+         * one of three dlm calls.
+         *
+         * Internally, fs/dlm will pass these to a misc device, which
+         * a userspace daemon will read and write to.
+         *
+         * For now, cancel requests (which happen internally only),
+         * are turned into unlocks. Most of this function taken from
+         * gfs2_lock.
+         */
+
+        if (cmd == F_CANCELLK) {
+                cmd = F_SETLK;
+                fl->fl_type = F_UNLCK;
+        }
+
+        if (IS_GETLK(cmd))
+                return dlm_posix_get(conn->cc_lockspace, ino, file, fl);
+        else if (fl->fl_type == F_UNLCK)
+                return dlm_posix_unlock(conn->cc_lockspace, ino, file, fl);
+        else
+                return dlm_posix_lock(conn->cc_lockspace, ino, file, cmd, fl);
+}
+
 /*
  * Compare a requested locking protocol version against the current one.
  *
@@ -839,6 +871,7 @@ static struct ocfs2_stack_operations ocfs2_user_plugin_ops = {
         .dlm_unlock     = user_dlm_unlock,
         .lock_status    = user_dlm_lock_status,
         .lock_lvb       = user_dlm_lvb,
+        .plock          = user_plock,
         .dump_lksb      = user_dlm_dump_lksb,
 };
 
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 07f348b8d721..68b668b0e60a 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -288,6 +288,26 @@ void ocfs2_dlm_dump_lksb(union ocfs2_dlm_lksb *lksb)
 }
 EXPORT_SYMBOL_GPL(ocfs2_dlm_dump_lksb);
 
+int ocfs2_stack_supports_plocks(void)
+{
+        return active_stack && active_stack->sp_ops->plock;
+}
+EXPORT_SYMBOL_GPL(ocfs2_stack_supports_plocks);
+
+/*
+ * ocfs2_plock() can only be safely called if
+ * ocfs2_stack_supports_plocks() returned true
+ */
+int ocfs2_plock(struct ocfs2_cluster_connection *conn, u64 ino,
+                struct file *file, int cmd, struct file_lock *fl)
+{
+        WARN_ON_ONCE(active_stack->sp_ops->plock == NULL);
+        if (active_stack->sp_ops->plock)
+                return active_stack->sp_ops->plock(conn, ino, file, cmd, fl);
+        return -EOPNOTSUPP;
+}
+EXPORT_SYMBOL_GPL(ocfs2_plock);
+
 int ocfs2_cluster_connect(const char *stack_name,
                           const char *group,
                           int grouplen,
diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h
index db56281dd1be..c571af375ef8 100644
--- a/fs/ocfs2/stackglue.h
+++ b/fs/ocfs2/stackglue.h
@@ -28,6 +28,10 @@
 #include "dlm/dlmapi.h"
 #include <linux/dlm.h>
 
+/* Needed for plock-related prototypes */
+struct file;
+struct file_lock;
+
 /*
  * dlmconstants.h does not have a LOCAL flag.  We hope to remove it
  * some day, but right now we need it.  Let's fake it.  This value is larger
@@ -187,6 +191,17 @@ struct ocfs2_stack_operations {
         void *(*lock_lvb)(union ocfs2_dlm_lksb *lksb);
 
         /*
+         * Cluster-aware posix locks
+         *
+         * This is NULL for stacks which do not support posix locks.
+         */
+        int (*plock)(struct ocfs2_cluster_connection *conn,
+                     u64 ino,
+                     struct file *file,
+                     int cmd,
+                     struct file_lock *fl);
+
+        /*
          * This is an optoinal debugging hook.  If provided, the
          * stack can dump debugging information about this lock.
          */
@@ -240,6 +255,10 @@ int ocfs2_dlm_lock_status(union ocfs2_dlm_lksb *lksb);
 void *ocfs2_dlm_lvb(union ocfs2_dlm_lksb *lksb);
 void ocfs2_dlm_dump_lksb(union ocfs2_dlm_lksb *lksb);
 
+int ocfs2_stack_supports_plocks(void);
+int ocfs2_plock(struct ocfs2_cluster_connection *conn, u64 ino,
+                struct file *file, int cmd, struct file_lock *fl);
+
 void ocfs2_stack_glue_set_locking_protocol(struct ocfs2_locking_protocol *proto);
 
 
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index d2d278fb9819..c5ff18b46b57 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -62,15 +62,18 @@ static int ocfs2_block_group_fill(handle_t *handle,
                                   struct ocfs2_chain_list *cl);
 static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
                                    struct inode *alloc_inode,
-                                   struct buffer_head *bh);
+                                   struct buffer_head *bh,
+                                   u64 max_block);
 
 static int ocfs2_cluster_group_search(struct inode *inode,
                                       struct buffer_head *group_bh,
                                       u32 bits_wanted, u32 min_bits,
+                                      u64 max_block,
                                       u16 *bit_off, u16 *bits_found);
 static int ocfs2_block_group_search(struct inode *inode,
                                     struct buffer_head *group_bh,
                                     u32 bits_wanted, u32 min_bits,
+                                    u64 max_block,
                                     u16 *bit_off, u16 *bits_found);
 static int ocfs2_claim_suballoc_bits(struct ocfs2_super *osb,
                                      struct ocfs2_alloc_context *ac,
@@ -110,8 +113,11 @@ static inline void ocfs2_block_to_cluster_group(struct inode *inode,
                                                 u64 data_blkno,
                                                 u64 *bg_blkno,
                                                 u16 *bg_bit_off);
+static int ocfs2_reserve_clusters_with_limit(struct ocfs2_super *osb,
+                                             u32 bits_wanted, u64 max_block,
+                                             struct ocfs2_alloc_context **ac);
 
-static void ocfs2_free_ac_resource(struct ocfs2_alloc_context *ac)
+void ocfs2_free_ac_resource(struct ocfs2_alloc_context *ac)
 {
         struct inode *inode = ac->ac_inode;
 
@@ -124,10 +130,8 @@ static void ocfs2_free_ac_resource(struct ocfs2_alloc_context *ac)
                 iput(inode);
                 ac->ac_inode = NULL;
         }
-        if (ac->ac_bh) {
-                brelse(ac->ac_bh);
-                ac->ac_bh = NULL;
-        }
+        brelse(ac->ac_bh);
+        ac->ac_bh = NULL;
 }
 
 void ocfs2_free_alloc_context(struct ocfs2_alloc_context *ac)
@@ -276,7 +280,8 @@ static inline u16 ocfs2_find_smallest_chain(struct ocfs2_chain_list *cl)
  */
 static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
                                    struct inode *alloc_inode,
-                                   struct buffer_head *bh)
+                                   struct buffer_head *bh,
+                                   u64 max_block)
 {
         int status, credits;
         struct ocfs2_dinode *fe = (struct ocfs2_dinode *) bh->b_data;
@@ -294,9 +299,9 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
         mlog_entry_void();
 
         cl = &fe->id2.i_chain;
-        status = ocfs2_reserve_clusters(osb,
-                                        le16_to_cpu(cl->cl_cpg),
-                                        &ac);
+        status = ocfs2_reserve_clusters_with_limit(osb,
+                                                   le16_to_cpu(cl->cl_cpg),
+                                                   max_block, &ac);
         if (status < 0) {
                 if (status != -ENOSPC)
                         mlog_errno(status);
@@ -394,8 +399,7 @@ bail:
         if (ac)
                 ocfs2_free_alloc_context(ac);
 
-        if (bg_bh)
-                brelse(bg_bh);
+        brelse(bg_bh);
 
         mlog_exit(status);
         return status;
@@ -469,7 +473,8 @@ static int ocfs2_reserve_suballoc_bits(struct ocfs2_super *osb,
                         goto bail;
                 }
 
-                status = ocfs2_block_group_alloc(osb, alloc_inode, bh);
+                status = ocfs2_block_group_alloc(osb, alloc_inode, bh,
+                                                 ac->ac_max_block);
                 if (status < 0) {
                         if (status != -ENOSPC)
                                 mlog_errno(status);
@@ -486,16 +491,15 @@ static int ocfs2_reserve_suballoc_bits(struct ocfs2_super *osb,
         get_bh(bh);
         ac->ac_bh = bh;
 bail:
-        if (bh)
-                brelse(bh);
+        brelse(bh);
 
         mlog_exit(status);
         return status;
 }
 
-int ocfs2_reserve_new_metadata(struct ocfs2_super *osb,
-                               struct ocfs2_dinode *fe,
-                               struct ocfs2_alloc_context **ac)
+int ocfs2_reserve_new_metadata_blocks(struct ocfs2_super *osb,
+                                      int blocks,
+                                      struct ocfs2_alloc_context **ac)
 {
         int status;
         u32 slot;
@@ -507,7 +511,7 @@ int ocfs2_reserve_new_metadata(struct ocfs2_super *osb,
                 goto bail;
         }
 
-        (*ac)->ac_bits_wanted = ocfs2_extend_meta_needed(fe);
+        (*ac)->ac_bits_wanted = blocks;
         (*ac)->ac_which = OCFS2_AC_USE_META;
         slot = osb->slot_num;
         (*ac)->ac_group_search = ocfs2_block_group_search;
@@ -532,6 +536,15 @@ bail:
         return status;
 }
 
+int ocfs2_reserve_new_metadata(struct ocfs2_super *osb,
+                               struct ocfs2_extent_list *root_el,
+                               struct ocfs2_alloc_context **ac)
+{
+        return ocfs2_reserve_new_metadata_blocks(osb,
+                                        ocfs2_extend_meta_needed(root_el),
+                                        ac);
+}
+
 static int ocfs2_steal_inode_from_other_nodes(struct ocfs2_super *osb,
                                               struct ocfs2_alloc_context *ac)
 {
@@ -582,6 +595,14 @@ int ocfs2_reserve_new_inode(struct ocfs2_super *osb,
         (*ac)->ac_group_search = ocfs2_block_group_search;
 
         /*
+         * stat(2) can't handle i_ino > 32bits, so we tell the
+         * lower levels not to allocate us a block group past that
+         * limit.  The 'inode64' mount option avoids this behavior.
+         */
+        if (!(osb->s_mount_opt & OCFS2_MOUNT_INODE64))
+                (*ac)->ac_max_block = (u32)~0U;
+
+        /*
          * slot is set when we successfully steal inode from other nodes.
          * It is reset in 3 places:
          * 1. when we flush the truncate log
@@ -661,9 +682,9 @@ bail:
 /* Callers don't need to care which bitmap (local alloc or main) to
  * use so we figure it out for them, but unfortunately this clutters
  * things a bit. */
-int ocfs2_reserve_clusters(struct ocfs2_super *osb,
-                           u32 bits_wanted,
-                           struct ocfs2_alloc_context **ac)
+static int ocfs2_reserve_clusters_with_limit(struct ocfs2_super *osb,
+                                             u32 bits_wanted, u64 max_block,
+                                             struct ocfs2_alloc_context **ac)
 {
         int status;
 
@@ -677,24 +698,20 @@ int ocfs2_reserve_clusters(struct ocfs2_super *osb,
         }
 
         (*ac)->ac_bits_wanted = bits_wanted;
+        (*ac)->ac_max_block = max_block;
 
         status = -ENOSPC;
         if (ocfs2_alloc_should_use_local(osb, bits_wanted)) {
                 status = ocfs2_reserve_local_alloc_bits(osb,
                                                         bits_wanted,
                                                         *ac);
-                if ((status < 0) && (status != -ENOSPC)) {
+                if (status == -EFBIG) {
+                        /* The local alloc window is outside ac_max_block.
+                         * use the main bitmap. */
+                        status = -ENOSPC;
+                } else if ((status < 0) && (status != -ENOSPC)) {
                         mlog_errno(status);
                         goto bail;
-                } else if (status == -ENOSPC) {
-                        /* reserve_local_bits will return enospc with
-                         * the local alloc inode still locked, so we
-                         * can change this safely here. */
-                        mlog(0, "Disabling local alloc\n");
-                        /* We set to OCFS2_LA_DISABLED so that umount
-                         * can clean up what's left of the local
-                         * allocation */
-                        osb->local_alloc_state = OCFS2_LA_DISABLED;
                 }
         }
 
@@ -718,6 +735,13 @@ bail:
         return status;
 }
 
+int ocfs2_reserve_clusters(struct ocfs2_super *osb,
+                           u32 bits_wanted,
+                           struct ocfs2_alloc_context **ac)
+{
+        return ocfs2_reserve_clusters_with_limit(osb, bits_wanted, 0, ac);
+}
+
 /*
  * More or less lifted from ext3. I'll leave their description below:
  *
@@ -1000,11 +1024,14 @@ static inline int ocfs2_block_group_reasonably_empty(struct ocfs2_group_desc *bg
 static int ocfs2_cluster_group_search(struct inode *inode,
                                       struct buffer_head *group_bh,
                                       u32 bits_wanted, u32 min_bits,
+                                      u64 max_block,
                                       u16 *bit_off, u16 *bits_found)
 {
         int search = -ENOSPC;
         int ret;
+        u64 blkoff;
         struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *) group_bh->b_data;
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
         u16 tmp_off, tmp_found;
         unsigned int max_bits, gd_cluster_off;
 
@@ -1037,6 +1064,17 @@ static int ocfs2_cluster_group_search(struct inode *inode,
                 if (ret)
                         return ret;
 
+                if (max_block) {
+                        blkoff = ocfs2_clusters_to_blocks(inode->i_sb,
+                                                          gd_cluster_off +
+                                                          tmp_off + tmp_found);
+                        mlog(0, "Checking %llu against %llu\n",
+                             (unsigned long long)blkoff,
+                             (unsigned long long)max_block);
+                        if (blkoff > max_block)
+                                return -ENOSPC;
+                }
+
                 /* ocfs2_block_group_find_clear_bits() might
                  * return success, but we still want to return
                  * -ENOSPC unless it found the minimum number
@@ -1045,6 +1083,12 @@ static int ocfs2_cluster_group_search(struct inode *inode,
                         *bit_off = tmp_off;
                         *bits_found = tmp_found;
                         search = 0; /* success */
+                } else if (tmp_found) {
+                        /*
+                         * Don't show bits which we'll be returning
+                         * for allocation to the local alloc bitmap.
+                         */
+                        ocfs2_local_alloc_seen_free_bits(osb, tmp_found);
                 }
         }
 
@@ -1054,19 +1098,31 @@ static int ocfs2_cluster_group_search(struct inode *inode,
 static int ocfs2_block_group_search(struct inode *inode,
                                     struct buffer_head *group_bh,
                                     u32 bits_wanted, u32 min_bits,
+                                    u64 max_block,
                                     u16 *bit_off, u16 *bits_found)
 {
         int ret = -ENOSPC;
+        u64 blkoff;
         struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) group_bh->b_data;
 
         BUG_ON(min_bits != 1);
         BUG_ON(ocfs2_is_cluster_bitmap(inode));
 
-        if (bg->bg_free_bits_count)
+        if (bg->bg_free_bits_count) {
                 ret = ocfs2_block_group_find_clear_bits(OCFS2_SB(inode->i_sb),
                                                         group_bh, bits_wanted,
                                                         le16_to_cpu(bg->bg_bits),
                                                         bit_off, bits_found);
+                if (!ret && max_block) {
+                        blkoff = le64_to_cpu(bg->bg_blkno) + *bit_off +
+                                *bits_found;
+                        mlog(0, "Checking %llu against %llu\n",
+                             (unsigned long long)blkoff,
+                             (unsigned long long)max_block);
+                        if (blkoff > max_block)
+                                ret = -ENOSPC;
+                }
+        }
 
         return ret;
 }
@@ -1116,8 +1172,7 @@ static int ocfs2_search_one_group(struct ocfs2_alloc_context *ac,
         struct ocfs2_group_desc *gd;
         struct inode *alloc_inode = ac->ac_inode;
 
-        ret = ocfs2_read_block(OCFS2_SB(alloc_inode->i_sb), gd_blkno,
-                               &group_bh, OCFS2_BH_CACHED, alloc_inode);
+        ret = ocfs2_read_block(alloc_inode, gd_blkno, &group_bh);
         if (ret < 0) {
                 mlog_errno(ret);
                 return ret;
@@ -1131,7 +1186,7 @@ static int ocfs2_search_one_group(struct ocfs2_alloc_context *ac,
         }
 
         ret = ac->ac_group_search(alloc_inode, group_bh, bits_wanted, min_bits,
-                                  bit_off, &found);
+                                  ac->ac_max_block, bit_off, &found);
         if (ret < 0) {
                 if (ret != -ENOSPC)
                         mlog_errno(ret);
@@ -1186,9 +1241,9 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
              bits_wanted, chain,
              (unsigned long long)OCFS2_I(alloc_inode)->ip_blkno);
 
-        status = ocfs2_read_block(OCFS2_SB(alloc_inode->i_sb),
+        status = ocfs2_read_block(alloc_inode,
                                   le64_to_cpu(cl->cl_recs[chain].c_blkno),
-                                  &group_bh, OCFS2_BH_CACHED, alloc_inode);
+                                  &group_bh);
         if (status < 0) {
                 mlog_errno(status);
                 goto bail;
@@ -1204,21 +1259,20 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
         /* for now, the chain search is a bit simplistic. We just use
          * the 1st group with any empty bits. */
         while ((status = ac->ac_group_search(alloc_inode, group_bh,
-                                             bits_wanted, min_bits, bit_off,
+                                             bits_wanted, min_bits,
+                                             ac->ac_max_block, bit_off,
                                              &tmp_bits)) == -ENOSPC) {
                 if (!bg->bg_next_group)
                         break;
 
-                if (prev_group_bh) {
-                        brelse(prev_group_bh);
-                        prev_group_bh = NULL;
-                }
+                brelse(prev_group_bh);
+                prev_group_bh = NULL;
+
                 next_group = le64_to_cpu(bg->bg_next_group);
                 prev_group_bh = group_bh;
                 group_bh = NULL;
-                status = ocfs2_read_block(OCFS2_SB(alloc_inode->i_sb),
-                                          next_group, &group_bh,
-                                          OCFS2_BH_CACHED, alloc_inode);
+                status = ocfs2_read_block(alloc_inode,
+                                          next_group, &group_bh);
                 if (status < 0) {
                         mlog_errno(status);
                         goto bail;
@@ -1307,10 +1361,8 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
         *bg_blkno = le64_to_cpu(bg->bg_blkno);
         *bits_left = le16_to_cpu(bg->bg_free_bits_count);
 bail:
-        if (group_bh)
-                brelse(group_bh);
-        if (prev_group_bh)
-                brelse(prev_group_bh);
+        brelse(group_bh);
+        brelse(prev_group_bh);
 
         mlog_exit(status);
         return status;
@@ -1723,7 +1775,6 @@ int ocfs2_free_suballoc_bits(handle_t *handle,
 {
         int status = 0;
         u32 tmp_used;
-        struct ocfs2_super *osb = OCFS2_SB(alloc_inode->i_sb);
         struct ocfs2_dinode *fe = (struct ocfs2_dinode *) alloc_bh->b_data;
         struct ocfs2_chain_list *cl = &fe->id2.i_chain;
         struct buffer_head *group_bh = NULL;
@@ -1742,8 +1793,7 @@ int ocfs2_free_suballoc_bits(handle_t *handle,
              (unsigned long long)OCFS2_I(alloc_inode)->ip_blkno, count,
              (unsigned long long)bg_blkno, start_bit);
 
-        status = ocfs2_read_block(osb, bg_blkno, &group_bh, OCFS2_BH_CACHED,
-                                  alloc_inode);
+        status = ocfs2_read_block(alloc_inode, bg_blkno, &group_bh);
         if (status < 0) {
                 mlog_errno(status);
                 goto bail;
@@ -1784,8 +1834,7 @@ int ocfs2_free_suballoc_bits(handle_t *handle,
         }
 
 bail:
-        if (group_bh)
-                brelse(group_bh);
+        brelse(group_bh);
 
         mlog_exit(status);
         return status;
@@ -1838,9 +1887,15 @@ int ocfs2_free_clusters(handle_t *handle,
         status = ocfs2_free_suballoc_bits(handle, bitmap_inode, bitmap_bh,
                                           bg_start_bit, bg_blkno,
                                           num_clusters);
-        if (status < 0)
+        if (status < 0) {
                 mlog_errno(status);
+                goto out;
+        }
 
+        ocfs2_local_alloc_seen_free_bits(OCFS2_SB(bitmap_inode->i_sb),
+                                         num_clusters);
+
+out:
         mlog_exit(status);
         return status;
 }
@@ -1891,3 +1946,84 @@ static inline void ocfs2_debug_suballoc_inode(struct ocfs2_dinode *fe)
                        (unsigned long long)fe->id2.i_chain.cl_recs[i].c_blkno);
         }
 }
+
+/*
+ * For a given allocation, determine which allocators will need to be
+ * accessed, and lock them, reserving the appropriate number of bits.
+ *
+ * Sparse file systems call this from ocfs2_write_begin_nolock()
+ * and ocfs2_allocate_unwritten_extents().
+ *
+ * File systems which don't support holes call this from
+ * ocfs2_extend_allocation().
+ */
+int ocfs2_lock_allocators(struct inode *inode,
+                          struct ocfs2_extent_tree *et,
+                          u32 clusters_to_add, u32 extents_to_split,
+                          struct ocfs2_alloc_context **data_ac,
+                          struct ocfs2_alloc_context **meta_ac)
+{
+        int ret = 0, num_free_extents;
+        unsigned int max_recs_needed = clusters_to_add + 2 * extents_to_split;
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+        *meta_ac = NULL;
+        if (data_ac)
+                *data_ac = NULL;
+
+        BUG_ON(clusters_to_add != 0 && data_ac == NULL);
+
+        num_free_extents = ocfs2_num_free_extents(osb, inode, et);
+        if (num_free_extents < 0) {
+                ret = num_free_extents;
+                mlog_errno(ret);
+                goto out;
+        }
+
+        /*
+         * Sparse allocation file systems need to be more conservative
+         * with reserving room for expansion - the actual allocation
+         * happens while we've got a journal handle open so re-taking
+         * a cluster lock (because we ran out of room for another
+         * extent) will violate ordering rules.
+         *
+         * Most of the time we'll only be seeing this 1 cluster at a time
+         * anyway.
+         *
+         * Always lock for any unwritten extents - we might want to
+         * add blocks during a split.
+         */
+        if (!num_free_extents ||
+            (ocfs2_sparse_alloc(osb) && num_free_extents < max_recs_needed)) {
+                ret = ocfs2_reserve_new_metadata(osb, et->et_root_el, meta_ac);
+                if (ret < 0) {
+                        if (ret != -ENOSPC)
+                                mlog_errno(ret);
+                        goto out;
+                }
+        }
+
+        if (clusters_to_add == 0)
+                goto out;
+
+        ret = ocfs2_reserve_clusters(osb, clusters_to_add, data_ac);
+        if (ret < 0) {
+                if (ret != -ENOSPC)
+                        mlog_errno(ret);
+                goto out;
+        }
+
+out:
+        if (ret) {
+                if (*meta_ac) {
+                        ocfs2_free_alloc_context(*meta_ac);
+                        *meta_ac = NULL;
+                }
+
+                /*
+                 * We cannot have an error and a non null *data_ac.
+                 */
+        }
+
+        return ret;
+}
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index 544c600662bd..4df159d8f450 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -28,10 +28,11 @@
 
 typedef int (group_search_t)(struct inode *,
                              struct buffer_head *,
-                             u32,
-                             u32,
-                             u16 *,
-                             u16 *);
+                             u32,                       /* bits_wanted */
+                             u32,                       /* min_bits */
+                             u64,                       /* max_block */
+                             u16 *,                     /* *bit_off */
+                             u16 *);                    /* *bits_found */
 
 struct ocfs2_alloc_context {
         struct inode *ac_inode;    /* which bitmap are we allocating from? */
@@ -51,6 +52,8 @@ struct ocfs2_alloc_context {
         group_search_t *ac_group_search;
 
         u64    ac_last_group;
+        u64    ac_max_block;  /* Highest block number to allocate. 0 is
+                                 is the same as ~0 - unlimited */
 };
 
 void ocfs2_free_alloc_context(struct ocfs2_alloc_context *ac);
@@ -59,9 +62,17 @@ static inline int ocfs2_alloc_context_bits_left(struct ocfs2_alloc_context *ac)
         return ac->ac_bits_wanted - ac->ac_bits_given;
 }
 
+/*
+ * Please note that the caller must make sure that root_el is the root
+ * of extent tree. So for an inode, it should be &fe->id2.i_list. Otherwise
+ * the result may be wrong.
+ */
 int ocfs2_reserve_new_metadata(struct ocfs2_super *osb,
-                               struct ocfs2_dinode *fe,
+                               struct ocfs2_extent_list *root_el,
                                struct ocfs2_alloc_context **ac);
+int ocfs2_reserve_new_metadata_blocks(struct ocfs2_super *osb,
+                                      int blocks,
+                                      struct ocfs2_alloc_context **ac);
 int ocfs2_reserve_new_inode(struct ocfs2_super *osb,
                             struct ocfs2_alloc_context **ac);
 int ocfs2_reserve_clusters(struct ocfs2_super *osb,
@@ -147,6 +158,7 @@ static inline int ocfs2_is_cluster_bitmap(struct inode *inode)
  * apis above. */
 int ocfs2_reserve_cluster_bitmap_bits(struct ocfs2_super *osb,
                                       struct ocfs2_alloc_context *ac);
+void ocfs2_free_ac_resource(struct ocfs2_alloc_context *ac);
 
 /* given a cluster offset, calculate which block group it belongs to
  * and return that block offset. */
@@ -156,4 +168,8 @@ u64 ocfs2_which_cluster_group(struct inode *inode, u32 cluster);
 int ocfs2_check_group_descriptor(struct super_block *sb,
                                  struct ocfs2_dinode *di,
                                  struct ocfs2_group_desc *gd);
+int ocfs2_lock_allocators(struct inode *inode, struct ocfs2_extent_tree *et,
+                          u32 clusters_to_add, u32 extents_to_split,
+                          struct ocfs2_alloc_context **data_ac,
+                          struct ocfs2_alloc_context **meta_ac);
 #endif /* _CHAINALLOC_H_ */
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 88255d3f52b4..304b63ac78cf 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -64,6 +64,7 @@
 #include "sysfile.h"
 #include "uptodate.h"
 #include "ver.h"
+#include "xattr.h"
 
 #include "buffer_head_io.h"
 
@@ -154,10 +155,13 @@ enum {
         Opt_localalloc,
         Opt_localflocks,
         Opt_stack,
+        Opt_user_xattr,
+        Opt_nouser_xattr,
+        Opt_inode64,
         Opt_err,
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         {Opt_barrier, "barrier=%u"},
         {Opt_err_panic, "errors=panic"},
         {Opt_err_ro, "errors=remount-ro"},
@@ -173,6 +177,9 @@ static match_table_t tokens = {
         {Opt_localalloc, "localalloc=%d"},
         {Opt_localflocks, "localflocks"},
         {Opt_stack, "cluster_stack=%s"},
+        {Opt_user_xattr, "user_xattr"},
+        {Opt_nouser_xattr, "nouser_xattr"},
+        {Opt_inode64, "inode64"},
         {Opt_err, NULL}
 };
 
@@ -205,10 +212,11 @@ static int ocfs2_sync_fs(struct super_block *sb, int wait)
                 ocfs2_schedule_truncate_log_flush(osb, 0);
         }
 
-        if (journal_start_commit(OCFS2_SB(sb)->journal->j_journal, &target)) {
+        if (jbd2_journal_start_commit(OCFS2_SB(sb)->journal->j_journal,
+                                      &target)) {
                 if (wait)
-                        log_wait_commit(OCFS2_SB(sb)->journal->j_journal,
-                                        target);
+                        jbd2_log_wait_commit(OCFS2_SB(sb)->journal->j_journal,
+                                             target);
         }
         return 0;
 }
@@ -325,6 +333,7 @@ static struct inode *ocfs2_alloc_inode(struct super_block *sb)
         if (!oi)
                 return NULL;
 
+        jbd2_journal_init_jbd_inode(&oi->ip_jinode, &oi->vfs_inode);
         return &oi->vfs_inode;
 }
 
@@ -406,6 +415,15 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data)
                 goto out;
         }
 
+        /* Probably don't want this on remount; it might
+         * mess with other nodes */
+        if (!(osb->s_mount_opt & OCFS2_MOUNT_INODE64) &&
+            (parsed_options.mount_opt & OCFS2_MOUNT_INODE64)) {
+                ret = -EINVAL;
+                mlog(ML_ERROR, "Cannot enable inode64 on remount\n");
+                goto out;
+        }
+
         /* We're going to/from readonly mode. */
         if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY)) {
                 /* Lock here so the check of HARD_RO and the potential
@@ -637,7 +655,8 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
         osb->s_atime_quantum = parsed_options.atime_quantum;
         osb->preferred_slot = parsed_options.slot;
         osb->osb_commit_interval = parsed_options.commit_interval;
-        osb->local_alloc_size = parsed_options.localalloc_opt;
+        osb->local_alloc_default_bits = ocfs2_megabytes_to_clusters(sb, parsed_options.localalloc_opt);
+        osb->local_alloc_bits = osb->local_alloc_default_bits;
 
         status = ocfs2_verify_userspace_stack(osb, &parsed_options);
         if (status)
@@ -743,8 +762,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
         return status;
 
 read_super_error:
-        if (bh != NULL)
-                brelse(bh);
+        brelse(bh);
 
         if (inode)
                 iput(inode);
@@ -847,6 +865,12 @@ static int ocfs2_parse_options(struct super_block *sb,
                 case Opt_data_writeback:
                         mopt->mount_opt |= OCFS2_MOUNT_DATA_WRITEBACK;
                         break;
+                case Opt_user_xattr:
+                        mopt->mount_opt &= ~OCFS2_MOUNT_NOUSERXATTR;
+                        break;
+                case Opt_nouser_xattr:
+                        mopt->mount_opt |= OCFS2_MOUNT_NOUSERXATTR;
+                        break;
                 case Opt_atime_quantum:
                         if (match_int(&args[0], &option)) {
                                 status = 0;
@@ -873,7 +897,7 @@ static int ocfs2_parse_options(struct super_block *sb,
                         if (option < 0)
                                 return 0;
                         if (option == 0)
-                                option = JBD_DEFAULT_MAX_COMMIT_AGE;
+                                option = JBD2_DEFAULT_MAX_COMMIT_AGE;
                         mopt->commit_interval = HZ * option;
                         break;
                 case Opt_localalloc:
@@ -918,6 +942,9 @@ static int ocfs2_parse_options(struct super_block *sb,
                                OCFS2_STACK_LABEL_LEN);
                         mopt->cluster_stack[OCFS2_STACK_LABEL_LEN] = '\0';
                         break;
+                case Opt_inode64:
+                        mopt->mount_opt |= OCFS2_MOUNT_INODE64;
+                        break;
                 default:
                         mlog(ML_ERROR,
                              "Unrecognized mount option \"%s\" "
@@ -938,6 +965,7 @@ static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
 {
         struct ocfs2_super *osb = OCFS2_SB(mnt->mnt_sb);
         unsigned long opts = osb->s_mount_opt;
+        unsigned int local_alloc_megs;
 
         if (opts & OCFS2_MOUNT_HB_LOCAL)
                 seq_printf(s, ",_netdev,heartbeat=local");
@@ -970,8 +998,9 @@ static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
                 seq_printf(s, ",commit=%u",
                            (unsigned) (osb->osb_commit_interval / HZ));
 
-        if (osb->local_alloc_size != OCFS2_DEFAULT_LOCAL_ALLOC_SIZE)
-                seq_printf(s, ",localalloc=%d", osb->local_alloc_size);
+        local_alloc_megs = osb->local_alloc_bits >> (20 - osb->s_clustersize_bits);
+        if (local_alloc_megs != OCFS2_DEFAULT_LOCAL_ALLOC_SIZE)
+                seq_printf(s, ",localalloc=%d", local_alloc_megs);
 
         if (opts & OCFS2_MOUNT_LOCALFLOCKS)
                 seq_printf(s, ",localflocks,");
@@ -980,6 +1009,14 @@ static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
                 seq_printf(s, ",cluster_stack=%.*s", OCFS2_STACK_LABEL_LEN,
                            osb->osb_cluster_stack);
 
+        if (opts & OCFS2_MOUNT_NOUSERXATTR)
+                seq_printf(s, ",nouser_xattr");
+        else
+                seq_printf(s, ",user_xattr");
+
+        if (opts & OCFS2_MOUNT_INODE64)
+                seq_printf(s, ",inode64");
+
         return 0;
 }
 
@@ -1132,6 +1169,7 @@ static void ocfs2_inode_init_once(void *data)
         oi->ip_dir_start_lookup = 0;
 
         init_rwsem(&oi->ip_alloc_sem);
+        init_rwsem(&oi->ip_xattr_sem);
         mutex_init(&oi->ip_io_mutex);
 
         oi->ip_blkno = 0ULL;
@@ -1375,6 +1413,7 @@ static int ocfs2_initialize_super(struct super_block *sb,
         sb->s_fs_info = osb;
         sb->s_op = &ocfs2_sops;
         sb->s_export_op = &ocfs2_export_ops;
+        sb->s_xattr = ocfs2_xattr_handlers;
         sb->s_time_gran = 1;
         sb->s_flags |= MS_NOATIME;
         /* this is needed to support O_LARGEFILE */
@@ -1421,8 +1460,12 @@ static int ocfs2_initialize_super(struct super_block *sb,
 
         osb->slot_num = OCFS2_INVALID_SLOT;
 
+        osb->s_xattr_inline_size = le16_to_cpu(
+                                        di->id2.i_super.s_xattr_inline_size);
+
         osb->local_alloc_state = OCFS2_LA_UNUSED;
         osb->local_alloc_bh = NULL;
+        INIT_DELAYED_WORK(&osb->la_enable_wq, ocfs2_la_enable_worker);
 
         init_waitqueue_head(&osb->osb_mount_event);
 
@@ -1568,6 +1611,7 @@ static int ocfs2_initialize_super(struct super_block *sb,
         osb->first_cluster_group_blkno =
                 le64_to_cpu(di->id2.i_super.s_first_cluster_group);
         osb->fs_generation = le32_to_cpu(di->i_fs_generation);
+        osb->uuid_hash = le32_to_cpu(di->id2.i_super.s_uuid_hash);
         mlog(0, "vol_label: %s\n", osb->vol_label);
         mlog(0, "uuid: %s\n", osb->uuid_str);
         mlog(0, "root_blkno=%llu, system_dir_blkno=%llu\n",
diff --git a/fs/ocfs2/symlink.c b/fs/ocfs2/symlink.c
index ba9dbb51d25b..cbd03dfdc7b9 100644
--- a/fs/ocfs2/symlink.c
+++ b/fs/ocfs2/symlink.c
@@ -50,6 +50,7 @@
 #include "inode.h"
 #include "journal.h"
 #include "symlink.h"
+#include "xattr.h"
 
 #include "buffer_head_io.h"
 
@@ -83,11 +84,7 @@ static char *ocfs2_fast_symlink_getlink(struct inode *inode,
 
         mlog_entry_void();
 
-        status = ocfs2_read_block(OCFS2_SB(inode->i_sb),
-                                  OCFS2_I(inode)->ip_blkno,
-                                  bh,
-                                  OCFS2_BH_CACHED,
-                                  inode);
+        status = ocfs2_read_block(inode, OCFS2_I(inode)->ip_blkno, bh);
         if (status < 0) {
                 mlog_errno(status);
                 link = ERR_PTR(status);
@@ -157,8 +154,7 @@ bail:
                 kunmap(page);
                 page_cache_release(page);
         }
-        if (bh)
-                brelse(bh);
+        brelse(bh);
 
         return ERR_PTR(status);
 }
@@ -168,10 +164,18 @@ const struct inode_operations ocfs2_symlink_inode_operations = {
         .follow_link    = ocfs2_follow_link,
         .getattr        = ocfs2_getattr,
         .setattr        = ocfs2_setattr,
+        .setxattr       = generic_setxattr,
+        .getxattr       = generic_getxattr,
+        .listxattr      = ocfs2_listxattr,
+        .removexattr    = generic_removexattr,
 };
 const struct inode_operations ocfs2_fast_symlink_inode_operations = {
         .readlink       = ocfs2_readlink,
         .follow_link    = ocfs2_follow_link,
         .getattr        = ocfs2_getattr,
         .setattr        = ocfs2_setattr,
+        .setxattr       = generic_setxattr,
+        .getxattr       = generic_getxattr,
+        .listxattr      = ocfs2_listxattr,
+        .removexattr    = generic_removexattr,
 };
diff --git a/fs/ocfs2/uptodate.c b/fs/ocfs2/uptodate.c
index 4da8851f2b23..187b99ff0368 100644
--- a/fs/ocfs2/uptodate.c
+++ b/fs/ocfs2/uptodate.c
@@ -53,7 +53,11 @@
 #include <linux/highmem.h>
 #include <linux/buffer_head.h>
 #include <linux/rbtree.h>
-#include <linux/jbd.h>
+#ifndef CONFIG_OCFS2_COMPAT_JBD
+# include <linux/jbd2.h>
+#else
+# include <linux/jbd.h>
+#endif
 
 #define MLOG_MASK_PREFIX ML_UPTODATE
 
@@ -511,14 +515,10 @@ static void ocfs2_remove_metadata_tree(struct ocfs2_caching_info *ci,
         ci->ci_num_cached--;
 }
 
-/* Called when we remove a chunk of metadata from an inode. We don't
- * bother reverting things to an inlined array in the case of a remove
- * which moves us back under the limit. */
-void ocfs2_remove_from_cache(struct inode *inode,
-                             struct buffer_head *bh)
+static void ocfs2_remove_block_from_cache(struct inode *inode,
+                                          sector_t block)
 {
         int index;
-        sector_t block = bh->b_blocknr;
         struct ocfs2_meta_cache_item *item = NULL;
         struct ocfs2_inode_info *oi = OCFS2_I(inode);
         struct ocfs2_caching_info *ci = &oi->ip_metadata_cache;
@@ -544,6 +544,30 @@ void ocfs2_remove_from_cache(struct inode *inode,
                 kmem_cache_free(ocfs2_uptodate_cachep, item);
 }
 
+/*
+ * Called when we remove a chunk of metadata from an inode. We don't
+ * bother reverting things to an inlined array in the case of a remove
+ * which moves us back under the limit.
+ */
+void ocfs2_remove_from_cache(struct inode *inode,
+                             struct buffer_head *bh)
+{
+        sector_t block = bh->b_blocknr;
+
+        ocfs2_remove_block_from_cache(inode, block);
+}
+
+/* Called when we remove xattr clusters from an inode. */
+void ocfs2_remove_xattr_clusters_from_cache(struct inode *inode,
+                                            sector_t block,
+                                            u32 c_len)
+{
+        unsigned int i, b_len = ocfs2_clusters_to_blocks(inode->i_sb, 1) * c_len;
+
+        for (i = 0; i < b_len; i++, block++)
+                ocfs2_remove_block_from_cache(inode, block);
+}
+
 int __init init_ocfs2_uptodate_cache(void)
 {
         ocfs2_uptodate_cachep = kmem_cache_create("ocfs2_uptodate",
diff --git a/fs/ocfs2/uptodate.h b/fs/ocfs2/uptodate.h
index 2e73206059a8..531b4b3a0c47 100644
--- a/fs/ocfs2/uptodate.h
+++ b/fs/ocfs2/uptodate.h
@@ -40,6 +40,9 @@ void ocfs2_set_new_buffer_uptodate(struct inode *inode,
                                    struct buffer_head *bh);
 void ocfs2_remove_from_cache(struct inode *inode,
                              struct buffer_head *bh);
+void ocfs2_remove_xattr_clusters_from_cache(struct inode *inode,
+                                            sector_t block,
+                                            u32 c_len);
 int ocfs2_buffer_read_ahead(struct inode *inode,
                             struct buffer_head *bh);
 
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
new file mode 100644
index 000000000000..802c41492214
--- /dev/null
+++ b/fs/ocfs2/xattr.c
@@ -0,0 +1,4832 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * xattr.c
+ *
+ * Copyright (C) 2008 Oracle.  All rights reserved.
+ *
+ * CREDITS:
+ * Lots of code in this file is taken from ext3.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#include <linux/capability.h>
+#include <linux/fs.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/uio.h>
+#include <linux/sched.h>
+#include <linux/splice.h>
+#include <linux/mount.h>
+#include <linux/writeback.h>
+#include <linux/falloc.h>
+#include <linux/sort.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/string.h>
+
+#define MLOG_MASK_PREFIX ML_XATTR
+#include <cluster/masklog.h>
+
+#include "ocfs2.h"
+#include "alloc.h"
+#include "dlmglue.h"
+#include "file.h"
+#include "symlink.h"
+#include "sysfile.h"
+#include "inode.h"
+#include "journal.h"
+#include "ocfs2_fs.h"
+#include "suballoc.h"
+#include "uptodate.h"
+#include "buffer_head_io.h"
+#include "super.h"
+#include "xattr.h"
+
+
+struct ocfs2_xattr_def_value_root {
+        struct ocfs2_xattr_value_root   xv;
+        struct ocfs2_extent_rec         er;
+};
+
+struct ocfs2_xattr_bucket {
+        struct buffer_head *bhs[OCFS2_XATTR_MAX_BLOCKS_PER_BUCKET];
+        struct ocfs2_xattr_header *xh;
+};
+
+#define OCFS2_XATTR_ROOT_SIZE   (sizeof(struct ocfs2_xattr_def_value_root))
+#define OCFS2_XATTR_INLINE_SIZE 80
+
+static struct ocfs2_xattr_def_value_root def_xv = {
+        .xv.xr_list.l_count = cpu_to_le16(1),
+};
+
+struct xattr_handler *ocfs2_xattr_handlers[] = {
+        &ocfs2_xattr_user_handler,
+        &ocfs2_xattr_trusted_handler,
+        NULL
+};
+
+static struct xattr_handler *ocfs2_xattr_handler_map[] = {
+        [OCFS2_XATTR_INDEX_USER]        = &ocfs2_xattr_user_handler,
+        [OCFS2_XATTR_INDEX_TRUSTED]     = &ocfs2_xattr_trusted_handler,
+};
+
+struct ocfs2_xattr_info {
+        int name_index;
+        const char *name;
+        const void *value;
+        size_t value_len;
+};
+
+struct ocfs2_xattr_search {
+        struct buffer_head *inode_bh;
+        /*
+         * xattr_bh point to the block buffer head which has extended attribute
+         * when extended attribute in inode, xattr_bh is equal to inode_bh.
+         */
+        struct buffer_head *xattr_bh;
+        struct ocfs2_xattr_header *header;
+        struct ocfs2_xattr_bucket bucket;
+        void *base;
+        void *end;
+        struct ocfs2_xattr_entry *here;
+        int not_found;
+};
+
+static int ocfs2_xattr_bucket_get_name_value(struct inode *inode,
+                                             struct ocfs2_xattr_header *xh,
+                                             int index,
+                                             int *block_off,
+                                             int *new_offset);
+
+static int ocfs2_xattr_index_block_find(struct inode *inode,
+                                        struct buffer_head *root_bh,
+                                        int name_index,
+                                        const char *name,
+                                        struct ocfs2_xattr_search *xs);
+
+static int ocfs2_xattr_tree_list_index_block(struct inode *inode,
+                                        struct ocfs2_xattr_tree_root *xt,
+                                        char *buffer,
+                                        size_t buffer_size);
+
+static int ocfs2_xattr_create_index_block(struct inode *inode,
+                                          struct ocfs2_xattr_search *xs);
+
+static int ocfs2_xattr_set_entry_index_block(struct inode *inode,
+                                             struct ocfs2_xattr_info *xi,
+                                             struct ocfs2_xattr_search *xs);
+
+static int ocfs2_delete_xattr_index_block(struct inode *inode,
+                                          struct buffer_head *xb_bh);
+
+static inline const char *ocfs2_xattr_prefix(int name_index)
+{
+        struct xattr_handler *handler = NULL;
+
+        if (name_index > 0 && name_index < OCFS2_XATTR_MAX)
+                handler = ocfs2_xattr_handler_map[name_index];
+
+        return handler ? handler->prefix : NULL;
+}
+
+static u32 ocfs2_xattr_name_hash(struct inode *inode,
+                                 const char *name,
+                                 int name_len)
+{
+        /* Get hash value of uuid from super block */
+        u32 hash = OCFS2_SB(inode->i_sb)->uuid_hash;
+        int i;
+
+        /* hash extended attribute name */
+        for (i = 0; i < name_len; i++) {
+                hash = (hash << OCFS2_HASH_SHIFT) ^
+                       (hash >> (8*sizeof(hash) - OCFS2_HASH_SHIFT)) ^
+                       *name++;
+        }
+
+        return hash;
+}
+
+/*
+ * ocfs2_xattr_hash_entry()
+ *
+ * Compute the hash of an extended attribute.
+ */
+static void ocfs2_xattr_hash_entry(struct inode *inode,
+                                   struct ocfs2_xattr_header *header,
+                                   struct ocfs2_xattr_entry *entry)
+{
+        u32 hash = 0;
+        char *name = (char *)header + le16_to_cpu(entry->xe_name_offset);
+
+        hash = ocfs2_xattr_name_hash(inode, name, entry->xe_name_len);
+        entry->xe_name_hash = cpu_to_le32(hash);
+
+        return;
+}
+
+static int ocfs2_xattr_extend_allocation(struct inode *inode,
+                                         u32 clusters_to_add,
+                                         struct buffer_head *xattr_bh,
+                                         struct ocfs2_xattr_value_root *xv)
+{
+        int status = 0;
+        int restart_func = 0;
+        int credits = 0;
+        handle_t *handle = NULL;
+        struct ocfs2_alloc_context *data_ac = NULL;
+        struct ocfs2_alloc_context *meta_ac = NULL;
+        enum ocfs2_alloc_restarted why;
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+        u32 prev_clusters, logical_start = le32_to_cpu(xv->xr_clusters);
+        struct ocfs2_extent_tree et;
+
+        mlog(0, "(clusters_to_add for xattr= %u)\n", clusters_to_add);
+
+        ocfs2_init_xattr_value_extent_tree(&et, inode, xattr_bh, xv);
+
+restart_all:
+
+        status = ocfs2_lock_allocators(inode, &et, clusters_to_add, 0,
+                                       &data_ac, &meta_ac);
+        if (status) {
+                mlog_errno(status);
+                goto leave;
+        }
+
+        credits = ocfs2_calc_extend_credits(osb->sb, et.et_root_el,
+                                            clusters_to_add);
+        handle = ocfs2_start_trans(osb, credits);
+        if (IS_ERR(handle)) {
+                status = PTR_ERR(handle);
+                handle = NULL;
+                mlog_errno(status);
+                goto leave;
+        }
+
+restarted_transaction:
+        status = ocfs2_journal_access(handle, inode, xattr_bh,
+                                      OCFS2_JOURNAL_ACCESS_WRITE);
+        if (status < 0) {
+                mlog_errno(status);
+                goto leave;
+        }
+
+        prev_clusters = le32_to_cpu(xv->xr_clusters);
+        status = ocfs2_add_clusters_in_btree(osb,
+                                             inode,
+                                             &logical_start,
+                                             clusters_to_add,
+                                             0,
+                                             &et,
+                                             handle,
+                                             data_ac,
+                                             meta_ac,
+                                             &why);
+        if ((status < 0) && (status != -EAGAIN)) {
+                if (status != -ENOSPC)
+                        mlog_errno(status);
+                goto leave;
+        }
+
+        status = ocfs2_journal_dirty(handle, xattr_bh);
+        if (status < 0) {
+                mlog_errno(status);
+                goto leave;
+        }
+
+        clusters_to_add -= le32_to_cpu(xv->xr_clusters) - prev_clusters;
+
+        if (why != RESTART_NONE && clusters_to_add) {
+                if (why == RESTART_META) {
+                        mlog(0, "restarting function.\n");
+                        restart_func = 1;
+                } else {
+                        BUG_ON(why != RESTART_TRANS);
+
+                        mlog(0, "restarting transaction.\n");
+                        /* TODO: This can be more intelligent. */
+                        credits = ocfs2_calc_extend_credits(osb->sb,
+                                                            et.et_root_el,
+                                                            clusters_to_add);
+                        status = ocfs2_extend_trans(handle, credits);
+                        if (status < 0) {
+                                /* handle still has to be committed at
+                                 * this point. */
+                                status = -ENOMEM;
+                                mlog_errno(status);
+                                goto leave;
+                        }
+                        goto restarted_transaction;
+                }
+        }
+
+leave:
+        if (handle) {
+                ocfs2_commit_trans(osb, handle);
+                handle = NULL;
+        }
+        if (data_ac) {
+                ocfs2_free_alloc_context(data_ac);
+                data_ac = NULL;
+        }
+        if (meta_ac) {
+                ocfs2_free_alloc_context(meta_ac);
+                meta_ac = NULL;
+        }
+        if ((!status) && restart_func) {
+                restart_func = 0;
+                goto restart_all;
+        }
+
+        return status;
+}
+
+static int __ocfs2_remove_xattr_range(struct inode *inode,
+                                      struct buffer_head *root_bh,
+                                      struct ocfs2_xattr_value_root *xv,
+                                      u32 cpos, u32 phys_cpos, u32 len,
+                                      struct ocfs2_cached_dealloc_ctxt *dealloc)
+{
+        int ret;
+        u64 phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos);
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+        struct inode *tl_inode = osb->osb_tl_inode;
+        handle_t *handle;
+        struct ocfs2_alloc_context *meta_ac = NULL;
+        struct ocfs2_extent_tree et;
+
+        ocfs2_init_xattr_value_extent_tree(&et, inode, root_bh, xv);
+
+        ret = ocfs2_lock_allocators(inode, &et, 0, 1, NULL, &meta_ac);
+        if (ret) {
+                mlog_errno(ret);
+                return ret;
+        }
+
+        mutex_lock(&tl_inode->i_mutex);
+
+        if (ocfs2_truncate_log_needs_flush(osb)) {
+                ret = __ocfs2_flush_truncate_log(osb);
+                if (ret < 0) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+        }
+
+        handle = ocfs2_start_trans(osb, OCFS2_REMOVE_EXTENT_CREDITS);
+        if (IS_ERR(handle)) {
+                ret = PTR_ERR(handle);
+                mlog_errno(ret);
+                goto out;
+        }
+
+        ret = ocfs2_journal_access(handle, inode, root_bh,
+                                   OCFS2_JOURNAL_ACCESS_WRITE);
+        if (ret) {
+                mlog_errno(ret);
+                goto out_commit;
+        }
+
+        ret = ocfs2_remove_extent(inode, &et, cpos, len, handle, meta_ac,
+                                  dealloc);
+        if (ret) {
+                mlog_errno(ret);
+                goto out_commit;
+        }
+
+        le32_add_cpu(&xv->xr_clusters, -len);
+
+        ret = ocfs2_journal_dirty(handle, root_bh);
+        if (ret) {
+                mlog_errno(ret);
+                goto out_commit;
+        }
+
+        ret = ocfs2_truncate_log_append(osb, handle, phys_blkno, len);
+        if (ret)
+                mlog_errno(ret);
+
+out_commit:
+        ocfs2_commit_trans(osb, handle);
+out:
+        mutex_unlock(&tl_inode->i_mutex);
+
+        if (meta_ac)
+                ocfs2_free_alloc_context(meta_ac);
+
+        return ret;
+}
+
+static int ocfs2_xattr_shrink_size(struct inode *inode,
+                                   u32 old_clusters,
+                                   u32 new_clusters,
+                                   struct buffer_head *root_bh,
+                                   struct ocfs2_xattr_value_root *xv)
+{
+        int ret = 0;
+        u32 trunc_len, cpos, phys_cpos, alloc_size;
+        u64 block;
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+        struct ocfs2_cached_dealloc_ctxt dealloc;
+
+        ocfs2_init_dealloc_ctxt(&dealloc);
+
+        if (old_clusters <= new_clusters)
+                return 0;
+
+        cpos = new_clusters;
+        trunc_len = old_clusters - new_clusters;
+        while (trunc_len) {
+                ret = ocfs2_xattr_get_clusters(inode, cpos, &phys_cpos,
+                                               &alloc_size, &xv->xr_list);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+
+                if (alloc_size > trunc_len)
+                        alloc_size = trunc_len;
+
+                ret = __ocfs2_remove_xattr_range(inode, root_bh, xv, cpos,
+                                                 phys_cpos, alloc_size,
+                                                 &dealloc);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+
+                block = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos);
+                ocfs2_remove_xattr_clusters_from_cache(inode, block,
+                                                       alloc_size);
+                cpos += alloc_size;
+                trunc_len -= alloc_size;
+        }
+
+out:
+        ocfs2_schedule_truncate_log_flush(osb, 1);
+        ocfs2_run_deallocs(osb, &dealloc);
+
+        return ret;
+}
+
+static int ocfs2_xattr_value_truncate(struct inode *inode,
+                                      struct buffer_head *root_bh,
+                                      struct ocfs2_xattr_value_root *xv,
+                                      int len)
+{
+        int ret;
+        u32 new_clusters = ocfs2_clusters_for_bytes(inode->i_sb, len);
+        u32 old_clusters = le32_to_cpu(xv->xr_clusters);
+
+        if (new_clusters == old_clusters)
+                return 0;
+
+        if (new_clusters > old_clusters)
+                ret = ocfs2_xattr_extend_allocation(inode,
+                                                    new_clusters - old_clusters,
+                                                    root_bh, xv);
+        else
+                ret = ocfs2_xattr_shrink_size(inode,
+                                              old_clusters, new_clusters,
+                                              root_bh, xv);
+
+        return ret;
+}
+
+static int ocfs2_xattr_list_entry(char *buffer, size_t size,
+                                  size_t *result, const char *prefix,
+                                  const char *name, int name_len)
+{
+        char *p = buffer + *result;
+        int prefix_len = strlen(prefix);
+        int total_len = prefix_len + name_len + 1;
+
+        *result += total_len;
+
+        /* we are just looking for how big our buffer needs to be */
+        if (!size)
+                return 0;
+
+        if (*result > size)
+                return -ERANGE;
+
+        memcpy(p, prefix, prefix_len);
+        memcpy(p + prefix_len, name, name_len);
+        p[prefix_len + name_len] = '\0';
+
+        return 0;
+}
+
+static int ocfs2_xattr_list_entries(struct inode *inode,
+                                    struct ocfs2_xattr_header *header,
+                                    char *buffer, size_t buffer_size)
+{
+        size_t result = 0;
+        int i, type, ret;
+        const char *prefix, *name;
+
+        for (i = 0 ; i < le16_to_cpu(header->xh_count); i++) {
+                struct ocfs2_xattr_entry *entry = &header->xh_entries[i];
+                type = ocfs2_xattr_get_type(entry);
+                prefix = ocfs2_xattr_prefix(type);
+
+                if (prefix) {
+                        name = (const char *)header +
+                                le16_to_cpu(entry->xe_name_offset);
+
+                        ret = ocfs2_xattr_list_entry(buffer, buffer_size,
+                                                     &result, prefix, name,
+                                                     entry->xe_name_len);
+                        if (ret)
+                                return ret;
+                }
+        }
+
+        return result;
+}
+
+static int ocfs2_xattr_ibody_list(struct inode *inode,
+                                  struct ocfs2_dinode *di,
+                                  char *buffer,
+                                  size_t buffer_size)
+{
+        struct ocfs2_xattr_header *header = NULL;
+        struct ocfs2_inode_info *oi = OCFS2_I(inode);
+        int ret = 0;
+
+        if (!(oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL))
+                return ret;
+
+        header = (struct ocfs2_xattr_header *)
+                 ((void *)di + inode->i_sb->s_blocksize -
+                 le16_to_cpu(di->i_xattr_inline_size));
+
+        ret = ocfs2_xattr_list_entries(inode, header, buffer, buffer_size);
+
+        return ret;
+}
+
+static int ocfs2_xattr_block_list(struct inode *inode,
+                                  struct ocfs2_dinode *di,
+                                  char *buffer,
+                                  size_t buffer_size)
+{
+        struct buffer_head *blk_bh = NULL;
+        struct ocfs2_xattr_block *xb;
+        int ret = 0;
+
+        if (!di->i_xattr_loc)
+                return ret;
+
+        ret = ocfs2_read_block(inode, le64_to_cpu(di->i_xattr_loc), &blk_bh);
+        if (ret < 0) {
+                mlog_errno(ret);
+                return ret;
+        }
+        /*Verify the signature of xattr block*/
+        if (memcmp((void *)blk_bh->b_data, OCFS2_XATTR_BLOCK_SIGNATURE,
+                   strlen(OCFS2_XATTR_BLOCK_SIGNATURE))) {
+                ret = -EFAULT;
+                goto cleanup;
+        }
+
+        xb = (struct ocfs2_xattr_block *)blk_bh->b_data;
+
+        if (!(le16_to_cpu(xb->xb_flags) & OCFS2_XATTR_INDEXED)) {
+                struct ocfs2_xattr_header *header = &xb->xb_attrs.xb_header;
+                ret = ocfs2_xattr_list_entries(inode, header,
+                                               buffer, buffer_size);
+        } else {
+                struct ocfs2_xattr_tree_root *xt = &xb->xb_attrs.xb_root;
+                ret = ocfs2_xattr_tree_list_index_block(inode, xt,
+                                                   buffer, buffer_size);
+        }
+cleanup:
+        brelse(blk_bh);
+
+        return ret;
+}
+
+ssize_t ocfs2_listxattr(struct dentry *dentry,
+                        char *buffer,
+                        size_t size)
+{
+        int ret = 0, i_ret = 0, b_ret = 0;
+        struct buffer_head *di_bh = NULL;
+        struct ocfs2_dinode *di = NULL;
+        struct ocfs2_inode_info *oi = OCFS2_I(dentry->d_inode);
+
+        if (!ocfs2_supports_xattr(OCFS2_SB(dentry->d_sb)))
+                return -EOPNOTSUPP;
+
+        if (!(oi->ip_dyn_features & OCFS2_HAS_XATTR_FL))
+                return ret;
+
+        ret = ocfs2_inode_lock(dentry->d_inode, &di_bh, 0);
+        if (ret < 0) {
+                mlog_errno(ret);
+                return ret;
+        }
+
+        di = (struct ocfs2_dinode *)di_bh->b_data;
+
+        down_read(&oi->ip_xattr_sem);
+        i_ret = ocfs2_xattr_ibody_list(dentry->d_inode, di, buffer, size);
+        if (i_ret < 0)
+                b_ret = 0;
+        else {
+                if (buffer) {
+                        buffer += i_ret;
+                        size -= i_ret;
+                }
+                b_ret = ocfs2_xattr_block_list(dentry->d_inode, di,
+                                               buffer, size);
+                if (b_ret < 0)
+                        i_ret = 0;
+        }
+        up_read(&oi->ip_xattr_sem);
+        ocfs2_inode_unlock(dentry->d_inode, 0);
+
+        brelse(di_bh);
+
+        return i_ret + b_ret;
+}
+
+static int ocfs2_xattr_find_entry(int name_index,
+                                  const char *name,
+                                  struct ocfs2_xattr_search *xs)
+{
+        struct ocfs2_xattr_entry *entry;
+        size_t name_len;
+        int i, cmp = 1;
+
+        if (name == NULL)
+                return -EINVAL;
+
+        name_len = strlen(name);
+        entry = xs->here;
+        for (i = 0; i < le16_to_cpu(xs->header->xh_count); i++) {
+                cmp = name_index - ocfs2_xattr_get_type(entry);
+                if (!cmp)
+                        cmp = name_len - entry->xe_name_len;
+                if (!cmp)
+                        cmp = memcmp(name, (xs->base +
+                                     le16_to_cpu(entry->xe_name_offset)),
+                                     name_len);
+                if (cmp == 0)
+                        break;
+                entry += 1;
+        }
+        xs->here = entry;
+
+        return cmp ? -ENODATA : 0;
+}
+
+static int ocfs2_xattr_get_value_outside(struct inode *inode,
+                                         struct ocfs2_xattr_value_root *xv,
+                                         void *buffer,
+                                         size_t len)
+{
+        u32 cpos, p_cluster, num_clusters, bpc, clusters;
+        u64 blkno;
+        int i, ret = 0;
+        size_t cplen, blocksize;
+        struct buffer_head *bh = NULL;
+        struct ocfs2_extent_list *el;
+
+        el = &xv->xr_list;
+        clusters = le32_to_cpu(xv->xr_clusters);
+        bpc = ocfs2_clusters_to_blocks(inode->i_sb, 1);
+        blocksize = inode->i_sb->s_blocksize;
+
+        cpos = 0;
+        while (cpos < clusters) {
+                ret = ocfs2_xattr_get_clusters(inode, cpos, &p_cluster,
+                                               &num_clusters, el);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+
+                blkno = ocfs2_clusters_to_blocks(inode->i_sb, p_cluster);
+                /* Copy ocfs2_xattr_value */
+                for (i = 0; i < num_clusters * bpc; i++, blkno++) {
+                        ret = ocfs2_read_block(inode, blkno, &bh);
+                        if (ret) {
+                                mlog_errno(ret);
+                                goto out;
+                        }
+
+                        cplen = len >= blocksize ? blocksize : len;
+                        memcpy(buffer, bh->b_data, cplen);
+                        len -= cplen;
+                        buffer += cplen;
+
+                        brelse(bh);
+                        bh = NULL;
+                        if (len == 0)
+                                break;
+                }
+                cpos += num_clusters;
+        }
+out:
+        return ret;
+}
+
+static int ocfs2_xattr_ibody_get(struct inode *inode,
+                                 int name_index,
+                                 const char *name,
+                                 void *buffer,
+                                 size_t buffer_size,
+                                 struct ocfs2_xattr_search *xs)
+{
+        struct ocfs2_inode_info *oi = OCFS2_I(inode);
+        struct ocfs2_dinode *di = (struct ocfs2_dinode *)xs->inode_bh->b_data;
+        struct ocfs2_xattr_value_root *xv;
+        size_t size;
+        int ret = 0;
+
+        if (!(oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL))
+                return -ENODATA;
+
+        xs->end = (void *)di + inode->i_sb->s_blocksize;
+        xs->header = (struct ocfs2_xattr_header *)
+                        (xs->end - le16_to_cpu(di->i_xattr_inline_size));
+        xs->base = (void *)xs->header;
+        xs->here = xs->header->xh_entries;
+
+        ret = ocfs2_xattr_find_entry(name_index, name, xs);
+        if (ret)
+                return ret;
+        size = le64_to_cpu(xs->here->xe_value_size);
+        if (buffer) {
+                if (size > buffer_size)
+                        return -ERANGE;
+                if (ocfs2_xattr_is_local(xs->here)) {
+                        memcpy(buffer, (void *)xs->base +
+                               le16_to_cpu(xs->here->xe_name_offset) +
+                               OCFS2_XATTR_SIZE(xs->here->xe_name_len), size);
+                } else {
+                        xv = (struct ocfs2_xattr_value_root *)
+                                (xs->base + le16_to_cpu(
+                                 xs->here->xe_name_offset) +
+                                OCFS2_XATTR_SIZE(xs->here->xe_name_len));
+                        ret = ocfs2_xattr_get_value_outside(inode, xv,
+                                                            buffer, size);
+                        if (ret < 0) {
+                                mlog_errno(ret);
+                                return ret;
+                        }
+                }
+        }
+
+        return size;
+}
+
+static int ocfs2_xattr_block_get(struct inode *inode,
+                                 int name_index,
+                                 const char *name,
+                                 void *buffer,
+                                 size_t buffer_size,
+                                 struct ocfs2_xattr_search *xs)
+{
+        struct ocfs2_dinode *di = (struct ocfs2_dinode *)xs->inode_bh->b_data;
+        struct buffer_head *blk_bh = NULL;
+        struct ocfs2_xattr_block *xb;
+        struct ocfs2_xattr_value_root *xv;
+        size_t size;
+        int ret = -ENODATA, name_offset, name_len, block_off, i;
+
+        if (!di->i_xattr_loc)
+                return ret;
+
+        memset(&xs->bucket, 0, sizeof(xs->bucket));
+
+        ret = ocfs2_read_block(inode, le64_to_cpu(di->i_xattr_loc), &blk_bh);
+        if (ret < 0) {
+                mlog_errno(ret);
+                return ret;
+        }
+        /*Verify the signature of xattr block*/
+        if (memcmp((void *)blk_bh->b_data, OCFS2_XATTR_BLOCK_SIGNATURE,
+                   strlen(OCFS2_XATTR_BLOCK_SIGNATURE))) {
+                ret = -EFAULT;
+                goto cleanup;
+        }
+
+        xs->xattr_bh = blk_bh;
+        xb = (struct ocfs2_xattr_block *)blk_bh->b_data;
+
+        if (!(le16_to_cpu(xb->xb_flags) & OCFS2_XATTR_INDEXED)) {
+                xs->header = &xb->xb_attrs.xb_header;
+                xs->base = (void *)xs->header;
+                xs->end = (void *)(blk_bh->b_data) + blk_bh->b_size;
+                xs->here = xs->header->xh_entries;
+
+                ret = ocfs2_xattr_find_entry(name_index, name, xs);
+        } else
+                ret = ocfs2_xattr_index_block_find(inode, blk_bh,
+                                                   name_index,
+                                                   name, xs);
+
+        if (ret)
+                goto cleanup;
+        size = le64_to_cpu(xs->here->xe_value_size);
+        if (buffer) {
+                ret = -ERANGE;
+                if (size > buffer_size)
+                        goto cleanup;
+
+                name_offset = le16_to_cpu(xs->here->xe_name_offset);
+                name_len = OCFS2_XATTR_SIZE(xs->here->xe_name_len);
+                i = xs->here - xs->header->xh_entries;
+
+                if (le16_to_cpu(xb->xb_flags) & OCFS2_XATTR_INDEXED) {
+                        ret = ocfs2_xattr_bucket_get_name_value(inode,
+                                                                xs->bucket.xh,
+                                                                i,
+                                                                &block_off,
+                                                                &name_offset);
+                        xs->base = xs->bucket.bhs[block_off]->b_data;
+                }
+                if (ocfs2_xattr_is_local(xs->here)) {
+                        memcpy(buffer, (void *)xs->base +
+                               name_offset + name_len, size);
+                } else {
+                        xv = (struct ocfs2_xattr_value_root *)
+                                (xs->base + name_offset + name_len);
+                        ret = ocfs2_xattr_get_value_outside(inode, xv,
+                                                            buffer, size);
+                        if (ret < 0) {
+                                mlog_errno(ret);
+                                goto cleanup;
+                        }
+                }
+        }
+        ret = size;
+cleanup:
+        for (i = 0; i < OCFS2_XATTR_MAX_BLOCKS_PER_BUCKET; i++)
+                brelse(xs->bucket.bhs[i]);
+        memset(&xs->bucket, 0, sizeof(xs->bucket));
+
+        brelse(blk_bh);
+        return ret;
+}
+
+/* ocfs2_xattr_get()
+ *
+ * Copy an extended attribute into the buffer provided.
+ * Buffer is NULL to compute the size of buffer required.
+ */
+int ocfs2_xattr_get(struct inode *inode,
+                    int name_index,
+                    const char *name,
+                    void *buffer,
+                    size_t buffer_size)
+{
+        int ret;
+        struct ocfs2_dinode *di = NULL;
+        struct buffer_head *di_bh = NULL;
+        struct ocfs2_inode_info *oi = OCFS2_I(inode);
+        struct ocfs2_xattr_search xis = {
+                .not_found = -ENODATA,
+        };
+        struct ocfs2_xattr_search xbs = {
+                .not_found = -ENODATA,
+        };
+
+        if (!ocfs2_supports_xattr(OCFS2_SB(inode->i_sb)))
+                return -EOPNOTSUPP;
+
+        if (!(oi->ip_dyn_features & OCFS2_HAS_XATTR_FL))
+                ret = -ENODATA;
+
+        ret = ocfs2_inode_lock(inode, &di_bh, 0);
+        if (ret < 0) {
+                mlog_errno(ret);
+                return ret;
+        }
+        xis.inode_bh = xbs.inode_bh = di_bh;
+        di = (struct ocfs2_dinode *)di_bh->b_data;
+
+        down_read(&oi->ip_xattr_sem);
+        ret = ocfs2_xattr_ibody_get(inode, name_index, name, buffer,
+                                    buffer_size, &xis);
+        if (ret == -ENODATA)
+                ret = ocfs2_xattr_block_get(inode, name_index, name, buffer,
+                                            buffer_size, &xbs);
+        up_read(&oi->ip_xattr_sem);
+        ocfs2_inode_unlock(inode, 0);
+
+        brelse(di_bh);
+
+        return ret;
+}
+
+static int __ocfs2_xattr_set_value_outside(struct inode *inode,
+                                           struct ocfs2_xattr_value_root *xv,
+                                           const void *value,
+                                           int value_len)
+{
+        int ret = 0, i, cp_len, credits;
+        u16 blocksize = inode->i_sb->s_blocksize;
+        u32 p_cluster, num_clusters;
+        u32 cpos = 0, bpc = ocfs2_clusters_to_blocks(inode->i_sb, 1);
+        u32 clusters = ocfs2_clusters_for_bytes(inode->i_sb, value_len);
+        u64 blkno;
+        struct buffer_head *bh = NULL;
+        handle_t *handle;
+
+        BUG_ON(clusters > le32_to_cpu(xv->xr_clusters));
+
+        credits = clusters * bpc;
+        handle = ocfs2_start_trans(OCFS2_SB(inode->i_sb), credits);
+        if (IS_ERR(handle)) {
+                ret = PTR_ERR(handle);
+                mlog_errno(ret);
+                goto out;
+        }
+
+        while (cpos < clusters) {
+                ret = ocfs2_xattr_get_clusters(inode, cpos, &p_cluster,
+                                               &num_clusters, &xv->xr_list);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out_commit;
+                }
+
+                blkno = ocfs2_clusters_to_blocks(inode->i_sb, p_cluster);
+
+                for (i = 0; i < num_clusters * bpc; i++, blkno++) {
+                        ret = ocfs2_read_block(inode, blkno, &bh);
+                        if (ret) {
+                                mlog_errno(ret);
+                                goto out_commit;
+                        }
+
+                        ret = ocfs2_journal_access(handle,
+                                                   inode,
+                                                   bh,
+                                                   OCFS2_JOURNAL_ACCESS_WRITE);
+                        if (ret < 0) {
+                                mlog_errno(ret);
+                                goto out_commit;
+                        }
+
+                        cp_len = value_len > blocksize ? blocksize : value_len;
+                        memcpy(bh->b_data, value, cp_len);
+                        value_len -= cp_len;
+                        value += cp_len;
+                        if (cp_len < blocksize)
+                                memset(bh->b_data + cp_len, 0,
+                                       blocksize - cp_len);
+
+                        ret = ocfs2_journal_dirty(handle, bh);
+                        if (ret < 0) {
+                                mlog_errno(ret);
+                                goto out_commit;
+                        }
+                        brelse(bh);
+                        bh = NULL;
+
+                        /*
+                         * XXX: do we need to empty all the following
+                         * blocks in this cluster?
+                         */
+                        if (!value_len)
+                                break;
+                }
+                cpos += num_clusters;
+        }
+out_commit:
+        ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
+out:
+        brelse(bh);
+
+        return ret;
+}
+
+static int ocfs2_xattr_cleanup(struct inode *inode,
+                               struct ocfs2_xattr_info *xi,
+                               struct ocfs2_xattr_search *xs,
+                               size_t offs)
+{
+        handle_t *handle = NULL;
+        int ret = 0;
+        size_t name_len = strlen(xi->name);
+        void *val = xs->base + offs;
+        size_t size = OCFS2_XATTR_SIZE(name_len) + OCFS2_XATTR_ROOT_SIZE;
+
+        handle = ocfs2_start_trans((OCFS2_SB(inode->i_sb)),
+                                   OCFS2_XATTR_BLOCK_UPDATE_CREDITS);
+        if (IS_ERR(handle)) {
+                ret = PTR_ERR(handle);
+                mlog_errno(ret);
+                goto out;
+        }
+        ret = ocfs2_journal_access(handle, inode, xs->xattr_bh,
+                                   OCFS2_JOURNAL_ACCESS_WRITE);
+        if (ret) {
+                mlog_errno(ret);
+                goto out_commit;
+        }
+        /* Decrease xattr count */
+        le16_add_cpu(&xs->header->xh_count, -1);
+        /* Remove the xattr entry and tree root which has already be set*/
+        memset((void *)xs->here, 0, sizeof(struct ocfs2_xattr_entry));
+        memset(val, 0, size);
+
+        ret = ocfs2_journal_dirty(handle, xs->xattr_bh);
+        if (ret < 0)
+                mlog_errno(ret);
+out_commit:
+        ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
+out:
+        return ret;
+}
+
+static int ocfs2_xattr_update_entry(struct inode *inode,
+                                    struct ocfs2_xattr_info *xi,
+                                    struct ocfs2_xattr_search *xs,
+                                    size_t offs)
+{
+        handle_t *handle = NULL;
+        int ret = 0;
+
+        handle = ocfs2_start_trans((OCFS2_SB(inode->i_sb)),
+                                   OCFS2_XATTR_BLOCK_UPDATE_CREDITS);
+        if (IS_ERR(handle)) {
+                ret = PTR_ERR(handle);
+                mlog_errno(ret);
+                goto out;
+        }
+        ret = ocfs2_journal_access(handle, inode, xs->xattr_bh,
+                                   OCFS2_JOURNAL_ACCESS_WRITE);
+        if (ret) {
+                mlog_errno(ret);
+                goto out_commit;
+        }
+
+        xs->here->xe_name_offset = cpu_to_le16(offs);
+        xs->here->xe_value_size = cpu_to_le64(xi->value_len);
+        if (xi->value_len <= OCFS2_XATTR_INLINE_SIZE)
+                ocfs2_xattr_set_local(xs->here, 1);
+        else
+                ocfs2_xattr_set_local(xs->here, 0);
+        ocfs2_xattr_hash_entry(inode, xs->header, xs->here);
+
+        ret = ocfs2_journal_dirty(handle, xs->xattr_bh);
+        if (ret < 0)
+                mlog_errno(ret);
+out_commit:
+        ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
+out:
+        return ret;
+}
+
+/*
+ * ocfs2_xattr_set_value_outside()
+ *
+ * Set large size value in B tree.
+ */
+static int ocfs2_xattr_set_value_outside(struct inode *inode,
+                                         struct ocfs2_xattr_info *xi,
+                                         struct ocfs2_xattr_search *xs,
+                                         size_t offs)
+{
+        size_t name_len = strlen(xi->name);
+        void *val = xs->base + offs;
+        struct ocfs2_xattr_value_root *xv = NULL;
+        size_t size = OCFS2_XATTR_SIZE(name_len) + OCFS2_XATTR_ROOT_SIZE;
+        int ret = 0;
+
+        memset(val, 0, size);
+        memcpy(val, xi->name, name_len);
+        xv = (struct ocfs2_xattr_value_root *)
+                (val + OCFS2_XATTR_SIZE(name_len));
+        xv->xr_clusters = 0;
+        xv->xr_last_eb_blk = 0;
+        xv->xr_list.l_tree_depth = 0;
+        xv->xr_list.l_count = cpu_to_le16(1);
+        xv->xr_list.l_next_free_rec = 0;
+
+        ret = ocfs2_xattr_value_truncate(inode, xs->xattr_bh, xv,
+                                         xi->value_len);
+        if (ret < 0) {
+                mlog_errno(ret);
+                return ret;
+        }
+        ret = __ocfs2_xattr_set_value_outside(inode, xv, xi->value,
+                                              xi->value_len);
+        if (ret < 0) {
+                mlog_errno(ret);
+                return ret;
+        }
+        ret = ocfs2_xattr_update_entry(inode, xi, xs, offs);
+        if (ret < 0)
+                mlog_errno(ret);
+
+        return ret;
+}
+
+/*
+ * ocfs2_xattr_set_entry_local()
+ *
+ * Set, replace or remove extended attribute in local.
+ */
+static void ocfs2_xattr_set_entry_local(struct inode *inode,
+                                        struct ocfs2_xattr_info *xi,
+                                        struct ocfs2_xattr_search *xs,
+                                        struct ocfs2_xattr_entry *last,
+                                        size_t min_offs)
+{
+        size_t name_len = strlen(xi->name);
+        int i;
+
+        if (xi->value && xs->not_found) {
+                /* Insert the new xattr entry. */
+                le16_add_cpu(&xs->header->xh_count, 1);
+                ocfs2_xattr_set_type(last, xi->name_index);
+                ocfs2_xattr_set_local(last, 1);
+                last->xe_name_len = name_len;
+        } else {
+                void *first_val;
+                void *val;
+                size_t offs, size;
+
+                first_val = xs->base + min_offs;
+                offs = le16_to_cpu(xs->here->xe_name_offset);
+                val = xs->base + offs;
+
+                if (le64_to_cpu(xs->here->xe_value_size) >
+                    OCFS2_XATTR_INLINE_SIZE)
+                        size = OCFS2_XATTR_SIZE(name_len) +
+                                OCFS2_XATTR_ROOT_SIZE;
+                else
+                        size = OCFS2_XATTR_SIZE(name_len) +
+                        OCFS2_XATTR_SIZE(le64_to_cpu(xs->here->xe_value_size));
+
+                if (xi->value && size == OCFS2_XATTR_SIZE(name_len) +
+                                OCFS2_XATTR_SIZE(xi->value_len)) {
+                        /* The old and the new value have the
+                           same size. Just replace the value. */
+                        ocfs2_xattr_set_local(xs->here, 1);
+                        xs->here->xe_value_size = cpu_to_le64(xi->value_len);
+                        /* Clear value bytes. */
+                        memset(val + OCFS2_XATTR_SIZE(name_len),
+                               0,
+                               OCFS2_XATTR_SIZE(xi->value_len));
+                        memcpy(val + OCFS2_XATTR_SIZE(name_len),
+                               xi->value,
+                               xi->value_len);
+                        return;
+                }
+                /* Remove the old name+value. */
+                memmove(first_val + size, first_val, val - first_val);
+                memset(first_val, 0, size);
+                xs->here->xe_name_hash = 0;
+                xs->here->xe_name_offset = 0;
+                ocfs2_xattr_set_local(xs->here, 1);
+                xs->here->xe_value_size = 0;
+
+                min_offs += size;
+
+                /* Adjust all value offsets. */
+                last = xs->header->xh_entries;
+                for (i = 0 ; i < le16_to_cpu(xs->header->xh_count); i++) {
+                        size_t o = le16_to_cpu(last->xe_name_offset);
+
+                        if (o < offs)
+                                last->xe_name_offset = cpu_to_le16(o + size);
+                        last += 1;
+                }
+
+                if (!xi->value) {
+                        /* Remove the old entry. */
+                        last -= 1;
+                        memmove(xs->here, xs->here + 1,
+                                (void *)last - (void *)xs->here);
+                        memset(last, 0, sizeof(struct ocfs2_xattr_entry));
+                        le16_add_cpu(&xs->header->xh_count, -1);
+                }
+        }
+        if (xi->value) {
+                /* Insert the new name+value. */
+                size_t size = OCFS2_XATTR_SIZE(name_len) +
+                                OCFS2_XATTR_SIZE(xi->value_len);
+                void *val = xs->base + min_offs - size;
+
+                xs->here->xe_name_offset = cpu_to_le16(min_offs - size);
+                memset(val, 0, size);
+                memcpy(val, xi->name, name_len);
+                memcpy(val + OCFS2_XATTR_SIZE(name_len),
+                       xi->value,
+                       xi->value_len);
+                xs->here->xe_value_size = cpu_to_le64(xi->value_len);
+                ocfs2_xattr_set_local(xs->here, 1);
+                ocfs2_xattr_hash_entry(inode, xs->header, xs->here);
+        }
+
+        return;
+}
+
+/*
+ * ocfs2_xattr_set_entry()
+ *
+ * Set extended attribute entry into inode or block.
+ *
+ * If extended attribute value size > OCFS2_XATTR_INLINE_SIZE,
+ * We first insert tree root(ocfs2_xattr_value_root) with set_entry_local(),
+ * then set value in B tree with set_value_outside().
+ */
+static int ocfs2_xattr_set_entry(struct inode *inode,
+                                 struct ocfs2_xattr_info *xi,
+                                 struct ocfs2_xattr_search *xs,
+                                 int flag)
+{
+        struct ocfs2_xattr_entry *last;
+        struct ocfs2_inode_info *oi = OCFS2_I(inode);
+        struct ocfs2_dinode *di = (struct ocfs2_dinode *)xs->inode_bh->b_data;
+        size_t min_offs = xs->end - xs->base, name_len = strlen(xi->name);
+        size_t size_l = 0;
+        handle_t *handle = NULL;
+        int free, i, ret;
+        struct ocfs2_xattr_info xi_l = {
+                .name_index = xi->name_index,
+                .name = xi->name,
+                .value = xi->value,
+                .value_len = xi->value_len,
+        };
+
+        /* Compute min_offs, last and free space. */
+        last = xs->header->xh_entries;
+
+        for (i = 0 ; i < le16_to_cpu(xs->header->xh_count); i++) {
+                size_t offs = le16_to_cpu(last->xe_name_offset);
+                if (offs < min_offs)
+                        min_offs = offs;
+                last += 1;
+        }
+
+        free = min_offs - ((void *)last - xs->base) - sizeof(__u32);
+        if (free < 0)
+                return -EFAULT;
+
+        if (!xs->not_found) {
+                size_t size = 0;
+                if (ocfs2_xattr_is_local(xs->here))
+                        size = OCFS2_XATTR_SIZE(name_len) +
+                        OCFS2_XATTR_SIZE(le64_to_cpu(xs->here->xe_value_size));
+                else
+                        size = OCFS2_XATTR_SIZE(name_len) +
+                                OCFS2_XATTR_ROOT_SIZE;
+                free += (size + sizeof(struct ocfs2_xattr_entry));
+        }
+        /* Check free space in inode or block */
+        if (xi->value && xi->value_len > OCFS2_XATTR_INLINE_SIZE) {
+                if (free < sizeof(struct ocfs2_xattr_entry) +
+                           OCFS2_XATTR_SIZE(name_len) +
+                           OCFS2_XATTR_ROOT_SIZE) {
+                        ret = -ENOSPC;
+                        goto out;
+                }
+                size_l = OCFS2_XATTR_SIZE(name_len) + OCFS2_XATTR_ROOT_SIZE;
+                xi_l.value = (void *)&def_xv;
+                xi_l.value_len = OCFS2_XATTR_ROOT_SIZE;
+        } else if (xi->value) {
+                if (free < sizeof(struct ocfs2_xattr_entry) +
+                           OCFS2_XATTR_SIZE(name_len) +
+                           OCFS2_XATTR_SIZE(xi->value_len)) {
+                        ret = -ENOSPC;
+                        goto out;
+                }
+        }
+
+        if (!xs->not_found) {
+                /* For existing extended attribute */
+                size_t size = OCFS2_XATTR_SIZE(name_len) +
+                        OCFS2_XATTR_SIZE(le64_to_cpu(xs->here->xe_value_size));
+                size_t offs = le16_to_cpu(xs->here->xe_name_offset);
+                void *val = xs->base + offs;
+
+                if (ocfs2_xattr_is_local(xs->here) && size == size_l) {
+                        /* Replace existing local xattr with tree root */
+                        ret = ocfs2_xattr_set_value_outside(inode, xi, xs,
+                                                            offs);
+                        if (ret < 0)
+                                mlog_errno(ret);
+                        goto out;
+                } else if (!ocfs2_xattr_is_local(xs->here)) {
+                        /* For existing xattr which has value outside */
+                        struct ocfs2_xattr_value_root *xv = NULL;
+                        xv = (struct ocfs2_xattr_value_root *)(val +
+                                OCFS2_XATTR_SIZE(name_len));
+
+                        if (xi->value_len > OCFS2_XATTR_INLINE_SIZE) {
+                                /*
+                                 * If new value need set outside also,
+                                 * first truncate old value to new value,
+                                 * then set new value with set_value_outside().
+                                 */
+                                ret = ocfs2_xattr_value_truncate(inode,
+                                                                 xs->xattr_bh,
+                                                                 xv,
+                                                                 xi->value_len);
+                                if (ret < 0) {
+                                        mlog_errno(ret);
+                                        goto out;
+                                }
+
+                                ret = __ocfs2_xattr_set_value_outside(inode,
+                                                                xv,
+                                                                xi->value,
+                                                                xi->value_len);
+                                if (ret < 0) {
+                                        mlog_errno(ret);
+                                        goto out;
+                                }
+
+                                ret = ocfs2_xattr_update_entry(inode,
+                                                               xi,
+                                                               xs,
+                                                               offs);
+                                if (ret < 0)
+                                        mlog_errno(ret);
+                                goto out;
+                        } else {
+                                /*
+                                 * If new value need set in local,
+                                 * just trucate old value to zero.
+                                 */
+                                 ret = ocfs2_xattr_value_truncate(inode,
+                                                                 xs->xattr_bh,
+                                                                 xv,
+                                                                 0);
+                                if (ret < 0)
+                                        mlog_errno(ret);
+                        }
+                }
+        }
+
+        handle = ocfs2_start_trans((OCFS2_SB(inode->i_sb)),
+                                   OCFS2_INODE_UPDATE_CREDITS);
+        if (IS_ERR(handle)) {
+                ret = PTR_ERR(handle);
+                mlog_errno(ret);
+                goto out;
+        }
+
+        ret = ocfs2_journal_access(handle, inode, xs->inode_bh,
+                                   OCFS2_JOURNAL_ACCESS_WRITE);
+        if (ret) {
+                mlog_errno(ret);
+                goto out_commit;
+        }
+
+        if (!(flag & OCFS2_INLINE_XATTR_FL)) {
+                /* set extended attribute in external block. */
+                ret = ocfs2_extend_trans(handle,
+                                         OCFS2_INODE_UPDATE_CREDITS +
+                                         OCFS2_XATTR_BLOCK_UPDATE_CREDITS);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out_commit;
+                }
+                ret = ocfs2_journal_access(handle, inode, xs->xattr_bh,
+                                           OCFS2_JOURNAL_ACCESS_WRITE);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out_commit;
+                }
+        }
+
+        /*
+         * Set value in local, include set tree root in local.
+         * This is the first step for value size >INLINE_SIZE.
+         */
+        ocfs2_xattr_set_entry_local(inode, &xi_l, xs, last, min_offs);
+
+        if (!(flag & OCFS2_INLINE_XATTR_FL)) {
+                ret = ocfs2_journal_dirty(handle, xs->xattr_bh);
+                if (ret < 0) {
+                        mlog_errno(ret);
+                        goto out_commit;
+                }
+        }
+
+        if (!(oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL) &&
+            (flag & OCFS2_INLINE_XATTR_FL)) {
+                struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+                unsigned int xattrsize = osb->s_xattr_inline_size;
+
+                /*
+                 * Adjust extent record count or inline data size
+                 * to reserve space for extended attribute.
+                 */
+                if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+                        struct ocfs2_inline_data *idata = &di->id2.i_data;
+                        le16_add_cpu(&idata->id_count, -xattrsize);
+                } else if (!(ocfs2_inode_is_fast_symlink(inode))) {
+                        struct ocfs2_extent_list *el = &di->id2.i_list;
+                        le16_add_cpu(&el->l_count, -(xattrsize /
+                                        sizeof(struct ocfs2_extent_rec)));
+                }
+                di->i_xattr_inline_size = cpu_to_le16(xattrsize);
+        }
+        /* Update xattr flag */
+        spin_lock(&oi->ip_lock);
+        oi->ip_dyn_features |= flag;
+        di->i_dyn_features = cpu_to_le16(oi->ip_dyn_features);
+        spin_unlock(&oi->ip_lock);
+        /* Update inode ctime */
+        inode->i_ctime = CURRENT_TIME;
+        di->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
+        di->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
+
+        ret = ocfs2_journal_dirty(handle, xs->inode_bh);
+        if (ret < 0)
+                mlog_errno(ret);
+
+out_commit:
+        ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
+
+        if (!ret && xi->value_len > OCFS2_XATTR_INLINE_SIZE) {
+                /*
+                 * Set value outside in B tree.
+                 * This is the second step for value size > INLINE_SIZE.
+                 */
+                size_t offs = le16_to_cpu(xs->here->xe_name_offset);
+                ret = ocfs2_xattr_set_value_outside(inode, xi, xs, offs);
+                if (ret < 0) {
+                        int ret2;
+
+                        mlog_errno(ret);
+                        /*
+                         * If set value outside failed, we have to clean
+                         * the junk tree root we have already set in local.
+                         */
+                        ret2 = ocfs2_xattr_cleanup(inode, xi, xs, offs);
+                        if (ret2 < 0)
+                                mlog_errno(ret2);
+                }
+        }
+out:
+        return ret;
+
+}
+
+static int ocfs2_remove_value_outside(struct inode*inode,
+                                      struct buffer_head *bh,
+                                      struct ocfs2_xattr_header *header)
+{
+        int ret = 0, i;
+
+        for (i = 0; i < le16_to_cpu(header->xh_count); i++) {
+                struct ocfs2_xattr_entry *entry = &header->xh_entries[i];
+
+                if (!ocfs2_xattr_is_local(entry)) {
+                        struct ocfs2_xattr_value_root *xv;
+                        void *val;
+
+                        val = (void *)header +
+                                le16_to_cpu(entry->xe_name_offset);
+                        xv = (struct ocfs2_xattr_value_root *)
+                                (val + OCFS2_XATTR_SIZE(entry->xe_name_len));
+                        ret = ocfs2_xattr_value_truncate(inode, bh, xv, 0);
+                        if (ret < 0) {
+                                mlog_errno(ret);
+                                return ret;
+                        }
+                }
+        }
+
+        return ret;
+}
+
+static int ocfs2_xattr_ibody_remove(struct inode *inode,
+                                    struct buffer_head *di_bh)
+{
+
+        struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
+        struct ocfs2_xattr_header *header;
+        int ret;
+
+        header = (struct ocfs2_xattr_header *)
+                 ((void *)di + inode->i_sb->s_blocksize -
+                 le16_to_cpu(di->i_xattr_inline_size));
+
+        ret = ocfs2_remove_value_outside(inode, di_bh, header);
+
+        return ret;
+}
+
+static int ocfs2_xattr_block_remove(struct inode *inode,
+                                    struct buffer_head *blk_bh)
+{
+        struct ocfs2_xattr_block *xb;
+        int ret = 0;
+
+        xb = (struct ocfs2_xattr_block *)blk_bh->b_data;
+        if (!(le16_to_cpu(xb->xb_flags) & OCFS2_XATTR_INDEXED)) {
+                struct ocfs2_xattr_header *header = &(xb->xb_attrs.xb_header);
+                ret = ocfs2_remove_value_outside(inode, blk_bh, header);
+        } else
+                ret = ocfs2_delete_xattr_index_block(inode, blk_bh);
+
+        return ret;
+}
+
+static int ocfs2_xattr_free_block(struct inode *inode,
+                                  u64 block)
+{
+        struct inode *xb_alloc_inode;
+        struct buffer_head *xb_alloc_bh = NULL;
+        struct buffer_head *blk_bh = NULL;
+        struct ocfs2_xattr_block *xb;
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+        handle_t *handle;
+        int ret = 0;
+        u64 blk, bg_blkno;
+        u16 bit;
+
+        ret = ocfs2_read_block(inode, block, &blk_bh);
+        if (ret < 0) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        /*Verify the signature of xattr block*/
+        if (memcmp((void *)blk_bh->b_data, OCFS2_XATTR_BLOCK_SIGNATURE,
+                   strlen(OCFS2_XATTR_BLOCK_SIGNATURE))) {
+                ret = -EFAULT;
+                goto out;
+        }
+
+        ret = ocfs2_xattr_block_remove(inode, blk_bh);
+        if (ret < 0) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        xb = (struct ocfs2_xattr_block *)blk_bh->b_data;
+        blk = le64_to_cpu(xb->xb_blkno);
+        bit = le16_to_cpu(xb->xb_suballoc_bit);
+        bg_blkno = ocfs2_which_suballoc_group(blk, bit);
+
+        xb_alloc_inode = ocfs2_get_system_file_inode(osb,
+                                EXTENT_ALLOC_SYSTEM_INODE,
+                                le16_to_cpu(xb->xb_suballoc_slot));
+        if (!xb_alloc_inode) {
+                ret = -ENOMEM;
+                mlog_errno(ret);
+                goto out;
+        }
+        mutex_lock(&xb_alloc_inode->i_mutex);
+
+        ret = ocfs2_inode_lock(xb_alloc_inode, &xb_alloc_bh, 1);
+        if (ret < 0) {
+                mlog_errno(ret);
+                goto out_mutex;
+        }
+
+        handle = ocfs2_start_trans(osb, OCFS2_SUBALLOC_FREE);
+        if (IS_ERR(handle)) {
+                ret = PTR_ERR(handle);
+                mlog_errno(ret);
+                goto out_unlock;
+        }
+
+        ret = ocfs2_free_suballoc_bits(handle, xb_alloc_inode, xb_alloc_bh,
+                                       bit, bg_blkno, 1);
+        if (ret < 0)
+                mlog_errno(ret);
+
+        ocfs2_commit_trans(osb, handle);
+out_unlock:
+        ocfs2_inode_unlock(xb_alloc_inode, 1);
+        brelse(xb_alloc_bh);
+out_mutex:
+        mutex_unlock(&xb_alloc_inode->i_mutex);
+        iput(xb_alloc_inode);
+out:
+        brelse(blk_bh);
+        return ret;
+}
+
+/*
+ * ocfs2_xattr_remove()
+ *
+ * Free extended attribute resources associated with this inode.
+ */
+int ocfs2_xattr_remove(struct inode *inode, struct buffer_head *di_bh)
+{
+        struct ocfs2_inode_info *oi = OCFS2_I(inode);
+        struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
+        handle_t *handle;
+        int ret;
+
+        if (!ocfs2_supports_xattr(OCFS2_SB(inode->i_sb)))
+                return 0;
+
+        if (!(oi->ip_dyn_features & OCFS2_HAS_XATTR_FL))
+                return 0;
+
+        if (oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL) {
+                ret = ocfs2_xattr_ibody_remove(inode, di_bh);
+                if (ret < 0) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+        }
+
+        if (di->i_xattr_loc) {
+                ret = ocfs2_xattr_free_block(inode,
+                                             le64_to_cpu(di->i_xattr_loc));
+                if (ret < 0) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+        }
+
+        handle = ocfs2_start_trans((OCFS2_SB(inode->i_sb)),
+                                   OCFS2_INODE_UPDATE_CREDITS);
+        if (IS_ERR(handle)) {
+                ret = PTR_ERR(handle);
+                mlog_errno(ret);
+                goto out;
+        }
+        ret = ocfs2_journal_access(handle, inode, di_bh,
+                                   OCFS2_JOURNAL_ACCESS_WRITE);
+        if (ret) {
+                mlog_errno(ret);
+                goto out_commit;
+        }
+
+        di->i_xattr_loc = 0;
+
+        spin_lock(&oi->ip_lock);
+        oi->ip_dyn_features &= ~(OCFS2_INLINE_XATTR_FL | OCFS2_HAS_XATTR_FL);
+        di->i_dyn_features = cpu_to_le16(oi->ip_dyn_features);
+        spin_unlock(&oi->ip_lock);
+
+        ret = ocfs2_journal_dirty(handle, di_bh);
+        if (ret < 0)
+                mlog_errno(ret);
+out_commit:
+        ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
+out:
+        return ret;
+}
+
+static int ocfs2_xattr_has_space_inline(struct inode *inode,
+                                        struct ocfs2_dinode *di)
+{
+        struct ocfs2_inode_info *oi = OCFS2_I(inode);
+        unsigned int xattrsize = OCFS2_SB(inode->i_sb)->s_xattr_inline_size;
+        int free;
+
+        if (xattrsize < OCFS2_MIN_XATTR_INLINE_SIZE)
+                return 0;
+
+        if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+                struct ocfs2_inline_data *idata = &di->id2.i_data;
+                free = le16_to_cpu(idata->id_count) - le64_to_cpu(di->i_size);
+        } else if (ocfs2_inode_is_fast_symlink(inode)) {
+                free = ocfs2_fast_symlink_chars(inode->i_sb) -
+                        le64_to_cpu(di->i_size);
+        } else {
+                struct ocfs2_extent_list *el = &di->id2.i_list;
+                free = (le16_to_cpu(el->l_count) -
+                        le16_to_cpu(el->l_next_free_rec)) *
+                        sizeof(struct ocfs2_extent_rec);
+        }
+        if (free >= xattrsize)
+                return 1;
+
+        return 0;
+}
+
+/*
+ * ocfs2_xattr_ibody_find()
+ *
+ * Find extended attribute in inode block and
+ * fill search info into struct ocfs2_xattr_search.
+ */
+static int ocfs2_xattr_ibody_find(struct inode *inode,
+                                  int name_index,
+                                  const char *name,
+                                  struct ocfs2_xattr_search *xs)
+{
+        struct ocfs2_inode_info *oi = OCFS2_I(inode);
+        struct ocfs2_dinode *di = (struct ocfs2_dinode *)xs->inode_bh->b_data;
+        int ret;
+        int has_space = 0;
+
+        if (inode->i_sb->s_blocksize == OCFS2_MIN_BLOCKSIZE)
+                return 0;
+
+        if (!(oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL)) {
+                down_read(&oi->ip_alloc_sem);
+                has_space = ocfs2_xattr_has_space_inline(inode, di);
+                up_read(&oi->ip_alloc_sem);
+                if (!has_space)
+                        return 0;
+        }
+
+        xs->xattr_bh = xs->inode_bh;
+        xs->end = (void *)di + inode->i_sb->s_blocksize;
+        if (oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL)
+                xs->header = (struct ocfs2_xattr_header *)
+                        (xs->end - le16_to_cpu(di->i_xattr_inline_size));
+        else
+                xs->header = (struct ocfs2_xattr_header *)
+                        (xs->end - OCFS2_SB(inode->i_sb)->s_xattr_inline_size);
+        xs->base = (void *)xs->header;
+        xs->here = xs->header->xh_entries;
+
+        /* Find the named attribute. */
+        if (oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL) {
+                ret = ocfs2_xattr_find_entry(name_index, name, xs);
+                if (ret && ret != -ENODATA)
+                        return ret;
+                xs->not_found = ret;
+        }
+
+        return 0;
+}
+
+/*
+ * ocfs2_xattr_ibody_set()
+ *
+ * Set, replace or remove an extended attribute into inode block.
+ *
+ */
+static int ocfs2_xattr_ibody_set(struct inode *inode,
+                                 struct ocfs2_xattr_info *xi,
+                                 struct ocfs2_xattr_search *xs)
+{
+        struct ocfs2_inode_info *oi = OCFS2_I(inode);
+        struct ocfs2_dinode *di = (struct ocfs2_dinode *)xs->inode_bh->b_data;
+        int ret;
+
+        if (inode->i_sb->s_blocksize == OCFS2_MIN_BLOCKSIZE)
+                return -ENOSPC;
+
+        down_write(&oi->ip_alloc_sem);
+        if (!(oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL)) {
+                if (!ocfs2_xattr_has_space_inline(inode, di)) {
+                        ret = -ENOSPC;
+                        goto out;
+                }
+        }
+
+        ret = ocfs2_xattr_set_entry(inode, xi, xs,
+                                (OCFS2_INLINE_XATTR_FL | OCFS2_HAS_XATTR_FL));
+out:
+        up_write(&oi->ip_alloc_sem);
+
+        return ret;
+}
+
+/*
+ * ocfs2_xattr_block_find()
+ *
+ * Find extended attribute in external block and
+ * fill search info into struct ocfs2_xattr_search.
+ */
+static int ocfs2_xattr_block_find(struct inode *inode,
+                                  int name_index,
+                                  const char *name,
+                                  struct ocfs2_xattr_search *xs)
+{
+        struct ocfs2_dinode *di = (struct ocfs2_dinode *)xs->inode_bh->b_data;
+        struct buffer_head *blk_bh = NULL;
+        struct ocfs2_xattr_block *xb;
+        int ret = 0;
+
+        if (!di->i_xattr_loc)
+                return ret;
+
+        ret = ocfs2_read_block(inode, le64_to_cpu(di->i_xattr_loc), &blk_bh);
+        if (ret < 0) {
+                mlog_errno(ret);
+                return ret;
+        }
+        /*Verify the signature of xattr block*/
+        if (memcmp((void *)blk_bh->b_data, OCFS2_XATTR_BLOCK_SIGNATURE,
+                   strlen(OCFS2_XATTR_BLOCK_SIGNATURE))) {
+                        ret = -EFAULT;
+                        goto cleanup;
+        }
+
+        xs->xattr_bh = blk_bh;
+        xb = (struct ocfs2_xattr_block *)blk_bh->b_data;
+
+        if (!(le16_to_cpu(xb->xb_flags) & OCFS2_XATTR_INDEXED)) {
+                xs->header = &xb->xb_attrs.xb_header;
+                xs->base = (void *)xs->header;
+                xs->end = (void *)(blk_bh->b_data) + blk_bh->b_size;
+                xs->here = xs->header->xh_entries;
+
+                ret = ocfs2_xattr_find_entry(name_index, name, xs);
+        } else
+                ret = ocfs2_xattr_index_block_find(inode, blk_bh,
+                                                   name_index,
+                                                   name, xs);
+
+        if (ret && ret != -ENODATA) {
+                xs->xattr_bh = NULL;
+                goto cleanup;
+        }
+        xs->not_found = ret;
+        return 0;
+cleanup:
+        brelse(blk_bh);
+
+        return ret;
+}
+
+/*
+ * When all the xattrs are deleted from index btree, the ocfs2_xattr_tree
+ * will be erased and ocfs2_xattr_block will have its ocfs2_xattr_header
+ * re-initialized.
+ */
+static int ocfs2_restore_xattr_block(struct inode *inode,
+                                     struct ocfs2_xattr_search *xs)
+{
+        int ret;
+        handle_t *handle;
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+        struct ocfs2_xattr_block *xb =
+                (struct ocfs2_xattr_block *)xs->xattr_bh->b_data;
+        struct ocfs2_extent_list *el = &xb->xb_attrs.xb_root.xt_list;
+        u16 xb_flags = le16_to_cpu(xb->xb_flags);
+
+        BUG_ON(!(xb_flags & OCFS2_XATTR_INDEXED) ||
+                le16_to_cpu(el->l_next_free_rec) != 0);
+
+        handle = ocfs2_start_trans(osb, OCFS2_XATTR_BLOCK_UPDATE_CREDITS);
+        if (IS_ERR(handle)) {
+                ret = PTR_ERR(handle);
+                handle = NULL;
+                goto out;
+        }
+
+        ret = ocfs2_journal_access(handle, inode, xs->xattr_bh,
+                                   OCFS2_JOURNAL_ACCESS_WRITE);
+        if (ret < 0) {
+                mlog_errno(ret);
+                goto out_commit;
+        }
+
+        memset(&xb->xb_attrs, 0, inode->i_sb->s_blocksize -
+               offsetof(struct ocfs2_xattr_block, xb_attrs));
+
+        xb->xb_flags = cpu_to_le16(xb_flags & ~OCFS2_XATTR_INDEXED);
+
+        ocfs2_journal_dirty(handle, xs->xattr_bh);
+
+out_commit:
+        ocfs2_commit_trans(osb, handle);
+out:
+        return ret;
+}
+
+/*
+ * ocfs2_xattr_block_set()
+ *
+ * Set, replace or remove an extended attribute into external block.
+ *
+ */
+static int ocfs2_xattr_block_set(struct inode *inode,
+                                 struct ocfs2_xattr_info *xi,
+                                 struct ocfs2_xattr_search *xs)
+{
+        struct buffer_head *new_bh = NULL;
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+        struct ocfs2_dinode *di =  (struct ocfs2_dinode *)xs->inode_bh->b_data;
+        struct ocfs2_alloc_context *meta_ac = NULL;
+        handle_t *handle = NULL;
+        struct ocfs2_xattr_block *xblk = NULL;
+        u16 suballoc_bit_start;
+        u32 num_got;
+        u64 first_blkno;
+        int ret;
+
+        if (!xs->xattr_bh) {
+                /*
+                 * Alloc one external block for extended attribute
+                 * outside of inode.
+                 */
+                ret = ocfs2_reserve_new_metadata_blocks(osb, 1, &meta_ac);
+                if (ret < 0) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+                handle = ocfs2_start_trans(osb,
+                                           OCFS2_XATTR_BLOCK_CREATE_CREDITS);
+                if (IS_ERR(handle)) {
+                        ret = PTR_ERR(handle);
+                        mlog_errno(ret);
+                        goto out;
+                }
+                ret = ocfs2_journal_access(handle, inode, xs->inode_bh,
+                                           OCFS2_JOURNAL_ACCESS_CREATE);
+                if (ret < 0) {
+                        mlog_errno(ret);
+                        goto out_commit;
+                }
+
+                ret = ocfs2_claim_metadata(osb, handle, meta_ac, 1,
+                                           &suballoc_bit_start, &num_got,
+                                           &first_blkno);
+                if (ret < 0) {
+                        mlog_errno(ret);
+                        goto out_commit;
+                }
+
+                new_bh = sb_getblk(inode->i_sb, first_blkno);
+                ocfs2_set_new_buffer_uptodate(inode, new_bh);
+
+                ret = ocfs2_journal_access(handle, inode, new_bh,
+                                           OCFS2_JOURNAL_ACCESS_CREATE);
+                if (ret < 0) {
+                        mlog_errno(ret);
+                        goto out_commit;
+                }
+
+                /* Initialize ocfs2_xattr_block */
+                xs->xattr_bh = new_bh;
+                xblk = (struct ocfs2_xattr_block *)new_bh->b_data;
+                memset(xblk, 0, inode->i_sb->s_blocksize);
+                strcpy((void *)xblk, OCFS2_XATTR_BLOCK_SIGNATURE);
+                xblk->xb_suballoc_slot = cpu_to_le16(osb->slot_num);
+                xblk->xb_suballoc_bit = cpu_to_le16(suballoc_bit_start);
+                xblk->xb_fs_generation = cpu_to_le32(osb->fs_generation);
+                xblk->xb_blkno = cpu_to_le64(first_blkno);
+
+                xs->header = &xblk->xb_attrs.xb_header;
+                xs->base = (void *)xs->header;
+                xs->end = (void *)xblk + inode->i_sb->s_blocksize;
+                xs->here = xs->header->xh_entries;
+
+
+                ret = ocfs2_journal_dirty(handle, new_bh);
+                if (ret < 0) {
+                        mlog_errno(ret);
+                        goto out_commit;
+                }
+                di->i_xattr_loc = cpu_to_le64(first_blkno);
+                ret = ocfs2_journal_dirty(handle, xs->inode_bh);
+                if (ret < 0)
+                        mlog_errno(ret);
+out_commit:
+                ocfs2_commit_trans(osb, handle);
+out:
+                if (meta_ac)
+                        ocfs2_free_alloc_context(meta_ac);
+                if (ret < 0)
+                        return ret;
+        } else
+                xblk = (struct ocfs2_xattr_block *)xs->xattr_bh->b_data;
+
+        if (!(le16_to_cpu(xblk->xb_flags) & OCFS2_XATTR_INDEXED)) {
+                /* Set extended attribute into external block */
+                ret = ocfs2_xattr_set_entry(inode, xi, xs, OCFS2_HAS_XATTR_FL);
+                if (!ret || ret != -ENOSPC)
+                        goto end;
+
+                ret = ocfs2_xattr_create_index_block(inode, xs);
+                if (ret)
+                        goto end;
+        }
+
+        ret = ocfs2_xattr_set_entry_index_block(inode, xi, xs);
+        if (!ret && xblk->xb_attrs.xb_root.xt_list.l_next_free_rec == 0)
+                ret = ocfs2_restore_xattr_block(inode, xs);
+
+end:
+
+        return ret;
+}
+
+/*
+ * ocfs2_xattr_set()
+ *
+ * Set, replace or remove an extended attribute for this inode.
+ * value is NULL to remove an existing extended attribute, else either
+ * create or replace an extended attribute.
+ */
+int ocfs2_xattr_set(struct inode *inode,
+                    int name_index,
+                    const char *name,
+                    const void *value,
+                    size_t value_len,
+                    int flags)
+{
+        struct buffer_head *di_bh = NULL;
+        struct ocfs2_dinode *di;
+        int ret;
+        u16 i, blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
+
+        struct ocfs2_xattr_info xi = {
+                .name_index = name_index,
+                .name = name,
+                .value = value,
+                .value_len = value_len,
+        };
+
+        struct ocfs2_xattr_search xis = {
+                .not_found = -ENODATA,
+        };
+
+        struct ocfs2_xattr_search xbs = {
+                .not_found = -ENODATA,
+        };
+
+        if (!ocfs2_supports_xattr(OCFS2_SB(inode->i_sb)))
+                return -EOPNOTSUPP;
+
+        ret = ocfs2_inode_lock(inode, &di_bh, 1);
+        if (ret < 0) {
+                mlog_errno(ret);
+                return ret;
+        }
+        xis.inode_bh = xbs.inode_bh = di_bh;
+        di = (struct ocfs2_dinode *)di_bh->b_data;
+
+        down_write(&OCFS2_I(inode)->ip_xattr_sem);
+        /*
+         * Scan inode and external block to find the same name
+         * extended attribute and collect search infomation.
+         */
+        ret = ocfs2_xattr_ibody_find(inode, name_index, name, &xis);
+        if (ret)
+                goto cleanup;
+        if (xis.not_found) {
+                ret = ocfs2_xattr_block_find(inode, name_index, name, &xbs);
+                if (ret)
+                        goto cleanup;
+        }
+
+        if (xis.not_found && xbs.not_found) {
+                ret = -ENODATA;
+                if (flags & XATTR_REPLACE)
+                        goto cleanup;
+                ret = 0;
+                if (!value)
+                        goto cleanup;
+        } else {
+                ret = -EEXIST;
+                if (flags & XATTR_CREATE)
+                        goto cleanup;
+        }
+
+        if (!value) {
+                /* Remove existing extended attribute */
+                if (!xis.not_found)
+                        ret = ocfs2_xattr_ibody_set(inode, &xi, &xis);
+                else if (!xbs.not_found)
+                        ret = ocfs2_xattr_block_set(inode, &xi, &xbs);
+        } else {
+                /* We always try to set extended attribute into inode first*/
+                ret = ocfs2_xattr_ibody_set(inode, &xi, &xis);
+                if (!ret && !xbs.not_found) {
+                        /*
+                         * If succeed and that extended attribute existing in
+                         * external block, then we will remove it.
+                         */
+                        xi.value = NULL;
+                        xi.value_len = 0;
+                        ret = ocfs2_xattr_block_set(inode, &xi, &xbs);
+                } else if (ret == -ENOSPC) {
+                        if (di->i_xattr_loc && !xbs.xattr_bh) {
+                                ret = ocfs2_xattr_block_find(inode, name_index,
+                                                             name, &xbs);
+                                if (ret)
+                                        goto cleanup;
+                        }
+                        /*
+                         * If no space in inode, we will set extended attribute
+                         * into external block.
+                         */
+                        ret = ocfs2_xattr_block_set(inode, &xi, &xbs);
+                        if (ret)
+                                goto cleanup;
+                        if (!xis.not_found) {
+                                /*
+                                 * If succeed and that extended attribute
+                                 * existing in inode, we will remove it.
+                                 */
+                                xi.value = NULL;
+                                xi.value_len = 0;
+                                ret = ocfs2_xattr_ibody_set(inode, &xi, &xis);
+                        }
+                }
+        }
+cleanup:
+        up_write(&OCFS2_I(inode)->ip_xattr_sem);
+        ocfs2_inode_unlock(inode, 1);
+        brelse(di_bh);
+        brelse(xbs.xattr_bh);
+        for (i = 0; i < blk_per_bucket; i++)
+                brelse(xbs.bucket.bhs[i]);
+
+        return ret;
+}
+
+/*
+ * Find the xattr extent rec which may contains name_hash.
+ * e_cpos will be the first name hash of the xattr rec.
+ * el must be the ocfs2_xattr_header.xb_attrs.xb_root.xt_list.
+ */
+static int ocfs2_xattr_get_rec(struct inode *inode,
+                               u32 name_hash,
+                               u64 *p_blkno,
+                               u32 *e_cpos,
+                               u32 *num_clusters,
+                               struct ocfs2_extent_list *el)
+{
+        int ret = 0, i;
+        struct buffer_head *eb_bh = NULL;
+        struct ocfs2_extent_block *eb;
+        struct ocfs2_extent_rec *rec = NULL;
+        u64 e_blkno = 0;
+
+        if (el->l_tree_depth) {
+                ret = ocfs2_find_leaf(inode, el, name_hash, &eb_bh);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+
+                eb = (struct ocfs2_extent_block *) eb_bh->b_data;
+                el = &eb->h_list;
+
+                if (el->l_tree_depth) {
+                        ocfs2_error(inode->i_sb,
+                                    "Inode %lu has non zero tree depth in "
+                                    "xattr tree block %llu\n", inode->i_ino,
+                                    (unsigned long long)eb_bh->b_blocknr);
+                        ret = -EROFS;
+                        goto out;
+                }
+        }
+
+        for (i = le16_to_cpu(el->l_next_free_rec) - 1; i >= 0; i--) {
+                rec = &el->l_recs[i];
+
+                if (le32_to_cpu(rec->e_cpos) <= name_hash) {
+                        e_blkno = le64_to_cpu(rec->e_blkno);
+                        break;
+                }
+        }
+
+        if (!e_blkno) {
+                ocfs2_error(inode->i_sb, "Inode %lu has bad extent "
+                            "record (%u, %u, 0) in xattr", inode->i_ino,
+                            le32_to_cpu(rec->e_cpos),
+                            ocfs2_rec_clusters(el, rec));
+                ret = -EROFS;
+                goto out;
+        }
+
+        *p_blkno = le64_to_cpu(rec->e_blkno);
+        *num_clusters = le16_to_cpu(rec->e_leaf_clusters);
+        if (e_cpos)
+                *e_cpos = le32_to_cpu(rec->e_cpos);
+out:
+        brelse(eb_bh);
+        return ret;
+}
+
+typedef int (xattr_bucket_func)(struct inode *inode,
+                                struct ocfs2_xattr_bucket *bucket,
+                                void *para);
+
+static int ocfs2_find_xe_in_bucket(struct inode *inode,
+                                   struct buffer_head *header_bh,
+                                   int name_index,
+                                   const char *name,
+                                   u32 name_hash,
+                                   u16 *xe_index,
+                                   int *found)
+{
+        int i, ret = 0, cmp = 1, block_off, new_offset;
+        struct ocfs2_xattr_header *xh =
+                        (struct ocfs2_xattr_header *)header_bh->b_data;
+        size_t name_len = strlen(name);
+        struct ocfs2_xattr_entry *xe = NULL;
+        struct buffer_head *name_bh = NULL;
+        char *xe_name;
+
+        /*
+         * We don't use binary search in the bucket because there
+         * may be multiple entries with the same name hash.
+         */
+        for (i = 0; i < le16_to_cpu(xh->xh_count); i++) {
+                xe = &xh->xh_entries[i];
+
+                if (name_hash > le32_to_cpu(xe->xe_name_hash))
+                        continue;
+                else if (name_hash < le32_to_cpu(xe->xe_name_hash))
+                        break;
+
+                cmp = name_index - ocfs2_xattr_get_type(xe);
+                if (!cmp)
+                        cmp = name_len - xe->xe_name_len;
+                if (cmp)
+                        continue;
+
+                ret = ocfs2_xattr_bucket_get_name_value(inode,
+                                                        xh,
+                                                        i,
+                                                        &block_off,
+                                                        &new_offset);
+                if (ret) {
+                        mlog_errno(ret);
+                        break;
+                }
+
+                ret = ocfs2_read_block(inode, header_bh->b_blocknr + block_off,
+                                       &name_bh);
+                if (ret) {
+                        mlog_errno(ret);
+                        break;
+                }
+                xe_name = name_bh->b_data + new_offset;
+
+                cmp = memcmp(name, xe_name, name_len);
+                brelse(name_bh);
+                name_bh = NULL;
+
+                if (cmp == 0) {
+                        *xe_index = i;
+                        *found = 1;
+                        ret = 0;
+                        break;
+                }
+        }
+
+        return ret;
+}
+
+/*
+ * Find the specified xattr entry in a series of buckets.
+ * This series start from p_blkno and last for num_clusters.
+ * The ocfs2_xattr_header.xh_num_buckets of the first bucket contains
+ * the num of the valid buckets.
+ *
+ * Return the buffer_head this xattr should reside in. And if the xattr's
+ * hash is in the gap of 2 buckets, return the lower bucket.
+ */
+static int ocfs2_xattr_bucket_find(struct inode *inode,
+                                   int name_index,
+                                   const char *name,
+                                   u32 name_hash,
+                                   u64 p_blkno,
+                                   u32 first_hash,
+                                   u32 num_clusters,
+                                   struct ocfs2_xattr_search *xs)
+{
+        int ret, found = 0;
+        struct buffer_head *bh = NULL;
+        struct buffer_head *lower_bh = NULL;
+        struct ocfs2_xattr_header *xh = NULL;
+        struct ocfs2_xattr_entry *xe = NULL;
+        u16 index = 0;
+        u16 blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
+        int low_bucket = 0, bucket, high_bucket;
+        u32 last_hash;
+        u64 blkno;
+
+        ret = ocfs2_read_block(inode, p_blkno, &bh);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        xh = (struct ocfs2_xattr_header *)bh->b_data;
+        high_bucket = le16_to_cpu(xh->xh_num_buckets) - 1;
+
+        while (low_bucket <= high_bucket) {
+                brelse(bh);
+                bh = NULL;
+                bucket = (low_bucket + high_bucket) / 2;
+
+                blkno = p_blkno + bucket * blk_per_bucket;
+
+                ret = ocfs2_read_block(inode, blkno, &bh);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+
+                xh = (struct ocfs2_xattr_header *)bh->b_data;
+                xe = &xh->xh_entries[0];
+                if (name_hash < le32_to_cpu(xe->xe_name_hash)) {
+                        high_bucket = bucket - 1;
+                        continue;
+                }
+
+                /*
+                 * Check whether the hash of the last entry in our
+                 * bucket is larger than the search one. for an empty
+                 * bucket, the last one is also the first one.
+                 */
+                if (xh->xh_count)
+                        xe = &xh->xh_entries[le16_to_cpu(xh->xh_count) - 1];
+
+                last_hash = le32_to_cpu(xe->xe_name_hash);
+
+                /* record lower_bh which may be the insert place. */
+                brelse(lower_bh);
+                lower_bh = bh;
+                bh = NULL;
+
+                if (name_hash > le32_to_cpu(xe->xe_name_hash)) {
+                        low_bucket = bucket + 1;
+                        continue;
+                }
+
+                /* the searched xattr should reside in this bucket if exists. */
+                ret = ocfs2_find_xe_in_bucket(inode, lower_bh,
+                                              name_index, name, name_hash,
+                                              &index, &found);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+                break;
+        }
+
+        /*
+         * Record the bucket we have found.
+         * When the xattr's hash value is in the gap of 2 buckets, we will
+         * always set it to the previous bucket.
+         */
+        if (!lower_bh) {
+                /*
+                 * We can't find any bucket whose first name_hash is less
+                 * than the find name_hash.
+                 */
+                BUG_ON(bh->b_blocknr != p_blkno);
+                lower_bh = bh;
+                bh = NULL;
+        }
+        xs->bucket.bhs[0] = lower_bh;
+        xs->bucket.xh = (struct ocfs2_xattr_header *)
+                                        xs->bucket.bhs[0]->b_data;
+        lower_bh = NULL;
+
+        xs->header = xs->bucket.xh;
+        xs->base = xs->bucket.bhs[0]->b_data;
+        xs->end = xs->base + inode->i_sb->s_blocksize;
+
+        if (found) {
+                /*
+                 * If we have found the xattr enty, read all the blocks in
+                 * this bucket.
+                 */
+                ret = ocfs2_read_blocks(inode, xs->bucket.bhs[0]->b_blocknr + 1,
+                                        blk_per_bucket - 1, &xs->bucket.bhs[1],
+                                        0);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+
+                xs->here = &xs->header->xh_entries[index];
+                mlog(0, "find xattr %s in bucket %llu, entry = %u\n", name,
+                     (unsigned long long)xs->bucket.bhs[0]->b_blocknr, index);
+        } else
+                ret = -ENODATA;
+
+out:
+        brelse(bh);
+        brelse(lower_bh);
+        return ret;
+}
+
+static int ocfs2_xattr_index_block_find(struct inode *inode,
+                                        struct buffer_head *root_bh,
+                                        int name_index,
+                                        const char *name,
+                                        struct ocfs2_xattr_search *xs)
+{
+        int ret;
+        struct ocfs2_xattr_block *xb =
+                        (struct ocfs2_xattr_block *)root_bh->b_data;
+        struct ocfs2_xattr_tree_root *xb_root = &xb->xb_attrs.xb_root;
+        struct ocfs2_extent_list *el = &xb_root->xt_list;
+        u64 p_blkno = 0;
+        u32 first_hash, num_clusters = 0;
+        u32 name_hash = ocfs2_xattr_name_hash(inode, name, strlen(name));
+
+        if (le16_to_cpu(el->l_next_free_rec) == 0)
+                return -ENODATA;
+
+        mlog(0, "find xattr %s, hash = %u, index = %d in xattr tree\n",
+             name, name_hash, name_index);
+
+        ret = ocfs2_xattr_get_rec(inode, name_hash, &p_blkno, &first_hash,
+                                  &num_clusters, el);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        BUG_ON(p_blkno == 0 || num_clusters == 0 || first_hash > name_hash);
+
+        mlog(0, "find xattr extent rec %u clusters from %llu, the first hash "
+             "in the rec is %u\n", num_clusters, p_blkno, first_hash);
+
+        ret = ocfs2_xattr_bucket_find(inode, name_index, name, name_hash,
+                                      p_blkno, first_hash, num_clusters, xs);
+
+out:
+        return ret;
+}
+
+static int ocfs2_iterate_xattr_buckets(struct inode *inode,
+                                       u64 blkno,
+                                       u32 clusters,
+                                       xattr_bucket_func *func,
+                                       void *para)
+{
+        int i, j, ret = 0;
+        int blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
+        u32 bpc = ocfs2_xattr_buckets_per_cluster(OCFS2_SB(inode->i_sb));
+        u32 num_buckets = clusters * bpc;
+        struct ocfs2_xattr_bucket bucket;
+
+        memset(&bucket, 0, sizeof(bucket));
+
+        mlog(0, "iterating xattr buckets in %u clusters starting from %llu\n",
+             clusters, blkno);
+
+        for (i = 0; i < num_buckets; i++, blkno += blk_per_bucket) {
+                ret = ocfs2_read_blocks(inode, blkno, blk_per_bucket,
+                                        bucket.bhs, 0);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+
+                bucket.xh = (struct ocfs2_xattr_header *)bucket.bhs[0]->b_data;
+                /*
+                 * The real bucket num in this series of blocks is stored
+                 * in the 1st bucket.
+                 */
+                if (i == 0)
+                        num_buckets = le16_to_cpu(bucket.xh->xh_num_buckets);
+
+                mlog(0, "iterating xattr bucket %llu, first hash %u\n", blkno,
+                     le32_to_cpu(bucket.xh->xh_entries[0].xe_name_hash));
+                if (func) {
+                        ret = func(inode, &bucket, para);
+                        if (ret) {
+                                mlog_errno(ret);
+                                break;
+                        }
+                }
+
+                for (j = 0; j < blk_per_bucket; j++)
+                        brelse(bucket.bhs[j]);
+                memset(&bucket, 0, sizeof(bucket));
+        }
+
+out:
+        for (j = 0; j < blk_per_bucket; j++)
+                brelse(bucket.bhs[j]);
+
+        return ret;
+}
+
+struct ocfs2_xattr_tree_list {
+        char *buffer;
+        size_t buffer_size;
+        size_t result;
+};
+
+static int ocfs2_xattr_bucket_get_name_value(struct inode *inode,
+                                             struct ocfs2_xattr_header *xh,
+                                             int index,
+                                             int *block_off,
+                                             int *new_offset)
+{
+        u16 name_offset;
+
+        if (index < 0 || index >= le16_to_cpu(xh->xh_count))
+                return -EINVAL;
+
+        name_offset = le16_to_cpu(xh->xh_entries[index].xe_name_offset);
+
+        *block_off = name_offset >> inode->i_sb->s_blocksize_bits;
+        *new_offset = name_offset % inode->i_sb->s_blocksize;
+
+        return 0;
+}
+
+static int ocfs2_list_xattr_bucket(struct inode *inode,
+                                   struct ocfs2_xattr_bucket *bucket,
+                                   void *para)
+{
+        int ret = 0, type;
+        struct ocfs2_xattr_tree_list *xl = (struct ocfs2_xattr_tree_list *)para;
+        int i, block_off, new_offset;
+        const char *prefix, *name;
+
+        for (i = 0 ; i < le16_to_cpu(bucket->xh->xh_count); i++) {
+                struct ocfs2_xattr_entry *entry = &bucket->xh->xh_entries[i];
+                type = ocfs2_xattr_get_type(entry);
+                prefix = ocfs2_xattr_prefix(type);
+
+                if (prefix) {
+                        ret = ocfs2_xattr_bucket_get_name_value(inode,
+                                                                bucket->xh,
+                                                                i,
+                                                                &block_off,
+                                                                &new_offset);
+                        if (ret)
+                                break;
+
+                        name = (const char *)bucket->bhs[block_off]->b_data +
+                                new_offset;
+                        ret = ocfs2_xattr_list_entry(xl->buffer,
+                                                     xl->buffer_size,
+                                                     &xl->result,
+                                                     prefix, name,
+                                                     entry->xe_name_len);
+                        if (ret)
+                                break;
+                }
+        }
+
+        return ret;
+}
+
+static int ocfs2_xattr_tree_list_index_block(struct inode *inode,
+                                             struct ocfs2_xattr_tree_root *xt,
+                                             char *buffer,
+                                             size_t buffer_size)
+{
+        struct ocfs2_extent_list *el = &xt->xt_list;
+        int ret = 0;
+        u32 name_hash = UINT_MAX, e_cpos = 0, num_clusters = 0;
+        u64 p_blkno = 0;
+        struct ocfs2_xattr_tree_list xl = {
+                .buffer = buffer,
+                .buffer_size = buffer_size,
+                .result = 0,
+        };
+
+        if (le16_to_cpu(el->l_next_free_rec) == 0)
+                return 0;
+
+        while (name_hash > 0) {
+                ret = ocfs2_xattr_get_rec(inode, name_hash, &p_blkno,
+                                          &e_cpos, &num_clusters, el);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+
+                ret = ocfs2_iterate_xattr_buckets(inode, p_blkno, num_clusters,
+                                                  ocfs2_list_xattr_bucket,
+                                                  &xl);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+
+                if (e_cpos == 0)
+                        break;
+
+                name_hash = e_cpos - 1;
+        }
+
+        ret = xl.result;
+out:
+        return ret;
+}
+
+static int cmp_xe(const void *a, const void *b)
+{
+        const struct ocfs2_xattr_entry *l = a, *r = b;
+        u32 l_hash = le32_to_cpu(l->xe_name_hash);
+        u32 r_hash = le32_to_cpu(r->xe_name_hash);
+
+        if (l_hash > r_hash)
+                return 1;
+        if (l_hash < r_hash)
+                return -1;
+        return 0;
+}
+
+static void swap_xe(void *a, void *b, int size)
+{
+        struct ocfs2_xattr_entry *l = a, *r = b, tmp;
+
+        tmp = *l;
+        memcpy(l, r, sizeof(struct ocfs2_xattr_entry));
+        memcpy(r, &tmp, sizeof(struct ocfs2_xattr_entry));
+}
+
+/*
+ * When the ocfs2_xattr_block is filled up, new bucket will be created
+ * and all the xattr entries will be moved to the new bucket.
+ * Note: we need to sort the entries since they are not saved in order
+ * in the ocfs2_xattr_block.
+ */
+static void ocfs2_cp_xattr_block_to_bucket(struct inode *inode,
+                                           struct buffer_head *xb_bh,
+                                           struct buffer_head *xh_bh,
+                                           struct buffer_head *data_bh)
+{
+        int i, blocksize = inode->i_sb->s_blocksize;
+        u16 offset, size, off_change;
+        struct ocfs2_xattr_entry *xe;
+        struct ocfs2_xattr_block *xb =
+                                (struct ocfs2_xattr_block *)xb_bh->b_data;
+        struct ocfs2_xattr_header *xb_xh = &xb->xb_attrs.xb_header;
+        struct ocfs2_xattr_header *xh =
+                                (struct ocfs2_xattr_header *)xh_bh->b_data;
+        u16 count = le16_to_cpu(xb_xh->xh_count);
+        char *target = xh_bh->b_data, *src = xb_bh->b_data;
+
+        mlog(0, "cp xattr from block %llu to bucket %llu\n",
+             (unsigned long long)xb_bh->b_blocknr,
+             (unsigned long long)xh_bh->b_blocknr);
+
+        memset(xh_bh->b_data, 0, blocksize);
+        if (data_bh)
+                memset(data_bh->b_data, 0, blocksize);
+        /*
+         * Since the xe_name_offset is based on ocfs2_xattr_header,
+         * there is a offset change corresponding to the change of
+         * ocfs2_xattr_header's position.
+         */
+        off_change = offsetof(struct ocfs2_xattr_block, xb_attrs.xb_header);
+        xe = &xb_xh->xh_entries[count - 1];
+        offset = le16_to_cpu(xe->xe_name_offset) + off_change;
+        size = blocksize - offset;
+
+        /* copy all the names and values. */
+        if (data_bh)
+                target = data_bh->b_data;
+        memcpy(target + offset, src + offset, size);
+
+        /* Init new header now. */
+        xh->xh_count = xb_xh->xh_count;
+        xh->xh_num_buckets = cpu_to_le16(1);
+        xh->xh_name_value_len = cpu_to_le16(size);
+        xh->xh_free_start = cpu_to_le16(OCFS2_XATTR_BUCKET_SIZE - size);
+
+        /* copy all the entries. */
+        target = xh_bh->b_data;
+        offset = offsetof(struct ocfs2_xattr_header, xh_entries);
+        size = count * sizeof(struct ocfs2_xattr_entry);
+        memcpy(target + offset, (char *)xb_xh + offset, size);
+
+        /* Change the xe offset for all the xe because of the move. */
+        off_change = OCFS2_XATTR_BUCKET_SIZE - blocksize +
+                 offsetof(struct ocfs2_xattr_block, xb_attrs.xb_header);
+        for (i = 0; i < count; i++)
+                le16_add_cpu(&xh->xh_entries[i].xe_name_offset, off_change);
+
+        mlog(0, "copy entry: start = %u, size = %u, offset_change = %u\n",
+             offset, size, off_change);
+
+        sort(target + offset, count, sizeof(struct ocfs2_xattr_entry),
+             cmp_xe, swap_xe);
+}
+
+/*
+ * After we move xattr from block to index btree, we have to
+ * update ocfs2_xattr_search to the new xe and base.
+ *
+ * When the entry is in xattr block, xattr_bh indicates the storage place.
+ * While if the entry is in index b-tree, "bucket" indicates the
+ * real place of the xattr.
+ */
+static int ocfs2_xattr_update_xattr_search(struct inode *inode,
+                                           struct ocfs2_xattr_search *xs,
+                                           struct buffer_head *old_bh,
+                                           struct buffer_head *new_bh)
+{
+        int ret = 0;
+        char *buf = old_bh->b_data;
+        struct ocfs2_xattr_block *old_xb = (struct ocfs2_xattr_block *)buf;
+        struct ocfs2_xattr_header *old_xh = &old_xb->xb_attrs.xb_header;
+        int i, blocksize = inode->i_sb->s_blocksize;
+        u16 blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
+
+        xs->bucket.bhs[0] = new_bh;
+        get_bh(new_bh);
+        xs->bucket.xh = (struct ocfs2_xattr_header *)xs->bucket.bhs[0]->b_data;
+        xs->header = xs->bucket.xh;
+
+        xs->base = new_bh->b_data;
+        xs->end = xs->base + inode->i_sb->s_blocksize;
+
+        if (!xs->not_found) {
+                if (OCFS2_XATTR_BUCKET_SIZE != blocksize) {
+                        ret = ocfs2_read_blocks(inode,
+                                        xs->bucket.bhs[0]->b_blocknr + 1,
+                                        blk_per_bucket - 1, &xs->bucket.bhs[1],
+                                        0);
+                        if (ret) {
+                                mlog_errno(ret);
+                                return ret;
+                        }
+
+                        i = xs->here - old_xh->xh_entries;
+                        xs->here = &xs->header->xh_entries[i];
+                }
+        }
+
+        return ret;
+}
+
+static int ocfs2_xattr_create_index_block(struct inode *inode,
+                                          struct ocfs2_xattr_search *xs)
+{
+        int ret, credits = OCFS2_SUBALLOC_ALLOC;
+        u32 bit_off, len;
+        u64 blkno;
+        handle_t *handle;
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+        struct ocfs2_inode_info *oi = OCFS2_I(inode);
+        struct ocfs2_alloc_context *data_ac;
+        struct buffer_head *xh_bh = NULL, *data_bh = NULL;
+        struct buffer_head *xb_bh = xs->xattr_bh;
+        struct ocfs2_xattr_block *xb =
+                        (struct ocfs2_xattr_block *)xb_bh->b_data;
+        struct ocfs2_xattr_tree_root *xr;
+        u16 xb_flags = le16_to_cpu(xb->xb_flags);
+        u16 bpb = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
+
+        mlog(0, "create xattr index block for %llu\n",
+             (unsigned long long)xb_bh->b_blocknr);
+
+        BUG_ON(xb_flags & OCFS2_XATTR_INDEXED);
+
+        ret = ocfs2_reserve_clusters(osb, 1, &data_ac);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        /*
+         * XXX:
+         * We can use this lock for now, and maybe move to a dedicated mutex
+         * if performance becomes a problem later.
+         */
+        down_write(&oi->ip_alloc_sem);
+
+        /*
+         * 3 more credits, one for xattr block update, one for the 1st block
+         * of the new xattr bucket and one for the value/data.
+         */
+        credits += 3;
+        handle = ocfs2_start_trans(osb, credits);
+        if (IS_ERR(handle)) {
+                ret = PTR_ERR(handle);
+                mlog_errno(ret);
+                goto out_sem;
+        }
+
+        ret = ocfs2_journal_access(handle, inode, xb_bh,
+                                   OCFS2_JOURNAL_ACCESS_WRITE);
+        if (ret) {
+                mlog_errno(ret);
+                goto out_commit;
+        }
+
+        ret = ocfs2_claim_clusters(osb, handle, data_ac, 1, &bit_off, &len);
+        if (ret) {
+                mlog_errno(ret);
+                goto out_commit;
+        }
+
+        /*
+         * The bucket may spread in many blocks, and
+         * we will only touch the 1st block and the last block
+         * in the whole bucket(one for entry and one for data).
+         */
+        blkno = ocfs2_clusters_to_blocks(inode->i_sb, bit_off);
+
+        mlog(0, "allocate 1 cluster from %llu to xattr block\n", blkno);
+
+        xh_bh = sb_getblk(inode->i_sb, blkno);
+        if (!xh_bh) {
+                ret = -EIO;
+                mlog_errno(ret);
+                goto out_commit;
+        }
+
+        ocfs2_set_new_buffer_uptodate(inode, xh_bh);
+
+        ret = ocfs2_journal_access(handle, inode, xh_bh,
+                                   OCFS2_JOURNAL_ACCESS_CREATE);
+        if (ret) {
+                mlog_errno(ret);
+                goto out_commit;
+        }
+
+        if (bpb > 1) {
+                data_bh = sb_getblk(inode->i_sb, blkno + bpb - 1);
+                if (!data_bh) {
+                        ret = -EIO;
+                        mlog_errno(ret);
+                        goto out_commit;
+                }
+
+                ocfs2_set_new_buffer_uptodate(inode, data_bh);
+
+                ret = ocfs2_journal_access(handle, inode, data_bh,
+                                           OCFS2_JOURNAL_ACCESS_CREATE);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out_commit;
+                }
+        }
+
+        ocfs2_cp_xattr_block_to_bucket(inode, xb_bh, xh_bh, data_bh);
+
+        ocfs2_journal_dirty(handle, xh_bh);
+        if (data_bh)
+                ocfs2_journal_dirty(handle, data_bh);
+
+        ocfs2_xattr_update_xattr_search(inode, xs, xb_bh, xh_bh);
+
+        /* Change from ocfs2_xattr_header to ocfs2_xattr_tree_root */
+        memset(&xb->xb_attrs, 0, inode->i_sb->s_blocksize -
+               offsetof(struct ocfs2_xattr_block, xb_attrs));
+
+        xr = &xb->xb_attrs.xb_root;
+        xr->xt_clusters = cpu_to_le32(1);
+        xr->xt_last_eb_blk = 0;
+        xr->xt_list.l_tree_depth = 0;
+        xr->xt_list.l_count = cpu_to_le16(ocfs2_xattr_recs_per_xb(inode->i_sb));
+        xr->xt_list.l_next_free_rec = cpu_to_le16(1);
+
+        xr->xt_list.l_recs[0].e_cpos = 0;
+        xr->xt_list.l_recs[0].e_blkno = cpu_to_le64(blkno);
+        xr->xt_list.l_recs[0].e_leaf_clusters = cpu_to_le16(1);
+
+        xb->xb_flags = cpu_to_le16(xb_flags | OCFS2_XATTR_INDEXED);
+
+        ret = ocfs2_journal_dirty(handle, xb_bh);
+        if (ret) {
+                mlog_errno(ret);
+                goto out_commit;
+        }
+
+out_commit:
+        ocfs2_commit_trans(osb, handle);
+
+out_sem:
+        up_write(&oi->ip_alloc_sem);
+
+out:
+        if (data_ac)
+                ocfs2_free_alloc_context(data_ac);
+
+        brelse(xh_bh);
+        brelse(data_bh);
+
+        return ret;
+}
+
+static int cmp_xe_offset(const void *a, const void *b)
+{
+        const struct ocfs2_xattr_entry *l = a, *r = b;
+        u32 l_name_offset = le16_to_cpu(l->xe_name_offset);
+        u32 r_name_offset = le16_to_cpu(r->xe_name_offset);
+
+        if (l_name_offset < r_name_offset)
+                return 1;
+        if (l_name_offset > r_name_offset)
+                return -1;
+        return 0;
+}
+
+/*
+ * defrag a xattr bucket if we find that the bucket has some
+ * holes beteen name/value pairs.
+ * We will move all the name/value pairs to the end of the bucket
+ * so that we can spare some space for insertion.
+ */
+static int ocfs2_defrag_xattr_bucket(struct inode *inode,
+                                     struct ocfs2_xattr_bucket *bucket)
+{
+        int ret, i;
+        size_t end, offset, len, value_len;
+        struct ocfs2_xattr_header *xh;
+        char *entries, *buf, *bucket_buf = NULL;
+        u64 blkno = bucket->bhs[0]->b_blocknr;
+        u16 blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
+        u16 xh_free_start;
+        size_t blocksize = inode->i_sb->s_blocksize;
+        handle_t *handle;
+        struct buffer_head **bhs;
+        struct ocfs2_xattr_entry *xe;
+
+        bhs = kzalloc(sizeof(struct buffer_head *) * blk_per_bucket,
+                        GFP_NOFS);
+        if (!bhs)
+                return -ENOMEM;
+
+        ret = ocfs2_read_blocks(inode, blkno, blk_per_bucket, bhs, 0);
+        if (ret)
+                goto out;
+
+        /*
+         * In order to make the operation more efficient and generic,
+         * we copy all the blocks into a contiguous memory and do the
+         * defragment there, so if anything is error, we will not touch
+         * the real block.
+         */
+        bucket_buf = kmalloc(OCFS2_XATTR_BUCKET_SIZE, GFP_NOFS);
+        if (!bucket_buf) {
+                ret = -EIO;
+                goto out;
+        }
+
+        buf = bucket_buf;
+        for (i = 0; i < blk_per_bucket; i++, buf += blocksize)
+                memcpy(buf, bhs[i]->b_data, blocksize);
+
+        handle = ocfs2_start_trans((OCFS2_SB(inode->i_sb)), blk_per_bucket);
+        if (IS_ERR(handle)) {
+                ret = PTR_ERR(handle);
+                handle = NULL;
+                mlog_errno(ret);
+                goto out;
+        }
+
+        for (i = 0; i < blk_per_bucket; i++) {
+                ret = ocfs2_journal_access(handle, inode, bhs[i],
+                                           OCFS2_JOURNAL_ACCESS_WRITE);
+                if (ret < 0) {
+                        mlog_errno(ret);
+                        goto commit;
+                }
+        }
+
+        xh = (struct ocfs2_xattr_header *)bucket_buf;
+        entries = (char *)xh->xh_entries;
+        xh_free_start = le16_to_cpu(xh->xh_free_start);
+
+        mlog(0, "adjust xattr bucket in %llu, count = %u, "
+             "xh_free_start = %u, xh_name_value_len = %u.\n",
+             blkno, le16_to_cpu(xh->xh_count), xh_free_start,
+             le16_to_cpu(xh->xh_name_value_len));
+
+        /*
+         * sort all the entries by their offset.
+         * the largest will be the first, so that we can
+         * move them to the end one by one.
+         */
+        sort(entries, le16_to_cpu(xh->xh_count),
+             sizeof(struct ocfs2_xattr_entry),
+             cmp_xe_offset, swap_xe);
+
+        /* Move all name/values to the end of the bucket. */
+        xe = xh->xh_entries;
+        end = OCFS2_XATTR_BUCKET_SIZE;
+        for (i = 0; i < le16_to_cpu(xh->xh_count); i++, xe++) {
+                offset = le16_to_cpu(xe->xe_name_offset);
+                if (ocfs2_xattr_is_local(xe))
+                        value_len = OCFS2_XATTR_SIZE(
+                                        le64_to_cpu(xe->xe_value_size));
+                else
+                        value_len = OCFS2_XATTR_ROOT_SIZE;
+                len = OCFS2_XATTR_SIZE(xe->xe_name_len) + value_len;
+
+                /*
+                 * We must make sure that the name/value pair
+                 * exist in the same block. So adjust end to
+                 * the previous block end if needed.
+                 */
+                if (((end - len) / blocksize !=
+                        (end - 1) / blocksize))
+                        end = end - end % blocksize;
+
+                if (end > offset + len) {
+                        memmove(bucket_buf + end - len,
+                                bucket_buf + offset, len);
+                        xe->xe_name_offset = cpu_to_le16(end - len);
+                }
+
+                mlog_bug_on_msg(end < offset + len, "Defrag check failed for "
+                                "bucket %llu\n", (unsigned long long)blkno);
+
+                end -= len;
+        }
+
+        mlog_bug_on_msg(xh_free_start > end, "Defrag check failed for "
+                        "bucket %llu\n", (unsigned long long)blkno);
+
+        if (xh_free_start == end)
+                goto commit;
+
+        memset(bucket_buf + xh_free_start, 0, end - xh_free_start);
+        xh->xh_free_start = cpu_to_le16(end);
+
+        /* sort the entries by their name_hash. */
+        sort(entries, le16_to_cpu(xh->xh_count),
+             sizeof(struct ocfs2_xattr_entry),
+             cmp_xe, swap_xe);
+
+        buf = bucket_buf;
+        for (i = 0; i < blk_per_bucket; i++, buf += blocksize) {
+                memcpy(bhs[i]->b_data, buf, blocksize);
+                ocfs2_journal_dirty(handle, bhs[i]);
+        }
+
+commit:
+        ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
+out:
+
+        if (bhs) {
+                for (i = 0; i < blk_per_bucket; i++)
+                        brelse(bhs[i]);
+        }
+        kfree(bhs);
+
+        kfree(bucket_buf);
+        return ret;
+}
+
+/*
+ * Move half nums of the xattr bucket in the previous cluster to this new
+ * cluster. We only touch the last cluster of the previous extend record.
+ *
+ * first_bh is the first buffer_head of a series of bucket in the same
+ * extent rec and header_bh is the header of one bucket in this cluster.
+ * They will be updated if we move the data header_bh contains to the new
+ * cluster. first_hash will be set as the 1st xe's name_hash of the new cluster.
+ */
+static int ocfs2_mv_xattr_bucket_cross_cluster(struct inode *inode,
+                                               handle_t *handle,
+                                               struct buffer_head **first_bh,
+                                               struct buffer_head **header_bh,
+                                               u64 new_blkno,
+                                               u64 prev_blkno,
+                                               u32 num_clusters,
+                                               u32 *first_hash)
+{
+        int i, ret, credits;
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+        int bpc = ocfs2_clusters_to_blocks(inode->i_sb, 1);
+        int num_buckets = ocfs2_xattr_buckets_per_cluster(osb);
+        int blocksize = inode->i_sb->s_blocksize;
+        struct buffer_head *old_bh, *new_bh, *prev_bh, *new_first_bh = NULL;
+        struct ocfs2_xattr_header *new_xh;
+        struct ocfs2_xattr_header *xh =
+                        (struct ocfs2_xattr_header *)((*first_bh)->b_data);
+
+        BUG_ON(le16_to_cpu(xh->xh_num_buckets) < num_buckets);
+        BUG_ON(OCFS2_XATTR_BUCKET_SIZE == osb->s_clustersize);
+
+        prev_bh = *first_bh;
+        get_bh(prev_bh);
+        xh = (struct ocfs2_xattr_header *)prev_bh->b_data;
+
+        prev_blkno += (num_clusters - 1) * bpc + bpc / 2;
+
+        mlog(0, "move half of xattrs in cluster %llu to %llu\n",
+             prev_blkno, new_blkno);
+
+        /*
+         * We need to update the 1st half of the new cluster and
+         * 1 more for the update of the 1st bucket of the previous
+         * extent record.
+         */
+        credits = bpc / 2 + 1;
+        ret = ocfs2_extend_trans(handle, credits);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        ret = ocfs2_journal_access(handle, inode, prev_bh,
+                                   OCFS2_JOURNAL_ACCESS_WRITE);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        for (i = 0; i < bpc / 2; i++, prev_blkno++, new_blkno++) {
+                old_bh = new_bh = NULL;
+                new_bh = sb_getblk(inode->i_sb, new_blkno);
+                if (!new_bh) {
+                        ret = -EIO;
+                        mlog_errno(ret);
+                        goto out;
+                }
+
+                ocfs2_set_new_buffer_uptodate(inode, new_bh);
+
+                ret = ocfs2_journal_access(handle, inode, new_bh,
+                                           OCFS2_JOURNAL_ACCESS_CREATE);
+                if (ret < 0) {
+                        mlog_errno(ret);
+                        brelse(new_bh);
+                        goto out;
+                }
+
+                ret = ocfs2_read_block(inode, prev_blkno, &old_bh);
+                if (ret < 0) {
+                        mlog_errno(ret);
+                        brelse(new_bh);
+                        goto out;
+                }
+
+                memcpy(new_bh->b_data, old_bh->b_data, blocksize);
+
+                if (i == 0) {
+                        new_xh = (struct ocfs2_xattr_header *)new_bh->b_data;
+                        new_xh->xh_num_buckets = cpu_to_le16(num_buckets / 2);
+
+                        if (first_hash)
+                                *first_hash = le32_to_cpu(
+                                        new_xh->xh_entries[0].xe_name_hash);
+                        new_first_bh = new_bh;
+                        get_bh(new_first_bh);
+                }
+
+                ocfs2_journal_dirty(handle, new_bh);
+
+                if (*header_bh == old_bh) {
+                        brelse(*header_bh);
+                        *header_bh = new_bh;
+                        get_bh(*header_bh);
+
+                        brelse(*first_bh);
+                        *first_bh = new_first_bh;
+                        get_bh(*first_bh);
+                }
+                brelse(new_bh);
+                brelse(old_bh);
+        }
+
+        le16_add_cpu(&xh->xh_num_buckets, -(num_buckets / 2));
+
+        ocfs2_journal_dirty(handle, prev_bh);
+out:
+        brelse(prev_bh);
+        brelse(new_first_bh);
+        return ret;
+}
+
+static int ocfs2_read_xattr_bucket(struct inode *inode,
+                                   u64 blkno,
+                                   struct buffer_head **bhs,
+                                   int new)
+{
+        int ret = 0;
+        u16 i, blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
+
+        if (!new)
+                return ocfs2_read_blocks(inode, blkno,
+                                         blk_per_bucket, bhs, 0);
+
+        for (i = 0; i < blk_per_bucket; i++) {
+                bhs[i] = sb_getblk(inode->i_sb, blkno + i);
+                if (bhs[i] == NULL) {
+                        ret = -EIO;
+                        mlog_errno(ret);
+                        break;
+                }
+                ocfs2_set_new_buffer_uptodate(inode, bhs[i]);
+        }
+
+        return ret;
+}
+
+/*
+ * Move half num of the xattrs in old bucket(blk) to new bucket(new_blk).
+ * first_hash will record the 1st hash of the new bucket.
+ */
+static int ocfs2_half_xattr_bucket(struct inode *inode,
+                                   handle_t *handle,
+                                   u64 blk,
+                                   u64 new_blk,
+                                   u32 *first_hash,
+                                   int new_bucket_head)
+{
+        int ret, i;
+        u16 count, start, len, name_value_len, xe_len, name_offset;
+        u16 blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
+        struct buffer_head **s_bhs, **t_bhs = NULL;
+        struct ocfs2_xattr_header *xh;
+        struct ocfs2_xattr_entry *xe;
+        int blocksize = inode->i_sb->s_blocksize;
+
+        mlog(0, "move half of xattrs from bucket %llu to %llu\n",
+             blk, new_blk);
+
+        s_bhs = kcalloc(blk_per_bucket, sizeof(struct buffer_head *), GFP_NOFS);
+        if (!s_bhs)
+                return -ENOMEM;
+
+        ret = ocfs2_read_xattr_bucket(inode, blk, s_bhs, 0);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        ret = ocfs2_journal_access(handle, inode, s_bhs[0],
+                                   OCFS2_JOURNAL_ACCESS_WRITE);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        t_bhs = kcalloc(blk_per_bucket, sizeof(struct buffer_head *), GFP_NOFS);
+        if (!t_bhs) {
+                ret = -ENOMEM;
+                goto out;
+        }
+
+        ret = ocfs2_read_xattr_bucket(inode, new_blk, t_bhs, new_bucket_head);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        for (i = 0; i < blk_per_bucket; i++) {
+                ret = ocfs2_journal_access(handle, inode, t_bhs[i],
+                                           OCFS2_JOURNAL_ACCESS_CREATE);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+        }
+
+        /* copy the whole bucket to the new first. */
+        for (i = 0; i < blk_per_bucket; i++)
+                memcpy(t_bhs[i]->b_data, s_bhs[i]->b_data, blocksize);
+
+        /* update the new bucket. */
+        xh = (struct ocfs2_xattr_header *)t_bhs[0]->b_data;
+        count = le16_to_cpu(xh->xh_count);
+        start = count / 2;
+
+        /*
+         * Calculate the total name/value len and xh_free_start for
+         * the old bucket first.
+         */
+        name_offset = OCFS2_XATTR_BUCKET_SIZE;
+        name_value_len = 0;
+        for (i = 0; i < start; i++) {
+                xe = &xh->xh_entries[i];
+                xe_len = OCFS2_XATTR_SIZE(xe->xe_name_len);
+                if (ocfs2_xattr_is_local(xe))
+                        xe_len +=
+                           OCFS2_XATTR_SIZE(le64_to_cpu(xe->xe_value_size));
+                else
+                        xe_len += OCFS2_XATTR_ROOT_SIZE;
+                name_value_len += xe_len;
+                if (le16_to_cpu(xe->xe_name_offset) < name_offset)
+                        name_offset = le16_to_cpu(xe->xe_name_offset);
+        }
+
+        /*
+         * Now begin the modification to the new bucket.
+         *
+         * In the new bucket, We just move the xattr entry to the beginning
+         * and don't touch the name/value. So there will be some holes in the
+         * bucket, and they will be removed when ocfs2_defrag_xattr_bucket is
+         * called.
+         */
+        xe = &xh->xh_entries[start];
+        len = sizeof(struct ocfs2_xattr_entry) * (count - start);
+        mlog(0, "mv xattr entry len %d from %d to %d\n", len,
+             (int)((char *)xe - (char *)xh),
+             (int)((char *)xh->xh_entries - (char *)xh));
+        memmove((char *)xh->xh_entries, (char *)xe, len);
+        xe = &xh->xh_entries[count - start];
+        len = sizeof(struct ocfs2_xattr_entry) * start;
+        memset((char *)xe, 0, len);
+
+        le16_add_cpu(&xh->xh_count, -start);
+        le16_add_cpu(&xh->xh_name_value_len, -name_value_len);
+
+        /* Calculate xh_free_start for the new bucket. */
+        xh->xh_free_start = cpu_to_le16(OCFS2_XATTR_BUCKET_SIZE);
+        for (i = 0; i < le16_to_cpu(xh->xh_count); i++) {
+                xe = &xh->xh_entries[i];
+                xe_len = OCFS2_XATTR_SIZE(xe->xe_name_len);
+                if (ocfs2_xattr_is_local(xe))
+                        xe_len +=
+                           OCFS2_XATTR_SIZE(le64_to_cpu(xe->xe_value_size));
+                else
+                        xe_len += OCFS2_XATTR_ROOT_SIZE;
+                if (le16_to_cpu(xe->xe_name_offset) <
+                    le16_to_cpu(xh->xh_free_start))
+                        xh->xh_free_start = xe->xe_name_offset;
+        }
+
+        /* set xh->xh_num_buckets for the new xh. */
+        if (new_bucket_head)
+                xh->xh_num_buckets = cpu_to_le16(1);
+        else
+                xh->xh_num_buckets = 0;
+
+        for (i = 0; i < blk_per_bucket; i++) {
+                ocfs2_journal_dirty(handle, t_bhs[i]);
+                if (ret)
+                        mlog_errno(ret);
+        }
+
+        /* store the first_hash of the new bucket. */
+        if (first_hash)
+                *first_hash = le32_to_cpu(xh->xh_entries[0].xe_name_hash);
+
+        /*
+         * Now only update the 1st block of the old bucket.
+         * Please note that the entry has been sorted already above.
+         */
+        xh = (struct ocfs2_xattr_header *)s_bhs[0]->b_data;
+        memset(&xh->xh_entries[start], 0,
+               sizeof(struct ocfs2_xattr_entry) * (count - start));
+        xh->xh_count = cpu_to_le16(start);
+        xh->xh_free_start = cpu_to_le16(name_offset);
+        xh->xh_name_value_len = cpu_to_le16(name_value_len);
+
+        ocfs2_journal_dirty(handle, s_bhs[0]);
+        if (ret)
+                mlog_errno(ret);
+
+out:
+        if (s_bhs) {
+                for (i = 0; i < blk_per_bucket; i++)
+                        brelse(s_bhs[i]);
+        }
+        kfree(s_bhs);
+
+        if (t_bhs) {
+                for (i = 0; i < blk_per_bucket; i++)
+                        brelse(t_bhs[i]);
+        }
+        kfree(t_bhs);
+
+        return ret;
+}
+
+/*
+ * Copy xattr from one bucket to another bucket.
+ *
+ * The caller must make sure that the journal transaction
+ * has enough space for journaling.
+ */
+static int ocfs2_cp_xattr_bucket(struct inode *inode,
+                                 handle_t *handle,
+                                 u64 s_blkno,
+                                 u64 t_blkno,
+                                 int t_is_new)
+{
+        int ret, i;
+        int blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
+        int blocksize = inode->i_sb->s_blocksize;
+        struct buffer_head **s_bhs, **t_bhs = NULL;
+
+        BUG_ON(s_blkno == t_blkno);
+
+        mlog(0, "cp bucket %llu to %llu, target is %d\n",
+             s_blkno, t_blkno, t_is_new);
+
+        s_bhs = kzalloc(sizeof(struct buffer_head *) * blk_per_bucket,
+                        GFP_NOFS);
+        if (!s_bhs)
+                return -ENOMEM;
+
+        ret = ocfs2_read_xattr_bucket(inode, s_blkno, s_bhs, 0);
+        if (ret)
+                goto out;
+
+        t_bhs = kzalloc(sizeof(struct buffer_head *) * blk_per_bucket,
+                        GFP_NOFS);
+        if (!t_bhs) {
+                ret = -ENOMEM;
+                goto out;
+        }
+
+        ret = ocfs2_read_xattr_bucket(inode, t_blkno, t_bhs, t_is_new);
+        if (ret)
+                goto out;
+
+        for (i = 0; i < blk_per_bucket; i++) {
+                ret = ocfs2_journal_access(handle, inode, t_bhs[i],
+                                           OCFS2_JOURNAL_ACCESS_WRITE);
+                if (ret)
+                        goto out;
+        }
+
+        for (i = 0; i < blk_per_bucket; i++) {
+                memcpy(t_bhs[i]->b_data, s_bhs[i]->b_data, blocksize);
+                ocfs2_journal_dirty(handle, t_bhs[i]);
+        }
+
+out:
+        if (s_bhs) {
+                for (i = 0; i < blk_per_bucket; i++)
+                        brelse(s_bhs[i]);
+        }
+        kfree(s_bhs);
+
+        if (t_bhs) {
+                for (i = 0; i < blk_per_bucket; i++)
+                        brelse(t_bhs[i]);
+        }
+        kfree(t_bhs);
+
+        return ret;
+}
+
+/*
+ * Copy one xattr cluster from src_blk to to_blk.
+ * The to_blk will become the first bucket header of the cluster, so its
+ * xh_num_buckets will be initialized as the bucket num in the cluster.
+ */
+static int ocfs2_cp_xattr_cluster(struct inode *inode,
+                                  handle_t *handle,
+                                  struct buffer_head *first_bh,
+                                  u64 src_blk,
+                                  u64 to_blk,
+                                  u32 *first_hash)
+{
+        int i, ret, credits;
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+        int bpc = ocfs2_clusters_to_blocks(inode->i_sb, 1);
+        int num_buckets = ocfs2_xattr_buckets_per_cluster(osb);
+        struct buffer_head *bh = NULL;
+        struct ocfs2_xattr_header *xh;
+        u64 to_blk_start = to_blk;
+
+        mlog(0, "cp xattrs from cluster %llu to %llu\n", src_blk, to_blk);
+
+        /*
+         * We need to update the new cluster and 1 more for the update of
+         * the 1st bucket of the previous extent rec.
+         */
+        credits = bpc + 1;
+        ret = ocfs2_extend_trans(handle, credits);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        ret = ocfs2_journal_access(handle, inode, first_bh,
+                                   OCFS2_JOURNAL_ACCESS_WRITE);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        for (i = 0; i < num_buckets; i++) {
+                ret = ocfs2_cp_xattr_bucket(inode, handle,
+                                            src_blk, to_blk, 1);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+
+                src_blk += ocfs2_blocks_per_xattr_bucket(inode->i_sb);
+                to_blk += ocfs2_blocks_per_xattr_bucket(inode->i_sb);
+        }
+
+        /* update the old bucket header. */
+        xh = (struct ocfs2_xattr_header *)first_bh->b_data;
+        le16_add_cpu(&xh->xh_num_buckets, -num_buckets);
+
+        ocfs2_journal_dirty(handle, first_bh);
+
+        /* update the new bucket header. */
+        ret = ocfs2_read_block(inode, to_blk_start, &bh);
+        if (ret < 0) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        ret = ocfs2_journal_access(handle, inode, bh,
+                                   OCFS2_JOURNAL_ACCESS_WRITE);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        xh = (struct ocfs2_xattr_header *)bh->b_data;
+        xh->xh_num_buckets = cpu_to_le16(num_buckets);
+
+        ocfs2_journal_dirty(handle, bh);
+
+        if (first_hash)
+                *first_hash = le32_to_cpu(xh->xh_entries[0].xe_name_hash);
+out:
+        brelse(bh);
+        return ret;
+}
+
+/*
+ * Move half of the xattrs in this cluster to the new cluster.
+ * This function should only be called when bucket size == cluster size.
+ * Otherwise ocfs2_mv_xattr_bucket_cross_cluster should be used instead.
+ */
+static int ocfs2_half_xattr_cluster(struct inode *inode,
+                                    handle_t *handle,
+                                    u64 prev_blk,
+                                    u64 new_blk,
+                                    u32 *first_hash)
+{
+        u16 blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
+        int ret, credits = 2 * blk_per_bucket;
+
+        BUG_ON(OCFS2_XATTR_BUCKET_SIZE < OCFS2_SB(inode->i_sb)->s_clustersize);
+
+        ret = ocfs2_extend_trans(handle, credits);
+        if (ret) {
+                mlog_errno(ret);
+                return ret;
+        }
+
+        /* Move half of the xattr in start_blk to the next bucket. */
+        return  ocfs2_half_xattr_bucket(inode, handle, prev_blk,
+                                        new_blk, first_hash, 1);
+}
+
+/*
+ * Move some xattrs from the old cluster to the new one since they are not
+ * contiguous in ocfs2 xattr tree.
+ *
+ * new_blk starts a new separate cluster, and we will move some xattrs from
+ * prev_blk to it. v_start will be set as the first name hash value in this
+ * new cluster so that it can be used as e_cpos during tree insertion and
+ * don't collide with our original b-tree operations. first_bh and header_bh
+ * will also be updated since they will be used in ocfs2_extend_xattr_bucket
+ * to extend the insert bucket.
+ *
+ * The problem is how much xattr should we move to the new one and when should
+ * we update first_bh and header_bh?
+ * 1. If cluster size > bucket size, that means the previous cluster has more
+ *    than 1 bucket, so just move half nums of bucket into the new cluster and
+ *    update the first_bh and header_bh if the insert bucket has been moved
+ *    to the new cluster.
+ * 2. If cluster_size == bucket_size:
+ *    a) If the previous extent rec has more than one cluster and the insert
+ *       place isn't in the last cluster, copy the entire last cluster to the
+ *       new one. This time, we don't need to upate the first_bh and header_bh
+ *       since they will not be moved into the new cluster.
+ *    b) Otherwise, move the bottom half of the xattrs in the last cluster into
+ *       the new one. And we set the extend flag to zero if the insert place is
+ *       moved into the new allocated cluster since no extend is needed.
+ */
+static int ocfs2_adjust_xattr_cross_cluster(struct inode *inode,
+                                            handle_t *handle,
+                                            struct buffer_head **first_bh,
+                                            struct buffer_head **header_bh,
+                                            u64 new_blk,
+                                            u64 prev_blk,
+                                            u32 prev_clusters,
+                                            u32 *v_start,
+                                            int *extend)
+{
+        int ret = 0;
+        int bpc = ocfs2_clusters_to_blocks(inode->i_sb, 1);
+
+        mlog(0, "adjust xattrs from cluster %llu len %u to %llu\n",
+             prev_blk, prev_clusters, new_blk);
+
+        if (ocfs2_xattr_buckets_per_cluster(OCFS2_SB(inode->i_sb)) > 1)
+                ret = ocfs2_mv_xattr_bucket_cross_cluster(inode,
+                                                          handle,
+                                                          first_bh,
+                                                          header_bh,
+                                                          new_blk,
+                                                          prev_blk,
+                                                          prev_clusters,
+                                                          v_start);
+        else {
+                u64 last_blk = prev_blk + bpc * (prev_clusters - 1);
+
+                if (prev_clusters > 1 && (*header_bh)->b_blocknr != last_blk)
+                        ret = ocfs2_cp_xattr_cluster(inode, handle, *first_bh,
+                                                     last_blk, new_blk,
+                                                     v_start);
+                else {
+                        ret = ocfs2_half_xattr_cluster(inode, handle,
+                                                       last_blk, new_blk,
+                                                       v_start);
+
+                        if ((*header_bh)->b_blocknr == last_blk && extend)
+                                *extend = 0;
+                }
+        }
+
+        return ret;
+}
+
+/*
+ * Add a new cluster for xattr storage.
+ *
+ * If the new cluster is contiguous with the previous one, it will be
+ * appended to the same extent record, and num_clusters will be updated.
+ * If not, we will insert a new extent for it and move some xattrs in
+ * the last cluster into the new allocated one.
+ * We also need to limit the maximum size of a btree leaf, otherwise we'll
+ * lose the benefits of hashing because we'll have to search large leaves.
+ * So now the maximum size is OCFS2_MAX_XATTR_TREE_LEAF_SIZE(or clustersize,
+ * if it's bigger).
+ *
+ * first_bh is the first block of the previous extent rec and header_bh
+ * indicates the bucket we will insert the new xattrs. They will be updated
+ * when the header_bh is moved into the new cluster.
+ */
+static int ocfs2_add_new_xattr_cluster(struct inode *inode,
+                                       struct buffer_head *root_bh,
+                                       struct buffer_head **first_bh,
+                                       struct buffer_head **header_bh,
+                                       u32 *num_clusters,
+                                       u32 prev_cpos,
+                                       u64 prev_blkno,
+                                       int *extend)
+{
+        int ret, credits;
+        u16 bpc = ocfs2_clusters_to_blocks(inode->i_sb, 1);
+        u32 prev_clusters = *num_clusters;
+        u32 clusters_to_add = 1, bit_off, num_bits, v_start = 0;
+        u64 block;
+        handle_t *handle = NULL;
+        struct ocfs2_alloc_context *data_ac = NULL;
+        struct ocfs2_alloc_context *meta_ac = NULL;
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+        struct ocfs2_extent_tree et;
+
+        mlog(0, "Add new xattr cluster for %llu, previous xattr hash = %u, "
+             "previous xattr blkno = %llu\n",
+             (unsigned long long)OCFS2_I(inode)->ip_blkno,
+             prev_cpos, prev_blkno);
+
+        ocfs2_init_xattr_tree_extent_tree(&et, inode, root_bh);
+
+        ret = ocfs2_lock_allocators(inode, &et, clusters_to_add, 0,
+                                    &data_ac, &meta_ac);
+        if (ret) {
+                mlog_errno(ret);
+                goto leave;
+        }
+
+        credits = ocfs2_calc_extend_credits(osb->sb, et.et_root_el,
+                                            clusters_to_add);
+        handle = ocfs2_start_trans(osb, credits);
+        if (IS_ERR(handle)) {
+                ret = PTR_ERR(handle);
+                handle = NULL;
+                mlog_errno(ret);
+                goto leave;
+        }
+
+        ret = ocfs2_journal_access(handle, inode, root_bh,
+                                   OCFS2_JOURNAL_ACCESS_WRITE);
+        if (ret < 0) {
+                mlog_errno(ret);
+                goto leave;
+        }
+
+        ret = __ocfs2_claim_clusters(osb, handle, data_ac, 1,
+                                     clusters_to_add, &bit_off, &num_bits);
+        if (ret < 0) {
+                if (ret != -ENOSPC)
+                        mlog_errno(ret);
+                goto leave;
+        }
+
+        BUG_ON(num_bits > clusters_to_add);
+
+        block = ocfs2_clusters_to_blocks(osb->sb, bit_off);
+        mlog(0, "Allocating %u clusters at block %u for xattr in inode %llu\n",
+             num_bits, bit_off, (unsigned long long)OCFS2_I(inode)->ip_blkno);
+
+        if (prev_blkno + prev_clusters * bpc == block &&
+            (prev_clusters + num_bits) << osb->s_clustersize_bits <=
+             OCFS2_MAX_XATTR_TREE_LEAF_SIZE) {
+                /*
+                 * If this cluster is contiguous with the old one and
+                 * adding this new cluster, we don't surpass the limit of
+                 * OCFS2_MAX_XATTR_TREE_LEAF_SIZE, cool. We will let it be
+                 * initialized and used like other buckets in the previous
+                 * cluster.
+                 * So add it as a contiguous one. The caller will handle
+                 * its init process.
+                 */
+                v_start = prev_cpos + prev_clusters;
+                *num_clusters = prev_clusters + num_bits;
+                mlog(0, "Add contiguous %u clusters to previous extent rec.\n",
+                     num_bits);
+        } else {
+                ret = ocfs2_adjust_xattr_cross_cluster(inode,
+                                                       handle,
+                                                       first_bh,
+                                                       header_bh,
+                                                       block,
+                                                       prev_blkno,
+                                                       prev_clusters,
+                                                       &v_start,
+                                                       extend);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto leave;
+                }
+        }
+
+        if (handle->h_buffer_credits < credits) {
+                /*
+                 * The journal has been restarted before, and don't
+                 * have enough space for the insertion, so extend it
+                 * here.
+                 */
+                ret = ocfs2_extend_trans(handle, credits);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto leave;
+                }
+        }
+        mlog(0, "Insert %u clusters at block %llu for xattr at %u\n",
+             num_bits, block, v_start);
+        ret = ocfs2_insert_extent(osb, handle, inode, &et, v_start, block,
+                                  num_bits, 0, meta_ac);
+        if (ret < 0) {
+                mlog_errno(ret);
+                goto leave;
+        }
+
+        ret = ocfs2_journal_dirty(handle, root_bh);
+        if (ret < 0) {
+                mlog_errno(ret);
+                goto leave;
+        }
+
+leave:
+        if (handle)
+                ocfs2_commit_trans(osb, handle);
+        if (data_ac)
+                ocfs2_free_alloc_context(data_ac);
+        if (meta_ac)
+                ocfs2_free_alloc_context(meta_ac);
+
+        return ret;
+}
+
+/*
+ * Extend a new xattr bucket and move xattrs to the end one by one until
+ * We meet with start_bh. Only move half of the xattrs to the bucket after it.
+ */
+static int ocfs2_extend_xattr_bucket(struct inode *inode,
+                                     struct buffer_head *first_bh,
+                                     struct buffer_head *start_bh,
+                                     u32 num_clusters)
+{
+        int ret, credits;
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+        u16 blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
+        u64 start_blk = start_bh->b_blocknr, end_blk;
+        u32 num_buckets = num_clusters * ocfs2_xattr_buckets_per_cluster(osb);
+        handle_t *handle;
+        struct ocfs2_xattr_header *first_xh =
+                                (struct ocfs2_xattr_header *)first_bh->b_data;
+        u16 bucket = le16_to_cpu(first_xh->xh_num_buckets);
+
+        mlog(0, "extend xattr bucket in %llu, xattr extend rec starting "
+             "from %llu, len = %u\n", start_blk,
+             (unsigned long long)first_bh->b_blocknr, num_clusters);
+
+        BUG_ON(bucket >= num_buckets);
+
+        end_blk = first_bh->b_blocknr + (bucket - 1) * blk_per_bucket;
+
+        /*
+         * We will touch all the buckets after the start_bh(include it).
+         * Add one more bucket and modify the first_bh.
+         */
+        credits = end_blk - start_blk + 2 * blk_per_bucket + 1;
+        handle = ocfs2_start_trans(osb, credits);
+        if (IS_ERR(handle)) {
+                ret = PTR_ERR(handle);
+                handle = NULL;
+                mlog_errno(ret);
+                goto out;
+        }
+
+        ret = ocfs2_journal_access(handle, inode, first_bh,
+                                   OCFS2_JOURNAL_ACCESS_WRITE);
+        if (ret) {
+                mlog_errno(ret);
+                goto commit;
+        }
+
+        while (end_blk != start_blk) {
+                ret = ocfs2_cp_xattr_bucket(inode, handle, end_blk,
+                                            end_blk + blk_per_bucket, 0);
+                if (ret)
+                        goto commit;
+                end_blk -= blk_per_bucket;
+        }
+
+        /* Move half of the xattr in start_blk to the next bucket. */
+        ret = ocfs2_half_xattr_bucket(inode, handle, start_blk,
+                                      start_blk + blk_per_bucket, NULL, 0);
+
+        le16_add_cpu(&first_xh->xh_num_buckets, 1);
+        ocfs2_journal_dirty(handle, first_bh);
+
+commit:
+        ocfs2_commit_trans(osb, handle);
+out:
+        return ret;
+}
+
+/*
+ * Add new xattr bucket in an extent record and adjust the buckets accordingly.
+ * xb_bh is the ocfs2_xattr_block.
+ * We will move all the buckets starting from header_bh to the next place. As
+ * for this one, half num of its xattrs will be moved to the next one.
+ *
+ * We will allocate a new cluster if current cluster is full and adjust
+ * header_bh and first_bh if the insert place is moved to the new cluster.
+ */
+static int ocfs2_add_new_xattr_bucket(struct inode *inode,
+                                      struct buffer_head *xb_bh,
+                                      struct buffer_head *header_bh)
+{
+        struct ocfs2_xattr_header *first_xh = NULL;
+        struct buffer_head *first_bh = NULL;
+        struct ocfs2_xattr_block *xb =
+                        (struct ocfs2_xattr_block *)xb_bh->b_data;
+        struct ocfs2_xattr_tree_root *xb_root = &xb->xb_attrs.xb_root;
+        struct ocfs2_extent_list *el = &xb_root->xt_list;
+        struct ocfs2_xattr_header *xh =
+                        (struct ocfs2_xattr_header *)header_bh->b_data;
+        u32 name_hash = le32_to_cpu(xh->xh_entries[0].xe_name_hash);
+        struct super_block *sb = inode->i_sb;
+        struct ocfs2_super *osb = OCFS2_SB(sb);
+        int ret, num_buckets, extend = 1;
+        u64 p_blkno;
+        u32 e_cpos, num_clusters;
+
+        mlog(0, "Add new xattr bucket starting form %llu\n",
+             (unsigned long long)header_bh->b_blocknr);
+
+        /*
+         * Add refrence for header_bh here because it may be
+         * changed in ocfs2_add_new_xattr_cluster and we need
+         * to free it in the end.
+         */
+        get_bh(header_bh);
+
+        ret = ocfs2_xattr_get_rec(inode, name_hash, &p_blkno, &e_cpos,
+                                  &num_clusters, el);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        ret = ocfs2_read_block(inode, p_blkno, &first_bh);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        num_buckets = ocfs2_xattr_buckets_per_cluster(osb) * num_clusters;
+        first_xh = (struct ocfs2_xattr_header *)first_bh->b_data;
+
+        if (num_buckets == le16_to_cpu(first_xh->xh_num_buckets)) {
+                ret = ocfs2_add_new_xattr_cluster(inode,
+                                                  xb_bh,
+                                                  &first_bh,
+                                                  &header_bh,
+                                                  &num_clusters,
+                                                  e_cpos,
+                                                  p_blkno,
+                                                  &extend);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+        }
+
+        if (extend)
+                ret = ocfs2_extend_xattr_bucket(inode,
+                                                first_bh,
+                                                header_bh,
+                                                num_clusters);
+        if (ret)
+                mlog_errno(ret);
+out:
+        brelse(first_bh);
+        brelse(header_bh);
+        return ret;
+}
+
+static inline char *ocfs2_xattr_bucket_get_val(struct inode *inode,
+                                        struct ocfs2_xattr_bucket *bucket,
+                                        int offs)
+{
+        int block_off = offs >> inode->i_sb->s_blocksize_bits;
+
+        offs = offs % inode->i_sb->s_blocksize;
+        return bucket->bhs[block_off]->b_data + offs;
+}
+
+/*
+ * Handle the normal xattr set, including replace, delete and new.
+ *
+ * Note: "local" indicates the real data's locality. So we can't
+ * just its bucket locality by its length.
+ */
+static void ocfs2_xattr_set_entry_normal(struct inode *inode,
+                                         struct ocfs2_xattr_info *xi,
+                                         struct ocfs2_xattr_search *xs,
+                                         u32 name_hash,
+                                         int local)
+{
+        struct ocfs2_xattr_entry *last, *xe;
+        int name_len = strlen(xi->name);
+        struct ocfs2_xattr_header *xh = xs->header;
+        u16 count = le16_to_cpu(xh->xh_count), start;
+        size_t blocksize = inode->i_sb->s_blocksize;
+        char *val;
+        size_t offs, size, new_size;
+
+        last = &xh->xh_entries[count];
+        if (!xs->not_found) {
+                xe = xs->here;
+                offs = le16_to_cpu(xe->xe_name_offset);
+                if (ocfs2_xattr_is_local(xe))
+                        size = OCFS2_XATTR_SIZE(name_len) +
+                        OCFS2_XATTR_SIZE(le64_to_cpu(xe->xe_value_size));
+                else
+                        size = OCFS2_XATTR_SIZE(name_len) +
+                        OCFS2_XATTR_SIZE(OCFS2_XATTR_ROOT_SIZE);
+
+                /*
+                 * If the new value will be stored outside, xi->value has been
+                 * initalized as an empty ocfs2_xattr_value_root, and the same
+                 * goes with xi->value_len, so we can set new_size safely here.
+                 * See ocfs2_xattr_set_in_bucket.
+                 */
+                new_size = OCFS2_XATTR_SIZE(name_len) +
+                           OCFS2_XATTR_SIZE(xi->value_len);
+
+                le16_add_cpu(&xh->xh_name_value_len, -size);
+                if (xi->value) {
+                        if (new_size > size)
+                                goto set_new_name_value;
+
+                        /* Now replace the old value with new one. */
+                        if (local)
+                                xe->xe_value_size = cpu_to_le64(xi->value_len);
+                        else
+                                xe->xe_value_size = 0;
+
+                        val = ocfs2_xattr_bucket_get_val(inode,
+                                                         &xs->bucket, offs);
+                        memset(val + OCFS2_XATTR_SIZE(name_len), 0,
+                               size - OCFS2_XATTR_SIZE(name_len));
+                        if (OCFS2_XATTR_SIZE(xi->value_len) > 0)
+                                memcpy(val + OCFS2_XATTR_SIZE(name_len),
+                                       xi->value, xi->value_len);
+
+                        le16_add_cpu(&xh->xh_name_value_len, new_size);
+                        ocfs2_xattr_set_local(xe, local);
+                        return;
+                } else {
+                        /*
+                         * Remove the old entry if there is more than one.
+                         * We don't remove the last entry so that we can
+                         * use it to indicate the hash value of the empty
+                         * bucket.
+                         */
+                        last -= 1;
+                        le16_add_cpu(&xh->xh_count, -1);
+                        if (xh->xh_count) {
+                                memmove(xe, xe + 1,
+                                        (void *)last - (void *)xe);
+                                memset(last, 0,
+                                       sizeof(struct ocfs2_xattr_entry));
+                        } else
+                                xh->xh_free_start =
+                                        cpu_to_le16(OCFS2_XATTR_BUCKET_SIZE);
+
+                        return;
+                }
+        } else {
+                /* find a new entry for insert. */
+                int low = 0, high = count - 1, tmp;
+                struct ocfs2_xattr_entry *tmp_xe;
+
+                while (low <= high && count) {
+                        tmp = (low + high) / 2;
+                        tmp_xe = &xh->xh_entries[tmp];
+
+                        if (name_hash > le32_to_cpu(tmp_xe->xe_name_hash))
+                                low = tmp + 1;
+                        else if (name_hash <
+                                 le32_to_cpu(tmp_xe->xe_name_hash))
+                                high = tmp - 1;
+                        else {
+                                low = tmp;
+                                break;
+                        }
+                }
+
+                xe = &xh->xh_entries[low];
+                if (low != count)
+                        memmove(xe + 1, xe, (void *)last - (void *)xe);
+
+                le16_add_cpu(&xh->xh_count, 1);
+                memset(xe, 0, sizeof(struct ocfs2_xattr_entry));
+                xe->xe_name_hash = cpu_to_le32(name_hash);
+                xe->xe_name_len = name_len;
+                ocfs2_xattr_set_type(xe, xi->name_index);
+        }
+
+set_new_name_value:
+        /* Insert the new name+value. */
+        size = OCFS2_XATTR_SIZE(name_len) + OCFS2_XATTR_SIZE(xi->value_len);
+
+        /*
+         * We must make sure that the name/value pair
+         * exists in the same block.
+         */
+        offs = le16_to_cpu(xh->xh_free_start);
+        start = offs - size;
+
+        if (start >> inode->i_sb->s_blocksize_bits !=
+            (offs - 1) >> inode->i_sb->s_blocksize_bits) {
+                offs = offs - offs % blocksize;
+                xh->xh_free_start = cpu_to_le16(offs);
+        }
+
+        val = ocfs2_xattr_bucket_get_val(inode,
+                                         &xs->bucket, offs - size);
+        xe->xe_name_offset = cpu_to_le16(offs - size);
+
+        memset(val, 0, size);
+        memcpy(val, xi->name, name_len);
+        memcpy(val + OCFS2_XATTR_SIZE(name_len), xi->value, xi->value_len);
+
+        xe->xe_value_size = cpu_to_le64(xi->value_len);
+        ocfs2_xattr_set_local(xe, local);
+        xs->here = xe;
+        le16_add_cpu(&xh->xh_free_start, -size);
+        le16_add_cpu(&xh->xh_name_value_len, size);
+
+        return;
+}
+
+static int ocfs2_xattr_bucket_handle_journal(struct inode *inode,
+                                             handle_t *handle,
+                                             struct ocfs2_xattr_search *xs,
+                                             struct buffer_head **bhs,
+                                             u16 bh_num)
+{
+        int ret = 0, off, block_off;
+        struct ocfs2_xattr_entry *xe = xs->here;
+
+        /*
+         * First calculate all the blocks we should journal_access
+         * and journal_dirty. The first block should always be touched.
+         */
+        ret = ocfs2_journal_dirty(handle, bhs[0]);
+        if (ret)
+                mlog_errno(ret);
+
+        /* calc the data. */
+        off = le16_to_cpu(xe->xe_name_offset);
+        block_off = off >> inode->i_sb->s_blocksize_bits;
+        ret = ocfs2_journal_dirty(handle, bhs[block_off]);
+        if (ret)
+                mlog_errno(ret);
+
+        return ret;
+}
+
+/*
+ * Set the xattr entry in the specified bucket.
+ * The bucket is indicated by xs->bucket and it should have the enough
+ * space for the xattr insertion.
+ */
+static int ocfs2_xattr_set_entry_in_bucket(struct inode *inode,
+                                           struct ocfs2_xattr_info *xi,
+                                           struct ocfs2_xattr_search *xs,
+                                           u32 name_hash,
+                                           int local)
+{
+        int i, ret;
+        handle_t *handle = NULL;
+        u16 blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+        mlog(0, "Set xattr entry len = %lu index = %d in bucket %llu\n",
+             (unsigned long)xi->value_len, xi->name_index,
+             (unsigned long long)xs->bucket.bhs[0]->b_blocknr);
+
+        if (!xs->bucket.bhs[1]) {
+                ret = ocfs2_read_blocks(inode,
+                                        xs->bucket.bhs[0]->b_blocknr + 1,
+                                        blk_per_bucket - 1, &xs->bucket.bhs[1],
+                                        0);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+        }
+
+        handle = ocfs2_start_trans(osb, blk_per_bucket);
+        if (IS_ERR(handle)) {
+                ret = PTR_ERR(handle);
+                handle = NULL;
+                mlog_errno(ret);
+                goto out;
+        }
+
+        for (i = 0; i < blk_per_bucket; i++) {
+                ret = ocfs2_journal_access(handle, inode, xs->bucket.bhs[i],
+                                           OCFS2_JOURNAL_ACCESS_WRITE);
+                if (ret < 0) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+        }
+
+        ocfs2_xattr_set_entry_normal(inode, xi, xs, name_hash, local);
+
+        /*Only dirty the blocks we have touched in set xattr. */
+        ret = ocfs2_xattr_bucket_handle_journal(inode, handle, xs,
+                                                xs->bucket.bhs, blk_per_bucket);
+        if (ret)
+                mlog_errno(ret);
+out:
+        ocfs2_commit_trans(osb, handle);
+
+        return ret;
+}
+
+static int ocfs2_xattr_value_update_size(struct inode *inode,
+                                         struct buffer_head *xe_bh,
+                                         struct ocfs2_xattr_entry *xe,
+                                         u64 new_size)
+{
+        int ret;
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+        handle_t *handle = NULL;
+
+        handle = ocfs2_start_trans(osb, 1);
+        if (handle == NULL) {
+                ret = -ENOMEM;
+                mlog_errno(ret);
+                goto out;
+        }
+
+        ret = ocfs2_journal_access(handle, inode, xe_bh,
+                                   OCFS2_JOURNAL_ACCESS_WRITE);
+        if (ret < 0) {
+                mlog_errno(ret);
+                goto out_commit;
+        }
+
+        xe->xe_value_size = cpu_to_le64(new_size);
+
+        ret = ocfs2_journal_dirty(handle, xe_bh);
+        if (ret < 0)
+                mlog_errno(ret);
+
+out_commit:
+        ocfs2_commit_trans(osb, handle);
+out:
+        return ret;
+}
+
+/*
+ * Truncate the specified xe_off entry in xattr bucket.
+ * bucket is indicated by header_bh and len is the new length.
+ * Both the ocfs2_xattr_value_root and the entry will be updated here.
+ *
+ * Copy the new updated xe and xe_value_root to new_xe and new_xv if needed.
+ */
+static int ocfs2_xattr_bucket_value_truncate(struct inode *inode,
+                                             struct buffer_head *header_bh,
+                                             int xe_off,
+                                             int len)
+{
+        int ret, offset;
+        u64 value_blk;
+        struct buffer_head *value_bh = NULL;
+        struct ocfs2_xattr_value_root *xv;
+        struct ocfs2_xattr_entry *xe;
+        struct ocfs2_xattr_header *xh =
+                        (struct ocfs2_xattr_header *)header_bh->b_data;
+        size_t blocksize = inode->i_sb->s_blocksize;
+
+        xe = &xh->xh_entries[xe_off];
+
+        BUG_ON(!xe || ocfs2_xattr_is_local(xe));
+
+        offset = le16_to_cpu(xe->xe_name_offset) +
+                 OCFS2_XATTR_SIZE(xe->xe_name_len);
+
+        value_blk = offset / blocksize;
+
+        /* We don't allow ocfs2_xattr_value to be stored in different block. */
+        BUG_ON(value_blk != (offset + OCFS2_XATTR_ROOT_SIZE - 1) / blocksize);
+        value_blk += header_bh->b_blocknr;
+
+        ret = ocfs2_read_block(inode, value_blk, &value_bh);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        xv = (struct ocfs2_xattr_value_root *)
+                (value_bh->b_data + offset % blocksize);
+
+        mlog(0, "truncate %u in xattr bucket %llu to %d bytes.\n",
+             xe_off, (unsigned long long)header_bh->b_blocknr, len);
+        ret = ocfs2_xattr_value_truncate(inode, value_bh, xv, len);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        ret = ocfs2_xattr_value_update_size(inode, header_bh, xe, len);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+out:
+        brelse(value_bh);
+        return ret;
+}
+
+static int ocfs2_xattr_bucket_value_truncate_xs(struct inode *inode,
+                                                struct ocfs2_xattr_search *xs,
+                                                int len)
+{
+        int ret, offset;
+        struct ocfs2_xattr_entry *xe = xs->here;
+        struct ocfs2_xattr_header *xh = (struct ocfs2_xattr_header *)xs->base;
+
+        BUG_ON(!xs->bucket.bhs[0] || !xe || ocfs2_xattr_is_local(xe));
+
+        offset = xe - xh->xh_entries;
+        ret = ocfs2_xattr_bucket_value_truncate(inode, xs->bucket.bhs[0],
+                                                offset, len);
+        if (ret)
+                mlog_errno(ret);
+
+        return ret;
+}
+
+static int ocfs2_xattr_bucket_set_value_outside(struct inode *inode,
+                                                struct ocfs2_xattr_search *xs,
+                                                char *val,
+                                                int value_len)
+{
+        int offset;
+        struct ocfs2_xattr_value_root *xv;
+        struct ocfs2_xattr_entry *xe = xs->here;
+
+        BUG_ON(!xs->base || !xe || ocfs2_xattr_is_local(xe));
+
+        offset = le16_to_cpu(xe->xe_name_offset) +
+                 OCFS2_XATTR_SIZE(xe->xe_name_len);
+
+        xv = (struct ocfs2_xattr_value_root *)(xs->base + offset);
+
+        return __ocfs2_xattr_set_value_outside(inode, xv, val, value_len);
+}
+
+static int ocfs2_rm_xattr_cluster(struct inode *inode,
+                                  struct buffer_head *root_bh,
+                                  u64 blkno,
+                                  u32 cpos,
+                                  u32 len)
+{
+        int ret;
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+        struct inode *tl_inode = osb->osb_tl_inode;
+        handle_t *handle;
+        struct ocfs2_xattr_block *xb =
+                        (struct ocfs2_xattr_block *)root_bh->b_data;
+        struct ocfs2_alloc_context *meta_ac = NULL;
+        struct ocfs2_cached_dealloc_ctxt dealloc;
+        struct ocfs2_extent_tree et;
+
+        ocfs2_init_xattr_tree_extent_tree(&et, inode, root_bh);
+
+        ocfs2_init_dealloc_ctxt(&dealloc);
+
+        mlog(0, "rm xattr extent rec at %u len = %u, start from %llu\n",
+             cpos, len, (unsigned long long)blkno);
+
+        ocfs2_remove_xattr_clusters_from_cache(inode, blkno, len);
+
+        ret = ocfs2_lock_allocators(inode, &et, 0, 1, NULL, &meta_ac);
+        if (ret) {
+                mlog_errno(ret);
+                return ret;
+        }
+
+        mutex_lock(&tl_inode->i_mutex);
+
+        if (ocfs2_truncate_log_needs_flush(osb)) {
+                ret = __ocfs2_flush_truncate_log(osb);
+                if (ret < 0) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+        }
+
+        handle = ocfs2_start_trans(osb, OCFS2_REMOVE_EXTENT_CREDITS);
+        if (handle == NULL) {
+                ret = -ENOMEM;
+                mlog_errno(ret);
+                goto out;
+        }
+
+        ret = ocfs2_journal_access(handle, inode, root_bh,
+                                   OCFS2_JOURNAL_ACCESS_WRITE);
+        if (ret) {
+                mlog_errno(ret);
+                goto out_commit;
+        }
+
+        ret = ocfs2_remove_extent(inode, &et, cpos, len, handle, meta_ac,
+                                  &dealloc);
+        if (ret) {
+                mlog_errno(ret);
+                goto out_commit;
+        }
+
+        le32_add_cpu(&xb->xb_attrs.xb_root.xt_clusters, -len);
+
+        ret = ocfs2_journal_dirty(handle, root_bh);
+        if (ret) {
+                mlog_errno(ret);
+                goto out_commit;
+        }
+
+        ret = ocfs2_truncate_log_append(osb, handle, blkno, len);
+        if (ret)
+                mlog_errno(ret);
+
+out_commit:
+        ocfs2_commit_trans(osb, handle);
+out:
+        ocfs2_schedule_truncate_log_flush(osb, 1);
+
+        mutex_unlock(&tl_inode->i_mutex);
+
+        if (meta_ac)
+                ocfs2_free_alloc_context(meta_ac);
+
+        ocfs2_run_deallocs(osb, &dealloc);
+
+        return ret;
+}
+
+static void ocfs2_xattr_bucket_remove_xs(struct inode *inode,
+                                         struct ocfs2_xattr_search *xs)
+{
+        handle_t *handle = NULL;
+        struct ocfs2_xattr_header *xh = xs->bucket.xh;
+        struct ocfs2_xattr_entry *last = &xh->xh_entries[
+                                                le16_to_cpu(xh->xh_count) - 1];
+        int ret = 0;
+
+        handle = ocfs2_start_trans((OCFS2_SB(inode->i_sb)), 1);
+        if (IS_ERR(handle)) {
+                ret = PTR_ERR(handle);
+                mlog_errno(ret);
+                return;
+        }
+
+        ret = ocfs2_journal_access(handle, inode, xs->bucket.bhs[0],
+                                   OCFS2_JOURNAL_ACCESS_WRITE);
+        if (ret) {
+                mlog_errno(ret);
+                goto out_commit;
+        }
+
+        /* Remove the old entry. */
+        memmove(xs->here, xs->here + 1,
+                (void *)last - (void *)xs->here);
+        memset(last, 0, sizeof(struct ocfs2_xattr_entry));
+        le16_add_cpu(&xh->xh_count, -1);
+
+        ret = ocfs2_journal_dirty(handle, xs->bucket.bhs[0]);
+        if (ret < 0)
+                mlog_errno(ret);
+out_commit:
+        ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
+}
+
+/*
+ * Set the xattr name/value in the bucket specified in xs.
+ *
+ * As the new value in xi may be stored in the bucket or in an outside cluster,
+ * we divide the whole process into 3 steps:
+ * 1. insert name/value in the bucket(ocfs2_xattr_set_entry_in_bucket)
+ * 2. truncate of the outside cluster(ocfs2_xattr_bucket_value_truncate_xs)
+ * 3. Set the value to the outside cluster(ocfs2_xattr_bucket_set_value_outside)
+ * 4. If the clusters for the new outside value can't be allocated, we need
+ *    to free the xattr we allocated in set.
+ */
+static int ocfs2_xattr_set_in_bucket(struct inode *inode,
+                                     struct ocfs2_xattr_info *xi,
+                                     struct ocfs2_xattr_search *xs)
+{
+        int ret, local = 1;
+        size_t value_len;
+        char *val = (char *)xi->value;
+        struct ocfs2_xattr_entry *xe = xs->here;
+        u32 name_hash = ocfs2_xattr_name_hash(inode, xi->name,
+                                              strlen(xi->name));
+
+        if (!xs->not_found && !ocfs2_xattr_is_local(xe)) {
+                /*
+                 * We need to truncate the xattr storage first.
+                 *
+                 * If both the old and new value are stored to
+                 * outside block, we only need to truncate
+                 * the storage and then set the value outside.
+                 *
+                 * If the new value should be stored within block,
+                 * we should free all the outside block first and
+                 * the modification to the xattr block will be done
+                 * by following steps.
+                 */
+                if (xi->value_len > OCFS2_XATTR_INLINE_SIZE)
+                        value_len = xi->value_len;
+                else
+                        value_len = 0;
+
+                ret = ocfs2_xattr_bucket_value_truncate_xs(inode, xs,
+                                                           value_len);
+                if (ret)
+                        goto out;
+
+                if (value_len)
+                        goto set_value_outside;
+        }
+
+        value_len = xi->value_len;
+        /* So we have to handle the inside block change now. */
+        if (value_len > OCFS2_XATTR_INLINE_SIZE) {
+                /*
+                 * If the new value will be stored outside of block,
+                 * initalize a new empty value root and insert it first.
+                 */
+                local = 0;
+                xi->value = &def_xv;
+                xi->value_len = OCFS2_XATTR_ROOT_SIZE;
+        }
+
+        ret = ocfs2_xattr_set_entry_in_bucket(inode, xi, xs, name_hash, local);
+        if (ret) {
+                mlog_errno(ret);
+                goto out;
+        }
+
+        if (value_len <= OCFS2_XATTR_INLINE_SIZE)
+                goto out;
+
+        /* allocate the space now for the outside block storage. */
+        ret = ocfs2_xattr_bucket_value_truncate_xs(inode, xs,
+                                                   value_len);
+        if (ret) {
+                mlog_errno(ret);
+
+                if (xs->not_found) {
+                        /*
+                         * We can't allocate enough clusters for outside
+                         * storage and we have allocated xattr already,
+                         * so need to remove it.
+                         */
+                        ocfs2_xattr_bucket_remove_xs(inode, xs);
+                }
+                goto out;
+        }
+
+set_value_outside:
+        ret = ocfs2_xattr_bucket_set_value_outside(inode, xs, val, value_len);
+out:
+        return ret;
+}
+
+/* check whether the xattr bucket is filled up with the same hash value. */
+static int ocfs2_check_xattr_bucket_collision(struct inode *inode,
+                                              struct ocfs2_xattr_bucket *bucket)
+{
+        struct ocfs2_xattr_header *xh = bucket->xh;
+
+        if (xh->xh_entries[le16_to_cpu(xh->xh_count) - 1].xe_name_hash ==
+            xh->xh_entries[0].xe_name_hash) {
+                mlog(ML_ERROR, "Too much hash collision in xattr bucket %llu, "
+                     "hash = %u\n",
+                     (unsigned long long)bucket->bhs[0]->b_blocknr,
+                     le32_to_cpu(xh->xh_entries[0].xe_name_hash));
+                return -ENOSPC;
+        }
+
+        return 0;
+}
+
+static int ocfs2_xattr_set_entry_index_block(struct inode *inode,
+                                             struct ocfs2_xattr_info *xi,
+                                             struct ocfs2_xattr_search *xs)
+{
+        struct ocfs2_xattr_header *xh;
+        struct ocfs2_xattr_entry *xe;
+        u16 count, header_size, xh_free_start;
+        int i, free, max_free, need, old;
+        size_t value_size = 0, name_len = strlen(xi->name);
+        size_t blocksize = inode->i_sb->s_blocksize;
+        int ret, allocation = 0;
+        u16 blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
+
+        mlog_entry("Set xattr %s in xattr index block\n", xi->name);
+
+try_again:
+        xh = xs->header;
+        count = le16_to_cpu(xh->xh_count);
+        xh_free_start = le16_to_cpu(xh->xh_free_start);
+        header_size = sizeof(struct ocfs2_xattr_header) +
+                        count * sizeof(struct ocfs2_xattr_entry);
+        max_free = OCFS2_XATTR_BUCKET_SIZE -
+                le16_to_cpu(xh->xh_name_value_len) - header_size;
+
+        mlog_bug_on_msg(header_size > blocksize, "bucket %llu has header size "
+                        "of %u which exceed block size\n",
+                        (unsigned long long)xs->bucket.bhs[0]->b_blocknr,
+                        header_size);
+
+        if (xi->value && xi->value_len > OCFS2_XATTR_INLINE_SIZE)
+                value_size = OCFS2_XATTR_ROOT_SIZE;
+        else if (xi->value)
+                value_size = OCFS2_XATTR_SIZE(xi->value_len);
+
+        if (xs->not_found)
+                need = sizeof(struct ocfs2_xattr_entry) +
+                        OCFS2_XATTR_SIZE(name_len) + value_size;
+        else {
+                need = value_size + OCFS2_XATTR_SIZE(name_len);
+
+                /*
+                 * We only replace the old value if the new length is smaller
+                 * than the old one. Otherwise we will allocate new space in the
+                 * bucket to store it.
+                 */
+                xe = xs->here;
+                if (ocfs2_xattr_is_local(xe))
+                        old = OCFS2_XATTR_SIZE(le64_to_cpu(xe->xe_value_size));
+                else
+                        old = OCFS2_XATTR_SIZE(OCFS2_XATTR_ROOT_SIZE);
+
+                if (old >= value_size)
+                        need = 0;
+        }
+
+        free = xh_free_start - header_size;
+        /*
+         * We need to make sure the new name/value pair
+         * can exist in the same block.
+         */
+        if (xh_free_start % blocksize < need)
+                free -= xh_free_start % blocksize;
+
+        mlog(0, "xs->not_found = %d, in xattr bucket %llu: free = %d, "
+             "need = %d, max_free = %d, xh_free_start = %u, xh_name_value_len ="
+             " %u\n", xs->not_found,
+             (unsigned long long)xs->bucket.bhs[0]->b_blocknr,
+             free, need, max_free, le16_to_cpu(xh->xh_free_start),
+             le16_to_cpu(xh->xh_name_value_len));
+
+        if (free < need || count == ocfs2_xattr_max_xe_in_bucket(inode->i_sb)) {
+                if (need <= max_free &&
+                    count < ocfs2_xattr_max_xe_in_bucket(inode->i_sb)) {
+                        /*
+                         * We can create the space by defragment. Since only the
+                         * name/value will be moved, the xe shouldn't be changed
+                         * in xs.
+                         */
+                        ret = ocfs2_defrag_xattr_bucket(inode, &xs->bucket);
+                        if (ret) {
+                                mlog_errno(ret);
+                                goto out;
+                        }
+
+                        xh_free_start = le16_to_cpu(xh->xh_free_start);
+                        free = xh_free_start - header_size;
+                        if (xh_free_start % blocksize < need)
+                                free -= xh_free_start % blocksize;
+
+                        if (free >= need)
+                                goto xattr_set;
+
+                        mlog(0, "Can't get enough space for xattr insert by "
+                             "defragment. Need %u bytes, but we have %d, so "
+                             "allocate new bucket for it.\n", need, free);
+                }
+
+                /*
+                 * We have to add new buckets or clusters and one
+                 * allocation should leave us enough space for insert.
+                 */
+                BUG_ON(allocation);
+
+                /*
+                 * We do not allow for overlapping ranges between buckets. And
+                 * the maximum number of collisions we will allow for then is
+                 * one bucket's worth, so check it here whether we need to
+                 * add a new bucket for the insert.
+                 */
+                ret = ocfs2_check_xattr_bucket_collision(inode, &xs->bucket);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+
+                ret = ocfs2_add_new_xattr_bucket(inode,
+                                                 xs->xattr_bh,
+                                                 xs->bucket.bhs[0]);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+
+                for (i = 0; i < blk_per_bucket; i++)
+                        brelse(xs->bucket.bhs[i]);
+
+                memset(&xs->bucket, 0, sizeof(xs->bucket));
+
+                ret = ocfs2_xattr_index_block_find(inode, xs->xattr_bh,
+                                                   xi->name_index,
+                                                   xi->name, xs);
+                if (ret && ret != -ENODATA)
+                        goto out;
+                xs->not_found = ret;
+                allocation = 1;
+                goto try_again;
+        }
+
+xattr_set:
+        ret = ocfs2_xattr_set_in_bucket(inode, xi, xs);
+out:
+        mlog_exit(ret);
+        return ret;
+}
+
+static int ocfs2_delete_xattr_in_bucket(struct inode *inode,
+                                        struct ocfs2_xattr_bucket *bucket,
+                                        void *para)
+{
+        int ret = 0;
+        struct ocfs2_xattr_header *xh = bucket->xh;
+        u16 i;
+        struct ocfs2_xattr_entry *xe;
+
+        for (i = 0; i < le16_to_cpu(xh->xh_count); i++) {
+                xe = &xh->xh_entries[i];
+                if (ocfs2_xattr_is_local(xe))
+                        continue;
+
+                ret = ocfs2_xattr_bucket_value_truncate(inode,
+                                                        bucket->bhs[0],
+                                                        i, 0);
+                if (ret) {
+                        mlog_errno(ret);
+                        break;
+                }
+        }
+
+        return ret;
+}
+
+static int ocfs2_delete_xattr_index_block(struct inode *inode,
+                                          struct buffer_head *xb_bh)
+{
+        struct ocfs2_xattr_block *xb =
+                        (struct ocfs2_xattr_block *)xb_bh->b_data;
+        struct ocfs2_extent_list *el = &xb->xb_attrs.xb_root.xt_list;
+        int ret = 0;
+        u32 name_hash = UINT_MAX, e_cpos, num_clusters;
+        u64 p_blkno;
+
+        if (le16_to_cpu(el->l_next_free_rec) == 0)
+                return 0;
+
+        while (name_hash > 0) {
+                ret = ocfs2_xattr_get_rec(inode, name_hash, &p_blkno,
+                                          &e_cpos, &num_clusters, el);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+
+                ret = ocfs2_iterate_xattr_buckets(inode, p_blkno, num_clusters,
+                                                  ocfs2_delete_xattr_in_bucket,
+                                                  NULL);
+                if (ret) {
+                        mlog_errno(ret);
+                        goto out;
+                }
+
+                ret = ocfs2_rm_xattr_cluster(inode, xb_bh,
+                                             p_blkno, e_cpos, num_clusters);
+                if (ret) {
+                        mlog_errno(ret);
+                        break;
+                }
+
+                if (e_cpos == 0)
+                        break;
+
+                name_hash = e_cpos - 1;
+        }
+
+out:
+        return ret;
+}
+
+/*
+ * 'trusted' attributes support
+ */
+
+#define XATTR_TRUSTED_PREFIX "trusted."
+
+static size_t ocfs2_xattr_trusted_list(struct inode *inode, char *list,
+                                       size_t list_size, const char *name,
+                                       size_t name_len)
+{
+        const size_t prefix_len = sizeof(XATTR_TRUSTED_PREFIX) - 1;
+        const size_t total_len = prefix_len + name_len + 1;
+
+        if (list && total_len <= list_size) {
+                memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len);
+                memcpy(list + prefix_len, name, name_len);
+                list[prefix_len + name_len] = '\0';
+        }
+        return total_len;
+}
+
+static int ocfs2_xattr_trusted_get(struct inode *inode, const char *name,
+                                   void *buffer, size_t size)
+{
+        if (strcmp(name, "") == 0)
+                return -EINVAL;
+        return ocfs2_xattr_get(inode, OCFS2_XATTR_INDEX_TRUSTED, name,
+                               buffer, size);
+}
+
+static int ocfs2_xattr_trusted_set(struct inode *inode, const char *name,
+                                   const void *value, size_t size, int flags)
+{
+        if (strcmp(name, "") == 0)
+                return -EINVAL;
+
+        return ocfs2_xattr_set(inode, OCFS2_XATTR_INDEX_TRUSTED, name, value,
+                               size, flags);
+}
+
+struct xattr_handler ocfs2_xattr_trusted_handler = {
+        .prefix = XATTR_TRUSTED_PREFIX,
+        .list   = ocfs2_xattr_trusted_list,
+        .get    = ocfs2_xattr_trusted_get,
+        .set    = ocfs2_xattr_trusted_set,
+};
+
+
+/*
+ * 'user' attributes support
+ */
+
+#define XATTR_USER_PREFIX "user."
+
+static size_t ocfs2_xattr_user_list(struct inode *inode, char *list,
+                                    size_t list_size, const char *name,
+                                    size_t name_len)
+{
+        const size_t prefix_len = sizeof(XATTR_USER_PREFIX) - 1;
+        const size_t total_len = prefix_len + name_len + 1;
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+        if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR)
+                return 0;
+
+        if (list && total_len <= list_size) {
+                memcpy(list, XATTR_USER_PREFIX, prefix_len);
+                memcpy(list + prefix_len, name, name_len);
+                list[prefix_len + name_len] = '\0';
+        }
+        return total_len;
+}
+
+static int ocfs2_xattr_user_get(struct inode *inode, const char *name,
+                                void *buffer, size_t size)
+{
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+        if (strcmp(name, "") == 0)
+                return -EINVAL;
+        if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR)
+                return -EOPNOTSUPP;
+        return ocfs2_xattr_get(inode, OCFS2_XATTR_INDEX_USER, name,
+                               buffer, size);
+}
+
+static int ocfs2_xattr_user_set(struct inode *inode, const char *name,
+                                const void *value, size_t size, int flags)
+{
+        struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
+        if (strcmp(name, "") == 0)
+                return -EINVAL;
+        if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR)
+                return -EOPNOTSUPP;
+
+        return ocfs2_xattr_set(inode, OCFS2_XATTR_INDEX_USER, name, value,
+                               size, flags);
+}
+
+struct xattr_handler ocfs2_xattr_user_handler = {
+        .prefix = XATTR_USER_PREFIX,
+        .list   = ocfs2_xattr_user_list,
+        .get    = ocfs2_xattr_user_get,
+        .set    = ocfs2_xattr_user_set,
+};
diff --git a/fs/ocfs2/xattr.h b/fs/ocfs2/xattr.h
new file mode 100644
index 000000000000..c25c7c62a059
--- /dev/null
+++ b/fs/ocfs2/xattr.h
@@ -0,0 +1,68 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * xattr.h
+ *
+ * Function prototypes
+ *
+ * Copyright (C) 2008 Oracle.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#ifndef OCFS2_XATTR_H
+#define OCFS2_XATTR_H
+
+#include <linux/init.h>
+#include <linux/xattr.h>
+
+enum ocfs2_xattr_type {
+        OCFS2_XATTR_INDEX_USER = 1,
+        OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS,
+        OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT,
+        OCFS2_XATTR_INDEX_TRUSTED,
+        OCFS2_XATTR_INDEX_SECURITY,
+        OCFS2_XATTR_MAX
+};
+
+extern struct xattr_handler ocfs2_xattr_user_handler;
+extern struct xattr_handler ocfs2_xattr_trusted_handler;
+
+extern ssize_t ocfs2_listxattr(struct dentry *, char *, size_t);
+extern int ocfs2_xattr_get(struct inode *, int, const char *, void *, size_t);
+extern int ocfs2_xattr_set(struct inode *, int, const char *, const void *,
+                           size_t, int);
+extern int ocfs2_xattr_remove(struct inode *inode, struct buffer_head *di_bh);
+extern struct xattr_handler *ocfs2_xattr_handlers[];
+
+static inline u16 ocfs2_xattr_buckets_per_cluster(struct ocfs2_super *osb)
+{
+        return (1 << osb->s_clustersize_bits) / OCFS2_XATTR_BUCKET_SIZE;
+}
+
+static inline u16 ocfs2_blocks_per_xattr_bucket(struct super_block *sb)
+{
+        return OCFS2_XATTR_BUCKET_SIZE / (1 << sb->s_blocksize_bits);
+}
+
+static inline u16 ocfs2_xattr_max_xe_in_bucket(struct super_block *sb)
+{
+        u16 len = sb->s_blocksize -
+                 offsetof(struct ocfs2_xattr_header, xh_entries);
+
+        return len / sizeof(struct ocfs2_xattr_entry);
+}
+#endif /* OCFS2_XATTR_H */
diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c
index d29047b1b9b0..cbf047a847c5 100644
--- a/fs/omfs/inode.c
+++ b/fs/omfs/inode.c
@@ -346,7 +346,7 @@ enum {
         Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         {Opt_uid, "uid=%u"},
         {Opt_gid, "gid=%u"},
         {Opt_umask, "umask=%o"},
diff --git a/fs/open.c b/fs/open.c
index 07da9359481c..5596049863bf 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1141,8 +1141,7 @@ EXPORT_SYMBOL(sys_close);
 asmlinkage long sys_vhangup(void)
 {
         if (capable(CAP_SYS_TTY_CONFIG)) {
-                /* XXX: this needs locking */
-                tty_vhangup(current->signal->tty);
+                tty_vhangup_self();
                 return 0;
         }
         return -EPERM;
diff --git a/fs/partitions/acorn.c b/fs/partitions/acorn.c
index 3d3e16631472..a97b477ac0fc 100644
--- a/fs/partitions/acorn.c
+++ b/fs/partitions/acorn.c
@@ -275,16 +275,6 @@ adfspart_check_ADFS(struct parsed_partitions *state, struct block_device *bdev)
         id = data[0x1fc] & 15;
         put_dev_sector(sect);
 
-#ifdef CONFIG_BLK_DEV_MFM
-        if (MAJOR(bdev->bd_dev) == MFM_ACORN_MAJOR) {
-                extern void xd_set_geometry(struct block_device *,
-                        unsigned char, unsigned char, unsigned int);
-                xd_set_geometry(bdev, dr->secspertrack, heads, 1);
-                invalidate_bh_lrus();
-                truncate_inode_pages(bdev->bd_inode->i_mapping, 0);
-        }
-#endif
-
         /*
          * Work out start of non-adfs partition.
          */
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index ecc3330972e5..cfb0c80690aa 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -120,22 +120,21 @@ static int (*check_part[])(struct parsed_partitions *, struct block_device *) =
  * a pointer to that same buffer (for convenience).
  */
 
-char *disk_name(struct gendisk *hd, int part, char *buf)
+char *disk_name(struct gendisk *hd, int partno, char *buf)
 {
-        if (!part)
+        if (!partno)
                 snprintf(buf, BDEVNAME_SIZE, "%s", hd->disk_name);
         else if (isdigit(hd->disk_name[strlen(hd->disk_name)-1]))
-                snprintf(buf, BDEVNAME_SIZE, "%sp%d", hd->disk_name, part);
+                snprintf(buf, BDEVNAME_SIZE, "%sp%d", hd->disk_name, partno);
         else
-                snprintf(buf, BDEVNAME_SIZE, "%s%d", hd->disk_name, part);
+                snprintf(buf, BDEVNAME_SIZE, "%s%d", hd->disk_name, partno);
 
         return buf;
 }
 
 const char *bdevname(struct block_device *bdev, char *buf)
 {
-        int part = MINOR(bdev->bd_dev) - bdev->bd_disk->first_minor;
-        return disk_name(bdev->bd_disk, part, buf);
+        return disk_name(bdev->bd_disk, bdev->bd_part->partno, buf);
 }
 
 EXPORT_SYMBOL(bdevname);
@@ -169,7 +168,7 @@ check_partition(struct gendisk *hd, struct block_device *bdev)
         if (isdigit(state->name[strlen(state->name)-1]))
                 sprintf(state->name, "p");
 
-        state->limit = hd->minors;
+        state->limit = disk_max_parts(hd);
         i = res = err = 0;
         while (!res && check_part[i]) {
                 memset(&state->parts, 0, sizeof(state->parts));
@@ -196,6 +195,14 @@ check_partition(struct gendisk *hd, struct block_device *bdev)
         return ERR_PTR(res);
 }
 
+static ssize_t part_partition_show(struct device *dev,
+                                   struct device_attribute *attr, char *buf)
+{
+        struct hd_struct *p = dev_to_part(dev);
+
+        return sprintf(buf, "%d\n", p->partno);
+}
+
 static ssize_t part_start_show(struct device *dev,
                                struct device_attribute *attr, char *buf)
 {
@@ -204,21 +211,22 @@ static ssize_t part_start_show(struct device *dev,
         return sprintf(buf, "%llu\n",(unsigned long long)p->start_sect);
 }
 
-static ssize_t part_size_show(struct device *dev,
-                              struct device_attribute *attr, char *buf)
+ssize_t part_size_show(struct device *dev,
+                       struct device_attribute *attr, char *buf)
 {
         struct hd_struct *p = dev_to_part(dev);
         return sprintf(buf, "%llu\n",(unsigned long long)p->nr_sects);
 }
 
-static ssize_t part_stat_show(struct device *dev,
-                              struct device_attribute *attr, char *buf)
+ssize_t part_stat_show(struct device *dev,
+                       struct device_attribute *attr, char *buf)
 {
         struct hd_struct *p = dev_to_part(dev);
+        int cpu;
 
-        preempt_disable();
-        part_round_stats(p);
-        preempt_enable();
+        cpu = part_stat_lock();
+        part_round_stats(cpu, p);
+        part_stat_unlock();
         return sprintf(buf,
                 "%8lu %8lu %8llu %8u "
                 "%8lu %8lu %8llu %8u "
@@ -238,17 +246,17 @@ static ssize_t part_stat_show(struct device *dev,
 }
 
 #ifdef CONFIG_FAIL_MAKE_REQUEST
-static ssize_t part_fail_show(struct device *dev,
-                              struct device_attribute *attr, char *buf)
+ssize_t part_fail_show(struct device *dev,
+                       struct device_attribute *attr, char *buf)
 {
         struct hd_struct *p = dev_to_part(dev);
 
         return sprintf(buf, "%d\n", p->make_it_fail);
 }
 
-static ssize_t part_fail_store(struct device *dev,
-                               struct device_attribute *attr,
-                               const char *buf, size_t count)
+ssize_t part_fail_store(struct device *dev,
+                        struct device_attribute *attr,
+                        const char *buf, size_t count)
 {
         struct hd_struct *p = dev_to_part(dev);
         int i;
@@ -260,6 +268,7 @@ static ssize_t part_fail_store(struct device *dev,
 }
 #endif
 
+static DEVICE_ATTR(partition, S_IRUGO, part_partition_show, NULL);
 static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL);
 static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
 static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
@@ -269,6 +278,7 @@ static struct device_attribute dev_attr_fail =
 #endif
 
 static struct attribute *part_attrs[] = {
+        &dev_attr_partition.attr,
         &dev_attr_start.attr,
         &dev_attr_size.attr,
         &dev_attr_stat.attr,
@@ -300,40 +310,34 @@ struct device_type part_type = {
         .release        = part_release,
 };
 
-static inline void partition_sysfs_add_subdir(struct hd_struct *p)
+static void delete_partition_rcu_cb(struct rcu_head *head)
 {
-        struct kobject *k;
+        struct hd_struct *part = container_of(head, struct hd_struct, rcu_head);
 
-        k = kobject_get(&p->dev.kobj);
-        p->holder_dir = kobject_create_and_add("holders", k);
-        kobject_put(k);
+        part->start_sect = 0;
+        part->nr_sects = 0;
+        part_stat_set_all(part, 0);
+        put_device(part_to_dev(part));
 }
 
-static inline void disk_sysfs_add_subdirs(struct gendisk *disk)
+void delete_partition(struct gendisk *disk, int partno)
 {
-        struct kobject *k;
+        struct disk_part_tbl *ptbl = disk->part_tbl;
+        struct hd_struct *part;
 
-        k = kobject_get(&disk->dev.kobj);
-        disk->holder_dir = kobject_create_and_add("holders", k);
-        disk->slave_dir = kobject_create_and_add("slaves", k);
-        kobject_put(k);
-}
-
-void delete_partition(struct gendisk *disk, int part)
-{
-        struct hd_struct *p = disk->part[part-1];
-
-        if (!p)
+        if (partno >= ptbl->len)
                 return;
-        if (!p->nr_sects)
+
+        part = ptbl->part[partno];
+        if (!part)
                 return;
-        disk->part[part-1] = NULL;
-        p->start_sect = 0;
-        p->nr_sects = 0;
-        part_stat_set_all(p, 0);
-        kobject_put(p->holder_dir);
-        device_del(&p->dev);
-        put_device(&p->dev);
+
+        blk_free_devt(part_devt(part));
+        rcu_assign_pointer(ptbl->part[partno], NULL);
+        kobject_put(part->holder_dir);
+        device_del(part_to_dev(part));
+
+        call_rcu(&part->rcu_head, delete_partition_rcu_cb);
 }
 
 static ssize_t whole_disk_show(struct device *dev,
@@ -344,102 +348,132 @@ static ssize_t whole_disk_show(struct device *dev,
 static DEVICE_ATTR(whole_disk, S_IRUSR | S_IRGRP | S_IROTH,
                    whole_disk_show, NULL);
 
-int add_partition(struct gendisk *disk, int part, sector_t start, sector_t len, int flags)
+int add_partition(struct gendisk *disk, int partno,
+                  sector_t start, sector_t len, int flags)
 {
         struct hd_struct *p;
+        dev_t devt = MKDEV(0, 0);
+        struct device *ddev = disk_to_dev(disk);
+        struct device *pdev;
+        struct disk_part_tbl *ptbl;
+        const char *dname;
         int err;
 
+        err = disk_expand_part_tbl(disk, partno);
+        if (err)
+                return err;
+        ptbl = disk->part_tbl;
+
+        if (ptbl->part[partno])
+                return -EBUSY;
+
         p = kzalloc(sizeof(*p), GFP_KERNEL);
         if (!p)
                 return -ENOMEM;
 
         if (!init_part_stats(p)) {
                 err = -ENOMEM;
-                goto out0;
+                goto out_free;
         }
+        pdev = part_to_dev(p);
+
         p->start_sect = start;
         p->nr_sects = len;
-        p->partno = part;
-        p->policy = disk->policy;
+        p->partno = partno;
+        p->policy = get_disk_ro(disk);
 
-        if (isdigit(disk->dev.bus_id[strlen(disk->dev.bus_id)-1]))
-                snprintf(p->dev.bus_id, BUS_ID_SIZE,
-                "%sp%d", disk->dev.bus_id, part);
+        dname = dev_name(ddev);
+        if (isdigit(dname[strlen(dname) - 1]))
+                snprintf(pdev->bus_id, BUS_ID_SIZE, "%sp%d", dname, partno);
         else
-                snprintf(p->dev.bus_id, BUS_ID_SIZE,
-                         "%s%d", disk->dev.bus_id, part);
+                snprintf(pdev->bus_id, BUS_ID_SIZE, "%s%d", dname, partno);
+
+        device_initialize(pdev);
+        pdev->class = &block_class;
+        pdev->type = &part_type;
+        pdev->parent = ddev;
 
-        device_initialize(&p->dev);
-        p->dev.devt = MKDEV(disk->major, disk->first_minor + part);
-        p->dev.class = &block_class;
-        p->dev.type = &part_type;
-        p->dev.parent = &disk->dev;
-        disk->part[part-1] = p;
+        err = blk_alloc_devt(p, &devt);
+        if (err)
+                goto out_free;
+        pdev->devt = devt;
 
         /* delay uevent until 'holders' subdir is created */
-        p->dev.uevent_suppress = 1;
-        err = device_add(&p->dev);
+        pdev->uevent_suppress = 1;
+        err = device_add(pdev);
         if (err)
-                goto out1;
-        partition_sysfs_add_subdir(p);
-        p->dev.uevent_suppress = 0;
+                goto out_put;
+
+        err = -ENOMEM;
+        p->holder_dir = kobject_create_and_add("holders", &pdev->kobj);
+        if (!p->holder_dir)
+                goto out_del;
+
+        pdev->uevent_suppress = 0;
         if (flags & ADDPART_FLAG_WHOLEDISK) {
-                err = device_create_file(&p->dev, &dev_attr_whole_disk);
+                err = device_create_file(pdev, &dev_attr_whole_disk);
                 if (err)
-                        goto out2;
+                        goto out_del;
         }
 
+        /* everything is up and running, commence */
+        INIT_RCU_HEAD(&p->rcu_head);
+        rcu_assign_pointer(ptbl->part[partno], p);
+
         /* suppress uevent if the disk supresses it */
-        if (!disk->dev.uevent_suppress)
-                kobject_uevent(&p->dev.kobj, KOBJ_ADD);
+        if (!ddev->uevent_suppress)
+                kobject_uevent(&pdev->kobj, KOBJ_ADD);
 
         return 0;
 
-out2:
-        device_del(&p->dev);
-out1:
-        put_device(&p->dev);
-        free_part_stats(p);
-out0:
+out_free:
         kfree(p);
         return err;
+out_del:
+        kobject_put(p->holder_dir);
+        device_del(pdev);
+out_put:
+        put_device(pdev);
+        blk_free_devt(devt);
+        return err;
 }
 
 /* Not exported, helper to add_disk(). */
 void register_disk(struct gendisk *disk)
 {
+        struct device *ddev = disk_to_dev(disk);
         struct block_device *bdev;
+        struct disk_part_iter piter;
+        struct hd_struct *part;
         char *s;
-        int i;
-        struct hd_struct *p;
         int err;
 
-        disk->dev.parent = disk->driverfs_dev;
-        disk->dev.devt = MKDEV(disk->major, disk->first_minor);
+        ddev->parent = disk->driverfs_dev;
 
-        strlcpy(disk->dev.bus_id, disk->disk_name, BUS_ID_SIZE);
+        strlcpy(ddev->bus_id, disk->disk_name, BUS_ID_SIZE);
         /* ewww... some of these buggers have / in the name... */
-        s = strchr(disk->dev.bus_id, '/');
+        s = strchr(ddev->bus_id, '/');
         if (s)
                 *s = '!';
 
         /* delay uevents, until we scanned partition table */
-        disk->dev.uevent_suppress = 1;
+        ddev->uevent_suppress = 1;
 
-        if (device_add(&disk->dev))
+        if (device_add(ddev))
                 return;
 #ifndef CONFIG_SYSFS_DEPRECATED
-        err = sysfs_create_link(block_depr, &disk->dev.kobj,
-                                kobject_name(&disk->dev.kobj));
+        err = sysfs_create_link(block_depr, &ddev->kobj,
+                                kobject_name(&ddev->kobj));
         if (err) {
-                device_del(&disk->dev);
+                device_del(ddev);
                 return;
         }
 #endif
-        disk_sysfs_add_subdirs(disk);
+        disk->part0.holder_dir = kobject_create_and_add("holders", &ddev->kobj);
+        disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj);
 
         /* No minors to use for partitions */
-        if (disk->minors == 1)
+        if (!disk_partitionable(disk))
                 goto exit;
 
         /* No such device (e.g., media were just removed) */
@@ -458,50 +492,79 @@ void register_disk(struct gendisk *disk)
 
 exit:
         /* announce disk after possible partitions are created */
-        disk->dev.uevent_suppress = 0;
-        kobject_uevent(&disk->dev.kobj, KOBJ_ADD);
+        ddev->uevent_suppress = 0;
+        kobject_uevent(&ddev->kobj, KOBJ_ADD);
 
         /* announce possible partitions */
-        for (i = 1; i < disk->minors; i++) {
-                p = disk->part[i-1];
-                if (!p || !p->nr_sects)
-                        continue;
-                kobject_uevent(&p->dev.kobj, KOBJ_ADD);
-        }
+        disk_part_iter_init(&piter, disk, 0);
+        while ((part = disk_part_iter_next(&piter)))
+                kobject_uevent(&part_to_dev(part)->kobj, KOBJ_ADD);
+        disk_part_iter_exit(&piter);
 }
 
 int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
 {
+        struct disk_part_iter piter;
+        struct hd_struct *part;
         struct parsed_partitions *state;
-        int p, res;
+        int p, highest, res;
 
         if (bdev->bd_part_count)
                 return -EBUSY;
         res = invalidate_partition(disk, 0);
         if (res)
                 return res;
-        bdev->bd_invalidated = 0;
-        for (p = 1; p < disk->minors; p++)
-                delete_partition(disk, p);
+
+        disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
+        while ((part = disk_part_iter_next(&piter)))
+                delete_partition(disk, part->partno);
+        disk_part_iter_exit(&piter);
+
         if (disk->fops->revalidate_disk)
                 disk->fops->revalidate_disk(disk);
+        check_disk_size_change(disk, bdev);
+        bdev->bd_invalidated = 0;
         if (!get_capacity(disk) || !(state = check_partition(disk, bdev)))
                 return 0;
         if (IS_ERR(state))      /* I/O error reading the partition table */
                 return -EIO;
 
         /* tell userspace that the media / partition table may have changed */
-        kobject_uevent(&disk->dev.kobj, KOBJ_CHANGE);
+        kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE);
+
+        /* Detect the highest partition number and preallocate
+         * disk->part_tbl.  This is an optimization and not strictly
+         * necessary.
+         */
+        for (p = 1, highest = 0; p < state->limit; p++)
+                if (state->parts[p].size)
+                        highest = p;
 
+        disk_expand_part_tbl(disk, highest);
+
+        /* add partitions */
         for (p = 1; p < state->limit; p++) {
                 sector_t size = state->parts[p].size;
                 sector_t from = state->parts[p].from;
                 if (!size)
                         continue;
+                if (from >= get_capacity(disk)) {
+                        printk(KERN_WARNING
+                               "%s: p%d ignored, start %llu is behind the end of the disk\n",
+                               disk->disk_name, p, (unsigned long long) from);
+                        continue;
+                }
                 if (from + size > get_capacity(disk)) {
+                        /*
+                         * we can not ignore partitions of broken tables
+                         * created by for example camera firmware, but we
+                         * limit them to the end of the disk to avoid
+                         * creating invalid block devices
+                         */
                         printk(KERN_WARNING
-                                "%s: p%d exceeds device capacity\n",
-                                disk->disk_name, p);
+                               "%s: p%d size %llu limited to end of disk\n",
+                               disk->disk_name, p, (unsigned long long) size);
+                        size = get_capacity(disk) - from;
                 }
                 res = add_partition(disk, p, from, size, state->parts[p].flags);
                 if (res) {
@@ -541,25 +604,31 @@ EXPORT_SYMBOL(read_dev_sector);
 
 void del_gendisk(struct gendisk *disk)
 {
-        int p;
+        struct disk_part_iter piter;
+        struct hd_struct *part;
 
         /* invalidate stuff */
-        for (p = disk->minors - 1; p > 0; p--) {
-                invalidate_partition(disk, p);
-                delete_partition(disk, p);
+        disk_part_iter_init(&piter, disk,
+                             DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
+        while ((part = disk_part_iter_next(&piter))) {
+                invalidate_partition(disk, part->partno);
+                delete_partition(disk, part->partno);
         }
+        disk_part_iter_exit(&piter);
+
         invalidate_partition(disk, 0);
-        disk->capacity = 0;
+        blk_free_devt(disk_to_dev(disk)->devt);
+        set_capacity(disk, 0);
         disk->flags &= ~GENHD_FL_UP;
         unlink_gendisk(disk);
-        disk_stat_set_all(disk, 0);
-        disk->stamp = 0;
+        part_stat_set_all(&disk->part0, 0);
+        disk->part0.stamp = 0;
 
-        kobject_put(disk->holder_dir);
+        kobject_put(disk->part0.holder_dir);
         kobject_put(disk->slave_dir);
         disk->driverfs_dev = NULL;
 #ifndef CONFIG_SYSFS_DEPRECATED
-        sysfs_remove_link(block_depr, disk->dev.bus_id);
+        sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
 #endif
-        device_del(&disk->dev);
+        device_del(disk_to_dev(disk));
 }
diff --git a/fs/partitions/check.h b/fs/partitions/check.h
index 17ae8ecd9e8b..98dbe1a84528 100644
--- a/fs/partitions/check.h
+++ b/fs/partitions/check.h
@@ -5,15 +5,13 @@
  * add_gd_partition adds a partitions details to the devices partition
  * description.
  */
-enum { MAX_PART = 256 };
-
 struct parsed_partitions {
         char name[BDEVNAME_SIZE];
         struct {
                 sector_t from;
                 sector_t size;
                 int flags;
-        } parts[MAX_PART];
+        } parts[DISK_MAX_PARTS];
         int next;
         int limit;
 };
diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig
index 73cd7a418f06..50f8f0600f06 100644
--- a/fs/proc/Kconfig
+++ b/fs/proc/Kconfig
@@ -57,3 +57,13 @@ config PROC_SYSCTL
           As it is generally a good thing, you should say Y here unless
           building a kernel for install/rescue disks or your system is very
           limited in memory.
+
+config PROC_PAGE_MONITOR
+        default y
+        depends on PROC_FS && MMU
+        bool "Enable /proc page monitoring" if EMBEDDED
+        help
+          Various /proc files exist to monitor process memory utilization:
+          /proc/pid/smaps, /proc/pid/clear_refs, /proc/pid/pagemap,
+          /proc/kpagecount, and /proc/kpageflags. Disabling these
+          interfaces will reduce the size of the kernel by approximately 4kb.
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 71c9be59c9c2..bb9f4b05703d 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -86,11 +86,6 @@
 #include <asm/processor.h>
 #include "internal.h"
 
-/* Gcc optimizes away "strlen(x)" for constant x */
-#define ADDBUF(buffer, string) \
-do { memcpy(buffer, string, strlen(string)); \
-     buffer += strlen(string); } while (0)
-
 static inline void task_name(struct seq_file *m, struct task_struct *p)
 {
         int i;
@@ -261,7 +256,6 @@ static inline void task_sig(struct seq_file *m, struct task_struct *p)
         sigemptyset(&ignored);
         sigemptyset(&caught);
 
-        rcu_read_lock();
         if (lock_task_sighand(p, &flags)) {
                 pending = p->pending.signal;
                 shpending = p->signal->shared_pending.signal;
@@ -272,7 +266,6 @@ static inline void task_sig(struct seq_file *m, struct task_struct *p)
                 qlim = p->signal->rlim[RLIMIT_SIGPENDING].rlim_cur;
                 unlock_task_sighand(p, &flags);
         }
-        rcu_read_unlock();
 
         seq_printf(m, "Threads:\t%d\n", num_threads);
         seq_printf(m, "SigQ:\t%lu/%lu\n", qsize, qlim);
@@ -395,20 +388,20 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
                 /* add up live thread stats at the group level */
                 if (whole) {
+                        struct task_cputime cputime;
                         struct task_struct *t = task;
                         do {
                                 min_flt += t->min_flt;
                                 maj_flt += t->maj_flt;
-                                utime = cputime_add(utime, task_utime(t));
-                                stime = cputime_add(stime, task_stime(t));
                                 gtime = cputime_add(gtime, task_gtime(t));
                                 t = next_thread(t);
                         } while (t != task);
 
                         min_flt += sig->min_flt;
                         maj_flt += sig->maj_flt;
-                        utime = cputime_add(utime, sig->utime);
-                        stime = cputime_add(stime, sig->stime);
+                        thread_group_cputime(task, &cputime);
+                        utime = cputime.utime;
+                        stime = cputime.stime;
                         gtime = cputime_add(gtime, sig->gtime);
                 }
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index a28840b11b89..b5918ae8ca79 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -148,9 +148,6 @@ static unsigned int pid_entry_count_dirs(const struct pid_entry *entries,
         return count;
 }
 
-int maps_protect;
-EXPORT_SYMBOL(maps_protect);
-
 static struct fs_struct *get_fs_struct(struct task_struct *task)
 {
         struct fs_struct *fs;
@@ -164,7 +161,6 @@ static struct fs_struct *get_fs_struct(struct task_struct *task)
 
 static int get_nr_threads(struct task_struct *tsk)
 {
-        /* Must be called with the rcu_read_lock held */
         unsigned long flags;
         int count = 0;
 
@@ -471,14 +467,10 @@ static int proc_pid_limits(struct task_struct *task, char *buffer)
 
         struct rlimit rlim[RLIM_NLIMITS];
 
-        rcu_read_lock();
-        if (!lock_task_sighand(task,&flags)) {
-                rcu_read_unlock();
+        if (!lock_task_sighand(task, &flags))
                 return 0;
-        }
         memcpy(rlim, task->signal->rlim, sizeof(struct rlimit) * RLIM_NLIMITS);
         unlock_task_sighand(task, &flags);
-        rcu_read_unlock();
 
         /*
          * print the file header
@@ -2443,6 +2435,13 @@ static int proc_tgid_io_accounting(struct task_struct *task, char *buffer)
 }
 #endif /* CONFIG_TASK_IO_ACCOUNTING */
 
+static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns,
+                                struct pid *pid, struct task_struct *task)
+{
+        seq_printf(m, "%08x\n", task->personality);
+        return 0;
+}
+
 /*
  * Thread groups
  */
@@ -2459,6 +2458,7 @@ static const struct pid_entry tgid_base_stuff[] = {
         REG("environ",    S_IRUSR, environ),
         INF("auxv",       S_IRUSR, pid_auxv),
         ONE("status",     S_IRUGO, pid_status),
+        ONE("personality", S_IRUSR, pid_personality),
         INF("limits",     S_IRUSR, pid_limits),
 #ifdef CONFIG_SCHED_DEBUG
         REG("sched",      S_IRUGO|S_IWUSR, pid_sched),
@@ -2794,6 +2794,7 @@ static const struct pid_entry tid_base_stuff[] = {
         REG("environ",   S_IRUSR, environ),
         INF("auxv",      S_IRUSR, pid_auxv),
         ONE("status",    S_IRUGO, pid_status),
+        ONE("personality", S_IRUSR, pid_personality),
         INF("limits",    S_IRUSR, pid_limits),
 #ifdef CONFIG_SCHED_DEBUG
         REG("sched",     S_IRUGO|S_IWUSR, pid_sched),
@@ -3088,9 +3089,7 @@ static int proc_task_getattr(struct vfsmount *mnt, struct dentry *dentry, struct
         generic_fillattr(inode, stat);
 
         if (p) {
-                rcu_read_lock();
                 stat->nlink += get_nr_threads(p);
-                rcu_read_unlock();
                 put_task_struct(p);
         }
 
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 8bb03f056c28..c6b4fa7e3b49 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -342,7 +342,7 @@ static int proc_reg_open(struct inode *inode, struct file *file)
         if (!pde->proc_fops) {
                 spin_unlock(&pde->pde_unload_lock);
                 kfree(pdeo);
-                return rv;
+                return -EINVAL;
         }
         pde->pde_users++;
         open = pde->proc_fops->open;
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 442202314d53..3bfb7b8747b3 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -45,8 +45,6 @@ do {						\
 extern int nommu_vma_show(struct seq_file *, struct vm_area_struct *);
 #endif
 
-extern int maps_protect;
-
 extern int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns,
                                 struct pid *pid, struct task_struct *task);
 extern int proc_tgid_stat(struct seq_file *m, struct pid_namespace *ns,
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 29e20c6b1f7f..7ea52c79b2da 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -30,6 +30,7 @@
 #include <linux/mm.h>
 #include <linux/mmzone.h>
 #include <linux/pagemap.h>
+#include <linux/irq.h>
 #include <linux/interrupt.h>
 #include <linux/swap.h>
 #include <linux/slab.h>
@@ -45,7 +46,6 @@
 #include <linux/blkdev.h>
 #include <linux/hugetlb.h>
 #include <linux/jiffies.h>
-#include <linux/sysrq.h>
 #include <linux/vmalloc.h>
 #include <linux/crash_dump.h>
 #include <linux/pid_namespace.h>
@@ -68,7 +68,6 @@
 extern int get_hardware_list(char *);
 extern int get_stram_list(char *);
 extern int get_exec_domain_list(char *);
-extern int get_dma_list(char *);
 
 static int proc_calc_metrics(char *page, char **start, off_t off,
                                  int count, int *eof, int len)
@@ -138,6 +137,8 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
         unsigned long allowed;
         struct vmalloc_info vmi;
         long cached;
+        unsigned long pages[NR_LRU_LISTS];
+        int lru;
 
 /*
  * display in kilobytes.
@@ -156,51 +157,70 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
 
         get_vmalloc_info(&vmi);
 
+        for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
+                pages[lru] = global_page_state(NR_LRU_BASE + lru);
+
         /*
          * Tagged format, for easy grepping and expansion.
          */
         len = sprintf(page,
-                "MemTotal:     %8lu kB\n"
-                "MemFree:      %8lu kB\n"
-                "Buffers:      %8lu kB\n"
-                "Cached:       %8lu kB\n"
-                "SwapCached:   %8lu kB\n"
-                "Active:       %8lu kB\n"
-                "Inactive:     %8lu kB\n"
+                "MemTotal:       %8lu kB\n"
+                "MemFree:        %8lu kB\n"
+                "Buffers:        %8lu kB\n"
+                "Cached:         %8lu kB\n"
+                "SwapCached:     %8lu kB\n"
+                "Active:         %8lu kB\n"
+                "Inactive:       %8lu kB\n"
+                "Active(anon):   %8lu kB\n"
+                "Inactive(anon): %8lu kB\n"
+                "Active(file):   %8lu kB\n"
+                "Inactive(file): %8lu kB\n"
+#ifdef CONFIG_UNEVICTABLE_LRU
+                "Unevictable:    %8lu kB\n"
+                "Mlocked:        %8lu kB\n"
+#endif
 #ifdef CONFIG_HIGHMEM
-                "HighTotal:    %8lu kB\n"
-                "HighFree:     %8lu kB\n"
-                "LowTotal:     %8lu kB\n"
-                "LowFree:      %8lu kB\n"
+                "HighTotal:      %8lu kB\n"
+                "HighFree:       %8lu kB\n"
+                "LowTotal:       %8lu kB\n"
+                "LowFree:        %8lu kB\n"
 #endif
-                "SwapTotal:    %8lu kB\n"
-                "SwapFree:     %8lu kB\n"
-                "Dirty:        %8lu kB\n"
-                "Writeback:    %8lu kB\n"
-                "AnonPages:    %8lu kB\n"
-                "Mapped:       %8lu kB\n"
-                "Slab:         %8lu kB\n"
-                "SReclaimable: %8lu kB\n"
-                "SUnreclaim:   %8lu kB\n"
-                "PageTables:   %8lu kB\n"
+                "SwapTotal:      %8lu kB\n"
+                "SwapFree:       %8lu kB\n"
+                "Dirty:          %8lu kB\n"
+                "Writeback:      %8lu kB\n"
+                "AnonPages:      %8lu kB\n"
+                "Mapped:         %8lu kB\n"
+                "Slab:           %8lu kB\n"
+                "SReclaimable:   %8lu kB\n"
+                "SUnreclaim:     %8lu kB\n"
+                "PageTables:     %8lu kB\n"
 #ifdef CONFIG_QUICKLIST
-                "Quicklists:   %8lu kB\n"
+                "Quicklists:     %8lu kB\n"
 #endif
-                "NFS_Unstable: %8lu kB\n"
-                "Bounce:       %8lu kB\n"
-                "WritebackTmp: %8lu kB\n"
-                "CommitLimit:  %8lu kB\n"
-                "Committed_AS: %8lu kB\n"
-                "VmallocTotal: %8lu kB\n"
-                "VmallocUsed:  %8lu kB\n"
-                "VmallocChunk: %8lu kB\n",
+                "NFS_Unstable:   %8lu kB\n"
+                "Bounce:         %8lu kB\n"
+                "WritebackTmp:   %8lu kB\n"
+                "CommitLimit:    %8lu kB\n"
+                "Committed_AS:   %8lu kB\n"
+                "VmallocTotal:   %8lu kB\n"
+                "VmallocUsed:    %8lu kB\n"
+                "VmallocChunk:   %8lu kB\n",
                 K(i.totalram),
                 K(i.freeram),
                 K(i.bufferram),
                 K(cached),
                 K(total_swapcache_pages),
-                K(global_page_state(NR_ACTIVE)),
-                K(global_page_state(NR_INACTIVE)),
+                K(pages[LRU_ACTIVE_ANON]   + pages[LRU_ACTIVE_FILE]),
+                K(pages[LRU_INACTIVE_ANON] + pages[LRU_INACTIVE_FILE]),
+                K(pages[LRU_ACTIVE_ANON]),
+                K(pages[LRU_INACTIVE_ANON]),
+                K(pages[LRU_ACTIVE_FILE]),
+                K(pages[LRU_INACTIVE_FILE]),
+#ifdef CONFIG_UNEVICTABLE_LRU
+                K(pages[LRU_UNEVICTABLE]),
+                K(global_page_state(NR_MLOCK)),
+#endif
 #ifdef CONFIG_HIGHMEM
                 K(i.totalhigh),
                 K(i.freehigh),
@@ -502,17 +522,13 @@ static const struct file_operations proc_vmalloc_operations = {
 
 static int show_stat(struct seq_file *p, void *v)
 {
-        int i;
+        int i, j;
         unsigned long jif;
         cputime64_t user, nice, system, idle, iowait, irq, softirq, steal;
         cputime64_t guest;
         u64 sum = 0;
         struct timespec boottime;
-        unsigned int *per_irq_sum;
-
-        per_irq_sum = kzalloc(sizeof(unsigned int)*NR_IRQS, GFP_KERNEL);
-        if (!per_irq_sum)
-                return -ENOMEM;
+        unsigned int per_irq_sum;
 
         user = nice = system = idle = iowait =
                 irq = softirq = steal = cputime64_zero;
@@ -521,8 +537,6 @@ static int show_stat(struct seq_file *p, void *v)
         jif = boottime.tv_sec;
 
         for_each_possible_cpu(i) {
-                int j;
-
                 user = cputime64_add(user, kstat_cpu(i).cpustat.user);
                 nice = cputime64_add(nice, kstat_cpu(i).cpustat.nice);
                 system = cputime64_add(system, kstat_cpu(i).cpustat.system);
@@ -532,11 +546,10 @@ static int show_stat(struct seq_file *p, void *v)
                 softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq);
                 steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal);
                 guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest);
-                for (j = 0; j < NR_IRQS; j++) {
-                        unsigned int temp = kstat_cpu(i).irqs[j];
-                        sum += temp;
-                        per_irq_sum[j] += temp;
-                }
+
+                for_each_irq_nr(j)
+                        sum += kstat_irqs_cpu(j, i);
+
                 sum += arch_irq_stat_cpu(i);
         }
         sum += arch_irq_stat();
@@ -578,8 +591,15 @@ static int show_stat(struct seq_file *p, void *v)
         }
         seq_printf(p, "intr %llu", (unsigned long long)sum);
 
-        for (i = 0; i < NR_IRQS; i++)
-                seq_printf(p, " %u", per_irq_sum[i]);
+        /* sum again ? it could be updated? */
+        for_each_irq_nr(j) {
+                per_irq_sum = 0;
+
+                for_each_possible_cpu(i)
+                        per_irq_sum += kstat_irqs_cpu(j, i);
+
+                seq_printf(p, " %u", per_irq_sum);
+        }
 
         seq_printf(p,
                 "\nctxt %llu\n"
@@ -593,7 +613,6 @@ static int show_stat(struct seq_file *p, void *v)
                 nr_running(),
                 nr_iowait());
 
-        kfree(per_irq_sum);
         return 0;
 }
 
@@ -632,15 +651,14 @@ static const struct file_operations proc_stat_operations = {
  */
 static void *int_seq_start(struct seq_file *f, loff_t *pos)
 {
-        return (*pos <= NR_IRQS) ? pos : NULL;
+        return (*pos <= nr_irqs) ? pos : NULL;
 }
 
+
 static void *int_seq_next(struct seq_file *f, void *v, loff_t *pos)
 {
         (*pos)++;
-        if (*pos > NR_IRQS)
-                return NULL;
-        return pos;
+        return (*pos <= nr_irqs) ? pos : NULL;
 }
 
 static void int_seq_stop(struct seq_file *f, void *v)
@@ -648,7 +666,6 @@ static void int_seq_stop(struct seq_file *f, void *v)
         /* Nothing to do */
 }
 
-
 static const struct seq_operations int_seq_ops = {
         .start = int_seq_start,
         .next  = int_seq_next,
@@ -684,6 +701,7 @@ static int cmdline_read_proc(char *page, char **start, off_t off,
         return proc_calc_metrics(page, start, off, count, eof, len);
 }
 
+#ifdef CONFIG_FILE_LOCKING
 static int locks_open(struct inode *inode, struct file *filp)
 {
         return seq_open(filp, &locks_seq_operations);
@@ -695,6 +713,7 @@ static const struct file_operations proc_locks_operations = {
         .llseek         = seq_lseek,
         .release        = seq_release,
 };
+#endif /* CONFIG_FILE_LOCKING */
 
 static int execdomains_read_proc(char *page, char **start, off_t off,
                                  int count, int *eof, void *data)
@@ -703,28 +722,6 @@ static int execdomains_read_proc(char *page, char **start, off_t off,
         return proc_calc_metrics(page, start, off, count, eof, len);
 }
 
-#ifdef CONFIG_MAGIC_SYSRQ
-/*
- * writing 'C' to /proc/sysrq-trigger is like sysrq-C
- */
-static ssize_t write_sysrq_trigger(struct file *file, const char __user *buf,
-                                   size_t count, loff_t *ppos)
-{
-        if (count) {
-                char c;
-
-                if (get_user(c, buf))
-                        return -EFAULT;
-                __handle_sysrq(c, NULL, 0);
-        }
-        return count;
-}
-
-static const struct file_operations proc_sysrq_trigger_operations = {
-        .write          = write_sysrq_trigger,
-};
-#endif
-
 #ifdef CONFIG_PROC_PAGE_MONITOR
 #define KPMSIZE sizeof(u64)
 #define KPMMASK (KPMSIZE - 1)
@@ -888,7 +885,9 @@ void __init proc_misc_init(void)
 #ifdef CONFIG_PRINTK
         proc_create("kmsg", S_IRUSR, NULL, &proc_kmsg_operations);
 #endif
+#ifdef CONFIG_FILE_LOCKING
         proc_create("locks", 0, NULL, &proc_locks_operations);
+#endif
         proc_create("devices", 0, NULL, &proc_devinfo_operations);
         proc_create("cpuinfo", 0, NULL, &proc_cpuinfo_operations);
 #ifdef CONFIG_BLOCK
@@ -931,7 +930,4 @@ void __init proc_misc_init(void)
 #ifdef CONFIG_PROC_VMCORE
         proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &proc_vmcore_operations);
 #endif
-#ifdef CONFIG_MAGIC_SYSRQ
-        proc_create("sysrq-trigger", S_IWUSR, NULL, &proc_sysrq_trigger_operations);
-#endif
 }
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index f9a8b892718f..945a81043ba2 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -66,7 +66,7 @@ static struct ctl_table *find_in_table(struct ctl_table *p, struct qstr *name)
         return NULL;
 }
 
-struct ctl_table_header *grab_header(struct inode *inode)
+static struct ctl_table_header *grab_header(struct inode *inode)
 {
         if (PROC_I(inode)->sysctl)
                 return sysctl_head_grab(PROC_I(inode)->sysctl);
@@ -395,10 +395,10 @@ static struct dentry_operations proc_sys_dentry_operations = {
         .d_compare      = proc_sys_compare,
 };
 
-static struct proc_dir_entry *proc_sys_root;
-
 int proc_sys_init(void)
 {
+        struct proc_dir_entry *proc_sys_root;
+
         proc_sys_root = proc_mkdir("sys", NULL);
         proc_sys_root->proc_iops = &proc_sys_dir_operations;
         proc_sys_root->proc_fops = &proc_sys_dir_file_operations;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 73d1891ee625..4806830ea2a1 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -210,9 +210,6 @@ static int show_map(struct seq_file *m, void *v)
         dev_t dev = 0;
         int len;
 
-        if (maps_protect && !ptrace_may_access(task, PTRACE_MODE_READ))
-                return -EACCES;
-
         if (file) {
                 struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
                 dev = inode->i_sb->s_dev;
@@ -742,22 +739,11 @@ const struct file_operations proc_pagemap_operations = {
 #ifdef CONFIG_NUMA
 extern int show_numa_map(struct seq_file *m, void *v);
 
-static int show_numa_map_checked(struct seq_file *m, void *v)
-{
-        struct proc_maps_private *priv = m->private;
-        struct task_struct *task = priv->task;
-
-        if (maps_protect && !ptrace_may_access(task, PTRACE_MODE_READ))
-                return -EACCES;
-
-        return show_numa_map(m, v);
-}
-
 static const struct seq_operations proc_pid_numa_maps_op = {
         .start  = m_start,
         .next   = m_next,
         .stop   = m_stop,
-        .show   = show_numa_map_checked
+        .show   = show_numa_map,
 };
 
 static int numa_maps_open(struct inode *inode, struct file *file)
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 5d84e7121df8..219bd79ea894 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -110,11 +110,6 @@ int task_statm(struct mm_struct *mm, int *shared, int *text,
 static int show_map(struct seq_file *m, void *_vml)
 {
         struct vm_list_struct *vml = _vml;
-        struct proc_maps_private *priv = m->private;
-        struct task_struct *task = priv->task;
-
-        if (maps_protect && !ptrace_may_access(task, PTRACE_MODE_READ))
-                return -EACCES;
 
         return nommu_vma_show(m, vml->vma);
 }
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 9ac0f5e064e0..cd9ca67f841b 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -32,9 +32,6 @@ static size_t elfcorebuf_sz;
 /* Total size of vmcore file. */
 static u64 vmcore_size;
 
-/* Stores the physical address of elf header of crash image. */
-unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
-
 struct proc_dir_entry *proc_vmcore = NULL;
 
 /* Reads a page from the oldmem device from given offset. */
@@ -165,14 +162,8 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
         return acc;
 }
 
-static int open_vmcore(struct inode *inode, struct file *filp)
-{
-        return 0;
-}
-
 const struct file_operations proc_vmcore_operations = {
         .read           = read_vmcore,
-        .open           = open_vmcore,
 };
 
 static struct vmcore* __init get_new_element(void)
@@ -653,7 +644,7 @@ static int __init vmcore_init(void)
         int rc = 0;
 
         /* If elfcorehdr= has been passed in cmdline, then capture the dump.*/
-        if (!(elfcorehdr_addr < ELFCORE_ADDR_MAX))
+        if (!(is_vmcore_usable()))
                 return rc;
         rc = parse_crash_elf_headers();
         if (rc) {
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index 5145cb9125af..76acdbc34611 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -112,12 +112,12 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize)
                         goto add_error;
 
                 if (!pagevec_add(&lru_pvec, page))
-                        __pagevec_lru_add(&lru_pvec);
+                        __pagevec_lru_add_file(&lru_pvec);
 
                 unlock_page(page);
         }
 
-        pagevec_lru_add(&lru_pvec);
+        pagevec_lru_add_file(&lru_pvec);
         return 0;
 
  fsize_exceeded:
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index b13123424e49..f031d1c925f0 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -61,6 +61,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, int mode, dev_t dev)
                 inode->i_mapping->a_ops = &ramfs_aops;
                 inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info;
                 mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
+                mapping_set_unevictable(inode->i_mapping);
                 inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
                 switch (mode & S_IFMT) {
                 default:
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index b9dbeeca7049..37173fa07d15 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -8,8 +8,6 @@
 
 /* proc info support a la one created by Sizif@Botik.RU for PGC */
 
-/* $Id: procfs.c,v 1.1.8.2 2001/07/15 17:08:42 god Exp $ */
-
 #include <linux/module.h>
 #include <linux/time.h>
 #include <linux/seq_file.h>
@@ -621,7 +619,6 @@ int reiserfs_global_version_in_proc(char *buffer, char **start,
 #endif
 
 /*
- * $Log: procfs.c,v $
  * Revision 1.1.8.2  2001/07/15 17:08:42  god
  *  . use get_super() in procfs.c
  *  . remove remove_save_link() from reiserfs_do_truncate()
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index bb3cb5b7cdb2..ad92461cbfc3 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -155,7 +155,7 @@ static struct dentry *get_xa_file_dentry(const struct inode *inode,
         xadir = open_xa_dir(inode, flags);
         if (IS_ERR(xadir)) {
                 return ERR_CAST(xadir);
-        } else if (xadir && !xadir->d_inode) {
+        } else if (!xadir->d_inode) {
                 dput(xadir);
                 return ERR_PTR(-ENODATA);
         }
diff --git a/fs/seq_file.c b/fs/seq_file.c
index bd20f7f5a933..eba2eabcd2b8 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -452,17 +452,34 @@ int seq_dentry(struct seq_file *m, struct dentry *dentry, char *esc)
 
 int seq_bitmap(struct seq_file *m, unsigned long *bits, unsigned int nr_bits)
 {
-        size_t len = bitmap_scnprintf_len(nr_bits);
+        if (m->count < m->size) {
+                int len = bitmap_scnprintf(m->buf + m->count,
+                                m->size - m->count, bits, nr_bits);
+                if (m->count + len < m->size) {
+                        m->count += len;
+                        return 0;
+                }
+        }
+        m->count = m->size;
+        return -1;
+}
+EXPORT_SYMBOL(seq_bitmap);
 
-        if (m->count + len < m->size) {
-                bitmap_scnprintf(m->buf + m->count, m->size - m->count,
-                                 bits, nr_bits);
-                m->count += len;
-                return 0;
+int seq_bitmap_list(struct seq_file *m, unsigned long *bits,
+                unsigned int nr_bits)
+{
+        if (m->count < m->size) {
+                int len = bitmap_scnlistprintf(m->buf + m->count,
+                                m->size - m->count, bits, nr_bits);
+                if (m->count + len < m->size) {
+                        m->count += len;
+                        return 0;
+                }
         }
         m->count = m->size;
         return -1;
 }
+EXPORT_SYMBOL(seq_bitmap_list);
 
 static void *single_start(struct seq_file *p, loff_t *pos)
 {
diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c
index 006fc64227dd..66f6e58a7e4b 100644
--- a/fs/sysfs/bin.c
+++ b/fs/sysfs/bin.c
@@ -61,6 +61,7 @@ read(struct file *file, char __user *userbuf, size_t bytes, loff_t *off)
         int size = dentry->d_inode->i_size;
         loff_t offs = *off;
         int count = min_t(size_t, bytes, PAGE_SIZE);
+        char *temp;
 
         if (size) {
                 if (offs > size)
@@ -69,23 +70,33 @@ read(struct file *file, char __user *userbuf, size_t bytes, loff_t *off)
                         count = size - offs;
         }
 
+        temp = kmalloc(count, GFP_KERNEL);
+        if (!temp)
+                return -ENOMEM;
+
         mutex_lock(&bb->mutex);
 
         count = fill_read(dentry, bb->buffer, offs, count);
-        if (count < 0)
-                goto out_unlock;
+        if (count < 0) {
+                mutex_unlock(&bb->mutex);
+                goto out_free;
+        }
 
-        if (copy_to_user(userbuf, bb->buffer, count)) {
+        memcpy(temp, bb->buffer, count);
+
+        mutex_unlock(&bb->mutex);
+
+        if (copy_to_user(userbuf, temp, count)) {
                 count = -EFAULT;
-                goto out_unlock;
+                goto out_free;
         }
 
         pr_debug("offs = %lld, *off = %lld, count = %d\n", offs, *off, count);
 
         *off = offs + count;
 
- out_unlock:
-        mutex_unlock(&bb->mutex);
+ out_free:
+        kfree(temp);
         return count;
 }
 
@@ -118,6 +129,7 @@ static ssize_t write(struct file *file, const char __user *userbuf,
         int size = dentry->d_inode->i_size;
         loff_t offs = *off;
         int count = min_t(size_t, bytes, PAGE_SIZE);
+        char *temp;
 
         if (size) {
                 if (offs > size)
@@ -126,19 +138,27 @@ static ssize_t write(struct file *file, const char __user *userbuf,
                         count = size - offs;
         }
 
-        mutex_lock(&bb->mutex);
+        temp = kmalloc(count, GFP_KERNEL);
+        if (!temp)
+                return -ENOMEM;
 
-        if (copy_from_user(bb->buffer, userbuf, count)) {
+        if (copy_from_user(temp, userbuf, count)) {
                 count = -EFAULT;
-                goto out_unlock;
+                goto out_free;
         }
 
+        mutex_lock(&bb->mutex);
+
+        memcpy(bb->buffer, temp, count);
+
         count = flush_write(dentry, bb->buffer, offs, count);
+        mutex_unlock(&bb->mutex);
+
         if (count > 0)
                 *off = offs + count;
 
- out_unlock:
-        mutex_unlock(&bb->mutex);
+out_free:
+        kfree(temp);
         return count;
 }
 
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index aedaeba82ae5..3a05a596e3b4 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -370,17 +370,17 @@ void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
         memset(acxt, 0, sizeof(*acxt));
         acxt->parent_sd = parent_sd;
 
-        /* Lookup parent inode.  inode initialization and I_NEW
-         * clearing are protected by sysfs_mutex.  By grabbing it and
-         * looking up with _nowait variant, inode state can be
-         * determined reliably.
+        /* Lookup parent inode.  inode initialization is protected by
+         * sysfs_mutex, so inode existence can be determined by
+         * looking up inode while holding sysfs_mutex.
          */
         mutex_lock(&sysfs_mutex);
 
-        inode = ilookup5_nowait(sysfs_sb, parent_sd->s_ino, sysfs_ilookup_test,
-                                parent_sd);
+        inode = ilookup5(sysfs_sb, parent_sd->s_ino, sysfs_ilookup_test,
+                         parent_sd);
+        if (inode) {
+                WARN_ON(inode->i_state & I_NEW);
 
-        if (inode && !(inode->i_state & I_NEW)) {
                 /* parent inode available */
                 acxt->parent_inode = inode;
 
@@ -393,8 +393,7 @@ void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
                         mutex_lock(&inode->i_mutex);
                         mutex_lock(&sysfs_mutex);
                 }
-        } else
-                iput(inode);
+        }
 }
 
 /**
@@ -636,6 +635,7 @@ struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd,
 
         return sd;
 }
+EXPORT_SYMBOL_GPL(sysfs_get_dirent);
 
 static int create_dir(struct kobject *kobj, struct sysfs_dirent *parent_sd,
                       const char *name, struct sysfs_dirent **p_sd)
@@ -829,16 +829,12 @@ int sysfs_rename_dir(struct kobject * kobj, const char *new_name)
         if (!new_dentry)
                 goto out_unlock;
 
-        /* rename kobject and sysfs_dirent */
+        /* rename sysfs_dirent */
         error = -ENOMEM;
         new_name = dup_name = kstrdup(new_name, GFP_KERNEL);
         if (!new_name)
                 goto out_unlock;
 
-        error = kobject_set_name(kobj, "%s", new_name);
-        if (error)
-                goto out_unlock;
-
         dup_name = sd->s_name;
         sd->s_name = new_name;
 
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index c9e4e5091da1..1f4a3f877262 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -19,10 +19,18 @@
 #include <linux/poll.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
+#include <linux/limits.h>
 #include <asm/uaccess.h>
 
 #include "sysfs.h"
 
+/* used in crash dumps to help with debugging */
+static char last_sysfs_file[PATH_MAX];
+void sysfs_printk_last_file(void)
+{
+        printk(KERN_EMERG "last sysfs file: %s\n", last_sysfs_file);
+}
+
 /*
  * There's one sysfs_buffer for each open file and one
  * sysfs_open_dirent for each sysfs_dirent with one or more open
@@ -328,6 +336,11 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
         struct sysfs_buffer *buffer;
         struct sysfs_ops *ops;
         int error = -EACCES;
+        char *p;
+
+        p = d_path(&file->f_path, last_sysfs_file, sizeof(last_sysfs_file));
+        if (p)
+                memmove(last_sysfs_file, p, strlen(p) + 1);
 
         /* need attr_sd for attr and ops, its parent for kobj */
         if (!sysfs_get_active_two(attr_sd))
@@ -440,7 +453,23 @@ static unsigned int sysfs_poll(struct file *filp, poll_table *wait)
         return POLLERR|POLLPRI;
 }
 
-void sysfs_notify(struct kobject *k, char *dir, char *attr)
+void sysfs_notify_dirent(struct sysfs_dirent *sd)
+{
+        struct sysfs_open_dirent *od;
+
+        spin_lock(&sysfs_open_dirent_lock);
+
+        od = sd->s_attr.open;
+        if (od) {
+                atomic_inc(&od->event);
+                wake_up_interruptible(&od->poll);
+        }
+
+        spin_unlock(&sysfs_open_dirent_lock);
+}
+EXPORT_SYMBOL_GPL(sysfs_notify_dirent);
+
+void sysfs_notify(struct kobject *k, const char *dir, const char *attr)
 {
         struct sysfs_dirent *sd = k->sd;
 
@@ -450,19 +479,8 @@ void sysfs_notify(struct kobject *k, char *dir, char *attr)
                 sd = sysfs_find_dirent(sd, dir);
         if (sd && attr)
                 sd = sysfs_find_dirent(sd, attr);
-        if (sd) {
-                struct sysfs_open_dirent *od;
-
-                spin_lock(&sysfs_open_dirent_lock);
-
-                od = sd->s_attr.open;
-                if (od) {
-                        atomic_inc(&od->event);
-                        wake_up_interruptible(&od->poll);
-                }
-
-                spin_unlock(&sysfs_open_dirent_lock);
-        }
+        if (sd)
+                sysfs_notify_dirent(sd);
 
         mutex_unlock(&sysfs_mutex);
 }
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 14f0023984d7..ab343e371d64 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -16,6 +16,7 @@
 #include <linux/mount.h>
 #include <linux/pagemap.h>
 #include <linux/init.h>
+#include <linux/module.h>
 
 #include "sysfs.h"
 
@@ -115,3 +116,17 @@ out_err:
         sysfs_dir_cachep = NULL;
         goto out;
 }
+
+#undef sysfs_get
+struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd)
+{
+        return __sysfs_get(sd);
+}
+EXPORT_SYMBOL_GPL(sysfs_get);
+
+#undef sysfs_put
+void sysfs_put(struct sysfs_dirent *sd)
+{
+        __sysfs_put(sd);
+}
+EXPORT_SYMBOL_GPL(sysfs_put);
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index a5db496f71c7..93c6d6b27c4d 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -124,7 +124,7 @@ int sysfs_create_subdir(struct kobject *kobj, const char *name,
                         struct sysfs_dirent **p_sd);
 void sysfs_remove_subdir(struct sysfs_dirent *sd);
 
-static inline struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd)
+static inline struct sysfs_dirent *__sysfs_get(struct sysfs_dirent *sd)
 {
         if (sd) {
                 WARN_ON(!atomic_read(&sd->s_count));
@@ -132,12 +132,14 @@ static inline struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd)
         }
         return sd;
 }
+#define sysfs_get(sd) __sysfs_get(sd)
 
-static inline void sysfs_put(struct sysfs_dirent *sd)
+static inline void __sysfs_put(struct sysfs_dirent *sd)
 {
         if (sd && atomic_dec_and_test(&sd->s_count))
                 release_sysfs_dirent(sd);
 }
+#define sysfs_put(sd) __sysfs_put(sd)
 
 /*
  * inode.c
diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c
index 73db464cd08b..1a4973e10664 100644
--- a/fs/ubifs/budget.c
+++ b/fs/ubifs/budget.c
@@ -414,19 +414,21 @@ static int do_budget_space(struct ubifs_info *c)
          *    @c->lst.empty_lebs + @c->freeable_cnt + @c->idx_gc_cnt -
          *    @c->lst.taken_empty_lebs
          *
-         * @empty_lebs are available because they are empty. @freeable_cnt are
-         * available because they contain only free and dirty space and the
-         * index allocation always occurs after wbufs are synch'ed.
-         * @idx_gc_cnt are available because they are index LEBs that have been
-         * garbage collected (including trivial GC) and are awaiting the commit
-         * before they can be unmapped - note that the in-the-gaps method will
-         * grab these if it needs them. @taken_empty_lebs are empty_lebs that
-         * have already been allocated for some purpose (also includes those
-         * LEBs on the @idx_gc list).
+         * @c->lst.empty_lebs are available because they are empty.
+         * @c->freeable_cnt are available because they contain only free and
+         * dirty space, @c->idx_gc_cnt are available because they are index
+         * LEBs that have been garbage collected and are awaiting the commit
+         * before they can be used. And the in-the-gaps method will grab these
+         * if it needs them. @c->lst.taken_empty_lebs are empty LEBs that have
+         * already been allocated for some purpose.
          *
-         * Note, @taken_empty_lebs may temporarily be higher by one because of
-         * the way we serialize LEB allocations and budgeting. See a comment in
-         * 'ubifs_find_free_space()'.
+         * Note, @c->idx_gc_cnt is included to both @c->lst.empty_lebs (because
+         * these LEBs are empty) and to @c->lst.taken_empty_lebs (because they
+         * are taken until after the commit).
+         *
+         * Note, @c->lst.taken_empty_lebs may temporarily be higher by one
+         * because of the way we serialize LEB allocations and budgeting. See a
+         * comment in 'ubifs_find_free_space()'.
          */
         lebs = c->lst.empty_lebs + c->freeable_cnt + c->idx_gc_cnt -
                c->lst.taken_empty_lebs;
diff --git a/fs/ubifs/compress.c b/fs/ubifs/compress.c
index 5bb51dac3c16..a0ada596b17c 100644
--- a/fs/ubifs/compress.c
+++ b/fs/ubifs/compress.c
@@ -91,8 +91,6 @@ struct ubifs_compressor *ubifs_compressors[UBIFS_COMPR_TYPES_CNT];
  *
  * Note, if the input buffer was not compressed, it is copied to the output
  * buffer and %UBIFS_COMPR_NONE is returned in @compr_type.
- *
- * This functions returns %0 on success or a negative error code on failure.
  */
 void ubifs_compress(const void *in_buf, int in_len, void *out_buf, int *out_len,
                     int *compr_type)
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index d7f7645779f2..7186400750e7 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -222,30 +222,38 @@ void dbg_dump_inode(const struct ubifs_info *c, const struct inode *inode)
 {
         const struct ubifs_inode *ui = ubifs_inode(inode);
 
-        printk(KERN_DEBUG "inode      %lu\n", inode->i_ino);
-        printk(KERN_DEBUG "size       %llu\n",
+        printk(KERN_DEBUG "Dump in-memory inode:");
+        printk(KERN_DEBUG "\tinode          %lu\n", inode->i_ino);
+        printk(KERN_DEBUG "\tsize           %llu\n",
                (unsigned long long)i_size_read(inode));
-        printk(KERN_DEBUG "nlink      %u\n", inode->i_nlink);
-        printk(KERN_DEBUG "uid        %u\n", (unsigned int)inode->i_uid);
-        printk(KERN_DEBUG "gid        %u\n", (unsigned int)inode->i_gid);
-        printk(KERN_DEBUG "atime      %u.%u\n",
+        printk(KERN_DEBUG "\tnlink          %u\n", inode->i_nlink);
+        printk(KERN_DEBUG "\tuid            %u\n", (unsigned int)inode->i_uid);
+        printk(KERN_DEBUG "\tgid            %u\n", (unsigned int)inode->i_gid);
+        printk(KERN_DEBUG "\tatime          %u.%u\n",
                (unsigned int)inode->i_atime.tv_sec,
                (unsigned int)inode->i_atime.tv_nsec);
-        printk(KERN_DEBUG "mtime      %u.%u\n",
+        printk(KERN_DEBUG "\tmtime          %u.%u\n",
                (unsigned int)inode->i_mtime.tv_sec,
                (unsigned int)inode->i_mtime.tv_nsec);
-        printk(KERN_DEBUG "ctime       %u.%u\n",
+        printk(KERN_DEBUG "\tctime          %u.%u\n",
                (unsigned int)inode->i_ctime.tv_sec,
                (unsigned int)inode->i_ctime.tv_nsec);
-        printk(KERN_DEBUG "creat_sqnum %llu\n", ui->creat_sqnum);
-        printk(KERN_DEBUG "xattr_size  %u\n", ui->xattr_size);
-        printk(KERN_DEBUG "xattr_cnt   %u\n", ui->xattr_cnt);
-        printk(KERN_DEBUG "xattr_names %u\n", ui->xattr_names);
-        printk(KERN_DEBUG "dirty       %u\n", ui->dirty);
-        printk(KERN_DEBUG "xattr       %u\n", ui->xattr);
-        printk(KERN_DEBUG "flags       %d\n", ui->flags);
-        printk(KERN_DEBUG "compr_type  %d\n", ui->compr_type);
-        printk(KERN_DEBUG "data_len    %d\n", ui->data_len);
+        printk(KERN_DEBUG "\tcreat_sqnum    %llu\n", ui->creat_sqnum);
+        printk(KERN_DEBUG "\txattr_size     %u\n", ui->xattr_size);
+        printk(KERN_DEBUG "\txattr_cnt      %u\n", ui->xattr_cnt);
+        printk(KERN_DEBUG "\txattr_names    %u\n", ui->xattr_names);
+        printk(KERN_DEBUG "\tdirty          %u\n", ui->dirty);
+        printk(KERN_DEBUG "\txattr          %u\n", ui->xattr);
+        printk(KERN_DEBUG "\tbulk_read      %u\n", ui->xattr);
+        printk(KERN_DEBUG "\tsynced_i_size  %llu\n",
+               (unsigned long long)ui->synced_i_size);
+        printk(KERN_DEBUG "\tui_size        %llu\n",
+               (unsigned long long)ui->ui_size);
+        printk(KERN_DEBUG "\tflags          %d\n", ui->flags);
+        printk(KERN_DEBUG "\tcompr_type     %d\n", ui->compr_type);
+        printk(KERN_DEBUG "\tlast_page_read %lu\n", ui->last_page_read);
+        printk(KERN_DEBUG "\tread_in_a_row  %lu\n", ui->read_in_a_row);
+        printk(KERN_DEBUG "\tdata_len       %d\n", ui->data_len);
 }
 
 void dbg_dump_node(const struct ubifs_info *c, const void *node)
@@ -647,6 +655,43 @@ void dbg_dump_lprops(struct ubifs_info *c)
         }
 }
 
+void dbg_dump_lpt_info(struct ubifs_info *c)
+{
+        int i;
+
+        spin_lock(&dbg_lock);
+        printk(KERN_DEBUG "\tlpt_sz:        %lld\n", c->lpt_sz);
+        printk(KERN_DEBUG "\tpnode_sz:      %d\n", c->pnode_sz);
+        printk(KERN_DEBUG "\tnnode_sz:      %d\n", c->nnode_sz);
+        printk(KERN_DEBUG "\tltab_sz:       %d\n", c->ltab_sz);
+        printk(KERN_DEBUG "\tlsave_sz:      %d\n", c->lsave_sz);
+        printk(KERN_DEBUG "\tbig_lpt:       %d\n", c->big_lpt);
+        printk(KERN_DEBUG "\tlpt_hght:      %d\n", c->lpt_hght);
+        printk(KERN_DEBUG "\tpnode_cnt:     %d\n", c->pnode_cnt);
+        printk(KERN_DEBUG "\tnnode_cnt:     %d\n", c->nnode_cnt);
+        printk(KERN_DEBUG "\tdirty_pn_cnt:  %d\n", c->dirty_pn_cnt);
+        printk(KERN_DEBUG "\tdirty_nn_cnt:  %d\n", c->dirty_nn_cnt);
+        printk(KERN_DEBUG "\tlsave_cnt:     %d\n", c->lsave_cnt);
+        printk(KERN_DEBUG "\tspace_bits:    %d\n", c->space_bits);
+        printk(KERN_DEBUG "\tlpt_lnum_bits: %d\n", c->lpt_lnum_bits);
+        printk(KERN_DEBUG "\tlpt_offs_bits: %d\n", c->lpt_offs_bits);
+        printk(KERN_DEBUG "\tlpt_spc_bits:  %d\n", c->lpt_spc_bits);
+        printk(KERN_DEBUG "\tpcnt_bits:     %d\n", c->pcnt_bits);
+        printk(KERN_DEBUG "\tlnum_bits:     %d\n", c->lnum_bits);
+        printk(KERN_DEBUG "\tLPT root is at %d:%d\n", c->lpt_lnum, c->lpt_offs);
+        printk(KERN_DEBUG "\tLPT head is at %d:%d\n",
+               c->nhead_lnum, c->nhead_offs);
+        printk(KERN_DEBUG "\tLPT ltab is at %d:%d\n", c->ltab_lnum, c->ltab_offs);
+        if (c->big_lpt)
+                printk(KERN_DEBUG "\tLPT lsave is at %d:%d\n",
+                       c->lsave_lnum, c->lsave_offs);
+        for (i = 0; i < c->lpt_lebs; i++)
+                printk(KERN_DEBUG "\tLPT LEB %d free %d dirty %d tgc %d "
+                       "cmt %d\n", i + c->lpt_first, c->ltab[i].free,
+                       c->ltab[i].dirty, c->ltab[i].tgc, c->ltab[i].cmt);
+        spin_unlock(&dbg_lock);
+}
+
 void dbg_dump_leb(const struct ubifs_info *c, int lnum)
 {
         struct ubifs_scan_leb *sleb;
diff --git a/fs/ubifs/debug.h b/fs/ubifs/debug.h
index 50315fc57185..33d6b95071e4 100644
--- a/fs/ubifs/debug.h
+++ b/fs/ubifs/debug.h
@@ -224,6 +224,7 @@ void dbg_dump_lstats(const struct ubifs_lp_stats *lst);
 void dbg_dump_budg(struct ubifs_info *c);
 void dbg_dump_lprop(const struct ubifs_info *c, const struct ubifs_lprops *lp);
 void dbg_dump_lprops(struct ubifs_info *c);
+void dbg_dump_lpt_info(struct ubifs_info *c);
 void dbg_dump_leb(const struct ubifs_info *c, int lnum);
 void dbg_dump_znode(const struct ubifs_info *c,
                     const struct ubifs_znode *znode);
@@ -249,6 +250,8 @@ int dbg_old_index_check_init(struct ubifs_info *c, struct ubifs_zbranch *zroot);
 int dbg_check_old_index(struct ubifs_info *c, struct ubifs_zbranch *zroot);
 int dbg_check_cats(struct ubifs_info *c);
 int dbg_check_ltab(struct ubifs_info *c);
+int dbg_chk_lpt_free_spc(struct ubifs_info *c);
+int dbg_chk_lpt_sz(struct ubifs_info *c, int action, int len);
 int dbg_check_synced_i_size(struct inode *inode);
 int dbg_check_dir_size(struct ubifs_info *c, const struct inode *dir);
 int dbg_check_tnc(struct ubifs_info *c, int extra);
@@ -367,6 +370,7 @@ static inline int dbg_change(struct ubi_volume_desc *desc, int lnum,
 #define dbg_dump_budg(c)                      ({})
 #define dbg_dump_lprop(c, lp)                 ({})
 #define dbg_dump_lprops(c)                    ({})
+#define dbg_dump_lpt_info(c)                  ({})
 #define dbg_dump_leb(c, lnum)                 ({})
 #define dbg_dump_znode(c, znode)              ({})
 #define dbg_dump_heap(c, heap, cat)           ({})
@@ -379,6 +383,8 @@ static inline int dbg_change(struct ubi_volume_desc *desc, int lnum,
 #define dbg_check_old_index(c, zroot)              0
 #define dbg_check_cats(c)                          0
 #define dbg_check_ltab(c)                          0
+#define dbg_chk_lpt_free_spc(c)                    0
+#define dbg_chk_lpt_sz(c, action, len)             0
 #define dbg_check_synced_i_size(inode)             0
 #define dbg_check_dir_size(c, dir)                 0
 #define dbg_check_tnc(c, x)                        0
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 3d698e2022b1..51cf511d44d9 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -147,6 +147,12 @@ static int do_readpage(struct page *page)
                                 err = ret;
                                 if (err != -ENOENT)
                                         break;
+                        } else if (block + 1 == beyond) {
+                                int dlen = le32_to_cpu(dn->size);
+                                int ilen = i_size & (UBIFS_BLOCK_SIZE - 1);
+
+                                if (ilen && ilen < dlen)
+                                        memset(addr + ilen, 0, dlen - ilen);
                         }
                 }
                 if (++i >= UBIFS_BLOCKS_PER_PAGE)
@@ -577,8 +583,262 @@ out:
         return copied;
 }
 
+/**
+ * populate_page - copy data nodes into a page for bulk-read.
+ * @c: UBIFS file-system description object
+ * @page: page
+ * @bu: bulk-read information
+ * @n: next zbranch slot
+ *
+ * This function returns %0 on success and a negative error code on failure.
+ */
+static int populate_page(struct ubifs_info *c, struct page *page,
+                         struct bu_info *bu, int *n)
+{
+        int i = 0, nn = *n, offs = bu->zbranch[0].offs, hole = 0, read = 0;
+        struct inode *inode = page->mapping->host;
+        loff_t i_size = i_size_read(inode);
+        unsigned int page_block;
+        void *addr, *zaddr;
+        pgoff_t end_index;
+
+        dbg_gen("ino %lu, pg %lu, i_size %lld, flags %#lx",
+                inode->i_ino, page->index, i_size, page->flags);
+
+        addr = zaddr = kmap(page);
+
+        end_index = (i_size - 1) >> PAGE_CACHE_SHIFT;
+        if (!i_size || page->index > end_index) {
+                hole = 1;
+                memset(addr, 0, PAGE_CACHE_SIZE);
+                goto out_hole;
+        }
+
+        page_block = page->index << UBIFS_BLOCKS_PER_PAGE_SHIFT;
+        while (1) {
+                int err, len, out_len, dlen;
+
+                if (nn >= bu->cnt) {
+                        hole = 1;
+                        memset(addr, 0, UBIFS_BLOCK_SIZE);
+                } else if (key_block(c, &bu->zbranch[nn].key) == page_block) {
+                        struct ubifs_data_node *dn;
+
+                        dn = bu->buf + (bu->zbranch[nn].offs - offs);
+
+                        ubifs_assert(dn->ch.sqnum >
+                                     ubifs_inode(inode)->creat_sqnum);
+
+                        len = le32_to_cpu(dn->size);
+                        if (len <= 0 || len > UBIFS_BLOCK_SIZE)
+                                goto out_err;
+
+                        dlen = le32_to_cpu(dn->ch.len) - UBIFS_DATA_NODE_SZ;
+                        out_len = UBIFS_BLOCK_SIZE;
+                        err = ubifs_decompress(&dn->data, dlen, addr, &out_len,
+                                               le16_to_cpu(dn->compr_type));
+                        if (err || len != out_len)
+                                goto out_err;
+
+                        if (len < UBIFS_BLOCK_SIZE)
+                                memset(addr + len, 0, UBIFS_BLOCK_SIZE - len);
+
+                        nn += 1;
+                        read = (i << UBIFS_BLOCK_SHIFT) + len;
+                } else if (key_block(c, &bu->zbranch[nn].key) < page_block) {
+                        nn += 1;
+                        continue;
+                } else {
+                        hole = 1;
+                        memset(addr, 0, UBIFS_BLOCK_SIZE);
+                }
+                if (++i >= UBIFS_BLOCKS_PER_PAGE)
+                        break;
+                addr += UBIFS_BLOCK_SIZE;
+                page_block += 1;
+        }
+
+        if (end_index == page->index) {
+                int len = i_size & (PAGE_CACHE_SIZE - 1);
+
+                if (len && len < read)
+                        memset(zaddr + len, 0, read - len);
+        }
+
+out_hole:
+        if (hole) {
+                SetPageChecked(page);
+                dbg_gen("hole");
+        }
+
+        SetPageUptodate(page);
+        ClearPageError(page);
+        flush_dcache_page(page);
+        kunmap(page);
+        *n = nn;
+        return 0;
+
+out_err:
+        ClearPageUptodate(page);
+        SetPageError(page);
+        flush_dcache_page(page);
+        kunmap(page);
+        ubifs_err("bad data node (block %u, inode %lu)",
+                  page_block, inode->i_ino);
+        return -EINVAL;
+}
+
+/**
+ * ubifs_do_bulk_read - do bulk-read.
+ * @c: UBIFS file-system description object
+ * @page1: first page
+ *
+ * This function returns %1 if the bulk-read is done, otherwise %0 is returned.
+ */
+static int ubifs_do_bulk_read(struct ubifs_info *c, struct page *page1)
+{
+        pgoff_t offset = page1->index, end_index;
+        struct address_space *mapping = page1->mapping;
+        struct inode *inode = mapping->host;
+        struct ubifs_inode *ui = ubifs_inode(inode);
+        struct bu_info *bu;
+        int err, page_idx, page_cnt, ret = 0, n = 0;
+        loff_t isize;
+
+        bu = kmalloc(sizeof(struct bu_info), GFP_NOFS);
+        if (!bu)
+                return 0;
+
+        bu->buf_len = c->bulk_read_buf_size;
+        bu->buf = kmalloc(bu->buf_len, GFP_NOFS);
+        if (!bu->buf)
+                goto out_free;
+
+        data_key_init(c, &bu->key, inode->i_ino,
+                      offset << UBIFS_BLOCKS_PER_PAGE_SHIFT);
+
+        err = ubifs_tnc_get_bu_keys(c, bu);
+        if (err)
+                goto out_warn;
+
+        if (bu->eof) {
+                /* Turn off bulk-read at the end of the file */
+                ui->read_in_a_row = 1;
+                ui->bulk_read = 0;
+        }
+
+        page_cnt = bu->blk_cnt >> UBIFS_BLOCKS_PER_PAGE_SHIFT;
+        if (!page_cnt) {
+                /*
+                 * This happens when there are multiple blocks per page and the
+                 * blocks for the first page we are looking for, are not
+                 * together. If all the pages were like this, bulk-read would
+                 * reduce performance, so we turn it off for a while.
+                 */
+                ui->read_in_a_row = 0;
+                ui->bulk_read = 0;
+                goto out_free;
+        }
+
+        if (bu->cnt) {
+                err = ubifs_tnc_bulk_read(c, bu);
+                if (err)
+                        goto out_warn;
+        }
+
+        err = populate_page(c, page1, bu, &n);
+        if (err)
+                goto out_warn;
+
+        unlock_page(page1);
+        ret = 1;
+
+        isize = i_size_read(inode);
+        if (isize == 0)
+                goto out_free;
+        end_index = ((isize - 1) >> PAGE_CACHE_SHIFT);
+
+        for (page_idx = 1; page_idx < page_cnt; page_idx++) {
+                pgoff_t page_offset = offset + page_idx;
+                struct page *page;
+
+                if (page_offset > end_index)
+                        break;
+                page = find_or_create_page(mapping, page_offset,
+                                           GFP_NOFS | __GFP_COLD);
+                if (!page)
+                        break;
+                if (!PageUptodate(page))
+                        err = populate_page(c, page, bu, &n);
+                unlock_page(page);
+                page_cache_release(page);
+                if (err)
+                        break;
+        }
+
+        ui->last_page_read = offset + page_idx - 1;
+
+out_free:
+        kfree(bu->buf);
+        kfree(bu);
+        return ret;
+
+out_warn:
+        ubifs_warn("ignoring error %d and skipping bulk-read", err);
+        goto out_free;
+}
+
+/**
+ * ubifs_bulk_read - determine whether to bulk-read and, if so, do it.
+ * @page: page from which to start bulk-read.
+ *
+ * Some flash media are capable of reading sequentially at faster rates. UBIFS
+ * bulk-read facility is designed to take advantage of that, by reading in one
+ * go consecutive data nodes that are also located consecutively in the same
+ * LEB. This function returns %1 if a bulk-read is done and %0 otherwise.
+ */
+static int ubifs_bulk_read(struct page *page)
+{
+        struct inode *inode = page->mapping->host;
+        struct ubifs_info *c = inode->i_sb->s_fs_info;
+        struct ubifs_inode *ui = ubifs_inode(inode);
+        pgoff_t index = page->index, last_page_read = ui->last_page_read;
+        int ret = 0;
+
+        ui->last_page_read = index;
+
+        if (!c->bulk_read)
+                return 0;
+        /*
+         * Bulk-read is protected by ui_mutex, but it is an optimization, so
+         * don't bother if we cannot lock the mutex.
+         */
+        if (!mutex_trylock(&ui->ui_mutex))
+                return 0;
+        if (index != last_page_read + 1) {
+                /* Turn off bulk-read if we stop reading sequentially */
+                ui->read_in_a_row = 1;
+                if (ui->bulk_read)
+                        ui->bulk_read = 0;
+                goto out_unlock;
+        }
+        if (!ui->bulk_read) {
+                ui->read_in_a_row += 1;
+                if (ui->read_in_a_row < 3)
+                        goto out_unlock;
+                /* Three reads in a row, so switch on bulk-read */
+                ui->bulk_read = 1;
+        }
+        ret = ubifs_do_bulk_read(c, page);
+out_unlock:
+        mutex_unlock(&ui->ui_mutex);
+        return ret;
+}
+
 static int ubifs_readpage(struct file *file, struct page *page)
 {
+        if (ubifs_bulk_read(page))
+                return 0;
         do_readpage(page);
         unlock_page(page);
         return 0;
diff --git a/fs/ubifs/find.c b/fs/ubifs/find.c
index 47814cde2407..717d79c97c5e 100644
--- a/fs/ubifs/find.c
+++ b/fs/ubifs/find.c
@@ -901,11 +901,11 @@ static int get_idx_gc_leb(struct ubifs_info *c)
          * it is needed now for this commit.
          */
         lp = ubifs_lpt_lookup_dirty(c, lnum);
-        if (unlikely(IS_ERR(lp)))
+        if (IS_ERR(lp))
                 return PTR_ERR(lp);
         lp = ubifs_change_lp(c, lp, LPROPS_NC, LPROPS_NC,
                              lp->flags | LPROPS_INDEX, -1);
-        if (unlikely(IS_ERR(lp)))
+        if (IS_ERR(lp))
                 return PTR_ERR(lp);
         dbg_find("LEB %d, dirty %d and free %d flags %#x",
                  lp->lnum, lp->dirty, lp->free, lp->flags);
diff --git a/fs/ubifs/gc.c b/fs/ubifs/gc.c
index 02aba36fe3d4..0bef6501d58a 100644
--- a/fs/ubifs/gc.c
+++ b/fs/ubifs/gc.c
@@ -96,6 +96,48 @@ static int switch_gc_head(struct ubifs_info *c)
 }
 
 /**
+ * joinup - bring data nodes for an inode together.
+ * @c: UBIFS file-system description object
+ * @sleb: describes scanned LEB
+ * @inum: inode number
+ * @blk: block number
+ * @data: list to which to add data nodes
+ *
+ * This function looks at the first few nodes in the scanned LEB @sleb and adds
+ * them to @data if they are data nodes from @inum and have a larger block
+ * number than @blk. This function returns %0 on success and a negative error
+ * code on failure.
+ */
+static int joinup(struct ubifs_info *c, struct ubifs_scan_leb *sleb, ino_t inum,
+                  unsigned int blk, struct list_head *data)
+{
+        int err, cnt = 6, lnum = sleb->lnum, offs;
+        struct ubifs_scan_node *snod, *tmp;
+        union ubifs_key *key;
+
+        list_for_each_entry_safe(snod, tmp, &sleb->nodes, list) {
+                key = &snod->key;
+                if (key_inum(c, key) == inum &&
+                    key_type(c, key) == UBIFS_DATA_KEY &&
+                    key_block(c, key) > blk) {
+                        offs = snod->offs;
+                        err = ubifs_tnc_has_node(c, key, 0, lnum, offs, 0);
+                        if (err < 0)
+                                return err;
+                        list_del(&snod->list);
+                        if (err) {
+                                list_add_tail(&snod->list, data);
+                                blk = key_block(c, key);
+                        } else
+                                kfree(snod);
+                        cnt = 6;
+                } else if (--cnt == 0)
+                        break;
+        }
+        return 0;
+}
+
+/**
  * move_nodes - move nodes.
  * @c: UBIFS file-system description object
  * @sleb: describes nodes to move
@@ -116,16 +158,21 @@ static int switch_gc_head(struct ubifs_info *c)
 static int move_nodes(struct ubifs_info *c, struct ubifs_scan_leb *sleb)
 {
         struct ubifs_scan_node *snod, *tmp;
-        struct list_head large, medium, small;
+        struct list_head data, large, medium, small;
         struct ubifs_wbuf *wbuf = &c->jheads[GCHD].wbuf;
         int avail, err, min = INT_MAX;
+        unsigned int blk = 0;
+        ino_t inum = 0;
 
+        INIT_LIST_HEAD(&data);
         INIT_LIST_HEAD(&large);
         INIT_LIST_HEAD(&medium);
         INIT_LIST_HEAD(&small);
 
-        list_for_each_entry_safe(snod, tmp, &sleb->nodes, list) {
-                struct list_head *lst;
+        while (!list_empty(&sleb->nodes)) {
+                struct list_head *lst = sleb->nodes.next;
+
+                snod = list_entry(lst, struct ubifs_scan_node, list);
 
                 ubifs_assert(snod->type != UBIFS_IDX_NODE);
                 ubifs_assert(snod->type != UBIFS_REF_NODE);
@@ -136,7 +183,6 @@ static int move_nodes(struct ubifs_info *c, struct ubifs_scan_leb *sleb)
                 if (err < 0)
                         goto out;
 
-                lst = &snod->list;
                 list_del(lst);
                 if (!err) {
                         /* The node is obsolete, remove it from the list */
@@ -145,15 +191,30 @@ static int move_nodes(struct ubifs_info *c, struct ubifs_scan_leb *sleb)
                 }
 
                 /*
-                 * Sort the list of nodes so that large nodes go first, and
-                 * small nodes go last.
+                 * Sort the list of nodes so that data nodes go first, large
+                 * nodes go second, and small nodes go last.
                  */
-                if (snod->len > MEDIUM_NODE_WM)
-                        list_add(lst, &large);
+                if (key_type(c, &snod->key) == UBIFS_DATA_KEY) {
+                        if (inum != key_inum(c, &snod->key)) {
+                                if (inum) {
+                                        /*
+                                         * Try to move data nodes from the same
+                                         * inode together.
+                                         */
+                                        err = joinup(c, sleb, inum, blk, &data);
+                                        if (err)
+                                                goto out;
+                                }
+                                inum = key_inum(c, &snod->key);
+                                blk = key_block(c, &snod->key);
+                        }
+                        list_add_tail(lst, &data);
+                } else if (snod->len > MEDIUM_NODE_WM)
+                        list_add_tail(lst, &large);
                 else if (snod->len > SMALL_NODE_WM)
-                        list_add(lst, &medium);
+                        list_add_tail(lst, &medium);
                 else
-                        list_add(lst, &small);
+                        list_add_tail(lst, &small);
 
                 /* And find the smallest node */
                 if (snod->len < min)
@@ -164,6 +225,7 @@ static int move_nodes(struct ubifs_info *c, struct ubifs_scan_leb *sleb)
          * Join the tree lists so that we'd have one roughly sorted list
          * ('large' will be the head of the joined list).
          */
+        list_splice(&data, &large);
         list_splice(&medium, large.prev);
         list_splice(&small, large.prev);
 
@@ -653,7 +715,7 @@ int ubifs_gc_start_commit(struct ubifs_info *c)
          */
         while (1) {
                 lp = ubifs_fast_find_freeable(c);
-                if (unlikely(IS_ERR(lp))) {
+                if (IS_ERR(lp)) {
                         err = PTR_ERR(lp);
                         goto out;
                 }
@@ -665,7 +727,7 @@ int ubifs_gc_start_commit(struct ubifs_info *c)
                 if (err)
                         goto out;
                 lp = ubifs_change_lp(c, lp, c->leb_size, 0, lp->flags, 0);
-                if (unlikely(IS_ERR(lp))) {
+                if (IS_ERR(lp)) {
                         err = PTR_ERR(lp);
                         goto out;
                 }
@@ -680,7 +742,7 @@ int ubifs_gc_start_commit(struct ubifs_info *c)
         /* Record index freeable LEBs for unmapping after commit */
         while (1) {
                 lp = ubifs_fast_find_frdi_idx(c);
-                if (unlikely(IS_ERR(lp))) {
+                if (IS_ERR(lp)) {
                         err = PTR_ERR(lp);
                         goto out;
                 }
@@ -696,7 +758,7 @@ int ubifs_gc_start_commit(struct ubifs_info *c)
                 /* Don't release the LEB until after the next commit */
                 flags = (lp->flags | LPROPS_TAKEN) ^ LPROPS_INDEX;
                 lp = ubifs_change_lp(c, lp, c->leb_size, 0, flags, 1);
-                if (unlikely(IS_ERR(lp))) {
+                if (IS_ERR(lp)) {
                         err = PTR_ERR(lp);
                         kfree(idx_gc);
                         goto out;
diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c
index 054363f2b207..01682713af69 100644
--- a/fs/ubifs/io.c
+++ b/fs/ubifs/io.c
@@ -62,6 +62,7 @@ void ubifs_ro_mode(struct ubifs_info *c, int err)
 {
         if (!c->ro_media) {
                 c->ro_media = 1;
+                c->no_chk_data_crc = 0;
                 ubifs_warn("switched to read-only mode, error %d", err);
                 dbg_dump_stack();
         }
@@ -74,6 +75,7 @@ void ubifs_ro_mode(struct ubifs_info *c, int err)
  * @lnum: logical eraseblock number
  * @offs: offset within the logical eraseblock
  * @quiet: print no messages
+ * @chk_crc: indicates whether to always check the CRC
  *
  * This function checks node magic number and CRC checksum. This function also
  * validates node length to prevent UBIFS from becoming crazy when an attacker
@@ -85,7 +87,7 @@ void ubifs_ro_mode(struct ubifs_info *c, int err)
  * or magic.
  */
 int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum,
-                     int offs, int quiet)
+                     int offs, int quiet, int chk_crc)
 {
         int err = -EINVAL, type, node_len;
         uint32_t crc, node_crc, magic;
@@ -121,6 +123,10 @@ int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum,
                    node_len > c->ranges[type].max_len)
                 goto out_len;
 
+        if (!chk_crc && type == UBIFS_DATA_NODE && !c->always_chk_crc)
+                if (c->no_chk_data_crc)
+                        return 0;
+
         crc = crc32(UBIFS_CRC32_INIT, buf + 8, node_len - 8);
         node_crc = le32_to_cpu(ch->crc);
         if (crc != node_crc) {
@@ -722,7 +728,7 @@ int ubifs_read_node_wbuf(struct ubifs_wbuf *wbuf, void *buf, int type, int len,
                 goto out;
         }
 
-        err = ubifs_check_node(c, buf, lnum, offs, 0);
+        err = ubifs_check_node(c, buf, lnum, offs, 0, 0);
         if (err) {
                 ubifs_err("expected node type %d", type);
                 return err;
@@ -781,7 +787,7 @@ int ubifs_read_node(const struct ubifs_info *c, void *buf, int type, int len,
                 goto out;
         }
 
-        err = ubifs_check_node(c, buf, lnum, offs, 0);
+        err = ubifs_check_node(c, buf, lnum, offs, 0, 0);
         if (err) {
                 ubifs_err("expected node type %d", type);
                 return err;
diff --git a/fs/ubifs/key.h b/fs/ubifs/key.h
index 8f7476007549..9ee65086f627 100644
--- a/fs/ubifs/key.h
+++ b/fs/ubifs/key.h
@@ -484,7 +484,7 @@ static inline void key_copy(const struct ubifs_info *c,
  * @key2: the second key to compare
  *
  * This function compares 2 keys and returns %-1 if @key1 is less than
- * @key2, 0 if the keys are equivalent and %1 if @key1 is greater than @key2.
+ * @key2, %0 if the keys are equivalent and %1 if @key1 is greater than @key2.
  */
 static inline int keys_cmp(const struct ubifs_info *c,
                            const union ubifs_key *key1,
@@ -503,6 +503,26 @@ static inline int keys_cmp(const struct ubifs_info *c,
 }
 
 /**
+ * keys_eq - determine if keys are equivalent.
+ * @c: UBIFS file-system description object
+ * @key1: the first key to compare
+ * @key2: the second key to compare
+ *
+ * This function compares 2 keys and returns %1 if @key1 is equal to @key2 and
+ * %0 if not.
+ */
+static inline int keys_eq(const struct ubifs_info *c,
+                          const union ubifs_key *key1,
+                          const union ubifs_key *key2)
+{
+        if (key1->u32[0] != key2->u32[0])
+                return 0;
+        if (key1->u32[1] != key2->u32[1])
+                return 0;
+        return 1;
+}
+
+/**
  * is_hash_key - is a key vulnerable to hash collisions.
  * @c: UBIFS file-system description object
  * @key: key
diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c
index 2ba93da71b65..f27176e9b70d 100644
--- a/fs/ubifs/lprops.c
+++ b/fs/ubifs/lprops.c
@@ -125,6 +125,7 @@ static void adjust_lpt_heap(struct ubifs_info *c, struct ubifs_lpt_heap *heap,
                         }
                 }
         }
+
         /* Not greater than parent, so compare to children */
         while (1) {
                 /* Compare to left child */
@@ -460,18 +461,6 @@ static void change_category(struct ubifs_info *c, struct ubifs_lprops *lprops)
 }
 
 /**
- * ubifs_get_lprops - get reference to LEB properties.
- * @c: the UBIFS file-system description object
- *
- * This function locks lprops. Lprops have to be unlocked by
- * 'ubifs_release_lprops()'.
- */
-void ubifs_get_lprops(struct ubifs_info *c)
-{
-        mutex_lock(&c->lp_mutex);
-}
-
-/**
  * calc_dark - calculate LEB dark space size.
  * @c: the UBIFS file-system description object
  * @spc: amount of free and dirty space in the LEB
@@ -576,7 +565,6 @@ const struct ubifs_lprops *ubifs_change_lp(struct ubifs_info *c,
         ubifs_assert(!(lprops->free & 7) && !(lprops->dirty & 7));
 
         spin_lock(&c->space_lock);
-
         if ((lprops->flags & LPROPS_TAKEN) && lprops->free == c->leb_size)
                 c->lst.taken_empty_lebs -= 1;
 
@@ -637,31 +625,12 @@ const struct ubifs_lprops *ubifs_change_lp(struct ubifs_info *c,
                 c->lst.taken_empty_lebs += 1;
 
         change_category(c, lprops);
-
         c->idx_gc_cnt += idx_gc_cnt;
-
         spin_unlock(&c->space_lock);
-
         return lprops;
 }
 
 /**
- * ubifs_release_lprops - release lprops lock.
- * @c: the UBIFS file-system description object
- *
- * This function has to be called after each 'ubifs_get_lprops()' call to
- * unlock lprops.
- */
-void ubifs_release_lprops(struct ubifs_info *c)
-{
-        ubifs_assert(mutex_is_locked(&c->lp_mutex));
-        ubifs_assert(c->lst.empty_lebs >= 0 &&
-                     c->lst.empty_lebs <= c->main_lebs);
-
-        mutex_unlock(&c->lp_mutex);
-}
-
-/**
  * ubifs_get_lp_stats - get lprops statistics.
  * @c: UBIFS file-system description object
  * @st: return statistics
@@ -1262,7 +1231,6 @@ static int scan_check_cb(struct ubifs_info *c,
         }
 
         ubifs_scan_destroy(sleb);
-
         return LPT_SCAN_CONTINUE;
 
 out_print:
diff --git a/fs/ubifs/lpt.c b/fs/ubifs/lpt.c
index 9ff2463177e5..db8bd0e518b2 100644
--- a/fs/ubifs/lpt.c
+++ b/fs/ubifs/lpt.c
@@ -109,7 +109,8 @@ static void do_calc_lpt_geom(struct ubifs_info *c)
         c->lpt_sz = (long long)c->pnode_cnt * c->pnode_sz;
         c->lpt_sz += (long long)c->nnode_cnt * c->nnode_sz;
         c->lpt_sz += c->ltab_sz;
-        c->lpt_sz += c->lsave_sz;
+        if (c->big_lpt)
+                c->lpt_sz += c->lsave_sz;
 
         /* Add wastage */
         sz = c->lpt_sz;
@@ -287,25 +288,56 @@ uint32_t ubifs_unpack_bits(uint8_t **addr, int *pos, int nrbits)
         const int k = 32 - nrbits;
         uint8_t *p = *addr;
         int b = *pos;
-        uint32_t val;
+        uint32_t uninitialized_var(val);
+        const int bytes = (nrbits + b + 7) >> 3;
 
         ubifs_assert(nrbits > 0);
         ubifs_assert(nrbits <= 32);
         ubifs_assert(*pos >= 0);
         ubifs_assert(*pos < 8);
         if (b) {
-                val = p[1] | ((uint32_t)p[2] << 8) | ((uint32_t)p[3] << 16) |
-                      ((uint32_t)p[4] << 24);
+                switch (bytes) {
+                case 2:
+                        val = p[1];
+                        break;
+                case 3:
+                        val = p[1] | ((uint32_t)p[2] << 8);
+                        break;
+                case 4:
+                        val = p[1] | ((uint32_t)p[2] << 8) |
+                                     ((uint32_t)p[3] << 16);
+                        break;
+                case 5:
+                        val = p[1] | ((uint32_t)p[2] << 8) |
+                                     ((uint32_t)p[3] << 16) |
+                                     ((uint32_t)p[4] << 24);
+                }
                 val <<= (8 - b);
                 val |= *p >> b;
                 nrbits += b;
-        } else
-                val = p[0] | ((uint32_t)p[1] << 8) | ((uint32_t)p[2] << 16) |
-                      ((uint32_t)p[3] << 24);
+        } else {
+                switch (bytes) {
+                case 1:
+                        val = p[0];
+                        break;
+                case 2:
+                        val = p[0] | ((uint32_t)p[1] << 8);
+                        break;
+                case 3:
+                        val = p[0] | ((uint32_t)p[1] << 8) |
+                                     ((uint32_t)p[2] << 16);
+                        break;
+                case 4:
+                        val = p[0] | ((uint32_t)p[1] << 8) |
+                                     ((uint32_t)p[2] << 16) |
+                                     ((uint32_t)p[3] << 24);
+                        break;
+                }
+        }
         val <<= k;
         val >>= k;
         b = nrbits & 7;
-        p += nrbits / 8;
+        p += nrbits >> 3;
         *addr = p;
         *pos = b;
         ubifs_assert((val >> nrbits) == 0 || nrbits - b == 32);
diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c
index 5f0b83e20af6..eed5a0025d63 100644
--- a/fs/ubifs/lpt_commit.c
+++ b/fs/ubifs/lpt_commit.c
@@ -177,8 +177,6 @@ static int alloc_lpt_leb(struct ubifs_info *c, int *lnum)
                         return 0;
                 }
         }
-        dbg_err("last LEB %d", *lnum);
-        dump_stack();
         return -ENOSPC;
 }
 
@@ -193,6 +191,9 @@ static int layout_cnodes(struct ubifs_info *c)
         int lnum, offs, len, alen, done_lsave, done_ltab, err;
         struct ubifs_cnode *cnode;
 
+        err = dbg_chk_lpt_sz(c, 0, 0);
+        if (err)
+                return err;
         cnode = c->lpt_cnext;
         if (!cnode)
                 return 0;
@@ -206,6 +207,7 @@ static int layout_cnodes(struct ubifs_info *c)
                 c->lsave_lnum = lnum;
                 c->lsave_offs = offs;
                 offs += c->lsave_sz;
+                dbg_chk_lpt_sz(c, 1, c->lsave_sz);
         }
 
         if (offs + c->ltab_sz <= c->leb_size) {
@@ -213,6 +215,7 @@ static int layout_cnodes(struct ubifs_info *c)
                 c->ltab_lnum = lnum;
                 c->ltab_offs = offs;
                 offs += c->ltab_sz;
+                dbg_chk_lpt_sz(c, 1, c->ltab_sz);
         }
 
         do {
@@ -226,9 +229,10 @@ static int layout_cnodes(struct ubifs_info *c)
                 while (offs + len > c->leb_size) {
                         alen = ALIGN(offs, c->min_io_size);
                         upd_ltab(c, lnum, c->leb_size - alen, alen - offs);
+                        dbg_chk_lpt_sz(c, 2, alen - offs);
                         err = alloc_lpt_leb(c, &lnum);
                         if (err)
-                                return err;
+                                goto no_space;
                         offs = 0;
                         ubifs_assert(lnum >= c->lpt_first &&
                                      lnum <= c->lpt_last);
@@ -238,6 +242,7 @@ static int layout_cnodes(struct ubifs_info *c)
                                 c->lsave_lnum = lnum;
                                 c->lsave_offs = offs;
                                 offs += c->lsave_sz;
+                                dbg_chk_lpt_sz(c, 1, c->lsave_sz);
                                 continue;
                         }
                         if (!done_ltab) {
@@ -245,6 +250,7 @@ static int layout_cnodes(struct ubifs_info *c)
                                 c->ltab_lnum = lnum;
                                 c->ltab_offs = offs;
                                 offs += c->ltab_sz;
+                                dbg_chk_lpt_sz(c, 1, c->ltab_sz);
                                 continue;
                         }
                         break;
@@ -257,6 +263,7 @@ static int layout_cnodes(struct ubifs_info *c)
                         c->lpt_offs = offs;
                 }
                 offs += len;
+                dbg_chk_lpt_sz(c, 1, len);
                 cnode = cnode->cnext;
         } while (cnode && cnode != c->lpt_cnext);
 
@@ -265,9 +272,10 @@ static int layout_cnodes(struct ubifs_info *c)
                 if (offs + c->lsave_sz > c->leb_size) {
                         alen = ALIGN(offs, c->min_io_size);
                         upd_ltab(c, lnum, c->leb_size - alen, alen - offs);
+                        dbg_chk_lpt_sz(c, 2, alen - offs);
                         err = alloc_lpt_leb(c, &lnum);
                         if (err)
-                                return err;
+                                goto no_space;
                         offs = 0;
                         ubifs_assert(lnum >= c->lpt_first &&
                                      lnum <= c->lpt_last);
@@ -276,6 +284,7 @@ static int layout_cnodes(struct ubifs_info *c)
                 c->lsave_lnum = lnum;
                 c->lsave_offs = offs;
                 offs += c->lsave_sz;
+                dbg_chk_lpt_sz(c, 1, c->lsave_sz);
         }
 
         /* Make sure to place LPT's own lprops table */
@@ -283,9 +292,10 @@ static int layout_cnodes(struct ubifs_info *c)
                 if (offs + c->ltab_sz > c->leb_size) {
                         alen = ALIGN(offs, c->min_io_size);
                         upd_ltab(c, lnum, c->leb_size - alen, alen - offs);
+                        dbg_chk_lpt_sz(c, 2, alen - offs);
                         err = alloc_lpt_leb(c, &lnum);
                         if (err)
-                                return err;
+                                goto no_space;
                         offs = 0;
                         ubifs_assert(lnum >= c->lpt_first &&
                                      lnum <= c->lpt_last);
@@ -294,11 +304,23 @@ static int layout_cnodes(struct ubifs_info *c)
                 c->ltab_lnum = lnum;
                 c->ltab_offs = offs;
                 offs += c->ltab_sz;
+                dbg_chk_lpt_sz(c, 1, c->ltab_sz);
         }
 
         alen = ALIGN(offs, c->min_io_size);
         upd_ltab(c, lnum, c->leb_size - alen, alen - offs);
+        dbg_chk_lpt_sz(c, 4, alen - offs);
+        err = dbg_chk_lpt_sz(c, 3, alen);
+        if (err)
+                return err;
         return 0;
+
+no_space:
+        ubifs_err("LPT out of space");
+        dbg_err("LPT out of space at LEB %d:%d needing %d, done_ltab %d, "
+                "done_lsave %d", lnum, offs, len, done_ltab, done_lsave);
+        dbg_dump_lpt_info(c);
+        return err;
 }
 
 /**
@@ -333,8 +355,6 @@ static int realloc_lpt_leb(struct ubifs_info *c, int *lnum)
                         *lnum = i + c->lpt_first;
                         return 0;
                 }
-        dbg_err("last LEB %d", *lnum);
-        dump_stack();
         return -ENOSPC;
 }
 
@@ -369,12 +389,14 @@ static int write_cnodes(struct ubifs_info *c)
                 done_lsave = 1;
                 ubifs_pack_lsave(c, buf + offs, c->lsave);
                 offs += c->lsave_sz;
+                dbg_chk_lpt_sz(c, 1, c->lsave_sz);
         }
 
         if (offs + c->ltab_sz <= c->leb_size) {
                 done_ltab = 1;
                 ubifs_pack_ltab(c, buf + offs, c->ltab_cmt);
                 offs += c->ltab_sz;
+                dbg_chk_lpt_sz(c, 1, c->ltab_sz);
         }
 
         /* Loop for each cnode */
@@ -392,10 +414,12 @@ static int write_cnodes(struct ubifs_info *c)
                                                        alen, UBI_SHORTTERM);
                                 if (err)
                                         return err;
+                                dbg_chk_lpt_sz(c, 4, alen - wlen);
                         }
+                        dbg_chk_lpt_sz(c, 2, 0);
                         err = realloc_lpt_leb(c, &lnum);
                         if (err)
-                                return err;
+                                goto no_space;
                         offs = 0;
                         from = 0;
                         ubifs_assert(lnum >= c->lpt_first &&
@@ -408,12 +432,14 @@ static int write_cnodes(struct ubifs_info *c)
                                 done_lsave = 1;
                                 ubifs_pack_lsave(c, buf + offs, c->lsave);
                                 offs += c->lsave_sz;
+                                dbg_chk_lpt_sz(c, 1, c->lsave_sz);
                                 continue;
                         }
                         if (!done_ltab) {
                                 done_ltab = 1;
                                 ubifs_pack_ltab(c, buf + offs, c->ltab_cmt);
                                 offs += c->ltab_sz;
+                                dbg_chk_lpt_sz(c, 1, c->ltab_sz);
                                 continue;
                         }
                         break;
@@ -435,6 +461,7 @@ static int write_cnodes(struct ubifs_info *c)
                 clear_bit(COW_ZNODE, &cnode->flags);
                 smp_mb__after_clear_bit();
                 offs += len;
+                dbg_chk_lpt_sz(c, 1, len);
                 cnode = cnode->cnext;
         } while (cnode && cnode != c->lpt_cnext);
 
@@ -448,9 +475,10 @@ static int write_cnodes(struct ubifs_info *c)
                                               UBI_SHORTTERM);
                         if (err)
                                 return err;
+                        dbg_chk_lpt_sz(c, 2, alen - wlen);
                         err = realloc_lpt_leb(c, &lnum);
                         if (err)
-                                return err;
+                                goto no_space;
                         offs = 0;
                         ubifs_assert(lnum >= c->lpt_first &&
                                      lnum <= c->lpt_last);
@@ -461,6 +489,7 @@ static int write_cnodes(struct ubifs_info *c)
                 done_lsave = 1;
                 ubifs_pack_lsave(c, buf + offs, c->lsave);
                 offs += c->lsave_sz;
+                dbg_chk_lpt_sz(c, 1, c->lsave_sz);
         }
 
         /* Make sure to place LPT's own lprops table */
@@ -473,9 +502,10 @@ static int write_cnodes(struct ubifs_info *c)
                                               UBI_SHORTTERM);
                         if (err)
                                 return err;
+                        dbg_chk_lpt_sz(c, 2, alen - wlen);
                         err = realloc_lpt_leb(c, &lnum);
                         if (err)
-                                return err;
+                                goto no_space;
                         offs = 0;
                         ubifs_assert(lnum >= c->lpt_first &&
                                      lnum <= c->lpt_last);
@@ -486,6 +516,7 @@ static int write_cnodes(struct ubifs_info *c)
                 done_ltab = 1;
                 ubifs_pack_ltab(c, buf + offs, c->ltab_cmt);
                 offs += c->ltab_sz;
+                dbg_chk_lpt_sz(c, 1, c->ltab_sz);
         }
 
         /* Write remaining data in buffer */
@@ -495,6 +526,12 @@ static int write_cnodes(struct ubifs_info *c)
         err = ubifs_leb_write(c, lnum, buf + from, from, alen, UBI_SHORTTERM);
         if (err)
                 return err;
+
+        dbg_chk_lpt_sz(c, 4, alen - wlen);
+        err = dbg_chk_lpt_sz(c, 3, ALIGN(offs, c->min_io_size));
+        if (err)
+                return err;
+
         c->nhead_lnum = lnum;
         c->nhead_offs = ALIGN(offs, c->min_io_size);
 
@@ -503,7 +540,15 @@ static int write_cnodes(struct ubifs_info *c)
         dbg_lp("LPT ltab is at %d:%d", c->ltab_lnum, c->ltab_offs);
         if (c->big_lpt)
                 dbg_lp("LPT lsave is at %d:%d", c->lsave_lnum, c->lsave_offs);
+
         return 0;
+
+no_space:
+        ubifs_err("LPT out of space mismatch");
+        dbg_err("LPT out of space mismatch at LEB %d:%d needing %d, done_ltab "
+                "%d, done_lsave %d", lnum, offs, len, done_ltab, done_lsave);
+        dbg_dump_lpt_info(c);
+        return err;
 }
 
 /**
@@ -1044,6 +1089,8 @@ static int is_a_node(struct ubifs_info *c, uint8_t *buf, int len)
         int pos = 0, node_type, node_len;
         uint16_t crc, calc_crc;
 
+        if (len < UBIFS_LPT_CRC_BYTES + (UBIFS_LPT_TYPE_BITS + 7) / 8)
+                return 0;
         node_type = ubifs_unpack_bits(&addr, &pos, UBIFS_LPT_TYPE_BITS);
         if (node_type == UBIFS_LPT_NOT_A_NODE)
                 return 0;
@@ -1156,6 +1203,9 @@ int ubifs_lpt_start_commit(struct ubifs_info *c)
         dbg_lp("");
 
         mutex_lock(&c->lp_mutex);
+        err = dbg_chk_lpt_free_spc(c);
+        if (err)
+                goto out;
         err = dbg_check_ltab(c);
         if (err)
                 goto out;
@@ -1645,4 +1695,121 @@ int dbg_check_ltab(struct ubifs_info *c)
         return 0;
 }
 
+/**
+ * dbg_chk_lpt_free_spc - check LPT free space is enough to write entire LPT.
+ * @c: the UBIFS file-system description object
+ *
+ * This function returns %0 on success and a negative error code on failure.
+ */
+int dbg_chk_lpt_free_spc(struct ubifs_info *c)
+{
+        long long free = 0;
+        int i;
+
+        for (i = 0; i < c->lpt_lebs; i++) {
+                if (c->ltab[i].tgc || c->ltab[i].cmt)
+                        continue;
+                if (i + c->lpt_first == c->nhead_lnum)
+                        free += c->leb_size - c->nhead_offs;
+                else if (c->ltab[i].free == c->leb_size)
+                        free += c->leb_size;
+        }
+        if (free < c->lpt_sz) {
+                dbg_err("LPT space error: free %lld lpt_sz %lld",
+                        free, c->lpt_sz);
+                dbg_dump_lpt_info(c);
+                return -EINVAL;
+        }
+        return 0;
+}
+
+/**
+ * dbg_chk_lpt_sz - check LPT does not write more than LPT size.
+ * @c: the UBIFS file-system description object
+ * @action: action
+ * @len: length written
+ *
+ * This function returns %0 on success and a negative error code on failure.
+ */
+int dbg_chk_lpt_sz(struct ubifs_info *c, int action, int len)
+{
+        long long chk_lpt_sz, lpt_sz;
+        int err = 0;
+
+        switch (action) {
+        case 0:
+                c->chk_lpt_sz = 0;
+                c->chk_lpt_sz2 = 0;
+                c->chk_lpt_lebs = 0;
+                c->chk_lpt_wastage = 0;
+                if (c->dirty_pn_cnt > c->pnode_cnt) {
+                        dbg_err("dirty pnodes %d exceed max %d",
+                                c->dirty_pn_cnt, c->pnode_cnt);
+                        err = -EINVAL;
+                }
+                if (c->dirty_nn_cnt > c->nnode_cnt) {
+                        dbg_err("dirty nnodes %d exceed max %d",
+                                c->dirty_nn_cnt, c->nnode_cnt);
+                        err = -EINVAL;
+                }
+                return err;
+        case 1:
+                c->chk_lpt_sz += len;
+                return 0;
+        case 2:
+                c->chk_lpt_sz += len;
+                c->chk_lpt_wastage += len;
+                c->chk_lpt_lebs += 1;
+                return 0;
+        case 3:
+                chk_lpt_sz = c->leb_size;
+                chk_lpt_sz *= c->chk_lpt_lebs;
+                chk_lpt_sz += len - c->nhead_offs;
+                if (c->chk_lpt_sz != chk_lpt_sz) {
+                        dbg_err("LPT wrote %lld but space used was %lld",
+                                c->chk_lpt_sz, chk_lpt_sz);
+                        err = -EINVAL;
+                }
+                if (c->chk_lpt_sz > c->lpt_sz) {
+                        dbg_err("LPT wrote %lld but lpt_sz is %lld",
+                                c->chk_lpt_sz, c->lpt_sz);
+                        err = -EINVAL;
+                }
+                if (c->chk_lpt_sz2 && c->chk_lpt_sz != c->chk_lpt_sz2) {
+                        dbg_err("LPT layout size %lld but wrote %lld",
+                                c->chk_lpt_sz, c->chk_lpt_sz2);
+                        err = -EINVAL;
+                }
+                if (c->chk_lpt_sz2 && c->new_nhead_offs != len) {
+                        dbg_err("LPT new nhead offs: expected %d was %d",
+                                c->new_nhead_offs, len);
+                        err = -EINVAL;
+                }
+                lpt_sz = (long long)c->pnode_cnt * c->pnode_sz;
+                lpt_sz += (long long)c->nnode_cnt * c->nnode_sz;
+                lpt_sz += c->ltab_sz;
+                if (c->big_lpt)
+                        lpt_sz += c->lsave_sz;
+                if (c->chk_lpt_sz - c->chk_lpt_wastage > lpt_sz) {
+                        dbg_err("LPT chk_lpt_sz %lld + waste %lld exceeds %lld",
+                                c->chk_lpt_sz, c->chk_lpt_wastage, lpt_sz);
+                        err = -EINVAL;
+                }
+                if (err)
+                        dbg_dump_lpt_info(c);
+                c->chk_lpt_sz2 = c->chk_lpt_sz;
+                c->chk_lpt_sz = 0;
+                c->chk_lpt_wastage = 0;
+                c->chk_lpt_lebs = 0;
+                c->new_nhead_offs = len;
+                return err;
+        case 4:
+                c->chk_lpt_sz += len;
+                c->chk_lpt_wastage += len;
+                return 0;
+        default:
+                return -EINVAL;
+        }
+}
+
 #endif /* CONFIG_UBIFS_FS_DEBUG */
diff --git a/fs/ubifs/misc.h b/fs/ubifs/misc.h
index 4c12a9215d7f..4fa81d867e41 100644
--- a/fs/ubifs/misc.h
+++ b/fs/ubifs/misc.h
@@ -310,4 +310,31 @@ static inline int ubifs_tnc_lookup(struct ubifs_info *c,
         return ubifs_tnc_locate(c, key, node, NULL, NULL);
 }
 
+/**
+ * ubifs_get_lprops - get reference to LEB properties.
+ * @c: the UBIFS file-system description object
+ *
+ * This function locks lprops. Lprops have to be unlocked by
+ * 'ubifs_release_lprops()'.
+ */
+static inline void ubifs_get_lprops(struct ubifs_info *c)
+{
+        mutex_lock(&c->lp_mutex);
+}
+
+/**
+ * ubifs_release_lprops - release lprops lock.
+ * @c: the UBIFS file-system description object
+ *
+ * This function has to be called after each 'ubifs_get_lprops()' call to
+ * unlock lprops.
+ */
+static inline void ubifs_release_lprops(struct ubifs_info *c)
+{
+        ubifs_assert(mutex_is_locked(&c->lp_mutex));
+        ubifs_assert(c->lst.empty_lebs >= 0 &&
+                     c->lst.empty_lebs <= c->main_lebs);
+        mutex_unlock(&c->lp_mutex);
+}
+
 #endif /* __UBIFS_MISC_H__ */
diff --git a/fs/ubifs/scan.c b/fs/ubifs/scan.c
index acf5c5fffc60..0ed82479b44b 100644
--- a/fs/ubifs/scan.c
+++ b/fs/ubifs/scan.c
@@ -87,7 +87,7 @@ int ubifs_scan_a_node(const struct ubifs_info *c, void *buf, int len, int lnum,
 
         dbg_scan("scanning %s", dbg_ntype(ch->node_type));
 
-        if (ubifs_check_node(c, buf, lnum, offs, quiet))
+        if (ubifs_check_node(c, buf, lnum, offs, quiet, 1))
                 return SCANNED_A_CORRUPT_NODE;
 
         if (ch->node_type == UBIFS_PAD_NODE) {
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 3f4902060c7a..8780efbf40ac 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -401,6 +401,16 @@ static int ubifs_show_options(struct seq_file *s, struct vfsmount *mnt)
         else if (c->mount_opts.unmount_mode == 1)
                 seq_printf(s, ",norm_unmount");
 
+        if (c->mount_opts.bulk_read == 2)
+                seq_printf(s, ",bulk_read");
+        else if (c->mount_opts.bulk_read == 1)
+                seq_printf(s, ",no_bulk_read");
+
+        if (c->mount_opts.chk_data_crc == 2)
+                seq_printf(s, ",chk_data_crc");
+        else if (c->mount_opts.chk_data_crc == 1)
+                seq_printf(s, ",no_chk_data_crc");
+
         return 0;
 }
 
@@ -408,13 +418,26 @@ static int ubifs_sync_fs(struct super_block *sb, int wait)
 {
         struct ubifs_info *c = sb->s_fs_info;
         int i, ret = 0, err;
+        long long bud_bytes;
 
-        if (c->jheads)
+        if (c->jheads) {
                 for (i = 0; i < c->jhead_cnt; i++) {
                         err = ubifs_wbuf_sync(&c->jheads[i].wbuf);
                         if (err && !ret)
                                 ret = err;
                 }
+
+                /* Commit the journal unless it has too little data */
+                spin_lock(&c->buds_lock);
+                bud_bytes = c->bud_bytes;
+                spin_unlock(&c->buds_lock);
+                if (bud_bytes > c->leb_size) {
+                        err = ubifs_run_commit(c);
+                        if (err)
+                                return err;
+                }
+        }
+
         /*
          * We ought to call sync for c->ubi but it does not have one. If it had
          * it would in turn call mtd->sync, however mtd operations are
@@ -538,6 +561,18 @@ static int init_constants_early(struct ubifs_info *c)
          * calculations when reporting free space.
          */
         c->leb_overhead = c->leb_size % UBIFS_MAX_DATA_NODE_SZ;
+        /* Buffer size for bulk-reads */
+        c->bulk_read_buf_size = UBIFS_MAX_BULK_READ * UBIFS_MAX_DATA_NODE_SZ;
+        if (c->bulk_read_buf_size > c->leb_size)
+                c->bulk_read_buf_size = c->leb_size;
+        if (c->bulk_read_buf_size > 128 * 1024) {
+                /* Check if we can kmalloc more than 128KiB */
+                void *try = kmalloc(c->bulk_read_buf_size, GFP_KERNEL);
+
+                kfree(try);
+                if (!try)
+                        c->bulk_read_buf_size = 128 * 1024;
+        }
         return 0;
 }
 
@@ -840,17 +875,29 @@ static int check_volume_empty(struct ubifs_info *c)
  *
  * Opt_fast_unmount: do not run a journal commit before un-mounting
  * Opt_norm_unmount: run a journal commit before un-mounting
+ * Opt_bulk_read: enable bulk-reads
+ * Opt_no_bulk_read: disable bulk-reads
+ * Opt_chk_data_crc: check CRCs when reading data nodes
+ * Opt_no_chk_data_crc: do not check CRCs when reading data nodes
  * Opt_err: just end of array marker
  */
 enum {
         Opt_fast_unmount,
         Opt_norm_unmount,
+        Opt_bulk_read,
+        Opt_no_bulk_read,
+        Opt_chk_data_crc,
+        Opt_no_chk_data_crc,
         Opt_err,
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         {Opt_fast_unmount, "fast_unmount"},
         {Opt_norm_unmount, "norm_unmount"},
+        {Opt_bulk_read, "bulk_read"},
+        {Opt_no_bulk_read, "no_bulk_read"},
+        {Opt_chk_data_crc, "chk_data_crc"},
+        {Opt_no_chk_data_crc, "no_chk_data_crc"},
         {Opt_err, NULL},
 };
 
@@ -888,6 +935,22 @@ static int ubifs_parse_options(struct ubifs_info *c, char *options,
                         c->mount_opts.unmount_mode = 1;
                         c->fast_unmount = 0;
                         break;
+                case Opt_bulk_read:
+                        c->mount_opts.bulk_read = 2;
+                        c->bulk_read = 1;
+                        break;
+                case Opt_no_bulk_read:
+                        c->mount_opts.bulk_read = 1;
+                        c->bulk_read = 0;
+                        break;
+                case Opt_chk_data_crc:
+                        c->mount_opts.chk_data_crc = 2;
+                        c->no_chk_data_crc = 0;
+                        break;
+                case Opt_no_chk_data_crc:
+                        c->mount_opts.chk_data_crc = 1;
+                        c->no_chk_data_crc = 1;
+                        break;
                 default:
                         ubifs_err("unrecognized mount option \"%s\" "
                                   "or missing value", p);
@@ -996,6 +1059,8 @@ static int mount_ubifs(struct ubifs_info *c)
                         goto out_free;
         }
 
+        c->always_chk_crc = 1;
+
         err = ubifs_read_superblock(c);
         if (err)
                 goto out_free;
@@ -1032,8 +1097,6 @@ static int mount_ubifs(struct ubifs_info *c)
 
                 /* Create background thread */
                 c->bgt = kthread_create(ubifs_bg_thread, c, c->bgt_name);
-                if (!c->bgt)
-                        c->bgt = ERR_PTR(-EINVAL);
                 if (IS_ERR(c->bgt)) {
                         err = PTR_ERR(c->bgt);
                         c->bgt = NULL;
@@ -1139,24 +1202,28 @@ static int mount_ubifs(struct ubifs_info *c)
         if (err)
                 goto out_infos;
 
+        c->always_chk_crc = 0;
+
         ubifs_msg("mounted UBI device %d, volume %d, name \"%s\"",
                   c->vi.ubi_num, c->vi.vol_id, c->vi.name);
         if (mounted_read_only)
                 ubifs_msg("mounted read-only");
         x = (long long)c->main_lebs * c->leb_size;
-        ubifs_msg("file system size: %lld bytes (%lld KiB, %lld MiB, %d LEBs)",
-                  x, x >> 10, x >> 20, c->main_lebs);
+        ubifs_msg("file system size:   %lld bytes (%lld KiB, %lld MiB, %d "
+                  "LEBs)", x, x >> 10, x >> 20, c->main_lebs);
         x = (long long)c->log_lebs * c->leb_size + c->max_bud_bytes;
-        ubifs_msg("journal size: %lld bytes (%lld KiB, %lld MiB, %d LEBs)",
-                  x, x >> 10, x >> 20, c->log_lebs + c->max_bud_cnt);
-        ubifs_msg("default compressor: %s", ubifs_compr_name(c->default_compr));
-        ubifs_msg("media format %d, latest format %d",
+        ubifs_msg("journal size:       %lld bytes (%lld KiB, %lld MiB, %d "
+                  "LEBs)", x, x >> 10, x >> 20, c->log_lebs + c->max_bud_cnt);
+        ubifs_msg("media format:       %d (latest is %d)",
                   c->fmt_version, UBIFS_FORMAT_VERSION);
+        ubifs_msg("default compressor: %s", ubifs_compr_name(c->default_compr));
+        ubifs_msg("reserved for root:  %llu bytes (%llu KiB)",
+                c->report_rp_size, c->report_rp_size >> 10);
 
         dbg_msg("compiled on:         " __DATE__ " at " __TIME__);
         dbg_msg("min. I/O unit size:  %d bytes", c->min_io_size);
         dbg_msg("LEB size:            %d bytes (%d KiB)",
-                c->leb_size, c->leb_size / 1024);
+                c->leb_size, c->leb_size >> 10);
         dbg_msg("data journal heads:  %d",
                 c->jhead_cnt - NONDATA_JHEADS_CNT);
         dbg_msg("UUID:                %02X%02X%02X%02X-%02X%02X"
@@ -1282,6 +1349,7 @@ static int ubifs_remount_rw(struct ubifs_info *c)
 
         mutex_lock(&c->umount_mutex);
         c->remounting_rw = 1;
+        c->always_chk_crc = 1;
 
         /* Check for enough free space */
         if (ubifs_calc_available(c, c->min_idx_lebs) <= 0) {
@@ -1345,20 +1413,20 @@ static int ubifs_remount_rw(struct ubifs_info *c)
 
         /* Create background thread */
         c->bgt = kthread_create(ubifs_bg_thread, c, c->bgt_name);
-        if (!c->bgt)
-                c->bgt = ERR_PTR(-EINVAL);
         if (IS_ERR(c->bgt)) {
                 err = PTR_ERR(c->bgt);
                 c->bgt = NULL;
                 ubifs_err("cannot spawn \"%s\", error %d",
                           c->bgt_name, err);
-                return err;
+                goto out;
         }
         wake_up_process(c->bgt);
 
         c->orph_buf = vmalloc(c->leb_size);
-        if (!c->orph_buf)
-                return -ENOMEM;
+        if (!c->orph_buf) {
+                err = -ENOMEM;
+                goto out;
+        }
 
         /* Check for enough log space */
         lnum = c->lhead_lnum + 1;
@@ -1385,6 +1453,7 @@ static int ubifs_remount_rw(struct ubifs_info *c)
         dbg_gen("re-mounted read-write");
         c->vfs_sb->s_flags &= ~MS_RDONLY;
         c->remounting_rw = 0;
+        c->always_chk_crc = 0;
         mutex_unlock(&c->umount_mutex);
         return 0;
 
@@ -1400,6 +1469,7 @@ out:
         c->ileb_buf = NULL;
         ubifs_lpt_free(c, 1);
         c->remounting_rw = 0;
+        c->always_chk_crc = 0;
         mutex_unlock(&c->umount_mutex);
         return err;
 }
@@ -1408,12 +1478,9 @@ out:
  * commit_on_unmount - commit the journal when un-mounting.
  * @c: UBIFS file-system description object
  *
- * This function is called during un-mounting and it commits the journal unless
- * the "fast unmount" mode is enabled. It also avoids committing the journal if
- * it contains too few data.
- *
- * Sometimes recovery requires the journal to be committed at least once, and
- * this function takes care about this.
+ * This function is called during un-mounting and re-mounting, and it commits
+ * the journal unless the "fast unmount" mode is enabled. It also avoids
+ * committing the journal if it contains too few data.
  */
 static void commit_on_unmount(struct ubifs_info *c)
 {
diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c
index 7634c5970887..d27fd918b9c9 100644
--- a/fs/ubifs/tnc.c
+++ b/fs/ubifs/tnc.c
@@ -284,7 +284,7 @@ static struct ubifs_znode *dirty_cow_znode(struct ubifs_info *c,
         }
 
         zn = copy_znode(c, znode);
-        if (unlikely(IS_ERR(zn)))
+        if (IS_ERR(zn))
                 return zn;
 
         if (zbr->len) {
@@ -470,6 +470,10 @@ static int try_read_node(const struct ubifs_info *c, void *buf, int type,
         if (node_len != len)
                 return 0;
 
+        if (type == UBIFS_DATA_NODE && !c->always_chk_crc)
+                if (c->no_chk_data_crc)
+                        return 0;
+
         crc = crc32(UBIFS_CRC32_INIT, buf + 8, node_len - 8);
         node_crc = le32_to_cpu(ch->crc);
         if (crc != node_crc)
@@ -1128,7 +1132,7 @@ static struct ubifs_znode *dirty_cow_bottom_up(struct ubifs_info *c,
                         ubifs_assert(znode == c->zroot.znode);
                         znode = dirty_cow_znode(c, &c->zroot);
                 }
-                if (unlikely(IS_ERR(znode)) || !p)
+                if (IS_ERR(znode) || !p)
                         break;
                 ubifs_assert(path[p - 1] >= 0);
                 ubifs_assert(path[p - 1] < znode->child_cnt);
@@ -1492,6 +1496,289 @@ out:
 }
 
 /**
+ * ubifs_tnc_get_bu_keys - lookup keys for bulk-read.
+ * @c: UBIFS file-system description object
+ * @bu: bulk-read parameters and results
+ *
+ * Lookup consecutive data node keys for the same inode that reside
+ * consecutively in the same LEB.
+ */
+int ubifs_tnc_get_bu_keys(struct ubifs_info *c, struct bu_info *bu)
+{
+        int n, err = 0, lnum = -1, uninitialized_var(offs);
+        int uninitialized_var(len);
+        unsigned int block = key_block(c, &bu->key);
+        struct ubifs_znode *znode;
+
+        bu->cnt = 0;
+        bu->blk_cnt = 0;
+        bu->eof = 0;
+
+        mutex_lock(&c->tnc_mutex);
+        /* Find first key */
+        err = ubifs_lookup_level0(c, &bu->key, &znode, &n);
+        if (err < 0)
+                goto out;
+        if (err) {
+                /* Key found */
+                len = znode->zbranch[n].len;
+                /* The buffer must be big enough for at least 1 node */
+                if (len > bu->buf_len) {
+                        err = -EINVAL;
+                        goto out;
+                }
+                /* Add this key */
+                bu->zbranch[bu->cnt++] = znode->zbranch[n];
+                bu->blk_cnt += 1;
+                lnum = znode->zbranch[n].lnum;
+                offs = ALIGN(znode->zbranch[n].offs + len, 8);
+        }
+        while (1) {
+                struct ubifs_zbranch *zbr;
+                union ubifs_key *key;
+                unsigned int next_block;
+
+                /* Find next key */
+                err = tnc_next(c, &znode, &n);
+                if (err)
+                        goto out;
+                zbr = &znode->zbranch[n];
+                key = &zbr->key;
+                /* See if there is another data key for this file */
+                if (key_inum(c, key) != key_inum(c, &bu->key) ||
+                    key_type(c, key) != UBIFS_DATA_KEY) {
+                        err = -ENOENT;
+                        goto out;
+                }
+                if (lnum < 0) {
+                        /* First key found */
+                        lnum = zbr->lnum;
+                        offs = ALIGN(zbr->offs + zbr->len, 8);
+                        len = zbr->len;
+                        if (len > bu->buf_len) {
+                                err = -EINVAL;
+                                goto out;
+                        }
+                } else {
+                        /*
+                         * The data nodes must be in consecutive positions in
+                         * the same LEB.
+                         */
+                        if (zbr->lnum != lnum || zbr->offs != offs)
+                                goto out;
+                        offs += ALIGN(zbr->len, 8);
+                        len = ALIGN(len, 8) + zbr->len;
+                        /* Must not exceed buffer length */
+                        if (len > bu->buf_len)
+                                goto out;
+                }
+                /* Allow for holes */
+                next_block = key_block(c, key);
+                bu->blk_cnt += (next_block - block - 1);
+                if (bu->blk_cnt >= UBIFS_MAX_BULK_READ)
+                        goto out;
+                block = next_block;
+                /* Add this key */
+                bu->zbranch[bu->cnt++] = *zbr;
+                bu->blk_cnt += 1;
+                /* See if we have room for more */
+                if (bu->cnt >= UBIFS_MAX_BULK_READ)
+                        goto out;
+                if (bu->blk_cnt >= UBIFS_MAX_BULK_READ)
+                        goto out;
+        }
+out:
+        if (err == -ENOENT) {
+                bu->eof = 1;
+                err = 0;
+        }
+        bu->gc_seq = c->gc_seq;
+        mutex_unlock(&c->tnc_mutex);
+        if (err)
+                return err;
+        /*
+         * An enormous hole could cause bulk-read to encompass too many
+         * page cache pages, so limit the number here.
+         */
+        if (bu->blk_cnt > UBIFS_MAX_BULK_READ)
+                bu->blk_cnt = UBIFS_MAX_BULK_READ;
+        /*
+         * Ensure that bulk-read covers a whole number of page cache
+         * pages.
+         */
+        if (UBIFS_BLOCKS_PER_PAGE == 1 ||
+            !(bu->blk_cnt & (UBIFS_BLOCKS_PER_PAGE - 1)))
+                return 0;
+        if (bu->eof) {
+                /* At the end of file we can round up */
+                bu->blk_cnt += UBIFS_BLOCKS_PER_PAGE - 1;
+                return 0;
+        }
+        /* Exclude data nodes that do not make up a whole page cache page */
+        block = key_block(c, &bu->key) + bu->blk_cnt;
+        block &= ~(UBIFS_BLOCKS_PER_PAGE - 1);
+        while (bu->cnt) {
+                if (key_block(c, &bu->zbranch[bu->cnt - 1].key) < block)
+                        break;
+                bu->cnt -= 1;
+        }
+        return 0;
+}
+
+/**
+ * read_wbuf - bulk-read from a LEB with a wbuf.
+ * @wbuf: wbuf that may overlap the read
+ * @buf: buffer into which to read
+ * @len: read length
+ * @lnum: LEB number from which to read
+ * @offs: offset from which to read
+ *
+ * This functions returns %0 on success or a negative error code on failure.
+ */
+static int read_wbuf(struct ubifs_wbuf *wbuf, void *buf, int len, int lnum,
+                     int offs)
+{
+        const struct ubifs_info *c = wbuf->c;
+        int rlen, overlap;
+
+        dbg_io("LEB %d:%d, length %d", lnum, offs, len);
+        ubifs_assert(wbuf && lnum >= 0 && lnum < c->leb_cnt && offs >= 0);
+        ubifs_assert(!(offs & 7) && offs < c->leb_size);
+        ubifs_assert(offs + len <= c->leb_size);
+
+        spin_lock(&wbuf->lock);
+        overlap = (lnum == wbuf->lnum && offs + len > wbuf->offs);
+        if (!overlap) {
+                /* We may safely unlock the write-buffer and read the data */
+                spin_unlock(&wbuf->lock);
+                return ubi_read(c->ubi, lnum, buf, offs, len);
+        }
+
+        /* Don't read under wbuf */
+        rlen = wbuf->offs - offs;
+        if (rlen < 0)
+                rlen = 0;
+
+        /* Copy the rest from the write-buffer */
+        memcpy(buf + rlen, wbuf->buf + offs + rlen - wbuf->offs, len - rlen);
+        spin_unlock(&wbuf->lock);
+
+        if (rlen > 0)
+                /* Read everything that goes before write-buffer */
+                return ubi_read(c->ubi, lnum, buf, offs, rlen);
+
+        return 0;
+}
+
+/**
+ * validate_data_node - validate data nodes for bulk-read.
+ * @c: UBIFS file-system description object
+ * @buf: buffer containing data node to validate
+ * @zbr: zbranch of data node to validate
+ *
+ * This functions returns %0 on success or a negative error code on failure.
+ */
+static int validate_data_node(struct ubifs_info *c, void *buf,
+                              struct ubifs_zbranch *zbr)
+{
+        union ubifs_key key1;
+        struct ubifs_ch *ch = buf;
+        int err, len;
+
+        if (ch->node_type != UBIFS_DATA_NODE) {
+                ubifs_err("bad node type (%d but expected %d)",
+                          ch->node_type, UBIFS_DATA_NODE);
+                goto out_err;
+        }
+
+        err = ubifs_check_node(c, buf, zbr->lnum, zbr->offs, 0, 0);
+        if (err) {
+                ubifs_err("expected node type %d", UBIFS_DATA_NODE);
+                goto out;
+        }
+
+        len = le32_to_cpu(ch->len);
+        if (len != zbr->len) {
+                ubifs_err("bad node length %d, expected %d", len, zbr->len);
+                goto out_err;
+        }
+
+        /* Make sure the key of the read node is correct */
+        key_read(c, buf + UBIFS_KEY_OFFSET, &key1);
+        if (!keys_eq(c, &zbr->key, &key1)) {
+                ubifs_err("bad key in node at LEB %d:%d",
+                          zbr->lnum, zbr->offs);
+                dbg_tnc("looked for key %s found node's key %s",
+                        DBGKEY(&zbr->key), DBGKEY1(&key1));
+                goto out_err;
+        }
+
+        return 0;
+
+out_err:
+        err = -EINVAL;
+out:
+        ubifs_err("bad node at LEB %d:%d", zbr->lnum, zbr->offs);
+        dbg_dump_node(c, buf);
+        dbg_dump_stack();
+        return err;
+}
+
+/**
+ * ubifs_tnc_bulk_read - read a number of data nodes in one go.
+ * @c: UBIFS file-system description object
+ * @bu: bulk-read parameters and results
+ *
+ * This functions reads and validates the data nodes that were identified by the
+ * 'ubifs_tnc_get_bu_keys()' function. This functions returns %0 on success,
+ * -EAGAIN to indicate a race with GC, or another negative error code on
+ * failure.
+ */
+int ubifs_tnc_bulk_read(struct ubifs_info *c, struct bu_info *bu)
+{
+        int lnum = bu->zbranch[0].lnum, offs = bu->zbranch[0].offs, len, err, i;
+        struct ubifs_wbuf *wbuf;
+        void *buf;
+
+        len = bu->zbranch[bu->cnt - 1].offs;
+        len += bu->zbranch[bu->cnt - 1].len - offs;
+        if (len > bu->buf_len) {
+                ubifs_err("buffer too small %d vs %d", bu->buf_len, len);
+                return -EINVAL;
+        }
+
+        /* Do the read */
+        wbuf = ubifs_get_wbuf(c, lnum);
+        if (wbuf)
+                err = read_wbuf(wbuf, bu->buf, len, lnum, offs);
+        else
+                err = ubi_read(c->ubi, lnum, bu->buf, offs, len);
+
+        /* Check for a race with GC */
+        if (maybe_leb_gced(c, lnum, bu->gc_seq))
+                return -EAGAIN;
+
+        if (err && err != -EBADMSG) {
+                ubifs_err("failed to read from LEB %d:%d, error %d",
+                          lnum, offs, err);
+                dbg_dump_stack();
+                dbg_tnc("key %s", DBGKEY(&bu->key));
+                return err;
+        }
+
+        /* Validate the nodes read */
+        buf = bu->buf;
+        for (i = 0; i < bu->cnt; i++) {
+                err = validate_data_node(c, buf, &bu->zbranch[i]);
+                if (err)
+                        return err;
+                buf = buf + ALIGN(bu->zbranch[i].len, 8);
+        }
+
+        return 0;
+}
+
+/**
  * do_lookup_nm- look up a "hashed" node.
  * @c: UBIFS file-system description object
  * @key: node key to lookup
@@ -1675,7 +1962,7 @@ static int tnc_insert(struct ubifs_info *c, struct ubifs_znode *znode,
 {
         struct ubifs_znode *zn, *zi, *zp;
         int i, keep, move, appending = 0;
-        union ubifs_key *key = &zbr->key;
+        union ubifs_key *key = &zbr->key, *key1;
 
         ubifs_assert(n >= 0 && n <= c->fanout);
 
@@ -1716,20 +2003,33 @@ again:
         zn->level = znode->level;
 
         /* Decide where to split */
-        if (znode->level == 0 && n == c->fanout &&
-            key_type(c, key) == UBIFS_DATA_KEY) {
-                union ubifs_key *key1;
-
-                /*
-                 * If this is an inode which is being appended - do not split
-                 * it because no other zbranches can be inserted between
-                 * zbranches of consecutive data nodes anyway.
-                 */
-                key1 = &znode->zbranch[n - 1].key;
-                if (key_inum(c, key1) == key_inum(c, key) &&
-                    key_type(c, key1) == UBIFS_DATA_KEY &&
-                    key_block(c, key1) == key_block(c, key) - 1)
-                        appending = 1;
+        if (znode->level == 0 && key_type(c, key) == UBIFS_DATA_KEY) {
+                /* Try not to split consecutive data keys */
+                if (n == c->fanout) {
+                        key1 = &znode->zbranch[n - 1].key;
+                        if (key_inum(c, key1) == key_inum(c, key) &&
+                            key_type(c, key1) == UBIFS_DATA_KEY)
+                                appending = 1;
+                } else
+                        goto check_split;
+        } else if (appending && n != c->fanout) {
+                /* Try not to split consecutive data keys */
+                appending = 0;
+check_split:
+                if (n >= (c->fanout + 1) / 2) {
+                        key1 = &znode->zbranch[0].key;
+                        if (key_inum(c, key1) == key_inum(c, key) &&
+                            key_type(c, key1) == UBIFS_DATA_KEY) {
+                                key1 = &znode->zbranch[n].key;
+                                if (key_inum(c, key1) != key_inum(c, key) ||
+                                    key_type(c, key1) != UBIFS_DATA_KEY) {
+                                        keep = n;
+                                        move = c->fanout - keep;
+                                        zi = znode;
+                                        goto do_split;
+                                }
+                        }
+                }
         }
 
         if (appending) {
@@ -1759,6 +2059,8 @@ again:
                         zbr->znode->parent = zn;
         }
 
+do_split:
+
         __set_bit(DIRTY_ZNODE, &zn->flags);
         atomic_long_inc(&c->dirty_zn_cnt);
 
@@ -1785,14 +2087,11 @@ again:
 
         /* Insert new znode (produced by spitting) into the parent */
         if (zp) {
-                i = n;
+                if (n == 0 && zi == znode && znode->iip == 0)
+                        correct_parent_keys(c, znode);
+
                 /* Locate insertion point */
                 n = znode->iip + 1;
-                if (appending && n != c->fanout)
-                        appending = 0;
-
-                if (i == 0 && zi == znode && znode->iip == 0)
-                        correct_parent_keys(c, znode);
 
                 /* Tail recursion */
                 zbr->key = zn->zbranch[0].key;
diff --git a/fs/ubifs/tnc_misc.c b/fs/ubifs/tnc_misc.c
index a25c1cc1f8d9..b48db999903e 100644
--- a/fs/ubifs/tnc_misc.c
+++ b/fs/ubifs/tnc_misc.c
@@ -480,8 +480,8 @@ int ubifs_tnc_read_node(struct ubifs_info *c, struct ubifs_zbranch *zbr,
         }
 
         /* Make sure the key of the read node is correct */
-        key_read(c, key, &key1);
-        if (memcmp(node + UBIFS_KEY_OFFSET, &key1, c->key_len)) {
+        key_read(c, node + UBIFS_KEY_OFFSET, &key1);
+        if (!keys_eq(c, key, &key1)) {
                 ubifs_err("bad key in node at LEB %d:%d",
                           zbr->lnum, zbr->offs);
                 dbg_tnc("looked for key %s found node's key %s",
diff --git a/fs/ubifs/ubifs-media.h b/fs/ubifs/ubifs-media.h
index a9ecbd9af20d..0b378042a3a2 100644
--- a/fs/ubifs/ubifs-media.h
+++ b/fs/ubifs/ubifs-media.h
@@ -75,7 +75,6 @@
  */
 #define UBIFS_BLOCK_SIZE  4096
 #define UBIFS_BLOCK_SHIFT 12
-#define UBIFS_BLOCK_MASK  0x00000FFF
 
 /* UBIFS padding byte pattern (must not be first or last byte of node magic) */
 #define UBIFS_PADDING_BYTE 0xCE
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index 17c620b93eec..a7bd32fa15b9 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -142,6 +142,9 @@
 /* Maximum expected tree height for use by bottom_up_buf */
 #define BOTTOM_UP_HEIGHT 64
 
+/* Maximum number of data nodes to bulk-read */
+#define UBIFS_MAX_BULK_READ 32
+
 /*
  * Lockdep classes for UBIFS inode @ui_mutex.
  */
@@ -328,9 +331,10 @@ struct ubifs_gced_idx_leb {
  *               this inode
  * @dirty: non-zero if the inode is dirty
  * @xattr: non-zero if this is an extended attribute inode
+ * @bulk_read: non-zero if bulk-read should be used
  * @ui_mutex: serializes inode write-back with the rest of VFS operations,
- *            serializes "clean <-> dirty" state changes, protects @dirty,
- *            @ui_size, and @xattr_size
+ *            serializes "clean <-> dirty" state changes, serializes bulk-read,
+ *            protects @dirty, @bulk_read, @ui_size, and @xattr_size
  * @ui_lock: protects @synced_i_size
  * @synced_i_size: synchronized size of inode, i.e. the value of inode size
  *                 currently stored on the flash; used only for regular file
@@ -338,6 +342,8 @@ struct ubifs_gced_idx_leb {
  * @ui_size: inode size used by UBIFS when writing to flash
  * @flags: inode flags (@UBIFS_COMPR_FL, etc)
  * @compr_type: default compression type used for this inode
+ * @last_page_read: page number of last page read (for bulk read)
+ * @read_in_a_row: number of consecutive pages read in a row (for bulk read)
  * @data_len: length of the data attached to the inode
  * @data: inode's data
  *
@@ -379,12 +385,15 @@ struct ubifs_inode {
         unsigned int xattr_names;
         unsigned int dirty:1;
         unsigned int xattr:1;
+        unsigned int bulk_read:1;
         struct mutex ui_mutex;
         spinlock_t ui_lock;
         loff_t synced_i_size;
         loff_t ui_size;
         int flags;
         int compr_type;
+        pgoff_t last_page_read;
+        pgoff_t read_in_a_row;
         int data_len;
         void *data;
 };
@@ -698,8 +707,8 @@ struct ubifs_jhead {
  * struct ubifs_zbranch - key/coordinate/length branch stored in znodes.
  * @key: key
  * @znode: znode address in memory
- * @lnum: LEB number of the indexing node
- * @offs: offset of the indexing node within @lnum
+ * @lnum: LEB number of the target node (indexing node or data node)
+ * @offs: target node offset within @lnum
  * @len: target node length
  */
 struct ubifs_zbranch {
@@ -744,6 +753,28 @@ struct ubifs_znode {
 };
 
 /**
+ * struct bu_info - bulk-read information
+ * @key: first data node key
+ * @zbranch: zbranches of data nodes to bulk read
+ * @buf: buffer to read into
+ * @buf_len: buffer length
+ * @gc_seq: GC sequence number to detect races with GC
+ * @cnt: number of data nodes for bulk read
+ * @blk_cnt: number of data blocks including holes
+ * @oef: end of file reached
+ */
+struct bu_info {
+        union ubifs_key key;
+        struct ubifs_zbranch zbranch[UBIFS_MAX_BULK_READ];
+        void *buf;
+        int buf_len;
+        int gc_seq;
+        int cnt;
+        int blk_cnt;
+        int eof;
+};
+
+/**
  * struct ubifs_node_range - node length range description data structure.
  * @len: fixed node length
  * @min_len: minimum possible node length
@@ -862,9 +893,13 @@ struct ubifs_orphan {
 /**
  * struct ubifs_mount_opts - UBIFS-specific mount options information.
  * @unmount_mode: selected unmount mode (%0 default, %1 normal, %2 fast)
+ * @bulk_read: enable bulk-reads
+ * @chk_data_crc: check CRCs when reading data nodes
  */
 struct ubifs_mount_opts {
         unsigned int unmount_mode:2;
+        unsigned int bulk_read:2;
+        unsigned int chk_data_crc:2;
 };
 
 /**
@@ -905,13 +940,12 @@ struct ubifs_mount_opts {
  * @cmt_state: commit state
  * @cs_lock: commit state lock
  * @cmt_wq: wait queue to sleep on if the log is full and a commit is running
+ *
  * @fast_unmount: do not run journal commit before un-mounting
  * @big_lpt: flag that LPT is too big to write whole during commit
- * @check_lpt_free: flag that indicates LPT GC may be needed
- * @nospace: non-zero if the file-system does not have flash space (used as
- *           optimization)
- * @nospace_rp: the same as @nospace, but additionally means that even reserved
- *              pool is full
+ * @no_chk_data_crc: do not check CRCs when reading data nodes (except during
+ *                   recovery)
+ * @bulk_read: enable bulk-reads
  *
  * @tnc_mutex: protects the Tree Node Cache (TNC), @zroot, @cnext, @enext, and
  *             @calc_idx_sz
@@ -935,6 +969,7 @@ struct ubifs_mount_opts {
  * @mst_node: master node
  * @mst_offs: offset of valid master node
  * @mst_mutex: protects the master node area, @mst_node, and @mst_offs
+ * @bulk_read_buf_size: buffer size for bulk-reads
  *
  * @log_lebs: number of logical eraseblocks in the log
  * @log_bytes: log size in bytes
@@ -977,12 +1012,17 @@ struct ubifs_mount_opts {
  *                        but which still have to be taken into account because
  *                        the index has not been committed so far
  * @space_lock: protects @budg_idx_growth, @budg_data_growth, @budg_dd_growth,
- *              @budg_uncommited_idx, @min_idx_lebs, @old_idx_sz, and @lst;
+ *              @budg_uncommited_idx, @min_idx_lebs, @old_idx_sz, @lst,
+ *              @nospace, and @nospace_rp;
  * @min_idx_lebs: minimum number of LEBs required for the index
  * @old_idx_sz: size of index on flash
  * @calc_idx_sz: temporary variable which is used to calculate new index size
  *               (contains accurate new index size at end of TNC commit start)
  * @lst: lprops statistics
+ * @nospace: non-zero if the file-system does not have flash space (used as
+ *           optimization)
+ * @nospace_rp: the same as @nospace, but additionally means that even reserved
+ *              pool is full
  *
  * @page_budget: budget for a page
  * @inode_budget: budget for an inode
@@ -1061,6 +1101,7 @@ struct ubifs_mount_opts {
  * @lpt_drty_flgs: dirty flags for LPT special nodes e.g. ltab
  * @dirty_nn_cnt: number of dirty nnodes
  * @dirty_pn_cnt: number of dirty pnodes
+ * @check_lpt_free: flag that indicates LPT GC may be needed
  * @lpt_sz: LPT size
  * @lpt_nod_buf: buffer for an on-flash nnode or pnode
  * @lpt_buf: buffer of LEB size used by LPT
@@ -1102,6 +1143,7 @@ struct ubifs_mount_opts {
  * @rcvrd_mst_node: recovered master node to write when mounting ro to rw
  * @size_tree: inode size information for recovery
  * @remounting_rw: set while remounting from ro to rw (sb flags have MS_RDONLY)
+ * @always_chk_crc: always check CRCs (while mounting and remounting rw)
  * @mount_opts: UBIFS-specific mount options
  *
  * @dbg_buf: a buffer of LEB size used for debugging purposes
@@ -1146,11 +1188,11 @@ struct ubifs_info {
         int cmt_state;
         spinlock_t cs_lock;
         wait_queue_head_t cmt_wq;
+
         unsigned int fast_unmount:1;
         unsigned int big_lpt:1;
-        unsigned int check_lpt_free:1;
-        unsigned int nospace:1;
-        unsigned int nospace_rp:1;
+        unsigned int no_chk_data_crc:1;
+        unsigned int bulk_read:1;
 
         struct mutex tnc_mutex;
         struct ubifs_zbranch zroot;
@@ -1175,6 +1217,7 @@ struct ubifs_info {
         struct ubifs_mst_node *mst_node;
         int mst_offs;
         struct mutex mst_mutex;
+        int bulk_read_buf_size;
 
         int log_lebs;
         long long log_bytes;
@@ -1218,6 +1261,8 @@ struct ubifs_info {
         unsigned long long old_idx_sz;
         unsigned long long calc_idx_sz;
         struct ubifs_lp_stats lst;
+        unsigned int nospace:1;
+        unsigned int nospace_rp:1;
 
         int page_budget;
         int inode_budget;
@@ -1294,6 +1339,7 @@ struct ubifs_info {
         int lpt_drty_flgs;
         int dirty_nn_cnt;
         int dirty_pn_cnt;
+        int check_lpt_free;
         long long lpt_sz;
         void *lpt_nod_buf;
         void *lpt_buf;
@@ -1335,6 +1381,7 @@ struct ubifs_info {
         struct ubifs_mst_node *rcvrd_mst_node;
         struct rb_root size_tree;
         int remounting_rw;
+        int always_chk_crc;
         struct ubifs_mount_opts mount_opts;
 
 #ifdef CONFIG_UBIFS_FS_DEBUG
@@ -1347,6 +1394,12 @@ struct ubifs_info {
         unsigned long fail_timeout;
         unsigned int fail_cnt;
         unsigned int fail_cnt_max;
+        long long chk_lpt_sz;
+        long long chk_lpt_sz2;
+        long long chk_lpt_wastage;
+        int chk_lpt_lebs;
+        int new_nhead_lnum;
+        int new_nhead_offs;
 #endif
 };
 
@@ -1377,7 +1430,7 @@ int ubifs_read_node_wbuf(struct ubifs_wbuf *wbuf, void *buf, int type, int len,
 int ubifs_write_node(struct ubifs_info *c, void *node, int len, int lnum,
                      int offs, int dtype);
 int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum,
-                     int offs, int quiet);
+                     int offs, int quiet, int chk_crc);
 void ubifs_prepare_node(struct ubifs_info *c, void *buf, int len, int pad);
 void ubifs_prep_grp_node(struct ubifs_info *c, void *node, int len, int last);
 int ubifs_io_init(struct ubifs_info *c);
@@ -1490,6 +1543,8 @@ void destroy_old_idx(struct ubifs_info *c);
 int is_idx_node_in_tnc(struct ubifs_info *c, union ubifs_key *key, int level,
                        int lnum, int offs);
 int insert_old_idx_znode(struct ubifs_info *c, struct ubifs_znode *znode);
+int ubifs_tnc_get_bu_keys(struct ubifs_info *c, struct bu_info *bu);
+int ubifs_tnc_bulk_read(struct ubifs_info *c, struct bu_info *bu);
 
 /* tnc_misc.c */
 struct ubifs_znode *ubifs_tnc_levelorder_next(struct ubifs_znode *zr,
@@ -1586,12 +1641,10 @@ int ubifs_lpt_post_commit(struct ubifs_info *c);
 void ubifs_lpt_free(struct ubifs_info *c, int wr_only);
 
 /* lprops.c */
-void ubifs_get_lprops(struct ubifs_info *c);
 const struct ubifs_lprops *ubifs_change_lp(struct ubifs_info *c,
                                            const struct ubifs_lprops *lp,
                                            int free, int dirty, int flags,
                                            int idx_gc_cnt);
-void ubifs_release_lprops(struct ubifs_info *c);
 void ubifs_get_lp_stats(struct ubifs_info *c, struct ubifs_lp_stats *stats);
 void ubifs_add_to_cat(struct ubifs_info *c, struct ubifs_lprops *lprops,
                       int cat);
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index 649bec78b645..cfd31e229c89 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -446,7 +446,7 @@ ssize_t ubifs_listxattr(struct dentry *dentry, char *buffer, size_t size)
                 int type;
 
                 xent = ubifs_tnc_next_ent(c, &key, &nm);
-                if (unlikely(IS_ERR(xent))) {
+                if (IS_ERR(xent)) {
                         err = PTR_ERR(xent);
                         break;
                 }
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 5698bbf83bbf..e25e7010627b 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -369,7 +369,7 @@ enum {
         Opt_err, Opt_uforget, Opt_uignore, Opt_gforget, Opt_gignore
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         {Opt_novrs,     "novrs"},
         {Opt_nostrict,  "nostrict"},
         {Opt_bs,        "bs=%u"},
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index 3141969b456d..e65212dfb60e 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -309,7 +309,7 @@ enum {
        Opt_err
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         {Opt_type_old, "ufstype=old"},
         {Opt_type_sunx86, "ufstype=sunx86"},
         {Opt_type_sun, "ufstype=sun"},
@@ -1233,7 +1233,7 @@ static int ufs_show_options(struct seq_file *seq, struct vfsmount *vfs)
 {
         struct ufs_sb_info *sbi = UFS_SB(vfs->mnt_sb);
         unsigned mval = sbi->s_mount_opt & UFS_MOUNT_UFSTYPE;
-        struct match_token *tp = tokens;
+        const struct match_token *tp = tokens;
 
         while (tp->token != Opt_onerror_panic && tp->token != mval)
                 ++tp;
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 986061ae1b9b..36d5fcd3f593 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -1001,12 +1001,13 @@ xfs_buf_iodone_work(
          * We can get an EOPNOTSUPP to ordered writes.  Here we clear the
          * ordered flag and reissue them.  Because we can't tell the higher
          * layers directly that they should not issue ordered I/O anymore, they
-         * need to check if the ordered flag was cleared during I/O completion.
+         * need to check if the _XFS_BARRIER_FAILED flag was set during I/O completion.
          */
         if ((bp->b_error == EOPNOTSUPP) &&
             (bp->b_flags & (XBF_ORDERED|XBF_ASYNC)) == (XBF_ORDERED|XBF_ASYNC)) {
                 XB_TRACE(bp, "ordered_retry", bp->b_iodone);
                 bp->b_flags &= ~XBF_ORDERED;
+                bp->b_flags |= _XFS_BARRIER_FAILED;
                 xfs_buf_iorequest(bp);
         } else if (bp->b_iodone)
                 (*(bp->b_iodone))(bp);
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index fe0109956656..456519a088c7 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -85,6 +85,14 @@ typedef enum {
          * modifications being lost.
          */
         _XBF_PAGE_LOCKED = (1 << 22),
+
+        /*
+         * If we try a barrier write, but it fails we have to communicate
+         * this to the upper layers.  Unfortunately b_error gets overwritten
+         * when the buffer is re-issued so we have to add another flag to
+         * keep this information.
+         */
+        _XFS_BARRIER_FAILED = (1 << 23),
 } xfs_buf_flags_t;
 
 typedef enum {
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 18d3c8487835..e39013619b26 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -158,7 +158,7 @@ enum {
         Opt_barrier, Opt_nobarrier, Opt_err
 };
 
-static match_table_t tokens = {
+static const match_table_t tokens = {
         {Opt_barrier, "barrier"},
         {Opt_nobarrier, "nobarrier"},
         {Opt_err, NULL}
@@ -1323,7 +1323,7 @@ xfs_fs_remount(
         "XFS: mount option \"%s\" not supported for remount\n", p);
                         return -EINVAL;
 #else
-                        return 0;
+                        break;
 #endif
                 }
         }
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 503ea89e8b9a..0b02c6443551 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1033,11 +1033,12 @@ xlog_iodone(xfs_buf_t *bp)
         l = iclog->ic_log;
 
         /*
-         * If the ordered flag has been removed by a lower
-         * layer, it means the underlyin device no longer supports
+         * If the _XFS_BARRIER_FAILED flag was set by a lower
+         * layer, it means the underlying device no longer supports
          * barrier I/O. Warn loudly and turn off barriers.
          */
-        if ((l->l_mp->m_flags & XFS_MOUNT_BARRIER) && !XFS_BUF_ISORDERED(bp)) {
+        if (bp->b_flags & _XFS_BARRIER_FAILED) {
+                bp->b_flags &= ~_XFS_BARRIER_FAILED;
                 l->l_mp->m_flags &= ~XFS_MOUNT_BARRIER;
                 xfs_fs_cmn_err(CE_WARN, l->l_mp,
                                 "xlog_iodone: Barriers are no longer supported"