225 files changed, 4035 insertions, 3011 deletions

diff --git a/fs/9p/acl.c b/fs/9p/acl.c
index 515455296378..535ab6eccb1a 100644
--- a/fs/9p/acl.c
+++ b/fs/9p/acl.c
@@ -262,7 +262,7 @@ static int v9fs_xattr_get_acl(struct dentry *dentry, const char *name,
         if (strcmp(name, "") != 0)
                 return -EINVAL;
 
-        v9ses = v9fs_inode2v9ses(dentry->d_inode);
+        v9ses = v9fs_dentry2v9ses(dentry);
         /*
          * We allow set/get/list of acl when access=client is not specified
          */
@@ -312,7 +312,7 @@ static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name,
         if (strcmp(name, "") != 0)
                 return -EINVAL;
 
-        v9ses = v9fs_inode2v9ses(dentry->d_inode);
+        v9ses = v9fs_dentry2v9ses(dentry);
         /*
          * set the attribute on the remote. Without even looking at the
          * xattr value. We leave it to the server to validate
@@ -323,7 +323,7 @@ static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name,
 
         if (S_ISLNK(inode->i_mode))
                 return -EOPNOTSUPP;
-        if (!is_owner_or_cap(inode))
+        if (!inode_owner_or_capable(inode))
                 return -EPERM;
         if (value) {
                 /* update the cached acl value */
diff --git a/fs/9p/fid.c b/fs/9p/fid.c
index cd63e002d826..0ee594569dcc 100644
--- a/fs/9p/fid.c
+++ b/fs/9p/fid.c
@@ -134,7 +134,7 @@ static struct p9_fid *v9fs_fid_lookup_with_uid(struct dentry *dentry,
         struct v9fs_session_info *v9ses;
         struct p9_fid *fid, *old_fid = NULL;
 
-        v9ses = v9fs_inode2v9ses(dentry->d_inode);
+        v9ses = v9fs_dentry2v9ses(dentry);
         access = v9ses->flags & V9FS_ACCESS_MASK;
         fid = v9fs_fid_find(dentry, uid, any);
         if (fid)
@@ -237,7 +237,7 @@ struct p9_fid *v9fs_fid_lookup(struct dentry *dentry)
         int  any, access;
         struct v9fs_session_info *v9ses;
 
-        v9ses = v9fs_inode2v9ses(dentry->d_inode);
+        v9ses = v9fs_dentry2v9ses(dentry);
         access = v9ses->flags & V9FS_ACCESS_MASK;
         switch (access) {
         case V9FS_ACCESS_SINGLE:
@@ -286,9 +286,11 @@ static struct p9_fid *v9fs_fid_clone_with_uid(struct dentry *dentry, uid_t uid)
 
 struct p9_fid *v9fs_writeback_fid(struct dentry *dentry)
 {
-        int err;
+        int err, flags;
         struct p9_fid *fid;
+        struct v9fs_session_info *v9ses;
 
+        v9ses = v9fs_dentry2v9ses(dentry);
         fid = v9fs_fid_clone_with_uid(dentry, 0);
         if (IS_ERR(fid))
                 goto error_out;
@@ -297,8 +299,17 @@ struct p9_fid *v9fs_writeback_fid(struct dentry *dentry)
          * dirty pages. We always request for the open fid in read-write
          * mode so that a partial page write which result in page
          * read can work.
+         *
+         * we don't have a tsyncfs operation for older version
+         * of protocol. So make sure the write back fid is
+         * opened in O_SYNC mode.
          */
-        err = p9_client_open(fid, O_RDWR);
+        if (!v9fs_proto_dotl(v9ses))
+                flags = O_RDWR | O_SYNC;
+        else
+                flags = O_RDWR;
+
+        err = p9_client_open(fid, flags);
         if (err < 0) {
                 p9_client_clunk(fid);
                 fid = ERR_PTR(err);
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index bd8496db135b..9665c2b840e6 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -130,6 +130,7 @@ struct v9fs_inode {
 #endif
         unsigned int cache_validity;
         struct p9_fid *writeback_fid;
+        struct mutex v_mutex;
         struct inode vfs_inode;
 };
 
@@ -173,6 +174,11 @@ static inline struct v9fs_session_info *v9fs_inode2v9ses(struct inode *inode)
         return (inode->i_sb->s_fs_info);
 }
 
+static inline struct v9fs_session_info *v9fs_dentry2v9ses(struct dentry *dentry)
+{
+        return dentry->d_sb->s_fs_info;
+}
+
 static inline int v9fs_proto_dotu(struct v9fs_session_info *v9ses)
 {
         return v9ses->flags & V9FS_PROTO_2000U;
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 78bcb97c3425..ffed55817f0c 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -90,7 +90,9 @@ int v9fs_file_open(struct inode *inode, struct file *file)
         }
 
         file->private_data = fid;
-        if (v9ses->cache && !v9inode->writeback_fid) {
+        mutex_lock(&v9inode->v_mutex);
+        if (v9ses->cache && !v9inode->writeback_fid &&
+            ((file->f_flags & O_ACCMODE) != O_RDONLY)) {
                 /*
                  * clone a fid and add it to writeback_fid
                  * we do it during open time instead of
@@ -101,10 +103,12 @@ int v9fs_file_open(struct inode *inode, struct file *file)
                 fid = v9fs_writeback_fid(file->f_path.dentry);
                 if (IS_ERR(fid)) {
                         err = PTR_ERR(fid);
+                        mutex_unlock(&v9inode->v_mutex);
                         goto out_error;
                 }
                 v9inode->writeback_fid = (void *) fid;
         }
+        mutex_unlock(&v9inode->v_mutex);
 #ifdef CONFIG_9P_FSCACHE
         if (v9ses->cache)
                 v9fs_cache_inode_set_cookie(inode, file);
@@ -504,9 +508,12 @@ v9fs_file_write(struct file *filp, const char __user * data,
         if (!count)
                 goto out;
 
-        return v9fs_file_write_internal(filp->f_path.dentry->d_inode,
+        retval = v9fs_file_write_internal(filp->f_path.dentry->d_inode,
                                         filp->private_data,
-                                        data, count, offset, 1);
+                                        data, count, &origin, 1);
+        /* update offset on successful write */
+        if (retval > 0)
+                *offset = origin;
 out:
         return retval;
 }
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 8a2c232f708a..7f6c67703195 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -221,6 +221,7 @@ struct inode *v9fs_alloc_inode(struct super_block *sb)
 #endif
         v9inode->writeback_fid = NULL;
         v9inode->cache_validity = 0;
+        mutex_init(&v9inode->v_mutex);
         return &v9inode->vfs_inode;
 }
 
@@ -650,7 +651,9 @@ v9fs_vfs_create(struct inode *dir, struct dentry *dentry, int mode,
         /* if we are opening a file, assign the open fid to the file */
         if (nd && nd->flags & LOOKUP_OPEN) {
                 v9inode = V9FS_I(dentry->d_inode);
-                if (v9ses->cache && !v9inode->writeback_fid) {
+                mutex_lock(&v9inode->v_mutex);
+                if (v9ses->cache && !v9inode->writeback_fid &&
+                    ((flags & O_ACCMODE) != O_RDONLY)) {
                         /*
                          * clone a fid and add it to writeback_fid
                          * we do it during open time instead of
@@ -661,10 +664,12 @@ v9fs_vfs_create(struct inode *dir, struct dentry *dentry, int mode,
                         inode_fid = v9fs_writeback_fid(dentry);
                         if (IS_ERR(inode_fid)) {
                                 err = PTR_ERR(inode_fid);
+                                mutex_unlock(&v9inode->v_mutex);
                                 goto error;
                         }
                         v9inode->writeback_fid = (void *) inode_fid;
                 }
+                mutex_unlock(&v9inode->v_mutex);
                 filp = lookup_instantiate_filp(nd, dentry, generic_file_open);
                 if (IS_ERR(filp)) {
                         err = PTR_ERR(filp);
@@ -931,7 +936,7 @@ v9fs_vfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
 
         P9_DPRINTK(P9_DEBUG_VFS, "dentry: %p\n", dentry);
         err = -EPERM;
-        v9ses = v9fs_inode2v9ses(dentry->d_inode);
+        v9ses = v9fs_dentry2v9ses(dentry);
         if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
                 generic_fillattr(dentry->d_inode, stat);
                 return 0;
@@ -967,8 +972,12 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr)
         struct p9_wstat wstat;
 
         P9_DPRINTK(P9_DEBUG_VFS, "\n");
+        retval = inode_change_ok(dentry->d_inode, iattr);
+        if (retval)
+                return retval;
+
         retval = -EPERM;
-        v9ses = v9fs_inode2v9ses(dentry->d_inode);
+        v9ses = v9fs_dentry2v9ses(dentry);
         fid = v9fs_fid_lookup(dentry);
         if(IS_ERR(fid))
                 return PTR_ERR(fid);
@@ -993,12 +1002,7 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr)
                 if (iattr->ia_valid & ATTR_GID)
                         wstat.n_gid = iattr->ia_gid;
         }
-        if ((iattr->ia_valid & ATTR_SIZE) &&
-            iattr->ia_size != i_size_read(dentry->d_inode)) {
-                retval = vmtruncate(dentry->d_inode, iattr->ia_size);
-                if (retval)
-                        return retval;
-        }
+
         /* Write all dirty data */
         if (S_ISREG(dentry->d_inode->i_mode))
                 filemap_write_and_wait(dentry->d_inode->i_mapping);
@@ -1006,6 +1010,11 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr)
         retval = p9_client_wstat(fid, &wstat);
         if (retval < 0)
                 return retval;
+
+        if ((iattr->ia_valid & ATTR_SIZE) &&
+            iattr->ia_size != i_size_read(dentry->d_inode))
+                truncate_setsize(dentry->d_inode, iattr->ia_size);
+
         v9fs_invalidate_inode_attr(dentry->d_inode);
 
         setattr_copy(dentry->d_inode, iattr);
@@ -1130,7 +1139,7 @@ static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen)
 
         P9_DPRINTK(P9_DEBUG_VFS, " %s\n", dentry->d_name.name);
         retval = -EPERM;
-        v9ses = v9fs_inode2v9ses(dentry->d_inode);
+        v9ses = v9fs_dentry2v9ses(dentry);
         fid = v9fs_fid_lookup(dentry);
         if (IS_ERR(fid))
                 return PTR_ERR(fid);
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 67c138e94feb..ffbb113d5f33 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -245,7 +245,9 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, int omode,
         v9fs_set_create_acl(dentry, dacl, pacl);
 
         v9inode = V9FS_I(inode);
-        if (v9ses->cache && !v9inode->writeback_fid) {
+        mutex_lock(&v9inode->v_mutex);
+        if (v9ses->cache && !v9inode->writeback_fid &&
+            ((flags & O_ACCMODE) != O_RDONLY)) {
                 /*
                  * clone a fid and add it to writeback_fid
                  * we do it during open time instead of
@@ -256,10 +258,12 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, int omode,
                 inode_fid = v9fs_writeback_fid(dentry);
                 if (IS_ERR(inode_fid)) {
                         err = PTR_ERR(inode_fid);
+                        mutex_unlock(&v9inode->v_mutex);
                         goto error;
                 }
                 v9inode->writeback_fid = (void *) inode_fid;
         }
+        mutex_unlock(&v9inode->v_mutex);
         /* Since we are opening a file, assign the open fid to the file */
         filp = lookup_instantiate_filp(nd, dentry, generic_file_open);
         if (IS_ERR(filp)) {
@@ -391,7 +395,7 @@ v9fs_vfs_getattr_dotl(struct vfsmount *mnt, struct dentry *dentry,
 
         P9_DPRINTK(P9_DEBUG_VFS, "dentry: %p\n", dentry);
         err = -EPERM;
-        v9ses = v9fs_inode2v9ses(dentry->d_inode);
+        v9ses = v9fs_dentry2v9ses(dentry);
         if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
                 generic_fillattr(dentry->d_inode, stat);
                 return 0;
@@ -448,17 +452,11 @@ int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr)
         p9attr.mtime_nsec = iattr->ia_mtime.tv_nsec;
 
         retval = -EPERM;
-        v9ses = v9fs_inode2v9ses(dentry->d_inode);
+        v9ses = v9fs_dentry2v9ses(dentry);
         fid = v9fs_fid_lookup(dentry);
         if (IS_ERR(fid))
                 return PTR_ERR(fid);
 
-        if ((iattr->ia_valid & ATTR_SIZE) &&
-            iattr->ia_size != i_size_read(dentry->d_inode)) {
-                retval = vmtruncate(dentry->d_inode, iattr->ia_size);
-                if (retval)
-                        return retval;
-        }
         /* Write all dirty data */
         if (S_ISREG(dentry->d_inode->i_mode))
                 filemap_write_and_wait(dentry->d_inode->i_mapping);
@@ -466,8 +464,12 @@ int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr)
         retval = p9_client_setattr(fid, &p9attr);
         if (retval < 0)
                 return retval;
-        v9fs_invalidate_inode_attr(dentry->d_inode);
 
+        if ((iattr->ia_valid & ATTR_SIZE) &&
+            iattr->ia_size != i_size_read(dentry->d_inode))
+                truncate_setsize(dentry->d_inode, iattr->ia_size);
+
+        v9fs_invalidate_inode_attr(dentry->d_inode);
         setattr_copy(dentry->d_inode, iattr);
         mark_inode_dirty(dentry->d_inode);
         if (iattr->ia_valid & ATTR_MODE) {
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 09fd08d1606f..f3eed3383e4f 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -262,7 +262,7 @@ static int v9fs_statfs(struct dentry *dentry, struct kstatfs *buf)
                 goto done;
         }
 
-        v9ses = v9fs_inode2v9ses(dentry->d_inode);
+        v9ses = v9fs_dentry2v9ses(dentry);
         if (v9fs_proto_dotl(v9ses)) {
                 res = p9_client_statfs(fid, &rs);
                 if (res == 0) {
diff --git a/fs/adfs/adfs.h b/fs/adfs/adfs.h
index 2ff622f6f547..718ac1f440c6 100644
--- a/fs/adfs/adfs.h
+++ b/fs/adfs/adfs.h
@@ -50,6 +50,7 @@ struct adfs_sb_info {
         gid_t           s_gid;          /* owner gid                             */
         umode_t         s_owner_mask;   /* ADFS owner perm -> unix perm          */
         umode_t         s_other_mask;   /* ADFS other perm -> unix perm          */
+        int             s_ftsuffix;     /* ,xyz hex filetype suffix option */
 
         __u32           s_ids_per_zone; /* max. no ids in one zone               */
         __u32           s_idlen;        /* length of ID in map                   */
@@ -79,6 +80,10 @@ struct adfs_dir {
 
         int                     nr_buffers;
         struct buffer_head      *bh[4];
+
+        /* big directories need allocated buffers */
+        struct buffer_head      **bh_fplus;
+
         unsigned int            pos;
         unsigned int            parent_id;
 
@@ -89,7 +94,7 @@ struct adfs_dir {
 /*
  * This is the overall maximum name length
  */
-#define ADFS_MAX_NAME_LEN       256
+#define ADFS_MAX_NAME_LEN       (256 + 4) /* +4 for ,xyz hex filetype suffix */
 struct object_info {
         __u32           parent_id;              /* parent object id     */
         __u32           file_id;                /* object id            */
@@ -97,10 +102,26 @@ struct object_info {
         __u32           execaddr;               /* execution address    */
         __u32           size;                   /* size                 */
         __u8            attr;                   /* RISC OS attributes   */
-        unsigned char   name_len;               /* name length          */
+        unsigned int    name_len;               /* name length          */
         char            name[ADFS_MAX_NAME_LEN];/* file name            */
+
+        /* RISC OS file type (12-bit: derived from loadaddr) */
+        __u16           filetype;
 };
 
+/* RISC OS 12-bit filetype converts to ,xyz hex filename suffix */
+static inline int append_filetype_suffix(char *buf, __u16 filetype)
+{
+        if (filetype == 0xffff) /* no explicit 12-bit file type was set */
+                return 0;
+
+        *buf++ = ',';
+        *buf++ = hex_asc_lo(filetype >> 8);
+        *buf++ = hex_asc_lo(filetype >> 4);
+        *buf++ = hex_asc_lo(filetype >> 0);
+        return 4;
+}
+
 struct adfs_dir_ops {
         int     (*read)(struct super_block *sb, unsigned int id, unsigned int sz, struct adfs_dir *dir);
         int     (*setpos)(struct adfs_dir *dir, unsigned int fpos);
diff --git a/fs/adfs/dir_f.c b/fs/adfs/dir_f.c
index bafc71222e25..4bbe853ee50a 100644
--- a/fs/adfs/dir_f.c
+++ b/fs/adfs/dir_f.c
@@ -52,7 +52,6 @@ static inline int adfs_readname(char *buf, char *ptr, int maxlen)
                         *buf++ = *ptr;
                 ptr++;
         }
-        *buf = '\0';
 
         return buf - old_buf;
 }
@@ -208,7 +207,8 @@ release_buffers:
  * convert a disk-based directory entry to a Linux ADFS directory entry
  */
 static inline void
-adfs_dir2obj(struct object_info *obj, struct adfs_direntry *de)
+adfs_dir2obj(struct adfs_dir *dir, struct object_info *obj,
+        struct adfs_direntry *de)
 {
         obj->name_len = adfs_readname(obj->name, de->dirobname, ADFS_F_NAME_LEN);
         obj->file_id  = adfs_readval(de->dirinddiscadd, 3);
@@ -216,6 +216,23 @@ adfs_dir2obj(struct object_info *obj, struct adfs_direntry *de)
         obj->execaddr = adfs_readval(de->direxec, 4);
         obj->size     = adfs_readval(de->dirlen,  4);
         obj->attr     = de->newdiratts;
+        obj->filetype = -1;
+
+        /*
+         * object is a file and is filetyped and timestamped?
+         * RISC OS 12-bit filetype is stored in load_address[19:8]
+         */
+        if ((0 == (obj->attr & ADFS_NDA_DIRECTORY)) &&
+                (0xfff00000 == (0xfff00000 & obj->loadaddr))) {
+                obj->filetype = (__u16) ((0x000fff00 & obj->loadaddr) >> 8);
+
+                /* optionally append the ,xyz hex filetype suffix */
+                if (ADFS_SB(dir->sb)->s_ftsuffix)
+                        obj->name_len +=
+                                append_filetype_suffix(
+                                        &obj->name[obj->name_len],
+                                        obj->filetype);
+        }
 }
 
 /*
@@ -260,7 +277,7 @@ __adfs_dir_get(struct adfs_dir *dir, int pos, struct object_info *obj)
         if (!de.dirobname[0])
                 return -ENOENT;
 
-        adfs_dir2obj(obj, &de);
+        adfs_dir2obj(dir, obj, &de);
 
         return 0;
 }
diff --git a/fs/adfs/dir_fplus.c b/fs/adfs/dir_fplus.c
index 1796bb352d05..d9e3bee4e653 100644
--- a/fs/adfs/dir_fplus.c
+++ b/fs/adfs/dir_fplus.c
@@ -8,6 +8,7 @@
  * published by the Free Software Foundation.
  */
 #include <linux/buffer_head.h>
+#include <linux/slab.h>
 #include "adfs.h"
 #include "dir_fplus.h"
 
@@ -22,30 +23,53 @@ adfs_fplus_read(struct super_block *sb, unsigned int id, unsigned int sz, struct
 
         dir->nr_buffers = 0;
 
+        /* start off using fixed bh set - only alloc for big dirs */
+        dir->bh_fplus = &dir->bh[0];
+
         block = __adfs_block_map(sb, id, 0);
         if (!block) {
                 adfs_error(sb, "dir object %X has a hole at offset 0", id);
                 goto out;
         }
 
-        dir->bh[0] = sb_bread(sb, block);
-        if (!dir->bh[0])
+        dir->bh_fplus[0] = sb_bread(sb, block);
+        if (!dir->bh_fplus[0])
                 goto out;
         dir->nr_buffers += 1;
 
-        h = (struct adfs_bigdirheader *)dir->bh[0]->b_data;
+        h = (struct adfs_bigdirheader *)dir->bh_fplus[0]->b_data;
         size = le32_to_cpu(h->bigdirsize);
         if (size != sz) {
-                printk(KERN_WARNING "adfs: adfs_fplus_read: directory header size\n"
-                                " does not match directory size\n");
+                printk(KERN_WARNING "adfs: adfs_fplus_read:"
+                                        " directory header size %X\n"
+                                        " does not match directory size %X\n",
+                                        size, sz);
         }
 
         if (h->bigdirversion[0] != 0 || h->bigdirversion[1] != 0 ||
             h->bigdirversion[2] != 0 || size & 2047 ||
-            h->bigdirstartname != cpu_to_le32(BIGDIRSTARTNAME))
+            h->bigdirstartname != cpu_to_le32(BIGDIRSTARTNAME)) {
+                printk(KERN_WARNING "adfs: dir object %X has"
+                                        " malformed dir header\n", id);
                 goto out;
+        }
 
         size >>= sb->s_blocksize_bits;
+        if (size > sizeof(dir->bh)/sizeof(dir->bh[0])) {
+                /* this directory is too big for fixed bh set, must allocate */
+                struct buffer_head **bh_fplus =
+                        kzalloc(size * sizeof(struct buffer_head *),
+                                GFP_KERNEL);
+                if (!bh_fplus) {
+                        adfs_error(sb, "not enough memory for"
+                                        " dir object %X (%d blocks)", id, size);
+                        goto out;
+                }
+                dir->bh_fplus = bh_fplus;
+                /* copy over the pointer to the block that we've already read */
+                dir->bh_fplus[0] = dir->bh[0];
+        }
+
         for (blk = 1; blk < size; blk++) {
                 block = __adfs_block_map(sb, id, blk);
                 if (!block) {
@@ -53,25 +77,44 @@ adfs_fplus_read(struct super_block *sb, unsigned int id, unsigned int sz, struct
                         goto out;
                 }
 
-                dir->bh[blk] = sb_bread(sb, block);
-                if (!dir->bh[blk])
+                dir->bh_fplus[blk] = sb_bread(sb, block);
+                if (!dir->bh_fplus[blk]) {
+                        adfs_error(sb,  "dir object %X failed read for"
+                                        " offset %d, mapped block %X",
+                                        id, blk, block);
                         goto out;
-                dir->nr_buffers = blk;
+                }
+
+                dir->nr_buffers += 1;
         }
 
-        t = (struct adfs_bigdirtail *)(dir->bh[size - 1]->b_data + (sb->s_blocksize - 8));
+        t = (struct adfs_bigdirtail *)
+                (dir->bh_fplus[size - 1]->b_data + (sb->s_blocksize - 8));
 
         if (t->bigdirendname != cpu_to_le32(BIGDIRENDNAME) ||
             t->bigdirendmasseq != h->startmasseq ||
-            t->reserved[0] != 0 || t->reserved[1] != 0)
+            t->reserved[0] != 0 || t->reserved[1] != 0) {
+                printk(KERN_WARNING "adfs: dir object %X has "
+                                        "malformed dir end\n", id);
                 goto out;
+        }
 
         dir->parent_id = le32_to_cpu(h->bigdirparent);
         dir->sb = sb;
         return 0;
+
 out:
-        for (i = 0; i < dir->nr_buffers; i++)
-                brelse(dir->bh[i]);
+        if (dir->bh_fplus) {
+                for (i = 0; i < dir->nr_buffers; i++)
+                        brelse(dir->bh_fplus[i]);
+
+                if (&dir->bh[0] != dir->bh_fplus)
+                        kfree(dir->bh_fplus);
+
+                dir->bh_fplus = NULL;
+        }
+
+        dir->nr_buffers = 0;
         dir->sb = NULL;
         return ret;
 }
@@ -79,7 +122,8 @@ out:
 static int
 adfs_fplus_setpos(struct adfs_dir *dir, unsigned int fpos)
 {
-        struct adfs_bigdirheader *h = (struct adfs_bigdirheader *)dir->bh[0]->b_data;
+        struct adfs_bigdirheader *h =
+                (struct adfs_bigdirheader *) dir->bh_fplus[0]->b_data;
         int ret = -ENOENT;
 
         if (fpos <= le32_to_cpu(h->bigdirentries)) {
@@ -102,21 +146,27 @@ dir_memcpy(struct adfs_dir *dir, unsigned int offset, void *to, int len)
         partial = sb->s_blocksize - offset;
 
         if (partial >= len)
-                memcpy(to, dir->bh[buffer]->b_data + offset, len);
+                memcpy(to, dir->bh_fplus[buffer]->b_data + offset, len);
         else {
                 char *c = (char *)to;
 
                 remainder = len - partial;
 
-                memcpy(c, dir->bh[buffer]->b_data + offset, partial);
-                memcpy(c + partial, dir->bh[buffer + 1]->b_data, remainder);
+                memcpy(c,
+                        dir->bh_fplus[buffer]->b_data + offset,
+                        partial);
+
+                memcpy(c + partial,
+                        dir->bh_fplus[buffer + 1]->b_data,
+                        remainder);
         }
 }
 
 static int
 adfs_fplus_getnext(struct adfs_dir *dir, struct object_info *obj)
 {
-        struct adfs_bigdirheader *h = (struct adfs_bigdirheader *)dir->bh[0]->b_data;
+        struct adfs_bigdirheader *h =
+                (struct adfs_bigdirheader *) dir->bh_fplus[0]->b_data;
         struct adfs_bigdirentry bde;
         unsigned int offset;
         int i, ret = -ENOENT;
@@ -147,6 +197,24 @@ adfs_fplus_getnext(struct adfs_dir *dir, struct object_info *obj)
                 if (obj->name[i] == '/')
                         obj->name[i] = '.';
 
+        obj->filetype = -1;
+
+        /*
+         * object is a file and is filetyped and timestamped?
+         * RISC OS 12-bit filetype is stored in load_address[19:8]
+         */
+        if ((0 == (obj->attr & ADFS_NDA_DIRECTORY)) &&
+                (0xfff00000 == (0xfff00000 & obj->loadaddr))) {
+                obj->filetype = (__u16) ((0x000fff00 & obj->loadaddr) >> 8);
+
+                /* optionally append the ,xyz hex filetype suffix */
+                if (ADFS_SB(dir->sb)->s_ftsuffix)
+                        obj->name_len +=
+                                append_filetype_suffix(
+                                        &obj->name[obj->name_len],
+                                        obj->filetype);
+        }
+
         dir->pos += 1;
         ret = 0;
 out:
@@ -160,7 +228,7 @@ adfs_fplus_sync(struct adfs_dir *dir)
         int i;
 
         for (i = dir->nr_buffers - 1; i >= 0; i--) {
-                struct buffer_head *bh = dir->bh[i];
+                struct buffer_head *bh = dir->bh_fplus[i];
                 sync_dirty_buffer(bh);
                 if (buffer_req(bh) && !buffer_uptodate(bh))
                         err = -EIO;
@@ -174,8 +242,17 @@ adfs_fplus_free(struct adfs_dir *dir)
 {
         int i;
 
-        for (i = 0; i < dir->nr_buffers; i++)
-                brelse(dir->bh[i]);
+        if (dir->bh_fplus) {
+                for (i = 0; i < dir->nr_buffers; i++)
+                        brelse(dir->bh_fplus[i]);
+
+                if (&dir->bh[0] != dir->bh_fplus)
+                        kfree(dir->bh_fplus);
+
+                dir->bh_fplus = NULL;
+        }
+
+        dir->nr_buffers = 0;
         dir->sb = NULL;
 }
 
diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c
index 09fe40198d1c..92444e94f842 100644
--- a/fs/adfs/inode.c
+++ b/fs/adfs/inode.c
@@ -78,26 +78,13 @@ static const struct address_space_operations adfs_aops = {
         .bmap           = _adfs_bmap
 };
 
-static inline unsigned int
-adfs_filetype(struct inode *inode)
-{
-        unsigned int type;
-
-        if (ADFS_I(inode)->stamped)
-                type = (ADFS_I(inode)->loadaddr >> 8) & 0xfff;
-        else
-                type = (unsigned int) -1;
-
-        return type;
-}
-
 /*
  * Convert ADFS attributes and filetype to Linux permission.
  */
 static umode_t
 adfs_atts2mode(struct super_block *sb, struct inode *inode)
 {
-        unsigned int filetype, attr = ADFS_I(inode)->attr;
+        unsigned int attr = ADFS_I(inode)->attr;
         umode_t mode, rmask;
         struct adfs_sb_info *asb = ADFS_SB(sb);
 
@@ -106,9 +93,7 @@ adfs_atts2mode(struct super_block *sb, struct inode *inode)
                 return S_IFDIR | S_IXUGO | mode;
         }
 
-        filetype = adfs_filetype(inode);
-
-        switch (filetype) {
+        switch (ADFS_I(inode)->filetype) {
         case 0xfc0:     /* LinkFS */
                 return S_IFLNK|S_IRWXUGO;
 
@@ -174,50 +159,48 @@ adfs_mode2atts(struct super_block *sb, struct inode *inode)
 
 /*
  * Convert an ADFS time to Unix time.  ADFS has a 40-bit centi-second time
- * referenced to 1 Jan 1900 (til 2248)
+ * referenced to 1 Jan 1900 (til 2248) so we need to discard 2208988800 seconds
+ * of time to convert from RISC OS epoch to Unix epoch.
  */
 static void
 adfs_adfs2unix_time(struct timespec *tv, struct inode *inode)
 {
         unsigned int high, low;
+        /* 01 Jan 1970 00:00:00 (Unix epoch) as nanoseconds since
+         * 01 Jan 1900 00:00:00 (RISC OS epoch)
+         */
+        static const s64 nsec_unix_epoch_diff_risc_os_epoch =
+                                                        2208988800000000000LL;
+        s64 nsec;
 
         if (ADFS_I(inode)->stamped == 0)
                 goto cur_time;
 
-        high = ADFS_I(inode)->loadaddr << 24;
-        low  = ADFS_I(inode)->execaddr;
+        high = ADFS_I(inode)->loadaddr & 0xFF; /* top 8 bits of timestamp */
+        low  = ADFS_I(inode)->execaddr;    /* bottom 32 bits of timestamp */
 
-        high |= low >> 8;
-        low  &= 255;
+        /* convert 40-bit centi-seconds to 32-bit seconds
+         * going via nanoseconds to retain precision
+         */
+        nsec = (((s64) high << 32) | (s64) low) * 10000000; /* cs to ns */
 
         /* Files dated pre  01 Jan 1970 00:00:00. */
-        if (high < 0x336e996a)
+        if (nsec < nsec_unix_epoch_diff_risc_os_epoch)
                 goto too_early;
 
-        /* Files dated post 18 Jan 2038 03:14:05. */
-        if (high >= 0x656e9969)
-                goto too_late;
+        /* convert from RISC OS to Unix epoch */
+        nsec -= nsec_unix_epoch_diff_risc_os_epoch;
 
-        /* discard 2208988800 (0x336e996a00) seconds of time */
-        high -= 0x336e996a;
-
-        /* convert 40-bit centi-seconds to 32-bit seconds */
-        tv->tv_sec = (((high % 100) << 8) + low) / 100 + (high / 100 << 8);
-        tv->tv_nsec = 0;
+        *tv = ns_to_timespec(nsec);
         return;
 
  cur_time:
-        *tv = CURRENT_TIME_SEC;
+        *tv = CURRENT_TIME;
         return;
 
  too_early:
         tv->tv_sec = tv->tv_nsec = 0;
         return;
-
- too_late:
-        tv->tv_sec = 0x7ffffffd;
-        tv->tv_nsec = 0;
-        return;
 }
 
 /*
@@ -279,7 +262,8 @@ adfs_iget(struct super_block *sb, struct object_info *obj)
         ADFS_I(inode)->loadaddr  = obj->loadaddr;
         ADFS_I(inode)->execaddr  = obj->execaddr;
         ADFS_I(inode)->attr      = obj->attr;
-        ADFS_I(inode)->stamped    = ((obj->loadaddr & 0xfff00000) == 0xfff00000);
+        ADFS_I(inode)->filetype  = obj->filetype;
+        ADFS_I(inode)->stamped   = ((obj->loadaddr & 0xfff00000) == 0xfff00000);
 
         inode->i_mode    = adfs_atts2mode(sb, inode);
         adfs_adfs2unix_time(&inode->i_mtime, inode);
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index 06d7388b477b..c8bf36a1996a 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -138,17 +138,20 @@ static int adfs_show_options(struct seq_file *seq, struct vfsmount *mnt)
                 seq_printf(seq, ",ownmask=%o", asb->s_owner_mask);
         if (asb->s_other_mask != ADFS_DEFAULT_OTHER_MASK)
                 seq_printf(seq, ",othmask=%o", asb->s_other_mask);
+        if (asb->s_ftsuffix != 0)
+                seq_printf(seq, ",ftsuffix=%u", asb->s_ftsuffix);
 
         return 0;
 }
 
-enum {Opt_uid, Opt_gid, Opt_ownmask, Opt_othmask, Opt_err};
+enum {Opt_uid, Opt_gid, Opt_ownmask, Opt_othmask, Opt_ftsuffix, Opt_err};
 
 static const match_table_t tokens = {
         {Opt_uid, "uid=%u"},
         {Opt_gid, "gid=%u"},
         {Opt_ownmask, "ownmask=%o"},
         {Opt_othmask, "othmask=%o"},
+        {Opt_ftsuffix, "ftsuffix=%u"},
         {Opt_err, NULL}
 };
 
@@ -189,6 +192,11 @@ static int parse_options(struct super_block *sb, char *options)
                                 return -EINVAL;
                         asb->s_other_mask = option;
                         break;
+                case Opt_ftsuffix:
+                        if (match_int(args, &option))
+                                return -EINVAL;
+                        asb->s_ftsuffix = option;
+                        break;
                 default:
                         printk("ADFS-fs: unrecognised mount option \"%s\" "
                                         "or missing value\n", p);
@@ -366,6 +374,7 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent)
         asb->s_gid = 0;
         asb->s_owner_mask = ADFS_DEFAULT_OWNER_MASK;
         asb->s_other_mask = ADFS_DEFAULT_OTHER_MASK;
+        asb->s_ftsuffix = 0;
 
         if (parse_options(sb, data))
                 goto error;
@@ -445,11 +454,13 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent)
 
         root_obj.parent_id = root_obj.file_id = le32_to_cpu(dr->root);
         root_obj.name_len  = 0;
-        root_obj.loadaddr  = 0;
-        root_obj.execaddr  = 0;
+        /* Set root object date as 01 Jan 1987 00:00:00 */
+        root_obj.loadaddr  = 0xfff0003f;
+        root_obj.execaddr  = 0xec22c000;
         root_obj.size      = ADFS_NEWDIR_SIZE;
         root_obj.attr      = ADFS_NDA_DIRECTORY   | ADFS_NDA_OWNER_READ |
                              ADFS_NDA_OWNER_WRITE | ADFS_NDA_PUBLIC_READ;
+        root_obj.filetype  = -1;
 
         /*
          * If this is a F+ disk with variable length directories,
@@ -463,6 +474,12 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent)
                 asb->s_dir     = &adfs_f_dir_ops;
                 asb->s_namelen = ADFS_F_NAME_LEN;
         }
+        /*
+         * ,xyz hex filetype suffix may be added by driver
+         * to files that have valid RISC OS filetype
+         */
+        if (asb->s_ftsuffix)
+                asb->s_namelen += 4;
 
         sb->s_d_op = &adfs_dentry_operations;
         root = adfs_iget(sb, &root_obj);
diff --git a/fs/affs/Makefile b/fs/affs/Makefile
index b2c4f54446f3..3988b4a78339 100644
--- a/fs/affs/Makefile
+++ b/fs/affs/Makefile
@@ -2,7 +2,7 @@
 # Makefile for the Linux affs filesystem routines.
 #
 
-#EXTRA_CFLAGS=-DDEBUG=1
+#ccflags-y := -DDEBUG=1
 
 obj-$(CONFIG_AFFS_FS) += affs.o
 
diff --git a/fs/aio.c b/fs/aio.c
index 7f54f43b8f7c..ebb6a22e4e1b 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -520,7 +520,7 @@ static inline void really_put_req(struct kioctx *ctx, struct kiocb *req)
         ctx->reqs_active--;
 
         if (unlikely(!ctx->reqs_active && ctx->dead))
-                wake_up(&ctx->wait);
+                wake_up_all(&ctx->wait);
 }
 
 static void aio_fput_routine(struct work_struct *data)
@@ -1229,7 +1229,7 @@ static void io_destroy(struct kioctx *ioctx)
          * by other CPUs at this point.  Right now, we rely on the
          * locking done by the above calls to ensure this consistency.
          */
-        wake_up(&ioctx->wait);
+        wake_up_all(&ioctx->wait);
         put_ioctx(ioctx);       /* once for the lookup */
 }
 
diff --git a/fs/attr.c b/fs/attr.c
index 7ca41811afa1..1007ed616314 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -59,7 +59,7 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr)
 
         /* Make sure a caller can chmod. */
         if (ia_valid & ATTR_MODE) {
-                if (!is_owner_or_cap(inode))
+                if (!inode_owner_or_capable(inode))
                         return -EPERM;
                 /* Also check the setgid bit! */
                 if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid :
@@ -69,7 +69,7 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr)
 
         /* Check for setting the inode time. */
         if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)) {
-                if (!is_owner_or_cap(inode))
+                if (!inode_owner_or_capable(inode))
                         return -EPERM;
         }
 
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 014e7aba3b08..e6f84d26f4cf 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -36,7 +36,7 @@ static long autofs4_root_compat_ioctl(struct file *,unsigned int,unsigned long);
 static int autofs4_dir_open(struct inode *inode, struct file *file);
 static struct dentry *autofs4_lookup(struct inode *,struct dentry *, struct nameidata *);
 static struct vfsmount *autofs4_d_automount(struct path *);
-static int autofs4_d_manage(struct dentry *, bool, bool);
+static int autofs4_d_manage(struct dentry *, bool);
 static void autofs4_dentry_release(struct dentry *);
 
 const struct file_operations autofs4_root_operations = {
@@ -446,7 +446,7 @@ done:
         return NULL;
 }
 
-int autofs4_d_manage(struct dentry *dentry, bool mounting_here, bool rcu_walk)
+int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
 {
         struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 
@@ -454,7 +454,7 @@ int autofs4_d_manage(struct dentry *dentry, bool mounting_here, bool rcu_walk)
                 dentry, dentry->d_name.len, dentry->d_name.name);
 
         /* The daemon never waits. */
-        if (autofs4_oz_mode(sbi) || mounting_here) {
+        if (autofs4_oz_mode(sbi)) {
                 if (!d_mountpoint(dentry))
                         return -EISDIR;
                 return 0;
diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c
index 685ecff3ab31..b14cebfd9047 100644
--- a/fs/bfs/dir.c
+++ b/fs/bfs/dir.c
@@ -97,7 +97,7 @@ static int bfs_create(struct inode *dir, struct dentry *dentry, int mode,
         if (!inode)
                 return -ENOSPC;
         mutex_lock(&info->bfs_lock);
-        ino = find_first_zero_bit(info->si_imap, info->si_lasti);
+        ino = find_first_zero_bit(info->si_imap, info->si_lasti + 1);
         if (ino > info->si_lasti) {
                 mutex_unlock(&info->bfs_lock);
                 iput(inode);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index d5b640ba6cb1..f34078d702d3 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -570,7 +570,7 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
         unsigned long elf_entry;
         unsigned long interp_load_addr = 0;
         unsigned long start_code, end_code, start_data, end_data;
-        unsigned long reloc_func_desc = 0;
+        unsigned long reloc_func_desc __maybe_unused = 0;
         int executable_stack = EXSTACK_DEFAULT;
         unsigned long def_flags = 0;
         struct {
@@ -1906,7 +1906,7 @@ static int elf_core_dump(struct coredump_params *cprm)
         segs = current->mm->map_count;
         segs += elf_core_extra_phdrs();
 
-        gate_vma = get_gate_vma(current);
+        gate_vma = get_gate_vma(current->mm);
         if (gate_vma != NULL)
                 segs++;
 
diff --git a/fs/bio.c b/fs/bio.c
index 4bd454fa844e..4cf2a52fbc54 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -111,7 +111,7 @@ static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size)
         if (!slab)
                 goto out_unlock;
 
-        printk("bio: create slab <%s> at %d\n", bslab->name, entry);
+        printk(KERN_INFO "bio: create slab <%s> at %d\n", bslab->name, entry);
         bslab->slab = slab;
         bslab->slab_ref = 1;
         bslab->slab_size = sz;
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 9c949348510b..de34bfad9ec3 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -170,7 +170,7 @@ static int btrfs_xattr_acl_set(struct dentry *dentry, const char *name,
         int ret;
         struct posix_acl *acl = NULL;
 
-        if (!is_owner_or_cap(dentry->d_inode))
+        if (!inode_owner_or_capable(dentry->d_inode))
                 return -EPERM;
 
         if (!IS_POSIXACL(dentry->d_inode))
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index e1aa8d607bc7..100b07f021b4 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2493,7 +2493,7 @@ int close_ctree(struct btrfs_root *root)
          * ERROR state on disk.
          *
          * 2. when btrfs flips readonly just in btrfs_commit_super,
-         * and in such case, btrfs cannnot write sb via btrfs_commit_super,
+         * and in such case, btrfs cannot write sb via btrfs_commit_super,
          * and since fs_state has been set BTRFS_SUPER_FLAG_ERROR flag,
          * btrfs will cleanup all FS resources first and write sb then.
          */
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 5fdb2abc4fa7..d1bace3df9b6 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -158,7 +158,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
                       FS_SYNC_FL | FS_DIRSYNC_FL))
                 return -EOPNOTSUPP;
 
-        if (!is_owner_or_cap(inode))
+        if (!inode_owner_or_capable(inode))
                 return -EACCES;
 
         mutex_lock(&inode->i_mutex);
@@ -1077,7 +1077,7 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
         if (flags & ~BTRFS_SUBVOL_RDONLY)
                 return -EOPNOTSUPP;
 
-        if (!is_owner_or_cap(inode))
+        if (!inode_owner_or_capable(inode))
                 return -EACCES;
 
         down_write(&root->fs_info->subvol_sem);
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index f5ec2d44150d..faccd47c6c46 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -57,7 +57,8 @@ static struct list_head *zlib_alloc_workspace(void)
         if (!workspace)
                 return ERR_PTR(-ENOMEM);
 
-        workspace->def_strm.workspace = vmalloc(zlib_deflate_workspacesize());
+        workspace->def_strm.workspace = vmalloc(zlib_deflate_workspacesize(
+                                                MAX_WBITS, MAX_MEM_LEVEL));
         workspace->inf_strm.workspace = vmalloc(zlib_inflate_workspacesize());
         workspace->buf = kmalloc(PAGE_CACHE_SIZE, GFP_NOFS);
         if (!workspace->def_strm.workspace ||
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 08f65faac112..0dba6915712b 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -210,8 +210,6 @@ int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
         if (!fsc->debugfs_congestion_kb)
                 goto out;
 
-        dout("a\n");
-
         snprintf(name, sizeof(name), "../../bdi/%s",
                  dev_name(fsc->backing_dev_info.dev));
         fsc->debugfs_bdi =
@@ -221,7 +219,6 @@ int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
         if (!fsc->debugfs_bdi)
                 goto out;
 
-        dout("b\n");
         fsc->debugfs_mdsmap = debugfs_create_file("mdsmap",
                                         0600,
                                         fsc->client->debugfs_dir,
@@ -230,7 +227,6 @@ int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
         if (!fsc->debugfs_mdsmap)
                 goto out;
 
-        dout("ca\n");
         fsc->debugfs_mdsc = debugfs_create_file("mdsc",
                                                 0600,
                                                 fsc->client->debugfs_dir,
@@ -239,7 +235,6 @@ int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
         if (!fsc->debugfs_mdsc)
                 goto out;
 
-        dout("da\n");
         fsc->debugfs_caps = debugfs_create_file("caps",
                                                    0400,
                                                    fsc->client->debugfs_dir,
@@ -248,7 +243,6 @@ int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
         if (!fsc->debugfs_caps)
                 goto out;
 
-        dout("ea\n");
         fsc->debugfs_dentry_lru = debugfs_create_file("dentry_lru",
                                         0600,
                                         fsc->client->debugfs_dir,
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index ebafa65a29b6..1a867a3601ae 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -161,7 +161,7 @@ more:
         filp->f_pos = di->offset;
         err = filldir(dirent, dentry->d_name.name,
                       dentry->d_name.len, di->offset,
-                      dentry->d_inode->i_ino,
+                      ceph_translate_ino(dentry->d_sb, dentry->d_inode->i_ino),
                       dentry->d_inode->i_mode >> 12);
 
         if (last) {
@@ -245,15 +245,17 @@ static int ceph_readdir(struct file *filp, void *dirent, filldir_t filldir)
 
                 dout("readdir off 0 -> '.'\n");
                 if (filldir(dirent, ".", 1, ceph_make_fpos(0, 0),
-                            inode->i_ino, inode->i_mode >> 12) < 0)
+                            ceph_translate_ino(inode->i_sb, inode->i_ino),
+                            inode->i_mode >> 12) < 0)
                         return 0;
                 filp->f_pos = 1;
                 off = 1;
         }
         if (filp->f_pos == 1) {
+                ino_t ino = filp->f_dentry->d_parent->d_inode->i_ino;
                 dout("readdir off 1 -> '..'\n");
                 if (filldir(dirent, "..", 2, ceph_make_fpos(0, 1),
-                            filp->f_dentry->d_parent->d_inode->i_ino,
+                            ceph_translate_ino(inode->i_sb, ino),
                             inode->i_mode >> 12) < 0)
                         return 0;
                 filp->f_pos = 2;
@@ -377,7 +379,8 @@ more:
                 if (filldir(dirent,
                             rinfo->dir_dname[off - fi->offset],
                             rinfo->dir_dname_len[off - fi->offset],
-                            pos, ino, ftype) < 0) {
+                            pos,
+                            ceph_translate_ino(inode->i_sb, ino), ftype) < 0) {
                         dout("filldir stopping us...\n");
                         return 0;
                 }
@@ -1024,14 +1027,13 @@ out_touch:
 }
 
 /*
- * When a dentry is released, clear the dir I_COMPLETE if it was part
- * of the current dir gen or if this is in the snapshot namespace.
+ * Release our ceph_dentry_info.
  */
-static void ceph_dentry_release(struct dentry *dentry)
+static void ceph_d_release(struct dentry *dentry)
 {
         struct ceph_dentry_info *di = ceph_dentry(dentry);
 
-        dout("dentry_release %p\n", dentry);
+        dout("d_release %p\n", dentry);
         if (di) {
                 ceph_dentry_lru_del(dentry);
                 if (di->lease_session)
@@ -1256,14 +1258,14 @@ const struct inode_operations ceph_dir_iops = {
 
 const struct dentry_operations ceph_dentry_ops = {
         .d_revalidate = ceph_d_revalidate,
-        .d_release = ceph_dentry_release,
+        .d_release = ceph_d_release,
 };
 
 const struct dentry_operations ceph_snapdir_dentry_ops = {
         .d_revalidate = ceph_snapdir_d_revalidate,
-        .d_release = ceph_dentry_release,
+        .d_release = ceph_d_release,
 };
 
 const struct dentry_operations ceph_snap_dentry_ops = {
-        .d_release = ceph_dentry_release,
+        .d_release = ceph_d_release,
 };
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 7d0e4a82d898..159b512d5a27 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -564,11 +564,19 @@ more:
                          * start_request so that a tid has been assigned.
                          */
                         spin_lock(&ci->i_unsafe_lock);
-                        list_add(&req->r_unsafe_item, &ci->i_unsafe_writes);
+                        list_add_tail(&req->r_unsafe_item,
+                                      &ci->i_unsafe_writes);
                         spin_unlock(&ci->i_unsafe_lock);
                         ceph_get_cap_refs(ci, CEPH_CAP_FILE_WR);
                 }
+                
                 ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
+                if (ret < 0 && req->r_safe_callback) {
+                        spin_lock(&ci->i_unsafe_lock);
+                        list_del_init(&req->r_unsafe_item);
+                        spin_unlock(&ci->i_unsafe_lock);
+                        ceph_put_cap_refs(ci, CEPH_CAP_FILE_WR);
+                }
         }
 
         if (file->f_flags & O_DIRECT)
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 193bfa5e9cbd..b54c97da1c43 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -36,6 +36,13 @@ static void ceph_vmtruncate_work(struct work_struct *work);
 /*
  * find or create an inode, given the ceph ino number
  */
+static int ceph_set_ino_cb(struct inode *inode, void *data)
+{
+        ceph_inode(inode)->i_vino = *(struct ceph_vino *)data;
+        inode->i_ino = ceph_vino_to_ino(*(struct ceph_vino *)data);
+        return 0;
+}
+
 struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino)
 {
         struct inode *inode;
@@ -1030,9 +1037,6 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
                         dout("fill_trace doing d_move %p -> %p\n",
                              req->r_old_dentry, dn);
 
-                        /* d_move screws up d_subdirs order */
-                        ceph_i_clear(dir, CEPH_I_COMPLETE);
-
                         d_move(req->r_old_dentry, dn);
                         dout(" src %p '%.*s' dst %p '%.*s'\n",
                              req->r_old_dentry,
@@ -1044,12 +1048,15 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
                            rehashing bug in vfs_rename_dir */
                         ceph_invalidate_dentry_lease(dn);
 
-                        /* take overwritten dentry's readdir offset */
-                        dout("dn %p gets %p offset %lld (old offset %lld)\n",
-                             req->r_old_dentry, dn, ceph_dentry(dn)->offset,
+                        /*
+                         * d_move() puts the renamed dentry at the end of
+                         * d_subdirs.  We need to assign it an appropriate
+                         * directory offset so we can behave when holding
+                         * I_COMPLETE.
+                         */
+                        ceph_set_dentry_offset(req->r_old_dentry);
+                        dout("dn %p gets new offset %lld\n", req->r_old_dentry, 
                              ceph_dentry(req->r_old_dentry)->offset);
-                        ceph_dentry(req->r_old_dentry)->offset =
-                                ceph_dentry(dn)->offset;
 
                         dn = req->r_old_dentry;  /* use old_dentry */
                         in = dn->d_inode;
@@ -1809,7 +1816,7 @@ int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
         err = ceph_do_getattr(inode, CEPH_STAT_CAP_INODE_ALL);
         if (!err) {
                 generic_fillattr(inode, stat);
-                stat->ino = inode->i_ino;
+                stat->ino = ceph_translate_ino(inode->i_sb, inode->i_ino);
                 if (ceph_snap(inode) != CEPH_NOSNAP)
                         stat->dev = ceph_snap(inode);
                 else
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 9c5085465a63..a9e78b4a258c 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -131,6 +131,7 @@ enum {
         Opt_rbytes,
         Opt_norbytes,
         Opt_noasyncreaddir,
+        Opt_ino32,
 };
 
 static match_table_t fsopt_tokens = {
@@ -150,6 +151,7 @@ static match_table_t fsopt_tokens = {
         {Opt_rbytes, "rbytes"},
         {Opt_norbytes, "norbytes"},
         {Opt_noasyncreaddir, "noasyncreaddir"},
+        {Opt_ino32, "ino32"},
         {-1, NULL}
 };
 
@@ -225,6 +227,9 @@ static int parse_fsopt_token(char *c, void *private)
         case Opt_noasyncreaddir:
                 fsopt->flags |= CEPH_MOUNT_OPT_NOASYNCREADDIR;
                 break;
+        case Opt_ino32:
+                fsopt->flags |= CEPH_MOUNT_OPT_INO32;
+                break;
         default:
                 BUG_ON(token);
         }
@@ -288,7 +293,7 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt,
         fsopt->sb_flags = flags;
         fsopt->flags = CEPH_MOUNT_OPT_DEFAULT;
 
-        fsopt->rsize = CEPH_MOUNT_RSIZE_DEFAULT;
+        fsopt->rsize = CEPH_RSIZE_DEFAULT;
         fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL);
         fsopt->caps_wanted_delay_min = CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT;
         fsopt->caps_wanted_delay_max = CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT;
@@ -370,7 +375,7 @@ static int ceph_show_options(struct seq_file *m, struct vfsmount *mnt)
 
         if (fsopt->wsize)
                 seq_printf(m, ",wsize=%d", fsopt->wsize);
-        if (fsopt->rsize != CEPH_MOUNT_RSIZE_DEFAULT)
+        if (fsopt->rsize != CEPH_RSIZE_DEFAULT)
                 seq_printf(m, ",rsize=%d", fsopt->rsize);
         if (fsopt->congestion_kb != default_congestion_kb())
                 seq_printf(m, ",write_congestion_kb=%d", fsopt->congestion_kb);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 20b907d76ae2..619fe719968f 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -27,6 +27,7 @@
 #define CEPH_MOUNT_OPT_DIRSTAT         (1<<4) /* `cat dirname` for stats */
 #define CEPH_MOUNT_OPT_RBYTES          (1<<5) /* dir st_bytes = rbytes */
 #define CEPH_MOUNT_OPT_NOASYNCREADDIR  (1<<7) /* no dcache readdir */
+#define CEPH_MOUNT_OPT_INO32           (1<<8) /* 32 bit inos */
 
 #define CEPH_MOUNT_OPT_DEFAULT    (CEPH_MOUNT_OPT_RBYTES)
 
@@ -35,6 +36,7 @@
 #define ceph_test_mount_opt(fsc, opt) \
         (!!((fsc)->mount_options->flags & CEPH_MOUNT_OPT_##opt))
 
+#define CEPH_RSIZE_DEFAULT             (512*1024) /* readahead */
 #define CEPH_MAX_READDIR_DEFAULT        1024
 #define CEPH_MAX_READDIR_BYTES_DEFAULT  (512*1024)
 #define CEPH_SNAPDIRNAME_DEFAULT        ".snap"
@@ -319,6 +321,16 @@ static inline struct ceph_inode_info *ceph_inode(struct inode *inode)
         return container_of(inode, struct ceph_inode_info, vfs_inode);
 }
 
+static inline struct ceph_fs_client *ceph_inode_to_client(struct inode *inode)
+{
+        return (struct ceph_fs_client *)inode->i_sb->s_fs_info;
+}
+
+static inline struct ceph_fs_client *ceph_sb_to_client(struct super_block *sb)
+{
+        return (struct ceph_fs_client *)sb->s_fs_info;
+}
+
 static inline struct ceph_vino ceph_vino(struct inode *inode)
 {
         return ceph_inode(inode)->i_vino;
@@ -327,19 +339,49 @@ static inline struct ceph_vino ceph_vino(struct inode *inode)
 /*
  * ino_t is <64 bits on many architectures, blech.
  *
- * don't include snap in ino hash, at least for now.
+ *               i_ino (kernel inode)   st_ino (userspace)
+ * i386          32                     32
+ * x86_64+ino32  64                     32
+ * x86_64        64                     64
+ */
+static inline u32 ceph_ino_to_ino32(ino_t ino)
+{
+        ino ^= ino >> (sizeof(ino) * 8 - 32);
+        if (!ino)
+                ino = 1;
+        return ino;
+}
+
+/*
+ * kernel i_ino value
  */
 static inline ino_t ceph_vino_to_ino(struct ceph_vino vino)
 {
         ino_t ino = (ino_t)vino.ino;  /* ^ (vino.snap << 20); */
 #if BITS_PER_LONG == 32
-        ino ^= vino.ino >> (sizeof(u64)-sizeof(ino_t)) * 8;
-        if (!ino)
-                ino = 1;
+        ino = ceph_ino_to_ino32(ino);
 #endif
         return ino;
 }
 
+/*
+ * user-visible ino (stat, filldir)
+ */
+#if BITS_PER_LONG == 32
+static inline ino_t ceph_translate_ino(struct super_block *sb, ino_t ino)
+{
+        return ino;
+}
+#else
+static inline ino_t ceph_translate_ino(struct super_block *sb, ino_t ino)
+{
+        if (ceph_test_mount_opt(ceph_sb_to_client(sb), INO32))
+                ino = ceph_ino_to_ino32(ino);
+        return ino;
+}
+#endif
+
+
 /* for printf-style formatting */
 #define ceph_vinop(i) ceph_inode(i)->i_vino.ino, ceph_inode(i)->i_vino.snap
 
@@ -428,13 +470,6 @@ static inline loff_t ceph_make_fpos(unsigned frag, unsigned off)
         return ((loff_t)frag << 32) | (loff_t)off;
 }
 
-static inline int ceph_set_ino_cb(struct inode *inode, void *data)
-{
-        ceph_inode(inode)->i_vino = *(struct ceph_vino *)data;
-        inode->i_ino = ceph_vino_to_ino(*(struct ceph_vino *)data);
-        return 0;
-}
-
 /*
  * caps helpers
  */
@@ -503,15 +538,6 @@ extern void ceph_reservation_status(struct ceph_fs_client *client,
                                     int *total, int *avail, int *used,
                                     int *reserved, int *min);
 
-static inline struct ceph_fs_client *ceph_inode_to_client(struct inode *inode)
-{
-        return (struct ceph_fs_client *)inode->i_sb->s_fs_info;
-}
-
-static inline struct ceph_fs_client *ceph_sb_to_client(struct super_block *sb)
-{
-        return (struct ceph_fs_client *)sb->s_fs_info;
-}
 
 
 /*
diff --git a/fs/coda/Makefile b/fs/coda/Makefile
index 6c22e61da397..1bab69a0d347 100644
--- a/fs/coda/Makefile
+++ b/fs/coda/Makefile
@@ -9,4 +9,4 @@ coda-objs := psdev.o cache.o cnode.o inode.o dir.o file.o upcall.o \
 
 # If you want debugging output, please uncomment the following line.
 
-# EXTRA_CFLAGS += -DDEBUG -DDEBUG_SMB_MALLOC=1
+# ccflags-y := -DDEBUG -DDEBUG_SMB_MALLOC=1
diff --git a/fs/coda/sysctl.c b/fs/coda/sysctl.c
index c6405ce3c50e..06d27a41807f 100644
--- a/fs/coda/sysctl.c
+++ b/fs/coda/sysctl.c
@@ -13,7 +13,6 @@
 
 #ifdef CONFIG_SYSCTL
 static struct ctl_table_header *fs_table_header;
-#endif
 
 static ctl_table coda_table[] = {
         {
@@ -40,7 +39,6 @@ static ctl_table coda_table[] = {
         {}
 };
 
-#ifdef CONFIG_SYSCTL
 static ctl_table fs_table[] = {
         {
                 .procname       = "coda",
@@ -49,22 +47,18 @@ static ctl_table fs_table[] = {
         },
         {}
 };
-#endif
 
 void coda_sysctl_init(void)
 {
-#ifdef CONFIG_SYSCTL
         if ( !fs_table_header )
                 fs_table_header = register_sysctl_table(fs_table);
-#endif
 }
 
 void coda_sysctl_clean(void)
 {
-#ifdef CONFIG_SYSCTL
         if ( fs_table_header ) {
                 unregister_sysctl_table(fs_table_header);
                 fs_table_header = NULL;
         }
-#endif
 }
+#endif
diff --git a/fs/compat.c b/fs/compat.c
index c6d31a3bab88..72fe6cda9108 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -1671,9 +1671,6 @@ int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset,
  * Update: ERESTARTSYS breaks at least the xview clock binary, so
  * I'm trying ERESTARTNOHAND which restart only when you want to.
  */
-#define MAX_SELECT_SECONDS \
-        ((unsigned long) (MAX_SCHEDULE_TIMEOUT / HZ)-1)
-
 int compat_core_sys_select(int n, compat_ulong_t __user *inp,
         compat_ulong_t __user *outp, compat_ulong_t __user *exp,
         struct timespec *end_time)
diff --git a/fs/dcache.c b/fs/dcache.c
index a39fe47c466f..ad25c4cec7d5 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1612,10 +1612,13 @@ struct dentry *d_obtain_alias(struct inode *inode)
         __bit_spin_unlock(0, (unsigned long *)&tmp->d_sb->s_anon.first);
         spin_unlock(&tmp->d_lock);
         spin_unlock(&inode->i_lock);
+        security_d_instantiate(tmp, inode);
 
         return tmp;
 
  out_iput:
+        if (res && !IS_ERR(res))
+                security_d_instantiate(res, inode);
         iput(inode);
         return res;
 }
@@ -1808,7 +1811,7 @@ struct dentry *__d_lookup_rcu(struct dentry *parent, struct qstr *name,
          * false-negative result. d_lookup() protects against concurrent
          * renames using rename_lock seqlock.
          *
-         * See Documentation/vfs/dcache-locking.txt for more details.
+         * See Documentation/filesystems/path-lookup.txt for more details.
          */
         hlist_bl_for_each_entry_rcu(dentry, node, &b->head, d_hash) {
                 struct inode *i;
@@ -1928,7 +1931,7 @@ struct dentry *__d_lookup(struct dentry *parent, struct qstr *name)
          * false-negative result. d_lookup() protects against concurrent
          * renames using rename_lock seqlock.
          *
-         * See Documentation/vfs/dcache-locking.txt for more details.
+         * See Documentation/filesystems/path-lookup.txt for more details.
          */
         rcu_read_lock();
         
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 1bb547c9cad6..2f27e578d466 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -479,6 +479,7 @@ int devpts_pty_new(struct inode *ptmx_inode, struct tty_struct *tty)
         struct dentry *root = sb->s_root;
         struct pts_fs_info *fsi = DEVPTS_SB(sb);
         struct pts_mount_opts *opts = &fsi->mount_opts;
+        int ret = 0;
         char s[12];
 
         /* We're supposed to be given the slave end of a pty */
@@ -501,14 +502,17 @@ int devpts_pty_new(struct inode *ptmx_inode, struct tty_struct *tty)
         mutex_lock(&root->d_inode->i_mutex);
 
         dentry = d_alloc_name(root, s);
-        if (!IS_ERR(dentry)) {
+        if (dentry) {
                 d_add(dentry, inode);
                 fsnotify_create(root->d_inode, dentry);
+        } else {
+                iput(inode);
+                ret = -ENOMEM;
         }
 
         mutex_unlock(&root->d_inode->i_mutex);
 
-        return 0;
+        return ret;
 }
 
 struct tty_struct *devpts_get_tty(struct inode *pts_inode, int number)
@@ -544,17 +548,12 @@ void devpts_pty_kill(struct tty_struct *tty)
         mutex_lock(&root->d_inode->i_mutex);
 
         dentry = d_find_alias(inode);
-        if (IS_ERR(dentry))
-                goto out;
-
-        if (dentry) {
-                inode->i_nlink--;
-                d_delete(dentry);
-                dput(dentry);   /* d_alloc_name() in devpts_pty_new() */
-        }
 
+        inode->i_nlink--;
+        d_delete(dentry);
+        dput(dentry);   /* d_alloc_name() in devpts_pty_new() */
         dput(dentry);           /* d_find_alias above */
-out:
+
         mutex_unlock(&root->d_inode->i_mutex);
 }
 
diff --git a/fs/direct-io.c b/fs/direct-io.c
index b044705eedd4..dcb5577cde1d 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -645,11 +645,11 @@ static int dio_send_cur_page(struct dio *dio)
                 /*
                  * See whether this new request is contiguous with the old.
                  *
-                 * Btrfs cannot handl having logically non-contiguous requests
-                 * submitted.  For exmple if you have
+                 * Btrfs cannot handle having logically non-contiguous requests
+                 * submitted.  For example if you have
                  *
                  * Logical:  [0-4095][HOLE][8192-12287]
-                 * Phyiscal: [0-4095]      [4096-8181]
+                 * Physical: [0-4095]      [4096-8191]
                  *
                  * We cannot submit those pages together as one BIO.  So if our
                  * current logical offset in the file does not equal what would
diff --git a/fs/dlm/ast.c b/fs/dlm/ast.c
index 4314f0d48d85..abc49f292454 100644
--- a/fs/dlm/ast.c
+++ b/fs/dlm/ast.c
@@ -18,6 +18,7 @@
 
 #define WAKE_ASTS  0
 
+static uint64_t                 ast_seq_count;
 static struct list_head         ast_queue;
 static spinlock_t               ast_queue_lock;
 static struct task_struct *     astd_task;
@@ -25,40 +26,186 @@ static unsigned long		astd_wakeflags;
 static struct mutex             astd_running;
 
 
+static void dlm_dump_lkb_callbacks(struct dlm_lkb *lkb)
+{
+        int i;
+
+        log_print("last_bast %x %llu flags %x mode %d sb %d %x",
+                  lkb->lkb_id,
+                  (unsigned long long)lkb->lkb_last_bast.seq,
+                  lkb->lkb_last_bast.flags,
+                  lkb->lkb_last_bast.mode,
+                  lkb->lkb_last_bast.sb_status,
+                  lkb->lkb_last_bast.sb_flags);
+
+        log_print("last_cast %x %llu flags %x mode %d sb %d %x",
+                  lkb->lkb_id,
+                  (unsigned long long)lkb->lkb_last_cast.seq,
+                  lkb->lkb_last_cast.flags,
+                  lkb->lkb_last_cast.mode,
+                  lkb->lkb_last_cast.sb_status,
+                  lkb->lkb_last_cast.sb_flags);
+
+        for (i = 0; i < DLM_CALLBACKS_SIZE; i++) {
+                log_print("cb %x %llu flags %x mode %d sb %d %x",
+                          lkb->lkb_id,
+                          (unsigned long long)lkb->lkb_callbacks[i].seq,
+                          lkb->lkb_callbacks[i].flags,
+                          lkb->lkb_callbacks[i].mode,
+                          lkb->lkb_callbacks[i].sb_status,
+                          lkb->lkb_callbacks[i].sb_flags);
+        }
+}
+
 void dlm_del_ast(struct dlm_lkb *lkb)
 {
         spin_lock(&ast_queue_lock);
-        if (lkb->lkb_ast_type & (AST_COMP | AST_BAST))
-                list_del(&lkb->lkb_astqueue);
+        if (!list_empty(&lkb->lkb_astqueue))
+                list_del_init(&lkb->lkb_astqueue);
         spin_unlock(&ast_queue_lock);
 }
 
-void dlm_add_ast(struct dlm_lkb *lkb, int type, int mode)
+int dlm_add_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode,
+                         int status, uint32_t sbflags, uint64_t seq)
 {
+        struct dlm_ls *ls = lkb->lkb_resource->res_ls;
+        uint64_t prev_seq;
+        int prev_mode;
+        int i;
+
+        for (i = 0; i < DLM_CALLBACKS_SIZE; i++) {
+                if (lkb->lkb_callbacks[i].seq)
+                        continue;
+
+                /*
+                 * Suppress some redundant basts here, do more on removal.
+                 * Don't even add a bast if the callback just before it
+                 * is a bast for the same mode or a more restrictive mode.
+                 * (the addional > PR check is needed for PR/CW inversion)
+                 */
+
+                if ((i > 0) && (flags & DLM_CB_BAST) &&
+                    (lkb->lkb_callbacks[i-1].flags & DLM_CB_BAST)) {
+
+                        prev_seq = lkb->lkb_callbacks[i-1].seq;
+                        prev_mode = lkb->lkb_callbacks[i-1].mode;
+
+                        if ((prev_mode == mode) ||
+                            (prev_mode > mode && prev_mode > DLM_LOCK_PR)) {
+
+                                log_debug(ls, "skip %x add bast %llu mode %d "
+                                          "for bast %llu mode %d",
+                                          lkb->lkb_id,
+                                          (unsigned long long)seq,
+                                          mode,
+                                          (unsigned long long)prev_seq,
+                                          prev_mode);
+                                return 0;
+                        }
+                }
+
+                lkb->lkb_callbacks[i].seq = seq;
+                lkb->lkb_callbacks[i].flags = flags;
+                lkb->lkb_callbacks[i].mode = mode;
+                lkb->lkb_callbacks[i].sb_status = status;
+                lkb->lkb_callbacks[i].sb_flags = (sbflags & 0x000000FF);
+                break;
+        }
+
+        if (i == DLM_CALLBACKS_SIZE) {
+                log_error(ls, "no callbacks %x %llu flags %x mode %d sb %d %x",
+                          lkb->lkb_id, (unsigned long long)seq,
+                          flags, mode, status, sbflags);
+                dlm_dump_lkb_callbacks(lkb);
+                return -1;
+        }
+
+        return 0;
+}
+
+int dlm_rem_lkb_callback(struct dlm_ls *ls, struct dlm_lkb *lkb,
+                         struct dlm_callback *cb, int *resid)
+{
+        int i;
+
+        *resid = 0;
+
+        if (!lkb->lkb_callbacks[0].seq)
+                return -ENOENT;
+
+        /* oldest undelivered cb is callbacks[0] */
+
+        memcpy(cb, &lkb->lkb_callbacks[0], sizeof(struct dlm_callback));
+        memset(&lkb->lkb_callbacks[0], 0, sizeof(struct dlm_callback));
+
+        /* shift others down */
+
+        for (i = 1; i < DLM_CALLBACKS_SIZE; i++) {
+                if (!lkb->lkb_callbacks[i].seq)
+                        break;
+                memcpy(&lkb->lkb_callbacks[i-1], &lkb->lkb_callbacks[i],
+                       sizeof(struct dlm_callback));
+                memset(&lkb->lkb_callbacks[i], 0, sizeof(struct dlm_callback));
+                (*resid)++;
+        }
+
+        /* if cb is a bast, it should be skipped if the blocking mode is
+           compatible with the last granted mode */
+
+        if ((cb->flags & DLM_CB_BAST) && lkb->lkb_last_cast.seq) {
+                if (dlm_modes_compat(cb->mode, lkb->lkb_last_cast.mode)) {
+                        cb->flags |= DLM_CB_SKIP;
+
+                        log_debug(ls, "skip %x bast %llu mode %d "
+                                  "for cast %llu mode %d",
+                                  lkb->lkb_id,
+                                  (unsigned long long)cb->seq,
+                                  cb->mode,
+                                  (unsigned long long)lkb->lkb_last_cast.seq,
+                                  lkb->lkb_last_cast.mode);
+                        return 0;
+                }
+        }
+
+        if (cb->flags & DLM_CB_CAST) {
+                memcpy(&lkb->lkb_last_cast, cb, sizeof(struct dlm_callback));
+                lkb->lkb_last_cast_time = ktime_get();
+        }
+
+        if (cb->flags & DLM_CB_BAST) {
+                memcpy(&lkb->lkb_last_bast, cb, sizeof(struct dlm_callback));
+                lkb->lkb_last_bast_time = ktime_get();
+        }
+
+        return 0;
+}
+
+void dlm_add_ast(struct dlm_lkb *lkb, uint32_t flags, int mode, int status,
+                 uint32_t sbflags)
+{
+        uint64_t seq;
+        int rv;
+
+        spin_lock(&ast_queue_lock);
+
+        seq = ++ast_seq_count;
+
         if (lkb->lkb_flags & DLM_IFL_USER) {
-                dlm_user_add_ast(lkb, type, mode);
+                spin_unlock(&ast_queue_lock);
+                dlm_user_add_ast(lkb, flags, mode, status, sbflags, seq);
                 return;
         }
 
-        spin_lock(&ast_queue_lock);
-        if (!(lkb->lkb_ast_type & (AST_COMP | AST_BAST))) {
+        rv = dlm_add_lkb_callback(lkb, flags, mode, status, sbflags, seq);
+        if (rv < 0) {
+                spin_unlock(&ast_queue_lock);
+                return;
+        }
+
+        if (list_empty(&lkb->lkb_astqueue)) {
                 kref_get(&lkb->lkb_ref);
                 list_add_tail(&lkb->lkb_astqueue, &ast_queue);
-                lkb->lkb_ast_first = type;
         }
-
-        /* sanity check, this should not happen */
-
-        if ((type == AST_COMP) && (lkb->lkb_ast_type & AST_COMP))
-                log_print("repeat cast %d castmode %d lock %x %s",
-                          mode, lkb->lkb_castmode,
-                          lkb->lkb_id, lkb->lkb_resource->res_name);
-
-        lkb->lkb_ast_type |= type;
-        if (type == AST_BAST)
-                lkb->lkb_bastmode = mode;
-        else
-                lkb->lkb_castmode = mode;
         spin_unlock(&ast_queue_lock);
 
         set_bit(WAKE_ASTS, &astd_wakeflags);
@@ -72,7 +219,8 @@ static void process_asts(void)
         struct dlm_lkb *lkb;
         void (*castfn) (void *astparam);
         void (*bastfn) (void *astparam, int mode);
-        int type, first, bastmode, castmode, do_bast, do_cast, last_castmode;
+        struct dlm_callback callbacks[DLM_CALLBACKS_SIZE];
+        int i, rv, resid;
 
 repeat:
         spin_lock(&ast_queue_lock);
@@ -83,54 +231,45 @@ repeat:
                 if (dlm_locking_stopped(ls))
                         continue;
 
-                list_del(&lkb->lkb_astqueue);
-                type = lkb->lkb_ast_type;
-                lkb->lkb_ast_type = 0;
-                first = lkb->lkb_ast_first;
-                lkb->lkb_ast_first = 0;
-                bastmode = lkb->lkb_bastmode;
-                castmode = lkb->lkb_castmode;
+                /* we remove from astqueue list and remove everything in
+                   lkb_callbacks before releasing the spinlock so empty
+                   lkb_astqueue is always consistent with empty lkb_callbacks */
+
+                list_del_init(&lkb->lkb_astqueue);
+
                 castfn = lkb->lkb_astfn;
                 bastfn = lkb->lkb_bastfn;
-                spin_unlock(&ast_queue_lock);
 
-                do_cast = (type & AST_COMP) && castfn;
-                do_bast = (type & AST_BAST) && bastfn;
+                memset(&callbacks, 0, sizeof(callbacks));
 
-                /* Skip a bast if its blocking mode is compatible with the
-                   granted mode of the preceding cast. */
+                for (i = 0; i < DLM_CALLBACKS_SIZE; i++) {
+                        rv = dlm_rem_lkb_callback(ls, lkb, &callbacks[i], &resid);
+                        if (rv < 0)
+                                break;
+                }
+                spin_unlock(&ast_queue_lock);
 
-                if (do_bast) {
-                        if (first == AST_COMP)
-                                last_castmode = castmode;
-                        else
-                                last_castmode = lkb->lkb_castmode_done;
-                        if (dlm_modes_compat(bastmode, last_castmode))
-                                do_bast = 0;
+                if (resid) {
+                        /* shouldn't happen, for loop should have removed all */
+                        log_error(ls, "callback resid %d lkb %x",
+                                  resid, lkb->lkb_id);
                 }
 
-                if (first == AST_COMP) {
-                        if (do_cast)
-                                castfn(lkb->lkb_astparam);
-                        if (do_bast)
-                                bastfn(lkb->lkb_astparam, bastmode);
-                } else if (first == AST_BAST) {
-                        if (do_bast)
-                                bastfn(lkb->lkb_astparam, bastmode);
-                        if (do_cast)
+                for (i = 0; i < DLM_CALLBACKS_SIZE; i++) {
+                        if (!callbacks[i].seq)
+                                break;
+                        if (callbacks[i].flags & DLM_CB_SKIP) {
+                                continue;
+                        } else if (callbacks[i].flags & DLM_CB_BAST) {
+                                bastfn(lkb->lkb_astparam, callbacks[i].mode);
+                        } else if (callbacks[i].flags & DLM_CB_CAST) {
+                                lkb->lkb_lksb->sb_status = callbacks[i].sb_status;
+                                lkb->lkb_lksb->sb_flags = callbacks[i].sb_flags;
                                 castfn(lkb->lkb_astparam);
-                } else {
-                        log_error(ls, "bad ast_first %d ast_type %d",
-                                  first, type);
+                        }
                 }
 
-                if (do_cast)
-                        lkb->lkb_castmode_done = castmode;
-                if (do_bast)
-                        lkb->lkb_bastmode_done = bastmode;
-
-                /* this removes the reference added by dlm_add_ast
-                   and may result in the lkb being freed */
+                /* removes ref for ast_queue, may cause lkb to be freed */
                 dlm_put_lkb(lkb);
 
                 cond_resched();
diff --git a/fs/dlm/ast.h b/fs/dlm/ast.h
index bcb1aaba519d..8aa89c9b5611 100644
--- a/fs/dlm/ast.h
+++ b/fs/dlm/ast.h
@@ -13,8 +13,13 @@
 #ifndef __ASTD_DOT_H__
 #define __ASTD_DOT_H__
 
-void dlm_add_ast(struct dlm_lkb *lkb, int type, int mode);
 void dlm_del_ast(struct dlm_lkb *lkb);
+int dlm_add_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode,
+                         int status, uint32_t sbflags, uint64_t seq);
+int dlm_rem_lkb_callback(struct dlm_ls *ls, struct dlm_lkb *lkb,
+                         struct dlm_callback *cb, int *resid);
+void dlm_add_ast(struct dlm_lkb *lkb, uint32_t flags, int mode, int status,
+                 uint32_t sbflags);
 
 void dlm_astd_wake(void);
 int dlm_astd_start(void);
diff --git a/fs/dlm/config.c b/fs/dlm/config.c
index b54bca03d92f..0d329ff8ed4c 100644
--- a/fs/dlm/config.c
+++ b/fs/dlm/config.c
@@ -977,9 +977,9 @@ int dlm_our_addr(struct sockaddr_storage *addr, int num)
 /* Config file defaults */
 #define DEFAULT_TCP_PORT       21064
 #define DEFAULT_BUFFER_SIZE     4096
-#define DEFAULT_RSBTBL_SIZE      256
+#define DEFAULT_RSBTBL_SIZE     1024
 #define DEFAULT_LKBTBL_SIZE     1024
-#define DEFAULT_DIRTBL_SIZE      512
+#define DEFAULT_DIRTBL_SIZE     1024
 #define DEFAULT_RECOVER_TIMER      5
 #define DEFAULT_TOSS_SECS         10
 #define DEFAULT_SCAN_SECS          5
diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c
index 6b42ba807dfd..59779237e2b4 100644
--- a/fs/dlm/debug_fs.c
+++ b/fs/dlm/debug_fs.c
@@ -257,12 +257,12 @@ static int print_format3_lock(struct seq_file *s, struct dlm_lkb *lkb,
                         lkb->lkb_status,
                         lkb->lkb_grmode,
                         lkb->lkb_rqmode,
-                        lkb->lkb_bastmode,
+                        lkb->lkb_last_bast.mode,
                         rsb_lookup,
                         lkb->lkb_wait_type,
                         lkb->lkb_lvbseq,
                         (unsigned long long)ktime_to_ns(lkb->lkb_timestamp),
-                        (unsigned long long)ktime_to_ns(lkb->lkb_time_bast));
+                        (unsigned long long)ktime_to_ns(lkb->lkb_last_bast_time));
         return rv;
 }
 
diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h
index f632b58cd222..b94204913011 100644
--- a/fs/dlm/dlm_internal.h
+++ b/fs/dlm/dlm_internal.h
@@ -192,11 +192,6 @@ struct dlm_args {
  * lkb is a process copy, the nodeid specifies the lock master.
  */
 
-/* lkb_ast_type */
-
-#define AST_COMP                1
-#define AST_BAST                2
-
 /* lkb_status */
 
 #define DLM_LKSTS_WAITING       1
@@ -217,6 +212,20 @@ struct dlm_args {
 #define DLM_IFL_USER            0x00000001
 #define DLM_IFL_ORPHAN          0x00000002
 
+#define DLM_CALLBACKS_SIZE      6
+
+#define DLM_CB_CAST             0x00000001
+#define DLM_CB_BAST             0x00000002
+#define DLM_CB_SKIP             0x00000004
+
+struct dlm_callback {
+        uint64_t                seq;
+        uint32_t                flags;          /* DLM_CBF_ */
+        int                     sb_status;      /* copy to lksb status */
+        uint8_t                 sb_flags;       /* copy to lksb flags */
+        int8_t                  mode; /* rq mode of bast, gr mode of cast */
+};
+
 struct dlm_lkb {
         struct dlm_rsb          *lkb_resource;  /* the rsb */
         struct kref             lkb_ref;
@@ -236,13 +245,6 @@ struct dlm_lkb {
 
         int8_t                  lkb_wait_type;  /* type of reply waiting for */
         int8_t                  lkb_wait_count;
-        int8_t                  lkb_ast_type;   /* type of ast queued for */
-        int8_t                  lkb_ast_first;  /* type of first ast queued */
-
-        int8_t                  lkb_bastmode;   /* req mode of queued bast */
-        int8_t                  lkb_castmode;   /* gr mode of queued cast */
-        int8_t                  lkb_bastmode_done; /* last delivered bastmode */
-        int8_t                  lkb_castmode_done; /* last delivered castmode */
 
         struct list_head        lkb_idtbl_list; /* lockspace lkbtbl */
         struct list_head        lkb_statequeue; /* rsb g/c/w list */
@@ -251,10 +253,15 @@ struct dlm_lkb {
         struct list_head        lkb_astqueue;   /* need ast to be sent */
         struct list_head        lkb_ownqueue;   /* list of locks for a process */
         struct list_head        lkb_time_list;
-        ktime_t                 lkb_time_bast;  /* for debugging */
         ktime_t                 lkb_timestamp;
         unsigned long           lkb_timeout_cs;
 
+        struct dlm_callback     lkb_callbacks[DLM_CALLBACKS_SIZE];
+        struct dlm_callback     lkb_last_cast;
+        struct dlm_callback     lkb_last_bast;
+        ktime_t                 lkb_last_cast_time;     /* for debugging */
+        ktime_t                 lkb_last_bast_time;     /* for debugging */
+
         char                    *lkb_lvbptr;
         struct dlm_lksb         *lkb_lksb;      /* caller's status block */
         void                    (*lkb_astfn) (void *astparam);
@@ -544,8 +551,6 @@ struct dlm_user_args {
                                           (dlm_user_proc) on the struct file,
                                           the process's locks point back to it*/
         struct dlm_lksb         lksb;
-        int                     old_mode;
-        int                     update_user_lvb;
         struct dlm_lksb __user  *user_lksb;
         void __user             *castparam;
         void __user             *castaddr;
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index 64e5f3efdd81..04b8c449303f 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -160,10 +160,10 @@ static const int __quecvt_compat_matrix[8][8] = {
 void dlm_print_lkb(struct dlm_lkb *lkb)
 {
         printk(KERN_ERR "lkb: nodeid %d id %x remid %x exflags %x flags %x\n"
-               "     status %d rqmode %d grmode %d wait_type %d ast_type %d\n",
+               "     status %d rqmode %d grmode %d wait_type %d\n",
                lkb->lkb_nodeid, lkb->lkb_id, lkb->lkb_remid, lkb->lkb_exflags,
                lkb->lkb_flags, lkb->lkb_status, lkb->lkb_rqmode,
-               lkb->lkb_grmode, lkb->lkb_wait_type, lkb->lkb_ast_type);
+               lkb->lkb_grmode, lkb->lkb_wait_type);
 }
 
 static void dlm_print_rsb(struct dlm_rsb *r)
@@ -305,10 +305,7 @@ static void queue_cast(struct dlm_rsb *r, struct dlm_lkb *lkb, int rv)
                 rv = -EDEADLK;
         }
 
-        lkb->lkb_lksb->sb_status = rv;
-        lkb->lkb_lksb->sb_flags = lkb->lkb_sbflags;
-
-        dlm_add_ast(lkb, AST_COMP, lkb->lkb_grmode);
+        dlm_add_ast(lkb, DLM_CB_CAST, lkb->lkb_grmode, rv, lkb->lkb_sbflags);
 }
 
 static inline void queue_cast_overlap(struct dlm_rsb *r, struct dlm_lkb *lkb)
@@ -319,13 +316,10 @@ static inline void queue_cast_overlap(struct dlm_rsb *r, struct dlm_lkb *lkb)
 
 static void queue_bast(struct dlm_rsb *r, struct dlm_lkb *lkb, int rqmode)
 {
-        lkb->lkb_time_bast = ktime_get();
-
         if (is_master_copy(lkb)) {
-                lkb->lkb_bastmode = rqmode; /* printed by debugfs */
                 send_bast(r, lkb, rqmode);
         } else {
-                dlm_add_ast(lkb, AST_BAST, rqmode);
+                dlm_add_ast(lkb, DLM_CB_BAST, rqmode, 0, 0);
         }
 }
 
@@ -600,6 +594,7 @@ static int create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret)
         INIT_LIST_HEAD(&lkb->lkb_ownqueue);
         INIT_LIST_HEAD(&lkb->lkb_rsb_lookup);
         INIT_LIST_HEAD(&lkb->lkb_time_list);
+        INIT_LIST_HEAD(&lkb->lkb_astqueue);
 
         get_random_bytes(&bucket, sizeof(bucket));
         bucket &= (ls->ls_lkbtbl_size - 1);
@@ -2819,9 +2814,9 @@ static void send_args(struct dlm_rsb *r, struct dlm_lkb *lkb,
            not from lkb fields */
 
         if (lkb->lkb_bastfn)
-                ms->m_asts |= AST_BAST;
+                ms->m_asts |= DLM_CB_BAST;
         if (lkb->lkb_astfn)
-                ms->m_asts |= AST_COMP;
+                ms->m_asts |= DLM_CB_CAST;
 
         /* compare with switch in create_message; send_remove() doesn't
            use send_args() */
@@ -3122,8 +3117,8 @@ static int receive_request_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
         lkb->lkb_grmode = DLM_LOCK_IV;
         lkb->lkb_rqmode = ms->m_rqmode;
 
-        lkb->lkb_bastfn = (ms->m_asts & AST_BAST) ? &fake_bastfn : NULL;
-        lkb->lkb_astfn = (ms->m_asts & AST_COMP) ? &fake_astfn : NULL;
+        lkb->lkb_bastfn = (ms->m_asts & DLM_CB_BAST) ? &fake_bastfn : NULL;
+        lkb->lkb_astfn = (ms->m_asts & DLM_CB_CAST) ? &fake_astfn : NULL;
 
         if (lkb->lkb_exflags & DLM_LKF_VALBLK) {
                 /* lkb was just created so there won't be an lvb yet */
@@ -4412,8 +4407,8 @@ static int receive_rcom_lock_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
         lkb->lkb_grmode = rl->rl_grmode;
         /* don't set lkb_status because add_lkb wants to itself */
 
-        lkb->lkb_bastfn = (rl->rl_asts & AST_BAST) ? &fake_bastfn : NULL;
-        lkb->lkb_astfn = (rl->rl_asts & AST_COMP) ? &fake_astfn : NULL;
+        lkb->lkb_bastfn = (rl->rl_asts & DLM_CB_BAST) ? &fake_bastfn : NULL;
+        lkb->lkb_astfn = (rl->rl_asts & DLM_CB_CAST) ? &fake_astfn : NULL;
 
         if (lkb->lkb_exflags & DLM_LKF_VALBLK) {
                 int lvblen = rc->rc_header.h_length - sizeof(struct dlm_rcom) -
@@ -4589,7 +4584,6 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua,
         error = set_lock_args(mode, &ua->lksb, flags, namelen, timeout_cs,
                               fake_astfn, ua, fake_bastfn, &args);
         lkb->lkb_flags |= DLM_IFL_USER;
-        ua->old_mode = DLM_LOCK_IV;
 
         if (error) {
                 __put_lkb(ls, lkb);
@@ -4658,7 +4652,6 @@ int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
         ua->bastparam = ua_tmp->bastparam;
         ua->bastaddr = ua_tmp->bastaddr;
         ua->user_lksb = ua_tmp->user_lksb;
-        ua->old_mode = lkb->lkb_grmode;
 
         error = set_lock_args(mode, &ua->lksb, flags, 0, timeout_cs,
                               fake_astfn, ua, fake_bastfn, &args);
@@ -4917,8 +4910,9 @@ void dlm_clear_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc)
         }
 
         list_for_each_entry_safe(lkb, safe, &proc->asts, lkb_astqueue) {
-                lkb->lkb_ast_type = 0;
-                list_del(&lkb->lkb_astqueue);
+                memset(&lkb->lkb_callbacks, 0,
+                       sizeof(struct dlm_callback) * DLM_CALLBACKS_SIZE);
+                list_del_init(&lkb->lkb_astqueue);
                 dlm_put_lkb(lkb);
         }
 
@@ -4958,7 +4952,9 @@ static void purge_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc)
 
         spin_lock(&proc->asts_spin);
         list_for_each_entry_safe(lkb, safe, &proc->asts, lkb_astqueue) {
-                list_del(&lkb->lkb_astqueue);
+                memset(&lkb->lkb_callbacks, 0,
+                       sizeof(struct dlm_callback) * DLM_CALLBACKS_SIZE);
+                list_del_init(&lkb->lkb_astqueue);
                 dlm_put_lkb(lkb);
         }
         spin_unlock(&proc->asts_spin);
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 2d8c87b951c2..bffa1e73b9a9 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -1468,13 +1468,15 @@ static void work_stop(void)
 
 static int work_start(void)
 {
-        recv_workqueue = create_singlethread_workqueue("dlm_recv");
+        recv_workqueue = alloc_workqueue("dlm_recv",
+                                         WQ_UNBOUND | WQ_MEM_RECLAIM, 1);
         if (!recv_workqueue) {
                 log_print("can't start dlm_recv");
                 return -ENOMEM;
         }
 
-        send_workqueue = create_singlethread_workqueue("dlm_send");
+        send_workqueue = alloc_workqueue("dlm_send",
+                                         WQ_UNBOUND | WQ_MEM_RECLAIM, 1);
         if (!send_workqueue) {
                 log_print("can't start dlm_send");
                 destroy_workqueue(recv_workqueue);
diff --git a/fs/dlm/rcom.c b/fs/dlm/rcom.c
index 3c83a49a48a3..f10a50f24e8f 100644
--- a/fs/dlm/rcom.c
+++ b/fs/dlm/rcom.c
@@ -321,9 +321,9 @@ static void pack_rcom_lock(struct dlm_rsb *r, struct dlm_lkb *lkb,
         rl->rl_wait_type = cpu_to_le16(lkb->lkb_wait_type);
 
         if (lkb->lkb_bastfn)
-                rl->rl_asts |= AST_BAST;
+                rl->rl_asts |= DLM_CB_BAST;
         if (lkb->lkb_astfn)
-                rl->rl_asts |= AST_COMP;
+                rl->rl_asts |= DLM_CB_CAST;
 
         rl->rl_namelen = cpu_to_le16(r->res_length);
         memcpy(rl->rl_name, r->res_name, r->res_length);
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index 66d6c16bf440..d5ab3fe7c198 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -24,6 +24,7 @@
 #include "lock.h"
 #include "lvb_table.h"
 #include "user.h"
+#include "ast.h"
 
 static const char name_prefix[] = "dlm";
 static const struct file_operations device_fops;
@@ -152,19 +153,16 @@ static void compat_output(struct dlm_lock_result *res,
    not related to the lifetime of the lkb struct which is managed
    entirely by refcount. */
 
-static int lkb_is_endoflife(struct dlm_lkb *lkb, int sb_status, int type)
+static int lkb_is_endoflife(int mode, int status)
 {
-        switch (sb_status) {
+        switch (status) {
         case -DLM_EUNLOCK:
                 return 1;
         case -DLM_ECANCEL:
         case -ETIMEDOUT:
         case -EDEADLK:
-                if (lkb->lkb_grmode == DLM_LOCK_IV)
-                        return 1;
-                break;
         case -EAGAIN:
-                if (type == AST_COMP && lkb->lkb_grmode == DLM_LOCK_IV)
+                if (mode == DLM_LOCK_IV)
                         return 1;
                 break;
         }
@@ -174,12 +172,13 @@ static int lkb_is_endoflife(struct dlm_lkb *lkb, int sb_status, int type)
 /* we could possibly check if the cancel of an orphan has resulted in the lkb
    being removed and then remove that lkb from the orphans list and free it */
 
-void dlm_user_add_ast(struct dlm_lkb *lkb, int type, int mode)
+void dlm_user_add_ast(struct dlm_lkb *lkb, uint32_t flags, int mode,
+                      int status, uint32_t sbflags, uint64_t seq)
 {
         struct dlm_ls *ls;
         struct dlm_user_args *ua;
         struct dlm_user_proc *proc;
-        int eol = 0, ast_type;
+        int rv;
 
         if (lkb->lkb_flags & (DLM_IFL_ORPHAN | DLM_IFL_DEAD))
                 return;
@@ -200,49 +199,29 @@ void dlm_user_add_ast(struct dlm_lkb *lkb, int type, int mode)
         ua = lkb->lkb_ua;
         proc = ua->proc;
 
-        if (type == AST_BAST && ua->bastaddr == NULL)
+        if ((flags & DLM_CB_BAST) && ua->bastaddr == NULL)
                 goto out;
 
+        if ((flags & DLM_CB_CAST) && lkb_is_endoflife(mode, status))
+                lkb->lkb_flags |= DLM_IFL_ENDOFLIFE;
+
         spin_lock(&proc->asts_spin);
 
-        ast_type = lkb->lkb_ast_type;
-        lkb->lkb_ast_type |= type;
-        if (type == AST_BAST)
-                lkb->lkb_bastmode = mode;
-        else
-                lkb->lkb_castmode = mode;
+        rv = dlm_add_lkb_callback(lkb, flags, mode, status, sbflags, seq);
+        if (rv < 0) {
+                spin_unlock(&proc->asts_spin);
+                goto out;
+        }
 
-        if (!ast_type) {
+        if (list_empty(&lkb->lkb_astqueue)) {
                 kref_get(&lkb->lkb_ref);
                 list_add_tail(&lkb->lkb_astqueue, &proc->asts);
-                lkb->lkb_ast_first = type;
                 wake_up_interruptible(&proc->wait);
         }
-        if (type == AST_COMP && (ast_type & AST_COMP))
-                log_debug(ls, "ast overlap %x status %x %x",
-                          lkb->lkb_id, ua->lksb.sb_status, lkb->lkb_flags);
-
-        eol = lkb_is_endoflife(lkb, ua->lksb.sb_status, type);
-        if (eol) {
-                lkb->lkb_flags |= DLM_IFL_ENDOFLIFE;
-        }
-
-        /* We want to copy the lvb to userspace when the completion
-           ast is read if the status is 0, the lock has an lvb and
-           lvb_ops says we should.  We could probably have set_lvb_lock()
-           set update_user_lvb instead and not need old_mode */
-
-        if ((lkb->lkb_ast_type & AST_COMP) &&
-            (lkb->lkb_lksb->sb_status == 0) &&
-            lkb->lkb_lksb->sb_lvbptr &&
-            dlm_lvb_operations[ua->old_mode + 1][lkb->lkb_grmode + 1])
-                ua->update_user_lvb = 1;
-        else
-                ua->update_user_lvb = 0;
-
         spin_unlock(&proc->asts_spin);
 
-        if (eol) {
+        if (lkb->lkb_flags & DLM_IFL_ENDOFLIFE) {
+                /* N.B. spin_lock locks_spin, not asts_spin */
                 spin_lock(&proc->locks_spin);
                 if (!list_empty(&lkb->lkb_ownqueue)) {
                         list_del_init(&lkb->lkb_ownqueue);
@@ -705,8 +684,9 @@ static int device_close(struct inode *inode, struct file *file)
         return 0;
 }
 
-static int copy_result_to_user(struct dlm_user_args *ua, int compat, int type,
-                               int mode, char __user *buf, size_t count)
+static int copy_result_to_user(struct dlm_user_args *ua, int compat,
+                               uint32_t flags, int mode, int copy_lvb,
+                               char __user *buf, size_t count)
 {
 #ifdef CONFIG_COMPAT
         struct dlm_lock_result32 result32;
@@ -730,7 +710,7 @@ static int copy_result_to_user(struct dlm_user_args *ua, int compat, int type,
            notes that a new blocking AST address and parameter are set even if
            the conversion fails, so maybe we should just do that. */
 
-        if (type == AST_BAST) {
+        if (flags & DLM_CB_BAST) {
                 result.user_astaddr = ua->bastaddr;
                 result.user_astparam = ua->bastparam;
                 result.bast_mode = mode;
@@ -750,8 +730,7 @@ static int copy_result_to_user(struct dlm_user_args *ua, int compat, int type,
         /* copy lvb to userspace if there is one, it's been updated, and
            the user buffer has space for it */
 
-        if (ua->update_user_lvb && ua->lksb.sb_lvbptr &&
-            count >= len + DLM_USER_LVB_LEN) {
+        if (copy_lvb && ua->lksb.sb_lvbptr && count >= len + DLM_USER_LVB_LEN) {
                 if (copy_to_user(buf+len, ua->lksb.sb_lvbptr,
                                  DLM_USER_LVB_LEN)) {
                         error = -EFAULT;
@@ -801,13 +780,12 @@ static ssize_t device_read(struct file *file, char __user *buf, size_t count,
         struct dlm_user_proc *proc = file->private_data;
         struct dlm_lkb *lkb;
         DECLARE_WAITQUEUE(wait, current);
-        int error = 0, removed;
-        int ret_type, ret_mode;
-        int bastmode, castmode, do_bast, do_cast;
+        struct dlm_callback cb;
+        int rv, resid, copy_lvb = 0;
 
         if (count == sizeof(struct dlm_device_version)) {
-                error = copy_version_to_user(buf, count);
-                return error;
+                rv = copy_version_to_user(buf, count);
+                return rv;
         }
 
         if (!proc) {
@@ -854,92 +832,57 @@ static ssize_t device_read(struct file *file, char __user *buf, size_t count,
                 }
         }
 
-        /* there may be both completion and blocking asts to return for
-           the lkb, don't remove lkb from asts list unless no asts remain */
+        /* if we empty lkb_callbacks, we don't want to unlock the spinlock
+           without removing lkb_astqueue; so empty lkb_astqueue is always
+           consistent with empty lkb_callbacks */
 
         lkb = list_entry(proc->asts.next, struct dlm_lkb, lkb_astqueue);
 
-        removed = 0;
-        ret_type = 0;
-        ret_mode = 0;
-        do_bast = lkb->lkb_ast_type & AST_BAST;
-        do_cast = lkb->lkb_ast_type & AST_COMP;
-        bastmode = lkb->lkb_bastmode;
-        castmode = lkb->lkb_castmode;
-
-        /* when both are queued figure out which to do first and
-           switch first so the other goes in the next read */
-
-        if (do_cast && do_bast) {
-                if (lkb->lkb_ast_first == AST_COMP) {
-                        ret_type = AST_COMP;
-                        ret_mode = castmode;
-                        lkb->lkb_ast_type &= ~AST_COMP;
-                        lkb->lkb_ast_first = AST_BAST;
-                } else {
-                        ret_type = AST_BAST;
-                        ret_mode = bastmode;
-                        lkb->lkb_ast_type &= ~AST_BAST;
-                        lkb->lkb_ast_first = AST_COMP;
-                }
-        } else {
-                ret_type = lkb->lkb_ast_first;
-                ret_mode = (ret_type == AST_COMP) ? castmode : bastmode;
-                lkb->lkb_ast_type &= ~ret_type;
-                lkb->lkb_ast_first = 0;
+        rv = dlm_rem_lkb_callback(lkb->lkb_resource->res_ls, lkb, &cb, &resid);
+        if (rv < 0) {
+                /* this shouldn't happen; lkb should have been removed from
+                   list when resid was zero */
+                log_print("dlm_rem_lkb_callback empty %x", lkb->lkb_id);
+                list_del_init(&lkb->lkb_astqueue);
+                spin_unlock(&proc->asts_spin);
+                /* removes ref for proc->asts, may cause lkb to be freed */
+                dlm_put_lkb(lkb);
+                goto try_another;
         }
+        if (!resid)
+                list_del_init(&lkb->lkb_astqueue);
+        spin_unlock(&proc->asts_spin);
 
-        /* if we're doing a bast but the bast is unnecessary, then
-           switch to do nothing or do a cast if that was needed next */
-
-        if ((ret_type == AST_BAST) &&
-            dlm_modes_compat(bastmode, lkb->lkb_castmode_done)) {
-                ret_type = 0;
-                ret_mode = 0;
-
-                if (do_cast) {
-                        ret_type = AST_COMP;
-                        ret_mode = castmode;
-                        lkb->lkb_ast_type &= ~AST_COMP;
-                        lkb->lkb_ast_first = 0;
-                }
+        if (cb.flags & DLM_CB_SKIP) {
+                /* removes ref for proc->asts, may cause lkb to be freed */
+                if (!resid)
+                        dlm_put_lkb(lkb);
+                goto try_another;
         }
 
-        if (lkb->lkb_ast_first != lkb->lkb_ast_type) {
-                log_print("device_read %x ast_first %x ast_type %x",
-                          lkb->lkb_id, lkb->lkb_ast_first, lkb->lkb_ast_type);
-        }
+        if (cb.flags & DLM_CB_CAST) {
+                int old_mode, new_mode;
 
-        if (!lkb->lkb_ast_type) {
-                list_del(&lkb->lkb_astqueue);
-                removed = 1;
-        }
-        spin_unlock(&proc->asts_spin);
+                old_mode = lkb->lkb_last_cast.mode;
+                new_mode = cb.mode;
 
-        if (ret_type) {
-                error = copy_result_to_user(lkb->lkb_ua,
-                                test_bit(DLM_PROC_FLAGS_COMPAT, &proc->flags),
-                                ret_type, ret_mode, buf, count);
+                if (!cb.sb_status && lkb->lkb_lksb->sb_lvbptr &&
+                    dlm_lvb_operations[old_mode + 1][new_mode + 1])
+                        copy_lvb = 1;
 
-                if (ret_type == AST_COMP)
-                        lkb->lkb_castmode_done = castmode;
-                if (ret_type == AST_BAST)
-                        lkb->lkb_bastmode_done = bastmode;
+                lkb->lkb_lksb->sb_status = cb.sb_status;
+                lkb->lkb_lksb->sb_flags = cb.sb_flags;
         }
 
-        /* removes reference for the proc->asts lists added by
-           dlm_user_add_ast() and may result in the lkb being freed */
+        rv = copy_result_to_user(lkb->lkb_ua,
+                                 test_bit(DLM_PROC_FLAGS_COMPAT, &proc->flags),
+                                 cb.flags, cb.mode, copy_lvb, buf, count);
 
-        if (removed)
+        /* removes ref for proc->asts, may cause lkb to be freed */
+        if (!resid)
                 dlm_put_lkb(lkb);
 
-        /* the bast that was queued was eliminated (see unnecessary above),
-           leaving nothing to return */
-
-        if (!ret_type)
-                goto try_another;
-
-        return error;
+        return rv;
 }
 
 static unsigned int device_poll(struct file *file, poll_table *wait)
diff --git a/fs/dlm/user.h b/fs/dlm/user.h
index f196091dd7ff..00499ab8835f 100644
--- a/fs/dlm/user.h
+++ b/fs/dlm/user.h
@@ -9,7 +9,8 @@
 #ifndef __USER_DOT_H__
 #define __USER_DOT_H__
 
-void dlm_user_add_ast(struct dlm_lkb *lkb, int type, int mode);
+void dlm_user_add_ast(struct dlm_lkb *lkb, uint32_t flags, int mode,
+                      int status, uint32_t sbflags, uint64_t seq);
 int dlm_user_init(void);
 void dlm_user_exit(void);
 int dlm_device_deregister(struct dlm_ls *ls);
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 2195c213ab2f..816f88e6b9ce 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -45,7 +45,11 @@ static void drop_slab(void)
 int drop_caches_sysctl_handler(ctl_table *table, int write,
         void __user *buffer, size_t *length, loff_t *ppos)
 {
-        proc_dointvec_minmax(table, write, buffer, length, ppos);
+        int ret;
+
+        ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
+        if (ret)
+                return ret;
         if (write) {
                 if (sysctl_drop_caches & 1)
                         iterate_supers(drop_pagecache_sb, NULL);
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 4a09af9e9a63..ed38801b57a7 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -62,7 +62,7 @@
  * This mutex is acquired by ep_free() during the epoll file
  * cleanup path and it is also acquired by eventpoll_release_file()
  * if a file has been pushed inside an epoll set and it is then
- * close()d without a previous call toepoll_ctl(EPOLL_CTL_DEL).
+ * close()d without a previous call to epoll_ctl(EPOLL_CTL_DEL).
  * It is also acquired when inserting an epoll fd onto another epoll
  * fd. We do this so that we walk the epoll tree and ensure that this
  * insertion does not create a cycle of epoll file descriptors, which
@@ -152,11 +152,11 @@ struct epitem {
 
 /*
  * This structure is stored inside the "private_data" member of the file
- * structure and rapresent the main data sructure for the eventpoll
+ * structure and represents the main data structure for the eventpoll
  * interface.
  */
 struct eventpoll {
-        /* Protect the this structure access */
+        /* Protect the access to this structure */
         spinlock_t lock;
 
         /*
@@ -316,6 +316,19 @@ static void ep_nested_calls_init(struct nested_calls *ncalls)
 }
 
 /**
+ * ep_events_available - Checks if ready events might be available.
+ *
+ * @ep: Pointer to the eventpoll context.
+ *
+ * Returns: Returns a value different than zero if ready events are available,
+ *          or zero otherwise.
+ */
+static inline int ep_events_available(struct eventpoll *ep)
+{
+        return !list_empty(&ep->rdllist) || ep->ovflist != EP_UNACTIVE_PTR;
+}
+
+/**
  * ep_call_nested - Perform a bound (possibly) nested call, by checking
  *                  that the recursion limit is not exceeded, and that
  *                  the same nested call (by the meaning of same cookie) is
@@ -793,7 +806,7 @@ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd)
 
 /*
  * This is the callback that is passed to the wait queue wakeup
- * machanism. It is called by the stored file descriptors when they
+ * mechanism. It is called by the stored file descriptors when they
  * have events to report.
  */
 static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *key)
@@ -824,9 +837,9 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
                 goto out_unlock;
 
         /*
-         * If we are trasfering events to userspace, we can hold no locks
+         * If we are transferring events to userspace, we can hold no locks
          * (because we're accessing user memory, and because of linux f_op->poll()
-         * semantics). All the events that happens during that period of time are
+         * semantics). All the events that happen during that period of time are
          * chained in ep->ovflist and requeued later on.
          */
         if (unlikely(ep->ovflist != EP_UNACTIVE_PTR)) {
@@ -1135,12 +1148,29 @@ static inline struct timespec ep_set_mstimeout(long ms)
         return timespec_add_safe(now, ts);
 }
 
+/**
+ * ep_poll - Retrieves ready events, and delivers them to the caller supplied
+ *           event buffer.
+ *
+ * @ep: Pointer to the eventpoll context.
+ * @events: Pointer to the userspace buffer where the ready events should be
+ *          stored.
+ * @maxevents: Size (in terms of number of events) of the caller event buffer.
+ * @timeout: Maximum timeout for the ready events fetch operation, in
+ *           milliseconds. If the @timeout is zero, the function will not block,
+ *           while if the @timeout is less than zero, the function will block
+ *           until at least one event has been retrieved (or an error
+ *           occurred).
+ *
+ * Returns: Returns the number of ready events which have been fetched, or an
+ *          error code, in case of error.
+ */
 static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
                    int maxevents, long timeout)
 {
-        int res, eavail, timed_out = 0;
+        int res = 0, eavail, timed_out = 0;
         unsigned long flags;
-        long slack;
+        long slack = 0;
         wait_queue_t wait;
         ktime_t expires, *to = NULL;
 
@@ -1151,14 +1181,19 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
                 to = &expires;
                 *to = timespec_to_ktime(end_time);
         } else if (timeout == 0) {
+                /*
+                 * Avoid the unnecessary trip to the wait queue loop, if the
+                 * caller specified a non blocking operation.
+                 */
                 timed_out = 1;
+                spin_lock_irqsave(&ep->lock, flags);
+                goto check_events;
         }
 
-retry:
+fetch_events:
         spin_lock_irqsave(&ep->lock, flags);
 
-        res = 0;
-        if (list_empty(&ep->rdllist)) {
+        if (!ep_events_available(ep)) {
                 /*
                  * We don't have any available event to return to the caller.
                  * We need to sleep here, and we will be wake up by
@@ -1174,7 +1209,7 @@ retry:
                          * to TASK_INTERRUPTIBLE before doing the checks.
                          */
                         set_current_state(TASK_INTERRUPTIBLE);
-                        if (!list_empty(&ep->rdllist) || timed_out)
+                        if (ep_events_available(ep) || timed_out)
                                 break;
                         if (signal_pending(current)) {
                                 res = -EINTR;
@@ -1191,8 +1226,9 @@ retry:
 
                 set_current_state(TASK_RUNNING);
         }
+check_events:
         /* Is it worth to try to dig for events ? */
-        eavail = !list_empty(&ep->rdllist) || ep->ovflist != EP_UNACTIVE_PTR;
+        eavail = ep_events_available(ep);
 
         spin_unlock_irqrestore(&ep->lock, flags);
 
@@ -1203,7 +1239,7 @@ retry:
          */
         if (!res && eavail &&
             !(res = ep_send_events(ep, events, maxevents)) && !timed_out)
-                goto retry;
+                goto fetch_events;
 
         return res;
 }
diff --git a/fs/exec.c b/fs/exec.c
index ba99e1abb1aa..5e62d26a4fec 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1875,7 +1875,7 @@ static void wait_for_dump_helpers(struct file *file)
 
 
 /*
- * uhm_pipe_setup
+ * umh_pipe_setup
  * helper function to customize the process used
  * to collect the core in userspace.  Specifically
  * it sets up a pipe and installs it as fd 0 (stdin)
diff --git a/fs/exofs/common.h b/fs/exofs/common.h
index f0d520312d8b..5e74ad3d4009 100644
--- a/fs/exofs/common.h
+++ b/fs/exofs/common.h
@@ -53,10 +53,14 @@
 #define EXOFS_ROOT_ID   0x10002 /* object ID for root directory */
 
 /* exofs Application specific page/attribute */
+/* Inode attrs */
 # define EXOFS_APAGE_FS_DATA    (OSD_APAGE_APP_DEFINED_FIRST + 3)
 # define EXOFS_ATTR_INODE_DATA  1
 # define EXOFS_ATTR_INODE_FILE_LAYOUT   2
 # define EXOFS_ATTR_INODE_DIR_LAYOUT    3
+/* Partition attrs */
+# define EXOFS_APAGE_SB_DATA    (0xF0000000U + 3)
+# define EXOFS_ATTR_SB_STATS    1
 
 /*
  * The maximum number of files we can have is limited by the size of the
@@ -86,8 +90,8 @@ enum {
  */
 enum {EXOFS_FSCB_VER = 1, EXOFS_DT_VER = 1};
 struct exofs_fscb {
-        __le64  s_nextid;       /* Highest object ID used */
-        __le64  s_numfiles;     /* Number of files on fs */
+        __le64  s_nextid;       /* Only used after mkfs */
+        __le64  s_numfiles;     /* Only used after mkfs */
         __le32  s_version;      /* == EXOFS_FSCB_VER */
         __le16  s_magic;        /* Magic signature */
         __le16  s_newfs;        /* Non-zero if this is a new fs */
@@ -98,6 +102,16 @@ struct exofs_fscb {
 } __packed;
 
 /*
+ * This struct is set on the FS partition's attributes.
+ * [EXOFS_APAGE_SB_DATA, EXOFS_ATTR_SB_STATS] and is written together
+ * with the create command, to atomically persist the sb writeable information.
+ */
+struct exofs_sb_stats {
+        __le64  s_nextid;       /* Highest object ID used */
+        __le64  s_numfiles;     /* Number of files on fs */
+} __packed;
+
+/*
  * Describes the raid used in the FS. It is part of the device table.
  * This here is taken from the pNFS-objects definition. In exofs we
  * use one raid policy through-out the filesystem. (NOTE: the funny
diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c
index dcc941d82d67..d0941c6a1f72 100644
--- a/fs/exofs/dir.c
+++ b/fs/exofs/dir.c
@@ -124,7 +124,7 @@ out:
 
 Ebadsize:
         EXOFS_ERR("ERROR [exofs_check_page]: "
-                "size of directory #%lu is not a multiple of chunk size",
+                "size of directory(0x%lx) is not a multiple of chunk size\n",
                 dir->i_ino
         );
         goto fail;
@@ -142,8 +142,8 @@ Espan:
         goto bad_entry;
 bad_entry:
         EXOFS_ERR(
-                "ERROR [exofs_check_page]: bad entry in directory #%lu: %s - "
-                "offset=%lu, inode=%llu, rec_len=%d, name_len=%d",
+                "ERROR [exofs_check_page]: bad entry in directory(0x%lx): %s - "
+                "offset=%lu, inode=0x%llu, rec_len=%d, name_len=%d\n",
                 dir->i_ino, error, (page->index<<PAGE_CACHE_SHIFT)+offs,
                 _LLU(le64_to_cpu(p->inode_no)),
                 rec_len, p->name_len);
@@ -151,8 +151,8 @@ bad_entry:
 Eend:
         p = (struct exofs_dir_entry *)(kaddr + offs);
         EXOFS_ERR("ERROR [exofs_check_page]: "
-                "entry in directory #%lu spans the page boundary"
-                "offset=%lu, inode=%llu",
+                "entry in directory(0x%lx) spans the page boundary"
+                "offset=%lu, inode=0x%llx\n",
                 dir->i_ino, (page->index<<PAGE_CACHE_SHIFT)+offs,
                 _LLU(le64_to_cpu(p->inode_no)));
 fail:
@@ -261,9 +261,8 @@ exofs_readdir(struct file *filp, void *dirent, filldir_t filldir)
                 struct page *page = exofs_get_page(inode, n);
 
                 if (IS_ERR(page)) {
-                        EXOFS_ERR("ERROR: "
-                                   "bad page in #%lu",
-                                   inode->i_ino);
+                        EXOFS_ERR("ERROR: bad page in directory(0x%lx)\n",
+                                  inode->i_ino);
                         filp->f_pos += PAGE_CACHE_SIZE - offset;
                         return PTR_ERR(page);
                 }
@@ -283,7 +282,8 @@ exofs_readdir(struct file *filp, void *dirent, filldir_t filldir)
                 for (; (char *)de <= limit; de = exofs_next_entry(de)) {
                         if (de->rec_len == 0) {
                                 EXOFS_ERR("ERROR: "
-                                        "zero-length directory entry");
+                                     "zero-length entry in directory(0x%lx)\n",
+                                     inode->i_ino);
                                 exofs_put_page(page);
                                 return -EIO;
                         }
@@ -342,9 +342,9 @@ struct exofs_dir_entry *exofs_find_entry(struct inode *dir,
                         kaddr += exofs_last_byte(dir, n) - reclen;
                         while ((char *) de <= kaddr) {
                                 if (de->rec_len == 0) {
-                                        EXOFS_ERR(
-                                                "ERROR: exofs_find_entry: "
-                                                "zero-length directory entry");
+                                        EXOFS_ERR("ERROR: zero-length entry in "
+                                                  "directory(0x%lx)\n",
+                                                  dir->i_ino);
                                         exofs_put_page(page);
                                         goto out;
                                 }
@@ -472,7 +472,8 @@ int exofs_add_link(struct dentry *dentry, struct inode *inode)
                         }
                         if (de->rec_len == 0) {
                                 EXOFS_ERR("ERROR: exofs_add_link: "
-                                        "zero-length directory entry");
+                                      "zero-length entry in directory(0x%lx)\n",
+                                      inode->i_ino);
                                 err = -EIO;
                                 goto out_unlock;
                         }
@@ -491,7 +492,8 @@ int exofs_add_link(struct dentry *dentry, struct inode *inode)
                 exofs_put_page(page);
         }
 
-        EXOFS_ERR("exofs_add_link: BAD dentry=%p or inode=%p", dentry, inode);
+        EXOFS_ERR("exofs_add_link: BAD dentry=%p or inode=0x%lx\n",
+                  dentry, inode->i_ino);
         return -EINVAL;
 
 got_it:
@@ -542,7 +544,8 @@ int exofs_delete_entry(struct exofs_dir_entry *dir, struct page *page)
         while (de < dir) {
                 if (de->rec_len == 0) {
                         EXOFS_ERR("ERROR: exofs_delete_entry:"
-                                "zero-length directory entry");
+                                  "zero-length entry in directory(0x%lx)\n",
+                                  inode->i_ino);
                         err = -EIO;
                         goto out;
                 }
diff --git a/fs/exofs/exofs.h b/fs/exofs/exofs.h
index 2dc925fa1010..c965806c2821 100644
--- a/fs/exofs/exofs.h
+++ b/fs/exofs/exofs.h
@@ -77,7 +77,7 @@ struct exofs_layout {
  * our extension to the in-memory superblock
  */
 struct exofs_sb_info {
-        struct exofs_fscb s_fscb;               /* Written often, pre-allocate*/
+        struct exofs_sb_stats s_ess;            /* Written often, pre-allocate*/
         int             s_timeout;              /* timeout for OSD operations */
         uint64_t        s_nextid;               /* highest object ID used     */
         uint32_t        s_numfiles;             /* number of files on fs      */
@@ -256,6 +256,8 @@ static inline int exofs_oi_read(struct exofs_i_info *oi,
 }
 
 /* inode.c               */
+unsigned exofs_max_io_pages(struct exofs_layout *layout,
+                            unsigned expected_pages);
 int exofs_setattr(struct dentry *, struct iattr *);
 int exofs_write_begin(struct file *file, struct address_space *mapping,
                 loff_t pos, unsigned len, unsigned flags,
@@ -279,7 +281,7 @@ int exofs_set_link(struct inode *, struct exofs_dir_entry *, struct page *,
                     struct inode *);
 
 /* super.c               */
-int exofs_sync_fs(struct super_block *sb, int wait);
+int exofs_sbi_write_stats(struct exofs_sb_info *sbi);
 
 /*********************
  * operation vectors *
diff --git a/fs/exofs/file.c b/fs/exofs/file.c
index b905c79b4f0a..45ca323d8363 100644
--- a/fs/exofs/file.c
+++ b/fs/exofs/file.c
@@ -45,22 +45,8 @@ static int exofs_release_file(struct inode *inode, struct file *filp)
 static int exofs_file_fsync(struct file *filp, int datasync)
 {
         int ret;
-        struct inode *inode = filp->f_mapping->host;
-        struct super_block *sb;
-
-        if (!(inode->i_state & I_DIRTY))
-                return 0;
-        if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
-                return 0;
-
-        ret = sync_inode_metadata(inode, 1);
-
-        /* This is a good place to write the sb */
-        /* TODO: Sechedule an sb-sync on create */
-        sb = inode->i_sb;
-        if (sb->s_dirt)
-                exofs_sync_fs(sb, 1);
 
+        ret = sync_inode_metadata(filp->f_mapping->host, 1);
         return ret;
 }
 
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index a7555238c41a..0c713cfbebf0 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -43,6 +43,17 @@ enum { BIO_MAX_PAGES_KMALLOC =
                 PAGE_SIZE / sizeof(struct page *),
 };
 
+unsigned exofs_max_io_pages(struct exofs_layout *layout,
+                            unsigned expected_pages)
+{
+        unsigned pages = min_t(unsigned, expected_pages, MAX_PAGES_KMALLOC);
+
+        /* TODO: easily support bio chaining */
+        pages =  min_t(unsigned, pages,
+                       layout->group_width * BIO_MAX_PAGES_KMALLOC);
+        return pages;
+}
+
 struct page_collect {
         struct exofs_sb_info *sbi;
         struct inode *inode;
@@ -97,8 +108,7 @@ static void _pcol_reset(struct page_collect *pcol)
 
 static int pcol_try_alloc(struct page_collect *pcol)
 {
-        unsigned pages = min_t(unsigned, pcol->expected_pages,
-                          MAX_PAGES_KMALLOC);
+        unsigned pages;
 
         if (!pcol->ios) { /* First time allocate io_state */
                 int ret = exofs_get_io_state(&pcol->sbi->layout, &pcol->ios);
@@ -108,8 +118,7 @@ static int pcol_try_alloc(struct page_collect *pcol)
         }
 
         /* TODO: easily support bio chaining */
-        pages =  min_t(unsigned, pages,
-                       pcol->sbi->layout.group_width * BIO_MAX_PAGES_KMALLOC);
+        pages =  exofs_max_io_pages(&pcol->sbi->layout, pcol->expected_pages);
 
         for (; pages; pages >>= 1) {
                 pcol->pages = kmalloc(pages * sizeof(struct page *),
@@ -350,8 +359,10 @@ static int readpage_strip(void *data, struct page *page)
 
                 if (!pcol->read_4_write)
                         unlock_page(page);
-                EXOFS_DBGMSG("readpage_strip(0x%lx, 0x%lx) empty page,"
-                             " splitting\n", inode->i_ino, page->index);
+                EXOFS_DBGMSG("readpage_strip(0x%lx) empty page len=%zx "
+                             "read_4_write=%d index=0x%lx end_index=0x%lx "
+                             "splitting\n", inode->i_ino, len,
+                             pcol->read_4_write, page->index, end_index);
 
                 return read_exec(pcol);
         }
@@ -722,11 +733,28 @@ int exofs_write_begin(struct file *file, struct address_space *mapping,
 
          /* read modify write */
         if (!PageUptodate(page) && (len != PAGE_CACHE_SIZE)) {
+                loff_t i_size = i_size_read(mapping->host);
+                pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
+                size_t rlen;
+
+                if (page->index < end_index)
+                        rlen = PAGE_CACHE_SIZE;
+                else if (page->index == end_index)
+                        rlen = i_size & ~PAGE_CACHE_MASK;
+                else
+                        rlen = 0;
+
+                if (!rlen) {
+                        clear_highpage(page);
+                        SetPageUptodate(page);
+                        goto out;
+                }
+
                 ret = _readpage(page, true);
                 if (ret) {
                         /*SetPageError was done by _readpage. Is it ok?*/
                         unlock_page(page);
-                        EXOFS_DBGMSG("__readpage_filler failed\n");
+                        EXOFS_DBGMSG("__readpage failed\n");
                 }
         }
 out:
@@ -1030,6 +1058,7 @@ struct inode *exofs_iget(struct super_block *sb, unsigned long ino)
                 memcpy(oi->i_data, fcb.i_data, sizeof(fcb.i_data));
         }
 
+        inode->i_mapping->backing_dev_info = sb->s_bdi;
         if (S_ISREG(inode->i_mode)) {
                 inode->i_op = &exofs_file_inode_operations;
                 inode->i_fop = &exofs_file_operations;
@@ -1073,6 +1102,7 @@ int __exofs_wait_obj_created(struct exofs_i_info *oi)
         }
         return unlikely(is_bad_inode(&oi->vfs_inode)) ? -EIO : 0;
 }
+
 /*
  * Callback function from exofs_new_inode().  The important thing is that we
  * set the obj_created flag so that other methods know that the object exists on
@@ -1130,7 +1160,7 @@ struct inode *exofs_new_inode(struct inode *dir, int mode)
 
         sbi = sb->s_fs_info;
 
-        sb->s_dirt = 1;
+        inode->i_mapping->backing_dev_info = sb->s_bdi;
         inode_init_owner(inode, dir, mode);
         inode->i_ino = sbi->s_nextid++;
         inode->i_blkbits = EXOFS_BLKSHIFT;
@@ -1141,6 +1171,8 @@ struct inode *exofs_new_inode(struct inode *dir, int mode)
         spin_unlock(&sbi->s_next_gen_lock);
         insert_inode_hash(inode);
 
+        exofs_sbi_write_stats(sbi); /* Make sure new sbi->s_nextid is on disk */
+
         mark_inode_dirty(inode);
 
         ret = exofs_get_io_state(&sbi->layout, &ios);
@@ -1271,7 +1303,8 @@ out:
 
 int exofs_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
-        return exofs_update_inode(inode, wbc->sync_mode == WB_SYNC_ALL);
+        /* FIXME: fix fsync and use wbc->sync_mode == WB_SYNC_ALL */
+        return exofs_update_inode(inode, 1);
 }
 
 /*
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 8c6c4669b381..06065bd37fc3 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -48,6 +48,7 @@
  * struct to hold what we get from mount options
  */
 struct exofs_mountopt {
+        bool is_osdname;
         const char *dev_name;
         uint64_t pid;
         int timeout;
@@ -56,7 +57,7 @@ struct exofs_mountopt {
 /*
  * exofs-specific mount-time options.
  */
-enum { Opt_pid, Opt_to, Opt_mkfs, Opt_format, Opt_err };
+enum { Opt_name, Opt_pid, Opt_to, Opt_err };
 
 /*
  * Our mount-time options.  These should ideally be 64-bit unsigned, but the
@@ -64,6 +65,7 @@ enum { Opt_pid, Opt_to, Opt_mkfs, Opt_format, Opt_err };
  * sufficient for most applications now.
  */
 static match_table_t tokens = {
+        {Opt_name, "osdname=%s"},
         {Opt_pid, "pid=%u"},
         {Opt_to, "to=%u"},
         {Opt_err, NULL}
@@ -94,6 +96,14 @@ static int parse_options(char *options, struct exofs_mountopt *opts)
 
                 token = match_token(p, tokens, args);
                 switch (token) {
+                case Opt_name:
+                        opts->dev_name = match_strdup(&args[0]);
+                        if (unlikely(!opts->dev_name)) {
+                                EXOFS_ERR("Error allocating dev_name");
+                                return -ENOMEM;
+                        }
+                        opts->is_osdname = true;
+                        break;
                 case Opt_pid:
                         if (0 == match_strlcpy(str, &args[0], sizeof(str)))
                                 return -EINVAL;
@@ -203,6 +213,101 @@ static void destroy_inodecache(void)
 static const struct super_operations exofs_sops;
 static const struct export_operations exofs_export_ops;
 
+static const struct osd_attr g_attr_sb_stats = ATTR_DEF(
+        EXOFS_APAGE_SB_DATA,
+        EXOFS_ATTR_SB_STATS,
+        sizeof(struct exofs_sb_stats));
+
+static int __sbi_read_stats(struct exofs_sb_info *sbi)
+{
+        struct osd_attr attrs[] = {
+                [0] = g_attr_sb_stats,
+        };
+        struct exofs_io_state *ios;
+        int ret;
+
+        ret = exofs_get_io_state(&sbi->layout, &ios);
+        if (unlikely(ret)) {
+                EXOFS_ERR("%s: exofs_get_io_state failed.\n", __func__);
+                return ret;
+        }
+
+        ios->cred = sbi->s_cred;
+
+        ios->in_attr = attrs;
+        ios->in_attr_len = ARRAY_SIZE(attrs);
+
+        ret = exofs_sbi_read(ios);
+        if (unlikely(ret)) {
+                EXOFS_ERR("Error reading super_block stats => %d\n", ret);
+                goto out;
+        }
+
+        ret = extract_attr_from_ios(ios, &attrs[0]);
+        if (ret) {
+                EXOFS_ERR("%s: extract_attr of sb_stats failed\n", __func__);
+                goto out;
+        }
+        if (attrs[0].len) {
+                struct exofs_sb_stats *ess;
+
+                if (unlikely(attrs[0].len != sizeof(*ess))) {
+                        EXOFS_ERR("%s: Wrong version of exofs_sb_stats "
+                                  "size(%d) != expected(%zd)\n",
+                                  __func__, attrs[0].len, sizeof(*ess));
+                        goto out;
+                }
+
+                ess = attrs[0].val_ptr;
+                sbi->s_nextid = le64_to_cpu(ess->s_nextid);
+                sbi->s_numfiles = le32_to_cpu(ess->s_numfiles);
+        }
+
+out:
+        exofs_put_io_state(ios);
+        return ret;
+}
+
+static void stats_done(struct exofs_io_state *ios, void *p)
+{
+        exofs_put_io_state(ios);
+        /* Good thanks nothing to do anymore */
+}
+
+/* Asynchronously write the stats attribute */
+int exofs_sbi_write_stats(struct exofs_sb_info *sbi)
+{
+        struct osd_attr attrs[] = {
+                [0] = g_attr_sb_stats,
+        };
+        struct exofs_io_state *ios;
+        int ret;
+
+        ret = exofs_get_io_state(&sbi->layout, &ios);
+        if (unlikely(ret)) {
+                EXOFS_ERR("%s: exofs_get_io_state failed.\n", __func__);
+                return ret;
+        }
+
+        sbi->s_ess.s_nextid   = cpu_to_le64(sbi->s_nextid);
+        sbi->s_ess.s_numfiles = cpu_to_le64(sbi->s_numfiles);
+        attrs[0].val_ptr = &sbi->s_ess;
+
+        ios->cred = sbi->s_cred;
+        ios->done = stats_done;
+        ios->private = sbi;
+        ios->out_attr = attrs;
+        ios->out_attr_len = ARRAY_SIZE(attrs);
+
+        ret = exofs_sbi_write(ios);
+        if (unlikely(ret)) {
+                EXOFS_ERR("%s: exofs_sbi_write failed.\n", __func__);
+                exofs_put_io_state(ios);
+        }
+
+        return ret;
+}
+
 /*
  * Write the superblock to the OSD
  */
@@ -213,18 +318,25 @@ int exofs_sync_fs(struct super_block *sb, int wait)
         struct exofs_io_state *ios;
         int ret = -ENOMEM;
 
-        lock_super(sb);
+        fscb = kmalloc(sizeof(*fscb), GFP_KERNEL);
+        if (unlikely(!fscb))
+                return -ENOMEM;
+
         sbi = sb->s_fs_info;
-        fscb = &sbi->s_fscb;
 
+        /* NOTE: We no longer dirty the super_block anywhere in exofs. The
+         * reason we write the fscb here on unmount is so we can stay backwards
+         * compatible with fscb->s_version == 1. (What we are not compatible
+         * with is if a new version FS crashed and then we try to mount an old
+         * version). Otherwise the exofs_fscb is read-only from mkfs time. All
+         * the writeable info is set in exofs_sbi_write_stats() above.
+         */
         ret = exofs_get_io_state(&sbi->layout, &ios);
-        if (ret)
+        if (unlikely(ret))
                 goto out;
 
-        /* Note: We only write the changing part of the fscb. .i.e upto the
-         *       the fscb->s_dev_table_oid member. There is no read-modify-write
-         *       here.
-         */
+        lock_super(sb);
+
         ios->length = offsetof(struct exofs_fscb, s_dev_table_oid);
         memset(fscb, 0, ios->length);
         fscb->s_nextid = cpu_to_le64(sbi->s_nextid);
@@ -239,16 +351,17 @@ int exofs_sync_fs(struct super_block *sb, int wait)
         ios->cred = sbi->s_cred;
 
         ret = exofs_sbi_write(ios);
-        if (unlikely(ret)) {
+        if (unlikely(ret))
                 EXOFS_ERR("%s: exofs_sbi_write failed.\n", __func__);
-                goto out;
-        }
-        sb->s_dirt = 0;
+        else
+                sb->s_dirt = 0;
+
 
+        unlock_super(sb);
 out:
         EXOFS_DBGMSG("s_nextid=0x%llx ret=%d\n", _LLU(sbi->s_nextid), ret);
         exofs_put_io_state(ios);
-        unlock_super(sb);
+        kfree(fscb);
         return ret;
 }
 
@@ -292,13 +405,14 @@ static void exofs_put_super(struct super_block *sb)
         int num_pend;
         struct exofs_sb_info *sbi = sb->s_fs_info;
 
-        if (sb->s_dirt)
-                exofs_write_super(sb);
-
         /* make sure there are no pending commands */
         for (num_pend = atomic_read(&sbi->s_curr_pending); num_pend > 0;
              num_pend = atomic_read(&sbi->s_curr_pending)) {
                 wait_queue_head_t wq;
+
+                printk(KERN_NOTICE "%s: !!Pending operations in flight. "
+                       "This is a BUG. please report to osd-dev@open-osd.org\n",
+                       __func__);
                 init_waitqueue_head(&wq);
                 wait_event_timeout(wq,
                                   (atomic_read(&sbi->s_curr_pending) == 0),
@@ -390,6 +504,23 @@ static int _read_and_match_data_map(struct exofs_sb_info *sbi, unsigned numdevs,
         return 0;
 }
 
+static unsigned __ra_pages(struct exofs_layout *layout)
+{
+        const unsigned _MIN_RA = 32; /* min 128K read-ahead */
+        unsigned ra_pages = layout->group_width * layout->stripe_unit /
+                                PAGE_SIZE;
+        unsigned max_io_pages = exofs_max_io_pages(layout, ~0);
+
+        ra_pages *= 2; /* two stripes */
+        if (ra_pages < _MIN_RA)
+                ra_pages = roundup(_MIN_RA, ra_pages / 2);
+
+        if (ra_pages > max_io_pages)
+                ra_pages = max_io_pages;
+
+        return ra_pages;
+}
+
 /* @odi is valid only as long as @fscb_dev is valid */
 static int exofs_devs_2_odi(struct exofs_dt_device_info *dt_dev,
                              struct osd_dev_info *odi)
@@ -495,7 +626,7 @@ static int exofs_read_lookup_dev_table(struct exofs_sb_info **psbi,
                 }
 
                 od = osduld_info_lookup(&odi);
-                if (unlikely(IS_ERR(od))) {
+                if (IS_ERR(od)) {
                         ret = PTR_ERR(od);
                         EXOFS_ERR("ERROR: device requested is not found "
                                   "osd_name-%s =>%d\n", odi.osdname, ret);
@@ -558,9 +689,17 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent)
                 goto free_bdi;
 
         /* use mount options to fill superblock */
-        od = osduld_path_lookup(opts->dev_name);
+        if (opts->is_osdname) {
+                struct osd_dev_info odi = {.systemid_len = 0};
+
+                odi.osdname_len = strlen(opts->dev_name);
+                odi.osdname = (u8 *)opts->dev_name;
+                od = osduld_info_lookup(&odi);
+        } else {
+                od = osduld_path_lookup(opts->dev_name);
+        }
         if (IS_ERR(od)) {
-                ret = PTR_ERR(od);
+                ret = -EINVAL;
                 goto free_sbi;
         }
 
@@ -594,6 +733,7 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent)
                 goto free_sbi;
 
         sb->s_magic = le16_to_cpu(fscb.s_magic);
+        /* NOTE: we read below to be backward compatible with old versions */
         sbi->s_nextid = le64_to_cpu(fscb.s_nextid);
         sbi->s_numfiles = le32_to_cpu(fscb.s_numfiles);
 
@@ -604,7 +744,7 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent)
                 ret = -EINVAL;
                 goto free_sbi;
         }
-        if (le32_to_cpu(fscb.s_version) != EXOFS_FSCB_VER) {
+        if (le32_to_cpu(fscb.s_version) > EXOFS_FSCB_VER) {
                 EXOFS_ERR("ERROR: Bad FSCB version expected-%d got-%d\n",
                           EXOFS_FSCB_VER, le32_to_cpu(fscb.s_version));
                 ret = -EINVAL;
@@ -622,7 +762,10 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent)
                         goto free_sbi;
         }
 
+        __sbi_read_stats(sbi);
+
         /* set up operation vectors */
+        sbi->bdi.ra_pages = __ra_pages(&sbi->layout);
         sb->s_bdi = &sbi->bdi;
         sb->s_fs_info = sbi;
         sb->s_op = &exofs_sops;
@@ -652,6 +795,8 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent)
 
         _exofs_print_device("Mounting", opts->dev_name, sbi->layout.s_ods[0],
                             sbi->layout.s_pid);
+        if (opts->is_osdname)
+                kfree(opts->dev_name);
         return 0;
 
 free_sbi:
@@ -660,6 +805,8 @@ free_bdi:
         EXOFS_ERR("Unable to mount exofs on %s pid=0x%llx err=%d\n",
                   opts->dev_name, sbi->layout.s_pid, ret);
         exofs_free_sbi(sbi);
+        if (opts->is_osdname)
+                kfree(opts->dev_name);
         return ret;
 }
 
@@ -677,7 +824,8 @@ static struct dentry *exofs_mount(struct file_system_type *type,
         if (ret)
                 return ERR_PTR(ret);
 
-        opts.dev_name = dev_name;
+        if (!opts.dev_name)
+                opts.dev_name = dev_name;
         return mount_nodev(type, flags, &opts, exofs_fill_super);
 }
 
diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c
index 7b4180554a62..abea5a17c764 100644
--- a/fs/ext2/acl.c
+++ b/fs/ext2/acl.c
@@ -406,7 +406,7 @@ ext2_xattr_set_acl(struct dentry *dentry, const char *name, const void *value,
                 return -EINVAL;
         if (!test_opt(dentry->d_sb, POSIX_ACL))
                 return -EOPNOTSUPP;
-        if (!is_owner_or_cap(dentry->d_inode))
+        if (!inode_owner_or_capable(dentry->d_inode))
                 return -EPERM;
 
         if (value) {
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 1b48c3370872..645be9e7ee47 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -174,3 +174,9 @@ ext2_group_first_block_no(struct super_block *sb, unsigned long group_no)
         return group_no * (ext2_fsblk_t)EXT2_BLOCKS_PER_GROUP(sb) +
                 le32_to_cpu(EXT2_SB(sb)->s_es->s_first_data_block);
 }
+
+#define ext2_set_bit    __test_and_set_bit_le
+#define ext2_clear_bit  __test_and_clear_bit_le
+#define ext2_test_bit   test_bit_le
+#define ext2_find_first_zero_bit        find_first_zero_bit_le
+#define ext2_find_next_zero_bit         find_next_zero_bit_le
diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c
index e7431309bdca..f81e250ac5c4 100644
--- a/fs/ext2/ioctl.c
+++ b/fs/ext2/ioctl.c
@@ -39,7 +39,7 @@ long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
                 if (ret)
                         return ret;
 
-                if (!is_owner_or_cap(inode)) {
+                if (!inode_owner_or_capable(inode)) {
                         ret = -EACCES;
                         goto setflags_out;
                 }
@@ -89,7 +89,7 @@ setflags_out:
         case EXT2_IOC_GETVERSION:
                 return put_user(inode->i_generation, (int __user *) arg);
         case EXT2_IOC_SETVERSION:
-                if (!is_owner_or_cap(inode))
+                if (!inode_owner_or_capable(inode))
                         return -EPERM;
                 ret = mnt_want_write(filp->f_path.mnt);
                 if (ret)
@@ -115,7 +115,7 @@ setflags_out:
                 if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode))
                         return -ENOTTY;
 
-                if (!is_owner_or_cap(inode))
+                if (!inode_owner_or_capable(inode))
                         return -EACCES;
 
                 if (get_user(rsv_window_size, (int __user *)arg))
diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c
index e4fa49e6c539..9d021c0d472a 100644
--- a/fs/ext3/acl.c
+++ b/fs/ext3/acl.c
@@ -435,7 +435,7 @@ ext3_xattr_set_acl(struct dentry *dentry, const char *name, const void *value,
                 return -EINVAL;
         if (!test_opt(inode->i_sb, POSIX_ACL))
                 return -EOPNOTSUPP;
-        if (!is_owner_or_cap(inode))
+        if (!inode_owner_or_capable(inode))
                 return -EPERM;
 
         if (value) {
diff --git a/fs/ext3/ioctl.c b/fs/ext3/ioctl.c
index fc080dd561f7..f4090bd2f345 100644
--- a/fs/ext3/ioctl.c
+++ b/fs/ext3/ioctl.c
@@ -38,7 +38,7 @@ long ext3_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
                 unsigned int oldflags;
                 unsigned int jflag;
 
-                if (!is_owner_or_cap(inode))
+                if (!inode_owner_or_capable(inode))
                         return -EACCES;
 
                 if (get_user(flags, (int __user *) arg))
@@ -123,7 +123,7 @@ flags_out:
                 __u32 generation;
                 int err;
 
-                if (!is_owner_or_cap(inode))
+                if (!inode_owner_or_capable(inode))
                         return -EPERM;
 
                 err = mnt_want_write(filp->f_path.mnt);
@@ -192,7 +192,7 @@ setversion_out:
                 if (err)
                         return err;
 
-                if (!is_owner_or_cap(inode)) {
+                if (!inode_owner_or_capable(inode)) {
                         err = -EACCES;
                         goto setrsvsz_out;
                 }
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index e0270d1f8d82..21eacd7b7d79 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -433,7 +433,7 @@ ext4_xattr_set_acl(struct dentry *dentry, const char *name, const void *value,
                 return -EINVAL;
         if (!test_opt(inode->i_sb, POSIX_ACL))
                 return -EOPNOTSUPP;
-        if (!is_owner_or_cap(inode))
+        if (!inode_owner_or_capable(inode))
                 return -EPERM;
 
         if (value) {
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 3aa0b72b3b94..4daaf2b753f4 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -923,14 +923,14 @@ struct ext4_inode_info {
 #define test_opt2(sb, opt)              (EXT4_SB(sb)->s_mount_opt2 & \
                                          EXT4_MOUNT2_##opt)
 
-#define ext4_set_bit                    ext2_set_bit
+#define ext4_set_bit                    __test_and_set_bit_le
 #define ext4_set_bit_atomic             ext2_set_bit_atomic
-#define ext4_clear_bit                  ext2_clear_bit
+#define ext4_clear_bit                  __test_and_clear_bit_le
 #define ext4_clear_bit_atomic           ext2_clear_bit_atomic
-#define ext4_test_bit                   ext2_test_bit
-#define ext4_find_first_zero_bit        ext2_find_first_zero_bit
-#define ext4_find_next_zero_bit         ext2_find_next_zero_bit
-#define ext4_find_next_bit              ext2_find_next_bit
+#define ext4_test_bit                   test_bit_le
+#define ext4_find_first_zero_bit        find_first_zero_bit_le
+#define ext4_find_next_zero_bit         find_next_zero_bit_le
+#define ext4_find_next_bit              find_next_bit_le
 
 /*
  * Maximal mount counts between two filesystem checks
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index ccce8a7e94ed..7516fb9c0bd5 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -131,7 +131,7 @@ static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
                  * fragmenting the file system's free space.  Maybe we
                  * should have some hueristics or some way to allow
                  * userspace to pass a hint to file system,
-                 * especiially if the latter case turns out to be
+                 * especially if the latter case turns out to be
                  * common.
                  */
                 ex = path[depth].p_ext;
@@ -2844,7 +2844,7 @@ fix_extent_len:
  * ext4_get_blocks_dio_write() when DIO to write
  * to an uninitialized extent.
  *
- * Writing to an uninitized extent may result in splitting the uninitialized
+ * Writing to an uninitialized extent may result in splitting the uninitialized
  * extent into multiple /initialized uninitialized extents (up to three)
  * There are three possibilities:
  *   a> There is no split required: Entire extent should be uninitialized
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index eb3bc2fe647e..a84faa110bcd 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -38,7 +38,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
                 unsigned int oldflags;
                 unsigned int jflag;
 
-                if (!is_owner_or_cap(inode))
+                if (!inode_owner_or_capable(inode))
                         return -EACCES;
 
                 if (get_user(flags, (int __user *) arg))
@@ -146,7 +146,7 @@ flags_out:
                 __u32 generation;
                 int err;
 
-                if (!is_owner_or_cap(inode))
+                if (!inode_owner_or_capable(inode))
                         return -EPERM;
 
                 err = mnt_want_write(filp->f_path.mnt);
@@ -298,7 +298,7 @@ mext_out:
         case EXT4_IOC_MIGRATE:
         {
                 int err;
-                if (!is_owner_or_cap(inode))
+                if (!inode_owner_or_capable(inode))
                         return -EACCES;
 
                 err = mnt_want_write(filp->f_path.mnt);
@@ -320,7 +320,7 @@ mext_out:
         case EXT4_IOC_ALLOC_DA_BLKS:
         {
                 int err;
-                if (!is_owner_or_cap(inode))
+                if (!inode_owner_or_capable(inode))
                         return -EACCES;
 
                 err = mnt_want_write(filp->f_path.mnt);
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 6c82e5bac039..22764c7c8382 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -159,7 +159,7 @@ static int setfl(int fd, struct file * filp, unsigned long arg)
 
         /* O_NOATIME can only be set by the owner or superuser */
         if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME))
-                if (!is_owner_or_cap(inode))
+                if (!inode_owner_or_capable(inode))
                         return -EPERM;
 
         /* required for strict SunOS emulation */
diff --git a/fs/fifo.c b/fs/fifo.c
index 4e303c22d5ee..b1a524d798e7 100644
--- a/fs/fifo.c
+++ b/fs/fifo.c
@@ -66,8 +66,7 @@ static int fifo_open(struct inode *inode, struct file *filp)
                                 /* suppress POLLHUP until we have
                                  * seen a writer */
                                 filp->f_version = pipe->w_counter;
-                        } else 
-                        {
+                        } else {
                                 wait_for_partner(inode, &pipe->w_counter);
                                 if(signal_pending(current))
                                         goto err_rd;
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index 3e87cce5837d..b6cca47f7b07 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -305,7 +305,7 @@ static void cuse_gendev_release(struct device *dev)
 static void cuse_process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 {
         struct cuse_conn *cc = fc_to_cc(fc);
-        struct cuse_init_out *arg = &req->misc.cuse_init_out;
+        struct cuse_init_out *arg = req->out.args[0].value;
         struct page *page = req->pages[0];
         struct cuse_devinfo devinfo = { };
         struct device *dev;
@@ -384,6 +384,7 @@ static void cuse_process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
         dev_set_uevent_suppress(dev, 0);
         kobject_uevent(&dev->kobj, KOBJ_ADD);
 out:
+        kfree(arg);
         __free_page(page);
         return;
 
@@ -405,6 +406,7 @@ static int cuse_send_init(struct cuse_conn *cc)
         struct page *page;
         struct fuse_conn *fc = &cc->fc;
         struct cuse_init_in *arg;
+        void *outarg;
 
         BUILD_BUG_ON(CUSE_INIT_INFO_MAX > PAGE_SIZE);
 
@@ -419,6 +421,10 @@ static int cuse_send_init(struct cuse_conn *cc)
         if (!page)
                 goto err_put_req;
 
+        outarg = kzalloc(sizeof(struct cuse_init_out), GFP_KERNEL);
+        if (!outarg)
+                goto err_free_page;
+
         arg = &req->misc.cuse_init_in;
         arg->major = FUSE_KERNEL_VERSION;
         arg->minor = FUSE_KERNEL_MINOR_VERSION;
@@ -429,7 +435,7 @@ static int cuse_send_init(struct cuse_conn *cc)
         req->in.args[0].value = arg;
         req->out.numargs = 2;
         req->out.args[0].size = sizeof(struct cuse_init_out);
-        req->out.args[0].value = &req->misc.cuse_init_out;
+        req->out.args[0].value = outarg;
         req->out.args[1].size = CUSE_INIT_INFO_MAX;
         req->out.argvar = 1;
         req->out.argpages = 1;
@@ -440,6 +446,8 @@ static int cuse_send_init(struct cuse_conn *cc)
 
         return 0;
 
+err_free_page:
+        __free_page(page);
 err_put_req:
         fuse_put_request(fc, req);
 err:
@@ -458,7 +466,7 @@ static void cuse_fc_release(struct fuse_conn *fc)
  * @file: file struct being opened
  *
  * Userland CUSE server can create a CUSE device by opening /dev/cuse
- * and replying to the initilaization request kernel sends.  This
+ * and replying to the initialization request kernel sends.  This
  * function is responsible for handling CUSE device initialization.
  * Because the fd opened by this function is used during
  * initialization, this function only creates cuse_conn and sends
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index cf8d28d1fbad..640fc229df10 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -737,14 +737,12 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
         if (WARN_ON(PageMlocked(oldpage)))
                 goto out_fallback_unlock;
 
-        remove_from_page_cache(oldpage);
-        page_cache_release(oldpage);
-
-        err = add_to_page_cache_locked(newpage, mapping, index, GFP_KERNEL);
+        err = replace_page_cache_page(oldpage, newpage, GFP_KERNEL);
         if (err) {
-                printk(KERN_WARNING "fuse_try_move_page: failed to add page");
-                goto out_fallback_unlock;
+                unlock_page(newpage);
+                return err;
         }
+
         page_cache_get(newpage);
 
         if (!(buf->flags & PIPE_BUF_FLAG_LRU))
@@ -1910,6 +1908,21 @@ __acquires(fc->lock)
                 kfree(dequeue_forget(fc, 1, NULL));
 }
 
+static void end_polls(struct fuse_conn *fc)
+{
+        struct rb_node *p;
+
+        p = rb_first(&fc->polled_files);
+
+        while (p) {
+                struct fuse_file *ff;
+                ff = rb_entry(p, struct fuse_file, polled_node);
+                wake_up_interruptible_all(&ff->poll_wait);
+
+                p = rb_next(p);
+        }
+}
+
 /*
  * Abort all requests.
  *
@@ -1937,6 +1950,7 @@ void fuse_abort_conn(struct fuse_conn *fc)
                 fc->blocked = 0;
                 end_io_requests(fc);
                 end_queued_requests(fc);
+                end_polls(fc);
                 wake_up_all(&fc->waitq);
                 wake_up_all(&fc->blocked_waitq);
                 kill_fasync(&fc->fasync, SIGIO, POLL_IN);
@@ -1953,6 +1967,7 @@ int fuse_dev_release(struct inode *inode, struct file *file)
                 fc->connected = 0;
                 fc->blocked = 0;
                 end_queued_requests(fc);
+                end_polls(fc);
                 wake_up_all(&fc->blocked_waitq);
                 spin_unlock(&fc->lock);
                 fuse_conn_put(fc);
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 8bd0ef9286c3..c6ba49bd95b3 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -158,10 +158,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
 {
         struct inode *inode;
 
-        if (nd && nd->flags & LOOKUP_RCU)
-                return -ECHILD;
-
-        inode = entry->d_inode;
+        inode = ACCESS_ONCE(entry->d_inode);
         if (inode && is_bad_inode(inode))
                 return 0;
         else if (fuse_dentry_time(entry) < get_jiffies_64()) {
@@ -177,6 +174,9 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
                 if (!inode)
                         return 0;
 
+                if (nd->flags & LOOKUP_RCU)
+                        return -ECHILD;
+
                 fc = get_fuse_conn(inode);
                 req = fuse_get_req(fc);
                 if (IS_ERR(req))
@@ -970,6 +970,14 @@ static int fuse_access(struct inode *inode, int mask)
         return err;
 }
 
+static int fuse_perm_getattr(struct inode *inode, int flags)
+{
+        if (flags & IPERM_FLAG_RCU)
+                return -ECHILD;
+
+        return fuse_do_getattr(inode, NULL, NULL);
+}
+
 /*
  * Check permission.  The two basic access models of FUSE are:
  *
@@ -989,9 +997,6 @@ static int fuse_permission(struct inode *inode, int mask, unsigned int flags)
         bool refreshed = false;
         int err = 0;
 
-        if (flags & IPERM_FLAG_RCU)
-                return -ECHILD;
-
         if (!fuse_allow_task(fc, current))
                 return -EACCES;
 
@@ -1000,9 +1005,15 @@ static int fuse_permission(struct inode *inode, int mask, unsigned int flags)
          */
         if ((fc->flags & FUSE_DEFAULT_PERMISSIONS) ||
             ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))) {
-                err = fuse_update_attributes(inode, NULL, NULL, &refreshed);
-                if (err)
-                        return err;
+                struct fuse_inode *fi = get_fuse_inode(inode);
+
+                if (fi->i_time < get_jiffies_64()) {
+                        refreshed = true;
+
+                        err = fuse_perm_getattr(inode, flags);
+                        if (err)
+                                return err;
+                }
         }
 
         if (fc->flags & FUSE_DEFAULT_PERMISSIONS) {
@@ -1012,7 +1023,7 @@ static int fuse_permission(struct inode *inode, int mask, unsigned int flags)
                    attributes.  This is also needed, because the root
                    node will at first have no permissions */
                 if (err == -EACCES && !refreshed) {
-                        err = fuse_do_getattr(inode, NULL, NULL);
+                        err = fuse_perm_getattr(inode, flags);
                         if (!err)
                                 err = generic_permission(inode, mask,
                                                         flags, NULL);
@@ -1023,13 +1034,16 @@ static int fuse_permission(struct inode *inode, int mask, unsigned int flags)
                    noticed immediately, only after the attribute
                    timeout has expired */
         } else if (mask & (MAY_ACCESS | MAY_CHDIR)) {
+                if (flags & IPERM_FLAG_RCU)
+                        return -ECHILD;
+
                 err = fuse_access(inode, mask);
         } else if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode)) {
                 if (!(inode->i_mode & S_IXUGO)) {
                         if (refreshed)
                                 return -EACCES;
 
-                        err = fuse_do_getattr(inode, NULL, NULL);
+                        err = fuse_perm_getattr(inode, flags);
                         if (!err && !(inode->i_mode & S_IXUGO))
                                 return -EACCES;
                 }
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 9e0832dbb1e3..6ea00734984e 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -222,7 +222,7 @@ static void fuse_prepare_release(struct fuse_file *ff, int flags, int opcode)
                 rb_erase(&ff->polled_node, &fc->polled_files);
         spin_unlock(&fc->lock);
 
-        wake_up_interruptible_sync(&ff->poll_wait);
+        wake_up_interruptible_all(&ff->poll_wait);
 
         inarg->fh = ff->fh;
         inarg->flags = flags;
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index d4286947bc2c..b788becada76 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -272,7 +272,6 @@ struct fuse_req {
                 struct fuse_init_in init_in;
                 struct fuse_init_out init_out;
                 struct cuse_init_in cuse_init_in;
-                struct cuse_init_out cuse_init_out;
                 struct {
                         struct fuse_read_in in;
                         u64 attr_ver;
diff --git a/fs/generic_acl.c b/fs/generic_acl.c
index 06c48a891832..8f26d1a58912 100644
--- a/fs/generic_acl.c
+++ b/fs/generic_acl.c
@@ -74,7 +74,7 @@ generic_acl_set(struct dentry *dentry, const char *name, const void *value,
                 return -EINVAL;
         if (S_ISLNK(inode->i_mode))
                 return -EOPNOTSUPP;
-        if (!is_owner_or_cap(inode))
+        if (!inode_owner_or_capable(inode))
                 return -EPERM;
         if (value) {
                 acl = posix_acl_from_xattr(value, size);
diff --git a/fs/gfs2/Makefile b/fs/gfs2/Makefile
index 21f7e46da4c0..f3d23ef4e876 100644
--- a/fs/gfs2/Makefile
+++ b/fs/gfs2/Makefile
@@ -1,4 +1,4 @@
-EXTRA_CFLAGS := -I$(src)
+ccflags-y := -I$(src)
 obj-$(CONFIG_GFS2_FS) += gfs2.o
 gfs2-y := acl.o bmap.o dir.o xattr.o glock.o \
         glops.o inode.o log.o lops.o main.o meta_io.o \
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 4074b952b059..b2682e073eee 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -221,7 +221,7 @@ static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask)
                 goto out_drop_write;
 
         error = -EACCES;
-        if (!is_owner_or_cap(inode))
+        if (!inode_owner_or_capable(inode))
                 goto out;
 
         error = 0;
diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c
index 508ce662ce12..fbaa6690c8e0 100644
--- a/fs/hfsplus/ioctl.c
+++ b/fs/hfsplus/ioctl.c
@@ -47,7 +47,7 @@ static int hfsplus_ioctl_setflags(struct file *file, int __user *user_flags)
         if (err)
                 goto out;
 
-        if (!is_owner_or_cap(inode)) {
+        if (!inode_owner_or_capable(inode)) {
                 err = -EACCES;
                 goto out_drop_write;
         }
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 9885082b470f..b9eeb1cd03ff 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -332,8 +332,7 @@ static void truncate_huge_page(struct page *page)
 {
         cancel_dirty_page(page, /* No IO accounting for huge pages? */0);
         ClearPageUptodate(page);
-        remove_from_page_cache(page);
-        put_page(page);
+        delete_from_page_cache(page);
 }
 
 static void truncate_hugepages(struct inode *inode, loff_t lstart)
diff --git a/fs/inode.c b/fs/inode.c
index 9910c039f026..0b3da4a77704 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -25,6 +25,7 @@
 #include <linux/async.h>
 #include <linux/posix_acl.h>
 #include <linux/ima.h>
+#include <linux/cred.h>
 
 /*
  * This is needed for the following functions:
@@ -1715,7 +1716,7 @@ void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev)
 EXPORT_SYMBOL(init_special_inode);
 
 /**
- * Init uid,gid,mode for new inode according to posix standards
+ * inode_init_owner - Init uid,gid,mode for new inode according to posix standards
  * @inode: New inode
  * @dir: Directory inode
  * @mode: mode of the new inode
@@ -1733,3 +1734,22 @@ void inode_init_owner(struct inode *inode, const struct inode *dir,
         inode->i_mode = mode;
 }
 EXPORT_SYMBOL(inode_init_owner);
+
+/**
+ * inode_owner_or_capable - check current task permissions to inode
+ * @inode: inode being checked
+ *
+ * Return true if current either has CAP_FOWNER to the inode, or
+ * owns the file.
+ */
+bool inode_owner_or_capable(const struct inode *inode)
+{
+        struct user_namespace *ns = inode_userns(inode);
+
+        if (current_user_ns() == ns && current_fsuid() == inode->i_uid)
+                return true;
+        if (ns_capable(ns, CAP_FOWNER))
+                return true;
+        return false;
+}
+EXPORT_SYMBOL(inode_owner_or_capable);
diff --git a/fs/internal.h b/fs/internal.h
index f3d15de44b15..8318059b42c6 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -12,6 +12,7 @@
 #include <linux/lglock.h>
 
 struct super_block;
+struct file_system_type;
 struct linux_binprm;
 struct path;
 
@@ -61,10 +62,9 @@ extern int check_unsafe_exec(struct linux_binprm *);
 extern int copy_mount_options(const void __user *, unsigned long *);
 extern int copy_mount_string(const void __user *, char **);
 
-extern void free_vfsmnt(struct vfsmount *);
-extern struct vfsmount *alloc_vfsmnt(const char *);
 extern unsigned int mnt_get_count(struct vfsmount *mnt);
 extern struct vfsmount *__lookup_mnt(struct vfsmount *, struct dentry *, int);
+extern struct vfsmount *lookup_mnt(struct path *);
 extern void mnt_set_mountpoint(struct vfsmount *, struct dentry *,
                                 struct vfsmount *);
 extern void release_mounts(struct list_head *);
@@ -99,6 +99,8 @@ extern struct file *get_empty_filp(void);
 extern int do_remount_sb(struct super_block *, int, void *, int);
 extern void __put_super(struct super_block *sb);
 extern void put_super(struct super_block *sb);
+extern struct dentry *mount_fs(struct file_system_type *,
+                               int, const char *, void *);
 
 /*
  * open.c
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 1eebeb72b202..1d9b9fcb2db4 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -548,6 +548,7 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
 {
         int error = 0;
         int __user *argp = (int __user *)arg;
+        struct inode *inode = filp->f_path.dentry->d_inode;
 
         switch (cmd) {
         case FIOCLEX:
@@ -567,13 +568,11 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
                 break;
 
         case FIOQSIZE:
-                if (S_ISDIR(filp->f_path.dentry->d_inode->i_mode) ||
-                    S_ISREG(filp->f_path.dentry->d_inode->i_mode) ||
-                    S_ISLNK(filp->f_path.dentry->d_inode->i_mode)) {
-                        loff_t res =
-                                inode_get_bytes(filp->f_path.dentry->d_inode);
-                        error = copy_to_user((loff_t __user *)arg, &res,
-                                             sizeof(res)) ? -EFAULT : 0;
+                if (S_ISDIR(inode->i_mode) || S_ISREG(inode->i_mode) ||
+                    S_ISLNK(inode->i_mode)) {
+                        loff_t res = inode_get_bytes(inode);
+                        error = copy_to_user(argp, &res, sizeof(res)) ?
+                                        -EFAULT : 0;
                 } else
                         error = -ENOTTY;
                 break;
@@ -590,14 +589,10 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
                 return ioctl_fiemap(filp, arg);
 
         case FIGETBSZ:
-        {
-                struct inode *inode = filp->f_path.dentry->d_inode;
-                int __user *p = (int __user *)arg;
-                return put_user(inode->i_sb->s_blocksize, p);
-        }
+                return put_user(inode->i_sb->s_blocksize, argp);
 
         default:
-                if (S_ISREG(filp->f_path.dentry->d_inode->i_mode))
+                if (S_ISREG(inode->i_mode))
                         error = file_ioctl(filp, cmd, arg);
                 else
                         error = vfs_ioctl(filp, cmd, arg);
diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c
index 95b79672150a..828a0e1ea438 100644
--- a/fs/jffs2/acl.c
+++ b/fs/jffs2/acl.c
@@ -402,7 +402,7 @@ static int jffs2_acl_setxattr(struct dentry *dentry, const char *name,
 
         if (name[0] != '\0')
                 return -EINVAL;
-        if (!is_owner_or_cap(dentry->d_inode))
+        if (!inode_owner_or_capable(dentry->d_inode))
                 return -EPERM;
 
         if (value) {
diff --git a/fs/jffs2/compr_zlib.c b/fs/jffs2/compr_zlib.c
index fd05a0b9431d..5a001020c542 100644
--- a/fs/jffs2/compr_zlib.c
+++ b/fs/jffs2/compr_zlib.c
@@ -40,12 +40,13 @@ static z_stream inf_strm, def_strm;
 
 static int __init alloc_workspaces(void)
 {
-        def_strm.workspace = vmalloc(zlib_deflate_workspacesize());
+        def_strm.workspace = vmalloc(zlib_deflate_workspacesize(MAX_WBITS,
+                                                        MAX_MEM_LEVEL));
         if (!def_strm.workspace) {
-                printk(KERN_WARNING "Failed to allocate %d bytes for deflate workspace\n", zlib_deflate_workspacesize());
+                printk(KERN_WARNING "Failed to allocate %d bytes for deflate workspace\n", zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL));
                 return -ENOMEM;
         }
-        D1(printk(KERN_DEBUG "Allocated %d bytes for deflate workspace\n", zlib_deflate_workspacesize()));
+        D1(printk(KERN_DEBUG "Allocated %d bytes for deflate workspace\n", zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL)));
         inf_strm.workspace = vmalloc(zlib_inflate_workspacesize());
         if (!inf_strm.workspace) {
                 printk(KERN_WARNING "Failed to allocate %d bytes for inflate workspace\n", zlib_inflate_workspacesize());
diff --git a/fs/jfs/Makefile b/fs/jfs/Makefile
index 3adb6395e42d..a58fa72d7e59 100644
--- a/fs/jfs/Makefile
+++ b/fs/jfs/Makefile
@@ -13,4 +13,4 @@ jfs-y    := super.o file.o inode.o namei.o jfs_mount.o jfs_umount.o \
 
 jfs-$(CONFIG_JFS_POSIX_ACL) += acl.o
 
-EXTRA_CFLAGS += -D_JFS_4K
+ccflags-y := -D_JFS_4K
diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c
index afe222bf300f..6f98a1866776 100644
--- a/fs/jfs/ioctl.c
+++ b/fs/jfs/ioctl.c
@@ -72,7 +72,7 @@ long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
                 if (err)
                         return err;
 
-                if (!is_owner_or_cap(inode)) {
+                if (!inode_owner_or_capable(inode)) {
                         err = -EACCES;
                         goto setflags_out;
                 }
diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c
index 3fa4c32272df..24838f1eeee5 100644
--- a/fs/jfs/xattr.c
+++ b/fs/jfs/xattr.c
@@ -678,7 +678,7 @@ static int can_set_system_xattr(struct inode *inode, const char *name,
         struct posix_acl *acl;
         int rc;
 
-        if (!is_owner_or_cap(inode))
+        if (!inode_owner_or_capable(inode))
                 return -EPERM;
 
         /*
diff --git a/fs/locks.c b/fs/locks.c
index 822c3d1843af..0a4f50dfadfb 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -414,17 +414,7 @@ static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl,
         fl->fl_ops = NULL;
         fl->fl_lmops = NULL;
 
-        switch (l->l_type) {
-        case F_RDLCK:
-        case F_WRLCK:
-        case F_UNLCK:
-                fl->fl_type = l->l_type;
-                break;
-        default:
-                return -EINVAL;
-        }
-
-        return (0);
+        return assign_type(fl, l->l_type);
 }
 #endif
 
diff --git a/fs/logfs/compr.c b/fs/logfs/compr.c
index 44bbfd249abc..961f02b86d97 100644
--- a/fs/logfs/compr.c
+++ b/fs/logfs/compr.c
@@ -81,7 +81,7 @@ error:
 
 int __init logfs_compr_init(void)
 {
-        size_t size = max(zlib_deflate_workspacesize(),
+        size_t size = max(zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL),
                         zlib_inflate_workspacesize());
         stream.workspace = vmalloc(size);
         if (!stream.workspace)
diff --git a/fs/logfs/file.c b/fs/logfs/file.c
index e86376b87af1..c2ad7028def4 100644
--- a/fs/logfs/file.c
+++ b/fs/logfs/file.c
@@ -196,7 +196,7 @@ long logfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
                 if (IS_RDONLY(inode))
                         return -EROFS;
 
-                if (!is_owner_or_cap(inode))
+                if (!inode_owner_or_capable(inode))
                         return -EACCES;
 
                 err = get_user(flags, (int __user *)arg);
diff --git a/fs/minix/Kconfig b/fs/minix/Kconfig
index 0fd7ca994264..6624684dd5de 100644
--- a/fs/minix/Kconfig
+++ b/fs/minix/Kconfig
@@ -15,3 +15,11 @@ config MINIX_FS
           module will be called minix.  Note that the file system of your root
           partition (the one containing the directory /) cannot be compiled as
           a module.
+
+config MINIX_FS_NATIVE_ENDIAN
+        def_bool MINIX_FS
+        depends on H8300 || M32R || MICROBLAZE || MIPS || S390 || SUPERH || SPARC || XTENSA || (M68K && !MMU)
+
+config MINIX_FS_BIG_ENDIAN_16BIT_INDEXED
+        def_bool MINIX_FS
+        depends on M68K && MMU
diff --git a/fs/minix/minix.h b/fs/minix/minix.h
index 407b1c84911e..341e2122879a 100644
--- a/fs/minix/minix.h
+++ b/fs/minix/minix.h
@@ -88,4 +88,78 @@ static inline struct minix_inode_info *minix_i(struct inode *inode)
         return list_entry(inode, struct minix_inode_info, vfs_inode);
 }
 
+#if defined(CONFIG_MINIX_FS_NATIVE_ENDIAN) && \
+        defined(CONFIG_MINIX_FS_BIG_ENDIAN_16BIT_INDEXED)
+
+#error Minix file system byte order broken
+
+#elif defined(CONFIG_MINIX_FS_NATIVE_ENDIAN)
+
+/*
+ * big-endian 32 or 64 bit indexed bitmaps on big-endian system or
+ * little-endian bitmaps on little-endian system
+ */
+
+#define minix_test_and_set_bit(nr, addr)        \
+        __test_and_set_bit((nr), (unsigned long *)(addr))
+#define minix_set_bit(nr, addr)         \
+        __set_bit((nr), (unsigned long *)(addr))
+#define minix_test_and_clear_bit(nr, addr) \
+        __test_and_clear_bit((nr), (unsigned long *)(addr))
+#define minix_test_bit(nr, addr)                \
+        test_bit((nr), (unsigned long *)(addr))
+#define minix_find_first_zero_bit(addr, size) \
+        find_first_zero_bit((unsigned long *)(addr), (size))
+
+#elif defined(CONFIG_MINIX_FS_BIG_ENDIAN_16BIT_INDEXED)
+
+/*
+ * big-endian 16bit indexed bitmaps
+ */
+
+static inline int minix_find_first_zero_bit(const void *vaddr, unsigned size)
+{
+        const unsigned short *p = vaddr, *addr = vaddr;
+        unsigned short num;
+
+        if (!size)
+                return 0;
+
+        size = (size >> 4) + ((size & 15) > 0);
+        while (*p++ == 0xffff) {
+                if (--size == 0)
+                        return (p - addr) << 4;
+        }
+
+        num = *--p;
+        return ((p - addr) << 4) + ffz(num);
+}
+
+#define minix_test_and_set_bit(nr, addr)        \
+        __test_and_set_bit((nr) ^ 16, (unsigned long *)(addr))
+#define minix_set_bit(nr, addr) \
+        __set_bit((nr) ^ 16, (unsigned long *)(addr))
+#define minix_test_and_clear_bit(nr, addr)      \
+        __test_and_clear_bit((nr) ^ 16, (unsigned long *)(addr))
+
+static inline int minix_test_bit(int nr, const void *vaddr)
+{
+        const unsigned short *p = vaddr;
+        return (p[nr >> 4] & (1U << (nr & 15))) != 0;
+}
+
+#else
+
+/*
+ * little-endian bitmaps
+ */
+
+#define minix_test_and_set_bit  __test_and_set_bit_le
+#define minix_set_bit           __set_bit_le
+#define minix_test_and_clear_bit        __test_and_clear_bit_le
+#define minix_test_bit  test_bit_le
+#define minix_find_first_zero_bit       find_first_zero_bit_le
+
+#endif
+
 #endif /* FS_MINIX_H */
diff --git a/fs/namei.c b/fs/namei.c
index b912b7abe747..d0066e17d45d 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -183,6 +183,9 @@ static int acl_permission_check(struct inode *inode, int mask, unsigned int flag
 
         mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
 
+        if (current_user_ns() != inode_userns(inode))
+                goto other_perms;
+
         if (current_fsuid() == inode->i_uid)
                 mode >>= 6;
         else {
@@ -196,6 +199,7 @@ static int acl_permission_check(struct inode *inode, int mask, unsigned int flag
                         mode >>= 3;
         }
 
+other_perms:
         /*
          * If the DACs are ok we don't need any capability check.
          */
@@ -237,7 +241,7 @@ int generic_permission(struct inode *inode, int mask, unsigned int flags,
          * Executable DACs are overridable if at least one exec bit is set.
          */
         if (!(mask & MAY_EXEC) || execute_ok(inode))
-                if (capable(CAP_DAC_OVERRIDE))
+                if (ns_capable(inode_userns(inode), CAP_DAC_OVERRIDE))
                         return 0;
 
         /*
@@ -245,7 +249,7 @@ int generic_permission(struct inode *inode, int mask, unsigned int flags,
          */
         mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
         if (mask == MAY_READ || (S_ISDIR(inode->i_mode) && !(mask & MAY_WRITE)))
-                if (capable(CAP_DAC_READ_SEARCH))
+                if (ns_capable(inode_userns(inode), CAP_DAC_READ_SEARCH))
                         return 0;
 
         return -EACCES;
@@ -654,6 +658,7 @@ static inline int handle_reval_path(struct nameidata *nd)
 static inline int exec_permission(struct inode *inode, unsigned int flags)
 {
         int ret;
+        struct user_namespace *ns = inode_userns(inode);
 
         if (inode->i_op->permission) {
                 ret = inode->i_op->permission(inode, MAY_EXEC, flags);
@@ -666,7 +671,8 @@ static inline int exec_permission(struct inode *inode, unsigned int flags)
         if (ret == -ECHILD)
                 return ret;
 
-        if (capable(CAP_DAC_OVERRIDE) || capable(CAP_DAC_READ_SEARCH))
+        if (ns_capable(ns, CAP_DAC_OVERRIDE) ||
+                        ns_capable(ns, CAP_DAC_READ_SEARCH))
                 goto ok;
 
         return ret;
@@ -933,8 +939,7 @@ static int follow_managed(struct path *path, unsigned flags)
                 if (managed & DCACHE_MANAGE_TRANSIT) {
                         BUG_ON(!path->dentry->d_op);
                         BUG_ON(!path->dentry->d_op->d_manage);
-                        ret = path->dentry->d_op->d_manage(path->dentry,
-                                                           false, false);
+                        ret = path->dentry->d_op->d_manage(path->dentry, false);
                         if (ret < 0)
                                 return ret == -EISDIR ? 0 : ret;
                 }
@@ -999,7 +1004,7 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
                 struct vfsmount *mounted;
                 if (unlikely(path->dentry->d_flags & DCACHE_MANAGE_TRANSIT) &&
                     !reverse_transit &&
-                    path->dentry->d_op->d_manage(path->dentry, false, true) < 0)
+                    path->dentry->d_op->d_manage(path->dentry, true) < 0)
                         return false;
                 mounted = __lookup_mnt(path->mnt, path->dentry, 1);
                 if (!mounted)
@@ -1065,7 +1070,7 @@ failed:
  * Care must be taken as namespace_sem may be held (indicated by mounting_here
  * being true).
  */
-int follow_down(struct path *path, bool mounting_here)
+int follow_down(struct path *path)
 {
         unsigned managed;
         int ret;
@@ -1086,7 +1091,7 @@ int follow_down(struct path *path, bool mounting_here)
                         BUG_ON(!path->dentry->d_op);
                         BUG_ON(!path->dentry->d_op->d_manage);
                         ret = path->dentry->d_op->d_manage(
-                                path->dentry, mounting_here, false);
+                                path->dentry, false);
                         if (ret < 0)
                                 return ret == -EISDIR ? 0 : ret;
                 }
@@ -1645,13 +1650,16 @@ static int path_lookupat(int dfd, const char *name,
                         err = -ECHILD;
         }
 
-        if (!err)
+        if (!err) {
                 err = handle_reval_path(nd);
+                if (err)
+                        path_put(&nd->path);
+        }
 
         if (!err && nd->flags & LOOKUP_DIRECTORY) {
                 if (!nd->inode->i_op->lookup) {
                         path_put(&nd->path);
-                        return -ENOTDIR;
+                        err = -ENOTDIR;
                 }
         }
 
@@ -1843,11 +1851,15 @@ static inline int check_sticky(struct inode *dir, struct inode *inode)
 
         if (!(dir->i_mode & S_ISVTX))
                 return 0;
+        if (current_user_ns() != inode_userns(inode))
+                goto other_userns;
         if (inode->i_uid == fsuid)
                 return 0;
         if (dir->i_uid == fsuid)
                 return 0;
-        return !capable(CAP_FOWNER);
+
+other_userns:
+        return !ns_capable(inode_userns(inode), CAP_FOWNER);
 }
 
 /*
@@ -2027,7 +2039,7 @@ static int may_open(struct path *path, int acc_mode, int flag)
         }
 
         /* O_NOATIME can only be set by the owner or superuser */
-        if (flag & O_NOATIME && !is_owner_or_cap(inode))
+        if (flag & O_NOATIME && !inode_owner_or_capable(inode))
                 return -EPERM;
 
         /*
@@ -2441,7 +2453,8 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
         if (error)
                 return error;
 
-        if ((S_ISCHR(mode) || S_ISBLK(mode)) && !capable(CAP_MKNOD))
+        if ((S_ISCHR(mode) || S_ISBLK(mode)) &&
+            !ns_capable(inode_userns(dir), CAP_MKNOD))
                 return -EPERM;
 
         if (!dir->i_op->mknod)
diff --git a/fs/namespace.c b/fs/namespace.c
index d7513485c1f3..7dba2ed03429 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -196,7 +196,7 @@ unsigned int mnt_get_count(struct vfsmount *mnt)
 #endif
 }
 
-struct vfsmount *alloc_vfsmnt(const char *name)
+static struct vfsmount *alloc_vfsmnt(const char *name)
 {
         struct vfsmount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL);
         if (mnt) {
@@ -466,15 +466,7 @@ static void __mnt_unmake_readonly(struct vfsmount *mnt)
         br_write_unlock(vfsmount_lock);
 }
 
-void simple_set_mnt(struct vfsmount *mnt, struct super_block *sb)
-{
-        mnt->mnt_sb = sb;
-        mnt->mnt_root = dget(sb->s_root);
-}
-
-EXPORT_SYMBOL(simple_set_mnt);
-
-void free_vfsmnt(struct vfsmount *mnt)
+static void free_vfsmnt(struct vfsmount *mnt)
 {
         kfree(mnt->mnt_devname);
         mnt_free_id(mnt);
@@ -678,6 +670,36 @@ static struct vfsmount *skip_mnt_tree(struct vfsmount *p)
         return p;
 }
 
+struct vfsmount *
+vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data)
+{
+        struct vfsmount *mnt;
+        struct dentry *root;
+
+        if (!type)
+                return ERR_PTR(-ENODEV);
+
+        mnt = alloc_vfsmnt(name);
+        if (!mnt)
+                return ERR_PTR(-ENOMEM);
+
+        if (flags & MS_KERNMOUNT)
+                mnt->mnt_flags = MNT_INTERNAL;
+
+        root = mount_fs(type, flags, name, data);
+        if (IS_ERR(root)) {
+                free_vfsmnt(mnt);
+                return ERR_CAST(root);
+        }
+
+        mnt->mnt_root = root;
+        mnt->mnt_sb = root->d_sb;
+        mnt->mnt_mountpoint = mnt->mnt_root;
+        mnt->mnt_parent = mnt;
+        return mnt;
+}
+EXPORT_SYMBOL_GPL(vfs_kern_mount);
+
 static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root,
                                         int flag)
 {
@@ -1641,9 +1663,35 @@ static int attach_recursive_mnt(struct vfsmount *source_mnt,
         return err;
 }
 
+static int lock_mount(struct path *path)
+{
+        struct vfsmount *mnt;
+retry:
+        mutex_lock(&path->dentry->d_inode->i_mutex);
+        if (unlikely(cant_mount(path->dentry))) {
+                mutex_unlock(&path->dentry->d_inode->i_mutex);
+                return -ENOENT;
+        }
+        down_write(&namespace_sem);
+        mnt = lookup_mnt(path);
+        if (likely(!mnt))
+                return 0;
+        up_write(&namespace_sem);
+        mutex_unlock(&path->dentry->d_inode->i_mutex);
+        path_put(path);
+        path->mnt = mnt;
+        path->dentry = dget(mnt->mnt_root);
+        goto retry;
+}
+
+static void unlock_mount(struct path *path)
+{
+        up_write(&namespace_sem);
+        mutex_unlock(&path->dentry->d_inode->i_mutex);
+}
+
 static int graft_tree(struct vfsmount *mnt, struct path *path)
 {
-        int err;
         if (mnt->mnt_sb->s_flags & MS_NOUSER)
                 return -EINVAL;
 
@@ -1651,16 +1699,10 @@ static int graft_tree(struct vfsmount *mnt, struct path *path)
               S_ISDIR(mnt->mnt_root->d_inode->i_mode))
                 return -ENOTDIR;
 
-        err = -ENOENT;
-        mutex_lock(&path->dentry->d_inode->i_mutex);
-        if (cant_mount(path->dentry))
-                goto out_unlock;
+        if (d_unlinked(path->dentry))
+                return -ENOENT;
 
-        if (!d_unlinked(path->dentry))
-                err = attach_recursive_mnt(mnt, path, NULL);
-out_unlock:
-        mutex_unlock(&path->dentry->d_inode->i_mutex);
-        return err;
+        return attach_recursive_mnt(mnt, path, NULL);
 }
 
 /*
@@ -1723,6 +1765,7 @@ static int do_change_type(struct path *path, int flag)
 static int do_loopback(struct path *path, char *old_name,
                                 int recurse)
 {
+        LIST_HEAD(umount_list);
         struct path old_path;
         struct vfsmount *mnt = NULL;
         int err = mount_is_safe(path);
@@ -1734,13 +1777,16 @@ static int do_loopback(struct path *path, char *old_name,
         if (err)
                 return err;
 
-        down_write(&namespace_sem);
+        err = lock_mount(path);
+        if (err)
+                goto out;
+
         err = -EINVAL;
         if (IS_MNT_UNBINDABLE(old_path.mnt))
-                goto out;
+                goto out2;
 
         if (!check_mnt(path->mnt) || !check_mnt(old_path.mnt))
-                goto out;
+                goto out2;
 
         err = -ENOMEM;
         if (recurse)
@@ -1749,20 +1795,18 @@ static int do_loopback(struct path *path, char *old_name,
                 mnt = clone_mnt(old_path.mnt, old_path.dentry, 0);
 
         if (!mnt)
-                goto out;
+                goto out2;
 
         err = graft_tree(mnt, path);
         if (err) {
-                LIST_HEAD(umount_list);
-
                 br_write_lock(vfsmount_lock);
                 umount_tree(mnt, 0, &umount_list);
                 br_write_unlock(vfsmount_lock);
-                release_mounts(&umount_list);
         }
-
+out2:
+        unlock_mount(path);
+        release_mounts(&umount_list);
 out:
-        up_write(&namespace_sem);
         path_put(&old_path);
         return err;
 }
@@ -1851,18 +1895,12 @@ static int do_move_mount(struct path *path, char *old_name)
         if (err)
                 return err;
 
-        down_write(&namespace_sem);
-        err = follow_down(path, true);
+        err = lock_mount(path);
         if (err < 0)
                 goto out;
 
         err = -EINVAL;
         if (!check_mnt(path->mnt) || !check_mnt(old_path.mnt))
-                goto out;
-
-        err = -ENOENT;
-        mutex_lock(&path->dentry->d_inode->i_mutex);
-        if (cant_mount(path->dentry))
                 goto out1;
 
         if (d_unlinked(path->dentry))
@@ -1904,16 +1942,87 @@ static int do_move_mount(struct path *path, char *old_name)
          * automatically */
         list_del_init(&old_path.mnt->mnt_expire);
 out1:
-        mutex_unlock(&path->dentry->d_inode->i_mutex);
+        unlock_mount(path);
 out:
-        up_write(&namespace_sem);
         if (!err)
                 path_put(&parent_path);
         path_put(&old_path);
         return err;
 }
 
-static int do_add_mount(struct vfsmount *, struct path *, int);
+static struct vfsmount *fs_set_subtype(struct vfsmount *mnt, const char *fstype)
+{
+        int err;
+        const char *subtype = strchr(fstype, '.');
+        if (subtype) {
+                subtype++;
+                err = -EINVAL;
+                if (!subtype[0])
+                        goto err;
+        } else
+                subtype = "";
+
+        mnt->mnt_sb->s_subtype = kstrdup(subtype, GFP_KERNEL);
+        err = -ENOMEM;
+        if (!mnt->mnt_sb->s_subtype)
+                goto err;
+        return mnt;
+
+ err:
+        mntput(mnt);
+        return ERR_PTR(err);
+}
+
+struct vfsmount *
+do_kern_mount(const char *fstype, int flags, const char *name, void *data)
+{
+        struct file_system_type *type = get_fs_type(fstype);
+        struct vfsmount *mnt;
+        if (!type)
+                return ERR_PTR(-ENODEV);
+        mnt = vfs_kern_mount(type, flags, name, data);
+        if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) &&
+            !mnt->mnt_sb->s_subtype)
+                mnt = fs_set_subtype(mnt, fstype);
+        put_filesystem(type);
+        return mnt;
+}
+EXPORT_SYMBOL_GPL(do_kern_mount);
+
+/*
+ * add a mount into a namespace's mount tree
+ */
+static int do_add_mount(struct vfsmount *newmnt, struct path *path, int mnt_flags)
+{
+        int err;
+
+        mnt_flags &= ~(MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL);
+
+        err = lock_mount(path);
+        if (err)
+                return err;
+
+        err = -EINVAL;
+        if (!(mnt_flags & MNT_SHRINKABLE) && !check_mnt(path->mnt))
+                goto unlock;
+
+        /* Refuse the same filesystem on the same mount point */
+        err = -EBUSY;
+        if (path->mnt->mnt_sb == newmnt->mnt_sb &&
+            path->mnt->mnt_root == path->dentry)
+                goto unlock;
+
+        err = -EINVAL;
+        if (S_ISLNK(newmnt->mnt_root->d_inode->i_mode))
+                goto unlock;
+
+        newmnt->mnt_flags = mnt_flags;
+        err = graft_tree(newmnt, path);
+
+unlock:
+        unlock_mount(path);
+        return err;
+}
 
 /*
  * create a new mount for userspace and request it to be added into the
@@ -1973,43 +2082,6 @@ fail:
         return err;
 }
 
-/*
- * add a mount into a namespace's mount tree
- */
-static int do_add_mount(struct vfsmount *newmnt, struct path *path, int mnt_flags)
-{
-        int err;
-
-        mnt_flags &= ~(MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL);
-
-        down_write(&namespace_sem);
-        /* Something was mounted here while we slept */
-        err = follow_down(path, true);
-        if (err < 0)
-                goto unlock;
-
-        err = -EINVAL;
-        if (!(mnt_flags & MNT_SHRINKABLE) && !check_mnt(path->mnt))
-                goto unlock;
-
-        /* Refuse the same filesystem on the same mount point */
-        err = -EBUSY;
-        if (path->mnt->mnt_sb == newmnt->mnt_sb &&
-            path->mnt->mnt_root == path->dentry)
-                goto unlock;
-
-        err = -EINVAL;
-        if (S_ISLNK(newmnt->mnt_root->d_inode->i_mode))
-                goto unlock;
-
-        newmnt->mnt_flags = mnt_flags;
-        err = graft_tree(newmnt, path);
-
-unlock:
-        up_write(&namespace_sem);
-        return err;
-}
-
 /**
  * mnt_set_expiry - Put a mount on an expiration list
  * @mnt: The mount to list.
@@ -2510,65 +2582,60 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
         error = user_path_dir(new_root, &new);
         if (error)
                 goto out0;
-        error = -EINVAL;
-        if (!check_mnt(new.mnt))
-                goto out1;
 
         error = user_path_dir(put_old, &old);
         if (error)
                 goto out1;
 
         error = security_sb_pivotroot(&old, &new);
-        if (error) {
-                path_put(&old);
-                goto out1;
-        }
+        if (error)
+                goto out2;
 
         get_fs_root(current->fs, &root);
-        down_write(&namespace_sem);
-        mutex_lock(&old.dentry->d_inode->i_mutex);
+        error = lock_mount(&old);
+        if (error)
+                goto out3;
+
         error = -EINVAL;
         if (IS_MNT_SHARED(old.mnt) ||
                 IS_MNT_SHARED(new.mnt->mnt_parent) ||
                 IS_MNT_SHARED(root.mnt->mnt_parent))
-                goto out2;
-        if (!check_mnt(root.mnt))
-                goto out2;
+                goto out4;
+        if (!check_mnt(root.mnt) || !check_mnt(new.mnt))
+                goto out4;
         error = -ENOENT;
-        if (cant_mount(old.dentry))
-                goto out2;
         if (d_unlinked(new.dentry))
-                goto out2;
+                goto out4;
         if (d_unlinked(old.dentry))
-                goto out2;
+                goto out4;
         error = -EBUSY;
         if (new.mnt == root.mnt ||
             old.mnt == root.mnt)
-                goto out2; /* loop, on the same file system  */
+                goto out4; /* loop, on the same file system  */
         error = -EINVAL;
         if (root.mnt->mnt_root != root.dentry)
-                goto out2; /* not a mountpoint */
+                goto out4; /* not a mountpoint */
         if (root.mnt->mnt_parent == root.mnt)
-                goto out2; /* not attached */
+                goto out4; /* not attached */
         if (new.mnt->mnt_root != new.dentry)
-                goto out2; /* not a mountpoint */
+                goto out4; /* not a mountpoint */
         if (new.mnt->mnt_parent == new.mnt)
-                goto out2; /* not attached */
+                goto out4; /* not attached */
         /* make sure we can reach put_old from new_root */
         tmp = old.mnt;
-        br_write_lock(vfsmount_lock);
         if (tmp != new.mnt) {
                 for (;;) {
                         if (tmp->mnt_parent == tmp)
-                                goto out3; /* already mounted on put_old */
+                                goto out4; /* already mounted on put_old */
                         if (tmp->mnt_parent == new.mnt)
                                 break;
                         tmp = tmp->mnt_parent;
                 }
                 if (!is_subdir(tmp->mnt_mountpoint, new.dentry))
-                        goto out3;
+                        goto out4;
         } else if (!is_subdir(old.dentry, new.dentry))
-                goto out3;
+                goto out4;
+        br_write_lock(vfsmount_lock);
         detach_mnt(new.mnt, &parent_path);
         detach_mnt(root.mnt, &root_parent);
         /* mount old root on put_old */
@@ -2578,22 +2645,21 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
         touch_mnt_namespace(current->nsproxy->mnt_ns);
         br_write_unlock(vfsmount_lock);
         chroot_fs_refs(&root, &new);
-
         error = 0;
-        path_put(&root_parent);
-        path_put(&parent_path);
-out2:
-        mutex_unlock(&old.dentry->d_inode->i_mutex);
-        up_write(&namespace_sem);
+out4:
+        unlock_mount(&old);
+        if (!error) {
+                path_put(&root_parent);
+                path_put(&parent_path);
+        }
+out3:
         path_put(&root);
+out2:
         path_put(&old);
 out1:
         path_put(&new);
 out0:
         return error;
-out3:
-        br_write_unlock(vfsmount_lock);
-        goto out2;
 }
 
 static void __init init_mount_tree(void)
@@ -2635,7 +2701,7 @@ void __init mnt_init(void)
         if (!mount_hashtable)
                 panic("Failed to allocate mount hash table\n");
 
-        printk("Mount-cache hash table entries: %lu\n", HASH_SIZE);
+        printk(KERN_INFO "Mount-cache hash table entries: %lu\n", HASH_SIZE);
 
         for (u = 0; u < HASH_SIZE; u++)
                 INIT_LIST_HEAD(&mount_hashtable[u]);
@@ -2668,3 +2734,9 @@ void put_mnt_ns(struct mnt_namespace *ns)
         kfree(ns);
 }
 EXPORT_SYMBOL(put_mnt_ns);
+
+struct vfsmount *kern_mount_data(struct file_system_type *type, void *data)
+{
+        return vfs_kern_mount(type, MS_KERNMOUNT, type->name, data);
+}
+EXPORT_SYMBOL_GPL(kern_mount_data);
diff --git a/fs/ncpfs/Makefile b/fs/ncpfs/Makefile
index 68ea095100a8..c66af563f2ce 100644
--- a/fs/ncpfs/Makefile
+++ b/fs/ncpfs/Makefile
@@ -11,6 +11,6 @@ ncpfs-$(CONFIG_NCPFS_EXTRAS)   += symlink.o
 ncpfs-$(CONFIG_NCPFS_NFS_NS)   += symlink.o
 
 # If you want debugging output, please uncomment the following line
-# EXTRA_CFLAGS += -DDEBUG_NCP=1
+# ccflags-y := -DDEBUG_NCP=1
 
 CFLAGS_ncplib_kernel.o := -finline-functions
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index c0b8344db0c6..bf1c68009ffd 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -98,7 +98,7 @@ rename_retry:
                 namelen--;
         buflen -= namelen;
         if (buflen < 0) {
-                spin_lock(&dentry->d_lock);
+                spin_unlock(&dentry->d_lock);
                 rcu_read_unlock();
                 goto Elong;
         }
@@ -108,7 +108,7 @@ rename_retry:
         rcu_read_unlock();
         return end;
 Elong_unlock:
-        spin_lock(&dentry->d_lock);
+        spin_unlock(&dentry->d_lock);
         rcu_read_unlock();
         if (read_seqretry(&rename_lock, seq))
                 goto rename_retry;
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 8b31e5f8795d..ad000aeb21a2 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -299,7 +299,6 @@ svc_expkey_update(struct svc_expkey *new, struct svc_expkey *old)
 
 #define EXPORT_HASHBITS         8
 #define EXPORT_HASHMAX          (1<< EXPORT_HASHBITS)
-#define EXPORT_HASHMASK         (EXPORT_HASHMAX -1)
 
 static struct cache_head *export_table[EXPORT_HASHMAX];
 
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index 6d2c397d458b..55780a22fdbd 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -63,7 +63,6 @@ struct ent {
 
 #define ENT_HASHBITS          8
 #define ENT_HASHMAX           (1 << ENT_HASHBITS)
-#define ENT_HASHMASK          (ENT_HASHMAX - 1)
 
 static void
 ent_init(struct cache_head *cnew, struct cache_head *citm)
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index db52546143d1..5fcb1396a7e3 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -984,8 +984,8 @@ typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *,
                               void *);
 enum nfsd4_op_flags {
         ALLOWED_WITHOUT_FH = 1 << 0,    /* No current filehandle required */
-        ALLOWED_ON_ABSENT_FS = 2 << 0,  /* ops processed on absent fs */
-        ALLOWED_AS_FIRST_OP = 3 << 0,   /* ops reqired first in compound */
+        ALLOWED_ON_ABSENT_FS = 1 << 1,  /* ops processed on absent fs */
+        ALLOWED_AS_FIRST_OP = 1 << 2,   /* ops reqired first in compound */
 };
 
 struct nfsd4_operation {
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 7b566ec14e18..fbde6f79922e 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -148,7 +148,7 @@ static struct list_head	ownerstr_hashtbl[OWNER_HASH_SIZE];
 /* hash table for nfs4_file */
 #define FILE_HASH_BITS                   8
 #define FILE_HASH_SIZE                  (1 << FILE_HASH_BITS)
-#define FILE_HASH_MASK                  (FILE_HASH_SIZE - 1)
+
 /* hash table for (open)nfs4_stateid */
 #define STATEID_HASH_BITS              10
 #define STATEID_HASH_SIZE              (1 << STATEID_HASH_BITS)
@@ -316,64 +316,6 @@ static struct list_head	unconf_id_hashtbl[CLIENT_HASH_SIZE];
 static struct list_head client_lru;
 static struct list_head close_lru;
 
-static void unhash_generic_stateid(struct nfs4_stateid *stp)
-{
-        list_del(&stp->st_hash);
-        list_del(&stp->st_perfile);
-        list_del(&stp->st_perstateowner);
-}
-
-static void free_generic_stateid(struct nfs4_stateid *stp)
-{
-        put_nfs4_file(stp->st_file);
-        kmem_cache_free(stateid_slab, stp);
-}
-
-static void release_lock_stateid(struct nfs4_stateid *stp)
-{
-        struct file *file;
-
-        unhash_generic_stateid(stp);
-        file = find_any_file(stp->st_file);
-        if (file)
-                locks_remove_posix(file, (fl_owner_t)stp->st_stateowner);
-        free_generic_stateid(stp);
-}
-
-static void unhash_lockowner(struct nfs4_stateowner *sop)
-{
-        struct nfs4_stateid *stp;
-
-        list_del(&sop->so_idhash);
-        list_del(&sop->so_strhash);
-        list_del(&sop->so_perstateid);
-        while (!list_empty(&sop->so_stateids)) {
-                stp = list_first_entry(&sop->so_stateids,
-                                struct nfs4_stateid, st_perstateowner);
-                release_lock_stateid(stp);
-        }
-}
-
-static void release_lockowner(struct nfs4_stateowner *sop)
-{
-        unhash_lockowner(sop);
-        nfs4_put_stateowner(sop);
-}
-
-static void
-release_stateid_lockowners(struct nfs4_stateid *open_stp)
-{
-        struct nfs4_stateowner *lock_sop;
-
-        while (!list_empty(&open_stp->st_lockowners)) {
-                lock_sop = list_entry(open_stp->st_lockowners.next,
-                                struct nfs4_stateowner, so_perstateid);
-                /* list_del(&open_stp->st_lockowners);  */
-                BUG_ON(lock_sop->so_is_open_owner);
-                release_lockowner(lock_sop);
-        }
-}
-
 /*
  * We store the NONE, READ, WRITE, and BOTH bits separately in the
  * st_{access,deny}_bmap field of the stateid, in order to track not
@@ -446,13 +388,71 @@ static int nfs4_access_bmap_to_omode(struct nfs4_stateid *stp)
         return nfs4_access_to_omode(access);
 }
 
-static void release_open_stateid(struct nfs4_stateid *stp)
+static void unhash_generic_stateid(struct nfs4_stateid *stp)
+{
+        list_del(&stp->st_hash);
+        list_del(&stp->st_perfile);
+        list_del(&stp->st_perstateowner);
+}
+
+static void free_generic_stateid(struct nfs4_stateid *stp)
 {
         int oflag = nfs4_access_bmap_to_omode(stp);
 
+        nfs4_file_put_access(stp->st_file, oflag);
+        put_nfs4_file(stp->st_file);
+        kmem_cache_free(stateid_slab, stp);
+}
+
+static void release_lock_stateid(struct nfs4_stateid *stp)
+{
+        struct file *file;
+
+        unhash_generic_stateid(stp);
+        file = find_any_file(stp->st_file);
+        if (file)
+                locks_remove_posix(file, (fl_owner_t)stp->st_stateowner);
+        free_generic_stateid(stp);
+}
+
+static void unhash_lockowner(struct nfs4_stateowner *sop)
+{
+        struct nfs4_stateid *stp;
+
+        list_del(&sop->so_idhash);
+        list_del(&sop->so_strhash);
+        list_del(&sop->so_perstateid);
+        while (!list_empty(&sop->so_stateids)) {
+                stp = list_first_entry(&sop->so_stateids,
+                                struct nfs4_stateid, st_perstateowner);
+                release_lock_stateid(stp);
+        }
+}
+
+static void release_lockowner(struct nfs4_stateowner *sop)
+{
+        unhash_lockowner(sop);
+        nfs4_put_stateowner(sop);
+}
+
+static void
+release_stateid_lockowners(struct nfs4_stateid *open_stp)
+{
+        struct nfs4_stateowner *lock_sop;
+
+        while (!list_empty(&open_stp->st_lockowners)) {
+                lock_sop = list_entry(open_stp->st_lockowners.next,
+                                struct nfs4_stateowner, so_perstateid);
+                /* list_del(&open_stp->st_lockowners);  */
+                BUG_ON(lock_sop->so_is_open_owner);
+                release_lockowner(lock_sop);
+        }
+}
+
+static void release_open_stateid(struct nfs4_stateid *stp)
+{
         unhash_generic_stateid(stp);
         release_stateid_lockowners(stp);
-        nfs4_file_put_access(stp->st_file, oflag);
         free_generic_stateid(stp);
 }
 
@@ -608,7 +608,8 @@ static void init_forechannel_attrs(struct nfsd4_channel_attrs *new, struct nfsd4
         u32 maxrpc = nfsd_serv->sv_max_mesg;
 
         new->maxreqs = numslots;
-        new->maxresp_cached = slotsize + NFSD_MIN_HDR_SEQ_SZ;
+        new->maxresp_cached = min_t(u32, req->maxresp_cached,
+                                        slotsize + NFSD_MIN_HDR_SEQ_SZ);
         new->maxreq_sz = min_t(u32, req->maxreq_sz, maxrpc);
         new->maxresp_sz = min_t(u32, req->maxresp_sz, maxrpc);
         new->maxops = min_t(u32, req->maxops, NFSD_MAX_OPS_PER_COMPOUND);
@@ -3735,6 +3736,7 @@ alloc_init_lock_stateid(struct nfs4_stateowner *sop, struct nfs4_file *fp, struc
         stp->st_stateid.si_stateownerid = sop->so_id;
         stp->st_stateid.si_fileid = fp->fi_id;
         stp->st_stateid.si_generation = 0;
+        stp->st_access_bmap = 0;
         stp->st_deny_bmap = open_stp->st_deny_bmap;
         stp->st_openstp = open_stp;
 
@@ -3749,6 +3751,17 @@ check_lock_length(u64 offset, u64 length)
              LOFF_OVERFLOW(offset, length)));
 }
 
+static void get_lock_access(struct nfs4_stateid *lock_stp, u32 access)
+{
+        struct nfs4_file *fp = lock_stp->st_file;
+        int oflag = nfs4_access_to_omode(access);
+
+        if (test_bit(access, &lock_stp->st_access_bmap))
+                return;
+        nfs4_file_get_access(fp, oflag);
+        __set_bit(access, &lock_stp->st_access_bmap);
+}
+
 /*
  *  LOCK operation 
  */
@@ -3765,7 +3778,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
         struct file_lock conflock;
         __be32 status = 0;
         unsigned int strhashval;
-        unsigned int cmd;
         int err;
 
         dprintk("NFSD: nfsd4_lock: start=%Ld length=%Ld\n",
@@ -3847,22 +3859,18 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
         switch (lock->lk_type) {
                 case NFS4_READ_LT:
                 case NFS4_READW_LT:
-                        if (find_readable_file(lock_stp->st_file)) {
-                                nfs4_get_vfs_file(rqstp, fp, &cstate->current_fh, NFS4_SHARE_ACCESS_READ);
-                                filp = find_readable_file(lock_stp->st_file);
-                        }
+                        filp = find_readable_file(lock_stp->st_file);
+                        if (filp)
+                                get_lock_access(lock_stp, NFS4_SHARE_ACCESS_READ);
                         file_lock.fl_type = F_RDLCK;
-                        cmd = F_SETLK;
-                break;
+                        break;
                 case NFS4_WRITE_LT:
                 case NFS4_WRITEW_LT:
-                        if (find_writeable_file(lock_stp->st_file)) {
-                                nfs4_get_vfs_file(rqstp, fp, &cstate->current_fh, NFS4_SHARE_ACCESS_WRITE);
-                                filp = find_writeable_file(lock_stp->st_file);
-                        }
+                        filp = find_writeable_file(lock_stp->st_file);
+                        if (filp)
+                                get_lock_access(lock_stp, NFS4_SHARE_ACCESS_WRITE);
                         file_lock.fl_type = F_WRLCK;
-                        cmd = F_SETLK;
-                break;
+                        break;
                 default:
                         status = nfserr_inval;
                 goto out;
@@ -3886,7 +3894,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
         * Note: locks.c uses the BKL to protect the inode's lock list.
         */
 
-        err = vfs_lock_file(filp, cmd, &file_lock, &conflock);
+        err = vfs_lock_file(filp, F_SETLK, &file_lock, &conflock);
         switch (-err) {
         case 0: /* success! */
                 update_stateid(&lock_stp->st_stateid);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 615f0a9f0600..c6766af00d98 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1142,7 +1142,7 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp,
 
         u32 dummy;
         char *machine_name;
-        int i, j;
+        int i;
         int nr_secflavs;
 
         READ_BUF(16);
@@ -1215,8 +1215,6 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp,
                         READ_BUF(4);
                         READ32(dummy);
                         READ_BUF(dummy * 4);
-                        for (j = 0; j < dummy; ++j)
-                                READ32(dummy);
                         break;
                 case RPC_AUTH_GSS:
                         dprintk("RPC_AUTH_GSS callback secflavor "
@@ -1232,7 +1230,6 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp,
                         READ_BUF(4);
                         READ32(dummy);
                         READ_BUF(dummy);
-                        p += XDR_QUADLEN(dummy);
                         break;
                 default:
                         dprintk("Illegal callback secflavor\n");
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 33b3e2b06779..1f5eae40f34e 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -12,13 +12,14 @@
 #include <linux/nfsd/syscall.h>
 #include <linux/lockd/lockd.h>
 #include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/gss_api.h>
 
 #include "idmap.h"
 #include "nfsd.h"
 #include "cache.h"
 
 /*
- *      We have a single directory with 9 nodes in it.
+ *      We have a single directory with several nodes in it.
  */
 enum {
         NFSD_Root = 1,
@@ -42,6 +43,7 @@ enum {
         NFSD_Versions,
         NFSD_Ports,
         NFSD_MaxBlkSize,
+        NFSD_SupportedEnctypes,
         /*
          * The below MUST come last.  Otherwise we leave a hole in nfsd_files[]
          * with !CONFIG_NFSD_V4 and simple_fill_super() goes oops
@@ -187,6 +189,34 @@ static struct file_operations export_features_operations = {
         .release        = single_release,
 };
 
+#ifdef CONFIG_SUNRPC_GSS
+static int supported_enctypes_show(struct seq_file *m, void *v)
+{
+        struct gss_api_mech *k5mech;
+
+        k5mech = gss_mech_get_by_name("krb5");
+        if (k5mech == NULL)
+                goto out;
+        if (k5mech->gm_upcall_enctypes != NULL)
+                seq_printf(m, k5mech->gm_upcall_enctypes);
+        gss_mech_put(k5mech);
+out:
+        return 0;
+}
+
+static int supported_enctypes_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, supported_enctypes_show, NULL);
+}
+
+static struct file_operations supported_enctypes_ops = {
+        .open           = supported_enctypes_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+};
+#endif /* CONFIG_SUNRPC_GSS */
+
 extern int nfsd_pool_stats_open(struct inode *inode, struct file *file);
 extern int nfsd_pool_stats_release(struct inode *inode, struct file *file);
 
@@ -1397,6 +1427,9 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent)
                 [NFSD_Versions] = {"versions", &transaction_ops, S_IWUSR|S_IRUSR},
                 [NFSD_Ports] = {"portlist", &transaction_ops, S_IWUSR|S_IRUGO},
                 [NFSD_MaxBlkSize] = {"max_block_size", &transaction_ops, S_IWUSR|S_IRUGO},
+#ifdef CONFIG_SUNRPC_GSS
+                [NFSD_SupportedEnctypes] = {"supported_krb5_enctypes", &supported_enctypes_ops, S_IRUGO},
+#endif /* CONFIG_SUNRPC_GSS */
 #ifdef CONFIG_NFSD_V4
                 [NFSD_Leasetime] = {"nfsv4leasetime", &transaction_ops, S_IWUSR|S_IRUSR},
                 [NFSD_Gracetime] = {"nfsv4gracetime", &transaction_ops, S_IWUSR|S_IRUSR},
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 2d31224b07bf..6bd2f3c21f2b 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -367,16 +367,12 @@ struct nfs4_file {
         struct list_head        fi_delegations;
         /* One each for O_RDONLY, O_WRONLY, O_RDWR: */
         struct file *           fi_fds[3];
-        /* One each for O_RDONLY, O_WRONLY: */
-        atomic_t                fi_access[2];
         /*
-         * Each open stateid contributes 1 to either fi_readers or
-         * fi_writers, or both, depending on the open mode.  A
-         * delegation also takes an fi_readers reference.  Lock
-         * stateid's take none.
+         * Each open or lock stateid contributes 1 to either
+         * fi_access[O_RDONLY], fi_access[O_WRONLY], or both, depending
+         * on open or lock mode:
          */
-        atomic_t                fi_readers;
-        atomic_t                fi_writers;
+        atomic_t                fi_access[2];
         struct file             *fi_deleg_file;
         struct file_lock        *fi_lease;
         atomic_t                fi_delegees;
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index da1d9701f8e4..2e1cebde90df 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -87,7 +87,7 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
                             .dentry = dget(dentry)};
         int err = 0;
 
-        err = follow_down(&path, false);
+        err = follow_down(&path);
         if (err < 0)
                 goto out;
 
@@ -1749,8 +1749,6 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
                 if (host_err)
                         goto out_drop_write;
         }
-        if (host_err)
-                goto out_drop_write;
         host_err = vfs_rename(fdir, odentry, tdir, ndentry);
         if (!host_err) {
                 host_err = commit_metadata(tfhp);
diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index d7fd696e595c..0a0a66d98cce 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -521,8 +521,8 @@ void nilfs_palloc_commit_free_entry(struct inode *inode,
                                     group_offset, bitmap))
                 printk(KERN_WARNING "%s: entry number %llu already freed\n",
                        __func__, (unsigned long long)req->pr_entry_nr);
-
-        nilfs_palloc_group_desc_add_entries(inode, group, desc, 1);
+        else
+                nilfs_palloc_group_desc_add_entries(inode, group, desc, 1);
 
         kunmap(req->pr_bitmap_bh->b_page);
         kunmap(req->pr_desc_bh->b_page);
@@ -558,8 +558,8 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode,
                                     group_offset, bitmap))
                 printk(KERN_WARNING "%s: entry number %llu already freed\n",
                        __func__, (unsigned long long)req->pr_entry_nr);
-
-        nilfs_palloc_group_desc_add_entries(inode, group, desc, 1);
+        else
+                nilfs_palloc_group_desc_add_entries(inode, group, desc, 1);
 
         kunmap(req->pr_bitmap_bh->b_page);
         kunmap(req->pr_desc_bh->b_page);
@@ -665,7 +665,7 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
                 for (j = i, n = 0;
                      (j < nitems) && nilfs_palloc_group_is_in(inode, group,
                                                               entry_nrs[j]);
-                     j++, n++) {
+                     j++) {
                         nilfs_palloc_group(inode, entry_nrs[j], &group_offset);
                         if (!nilfs_clear_bit_atomic(
                                     nilfs_mdt_bgl_lock(inode, group),
@@ -674,6 +674,8 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
                                        "%s: entry number %llu already freed\n",
                                        __func__,
                                        (unsigned long long)entry_nrs[j]);
+                        } else {
+                                n++;
                         }
                 }
                 nilfs_palloc_group_desc_add_entries(inode, group, desc, n);
diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h
index 9af34a7e6e13..f5fde36b9e28 100644
--- a/fs/nilfs2/alloc.h
+++ b/fs/nilfs2/alloc.h
@@ -74,7 +74,7 @@ int nilfs_palloc_freev(struct inode *, __u64 *, size_t);
 
 #define nilfs_set_bit_atomic            ext2_set_bit_atomic
 #define nilfs_clear_bit_atomic          ext2_clear_bit_atomic
-#define nilfs_find_next_zero_bit        ext2_find_next_zero_bit
+#define nilfs_find_next_zero_bit        find_next_zero_bit_le
 
 /*
  * persistent object allocator cache
diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c
index 3ee67c67cc52..4723f04e9b12 100644
--- a/fs/nilfs2/bmap.c
+++ b/fs/nilfs2/bmap.c
@@ -25,7 +25,6 @@
 #include <linux/errno.h>
 #include "nilfs.h"
 #include "bmap.h"
-#include "sb.h"
 #include "btree.h"
 #include "direct.h"
 #include "btnode.h"
@@ -425,17 +424,6 @@ int nilfs_bmap_test_and_clear_dirty(struct nilfs_bmap *bmap)
 /*
  * Internal use only
  */
-
-void nilfs_bmap_add_blocks(const struct nilfs_bmap *bmap, int n)
-{
-        inode_add_bytes(bmap->b_inode, (1 << bmap->b_inode->i_blkbits) * n);
-}
-
-void nilfs_bmap_sub_blocks(const struct nilfs_bmap *bmap, int n)
-{
-        inode_sub_bytes(bmap->b_inode, (1 << bmap->b_inode->i_blkbits) * n);
-}
-
 __u64 nilfs_bmap_data_get_key(const struct nilfs_bmap *bmap,
                               const struct buffer_head *bh)
 {
diff --git a/fs/nilfs2/bmap.h b/fs/nilfs2/bmap.h
index bde1c0aa2e15..40d9f453d31c 100644
--- a/fs/nilfs2/bmap.h
+++ b/fs/nilfs2/bmap.h
@@ -240,9 +240,6 @@ __u64 nilfs_bmap_data_get_key(const struct nilfs_bmap *,
 __u64 nilfs_bmap_find_target_seq(const struct nilfs_bmap *, __u64);
 __u64 nilfs_bmap_find_target_in_group(const struct nilfs_bmap *);
 
-void nilfs_bmap_add_blocks(const struct nilfs_bmap *, int);
-void nilfs_bmap_sub_blocks(const struct nilfs_bmap *, int);
-
 
 /* Assume that bmap semaphore is locked. */
 static inline int nilfs_bmap_dirty(const struct nilfs_bmap *bmap)
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index 300c2bc00c3f..d451ae0e0bf3 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -1174,7 +1174,7 @@ static int nilfs_btree_insert(struct nilfs_bmap *btree, __u64 key, __u64 ptr)
         if (ret < 0)
                 goto out;
         nilfs_btree_commit_insert(btree, path, level, key, ptr);
-        nilfs_bmap_add_blocks(btree, stats.bs_nblocks);
+        nilfs_inode_add_blocks(btree->b_inode, stats.bs_nblocks);
 
  out:
         nilfs_btree_free_path(path);
@@ -1511,7 +1511,7 @@ static int nilfs_btree_delete(struct nilfs_bmap *btree, __u64 key)
         if (ret < 0)
                 goto out;
         nilfs_btree_commit_delete(btree, path, level, dat);
-        nilfs_bmap_sub_blocks(btree, stats.bs_nblocks);
+        nilfs_inode_sub_blocks(btree->b_inode, stats.bs_nblocks);
 
 out:
         nilfs_btree_free_path(path);
@@ -1776,7 +1776,7 @@ int nilfs_btree_convert_and_insert(struct nilfs_bmap *btree,
                 return ret;
         nilfs_btree_commit_convert_and_insert(btree, key, ptr, keys, ptrs, n,
                                               di, ni, bh);
-        nilfs_bmap_add_blocks(btree, stats.bs_nblocks);
+        nilfs_inode_add_blocks(btree->b_inode, stats.bs_nblocks);
         return 0;
 }
 
diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index 9d45773b79e6..3a1923943b14 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -440,7 +440,6 @@ void nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de,
         nilfs_commit_chunk(page, mapping, from, to);
         nilfs_put_page(page);
         dir->i_mtime = dir->i_ctime = CURRENT_TIME;
-/*      NILFS_I(dir)->i_flags &= ~NILFS_BTREE_FL; */
 }
 
 /*
@@ -531,7 +530,6 @@ got_it:
         nilfs_set_de_type(de, inode);
         nilfs_commit_chunk(page, page->mapping, from, to);
         dir->i_mtime = dir->i_ctime = CURRENT_TIME;
-/*      NILFS_I(dir)->i_flags &= ~NILFS_BTREE_FL; */
         nilfs_mark_inode_dirty(dir);
         /* OFFSET_CACHE */
 out_put:
@@ -579,7 +577,6 @@ int nilfs_delete_entry(struct nilfs_dir_entry *dir, struct page *page)
         dir->inode = 0;
         nilfs_commit_chunk(page, mapping, from, to);
         inode->i_ctime = inode->i_mtime = CURRENT_TIME;
-/*      NILFS_I(inode)->i_flags &= ~NILFS_BTREE_FL; */
 out:
         nilfs_put_page(page);
         return err;
@@ -684,7 +681,7 @@ const struct file_operations nilfs_dir_operations = {
         .readdir        = nilfs_readdir,
         .unlocked_ioctl = nilfs_ioctl,
 #ifdef CONFIG_COMPAT
-        .compat_ioctl   = nilfs_ioctl,
+        .compat_ioctl   = nilfs_compat_ioctl,
 #endif  /* CONFIG_COMPAT */
         .fsync          = nilfs_sync_file,
 
diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c
index 324d80c57518..82f4865e86dd 100644
--- a/fs/nilfs2/direct.c
+++ b/fs/nilfs2/direct.c
@@ -146,7 +146,7 @@ static int nilfs_direct_insert(struct nilfs_bmap *bmap, __u64 key, __u64 ptr)
                 if (NILFS_BMAP_USE_VBN(bmap))
                         nilfs_bmap_set_target_v(bmap, key, req.bpr_ptr);
 
-                nilfs_bmap_add_blocks(bmap, 1);
+                nilfs_inode_add_blocks(bmap->b_inode, 1);
         }
         return ret;
 }
@@ -168,7 +168,7 @@ static int nilfs_direct_delete(struct nilfs_bmap *bmap, __u64 key)
         if (!ret) {
                 nilfs_bmap_commit_end_ptr(bmap, &req, dat);
                 nilfs_direct_set_ptr(bmap, key, NILFS_BMAP_INVALID_PTR);
-                nilfs_bmap_sub_blocks(bmap, 1);
+                nilfs_inode_sub_blocks(bmap->b_inode, 1);
         }
         return ret;
 }
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index 2f560c9fb808..93589fccdd97 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -59,7 +59,7 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
         struct nilfs_transaction_info ti;
         int ret;
 
-        if (unlikely(nilfs_near_disk_full(NILFS_SB(inode->i_sb)->s_nilfs)))
+        if (unlikely(nilfs_near_disk_full(inode->i_sb->s_fs_info)))
                 return VM_FAULT_SIGBUS; /* -ENOSPC */
 
         lock_page(page);
@@ -142,7 +142,7 @@ const struct file_operations nilfs_file_operations = {
         .aio_write      = generic_file_aio_write,
         .unlocked_ioctl = nilfs_ioctl,
 #ifdef CONFIG_COMPAT
-        .compat_ioctl   = nilfs_ioctl,
+        .compat_ioctl   = nilfs_compat_ioctl,
 #endif  /* CONFIG_COMPAT */
         .mmap           = nilfs_file_mmap,
         .open           = generic_file_open,
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 2fd440d8d6b8..d5625be236a8 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -41,6 +41,24 @@ struct nilfs_iget_args {
         int for_gc;
 };
 
+void nilfs_inode_add_blocks(struct inode *inode, int n)
+{
+        struct nilfs_root *root = NILFS_I(inode)->i_root;
+
+        inode_add_bytes(inode, (1 << inode->i_blkbits) * n);
+        if (root)
+                atomic_add(n, &root->blocks_count);
+}
+
+void nilfs_inode_sub_blocks(struct inode *inode, int n)
+{
+        struct nilfs_root *root = NILFS_I(inode)->i_root;
+
+        inode_sub_bytes(inode, (1 << inode->i_blkbits) * n);
+        if (root)
+                atomic_sub(n, &root->blocks_count);
+}
+
 /**
  * nilfs_get_block() - get a file block on the filesystem (callback function)
  * @inode - inode struct of the target file
@@ -277,7 +295,7 @@ const struct address_space_operations nilfs_aops = {
 struct inode *nilfs_new_inode(struct inode *dir, int mode)
 {
         struct super_block *sb = dir->i_sb;
-        struct nilfs_sb_info *sbi = NILFS_SB(sb);
+        struct the_nilfs *nilfs = sb->s_fs_info;
         struct inode *inode;
         struct nilfs_inode_info *ii;
         struct nilfs_root *root;
@@ -315,19 +333,16 @@ struct inode *nilfs_new_inode(struct inode *dir, int mode)
                 /* No lock is needed; iget() ensures it. */
         }
 
-        ii->i_flags = NILFS_I(dir)->i_flags;
-        if (S_ISLNK(mode))
-                ii->i_flags &= ~(NILFS_IMMUTABLE_FL | NILFS_APPEND_FL);
-        if (!S_ISDIR(mode))
-                ii->i_flags &= ~NILFS_DIRSYNC_FL;
+        ii->i_flags = nilfs_mask_flags(
+                mode, NILFS_I(dir)->i_flags & NILFS_FL_INHERITED);
 
         /* ii->i_file_acl = 0; */
         /* ii->i_dir_acl = 0; */
         ii->i_dir_start_lookup = 0;
         nilfs_set_inode_flags(inode);
-        spin_lock(&sbi->s_next_gen_lock);
-        inode->i_generation = sbi->s_next_generation++;
-        spin_unlock(&sbi->s_next_gen_lock);
+        spin_lock(&nilfs->ns_next_gen_lock);
+        inode->i_generation = nilfs->ns_next_generation++;
+        spin_unlock(&nilfs->ns_next_gen_lock);
         insert_inode_hash(inode);
 
         err = nilfs_init_acl(inode, dir);
@@ -359,17 +374,15 @@ void nilfs_set_inode_flags(struct inode *inode)
 
         inode->i_flags &= ~(S_SYNC | S_APPEND | S_IMMUTABLE | S_NOATIME |
                             S_DIRSYNC);
-        if (flags & NILFS_SYNC_FL)
+        if (flags & FS_SYNC_FL)
                 inode->i_flags |= S_SYNC;
-        if (flags & NILFS_APPEND_FL)
+        if (flags & FS_APPEND_FL)
                 inode->i_flags |= S_APPEND;
-        if (flags & NILFS_IMMUTABLE_FL)
+        if (flags & FS_IMMUTABLE_FL)
                 inode->i_flags |= S_IMMUTABLE;
-#ifndef NILFS_ATIME_DISABLE
-        if (flags & NILFS_NOATIME_FL)
-#endif
+        if (flags & FS_NOATIME_FL)
                 inode->i_flags |= S_NOATIME;
-        if (flags & NILFS_DIRSYNC_FL)
+        if (flags & FS_DIRSYNC_FL)
                 inode->i_flags |= S_DIRSYNC;
         mapping_set_gfp_mask(inode->i_mapping,
                              mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);
@@ -420,7 +433,7 @@ static int __nilfs_read_inode(struct super_block *sb,
                               struct nilfs_root *root, unsigned long ino,
                               struct inode *inode)
 {
-        struct the_nilfs *nilfs = NILFS_SB(sb)->s_nilfs;
+        struct the_nilfs *nilfs = sb->s_fs_info;
         struct buffer_head *bh;
         struct nilfs_inode *raw_inode;
         int err;
@@ -707,6 +720,7 @@ void nilfs_evict_inode(struct inode *inode)
         struct nilfs_transaction_info ti;
         struct super_block *sb = inode->i_sb;
         struct nilfs_inode_info *ii = NILFS_I(inode);
+        int ret;
 
         if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) {
                 if (inode->i_data.nrpages)
@@ -725,8 +739,9 @@ void nilfs_evict_inode(struct inode *inode)
         nilfs_mark_inode_dirty(inode);
         end_writeback(inode);
 
-        nilfs_ifile_delete_inode(ii->i_root->ifile, inode->i_ino);
-        atomic_dec(&ii->i_root->inodes_count);
+        ret = nilfs_ifile_delete_inode(ii->i_root->ifile, inode->i_ino);
+        if (!ret)
+                atomic_dec(&ii->i_root->inodes_count);
 
         nilfs_clear_inode(inode);
 
@@ -792,18 +807,18 @@ int nilfs_permission(struct inode *inode, int mask, unsigned int flags)
 
 int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh)
 {
-        struct nilfs_sb_info *sbi = NILFS_SB(inode->i_sb);
+        struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
         struct nilfs_inode_info *ii = NILFS_I(inode);
         int err;
 
-        spin_lock(&sbi->s_inode_lock);
+        spin_lock(&nilfs->ns_inode_lock);
         if (ii->i_bh == NULL) {
-                spin_unlock(&sbi->s_inode_lock);
+                spin_unlock(&nilfs->ns_inode_lock);
                 err = nilfs_ifile_get_inode_block(ii->i_root->ifile,
                                                   inode->i_ino, pbh);
                 if (unlikely(err))
                         return err;
-                spin_lock(&sbi->s_inode_lock);
+                spin_lock(&nilfs->ns_inode_lock);
                 if (ii->i_bh == NULL)
                         ii->i_bh = *pbh;
                 else {
@@ -814,36 +829,36 @@ int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh)
                 *pbh = ii->i_bh;
 
         get_bh(*pbh);
-        spin_unlock(&sbi->s_inode_lock);
+        spin_unlock(&nilfs->ns_inode_lock);
         return 0;
 }
 
 int nilfs_inode_dirty(struct inode *inode)
 {
         struct nilfs_inode_info *ii = NILFS_I(inode);
-        struct nilfs_sb_info *sbi = NILFS_SB(inode->i_sb);
+        struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
         int ret = 0;
 
         if (!list_empty(&ii->i_dirty)) {
-                spin_lock(&sbi->s_inode_lock);
+                spin_lock(&nilfs->ns_inode_lock);
                 ret = test_bit(NILFS_I_DIRTY, &ii->i_state) ||
                         test_bit(NILFS_I_BUSY, &ii->i_state);
-                spin_unlock(&sbi->s_inode_lock);
+                spin_unlock(&nilfs->ns_inode_lock);
         }
         return ret;
 }
 
 int nilfs_set_file_dirty(struct inode *inode, unsigned nr_dirty)
 {
-        struct nilfs_sb_info *sbi = NILFS_SB(inode->i_sb);
         struct nilfs_inode_info *ii = NILFS_I(inode);
+        struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
 
-        atomic_add(nr_dirty, &sbi->s_nilfs->ns_ndirtyblks);
+        atomic_add(nr_dirty, &nilfs->ns_ndirtyblks);
 
         if (test_and_set_bit(NILFS_I_DIRTY, &ii->i_state))
                 return 0;
 
-        spin_lock(&sbi->s_inode_lock);
+        spin_lock(&nilfs->ns_inode_lock);
         if (!test_bit(NILFS_I_QUEUED, &ii->i_state) &&
             !test_bit(NILFS_I_BUSY, &ii->i_state)) {
                 /* Because this routine may race with nilfs_dispose_list(),
@@ -851,18 +866,18 @@ int nilfs_set_file_dirty(struct inode *inode, unsigned nr_dirty)
                 if (list_empty(&ii->i_dirty) && igrab(inode) == NULL) {
                         /* This will happen when somebody is freeing
                            this inode. */
-                        nilfs_warning(sbi->s_super, __func__,
+                        nilfs_warning(inode->i_sb, __func__,
                                       "cannot get inode (ino=%lu)\n",
                                       inode->i_ino);
-                        spin_unlock(&sbi->s_inode_lock);
+                        spin_unlock(&nilfs->ns_inode_lock);
                         return -EINVAL; /* NILFS_I_DIRTY may remain for
                                            freeing inode */
                 }
                 list_del(&ii->i_dirty);
-                list_add_tail(&ii->i_dirty, &sbi->s_dirty_files);
+                list_add_tail(&ii->i_dirty, &nilfs->ns_dirty_files);
                 set_bit(NILFS_I_QUEUED, &ii->i_state);
         }
-        spin_unlock(&sbi->s_inode_lock);
+        spin_unlock(&nilfs->ns_inode_lock);
         return 0;
 }
 
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 496738963fdb..f2469ba6246b 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -26,7 +26,9 @@
 #include <linux/capability.h>   /* capable() */
 #include <linux/uaccess.h>      /* copy_from_user(), copy_to_user() */
 #include <linux/vmalloc.h>
+#include <linux/compat.h>       /* compat_ptr() */
 #include <linux/mount.h>        /* mnt_want_write(), mnt_drop_write() */
+#include <linux/buffer_head.h>
 #include <linux/nilfs2_fs.h>
 #include "nilfs.h"
 #include "segment.h"
@@ -97,11 +99,74 @@ static int nilfs_ioctl_wrap_copy(struct the_nilfs *nilfs,
         return ret;
 }
 
+static int nilfs_ioctl_getflags(struct inode *inode, void __user *argp)
+{
+        unsigned int flags = NILFS_I(inode)->i_flags & FS_FL_USER_VISIBLE;
+
+        return put_user(flags, (int __user *)argp);
+}
+
+static int nilfs_ioctl_setflags(struct inode *inode, struct file *filp,
+                                void __user *argp)
+{
+        struct nilfs_transaction_info ti;
+        unsigned int flags, oldflags;
+        int ret;
+
+        if (!inode_owner_or_capable(inode))
+                return -EACCES;
+
+        if (get_user(flags, (int __user *)argp))
+                return -EFAULT;
+
+        ret = mnt_want_write(filp->f_path.mnt);
+        if (ret)
+                return ret;
+
+        flags = nilfs_mask_flags(inode->i_mode, flags);
+
+        mutex_lock(&inode->i_mutex);
+
+        oldflags = NILFS_I(inode)->i_flags;
+
+        /*
+         * The IMMUTABLE and APPEND_ONLY flags can only be changed by the
+         * relevant capability.
+         */
+        ret = -EPERM;
+        if (((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) &&
+            !capable(CAP_LINUX_IMMUTABLE))
+                goto out;
+
+        ret = nilfs_transaction_begin(inode->i_sb, &ti, 0);
+        if (ret)
+                goto out;
+
+        NILFS_I(inode)->i_flags = (oldflags & ~FS_FL_USER_MODIFIABLE) |
+                (flags & FS_FL_USER_MODIFIABLE);
+
+        nilfs_set_inode_flags(inode);
+        inode->i_ctime = CURRENT_TIME;
+        if (IS_SYNC(inode))
+                nilfs_set_transaction_flag(NILFS_TI_SYNC);
+
+        nilfs_mark_inode_dirty(inode);
+        ret = nilfs_transaction_commit(inode->i_sb);
+out:
+        mutex_unlock(&inode->i_mutex);
+        mnt_drop_write(filp->f_path.mnt);
+        return ret;
+}
+
+static int nilfs_ioctl_getversion(struct inode *inode, void __user *argp)
+{
+        return put_user(inode->i_generation, (int __user *)argp);
+}
+
 static int nilfs_ioctl_change_cpmode(struct inode *inode, struct file *filp,
                                      unsigned int cmd, void __user *argp)
 {
-        struct the_nilfs *nilfs = NILFS_SB(inode->i_sb)->s_nilfs;
-        struct inode *cpfile = nilfs->ns_cpfile;
+        struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
         struct nilfs_transaction_info ti;
         struct nilfs_cpmode cpmode;
         int ret;
@@ -121,7 +186,7 @@ static int nilfs_ioctl_change_cpmode(struct inode *inode, struct file *filp,
 
         nilfs_transaction_begin(inode->i_sb, &ti, 0);
         ret = nilfs_cpfile_change_cpmode(
-                cpfile, cpmode.cm_cno, cpmode.cm_mode);
+                nilfs->ns_cpfile, cpmode.cm_cno, cpmode.cm_mode);
         if (unlikely(ret < 0))
                 nilfs_transaction_abort(inode->i_sb);
         else
@@ -137,7 +202,7 @@ static int
 nilfs_ioctl_delete_checkpoint(struct inode *inode, struct file *filp,
                               unsigned int cmd, void __user *argp)
 {
-        struct inode *cpfile = NILFS_SB(inode->i_sb)->s_nilfs->ns_cpfile;
+        struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
         struct nilfs_transaction_info ti;
         __u64 cno;
         int ret;
@@ -154,7 +219,7 @@ nilfs_ioctl_delete_checkpoint(struct inode *inode, struct file *filp,
                 goto out;
 
         nilfs_transaction_begin(inode->i_sb, &ti, 0);
-        ret = nilfs_cpfile_delete_checkpoint(cpfile, cno);
+        ret = nilfs_cpfile_delete_checkpoint(nilfs->ns_cpfile, cno);
         if (unlikely(ret < 0))
                 nilfs_transaction_abort(inode->i_sb);
         else
@@ -180,7 +245,7 @@ nilfs_ioctl_do_get_cpinfo(struct the_nilfs *nilfs, __u64 *posp, int flags,
 static int nilfs_ioctl_get_cpstat(struct inode *inode, struct file *filp,
                                   unsigned int cmd, void __user *argp)
 {
-        struct the_nilfs *nilfs = NILFS_SB(inode->i_sb)->s_nilfs;
+        struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
         struct nilfs_cpstat cpstat;
         int ret;
 
@@ -211,7 +276,7 @@ nilfs_ioctl_do_get_suinfo(struct the_nilfs *nilfs, __u64 *posp, int flags,
 static int nilfs_ioctl_get_sustat(struct inode *inode, struct file *filp,
                                   unsigned int cmd, void __user *argp)
 {
-        struct the_nilfs *nilfs = NILFS_SB(inode->i_sb)->s_nilfs;
+        struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
         struct nilfs_sustat sustat;
         int ret;
 
@@ -267,7 +332,7 @@ nilfs_ioctl_do_get_bdescs(struct the_nilfs *nilfs, __u64 *posp, int flags,
 static int nilfs_ioctl_get_bdescs(struct inode *inode, struct file *filp,
                                   unsigned int cmd, void __user *argp)
 {
-        struct the_nilfs *nilfs = NILFS_SB(inode->i_sb)->s_nilfs;
+        struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
         struct nilfs_argv argv;
         int ret;
 
@@ -336,7 +401,7 @@ static int nilfs_ioctl_move_blocks(struct super_block *sb,
                                    struct nilfs_argv *argv, void *buf)
 {
         size_t nmembs = argv->v_nmembs;
-        struct the_nilfs *nilfs = NILFS_SB(sb)->s_nilfs;
+        struct the_nilfs *nilfs = sb->s_fs_info;
         struct inode *inode;
         struct nilfs_vdesc *vdesc;
         struct buffer_head *bh, *n;
@@ -550,7 +615,7 @@ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp,
                 ret = PTR_ERR(kbufs[4]);
                 goto out;
         }
-        nilfs = NILFS_SB(inode->i_sb)->s_nilfs;
+        nilfs = inode->i_sb->s_fs_info;
 
         for (n = 0; n < 4; n++) {
                 ret = -EINVAL;
@@ -623,7 +688,7 @@ static int nilfs_ioctl_sync(struct inode *inode, struct file *filp,
                 return ret;
 
         if (argp != NULL) {
-                nilfs = NILFS_SB(inode->i_sb)->s_nilfs;
+                nilfs = inode->i_sb->s_fs_info;
                 down_read(&nilfs->ns_segctor_sem);
                 cno = nilfs->ns_cno - 1;
                 up_read(&nilfs->ns_segctor_sem);
@@ -641,7 +706,7 @@ static int nilfs_ioctl_get_info(struct inode *inode, struct file *filp,
                                                   void *, size_t, size_t))
 
 {
-        struct the_nilfs *nilfs = NILFS_SB(inode->i_sb)->s_nilfs;
+        struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
         struct nilfs_argv argv;
         int ret;
 
@@ -666,6 +731,12 @@ long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
         void __user *argp = (void __user *)arg;
 
         switch (cmd) {
+        case FS_IOC_GETFLAGS:
+                return nilfs_ioctl_getflags(inode, argp);
+        case FS_IOC_SETFLAGS:
+                return nilfs_ioctl_setflags(inode, filp, argp);
+        case FS_IOC_GETVERSION:
+                return nilfs_ioctl_getversion(inode, argp);
         case NILFS_IOCTL_CHANGE_CPMODE:
                 return nilfs_ioctl_change_cpmode(inode, filp, cmd, argp);
         case NILFS_IOCTL_DELETE_CHECKPOINT:
@@ -696,3 +767,23 @@ long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
                 return -ENOTTY;
         }
 }
+
+#ifdef CONFIG_COMPAT
+long nilfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+        switch (cmd) {
+        case FS_IOC32_GETFLAGS:
+                cmd = FS_IOC_GETFLAGS;
+                break;
+        case FS_IOC32_SETFLAGS:
+                cmd = FS_IOC_SETFLAGS;
+                break;
+        case FS_IOC32_GETVERSION:
+                cmd = FS_IOC_GETVERSION;
+                break;
+        default:
+                return -ENOIOCTLCMD;
+        }
+        return nilfs_ioctl(filp, cmd, (unsigned long)compat_ptr(arg));
+}
+#endif
diff --git a/fs/nilfs2/mdt.h b/fs/nilfs2/mdt.h
index b13734bf3521..ed68563ec708 100644
--- a/fs/nilfs2/mdt.h
+++ b/fs/nilfs2/mdt.h
@@ -66,7 +66,7 @@ static inline struct nilfs_mdt_info *NILFS_MDT(const struct inode *inode)
 
 static inline struct the_nilfs *NILFS_I_NILFS(struct inode *inode)
 {
-        return NILFS_SB(inode->i_sb)->s_nilfs;
+        return inode->i_sb->s_fs_info;
 }
 
 /* Default GFP flags using highmem */
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 161791d26458..546849b3e88f 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -482,7 +482,7 @@ static struct dentry *nilfs_get_dentry(struct super_block *sb, u64 cno,
         if (ino < NILFS_FIRST_INO(sb) && ino != NILFS_ROOT_INO)
                 return ERR_PTR(-ESTALE);
 
-        root = nilfs_lookup_root(NILFS_SB(sb)->s_nilfs, cno);
+        root = nilfs_lookup_root(sb->s_fs_info, cno);
         if (!root)
                 return ERR_PTR(-ESTALE);
 
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index 777e8fd04304..856e8e4e0b74 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -30,7 +30,6 @@
 #include <linux/blkdev.h>
 #include <linux/nilfs2_fs.h>
 #include "the_nilfs.h"
-#include "sb.h"
 #include "bmap.h"
 
 /*
@@ -122,7 +121,7 @@ enum {
 #define NILFS_SYS_INO_BITS   \
   ((unsigned int)(1 << NILFS_ROOT_INO) | NILFS_MDT_INO_BITS)
 
-#define NILFS_FIRST_INO(sb)  (NILFS_SB(sb)->s_nilfs->ns_first_ino)
+#define NILFS_FIRST_INO(sb) (((struct the_nilfs *)sb->s_fs_info)->ns_first_ino)
 
 #define NILFS_MDT_INODE(sb, ino) \
   ((ino) < NILFS_FIRST_INO(sb) && (NILFS_MDT_INO_BITS & (1 << (ino))))
@@ -212,6 +211,23 @@ static inline int nilfs_init_acl(struct inode *inode, struct inode *dir)
 
 #define NILFS_ATIME_DISABLE
 
+/* Flags that should be inherited by new inodes from their parent. */
+#define NILFS_FL_INHERITED                                              \
+        (FS_SECRM_FL | FS_UNRM_FL | FS_COMPR_FL | FS_SYNC_FL |          \
+         FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL |\
+         FS_COMPRBLK_FL | FS_NOCOMP_FL | FS_NOTAIL_FL | FS_DIRSYNC_FL)
+
+/* Mask out flags that are inappropriate for the given type of inode. */
+static inline __u32 nilfs_mask_flags(umode_t mode, __u32 flags)
+{
+        if (S_ISDIR(mode))
+                return flags;
+        else if (S_ISREG(mode))
+                return flags & ~(FS_DIRSYNC_FL | FS_TOPDIR_FL);
+        else
+                return flags & (FS_NODUMP_FL | FS_NOATIME_FL);
+}
+
 /* dir.c */
 extern int nilfs_add_link(struct dentry *, struct inode *);
 extern ino_t nilfs_inode_by_name(struct inode *, const struct qstr *);
@@ -229,10 +245,13 @@ extern int nilfs_sync_file(struct file *, int);
 
 /* ioctl.c */
 long nilfs_ioctl(struct file *, unsigned int, unsigned long);
+long nilfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 int nilfs_ioctl_prepare_clean_segments(struct the_nilfs *, struct nilfs_argv *,
                                        void **);
 
 /* inode.c */
+void nilfs_inode_add_blocks(struct inode *inode, int n);
+void nilfs_inode_sub_blocks(struct inode *inode, int n);
 extern struct inode *nilfs_new_inode(struct inode *, int);
 extern void nilfs_free_inode(struct inode *);
 extern int nilfs_get_block(struct inode *, sector_t, struct buffer_head *, int);
@@ -275,11 +294,11 @@ extern int nilfs_check_feature_compatibility(struct super_block *,
                                              struct nilfs_super_block *);
 extern void nilfs_set_log_cursor(struct nilfs_super_block *,
                                  struct the_nilfs *);
-extern struct nilfs_super_block **nilfs_prepare_super(struct nilfs_sb_info *,
-                                                      int flip);
-extern int nilfs_commit_super(struct nilfs_sb_info *, int);
-extern int nilfs_cleanup_super(struct nilfs_sb_info *);
-int nilfs_attach_checkpoint(struct nilfs_sb_info *sbi, __u64 cno, int curr_mnt,
+struct nilfs_super_block **nilfs_prepare_super(struct super_block *sb,
+                                               int flip);
+int nilfs_commit_super(struct super_block *sb, int flag);
+int nilfs_cleanup_super(struct super_block *sb);
+int nilfs_attach_checkpoint(struct super_block *sb, __u64 cno, int curr_mnt,
                             struct nilfs_root **root);
 int nilfs_checkpoint_is_mounted(struct super_block *sb, __u64 cno);
 
diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index 3dfcd3b7d389..ba4a64518f38 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -425,7 +425,7 @@ void nilfs_dispose_segment_list(struct list_head *head)
 }
 
 static int nilfs_prepare_segment_for_recovery(struct the_nilfs *nilfs,
-                                              struct nilfs_sb_info *sbi,
+                                              struct super_block *sb,
                                               struct nilfs_recovery_info *ri)
 {
         struct list_head *head = &ri->ri_used_segments;
@@ -501,7 +501,7 @@ static int nilfs_recovery_copy_block(struct the_nilfs *nilfs,
 }
 
 static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
-                                      struct nilfs_sb_info *sbi,
+                                      struct super_block *sb,
                                       struct nilfs_root *root,
                                       struct list_head *head,
                                       unsigned long *nr_salvaged_blocks)
@@ -514,7 +514,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
         int err = 0, err2 = 0;
 
         list_for_each_entry_safe(rb, n, head, list) {
-                inode = nilfs_iget(sbi->s_super, root, rb->ino);
+                inode = nilfs_iget(sb, root, rb->ino);
                 if (IS_ERR(inode)) {
                         err = PTR_ERR(inode);
                         inode = NULL;
@@ -572,11 +572,11 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
  * nilfs_do_roll_forward - salvage logical segments newer than the latest
  * checkpoint
  * @nilfs: nilfs object
- * @sbi: nilfs_sb_info
+ * @sb: super block instance
  * @ri: pointer to a nilfs_recovery_info
  */
 static int nilfs_do_roll_forward(struct the_nilfs *nilfs,
-                                 struct nilfs_sb_info *sbi,
+                                 struct super_block *sb,
                                  struct nilfs_root *root,
                                  struct nilfs_recovery_info *ri)
 {
@@ -648,7 +648,7 @@ static int nilfs_do_roll_forward(struct the_nilfs *nilfs,
                                 goto failed;
                         if (flags & NILFS_SS_LOGEND) {
                                 err = nilfs_recover_dsync_blocks(
-                                        nilfs, sbi, root, &dsync_blocks,
+                                        nilfs, sb, root, &dsync_blocks,
                                         &nsalvaged_blocks);
                                 if (unlikely(err))
                                         goto failed;
@@ -681,7 +681,7 @@ static int nilfs_do_roll_forward(struct the_nilfs *nilfs,
 
         if (nsalvaged_blocks) {
                 printk(KERN_INFO "NILFS (device %s): salvaged %lu blocks\n",
-                       sbi->s_super->s_id, nsalvaged_blocks);
+                       sb->s_id, nsalvaged_blocks);
                 ri->ri_need_recovery = NILFS_RECOVERY_ROLLFORWARD_DONE;
         }
  out:
@@ -695,7 +695,7 @@ static int nilfs_do_roll_forward(struct the_nilfs *nilfs,
         printk(KERN_ERR
                "NILFS (device %s): Error roll-forwarding "
                "(err=%d, pseg block=%llu). ",
-               sbi->s_super->s_id, err, (unsigned long long)pseg_start);
+               sb->s_id, err, (unsigned long long)pseg_start);
         goto out;
 }
 
@@ -724,7 +724,7 @@ static void nilfs_finish_roll_forward(struct the_nilfs *nilfs,
 /**
  * nilfs_salvage_orphan_logs - salvage logs written after the latest checkpoint
  * @nilfs: nilfs object
- * @sbi: nilfs_sb_info
+ * @sb: super block instance
  * @ri: pointer to a nilfs_recovery_info struct to store search results.
  *
  * Return Value: On success, 0 is returned.  On error, one of the following
@@ -741,7 +741,7 @@ static void nilfs_finish_roll_forward(struct the_nilfs *nilfs,
  * %-ENOMEM - Insufficient memory available.
  */
 int nilfs_salvage_orphan_logs(struct the_nilfs *nilfs,
-                              struct nilfs_sb_info *sbi,
+                              struct super_block *sb,
                               struct nilfs_recovery_info *ri)
 {
         struct nilfs_root *root;
@@ -750,32 +750,32 @@ int nilfs_salvage_orphan_logs(struct the_nilfs *nilfs,
         if (ri->ri_lsegs_start == 0 || ri->ri_lsegs_end == 0)
                 return 0;
 
-        err = nilfs_attach_checkpoint(sbi, ri->ri_cno, true, &root);
+        err = nilfs_attach_checkpoint(sb, ri->ri_cno, true, &root);
         if (unlikely(err)) {
                 printk(KERN_ERR
                        "NILFS: error loading the latest checkpoint.\n");
                 return err;
         }
 
-        err = nilfs_do_roll_forward(nilfs, sbi, root, ri);
+        err = nilfs_do_roll_forward(nilfs, sb, root, ri);
         if (unlikely(err))
                 goto failed;
 
         if (ri->ri_need_recovery == NILFS_RECOVERY_ROLLFORWARD_DONE) {
-                err = nilfs_prepare_segment_for_recovery(nilfs, sbi, ri);
+                err = nilfs_prepare_segment_for_recovery(nilfs, sb, ri);
                 if (unlikely(err)) {
                         printk(KERN_ERR "NILFS: Error preparing segments for "
                                "recovery.\n");
                         goto failed;
                 }
 
-                err = nilfs_attach_segment_constructor(sbi, root);
+                err = nilfs_attach_log_writer(sb, root);
                 if (unlikely(err))
                         goto failed;
 
                 set_nilfs_discontinued(nilfs);
-                err = nilfs_construct_segment(sbi->s_super);
-                nilfs_detach_segment_constructor(sbi);
+                err = nilfs_construct_segment(sb);
+                nilfs_detach_log_writer(sb);
 
                 if (unlikely(err)) {
                         printk(KERN_ERR "NILFS: Oops! recovery failed. "
diff --git a/fs/nilfs2/sb.h b/fs/nilfs2/sb.h
deleted file mode 100644
index 7a17715f215f..000000000000
--- a/fs/nilfs2/sb.h
+++ /dev/null
@@ -1,85 +0,0 @@
-/*
- * sb.h - NILFS on-memory super block structure.
- *
- * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
- *
- * 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., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- *
- * Written by Ryusuke Konishi <ryusuke@osrg.net>
- *
- */
-
-#ifndef _NILFS_SB
-#define _NILFS_SB
-
-#include <linux/types.h>
-#include <linux/fs.h>
-
-struct the_nilfs;
-struct nilfs_sc_info;
-
-/*
- * NILFS super-block data in memory
- */
-struct nilfs_sb_info {
-        /* Mount options */
-        unsigned long s_mount_opt;
-        uid_t s_resuid;
-        gid_t s_resgid;
-
-        unsigned long s_interval;       /* construction interval */
-        unsigned long s_watermark;      /* threshold of data amount
-                                           for the segment construction */
-
-        /* Fundamental members */
-        struct super_block *s_super;    /* reverse pointer to super_block */
-        struct the_nilfs *s_nilfs;
-
-        /* Segment constructor */
-        struct list_head s_dirty_files; /* dirty files list */
-        struct nilfs_sc_info *s_sc_info; /* segment constructor info */
-        spinlock_t s_inode_lock;        /* Lock for the nilfs inode.
-                                           It covers s_dirty_files list */
-
-        /* Inode allocator */
-        spinlock_t s_next_gen_lock;
-        u32 s_next_generation;
-};
-
-static inline struct nilfs_sb_info *NILFS_SB(struct super_block *sb)
-{
-        return sb->s_fs_info;
-}
-
-static inline struct nilfs_sc_info *NILFS_SC(struct nilfs_sb_info *sbi)
-{
-        return sbi->s_sc_info;
-}
-
-/*
- * Bit operations for the mount option
- */
-#define nilfs_clear_opt(sbi, opt)  \
-        do { (sbi)->s_mount_opt &= ~NILFS_MOUNT_##opt; } while (0)
-#define nilfs_set_opt(sbi, opt)  \
-        do { (sbi)->s_mount_opt |= NILFS_MOUNT_##opt; } while (0)
-#define nilfs_test_opt(sbi, opt)   ((sbi)->s_mount_opt & NILFS_MOUNT_##opt)
-#define nilfs_write_opt(sbi, mask, opt)                                 \
-        do { (sbi)->s_mount_opt =                                       \
-                (((sbi)->s_mount_opt & ~NILFS_MOUNT_##mask) |           \
-                 NILFS_MOUNT_##opt);                                    \
-        } while (0)
-
-#endif /* _NILFS_SB */
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 2de9f636792a..afe4f2183454 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -104,8 +104,7 @@ struct nilfs_sc_operations {
 static void nilfs_segctor_start_timer(struct nilfs_sc_info *);
 static void nilfs_segctor_do_flush(struct nilfs_sc_info *, int);
 static void nilfs_segctor_do_immediate_flush(struct nilfs_sc_info *);
-static void nilfs_dispose_list(struct nilfs_sb_info *, struct list_head *,
-                               int);
+static void nilfs_dispose_list(struct the_nilfs *, struct list_head *, int);
 
 #define nilfs_cnt32_gt(a, b)   \
         (typecheck(__u32, a) && typecheck(__u32, b) && \
@@ -182,7 +181,6 @@ int nilfs_transaction_begin(struct super_block *sb,
                             struct nilfs_transaction_info *ti,
                             int vacancy_check)
 {
-        struct nilfs_sb_info *sbi;
         struct the_nilfs *nilfs;
         int ret = nilfs_prepare_segment_lock(ti);
 
@@ -193,8 +191,7 @@ int nilfs_transaction_begin(struct super_block *sb,
 
         vfs_check_frozen(sb, SB_FREEZE_WRITE);
 
-        sbi = NILFS_SB(sb);
-        nilfs = sbi->s_nilfs;
+        nilfs = sb->s_fs_info;
         down_read(&nilfs->ns_segctor_sem);
         if (vacancy_check && nilfs_near_disk_full(nilfs)) {
                 up_read(&nilfs->ns_segctor_sem);
@@ -225,8 +222,7 @@ int nilfs_transaction_begin(struct super_block *sb,
 int nilfs_transaction_commit(struct super_block *sb)
 {
         struct nilfs_transaction_info *ti = current->journal_info;
-        struct nilfs_sb_info *sbi;
-        struct nilfs_sc_info *sci;
+        struct the_nilfs *nilfs = sb->s_fs_info;
         int err = 0;
 
         BUG_ON(ti == NULL || ti->ti_magic != NILFS_TI_MAGIC);
@@ -235,16 +231,15 @@ int nilfs_transaction_commit(struct super_block *sb)
                 ti->ti_count--;
                 return 0;
         }
-        sbi = NILFS_SB(sb);
-        sci = NILFS_SC(sbi);
-        if (sci != NULL) {
+        if (nilfs->ns_writer) {
+                struct nilfs_sc_info *sci = nilfs->ns_writer;
+
                 if (ti->ti_flags & NILFS_TI_COMMIT)
                         nilfs_segctor_start_timer(sci);
-                if (atomic_read(&sbi->s_nilfs->ns_ndirtyblks) >
-                    sci->sc_watermark)
+                if (atomic_read(&nilfs->ns_ndirtyblks) > sci->sc_watermark)
                         nilfs_segctor_do_flush(sci, 0);
         }
-        up_read(&sbi->s_nilfs->ns_segctor_sem);
+        up_read(&nilfs->ns_segctor_sem);
         current->journal_info = ti->ti_save;
 
         if (ti->ti_flags & NILFS_TI_SYNC)
@@ -257,13 +252,14 @@ int nilfs_transaction_commit(struct super_block *sb)
 void nilfs_transaction_abort(struct super_block *sb)
 {
         struct nilfs_transaction_info *ti = current->journal_info;
+        struct the_nilfs *nilfs = sb->s_fs_info;
 
         BUG_ON(ti == NULL || ti->ti_magic != NILFS_TI_MAGIC);
         if (ti->ti_count > 0) {
                 ti->ti_count--;
                 return;
         }
-        up_read(&NILFS_SB(sb)->s_nilfs->ns_segctor_sem);
+        up_read(&nilfs->ns_segctor_sem);
 
         current->journal_info = ti->ti_save;
         if (ti->ti_flags & NILFS_TI_DYNAMIC_ALLOC)
@@ -272,9 +268,8 @@ void nilfs_transaction_abort(struct super_block *sb)
 
 void nilfs_relax_pressure_in_lock(struct super_block *sb)
 {
-        struct nilfs_sb_info *sbi = NILFS_SB(sb);
-        struct nilfs_sc_info *sci = NILFS_SC(sbi);
-        struct the_nilfs *nilfs = sbi->s_nilfs;
+        struct the_nilfs *nilfs = sb->s_fs_info;
+        struct nilfs_sc_info *sci = nilfs->ns_writer;
 
         if (!sci || !sci->sc_flush_request)
                 return;
@@ -294,11 +289,13 @@ void nilfs_relax_pressure_in_lock(struct super_block *sb)
         downgrade_write(&nilfs->ns_segctor_sem);
 }
 
-static void nilfs_transaction_lock(struct nilfs_sb_info *sbi,
+static void nilfs_transaction_lock(struct super_block *sb,
                                    struct nilfs_transaction_info *ti,
                                    int gcflag)
 {
         struct nilfs_transaction_info *cur_ti = current->journal_info;
+        struct the_nilfs *nilfs = sb->s_fs_info;
+        struct nilfs_sc_info *sci = nilfs->ns_writer;
 
         WARN_ON(cur_ti);
         ti->ti_flags = NILFS_TI_WRITER;
@@ -309,30 +306,31 @@ static void nilfs_transaction_lock(struct nilfs_sb_info *sbi,
         current->journal_info = ti;
 
         for (;;) {
-                down_write(&sbi->s_nilfs->ns_segctor_sem);
-                if (!test_bit(NILFS_SC_PRIOR_FLUSH, &NILFS_SC(sbi)->sc_flags))
+                down_write(&nilfs->ns_segctor_sem);
+                if (!test_bit(NILFS_SC_PRIOR_FLUSH, &sci->sc_flags))
                         break;
 
-                nilfs_segctor_do_immediate_flush(NILFS_SC(sbi));
+                nilfs_segctor_do_immediate_flush(sci);
 
-                up_write(&sbi->s_nilfs->ns_segctor_sem);
+                up_write(&nilfs->ns_segctor_sem);
                 yield();
         }
         if (gcflag)
                 ti->ti_flags |= NILFS_TI_GC;
 }
 
-static void nilfs_transaction_unlock(struct nilfs_sb_info *sbi)
+static void nilfs_transaction_unlock(struct super_block *sb)
 {
         struct nilfs_transaction_info *ti = current->journal_info;
+        struct the_nilfs *nilfs = sb->s_fs_info;
 
         BUG_ON(ti == NULL || ti->ti_magic != NILFS_TI_MAGIC);
         BUG_ON(ti->ti_count > 0);
 
-        up_write(&sbi->s_nilfs->ns_segctor_sem);
+        up_write(&nilfs->ns_segctor_sem);
         current->journal_info = ti->ti_save;
         if (!list_empty(&ti->ti_garbage))
-                nilfs_dispose_list(sbi, &ti->ti_garbage, 0);
+                nilfs_dispose_list(nilfs, &ti->ti_garbage, 0);
 }
 
 static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci,
@@ -714,7 +712,7 @@ static void nilfs_lookup_dirty_node_buffers(struct inode *inode,
         }
 }
 
-static void nilfs_dispose_list(struct nilfs_sb_info *sbi,
+static void nilfs_dispose_list(struct the_nilfs *nilfs,
                                struct list_head *head, int force)
 {
         struct nilfs_inode_info *ii, *n;
@@ -722,7 +720,7 @@ static void nilfs_dispose_list(struct nilfs_sb_info *sbi,
         unsigned nv = 0;
 
         while (!list_empty(head)) {
-                spin_lock(&sbi->s_inode_lock);
+                spin_lock(&nilfs->ns_inode_lock);
                 list_for_each_entry_safe(ii, n, head, i_dirty) {
                         list_del_init(&ii->i_dirty);
                         if (force) {
@@ -733,14 +731,14 @@ static void nilfs_dispose_list(struct nilfs_sb_info *sbi,
                         } else if (test_bit(NILFS_I_DIRTY, &ii->i_state)) {
                                 set_bit(NILFS_I_QUEUED, &ii->i_state);
                                 list_add_tail(&ii->i_dirty,
-                                              &sbi->s_dirty_files);
+                                              &nilfs->ns_dirty_files);
                                 continue;
                         }
                         ivec[nv++] = ii;
                         if (nv == SC_N_INODEVEC)
                                 break;
                 }
-                spin_unlock(&sbi->s_inode_lock);
+                spin_unlock(&nilfs->ns_inode_lock);
 
                 for (pii = ivec; nv > 0; pii++, nv--)
                         iput(&(*pii)->vfs_inode);
@@ -773,24 +771,23 @@ static int nilfs_segctor_clean(struct nilfs_sc_info *sci)
 
 static int nilfs_segctor_confirm(struct nilfs_sc_info *sci)
 {
-        struct nilfs_sb_info *sbi = sci->sc_sbi;
+        struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
         int ret = 0;
 
-        if (nilfs_test_metadata_dirty(sbi->s_nilfs, sci->sc_root))
+        if (nilfs_test_metadata_dirty(nilfs, sci->sc_root))
                 set_bit(NILFS_SC_DIRTY, &sci->sc_flags);
 
-        spin_lock(&sbi->s_inode_lock);
-        if (list_empty(&sbi->s_dirty_files) && nilfs_segctor_clean(sci))
+        spin_lock(&nilfs->ns_inode_lock);
+        if (list_empty(&nilfs->ns_dirty_files) && nilfs_segctor_clean(sci))
                 ret++;
 
-        spin_unlock(&sbi->s_inode_lock);
+        spin_unlock(&nilfs->ns_inode_lock);
         return ret;
 }
 
 static void nilfs_segctor_clear_metadata_dirty(struct nilfs_sc_info *sci)
 {
-        struct nilfs_sb_info *sbi = sci->sc_sbi;
-        struct the_nilfs *nilfs = sbi->s_nilfs;
+        struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
 
         nilfs_mdt_clear_dirty(sci->sc_root->ifile);
         nilfs_mdt_clear_dirty(nilfs->ns_cpfile);
@@ -800,7 +797,7 @@ static void nilfs_segctor_clear_metadata_dirty(struct nilfs_sc_info *sci)
 
 static int nilfs_segctor_create_checkpoint(struct nilfs_sc_info *sci)
 {
-        struct the_nilfs *nilfs = sci->sc_sbi->s_nilfs;
+        struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
         struct buffer_head *bh_cp;
         struct nilfs_checkpoint *raw_cp;
         int err;
@@ -824,8 +821,7 @@ static int nilfs_segctor_create_checkpoint(struct nilfs_sc_info *sci)
 
 static int nilfs_segctor_fill_in_checkpoint(struct nilfs_sc_info *sci)
 {
-        struct nilfs_sb_info *sbi = sci->sc_sbi;
-        struct the_nilfs *nilfs = sbi->s_nilfs;
+        struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
         struct buffer_head *bh_cp;
         struct nilfs_checkpoint *raw_cp;
         int err;
@@ -1049,8 +1045,7 @@ static int nilfs_segctor_scan_file_dsync(struct nilfs_sc_info *sci,
 
 static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
 {
-        struct nilfs_sb_info *sbi = sci->sc_sbi;
-        struct the_nilfs *nilfs = sbi->s_nilfs;
+        struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
         struct list_head *head;
         struct nilfs_inode_info *ii;
         size_t ndone;
@@ -1859,7 +1854,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
 {
         struct nilfs_segment_buffer *segbuf;
         struct page *bd_page = NULL, *fs_page = NULL;
-        struct the_nilfs *nilfs = sci->sc_sbi->s_nilfs;
+        struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
         int update_sr = false;
 
         list_for_each_entry(segbuf, &sci->sc_write_logs, sb_list) {
@@ -1963,30 +1958,30 @@ static int nilfs_segctor_wait(struct nilfs_sc_info *sci)
         return ret;
 }
 
-static int nilfs_segctor_check_in_files(struct nilfs_sc_info *sci,
-                                        struct nilfs_sb_info *sbi)
+static int nilfs_segctor_collect_dirty_files(struct nilfs_sc_info *sci,
+                                             struct the_nilfs *nilfs)
 {
         struct nilfs_inode_info *ii, *n;
         struct inode *ifile = sci->sc_root->ifile;
 
-        spin_lock(&sbi->s_inode_lock);
+        spin_lock(&nilfs->ns_inode_lock);
  retry:
-        list_for_each_entry_safe(ii, n, &sbi->s_dirty_files, i_dirty) {
+        list_for_each_entry_safe(ii, n, &nilfs->ns_dirty_files, i_dirty) {
                 if (!ii->i_bh) {
                         struct buffer_head *ibh;
                         int err;
 
-                        spin_unlock(&sbi->s_inode_lock);
+                        spin_unlock(&nilfs->ns_inode_lock);
                         err = nilfs_ifile_get_inode_block(
                                 ifile, ii->vfs_inode.i_ino, &ibh);
                         if (unlikely(err)) {
-                                nilfs_warning(sbi->s_super, __func__,
+                                nilfs_warning(sci->sc_super, __func__,
                                               "failed to get inode block.\n");
                                 return err;
                         }
                         nilfs_mdt_mark_buffer_dirty(ibh);
                         nilfs_mdt_mark_dirty(ifile);
-                        spin_lock(&sbi->s_inode_lock);
+                        spin_lock(&nilfs->ns_inode_lock);
                         if (likely(!ii->i_bh))
                                 ii->i_bh = ibh;
                         else
@@ -1999,18 +1994,18 @@ static int nilfs_segctor_check_in_files(struct nilfs_sc_info *sci,
                 list_del(&ii->i_dirty);
                 list_add_tail(&ii->i_dirty, &sci->sc_dirty_files);
         }
-        spin_unlock(&sbi->s_inode_lock);
+        spin_unlock(&nilfs->ns_inode_lock);
 
         return 0;
 }
 
-static void nilfs_segctor_check_out_files(struct nilfs_sc_info *sci,
-                                          struct nilfs_sb_info *sbi)
+static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci,
+                                             struct the_nilfs *nilfs)
 {
         struct nilfs_transaction_info *ti = current->journal_info;
         struct nilfs_inode_info *ii, *n;
 
-        spin_lock(&sbi->s_inode_lock);
+        spin_lock(&nilfs->ns_inode_lock);
         list_for_each_entry_safe(ii, n, &sci->sc_dirty_files, i_dirty) {
                 if (!test_and_clear_bit(NILFS_I_UPDATED, &ii->i_state) ||
                     test_bit(NILFS_I_DIRTY, &ii->i_state))
@@ -2022,7 +2017,7 @@ static void nilfs_segctor_check_out_files(struct nilfs_sc_info *sci,
                 list_del(&ii->i_dirty);
                 list_add_tail(&ii->i_dirty, &ti->ti_garbage);
         }
-        spin_unlock(&sbi->s_inode_lock);
+        spin_unlock(&nilfs->ns_inode_lock);
 }
 
 /*
@@ -2030,15 +2025,14 @@ static void nilfs_segctor_check_out_files(struct nilfs_sc_info *sci,
  */
 static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode)
 {
-        struct nilfs_sb_info *sbi = sci->sc_sbi;
-        struct the_nilfs *nilfs = sbi->s_nilfs;
+        struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
         struct page *failed_page;
         int err;
 
         sci->sc_stage.scnt = NILFS_ST_INIT;
         sci->sc_cno = nilfs->ns_cno;
 
-        err = nilfs_segctor_check_in_files(sci, sbi);
+        err = nilfs_segctor_collect_dirty_files(sci, nilfs);
         if (unlikely(err))
                 goto out;
 
@@ -2116,7 +2110,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode)
         } while (sci->sc_stage.scnt != NILFS_ST_DONE);
 
  out:
-        nilfs_segctor_check_out_files(sci, sbi);
+        nilfs_segctor_drop_written_files(sci, nilfs);
         return err;
 
  failed_to_write:
@@ -2169,8 +2163,8 @@ static void nilfs_segctor_do_flush(struct nilfs_sc_info *sci, int bn)
  */
 void nilfs_flush_segment(struct super_block *sb, ino_t ino)
 {
-        struct nilfs_sb_info *sbi = NILFS_SB(sb);
-        struct nilfs_sc_info *sci = NILFS_SC(sbi);
+        struct the_nilfs *nilfs = sb->s_fs_info;
+        struct nilfs_sc_info *sci = nilfs->ns_writer;
 
         if (!sci || nilfs_doing_construction())
                 return;
@@ -2259,8 +2253,8 @@ static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err)
  */
 int nilfs_construct_segment(struct super_block *sb)
 {
-        struct nilfs_sb_info *sbi = NILFS_SB(sb);
-        struct nilfs_sc_info *sci = NILFS_SC(sbi);
+        struct the_nilfs *nilfs = sb->s_fs_info;
+        struct nilfs_sc_info *sci = nilfs->ns_writer;
         struct nilfs_transaction_info *ti;
         int err;
 
@@ -2297,8 +2291,8 @@ int nilfs_construct_segment(struct super_block *sb)
 int nilfs_construct_dsync_segment(struct super_block *sb, struct inode *inode,
                                   loff_t start, loff_t end)
 {
-        struct nilfs_sb_info *sbi = NILFS_SB(sb);
-        struct nilfs_sc_info *sci = NILFS_SC(sbi);
+        struct the_nilfs *nilfs = sb->s_fs_info;
+        struct nilfs_sc_info *sci = nilfs->ns_writer;
         struct nilfs_inode_info *ii;
         struct nilfs_transaction_info ti;
         int err = 0;
@@ -2306,33 +2300,33 @@ int nilfs_construct_dsync_segment(struct super_block *sb, struct inode *inode,
         if (!sci)
                 return -EROFS;
 
-        nilfs_transaction_lock(sbi, &ti, 0);
+        nilfs_transaction_lock(sb, &ti, 0);
 
         ii = NILFS_I(inode);
         if (test_bit(NILFS_I_INODE_DIRTY, &ii->i_state) ||
-            nilfs_test_opt(sbi, STRICT_ORDER) ||
+            nilfs_test_opt(nilfs, STRICT_ORDER) ||
             test_bit(NILFS_SC_UNCLOSED, &sci->sc_flags) ||
-            nilfs_discontinued(sbi->s_nilfs)) {
-                nilfs_transaction_unlock(sbi);
+            nilfs_discontinued(nilfs)) {
+                nilfs_transaction_unlock(sb);
                 err = nilfs_segctor_sync(sci);
                 return err;
         }
 
-        spin_lock(&sbi->s_inode_lock);
+        spin_lock(&nilfs->ns_inode_lock);
         if (!test_bit(NILFS_I_QUEUED, &ii->i_state) &&
             !test_bit(NILFS_I_BUSY, &ii->i_state)) {
-                spin_unlock(&sbi->s_inode_lock);
-                nilfs_transaction_unlock(sbi);
+                spin_unlock(&nilfs->ns_inode_lock);
+                nilfs_transaction_unlock(sb);
                 return 0;
         }
-        spin_unlock(&sbi->s_inode_lock);
+        spin_unlock(&nilfs->ns_inode_lock);
         sci->sc_dsync_inode = ii;
         sci->sc_dsync_start = start;
         sci->sc_dsync_end = end;
 
         err = nilfs_segctor_do_construct(sci, SC_LSEG_DSYNC);
 
-        nilfs_transaction_unlock(sbi);
+        nilfs_transaction_unlock(sb);
         return err;
 }
 
@@ -2388,8 +2382,7 @@ static void nilfs_segctor_notify(struct nilfs_sc_info *sci, int mode, int err)
  */
 static int nilfs_segctor_construct(struct nilfs_sc_info *sci, int mode)
 {
-        struct nilfs_sb_info *sbi = sci->sc_sbi;
-        struct the_nilfs *nilfs = sbi->s_nilfs;
+        struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
         struct nilfs_super_block **sbp;
         int err = 0;
 
@@ -2407,11 +2400,12 @@ static int nilfs_segctor_construct(struct nilfs_sc_info *sci, int mode)
                     nilfs_discontinued(nilfs)) {
                         down_write(&nilfs->ns_sem);
                         err = -EIO;
-                        sbp = nilfs_prepare_super(sbi,
+                        sbp = nilfs_prepare_super(sci->sc_super,
                                                   nilfs_sb_will_flip(nilfs));
                         if (likely(sbp)) {
                                 nilfs_set_log_cursor(sbp[0], nilfs);
-                                err = nilfs_commit_super(sbi, NILFS_SB_COMMIT);
+                                err = nilfs_commit_super(sci->sc_super,
+                                                         NILFS_SB_COMMIT);
                         }
                         up_write(&nilfs->ns_sem);
                 }
@@ -2443,16 +2437,15 @@ nilfs_remove_written_gcinodes(struct the_nilfs *nilfs, struct list_head *head)
 int nilfs_clean_segments(struct super_block *sb, struct nilfs_argv *argv,
                          void **kbufs)
 {
-        struct nilfs_sb_info *sbi = NILFS_SB(sb);
-        struct nilfs_sc_info *sci = NILFS_SC(sbi);
-        struct the_nilfs *nilfs = sbi->s_nilfs;
+        struct the_nilfs *nilfs = sb->s_fs_info;
+        struct nilfs_sc_info *sci = nilfs->ns_writer;
         struct nilfs_transaction_info ti;
         int err;
 
         if (unlikely(!sci))
                 return -EROFS;
 
-        nilfs_transaction_lock(sbi, &ti, 1);
+        nilfs_transaction_lock(sb, &ti, 1);
 
         err = nilfs_mdt_save_to_shadow_map(nilfs->ns_dat);
         if (unlikely(err))
@@ -2480,14 +2473,14 @@ int nilfs_clean_segments(struct super_block *sb, struct nilfs_argv *argv,
                 set_current_state(TASK_INTERRUPTIBLE);
                 schedule_timeout(sci->sc_interval);
         }
-        if (nilfs_test_opt(sbi, DISCARD)) {
+        if (nilfs_test_opt(nilfs, DISCARD)) {
                 int ret = nilfs_discard_segments(nilfs, sci->sc_freesegs,
                                                  sci->sc_nfreesegs);
                 if (ret) {
                         printk(KERN_WARNING
                                "NILFS warning: error %d on discard request, "
                                "turning discards off for the device\n", ret);
-                        nilfs_clear_opt(sbi, DISCARD);
+                        nilfs_clear_opt(nilfs, DISCARD);
                 }
         }
 
@@ -2495,16 +2488,15 @@ int nilfs_clean_segments(struct super_block *sb, struct nilfs_argv *argv,
         sci->sc_freesegs = NULL;
         sci->sc_nfreesegs = 0;
         nilfs_mdt_clear_shadow_map(nilfs->ns_dat);
-        nilfs_transaction_unlock(sbi);
+        nilfs_transaction_unlock(sb);
         return err;
 }
 
 static void nilfs_segctor_thread_construct(struct nilfs_sc_info *sci, int mode)
 {
-        struct nilfs_sb_info *sbi = sci->sc_sbi;
         struct nilfs_transaction_info ti;
 
-        nilfs_transaction_lock(sbi, &ti, 0);
+        nilfs_transaction_lock(sci->sc_super, &ti, 0);
         nilfs_segctor_construct(sci, mode);
 
         /*
@@ -2515,7 +2507,7 @@ static void nilfs_segctor_thread_construct(struct nilfs_sc_info *sci, int mode)
         if (test_bit(NILFS_SC_UNCLOSED, &sci->sc_flags))
                 nilfs_segctor_start_timer(sci);
 
-        nilfs_transaction_unlock(sbi);
+        nilfs_transaction_unlock(sci->sc_super);
 }
 
 static void nilfs_segctor_do_immediate_flush(struct nilfs_sc_info *sci)
@@ -2561,7 +2553,7 @@ static int nilfs_segctor_flush_mode(struct nilfs_sc_info *sci)
 static int nilfs_segctor_thread(void *arg)
 {
         struct nilfs_sc_info *sci = (struct nilfs_sc_info *)arg;
-        struct the_nilfs *nilfs = sci->sc_sbi->s_nilfs;
+        struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
         int timeout = 0;
 
         sci->sc_timer.data = (unsigned long)current;
@@ -2672,17 +2664,17 @@ static void nilfs_segctor_kill_thread(struct nilfs_sc_info *sci)
 /*
  * Setup & clean-up functions
  */
-static struct nilfs_sc_info *nilfs_segctor_new(struct nilfs_sb_info *sbi,
+static struct nilfs_sc_info *nilfs_segctor_new(struct super_block *sb,
                                                struct nilfs_root *root)
 {
+        struct the_nilfs *nilfs = sb->s_fs_info;
         struct nilfs_sc_info *sci;
 
         sci = kzalloc(sizeof(*sci), GFP_KERNEL);
         if (!sci)
                 return NULL;
 
-        sci->sc_sbi = sbi;
-        sci->sc_super = sbi->s_super;
+        sci->sc_super = sb;
 
         nilfs_get_root(root);
         sci->sc_root = root;
@@ -2702,10 +2694,10 @@ static struct nilfs_sc_info *nilfs_segctor_new(struct nilfs_sb_info *sbi,
         sci->sc_mjcp_freq = HZ * NILFS_SC_DEFAULT_SR_FREQ;
         sci->sc_watermark = NILFS_SC_DEFAULT_WATERMARK;
 
-        if (sbi->s_interval)
-                sci->sc_interval = sbi->s_interval;
-        if (sbi->s_watermark)
-                sci->sc_watermark = sbi->s_watermark;
+        if (nilfs->ns_interval)
+                sci->sc_interval = nilfs->ns_interval;
+        if (nilfs->ns_watermark)
+                sci->sc_watermark = nilfs->ns_watermark;
         return sci;
 }
 
@@ -2716,12 +2708,11 @@ static void nilfs_segctor_write_out(struct nilfs_sc_info *sci)
         /* The segctord thread was stopped and its timer was removed.
            But some tasks remain. */
         do {
-                struct nilfs_sb_info *sbi = sci->sc_sbi;
                 struct nilfs_transaction_info ti;
 
-                nilfs_transaction_lock(sbi, &ti, 0);
+                nilfs_transaction_lock(sci->sc_super, &ti, 0);
                 ret = nilfs_segctor_construct(sci, SC_LSEG_SR);
-                nilfs_transaction_unlock(sbi);
+                nilfs_transaction_unlock(sci->sc_super);
 
         } while (ret && retrycount-- > 0);
 }
@@ -2736,10 +2727,10 @@ static void nilfs_segctor_write_out(struct nilfs_sc_info *sci)
  */
 static void nilfs_segctor_destroy(struct nilfs_sc_info *sci)
 {
-        struct nilfs_sb_info *sbi = sci->sc_sbi;
+        struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
         int flag;
 
-        up_write(&sbi->s_nilfs->ns_segctor_sem);
+        up_write(&nilfs->ns_segctor_sem);
 
         spin_lock(&sci->sc_state_lock);
         nilfs_segctor_kill_thread(sci);
@@ -2753,9 +2744,9 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci)
         WARN_ON(!list_empty(&sci->sc_copied_buffers));
 
         if (!list_empty(&sci->sc_dirty_files)) {
-                nilfs_warning(sbi->s_super, __func__,
+                nilfs_warning(sci->sc_super, __func__,
                               "dirty file(s) after the final construction\n");
-                nilfs_dispose_list(sbi, &sci->sc_dirty_files, 1);
+                nilfs_dispose_list(nilfs, &sci->sc_dirty_files, 1);
         }
 
         WARN_ON(!list_empty(&sci->sc_segbufs));
@@ -2763,79 +2754,78 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci)
 
         nilfs_put_root(sci->sc_root);
 
-        down_write(&sbi->s_nilfs->ns_segctor_sem);
+        down_write(&nilfs->ns_segctor_sem);
 
         del_timer_sync(&sci->sc_timer);
         kfree(sci);
 }
 
 /**
- * nilfs_attach_segment_constructor - attach a segment constructor
- * @sbi: nilfs_sb_info
+ * nilfs_attach_log_writer - attach log writer
+ * @sb: super block instance
  * @root: root object of the current filesystem tree
  *
- * nilfs_attach_segment_constructor() allocates a struct nilfs_sc_info,
- * initializes it, and starts the segment constructor.
+ * This allocates a log writer object, initializes it, and starts the
+ * log writer.
  *
  * Return Value: On success, 0 is returned. On error, one of the following
  * negative error code is returned.
  *
  * %-ENOMEM - Insufficient memory available.
  */
-int nilfs_attach_segment_constructor(struct nilfs_sb_info *sbi,
-                                     struct nilfs_root *root)
+int nilfs_attach_log_writer(struct super_block *sb, struct nilfs_root *root)
 {
+        struct the_nilfs *nilfs = sb->s_fs_info;
         int err;
 
-        if (NILFS_SC(sbi)) {
+        if (nilfs->ns_writer) {
                 /*
                  * This happens if the filesystem was remounted
                  * read/write after nilfs_error degenerated it into a
                  * read-only mount.
                  */
-                nilfs_detach_segment_constructor(sbi);
+                nilfs_detach_log_writer(sb);
         }
 
-        sbi->s_sc_info = nilfs_segctor_new(sbi, root);
-        if (!sbi->s_sc_info)
+        nilfs->ns_writer = nilfs_segctor_new(sb, root);
+        if (!nilfs->ns_writer)
                 return -ENOMEM;
 
-        err = nilfs_segctor_start_thread(NILFS_SC(sbi));
+        err = nilfs_segctor_start_thread(nilfs->ns_writer);
         if (err) {
-                kfree(sbi->s_sc_info);
-                sbi->s_sc_info = NULL;
+                kfree(nilfs->ns_writer);
+                nilfs->ns_writer = NULL;
         }
         return err;
 }
 
 /**
- * nilfs_detach_segment_constructor - destroy the segment constructor
- * @sbi: nilfs_sb_info
+ * nilfs_detach_log_writer - destroy log writer
+ * @sb: super block instance
  *
- * nilfs_detach_segment_constructor() kills the segment constructor daemon,
- * frees the struct nilfs_sc_info, and destroy the dirty file list.
+ * This kills log writer daemon, frees the log writer object, and
+ * destroys list of dirty files.
  */
-void nilfs_detach_segment_constructor(struct nilfs_sb_info *sbi)
+void nilfs_detach_log_writer(struct super_block *sb)
 {
-        struct the_nilfs *nilfs = sbi->s_nilfs;
+        struct the_nilfs *nilfs = sb->s_fs_info;
         LIST_HEAD(garbage_list);
 
         down_write(&nilfs->ns_segctor_sem);
-        if (NILFS_SC(sbi)) {
-                nilfs_segctor_destroy(NILFS_SC(sbi));
-                sbi->s_sc_info = NULL;
+        if (nilfs->ns_writer) {
+                nilfs_segctor_destroy(nilfs->ns_writer);
+                nilfs->ns_writer = NULL;
         }
 
         /* Force to free the list of dirty files */
-        spin_lock(&sbi->s_inode_lock);
-        if (!list_empty(&sbi->s_dirty_files)) {
-                list_splice_init(&sbi->s_dirty_files, &garbage_list);
-                nilfs_warning(sbi->s_super, __func__,
-                              "Non empty dirty list after the last "
-                              "segment construction\n");
-        }
-        spin_unlock(&sbi->s_inode_lock);
+        spin_lock(&nilfs->ns_inode_lock);
+        if (!list_empty(&nilfs->ns_dirty_files)) {
+                list_splice_init(&nilfs->ns_dirty_files, &garbage_list);
+                nilfs_warning(sb, __func__,
+                              "Hit dirty file after stopped log writer\n");
+        }
+        spin_unlock(&nilfs->ns_inode_lock);
         up_write(&nilfs->ns_segctor_sem);
 
-        nilfs_dispose_list(sbi, &garbage_list, 1);
+        nilfs_dispose_list(nilfs, &garbage_list, 1);
 }
diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h
index cd8056e7cbed..6c02a86745fb 100644
--- a/fs/nilfs2/segment.h
+++ b/fs/nilfs2/segment.h
@@ -27,7 +27,7 @@
 #include <linux/fs.h>
 #include <linux/buffer_head.h>
 #include <linux/nilfs2_fs.h>
-#include "sb.h"
+#include "nilfs.h"
 
 struct nilfs_root;
 
@@ -88,7 +88,6 @@ struct nilfs_segsum_pointer {
 /**
  * struct nilfs_sc_info - Segment constructor information
  * @sc_super: Back pointer to super_block struct
- * @sc_sbi: Back pointer to nilfs_sb_info struct
  * @sc_root: root object of the current filesystem tree
  * @sc_nblk_inc: Block count of current generation
  * @sc_dirty_files: List of files to be written
@@ -131,7 +130,6 @@ struct nilfs_segsum_pointer {
  */
 struct nilfs_sc_info {
         struct super_block     *sc_super;
-        struct nilfs_sb_info   *sc_sbi;
         struct nilfs_root      *sc_root;
 
         unsigned long           sc_nblk_inc;
@@ -235,18 +233,16 @@ extern void nilfs_flush_segment(struct super_block *, ino_t);
 extern int nilfs_clean_segments(struct super_block *, struct nilfs_argv *,
                                 void **);
 
-int nilfs_attach_segment_constructor(struct nilfs_sb_info *sbi,
-                                     struct nilfs_root *root);
-extern void nilfs_detach_segment_constructor(struct nilfs_sb_info *);
+int nilfs_attach_log_writer(struct super_block *sb, struct nilfs_root *root);
+void nilfs_detach_log_writer(struct super_block *sb);
 
 /* recovery.c */
 extern int nilfs_read_super_root_block(struct the_nilfs *, sector_t,
                                        struct buffer_head **, int);
 extern int nilfs_search_super_root(struct the_nilfs *,
                                    struct nilfs_recovery_info *);
-extern int nilfs_salvage_orphan_logs(struct the_nilfs *,
-                                     struct nilfs_sb_info *,
-                                     struct nilfs_recovery_info *);
+int nilfs_salvage_orphan_logs(struct the_nilfs *nilfs, struct super_block *sb,
+                              struct nilfs_recovery_info *ri);
 extern void nilfs_dispose_segment_list(struct list_head *);
 
 #endif /* _NILFS_SEGMENT_H */
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 1673b3d99842..062cca065195 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -43,7 +43,6 @@
 #include <linux/init.h>
 #include <linux/blkdev.h>
 #include <linux/parser.h>
-#include <linux/random.h>
 #include <linux/crc32.h>
 #include <linux/vfs.h>
 #include <linux/writeback.h>
@@ -72,23 +71,23 @@ struct kmem_cache *nilfs_transaction_cachep;
 struct kmem_cache *nilfs_segbuf_cachep;
 struct kmem_cache *nilfs_btree_path_cache;
 
-static int nilfs_setup_super(struct nilfs_sb_info *sbi, int is_mount);
+static int nilfs_setup_super(struct super_block *sb, int is_mount);
 static int nilfs_remount(struct super_block *sb, int *flags, char *data);
 
-static void nilfs_set_error(struct nilfs_sb_info *sbi)
+static void nilfs_set_error(struct super_block *sb)
 {
-        struct the_nilfs *nilfs = sbi->s_nilfs;
+        struct the_nilfs *nilfs = sb->s_fs_info;
         struct nilfs_super_block **sbp;
 
         down_write(&nilfs->ns_sem);
         if (!(nilfs->ns_mount_state & NILFS_ERROR_FS)) {
                 nilfs->ns_mount_state |= NILFS_ERROR_FS;
-                sbp = nilfs_prepare_super(sbi, 0);
+                sbp = nilfs_prepare_super(sb, 0);
                 if (likely(sbp)) {
                         sbp[0]->s_state |= cpu_to_le16(NILFS_ERROR_FS);
                         if (sbp[1])
                                 sbp[1]->s_state |= cpu_to_le16(NILFS_ERROR_FS);
-                        nilfs_commit_super(sbi, NILFS_SB_COMMIT_ALL);
+                        nilfs_commit_super(sb, NILFS_SB_COMMIT_ALL);
                 }
         }
         up_write(&nilfs->ns_sem);
@@ -109,7 +108,7 @@ static void nilfs_set_error(struct nilfs_sb_info *sbi)
 void nilfs_error(struct super_block *sb, const char *function,
                  const char *fmt, ...)
 {
-        struct nilfs_sb_info *sbi = NILFS_SB(sb);
+        struct the_nilfs *nilfs = sb->s_fs_info;
         struct va_format vaf;
         va_list args;
 
@@ -124,15 +123,15 @@ void nilfs_error(struct super_block *sb, const char *function,
         va_end(args);
 
         if (!(sb->s_flags & MS_RDONLY)) {
-                nilfs_set_error(sbi);
+                nilfs_set_error(sb);
 
-                if (nilfs_test_opt(sbi, ERRORS_RO)) {
+                if (nilfs_test_opt(nilfs, ERRORS_RO)) {
                         printk(KERN_CRIT "Remounting filesystem read-only\n");
                         sb->s_flags |= MS_RDONLY;
                 }
         }
 
-        if (nilfs_test_opt(sbi, ERRORS_PANIC))
+        if (nilfs_test_opt(nilfs, ERRORS_PANIC))
                 panic("NILFS (device %s): panic forced after error\n",
                       sb->s_id);
 }
@@ -189,14 +188,14 @@ void nilfs_destroy_inode(struct inode *inode)
         call_rcu(&inode->i_rcu, nilfs_i_callback);
 }
 
-static int nilfs_sync_super(struct nilfs_sb_info *sbi, int flag)
+static int nilfs_sync_super(struct super_block *sb, int flag)
 {
-        struct the_nilfs *nilfs = sbi->s_nilfs;
+        struct the_nilfs *nilfs = sb->s_fs_info;
         int err;
 
  retry:
         set_buffer_dirty(nilfs->ns_sbh[0]);
-        if (nilfs_test_opt(sbi, BARRIER)) {
+        if (nilfs_test_opt(nilfs, BARRIER)) {
                 err = __sync_dirty_buffer(nilfs->ns_sbh[0],
                                           WRITE_SYNC | WRITE_FLUSH_FUA);
         } else {
@@ -263,10 +262,10 @@ void nilfs_set_log_cursor(struct nilfs_super_block *sbp,
         spin_unlock(&nilfs->ns_last_segment_lock);
 }
 
-struct nilfs_super_block **nilfs_prepare_super(struct nilfs_sb_info *sbi,
+struct nilfs_super_block **nilfs_prepare_super(struct super_block *sb,
                                                int flip)
 {
-        struct the_nilfs *nilfs = sbi->s_nilfs;
+        struct the_nilfs *nilfs = sb->s_fs_info;
         struct nilfs_super_block **sbp = nilfs->ns_sbp;
 
         /* nilfs->ns_sem must be locked by the caller. */
@@ -276,7 +275,7 @@ struct nilfs_super_block **nilfs_prepare_super(struct nilfs_sb_info *sbi,
                         memcpy(sbp[0], sbp[1], nilfs->ns_sbsize);
                 } else {
                         printk(KERN_CRIT "NILFS: superblock broke on dev %s\n",
-                               sbi->s_super->s_id);
+                               sb->s_id);
                         return NULL;
                 }
         } else if (sbp[1] &&
@@ -290,9 +289,9 @@ struct nilfs_super_block **nilfs_prepare_super(struct nilfs_sb_info *sbi,
         return sbp;
 }
 
-int nilfs_commit_super(struct nilfs_sb_info *sbi, int flag)
+int nilfs_commit_super(struct super_block *sb, int flag)
 {
-        struct the_nilfs *nilfs = sbi->s_nilfs;
+        struct the_nilfs *nilfs = sb->s_fs_info;
         struct nilfs_super_block **sbp = nilfs->ns_sbp;
         time_t t;
 
@@ -312,27 +311,28 @@ int nilfs_commit_super(struct nilfs_sb_info *sbi, int flag)
                                             nilfs->ns_sbsize));
         }
         clear_nilfs_sb_dirty(nilfs);
-        return nilfs_sync_super(sbi, flag);
+        return nilfs_sync_super(sb, flag);
 }
 
 /**
  * nilfs_cleanup_super() - write filesystem state for cleanup
- * @sbi: nilfs_sb_info to be unmounted or degraded to read-only
+ * @sb: super block instance to be unmounted or degraded to read-only
  *
  * This function restores state flags in the on-disk super block.
  * This will set "clean" flag (i.e. NILFS_VALID_FS) unless the
  * filesystem was not clean previously.
  */
-int nilfs_cleanup_super(struct nilfs_sb_info *sbi)
+int nilfs_cleanup_super(struct super_block *sb)
 {
+        struct the_nilfs *nilfs = sb->s_fs_info;
         struct nilfs_super_block **sbp;
         int flag = NILFS_SB_COMMIT;
         int ret = -EIO;
 
-        sbp = nilfs_prepare_super(sbi, 0);
+        sbp = nilfs_prepare_super(sb, 0);
         if (sbp) {
-                sbp[0]->s_state = cpu_to_le16(sbi->s_nilfs->ns_mount_state);
-                nilfs_set_log_cursor(sbp[0], sbi->s_nilfs);
+                sbp[0]->s_state = cpu_to_le16(nilfs->ns_mount_state);
+                nilfs_set_log_cursor(sbp[0], nilfs);
                 if (sbp[1] && sbp[0]->s_last_cno == sbp[1]->s_last_cno) {
                         /*
                          * make the "clean" flag also to the opposite
@@ -342,21 +342,20 @@ int nilfs_cleanup_super(struct nilfs_sb_info *sbi)
                         sbp[1]->s_state = sbp[0]->s_state;
                         flag = NILFS_SB_COMMIT_ALL;
                 }
-                ret = nilfs_commit_super(sbi, flag);
+                ret = nilfs_commit_super(sb, flag);
         }
         return ret;
 }
 
 static void nilfs_put_super(struct super_block *sb)
 {
-        struct nilfs_sb_info *sbi = NILFS_SB(sb);
-        struct the_nilfs *nilfs = sbi->s_nilfs;
+        struct the_nilfs *nilfs = sb->s_fs_info;
 
-        nilfs_detach_segment_constructor(sbi);
+        nilfs_detach_log_writer(sb);
 
         if (!(sb->s_flags & MS_RDONLY)) {
                 down_write(&nilfs->ns_sem);
-                nilfs_cleanup_super(sbi);
+                nilfs_cleanup_super(sb);
                 up_write(&nilfs->ns_sem);
         }
 
@@ -365,15 +364,12 @@ static void nilfs_put_super(struct super_block *sb)
         iput(nilfs->ns_dat);
 
         destroy_nilfs(nilfs);
-        sbi->s_super = NULL;
         sb->s_fs_info = NULL;
-        kfree(sbi);
 }
 
 static int nilfs_sync_fs(struct super_block *sb, int wait)
 {
-        struct nilfs_sb_info *sbi = NILFS_SB(sb);
-        struct the_nilfs *nilfs = sbi->s_nilfs;
+        struct the_nilfs *nilfs = sb->s_fs_info;
         struct nilfs_super_block **sbp;
         int err = 0;
 
@@ -383,10 +379,10 @@ static int nilfs_sync_fs(struct super_block *sb, int wait)
 
         down_write(&nilfs->ns_sem);
         if (nilfs_sb_dirty(nilfs)) {
-                sbp = nilfs_prepare_super(sbi, nilfs_sb_will_flip(nilfs));
+                sbp = nilfs_prepare_super(sb, nilfs_sb_will_flip(nilfs));
                 if (likely(sbp)) {
                         nilfs_set_log_cursor(sbp[0], nilfs);
-                        nilfs_commit_super(sbi, NILFS_SB_COMMIT);
+                        nilfs_commit_super(sb, NILFS_SB_COMMIT);
                 }
         }
         up_write(&nilfs->ns_sem);
@@ -394,10 +390,10 @@ static int nilfs_sync_fs(struct super_block *sb, int wait)
         return err;
 }
 
-int nilfs_attach_checkpoint(struct nilfs_sb_info *sbi, __u64 cno, int curr_mnt,
+int nilfs_attach_checkpoint(struct super_block *sb, __u64 cno, int curr_mnt,
                             struct nilfs_root **rootp)
 {
-        struct the_nilfs *nilfs = sbi->s_nilfs;
+        struct the_nilfs *nilfs = sb->s_fs_info;
         struct nilfs_root *root;
         struct nilfs_checkpoint *raw_cp;
         struct buffer_head *bh_cp;
@@ -426,7 +422,7 @@ int nilfs_attach_checkpoint(struct nilfs_sb_info *sbi, __u64 cno, int curr_mnt,
                 goto failed;
         }
 
-        err = nilfs_ifile_read(sbi->s_super, root, nilfs->ns_inode_size,
+        err = nilfs_ifile_read(sb, root, nilfs->ns_inode_size,
                                &raw_cp->cp_ifile_inode, &root->ifile);
         if (err)
                 goto failed_bh;
@@ -450,8 +446,7 @@ int nilfs_attach_checkpoint(struct nilfs_sb_info *sbi, __u64 cno, int curr_mnt,
 
 static int nilfs_freeze(struct super_block *sb)
 {
-        struct nilfs_sb_info *sbi = NILFS_SB(sb);
-        struct the_nilfs *nilfs = sbi->s_nilfs;
+        struct the_nilfs *nilfs = sb->s_fs_info;
         int err;
 
         if (sb->s_flags & MS_RDONLY)
@@ -459,21 +454,20 @@ static int nilfs_freeze(struct super_block *sb)
 
         /* Mark super block clean */
         down_write(&nilfs->ns_sem);
-        err = nilfs_cleanup_super(sbi);
+        err = nilfs_cleanup_super(sb);
         up_write(&nilfs->ns_sem);
         return err;
 }
 
 static int nilfs_unfreeze(struct super_block *sb)
 {
-        struct nilfs_sb_info *sbi = NILFS_SB(sb);
-        struct the_nilfs *nilfs = sbi->s_nilfs;
+        struct the_nilfs *nilfs = sb->s_fs_info;
 
         if (sb->s_flags & MS_RDONLY)
                 return 0;
 
         down_write(&nilfs->ns_sem);
-        nilfs_setup_super(sbi, false);
+        nilfs_setup_super(sb, false);
         up_write(&nilfs->ns_sem);
         return 0;
 }
@@ -530,22 +524,22 @@ static int nilfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 static int nilfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
 {
         struct super_block *sb = vfs->mnt_sb;
-        struct nilfs_sb_info *sbi = NILFS_SB(sb);
+        struct the_nilfs *nilfs = sb->s_fs_info;
         struct nilfs_root *root = NILFS_I(vfs->mnt_root->d_inode)->i_root;
 
-        if (!nilfs_test_opt(sbi, BARRIER))
+        if (!nilfs_test_opt(nilfs, BARRIER))
                 seq_puts(seq, ",nobarrier");
         if (root->cno != NILFS_CPTREE_CURRENT_CNO)
                 seq_printf(seq, ",cp=%llu", (unsigned long long)root->cno);
-        if (nilfs_test_opt(sbi, ERRORS_PANIC))
+        if (nilfs_test_opt(nilfs, ERRORS_PANIC))
                 seq_puts(seq, ",errors=panic");
-        if (nilfs_test_opt(sbi, ERRORS_CONT))
+        if (nilfs_test_opt(nilfs, ERRORS_CONT))
                 seq_puts(seq, ",errors=continue");
-        if (nilfs_test_opt(sbi, STRICT_ORDER))
+        if (nilfs_test_opt(nilfs, STRICT_ORDER))
                 seq_puts(seq, ",order=strict");
-        if (nilfs_test_opt(sbi, NORECOVERY))
+        if (nilfs_test_opt(nilfs, NORECOVERY))
                 seq_puts(seq, ",norecovery");
-        if (nilfs_test_opt(sbi, DISCARD))
+        if (nilfs_test_opt(nilfs, DISCARD))
                 seq_puts(seq, ",discard");
 
         return 0;
@@ -594,7 +588,7 @@ static match_table_t tokens = {
 
 static int parse_options(char *options, struct super_block *sb, int is_remount)
 {
-        struct nilfs_sb_info *sbi = NILFS_SB(sb);
+        struct the_nilfs *nilfs = sb->s_fs_info;
         char *p;
         substring_t args[MAX_OPT_ARGS];
 
@@ -609,29 +603,29 @@ static int parse_options(char *options, struct super_block *sb, int is_remount)
                 token = match_token(p, tokens, args);
                 switch (token) {
                 case Opt_barrier:
-                        nilfs_set_opt(sbi, BARRIER);
+                        nilfs_set_opt(nilfs, BARRIER);
                         break;
                 case Opt_nobarrier:
-                        nilfs_clear_opt(sbi, BARRIER);
+                        nilfs_clear_opt(nilfs, BARRIER);
                         break;
                 case Opt_order:
                         if (strcmp(args[0].from, "relaxed") == 0)
                                 /* Ordered data semantics */
-                                nilfs_clear_opt(sbi, STRICT_ORDER);
+                                nilfs_clear_opt(nilfs, STRICT_ORDER);
                         else if (strcmp(args[0].from, "strict") == 0)
                                 /* Strict in-order semantics */
-                                nilfs_set_opt(sbi, STRICT_ORDER);
+                                nilfs_set_opt(nilfs, STRICT_ORDER);
                         else
                                 return 0;
                         break;
                 case Opt_err_panic:
-                        nilfs_write_opt(sbi, ERROR_MODE, ERRORS_PANIC);
+                        nilfs_write_opt(nilfs, ERROR_MODE, ERRORS_PANIC);
                         break;
                 case Opt_err_ro:
-                        nilfs_write_opt(sbi, ERROR_MODE, ERRORS_RO);
+                        nilfs_write_opt(nilfs, ERROR_MODE, ERRORS_RO);
                         break;
                 case Opt_err_cont:
-                        nilfs_write_opt(sbi, ERROR_MODE, ERRORS_CONT);
+                        nilfs_write_opt(nilfs, ERROR_MODE, ERRORS_CONT);
                         break;
                 case Opt_snapshot:
                         if (is_remount) {
@@ -642,13 +636,13 @@ static int parse_options(char *options, struct super_block *sb, int is_remount)
                         }
                         break;
                 case Opt_norecovery:
-                        nilfs_set_opt(sbi, NORECOVERY);
+                        nilfs_set_opt(nilfs, NORECOVERY);
                         break;
                 case Opt_discard:
-                        nilfs_set_opt(sbi, DISCARD);
+                        nilfs_set_opt(nilfs, DISCARD);
                         break;
                 case Opt_nodiscard:
-                        nilfs_clear_opt(sbi, DISCARD);
+                        nilfs_clear_opt(nilfs, DISCARD);
                         break;
                 default:
                         printk(KERN_ERR
@@ -660,22 +654,24 @@ static int parse_options(char *options, struct super_block *sb, int is_remount)
 }
 
 static inline void
-nilfs_set_default_options(struct nilfs_sb_info *sbi,
+nilfs_set_default_options(struct super_block *sb,
                           struct nilfs_super_block *sbp)
 {
-        sbi->s_mount_opt =
+        struct the_nilfs *nilfs = sb->s_fs_info;
+
+        nilfs->ns_mount_opt =
                 NILFS_MOUNT_ERRORS_RO | NILFS_MOUNT_BARRIER;
 }
 
-static int nilfs_setup_super(struct nilfs_sb_info *sbi, int is_mount)
+static int nilfs_setup_super(struct super_block *sb, int is_mount)
 {
-        struct the_nilfs *nilfs = sbi->s_nilfs;
+        struct the_nilfs *nilfs = sb->s_fs_info;
         struct nilfs_super_block **sbp;
         int max_mnt_count;
         int mnt_count;
 
         /* nilfs->ns_sem must be locked by the caller. */
-        sbp = nilfs_prepare_super(sbi, 0);
+        sbp = nilfs_prepare_super(sb, 0);
         if (!sbp)
                 return -EIO;
 
@@ -706,7 +702,7 @@ skip_mount_setup:
         /* synchronize sbp[1] with sbp[0] */
         if (sbp[1])
                 memcpy(sbp[1], sbp[0], nilfs->ns_sbsize);
-        return nilfs_commit_super(sbi, NILFS_SB_COMMIT_ALL);
+        return nilfs_commit_super(sb, NILFS_SB_COMMIT_ALL);
 }
 
 struct nilfs_super_block *nilfs_read_super_block(struct super_block *sb,
@@ -727,7 +723,7 @@ int nilfs_store_magic_and_option(struct super_block *sb,
                                  struct nilfs_super_block *sbp,
                                  char *data)
 {
-        struct nilfs_sb_info *sbi = NILFS_SB(sb);
+        struct the_nilfs *nilfs = sb->s_fs_info;
 
         sb->s_magic = le16_to_cpu(sbp->s_magic);
 
@@ -736,12 +732,12 @@ int nilfs_store_magic_and_option(struct super_block *sb,
         sb->s_flags |= MS_NOATIME;
 #endif
 
-        nilfs_set_default_options(sbi, sbp);
+        nilfs_set_default_options(sb, sbp);
 
-        sbi->s_resuid = le16_to_cpu(sbp->s_def_resuid);
-        sbi->s_resgid = le16_to_cpu(sbp->s_def_resgid);
-        sbi->s_interval = le32_to_cpu(sbp->s_c_interval);
-        sbi->s_watermark = le32_to_cpu(sbp->s_c_block_max);
+        nilfs->ns_resuid = le16_to_cpu(sbp->s_def_resuid);
+        nilfs->ns_resgid = le16_to_cpu(sbp->s_def_resgid);
+        nilfs->ns_interval = le32_to_cpu(sbp->s_c_interval);
+        nilfs->ns_watermark = le32_to_cpu(sbp->s_c_block_max);
 
         return !parse_options(data, sb, 0) ? -EINVAL : 0 ;
 }
@@ -822,7 +818,7 @@ static int nilfs_get_root_dentry(struct super_block *sb,
 static int nilfs_attach_snapshot(struct super_block *s, __u64 cno,
                                  struct dentry **root_dentry)
 {
-        struct the_nilfs *nilfs = NILFS_SB(s)->s_nilfs;
+        struct the_nilfs *nilfs = s->s_fs_info;
         struct nilfs_root *root;
         int ret;
 
@@ -840,7 +836,7 @@ static int nilfs_attach_snapshot(struct super_block *s, __u64 cno,
                 goto out;
         }
 
-        ret = nilfs_attach_checkpoint(NILFS_SB(s), cno, false, &root);
+        ret = nilfs_attach_checkpoint(s, cno, false, &root);
         if (ret) {
                 printk(KERN_ERR "NILFS: error loading snapshot "
                        "(checkpoint number=%llu).\n",
@@ -874,7 +870,7 @@ static int nilfs_try_to_shrink_tree(struct dentry *root_dentry)
 
 int nilfs_checkpoint_is_mounted(struct super_block *sb, __u64 cno)
 {
-        struct the_nilfs *nilfs = NILFS_SB(sb)->s_nilfs;
+        struct the_nilfs *nilfs = sb->s_fs_info;
         struct nilfs_root *root;
         struct inode *inode;
         struct dentry *dentry;
@@ -887,7 +883,7 @@ int nilfs_checkpoint_is_mounted(struct super_block *sb, __u64 cno)
                 return true;    /* protect recent checkpoints */
 
         ret = false;
-        root = nilfs_lookup_root(NILFS_SB(sb)->s_nilfs, cno);
+        root = nilfs_lookup_root(nilfs, cno);
         if (root) {
                 inode = nilfs_ilookup(sb, root, NILFS_ROOT_INO);
                 if (inode) {
@@ -917,43 +913,21 @@ static int
 nilfs_fill_super(struct super_block *sb, void *data, int silent)
 {
         struct the_nilfs *nilfs;
-        struct nilfs_sb_info *sbi;
         struct nilfs_root *fsroot;
         struct backing_dev_info *bdi;
         __u64 cno;
         int err;
 
-        sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
-        if (!sbi)
+        nilfs = alloc_nilfs(sb->s_bdev);
+        if (!nilfs)
                 return -ENOMEM;
 
-        sb->s_fs_info = sbi;
-        sbi->s_super = sb;
-
-        nilfs = alloc_nilfs(sb->s_bdev);
-        if (!nilfs) {
-                err = -ENOMEM;
-                goto failed_sbi;
-        }
-        sbi->s_nilfs = nilfs;
+        sb->s_fs_info = nilfs;
 
-        err = init_nilfs(nilfs, sbi, (char *)data);
+        err = init_nilfs(nilfs, sb, (char *)data);
         if (err)
                 goto failed_nilfs;
 
-        spin_lock_init(&sbi->s_inode_lock);
-        INIT_LIST_HEAD(&sbi->s_dirty_files);
-
-        /*
-         * Following initialization is overlapped because
-         * nilfs_sb_info structure has been cleared at the beginning.
-         * But we reserve them to keep our interest and make ready
-         * for the future change.
-         */
-        get_random_bytes(&sbi->s_next_generation,
-                         sizeof(sbi->s_next_generation));
-        spin_lock_init(&sbi->s_next_gen_lock);
-
         sb->s_op = &nilfs_sops;
         sb->s_export_op = &nilfs_export_ops;
         sb->s_root = NULL;
@@ -962,12 +936,12 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
         bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info;
         sb->s_bdi = bdi ? : &default_backing_dev_info;
 
-        err = load_nilfs(nilfs, sbi);
+        err = load_nilfs(nilfs, sb);
         if (err)
                 goto failed_nilfs;
 
         cno = nilfs_last_cno(nilfs);
-        err = nilfs_attach_checkpoint(sbi, cno, true, &fsroot);
+        err = nilfs_attach_checkpoint(sb, cno, true, &fsroot);
         if (err) {
                 printk(KERN_ERR "NILFS: error loading last checkpoint "
                        "(checkpoint number=%llu).\n", (unsigned long long)cno);
@@ -975,7 +949,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
         }
 
         if (!(sb->s_flags & MS_RDONLY)) {
-                err = nilfs_attach_segment_constructor(sbi, fsroot);
+                err = nilfs_attach_log_writer(sb, fsroot);
                 if (err)
                         goto failed_checkpoint;
         }
@@ -988,14 +962,14 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
 
         if (!(sb->s_flags & MS_RDONLY)) {
                 down_write(&nilfs->ns_sem);
-                nilfs_setup_super(sbi, true);
+                nilfs_setup_super(sb, true);
                 up_write(&nilfs->ns_sem);
         }
 
         return 0;
 
  failed_segctor:
-        nilfs_detach_segment_constructor(sbi);
+        nilfs_detach_log_writer(sb);
 
  failed_checkpoint:
         nilfs_put_root(fsroot);
@@ -1007,23 +981,18 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
 
  failed_nilfs:
         destroy_nilfs(nilfs);
-
- failed_sbi:
-        sb->s_fs_info = NULL;
-        kfree(sbi);
         return err;
 }
 
 static int nilfs_remount(struct super_block *sb, int *flags, char *data)
 {
-        struct nilfs_sb_info *sbi = NILFS_SB(sb);
-        struct the_nilfs *nilfs = sbi->s_nilfs;
+        struct the_nilfs *nilfs = sb->s_fs_info;
         unsigned long old_sb_flags;
         unsigned long old_mount_opt;
         int err;
 
         old_sb_flags = sb->s_flags;
-        old_mount_opt = sbi->s_mount_opt;
+        old_mount_opt = nilfs->ns_mount_opt;
 
         if (!parse_options(data, sb, 1)) {
                 err = -EINVAL;
@@ -1043,8 +1012,8 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data)
         if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
                 goto out;
         if (*flags & MS_RDONLY) {
-                /* Shutting down the segment constructor */
-                nilfs_detach_segment_constructor(sbi);
+                /* Shutting down log writer */
+                nilfs_detach_log_writer(sb);
                 sb->s_flags |= MS_RDONLY;
 
                 /*
@@ -1052,7 +1021,7 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data)
                  * the RDONLY flag and then mark the partition as valid again.
                  */
                 down_write(&nilfs->ns_sem);
-                nilfs_cleanup_super(sbi);
+                nilfs_cleanup_super(sb);
                 up_write(&nilfs->ns_sem);
         } else {
                 __u64 features;
@@ -1079,12 +1048,12 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data)
                 sb->s_flags &= ~MS_RDONLY;
 
                 root = NILFS_I(sb->s_root->d_inode)->i_root;
-                err = nilfs_attach_segment_constructor(sbi, root);
+                err = nilfs_attach_log_writer(sb, root);
                 if (err)
                         goto restore_opts;
 
                 down_write(&nilfs->ns_sem);
-                nilfs_setup_super(sbi, true);
+                nilfs_setup_super(sb, true);
                 up_write(&nilfs->ns_sem);
         }
  out:
@@ -1092,13 +1061,12 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data)
 
  restore_opts:
         sb->s_flags = old_sb_flags;
-        sbi->s_mount_opt = old_mount_opt;
+        nilfs->ns_mount_opt = old_mount_opt;
         return err;
 }
 
 struct nilfs_super_data {
         struct block_device *bdev;
-        struct nilfs_sb_info *sbi;
         __u64 cno;
         int flags;
 };
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index ad4ac607cf57..d2acd1a651f3 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -25,6 +25,7 @@
 #include <linux/slab.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
+#include <linux/random.h>
 #include <linux/crc32.h>
 #include "nilfs.h"
 #include "segment.h"
@@ -75,7 +76,10 @@ struct the_nilfs *alloc_nilfs(struct block_device *bdev)
         nilfs->ns_bdev = bdev;
         atomic_set(&nilfs->ns_ndirtyblks, 0);
         init_rwsem(&nilfs->ns_sem);
+        INIT_LIST_HEAD(&nilfs->ns_dirty_files);
         INIT_LIST_HEAD(&nilfs->ns_gc_inodes);
+        spin_lock_init(&nilfs->ns_inode_lock);
+        spin_lock_init(&nilfs->ns_next_gen_lock);
         spin_lock_init(&nilfs->ns_last_segment_lock);
         nilfs->ns_cptree = RB_ROOT;
         spin_lock_init(&nilfs->ns_cptree_lock);
@@ -197,16 +201,16 @@ static int nilfs_store_log_cursor(struct the_nilfs *nilfs,
 /**
  * load_nilfs - load and recover the nilfs
  * @nilfs: the_nilfs structure to be released
- * @sbi: nilfs_sb_info used to recover past segment
+ * @sb: super block isntance used to recover past segment
  *
  * load_nilfs() searches and load the latest super root,
  * attaches the last segment, and does recovery if needed.
  * The caller must call this exclusively for simultaneous mounts.
  */
-int load_nilfs(struct the_nilfs *nilfs, struct nilfs_sb_info *sbi)
+int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 {
         struct nilfs_recovery_info ri;
-        unsigned int s_flags = sbi->s_super->s_flags;
+        unsigned int s_flags = sb->s_flags;
         int really_read_only = bdev_read_only(nilfs->ns_bdev);
         int valid_fs = nilfs_valid_fs(nilfs);
         int err;
@@ -271,7 +275,7 @@ int load_nilfs(struct the_nilfs *nilfs, struct nilfs_sb_info *sbi)
                         goto scan_error;
         }
 
-        err = nilfs_load_super_root(nilfs, sbi->s_super, ri.ri_super_root);
+        err = nilfs_load_super_root(nilfs, sb, ri.ri_super_root);
         if (unlikely(err)) {
                 printk(KERN_ERR "NILFS: error loading super root.\n");
                 goto failed;
@@ -283,7 +287,7 @@ int load_nilfs(struct the_nilfs *nilfs, struct nilfs_sb_info *sbi)
         if (s_flags & MS_RDONLY) {
                 __u64 features;
 
-                if (nilfs_test_opt(sbi, NORECOVERY)) {
+                if (nilfs_test_opt(nilfs, NORECOVERY)) {
                         printk(KERN_INFO "NILFS: norecovery option specified. "
                                "skipping roll-forward recovery\n");
                         goto skip_recovery;
@@ -304,21 +308,21 @@ int load_nilfs(struct the_nilfs *nilfs, struct nilfs_sb_info *sbi)
                         err = -EROFS;
                         goto failed_unload;
                 }
-                sbi->s_super->s_flags &= ~MS_RDONLY;
-        } else if (nilfs_test_opt(sbi, NORECOVERY)) {
+                sb->s_flags &= ~MS_RDONLY;
+        } else if (nilfs_test_opt(nilfs, NORECOVERY)) {
                 printk(KERN_ERR "NILFS: recovery cancelled because norecovery "
                        "option was specified for a read/write mount\n");
                 err = -EINVAL;
                 goto failed_unload;
         }
 
-        err = nilfs_salvage_orphan_logs(nilfs, sbi, &ri);
+        err = nilfs_salvage_orphan_logs(nilfs, sb, &ri);
         if (err)
                 goto failed_unload;
 
         down_write(&nilfs->ns_sem);
         nilfs->ns_mount_state |= NILFS_VALID_FS; /* set "clean" flag */
-        err = nilfs_cleanup_super(sbi);
+        err = nilfs_cleanup_super(sb);
         up_write(&nilfs->ns_sem);
 
         if (err) {
@@ -330,7 +334,7 @@ int load_nilfs(struct the_nilfs *nilfs, struct nilfs_sb_info *sbi)
 
  skip_recovery:
         nilfs_clear_recovery_info(&ri);
-        sbi->s_super->s_flags = s_flags;
+        sb->s_flags = s_flags;
         return 0;
 
  scan_error:
@@ -344,7 +348,7 @@ int load_nilfs(struct the_nilfs *nilfs, struct nilfs_sb_info *sbi)
 
  failed:
         nilfs_clear_recovery_info(&ri);
-        sbi->s_super->s_flags = s_flags;
+        sb->s_flags = s_flags;
         return err;
 }
 
@@ -475,10 +479,13 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs,
                         return -EIO;
                 }
                 printk(KERN_WARNING
-                       "NILFS warning: unable to read primary superblock\n");
-        } else if (!sbp[1])
+                       "NILFS warning: unable to read primary superblock "
+                       "(blocksize = %d)\n", blocksize);
+        } else if (!sbp[1]) {
                 printk(KERN_WARNING
-                       "NILFS warning: unable to read secondary superblock\n");
+                       "NILFS warning: unable to read secondary superblock "
+                       "(blocksize = %d)\n", blocksize);
+        }
 
         /*
          * Compare two super blocks and set 1 in swp if the secondary
@@ -505,7 +512,7 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs,
 
         if (!valid[!swp])
                 printk(KERN_WARNING "NILFS warning: broken superblock. "
-                       "using spare superblock.\n");
+                       "using spare superblock (blocksize = %d).\n", blocksize);
         if (swp)
                 nilfs_swap_super_block(nilfs);
 
@@ -519,7 +526,6 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs,
 /**
  * init_nilfs - initialize a NILFS instance.
  * @nilfs: the_nilfs structure
- * @sbi: nilfs_sb_info
  * @sb: super block
  * @data: mount options
  *
@@ -530,9 +536,8 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs,
  * Return Value: On success, 0 is returned. On error, a negative error
  * code is returned.
  */
-int init_nilfs(struct the_nilfs *nilfs, struct nilfs_sb_info *sbi, char *data)
+int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data)
 {
-        struct super_block *sb = sbi->s_super;
         struct nilfs_super_block *sbp;
         int blocksize;
         int err;
@@ -588,6 +593,9 @@ int init_nilfs(struct the_nilfs *nilfs, struct nilfs_sb_info *sbi, char *data)
         nilfs->ns_blocksize_bits = sb->s_blocksize_bits;
         nilfs->ns_blocksize = blocksize;
 
+        get_random_bytes(&nilfs->ns_next_generation,
+                         sizeof(nilfs->ns_next_generation));
+
         err = nilfs_store_disk_layout(nilfs, sbp);
         if (err)
                 goto failed_sbh;
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index fd85e4c05c6b..f4968145c2a3 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -31,7 +31,8 @@
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
 #include <linux/slab.h>
-#include "sb.h"
+
+struct nilfs_sc_info;
 
 /* the_nilfs struct */
 enum {
@@ -65,13 +66,23 @@ enum {
  * @ns_last_cno: checkpoint number of the latest segment
  * @ns_prot_seq: least sequence number of segments which must not be reclaimed
  * @ns_prev_seq: base sequence number used to decide if advance log cursor
- * @ns_segctor_sem: segment constructor semaphore
+ * @ns_writer: log writer
+ * @ns_segctor_sem: semaphore protecting log write
  * @ns_dat: DAT file inode
  * @ns_cpfile: checkpoint file inode
  * @ns_sufile: segusage file inode
  * @ns_cptree: rb-tree of all mounted checkpoints (nilfs_root)
  * @ns_cptree_lock: lock protecting @ns_cptree
+ * @ns_dirty_files: list of dirty files
+ * @ns_inode_lock: lock protecting @ns_dirty_files
  * @ns_gc_inodes: dummy inodes to keep live blocks
+ * @ns_next_generation: next generation number for inodes
+ * @ns_next_gen_lock: lock protecting @ns_next_generation
+ * @ns_mount_opt: mount options
+ * @ns_resuid: uid for reserved blocks
+ * @ns_resgid: gid for reserved blocks
+ * @ns_interval: checkpoint creation interval
+ * @ns_watermark: watermark for the number of dirty buffers
  * @ns_blocksize_bits: bit length of block size
  * @ns_blocksize: block size
  * @ns_nsegments: number of segments in filesystem
@@ -131,6 +142,7 @@ struct the_nilfs {
         u64                     ns_prot_seq;
         u64                     ns_prev_seq;
 
+        struct nilfs_sc_info   *ns_writer;
         struct rw_semaphore     ns_segctor_sem;
 
         /*
@@ -145,9 +157,25 @@ struct the_nilfs {
         struct rb_root          ns_cptree;
         spinlock_t              ns_cptree_lock;
 
+        /* Dirty inode list */
+        struct list_head        ns_dirty_files;
+        spinlock_t              ns_inode_lock;
+
         /* GC inode list */
         struct list_head        ns_gc_inodes;
 
+        /* Inode allocator */
+        u32                     ns_next_generation;
+        spinlock_t              ns_next_gen_lock;
+
+        /* Mount options */
+        unsigned long           ns_mount_opt;
+
+        uid_t                   ns_resuid;
+        gid_t                   ns_resgid;
+        unsigned long           ns_interval;
+        unsigned long           ns_watermark;
+
         /* Disk layout information (static) */
         unsigned int            ns_blocksize_bits;
         unsigned int            ns_blocksize;
@@ -180,6 +208,20 @@ THE_NILFS_FNS(DISCONTINUED, discontinued)
 THE_NILFS_FNS(GC_RUNNING, gc_running)
 THE_NILFS_FNS(SB_DIRTY, sb_dirty)
 
+/*
+ * Mount option operations
+ */
+#define nilfs_clear_opt(nilfs, opt)  \
+        do { (nilfs)->ns_mount_opt &= ~NILFS_MOUNT_##opt; } while (0)
+#define nilfs_set_opt(nilfs, opt)  \
+        do { (nilfs)->ns_mount_opt |= NILFS_MOUNT_##opt; } while (0)
+#define nilfs_test_opt(nilfs, opt) ((nilfs)->ns_mount_opt & NILFS_MOUNT_##opt)
+#define nilfs_write_opt(nilfs, mask, opt)                               \
+        do { (nilfs)->ns_mount_opt =                                    \
+                (((nilfs)->ns_mount_opt & ~NILFS_MOUNT_##mask) |        \
+                 NILFS_MOUNT_##opt);                                    \
+        } while (0)
+
 /**
  * struct nilfs_root - nilfs root object
  * @cno: checkpoint number
@@ -224,15 +266,14 @@ static inline int nilfs_sb_will_flip(struct the_nilfs *nilfs)
 void nilfs_set_last_segment(struct the_nilfs *, sector_t, u64, __u64);
 struct the_nilfs *alloc_nilfs(struct block_device *bdev);
 void destroy_nilfs(struct the_nilfs *nilfs);
-int init_nilfs(struct the_nilfs *, struct nilfs_sb_info *, char *);
-int load_nilfs(struct the_nilfs *, struct nilfs_sb_info *);
+int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data);
+int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb);
 int nilfs_discard_segments(struct the_nilfs *, __u64 *, size_t);
 int nilfs_count_free_blocks(struct the_nilfs *, sector_t *);
 struct nilfs_root *nilfs_lookup_root(struct the_nilfs *nilfs, __u64 cno);
 struct nilfs_root *nilfs_find_or_create_root(struct the_nilfs *nilfs,
                                              __u64 cno);
 void nilfs_put_root(struct nilfs_root *root);
-struct nilfs_sb_info *nilfs_find_sbinfo(struct the_nilfs *, int, __u64);
 int nilfs_near_disk_full(struct the_nilfs *);
 void nilfs_fall_back_super_block(struct the_nilfs *);
 void nilfs_swap_super_block(struct the_nilfs *);
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 8b61220cffc5..6b1305dc26c0 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -876,7 +876,7 @@ SYSCALL_ALIAS(sys_fanotify_mark, SyS_fanotify_mark);
 #endif
 
 /*
- * fanotify_user_setup - Our initialization function.  Note that we cannnot return
+ * fanotify_user_setup - Our initialization function.  Note that we cannot return
  * error because we have compiled-in VFS hooks.  So an (unlikely) failure here
  * must result in panic().
  */
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 4cd5d5d78f9f..bd46e7c8a0ef 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -841,7 +841,7 @@ out:
 }
 
 /*
- * inotify_user_setup - Our initialization function.  Note that we cannnot return
+ * inotify_user_setup - Our initialization function.  Note that we cannot return
  * error because we have compiled-in VFS hooks.  So an (unlikely) failure here
  * must result in panic().
  */
diff --git a/fs/ntfs/Makefile b/fs/ntfs/Makefile
index 4ff028fcfd6e..30206b238433 100644
--- a/fs/ntfs/Makefile
+++ b/fs/ntfs/Makefile
@@ -2,18 +2,13 @@
 
 obj-$(CONFIG_NTFS_FS) += ntfs.o
 
-ntfs-objs := aops.o attrib.o collate.o compress.o debug.o dir.o file.o \
-             index.o inode.o mft.o mst.o namei.o runlist.o super.o sysctl.o \
-             unistr.o upcase.o
+ntfs-y := aops.o attrib.o collate.o compress.o debug.o dir.o file.o \
+          index.o inode.o mft.o mst.o namei.o runlist.o super.o sysctl.o \
+          unistr.o upcase.o
 
-EXTRA_CFLAGS = -DNTFS_VERSION=\"2.1.30\"
+ntfs-$(CONFIG_NTFS_RW) += bitmap.o lcnalloc.o logfile.o quota.o usnjrnl.o
 
-ifeq ($(CONFIG_NTFS_DEBUG),y)
-EXTRA_CFLAGS += -DDEBUG
-endif
+ccflags-y := -DNTFS_VERSION=\"2.1.30\"
+ccflags-$(CONFIG_NTFS_DEBUG)    += -DDEBUG
+ccflags-$(CONFIG_NTFS_RW)       += -DNTFS_RW
 
-ifeq ($(CONFIG_NTFS_RW),y)
-EXTRA_CFLAGS += -DNTFS_RW
-
-ntfs-objs += bitmap.o lcnalloc.o logfile.o quota.o usnjrnl.o
-endif
diff --git a/fs/ocfs2/Makefile b/fs/ocfs2/Makefile
index 07d9fd854350..d8a0313e99e6 100644
--- a/fs/ocfs2/Makefile
+++ b/fs/ocfs2/Makefile
@@ -1,6 +1,6 @@
-EXTRA_CFLAGS += -Ifs/ocfs2
+ccflags-y := -Ifs/ocfs2
 
-EXTRA_CFLAGS += -DCATCH_BH_JBD_RACES
+ccflags-y += -DCATCH_BH_JBD_RACES
 
 obj-$(CONFIG_OCFS2_FS) +=       \
         ocfs2.o                 \
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index 704f6b1742f3..90f2729b7a5b 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -497,7 +497,7 @@ static int ocfs2_xattr_set_acl(struct dentry *dentry, const char *name,
         if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
                 return -EOPNOTSUPP;
 
-        if (!is_owner_or_cap(inode))
+        if (!inode_owner_or_capable(inode))
                 return -EPERM;
 
         if (value) {
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index d417b3f9b0c7..f97b6f1c61dd 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -354,7 +354,7 @@ static inline int ocfs2_match(int len,
 /*
  * Returns 0 if not found, -1 on failure, and 1 on success
  */
-static int inline ocfs2_search_dirblock(struct buffer_head *bh,
+static inline int ocfs2_search_dirblock(struct buffer_head *bh,
                                         struct inode *dir,
                                         const char *name, int namelen,
                                         unsigned long offset,
diff --git a/fs/ocfs2/dlm/Makefile b/fs/ocfs2/dlm/Makefile
index dcebf0d920fa..c8a044efbb15 100644
--- a/fs/ocfs2/dlm/Makefile
+++ b/fs/ocfs2/dlm/Makefile
@@ -1,4 +1,4 @@
-EXTRA_CFLAGS += -Ifs/ocfs2
+ccflags-y := -Ifs/ocfs2
 
 obj-$(CONFIG_OCFS2_FS_O2CB) += ocfs2_dlm.o
 
diff --git a/fs/ocfs2/dlmfs/Makefile b/fs/ocfs2/dlmfs/Makefile
index df69b4856d0d..f14be89a6701 100644
--- a/fs/ocfs2/dlmfs/Makefile
+++ b/fs/ocfs2/dlmfs/Makefile
@@ -1,4 +1,4 @@
-EXTRA_CFLAGS += -Ifs/ocfs2
+ccflags-y := -Ifs/ocfs2
 
 obj-$(CONFIG_OCFS2_FS) += ocfs2_dlmfs.o
 
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 7a4868196152..09de77ce002a 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -82,7 +82,7 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags,
         }
 
         status = -EACCES;
-        if (!is_owner_or_cap(inode))
+        if (!inode_owner_or_capable(inode))
                 goto bail_unlock;
 
         if (!S_ISDIR(inode->i_mode))
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 51cd6898e7f1..1a97ba1ec3fc 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -831,18 +831,18 @@ static inline unsigned int ocfs2_clusters_to_megabytes(struct super_block *sb,
 
 static inline void _ocfs2_set_bit(unsigned int bit, unsigned long *bitmap)
 {
-        ext2_set_bit(bit, bitmap);
+        __test_and_set_bit_le(bit, bitmap);
 }
 #define ocfs2_set_bit(bit, addr) _ocfs2_set_bit((bit), (unsigned long *)(addr))
 
 static inline void _ocfs2_clear_bit(unsigned int bit, unsigned long *bitmap)
 {
-        ext2_clear_bit(bit, bitmap);
+        __test_and_clear_bit_le(bit, bitmap);
 }
 #define ocfs2_clear_bit(bit, addr) _ocfs2_clear_bit((bit), (unsigned long *)(addr))
 
-#define ocfs2_test_bit ext2_test_bit
-#define ocfs2_find_next_zero_bit ext2_find_next_zero_bit
-#define ocfs2_find_next_bit ext2_find_next_bit
+#define ocfs2_test_bit test_bit_le
+#define ocfs2_find_next_zero_bit find_next_zero_bit_le
+#define ocfs2_find_next_bit find_next_bit_le
 #endif  /* OCFS2_H */
 
diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c
index 393f3f659da7..de4ff29f1e05 100644
--- a/fs/omfs/dir.c
+++ b/fs/omfs/dir.c
@@ -235,33 +235,22 @@ static int omfs_dir_is_empty(struct inode *inode)
         return *ptr != ~0;
 }
 
-static int omfs_unlink(struct inode *dir, struct dentry *dentry)
+static int omfs_remove(struct inode *dir, struct dentry *dentry)
 {
-        int ret;
         struct inode *inode = dentry->d_inode;
+        int ret;
+
+        if (S_ISDIR(inode->i_mode) && !omfs_dir_is_empty(inode))
+                return -ENOTEMPTY;
 
         ret = omfs_delete_entry(dentry);
         if (ret)
-                goto end_unlink;
-
-        inode_dec_link_count(inode);
+                return ret;
+        
+        clear_nlink(inode);
+        mark_inode_dirty(inode);
         mark_inode_dirty(dir);
-
-end_unlink:
-        return ret;
-}
-
-static int omfs_rmdir(struct inode *dir, struct dentry *dentry)
-{
-        int err = -ENOTEMPTY;
-        struct inode *inode = dentry->d_inode;
-
-        if (omfs_dir_is_empty(inode)) {
-                err = omfs_unlink(dir, dentry);
-                if (!err)
-                        inode_dec_link_count(inode);
-        }
-        return err;
+        return 0;
 }
 
 static int omfs_add_node(struct inode *dir, struct dentry *dentry, int mode)
@@ -372,9 +361,10 @@ static int omfs_fill_chain(struct file *filp, void *dirent, filldir_t filldir,
 
                 res = filldir(dirent, oi->i_name, strnlen(oi->i_name,
                         OMFS_NAMELEN), filp->f_pos, self, d_type);
-                if (res == 0)
-                        filp->f_pos++;
                 brelse(bh);
+                if (res < 0)
+                        break;
+                filp->f_pos++;
         }
 out:
         return res;
@@ -385,44 +375,28 @@ static int omfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 {
         struct inode *new_inode = new_dentry->d_inode;
         struct inode *old_inode = old_dentry->d_inode;
-        struct buffer_head *bh;
-        int is_dir;
         int err;
 
-        is_dir = S_ISDIR(old_inode->i_mode);
-
         if (new_inode) {
                 /* overwriting existing file/dir */
-                err = -ENOTEMPTY;
-                if (is_dir && !omfs_dir_is_empty(new_inode))
-                        goto out;
-
-                err = -ENOENT;
-                bh = omfs_find_entry(new_dir, new_dentry->d_name.name,
-                        new_dentry->d_name.len);
-                if (IS_ERR(bh))
-                        goto out;
-                brelse(bh);
-
-                err = omfs_unlink(new_dir, new_dentry);
+                err = omfs_remove(new_dir, new_dentry);
                 if (err)
                         goto out;
         }
 
         /* since omfs locates files by name, we need to unlink _before_
          * adding the new link or we won't find the old one */
-        inode_inc_link_count(old_inode);
-        err = omfs_unlink(old_dir, old_dentry);
-        if (err) {
-                inode_dec_link_count(old_inode);
+        err = omfs_delete_entry(old_dentry);
+        if (err)
                 goto out;
-        }
 
+        mark_inode_dirty(old_dir);
         err = omfs_add_link(new_dentry, old_inode);
         if (err)
                 goto out;
 
         old_inode->i_ctime = CURRENT_TIME_SEC;
+        mark_inode_dirty(old_inode);
 out:
         return err;
 }
@@ -488,8 +462,8 @@ const struct inode_operations omfs_dir_inops = {
         .mkdir = omfs_mkdir,
         .rename = omfs_rename,
         .create = omfs_create,
-        .unlink = omfs_unlink,
-        .rmdir = omfs_rmdir,
+        .unlink = omfs_remove,
+        .rmdir = omfs_remove,
 };
 
 const struct file_operations omfs_dir_operations = {
diff --git a/fs/open.c b/fs/open.c
index f83ca80cc59a..b52cf013ffa1 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -835,17 +835,8 @@ struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags,
 
         validate_creds(cred);
 
-        /*
-         * We must always pass in a valid mount pointer.   Historically
-         * callers got away with not passing it, but we must enforce this at
-         * the earliest possible point now to avoid strange problems deep in the
-         * filesystem stack.
-         */
-        if (!mnt) {
-                printk(KERN_WARNING "%s called with NULL vfsmount\n", __func__);
-                dump_stack();
-                return ERR_PTR(-EINVAL);
-        }
+        /* We must always pass in a valid mount pointer. */
+        BUG_ON(!mnt);
 
         error = -ENFILE;
         f = get_empty_filp();
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 7c99c1cf7e5c..5e4f776b0917 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -489,8 +489,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
                 vsize,
                 mm ? get_mm_rss(mm) : 0,
                 rsslim,
-                mm ? mm->start_code : 0,
-                mm ? mm->end_code : 0,
+                mm ? (permitted ? mm->start_code : 1) : 0,
+                mm ? (permitted ? mm->end_code : 1) : 0,
                 (permitted && mm) ? mm->start_stack : 0,
                 esp,
                 eip,
diff --git a/fs/proc/base.c b/fs/proc/base.c
index d49c4b5d2c3e..5a670c11aeac 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -191,17 +191,20 @@ static int proc_root_link(struct inode *inode, struct path *path)
         return result;
 }
 
-/*
- * Return zero if current may access user memory in @task, -error if not.
- */
-static int check_mem_permission(struct task_struct *task)
+static struct mm_struct *__check_mem_permission(struct task_struct *task)
 {
+        struct mm_struct *mm;
+
+        mm = get_task_mm(task);
+        if (!mm)
+                return ERR_PTR(-EINVAL);
+
         /*
          * A task can always look at itself, in case it chooses
          * to use system calls instead of load instructions.
          */
         if (task == current)
-                return 0;
+                return mm;
 
         /*
          * If current is actively ptrace'ing, and would also be
@@ -213,27 +216,53 @@ static int check_mem_permission(struct task_struct *task)
                 match = (tracehook_tracer_task(task) == current);
                 rcu_read_unlock();
                 if (match && ptrace_may_access(task, PTRACE_MODE_ATTACH))
-                        return 0;
+                        return mm;
         }
 
         /*
          * Noone else is allowed.
          */
-        return -EPERM;
+        mmput(mm);
+        return ERR_PTR(-EPERM);
+}
+
+/*
+ * If current may access user memory in @task return a reference to the
+ * corresponding mm, otherwise ERR_PTR.
+ */
+static struct mm_struct *check_mem_permission(struct task_struct *task)
+{
+        struct mm_struct *mm;
+        int err;
+
+        /*
+         * Avoid racing if task exec's as we might get a new mm but validate
+         * against old credentials.
+         */
+        err = mutex_lock_killable(&task->signal->cred_guard_mutex);
+        if (err)
+                return ERR_PTR(err);
+
+        mm = __check_mem_permission(task);
+        mutex_unlock(&task->signal->cred_guard_mutex);
+
+        return mm;
 }
 
 struct mm_struct *mm_for_maps(struct task_struct *task)
 {
         struct mm_struct *mm;
+        int err;
 
-        if (mutex_lock_killable(&task->signal->cred_guard_mutex))
-                return NULL;
+        err =  mutex_lock_killable(&task->signal->cred_guard_mutex);
+        if (err)
+                return ERR_PTR(err);
 
         mm = get_task_mm(task);
         if (mm && mm != current->mm &&
                         !ptrace_may_access(task, PTRACE_MODE_READ)) {
                 mmput(mm);
-                mm = NULL;
+                mm = ERR_PTR(-EACCES);
         }
         mutex_unlock(&task->signal->cred_guard_mutex);
 
@@ -279,9 +308,9 @@ out:
 
 static int proc_pid_auxv(struct task_struct *task, char *buffer)
 {
-        int res = 0;
-        struct mm_struct *mm = get_task_mm(task);
-        if (mm) {
+        struct mm_struct *mm = mm_for_maps(task);
+        int res = PTR_ERR(mm);
+        if (mm && !IS_ERR(mm)) {
                 unsigned int nwords = 0;
                 do {
                         nwords += 2;
@@ -318,6 +347,23 @@ static int proc_pid_wchan(struct task_struct *task, char *buffer)
 }
 #endif /* CONFIG_KALLSYMS */
 
+static int lock_trace(struct task_struct *task)
+{
+        int err = mutex_lock_killable(&task->signal->cred_guard_mutex);
+        if (err)
+                return err;
+        if (!ptrace_may_access(task, PTRACE_MODE_ATTACH)) {
+                mutex_unlock(&task->signal->cred_guard_mutex);
+                return -EPERM;
+        }
+        return 0;
+}
+
+static void unlock_trace(struct task_struct *task)
+{
+        mutex_unlock(&task->signal->cred_guard_mutex);
+}
+
 #ifdef CONFIG_STACKTRACE
 
 #define MAX_STACK_TRACE_DEPTH   64
@@ -327,6 +373,7 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
 {
         struct stack_trace trace;
         unsigned long *entries;
+        int err;
         int i;
 
         entries = kmalloc(MAX_STACK_TRACE_DEPTH * sizeof(*entries), GFP_KERNEL);
@@ -337,15 +384,20 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
         trace.max_entries       = MAX_STACK_TRACE_DEPTH;
         trace.entries           = entries;
         trace.skip              = 0;
-        save_stack_trace_tsk(task, &trace);
 
-        for (i = 0; i < trace.nr_entries; i++) {
-                seq_printf(m, "[<%p>] %pS\n",
-                           (void *)entries[i], (void *)entries[i]);
+        err = lock_trace(task);
+        if (!err) {
+                save_stack_trace_tsk(task, &trace);
+
+                for (i = 0; i < trace.nr_entries; i++) {
+                        seq_printf(m, "[<%pK>] %pS\n",
+                                   (void *)entries[i], (void *)entries[i]);
+                }
+                unlock_trace(task);
         }
         kfree(entries);
 
-        return 0;
+        return err;
 }
 #endif
 
@@ -508,18 +560,22 @@ static int proc_pid_syscall(struct task_struct *task, char *buffer)
 {
         long nr;
         unsigned long args[6], sp, pc;
+        int res = lock_trace(task);
+        if (res)
+                return res;
 
         if (task_current_syscall(task, &nr, args, 6, &sp, &pc))
-                return sprintf(buffer, "running\n");
-
-        if (nr < 0)
-                return sprintf(buffer, "%ld 0x%lx 0x%lx\n", nr, sp, pc);
-
-        return sprintf(buffer,
+                res = sprintf(buffer, "running\n");
+        else if (nr < 0)
+                res = sprintf(buffer, "%ld 0x%lx 0x%lx\n", nr, sp, pc);
+        else
+                res = sprintf(buffer,
                        "%ld 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n",
                        nr,
                        args[0], args[1], args[2], args[3], args[4], args[5],
                        sp, pc);
+        unlock_trace(task);
+        return res;
 }
 #endif /* CONFIG_HAVE_ARCH_TRACEHOOK */
 
@@ -775,18 +831,14 @@ static ssize_t mem_read(struct file * file, char __user * buf,
         if (!task)
                 goto out_no_task;
 
-        if (check_mem_permission(task))
-                goto out;
-
         ret = -ENOMEM;
         page = (char *)__get_free_page(GFP_TEMPORARY);
         if (!page)
                 goto out;
 
-        ret = 0;
- 
-        mm = get_task_mm(task);
-        if (!mm)
+        mm = check_mem_permission(task);
+        ret = PTR_ERR(mm);
+        if (IS_ERR(mm))
                 goto out_free;
 
         ret = -EIO;
@@ -800,8 +852,8 @@ static ssize_t mem_read(struct file * file, char __user * buf,
                 int this_len, retval;
 
                 this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
-                retval = access_process_vm(task, src, page, this_len, 0);
-                if (!retval || check_mem_permission(task)) {
+                retval = access_remote_vm(mm, src, page, this_len, 0);
+                if (!retval) {
                         if (!ret)
                                 ret = -EIO;
                         break;
@@ -829,10 +881,6 @@ out_no_task:
         return ret;
 }
 
-#define mem_write NULL
-
-#ifndef mem_write
-/* This is a security hazard */
 static ssize_t mem_write(struct file * file, const char __user *buf,
                          size_t count, loff_t *ppos)
 {
@@ -840,18 +888,25 @@ static ssize_t mem_write(struct file * file, const char __user *buf,
         char *page;
         struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
         unsigned long dst = *ppos;
+        struct mm_struct *mm;
 
         copied = -ESRCH;
         if (!task)
                 goto out_no_task;
 
-        if (check_mem_permission(task))
-                goto out;
+        mm = check_mem_permission(task);
+        copied = PTR_ERR(mm);
+        if (IS_ERR(mm))
+                goto out_task;
+
+        copied = -EIO;
+        if (file->private_data != (void *)((long)current->self_exec_id))
+                goto out_mm;
 
         copied = -ENOMEM;
         page = (char *)__get_free_page(GFP_TEMPORARY);
         if (!page)
-                goto out;
+                goto out_mm;
 
         copied = 0;
         while (count > 0) {
@@ -862,7 +917,7 @@ static ssize_t mem_write(struct file * file, const char __user *buf,
                         copied = -EFAULT;
                         break;
                 }
-                retval = access_process_vm(task, dst, page, this_len, 1);
+                retval = access_remote_vm(mm, dst, page, this_len, 1);
                 if (!retval) {
                         if (!copied)
                                 copied = -EIO;
@@ -875,12 +930,13 @@ static ssize_t mem_write(struct file * file, const char __user *buf,
         }
         *ppos = dst;
         free_page((unsigned long) page);
-out:
+out_mm:
+        mmput(mm);
+out_task:
         put_task_struct(task);
 out_no_task:
         return copied;
 }
-#endif
 
 loff_t mem_lseek(struct file *file, loff_t offset, int orig)
 {
@@ -917,20 +973,18 @@ static ssize_t environ_read(struct file *file, char __user *buf,
         if (!task)
                 goto out_no_task;
 
-        if (!ptrace_may_access(task, PTRACE_MODE_READ))
-                goto out;
-
         ret = -ENOMEM;
         page = (char *)__get_free_page(GFP_TEMPORARY);
         if (!page)
                 goto out;
 
-        ret = 0;
 
-        mm = get_task_mm(task);
-        if (!mm)
+        mm = mm_for_maps(task);
+        ret = PTR_ERR(mm);
+        if (!mm || IS_ERR(mm))
                 goto out_free;
 
+        ret = 0;
         while (count > 0) {
                 int this_len, retval, max_len;
 
@@ -2748,8 +2802,12 @@ static int proc_tgid_io_accounting(struct task_struct *task, char *buffer)
 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;
+        int err = lock_trace(task);
+        if (!err) {
+                seq_printf(m, "%08x\n", task->personality);
+                unlock_trace(task);
+        }
+        return err;
 }
 
 /*
@@ -2768,7 +2826,7 @@ static const struct pid_entry tgid_base_stuff[] = {
         REG("environ",    S_IRUSR, proc_environ_operations),
         INF("auxv",       S_IRUSR, proc_pid_auxv),
         ONE("status",     S_IRUGO, proc_pid_status),
-        ONE("personality", S_IRUSR, proc_pid_personality),
+        ONE("personality", S_IRUGO, proc_pid_personality),
         INF("limits",     S_IRUGO, proc_pid_limits),
 #ifdef CONFIG_SCHED_DEBUG
         REG("sched",      S_IRUGO|S_IWUSR, proc_pid_sched_operations),
@@ -2778,7 +2836,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 #endif
         REG("comm",      S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
 #ifdef CONFIG_HAVE_ARCH_TRACEHOOK
-        INF("syscall",    S_IRUSR, proc_pid_syscall),
+        INF("syscall",    S_IRUGO, proc_pid_syscall),
 #endif
         INF("cmdline",    S_IRUGO, proc_pid_cmdline),
         ONE("stat",       S_IRUGO, proc_tgid_stat),
@@ -2797,7 +2855,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_PROC_PAGE_MONITOR
         REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
         REG("smaps",      S_IRUGO, proc_smaps_operations),
-        REG("pagemap",    S_IRUSR, proc_pagemap_operations),
+        REG("pagemap",    S_IRUGO, proc_pagemap_operations),
 #endif
 #ifdef CONFIG_SECURITY
         DIR("attr",       S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations),
@@ -2806,7 +2864,7 @@ static const struct pid_entry tgid_base_stuff[] = {
         INF("wchan",      S_IRUGO, proc_pid_wchan),
 #endif
 #ifdef CONFIG_STACKTRACE
-        ONE("stack",      S_IRUSR, proc_pid_stack),
+        ONE("stack",      S_IRUGO, proc_pid_stack),
 #endif
 #ifdef CONFIG_SCHEDSTATS
         INF("schedstat",  S_IRUGO, proc_pid_schedstat),
@@ -3108,14 +3166,14 @@ static const struct pid_entry tid_base_stuff[] = {
         REG("environ",   S_IRUSR, proc_environ_operations),
         INF("auxv",      S_IRUSR, proc_pid_auxv),
         ONE("status",    S_IRUGO, proc_pid_status),
-        ONE("personality", S_IRUSR, proc_pid_personality),
+        ONE("personality", S_IRUGO, proc_pid_personality),
         INF("limits",    S_IRUGO, proc_pid_limits),
 #ifdef CONFIG_SCHED_DEBUG
         REG("sched",     S_IRUGO|S_IWUSR, proc_pid_sched_operations),
 #endif
         REG("comm",      S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
 #ifdef CONFIG_HAVE_ARCH_TRACEHOOK
-        INF("syscall",   S_IRUSR, proc_pid_syscall),
+        INF("syscall",   S_IRUGO, proc_pid_syscall),
 #endif
         INF("cmdline",   S_IRUGO, proc_pid_cmdline),
         ONE("stat",      S_IRUGO, proc_tid_stat),
@@ -3133,7 +3191,7 @@ static const struct pid_entry tid_base_stuff[] = {
 #ifdef CONFIG_PROC_PAGE_MONITOR
         REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
         REG("smaps",     S_IRUGO, proc_smaps_operations),
-        REG("pagemap",    S_IRUSR, proc_pagemap_operations),
+        REG("pagemap",    S_IRUGO, proc_pagemap_operations),
 #endif
 #ifdef CONFIG_SECURITY
         DIR("attr",      S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations),
@@ -3142,7 +3200,7 @@ static const struct pid_entry tid_base_stuff[] = {
         INF("wchan",     S_IRUGO, proc_pid_wchan),
 #endif
 #ifdef CONFIG_STACKTRACE
-        ONE("stack",      S_IRUSR, proc_pid_stack),
+        ONE("stack",      S_IRUGO, proc_pid_stack),
 #endif
 #ifdef CONFIG_SCHEDSTATS
         INF("schedstat", S_IRUGO, proc_pid_schedstat),
@@ -3161,7 +3219,7 @@ static const struct pid_entry tid_base_stuff[] = {
         REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
 #ifdef CONFIG_AUDITSYSCALL
         REG("loginuid",  S_IWUSR|S_IRUGO, proc_loginuid_operations),
-        REG("sessionid",  S_IRUSR, proc_sessionid_operations),
+        REG("sessionid",  S_IRUGO, proc_sessionid_operations),
 #endif
 #ifdef CONFIG_FAULT_INJECTION
         REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations),
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 01e07f2a188f..f1281339b6fa 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -28,7 +28,7 @@
 
 DEFINE_SPINLOCK(proc_subdir_lock);
 
-static int proc_match(int len, const char *name, struct proc_dir_entry *de)
+static int proc_match(unsigned int len, const char *name, struct proc_dir_entry *de)
 {
         if (de->namelen != len)
                 return 0;
@@ -303,7 +303,7 @@ static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret,
 {
         const char              *cp = name, *next;
         struct proc_dir_entry   *de;
-        int                     len;
+        unsigned int            len;
 
         de = *ret;
         if (!de)
@@ -602,7 +602,7 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
 {
         struct proc_dir_entry *ent = NULL;
         const char *fn = name;
-        int len;
+        unsigned int len;
 
         /* make sure name is valid */
         if (!name || !strlen(name)) goto out;
@@ -786,7 +786,7 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
         struct proc_dir_entry **p;
         struct proc_dir_entry *de = NULL;
         const char *fn = name;
-        int len;
+        unsigned int len;
 
         spin_lock(&proc_subdir_lock);
         if (__xlate_proc_name(name, &parent, &fn) != 0) {
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index d6a7ca1fdac5..d15aa1b1cc8f 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -46,8 +46,6 @@ static void proc_evict_inode(struct inode *inode)
         }
 }
 
-struct vfsmount *proc_mnt;
-
 static struct kmem_cache * proc_inode_cachep;
 
 static struct inode *proc_alloc_inode(struct super_block *sb)
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 9ad561ded409..c03e8d3a3a5b 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -107,7 +107,6 @@ static inline struct proc_dir_entry *pde_get(struct proc_dir_entry *pde)
 }
 void pde_put(struct proc_dir_entry *pde);
 
-extern struct vfsmount *proc_mnt;
 int proc_fill_super(struct super_block *);
 struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *);
 
diff --git a/fs/proc/root.c b/fs/proc/root.c
index ef9fa8e24ad6..a9000e9cfee5 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -43,17 +43,6 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
         struct pid_namespace *ns;
         struct proc_inode *ei;
 
-        if (proc_mnt) {
-                /* Seed the root directory with a pid so it doesn't need
-                 * to be special in base.c.  I would do this earlier but
-                 * the only task alive when /proc is mounted the first time
-                 * is the init_task and it doesn't have any pids.
-                 */
-                ei = PROC_I(proc_mnt->mnt_sb->s_root->d_inode);
-                if (!ei->pid)
-                        ei->pid = find_get_pid(1);
-        }
-
         if (flags & MS_KERNMOUNT)
                 ns = (struct pid_namespace *)data;
         else
@@ -71,16 +60,16 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
                         return ERR_PTR(err);
                 }
 
-                ei = PROC_I(sb->s_root->d_inode);
-                if (!ei->pid) {
-                        rcu_read_lock();
-                        ei->pid = get_pid(find_pid_ns(1, ns));
-                        rcu_read_unlock();
-                }
-
                 sb->s_flags |= MS_ACTIVE;
         }
 
+        ei = PROC_I(sb->s_root->d_inode);
+        if (!ei->pid) {
+                rcu_read_lock();
+                ei->pid = get_pid(find_pid_ns(1, ns));
+                rcu_read_unlock();
+        }
+
         return dget(sb->s_root);
 }
 
@@ -101,19 +90,20 @@ static struct file_system_type proc_fs_type = {
 
 void __init proc_root_init(void)
 {
+        struct vfsmount *mnt;
         int err;
 
         proc_init_inodecache();
         err = register_filesystem(&proc_fs_type);
         if (err)
                 return;
-        proc_mnt = kern_mount_data(&proc_fs_type, &init_pid_ns);
-        if (IS_ERR(proc_mnt)) {
+        mnt = kern_mount_data(&proc_fs_type, &init_pid_ns);
+        if (IS_ERR(mnt)) {
                 unregister_filesystem(&proc_fs_type);
                 return;
         }
 
-        init_pid_ns.proc_mnt = proc_mnt;
+        init_pid_ns.proc_mnt = mnt;
         proc_symlink("mounts", NULL, "self/mounts");
 
         proc_net_init();
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 60b914860f81..7c708a418acc 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1,5 +1,6 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
+#include <linux/huge_mm.h>
 #include <linux/mount.h>
 #include <linux/seq_file.h>
 #include <linux/highmem.h>
@@ -7,6 +8,7 @@
 #include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/mempolicy.h>
+#include <linux/rmap.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
 
@@ -119,14 +121,14 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 
         priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
         if (!priv->task)
-                return NULL;
+                return ERR_PTR(-ESRCH);
 
         mm = mm_for_maps(priv->task);
-        if (!mm)
-                return NULL;
+        if (!mm || IS_ERR(mm))
+                return mm;
         down_read(&mm->mmap_sem);
 
-        tail_vma = get_gate_vma(priv->task);
+        tail_vma = get_gate_vma(priv->task->mm);
         priv->tail_vma = tail_vma;
 
         /* Start with last addr hint */
@@ -249,8 +251,8 @@ static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
                 const char *name = arch_vma_name(vma);
                 if (!name) {
                         if (mm) {
-                                if (vma->vm_start <= mm->start_brk &&
-                                                vma->vm_end >= mm->brk) {
+                                if (vma->vm_start <= mm->brk &&
+                                                vma->vm_end >= mm->start_brk) {
                                         name = "[heap]";
                                 } else if (vma->vm_start <= mm->start_stack &&
                                            vma->vm_end >= mm->start_stack) {
@@ -277,7 +279,8 @@ static int show_map(struct seq_file *m, void *v)
         show_map_vma(m, vma);
 
         if (m->count < m->size)  /* vma is copied successfully */
-                m->version = (vma != get_gate_vma(task))? vma->vm_start: 0;
+                m->version = (vma != get_gate_vma(task->mm))
+                        ? vma->vm_start : 0;
         return 0;
 }
 
@@ -329,58 +332,86 @@ struct mem_size_stats {
         unsigned long private_dirty;
         unsigned long referenced;
         unsigned long anonymous;
+        unsigned long anonymous_thp;
         unsigned long swap;
         u64 pss;
 };
 
-static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
-                           struct mm_walk *walk)
+
+static void smaps_pte_entry(pte_t ptent, unsigned long addr,
+                unsigned long ptent_size, struct mm_walk *walk)
 {
         struct mem_size_stats *mss = walk->private;
         struct vm_area_struct *vma = mss->vma;
-        pte_t *pte, ptent;
-        spinlock_t *ptl;
         struct page *page;
         int mapcount;
 
-        pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
-        for (; addr != end; pte++, addr += PAGE_SIZE) {
-                ptent = *pte;
-
-                if (is_swap_pte(ptent)) {
-                        mss->swap += PAGE_SIZE;
-                        continue;
-                }
+        if (is_swap_pte(ptent)) {
+                mss->swap += ptent_size;
+                return;
+        }
 
-                if (!pte_present(ptent))
-                        continue;
+        if (!pte_present(ptent))
+                return;
+
+        page = vm_normal_page(vma, addr, ptent);
+        if (!page)
+                return;
+
+        if (PageAnon(page))
+                mss->anonymous += ptent_size;
+
+        mss->resident += ptent_size;
+        /* Accumulate the size in pages that have been accessed. */
+        if (pte_young(ptent) || PageReferenced(page))
+                mss->referenced += ptent_size;
+        mapcount = page_mapcount(page);
+        if (mapcount >= 2) {
+                if (pte_dirty(ptent) || PageDirty(page))
+                        mss->shared_dirty += ptent_size;
+                else
+                        mss->shared_clean += ptent_size;
+                mss->pss += (ptent_size << PSS_SHIFT) / mapcount;
+        } else {
+                if (pte_dirty(ptent) || PageDirty(page))
+                        mss->private_dirty += ptent_size;
+                else
+                        mss->private_clean += ptent_size;
+                mss->pss += (ptent_size << PSS_SHIFT);
+        }
+}
 
-                page = vm_normal_page(vma, addr, ptent);
-                if (!page)
-                        continue;
+static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+                           struct mm_walk *walk)
+{
+        struct mem_size_stats *mss = walk->private;
+        struct vm_area_struct *vma = mss->vma;
+        pte_t *pte;
+        spinlock_t *ptl;
 
-                if (PageAnon(page))
-                        mss->anonymous += PAGE_SIZE;
-
-                mss->resident += PAGE_SIZE;
-                /* Accumulate the size in pages that have been accessed. */
-                if (pte_young(ptent) || PageReferenced(page))
-                        mss->referenced += PAGE_SIZE;
-                mapcount = page_mapcount(page);
-                if (mapcount >= 2) {
-                        if (pte_dirty(ptent) || PageDirty(page))
-                                mss->shared_dirty += PAGE_SIZE;
-                        else
-                                mss->shared_clean += PAGE_SIZE;
-                        mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount;
+        spin_lock(&walk->mm->page_table_lock);
+        if (pmd_trans_huge(*pmd)) {
+                if (pmd_trans_splitting(*pmd)) {
+                        spin_unlock(&walk->mm->page_table_lock);
+                        wait_split_huge_page(vma->anon_vma, pmd);
                 } else {
-                        if (pte_dirty(ptent) || PageDirty(page))
-                                mss->private_dirty += PAGE_SIZE;
-                        else
-                                mss->private_clean += PAGE_SIZE;
-                        mss->pss += (PAGE_SIZE << PSS_SHIFT);
+                        smaps_pte_entry(*(pte_t *)pmd, addr,
+                                        HPAGE_PMD_SIZE, walk);
+                        spin_unlock(&walk->mm->page_table_lock);
+                        mss->anonymous_thp += HPAGE_PMD_SIZE;
+                        return 0;
                 }
+        } else {
+                spin_unlock(&walk->mm->page_table_lock);
         }
+        /*
+         * The mmap_sem held all the way back in m_start() is what
+         * keeps khugepaged out of here and from collapsing things
+         * in here.
+         */
+        pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+        for (; addr != end; pte++, addr += PAGE_SIZE)
+                smaps_pte_entry(*pte, addr, PAGE_SIZE, walk);
         pte_unmap_unlock(pte - 1, ptl);
         cond_resched();
         return 0;
@@ -416,6 +447,7 @@ static int show_smap(struct seq_file *m, void *v)
                    "Private_Dirty:  %8lu kB\n"
                    "Referenced:     %8lu kB\n"
                    "Anonymous:      %8lu kB\n"
+                   "AnonHugePages:  %8lu kB\n"
                    "Swap:           %8lu kB\n"
                    "KernelPageSize: %8lu kB\n"
                    "MMUPageSize:    %8lu kB\n"
@@ -429,6 +461,7 @@ static int show_smap(struct seq_file *m, void *v)
                    mss.private_dirty >> 10,
                    mss.referenced >> 10,
                    mss.anonymous >> 10,
+                   mss.anonymous_thp >> 10,
                    mss.swap >> 10,
                    vma_kernel_pagesize(vma) >> 10,
                    vma_mmu_pagesize(vma) >> 10,
@@ -436,7 +469,8 @@ static int show_smap(struct seq_file *m, void *v)
                         (unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0);
 
         if (m->count < m->size)  /* vma is copied successfully */
-                m->version = (vma != get_gate_vma(task)) ? vma->vm_start : 0;
+                m->version = (vma != get_gate_vma(task->mm))
+                        ? vma->vm_start : 0;
         return 0;
 }
 
@@ -467,6 +501,8 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
         spinlock_t *ptl;
         struct page *page;
 
+        split_huge_page_pmd(walk->mm, pmd);
+
         pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
         for (; addr != end; pte++, addr += PAGE_SIZE) {
                 ptent = *pte;
@@ -623,6 +659,8 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
         pte_t *pte;
         int err = 0;
 
+        split_huge_page_pmd(walk->mm, pmd);
+
         /* find the first VMA at or above 'addr' */
         vma = find_vma(walk->mm, addr);
         for (; addr != end; addr += PAGE_SIZE) {
@@ -728,8 +766,9 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
         if (!task)
                 goto out;
 
-        ret = -EACCES;
-        if (!ptrace_may_access(task, PTRACE_MODE_READ))
+        mm = mm_for_maps(task);
+        ret = PTR_ERR(mm);
+        if (!mm || IS_ERR(mm))
                 goto out_task;
 
         ret = -EINVAL;
@@ -742,10 +781,6 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
         if (!count)
                 goto out_task;
 
-        mm = get_task_mm(task);
-        if (!mm)
-                goto out_task;
-
         pm.len = PM_ENTRY_BYTES * (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
         pm.buffer = kmalloc(pm.len, GFP_TEMPORARY);
         ret = -ENOMEM;
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index b535d3e5d5f1..980de547c070 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -199,13 +199,13 @@ static void *m_start(struct seq_file *m, loff_t *pos)
         /* pin the task and mm whilst we play with them */
         priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
         if (!priv->task)
-                return NULL;
+                return ERR_PTR(-ESRCH);
 
         mm = mm_for_maps(priv->task);
-        if (!mm) {
+        if (!mm || IS_ERR(mm)) {
                 put_task_struct(priv->task);
                 priv->task = NULL;
-                return NULL;
+                return mm;
         }
         down_read(&mm->mmap_sem);
 
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index 549d245d0b42..977ed2723845 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -27,6 +27,7 @@
 #include <linux/string.h>
 #include <linux/mount.h>
 #include <linux/ramfs.h>
+#include <linux/parser.h>
 #include <linux/sched.h>
 #include <linux/magic.h>
 #include <linux/pstore.h>
@@ -40,9 +41,29 @@
 struct pstore_private {
         u64     id;
         int     (*erase)(u64);
+        ssize_t size;
+        char    data[];
 };
 
-#define pstore_get_inode ramfs_get_inode
+static int pstore_file_open(struct inode *inode, struct file *file)
+{
+        file->private_data = inode->i_private;
+        return 0;
+}
+
+static ssize_t pstore_file_read(struct file *file, char __user *userbuf,
+                                                size_t count, loff_t *ppos)
+{
+        struct pstore_private *ps = file->private_data;
+
+        return simple_read_from_buffer(userbuf, count, ppos, ps->data, ps->size);
+}
+
+static const struct file_operations pstore_file_operations = {
+        .open   = pstore_file_open,
+        .read   = pstore_file_read,
+        .llseek = default_llseek,
+};
 
 /*
  * When a file is unlinked from our file system we call the
@@ -53,54 +74,99 @@ static int pstore_unlink(struct inode *dir, struct dentry *dentry)
         struct pstore_private *p = dentry->d_inode->i_private;
 
         p->erase(p->id);
-        kfree(p);
 
         return simple_unlink(dir, dentry);
 }
 
+static void pstore_evict_inode(struct inode *inode)
+{
+        end_writeback(inode);
+        kfree(inode->i_private);
+}
+
 static const struct inode_operations pstore_dir_inode_operations = {
         .lookup         = simple_lookup,
         .unlink         = pstore_unlink,
 };
 
+static struct inode *pstore_get_inode(struct super_block *sb,
+                                        const struct inode *dir, int mode, dev_t dev)
+{
+        struct inode *inode = new_inode(sb);
+
+        if (inode) {
+                inode->i_ino = get_next_ino();
+                inode->i_uid = inode->i_gid = 0;
+                inode->i_mode = mode;
+                inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+                switch (mode & S_IFMT) {
+                case S_IFREG:
+                        inode->i_fop = &pstore_file_operations;
+                        break;
+                case S_IFDIR:
+                        inode->i_op = &pstore_dir_inode_operations;
+                        inode->i_fop = &simple_dir_operations;
+                        inc_nlink(inode);
+                        break;
+                }
+        }
+        return inode;
+}
+
+enum {
+        Opt_kmsg_bytes, Opt_err
+};
+
+static const match_table_t tokens = {
+        {Opt_kmsg_bytes, "kmsg_bytes=%u"},
+        {Opt_err, NULL}
+};
+
+static void parse_options(char *options)
+{
+        char            *p;
+        substring_t     args[MAX_OPT_ARGS];
+        int             option;
+
+        if (!options)
+                return;
+
+        while ((p = strsep(&options, ",")) != NULL) {
+                int token;
+
+                if (!*p)
+                        continue;
+
+                token = match_token(p, tokens, args);
+                switch (token) {
+                case Opt_kmsg_bytes:
+                        if (!match_int(&args[0], &option))
+                                pstore_set_kmsg_bytes(option);
+                        break;
+                }
+        }
+}
+
+static int pstore_remount(struct super_block *sb, int *flags, char *data)
+{
+        parse_options(data);
+
+        return 0;
+}
+
 static const struct super_operations pstore_ops = {
         .statfs         = simple_statfs,
         .drop_inode     = generic_delete_inode,
+        .evict_inode    = pstore_evict_inode,
+        .remount_fs     = pstore_remount,
         .show_options   = generic_show_options,
 };
 
 static struct super_block *pstore_sb;
-static struct vfsmount *pstore_mnt;
 
 int pstore_is_mounted(void)
 {
-        return pstore_mnt != NULL;
-}
-
-/*
- * Set up a file structure as if we had opened this file and
- * write our data to it.
- */
-static int pstore_writefile(struct inode *inode, struct dentry *dentry,
-        char *data, size_t size)
-{
-        struct file f;
-        ssize_t n;
-        mm_segment_t old_fs = get_fs();
-
-        memset(&f, '0', sizeof f);
-        f.f_mapping = inode->i_mapping;
-        f.f_path.dentry = dentry;
-        f.f_path.mnt = pstore_mnt;
-        f.f_pos = 0;
-        f.f_op = inode->i_fop;
-        set_fs(KERNEL_DS);
-        n = do_sync_write(&f, data, size, &f.f_pos);
-        set_fs(old_fs);
-
-        fsnotify_modify(&f);
-
-        return n == size;
+        return pstore_sb != NULL;
 }
 
 /*
@@ -123,8 +189,7 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id,
         inode = pstore_get_inode(pstore_sb, root->d_inode, S_IFREG | 0444, 0);
         if (!inode)
                 goto fail;
-        inode->i_uid = inode->i_gid = 0;
-        private = kmalloc(sizeof *private, GFP_KERNEL);
+        private = kmalloc(sizeof *private + size, GFP_KERNEL);
         if (!private)
                 goto fail_alloc;
         private->id = id;
@@ -152,28 +217,19 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id,
         if (IS_ERR(dentry))
                 goto fail_lockedalloc;
 
-        d_add(dentry, inode);
-
-        mutex_unlock(&root->d_inode->i_mutex);
-
-        if (!pstore_writefile(inode, dentry, data, size))
-                goto fail_write;
+        memcpy(private->data, data, size);
+        inode->i_size = private->size = size;
 
         inode->i_private = private;
 
         if (time.tv_sec)
                 inode->i_mtime = inode->i_ctime = time;
 
-        return 0;
+        d_add(dentry, inode);
 
-fail_write:
-        kfree(private);
-        inode->i_nlink--;
-        mutex_lock(&root->d_inode->i_mutex);
-        d_delete(dentry);
-        dput(dentry);
         mutex_unlock(&root->d_inode->i_mutex);
-        goto fail;
+
+        return 0;
 
 fail_lockedalloc:
         mutex_unlock(&root->d_inode->i_mutex);
@@ -202,6 +258,8 @@ int pstore_fill_super(struct super_block *sb, void *data, int silent)
         sb->s_op                = &pstore_ops;
         sb->s_time_gran         = 1;
 
+        parse_options(data);
+
         inode = pstore_get_inode(sb, NULL, S_IFDIR | 0755, 0);
         if (!inode) {
                 err = -ENOMEM;
@@ -225,59 +283,27 @@ fail:
         return err;
 }
 
-static int pstore_get_sb(struct file_system_type *fs_type,
-        int flags, const char *dev_name, void *data, struct vfsmount *mnt)
+static struct dentry *pstore_mount(struct file_system_type *fs_type,
+        int flags, const char *dev_name, void *data)
 {
-        struct dentry *root;
-
-        root = mount_nodev(fs_type, flags, data, pstore_fill_super);
-        if (IS_ERR(root))
-                return -ENOMEM;
-
-        mnt->mnt_root = root;
-        mnt->mnt_sb = root->d_sb;
-        pstore_mnt = mnt;
-
-        return 0;
+        return mount_single(fs_type, flags, data, pstore_fill_super);
 }
 
 static void pstore_kill_sb(struct super_block *sb)
 {
         kill_litter_super(sb);
         pstore_sb = NULL;
-        pstore_mnt = NULL;
 }
 
 static struct file_system_type pstore_fs_type = {
         .name           = "pstore",
-        .get_sb         = pstore_get_sb,
+        .mount          = pstore_mount,
         .kill_sb        = pstore_kill_sb,
 };
 
 static int __init init_pstore_fs(void)
 {
-        int rc = 0;
-        struct kobject *pstorefs_kobj;
-
-        pstorefs_kobj = kobject_create_and_add("pstore", fs_kobj);
-        if (!pstorefs_kobj) {
-                rc = -ENOMEM;
-                goto done;
-        }
-
-        rc = sysfs_create_file(pstorefs_kobj, &pstore_kmsg_bytes_attr.attr);
-        if (rc)
-                goto done1;
-
-        rc = register_filesystem(&pstore_fs_type);
-        if (rc == 0)
-                goto done;
-
-        sysfs_remove_file(pstorefs_kobj, &pstore_kmsg_bytes_attr.attr);
-done1:
-        kobject_put(pstorefs_kobj);
-done:
-        return rc;
+        return register_filesystem(&pstore_fs_type);
 }
 module_init(init_pstore_fs)
 
diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h
index 76c26d2fab29..8c9f23eb1645 100644
--- a/fs/pstore/internal.h
+++ b/fs/pstore/internal.h
@@ -1,7 +1,6 @@
+extern void     pstore_set_kmsg_bytes(int);
 extern void     pstore_get_records(void);
 extern int      pstore_mkfile(enum pstore_type_id, char *psname, u64 id,
                               char *data, size_t size,
                               struct timespec time, int (*erase)(u64));
 extern int      pstore_is_mounted(void);
-
-extern struct kobj_attribute pstore_kmsg_bytes_attr;
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 705fdf8abf6e..f835a25625ff 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -37,27 +37,21 @@
 static DEFINE_SPINLOCK(pstore_lock);
 static struct pstore_info *psinfo;
 
-/* How much of the console log to snapshot. /sys/fs/pstore/kmsg_bytes */
+/* How much of the console log to snapshot */
 static unsigned long kmsg_bytes = 10240;
 
-static ssize_t b_show(struct kobject *kobj,
-                      struct kobj_attribute *attr, char *buf)
+void pstore_set_kmsg_bytes(int bytes)
 {
-        return snprintf(buf, PAGE_SIZE, "%lu\n", kmsg_bytes);
+        kmsg_bytes = bytes;
 }
 
-static ssize_t b_store(struct kobject *kobj, struct kobj_attribute *attr,
-                       const char *buf, size_t count)
-{
-        return (sscanf(buf, "%lu", &kmsg_bytes) > 0) ? count : 0;
-}
-
-struct kobj_attribute pstore_kmsg_bytes_attr =
-        __ATTR(kmsg_bytes, S_IRUGO | S_IWUSR, b_show, b_store);
-
 /* Tag each group of saved records with a sequence number */
 static int      oopscount;
 
+static char *reason_str[] = {
+        "Oops", "Panic", "Kexec", "Restart", "Halt", "Poweroff", "Emergency"
+};
+
 /*
  * callback from kmsg_dump. (s2,l2) has the most recently
  * written bytes, older bytes are in (s1,l1). Save as much
@@ -71,15 +65,20 @@ static void pstore_dump(struct kmsg_dumper *dumper,
         unsigned long   s1_start, s2_start;
         unsigned long   l1_cpy, l2_cpy;
         unsigned long   size, total = 0;
-        char            *dst;
+        char            *dst, *why;
         u64             id;
         int             hsize, part = 1;
 
+        if (reason < ARRAY_SIZE(reason_str))
+                why = reason_str[reason];
+        else
+                why = "Unknown";
+
         mutex_lock(&psinfo->buf_mutex);
         oopscount++;
         while (total < kmsg_bytes) {
                 dst = psinfo->buf;
-                hsize = sprintf(dst, "Oops#%d Part%d\n", oopscount, part++);
+                hsize = sprintf(dst, "%s#%d Part%d\n", why, oopscount, part++);
                 size = psinfo->bufsize - hsize;
                 dst += hsize;
 
@@ -96,7 +95,7 @@ static void pstore_dump(struct kmsg_dumper *dumper,
                 memcpy(dst + l1_cpy, s2 + s2_start, l2_cpy);
 
                 id = psinfo->write(PSTORE_TYPE_DMESG, hsize + l1_cpy + l2_cpy);
-                if (pstore_is_mounted())
+                if (reason == KMSG_DUMP_OOPS && pstore_is_mounted())
                         pstore_mkfile(PSTORE_TYPE_DMESG, psinfo->name, id,
                                       psinfo->buf, hsize + l1_cpy + l2_cpy,
                                       CURRENT_TIME, psinfo->erase);
diff --git a/fs/reiserfs/Makefile b/fs/reiserfs/Makefile
index 792b3cb2cd18..3c3b00165114 100644
--- a/fs/reiserfs/Makefile
+++ b/fs/reiserfs/Makefile
@@ -31,9 +31,7 @@ endif
 # and causing a panic. Since this behavior only affects ppc32, this ifeq
 # will work around it. If any other architecture displays this behavior,
 # add it here.
-ifeq ($(CONFIG_PPC32),y)
-EXTRA_CFLAGS := $(call cc-ifversion, -lt, 0400, -O1)
-endif
+ccflags-$(CONFIG_PPC32) := $(call cc-ifversion, -lt, 0400, -O1)
 
 TAGS:
         etags *.c
diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c
index 79265fdc317a..4e153051bc75 100644
--- a/fs/reiserfs/ioctl.c
+++ b/fs/reiserfs/ioctl.c
@@ -59,7 +59,7 @@ long reiserfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
                         if (err)
                                 break;
 
-                        if (!is_owner_or_cap(inode)) {
+                        if (!inode_owner_or_capable(inode)) {
                                 err = -EPERM;
                                 goto setflags_out;
                         }
@@ -103,7 +103,7 @@ setflags_out:
                 err = put_user(inode->i_generation, (int __user *)arg);
                 break;
         case REISERFS_IOC_SETVERSION:
-                if (!is_owner_or_cap(inode)) {
+                if (!inode_owner_or_capable(inode)) {
                         err = -EPERM;
                         break;
                 }
diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c
index 90d2fcb67a31..3dc38f1206fc 100644
--- a/fs/reiserfs/xattr_acl.c
+++ b/fs/reiserfs/xattr_acl.c
@@ -26,7 +26,7 @@ posix_acl_set(struct dentry *dentry, const char *name, const void *value,
         size_t jcreate_blocks;
         if (!reiserfs_posixacl(inode->i_sb))
                 return -EOPNOTSUPP;
-        if (!is_owner_or_cap(inode))
+        if (!inode_owner_or_capable(inode))
                 return -EPERM;
 
         if (value) {
diff --git a/fs/select.c b/fs/select.c
index e56560d2b08a..d33418fdc858 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -517,9 +517,6 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
  * Update: ERESTARTSYS breaks at least the xview clock binary, so
  * I'm trying ERESTARTNOHAND which restart only when you want to.
  */
-#define MAX_SELECT_SECONDS \
-        ((unsigned long) (MAX_SCHEDULE_TIMEOUT / HZ)-1)
-
 int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
                            fd_set __user *exp, struct timespec *end_time)
 {
diff --git a/fs/squashfs/Kconfig b/fs/squashfs/Kconfig
index aa68a8a31518..efc309fa3035 100644
--- a/fs/squashfs/Kconfig
+++ b/fs/squashfs/Kconfig
@@ -5,12 +5,12 @@ config SQUASHFS
         help
           Saying Y here includes support for SquashFS 4.0 (a Compressed
           Read-Only File System).  Squashfs is a highly compressed read-only
-          filesystem for Linux.  It uses zlib/lzo compression to compress both
-          files, inodes and directories.  Inodes in the system are very small
-          and all blocks are packed to minimise data overhead. Block sizes
-          greater than 4K are supported up to a maximum of 1 Mbytes (default
-          block size 128K).  SquashFS 4.0 supports 64 bit filesystems and files
-          (larger than 4GB), full uid/gid information, hard links and
+          filesystem for Linux.  It uses zlib, lzo or xz compression to
+          compress both files, inodes and directories.  Inodes in the system
+          are very small and all blocks are packed to minimise data overhead.
+          Block sizes greater than 4K are supported up to a maximum of 1 Mbytes
+          (default block size 128K).  SquashFS 4.0 supports 64 bit filesystems
+          and files (larger than 4GB), full uid/gid information, hard links and
           timestamps.
 
           Squashfs is intended for general read-only filesystem use, for
diff --git a/fs/squashfs/decompressor.c b/fs/squashfs/decompressor.c
index a5940e54c4dd..e921bd213738 100644
--- a/fs/squashfs/decompressor.c
+++ b/fs/squashfs/decompressor.c
@@ -23,6 +23,7 @@
 
 #include <linux/types.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
 #include <linux/buffer_head.h>
 
 #include "squashfs_fs.h"
@@ -74,3 +75,36 @@ const struct squashfs_decompressor *squashfs_lookup_decompressor(int id)
 
         return decompressor[i];
 }
+
+
+void *squashfs_decompressor_init(struct super_block *sb, unsigned short flags)
+{
+        struct squashfs_sb_info *msblk = sb->s_fs_info;
+        void *strm, *buffer = NULL;
+        int length = 0;
+
+        /*
+         * Read decompressor specific options from file system if present
+         */
+        if (SQUASHFS_COMP_OPTS(flags)) {
+                buffer = kmalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
+                if (buffer == NULL)
+                        return ERR_PTR(-ENOMEM);
+
+                length = squashfs_read_data(sb, &buffer,
+                        sizeof(struct squashfs_super_block), 0, NULL,
+                        PAGE_CACHE_SIZE, 1);
+
+                if (length < 0) {
+                        strm = ERR_PTR(length);
+                        goto finished;
+                }
+        }
+
+        strm = msblk->decompressor->init(msblk, buffer, length);
+
+finished:
+        kfree(buffer);
+
+        return strm;
+}
diff --git a/fs/squashfs/decompressor.h b/fs/squashfs/decompressor.h
index 3b305a70f7aa..099745ad5691 100644
--- a/fs/squashfs/decompressor.h
+++ b/fs/squashfs/decompressor.h
@@ -24,7 +24,7 @@
  */
 
 struct squashfs_decompressor {
-        void    *(*init)(struct squashfs_sb_info *);
+        void    *(*init)(struct squashfs_sb_info *, void *, int);
         void    (*free)(void *);
         int     (*decompress)(struct squashfs_sb_info *, void **,
                 struct buffer_head **, int, int, int, int, int);
@@ -33,11 +33,6 @@ struct squashfs_decompressor {
         int     supported;
 };
 
-static inline void *squashfs_decompressor_init(struct squashfs_sb_info *msblk)
-{
-        return msblk->decompressor->init(msblk);
-}
-
 static inline void squashfs_decompressor_free(struct squashfs_sb_info *msblk,
         void *s)
 {
diff --git a/fs/squashfs/dir.c b/fs/squashfs/dir.c
index 0dc340aa2be9..3f79cd1d0c19 100644
--- a/fs/squashfs/dir.c
+++ b/fs/squashfs/dir.c
@@ -172,6 +172,11 @@ static int squashfs_readdir(struct file *file, void *dirent, filldir_t filldir)
                 length += sizeof(dirh);
 
                 dir_count = le32_to_cpu(dirh.count) + 1;
+
+                /* dir_count should never be larger than 256 */
+                if (dir_count > 256)
+                        goto failed_read;
+
                 while (dir_count--) {
                         /*
                          * Read directory entry.
@@ -183,6 +188,10 @@ static int squashfs_readdir(struct file *file, void *dirent, filldir_t filldir)
 
                         size = le16_to_cpu(dire->size) + 1;
 
+                        /* size should never be larger than SQUASHFS_NAME_LEN */
+                        if (size > SQUASHFS_NAME_LEN)
+                                goto failed_read;
+
                         err = squashfs_read_metadata(inode->i_sb, dire->name,
                                         &block, &offset, size);
                         if (err < 0)
diff --git a/fs/squashfs/lzo_wrapper.c b/fs/squashfs/lzo_wrapper.c
index 7da759e34c52..00f4dfc5f088 100644
--- a/fs/squashfs/lzo_wrapper.c
+++ b/fs/squashfs/lzo_wrapper.c
@@ -37,7 +37,7 @@ struct squashfs_lzo {
         void    *output;
 };
 
-static void *lzo_init(struct squashfs_sb_info *msblk)
+static void *lzo_init(struct squashfs_sb_info *msblk, void *buff, int len)
 {
         int block_size = max_t(int, msblk->block_size, SQUASHFS_METADATA_SIZE);
 
@@ -58,7 +58,7 @@ failed2:
 failed:
         ERROR("Failed to allocate lzo workspace\n");
         kfree(stream);
-        return NULL;
+        return ERR_PTR(-ENOMEM);
 }
 
 
diff --git a/fs/squashfs/namei.c b/fs/squashfs/namei.c
index 7a9464d08cf6..5d922a6701ab 100644
--- a/fs/squashfs/namei.c
+++ b/fs/squashfs/namei.c
@@ -176,6 +176,11 @@ static struct dentry *squashfs_lookup(struct inode *dir, struct dentry *dentry,
                 length += sizeof(dirh);
 
                 dir_count = le32_to_cpu(dirh.count) + 1;
+
+                /* dir_count should never be larger than 256 */
+                if (dir_count > 256)
+                        goto data_error;
+
                 while (dir_count--) {
                         /*
                          * Read directory entry.
@@ -187,6 +192,10 @@ static struct dentry *squashfs_lookup(struct inode *dir, struct dentry *dentry,
 
                         size = le16_to_cpu(dire->size) + 1;
 
+                        /* size should never be larger than SQUASHFS_NAME_LEN */
+                        if (size > SQUASHFS_NAME_LEN)
+                                goto data_error;
+
                         err = squashfs_read_metadata(dir->i_sb, dire->name,
                                         &block, &offset, size);
                         if (err < 0)
@@ -228,6 +237,9 @@ exit_lookup:
         d_add(dentry, inode);
         return ERR_PTR(0);
 
+data_error:
+        err = -EIO;
+
 read_failure:
         ERROR("Unable to read directory block [%llx:%x]\n",
                 squashfs_i(dir)->start + msblk->directory_table,
diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h
index ba729d808876..1f2e608b8785 100644
--- a/fs/squashfs/squashfs.h
+++ b/fs/squashfs/squashfs.h
@@ -48,6 +48,7 @@ extern int squashfs_read_table(struct super_block *, void *, u64, int);
 
 /* decompressor.c */
 extern const struct squashfs_decompressor *squashfs_lookup_decompressor(int);
+extern void *squashfs_decompressor_init(struct super_block *, unsigned short);
 
 /* export.c */
 extern __le64 *squashfs_read_inode_lookup_table(struct super_block *, u64,
diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h
index 39533feffd6d..4582c568ef4d 100644
--- a/fs/squashfs/squashfs_fs.h
+++ b/fs/squashfs/squashfs_fs.h
@@ -57,6 +57,7 @@
 #define SQUASHFS_ALWAYS_FRAG            5
 #define SQUASHFS_DUPLICATE              6
 #define SQUASHFS_EXPORT                 7
+#define SQUASHFS_COMP_OPT               10
 
 #define SQUASHFS_BIT(flag, bit)         ((flag >> bit) & 1)
 
@@ -81,6 +82,9 @@
 #define SQUASHFS_EXPORTABLE(flags)              SQUASHFS_BIT(flags, \
                                                 SQUASHFS_EXPORT)
 
+#define SQUASHFS_COMP_OPTS(flags)               SQUASHFS_BIT(flags, \
+                                                SQUASHFS_COMP_OPT)
+
 /* Max number of types and file types */
 #define SQUASHFS_DIR_TYPE               1
 #define SQUASHFS_REG_TYPE               2
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 20700b9f2b4c..5c8184c061a4 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -199,10 +199,6 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent)
 
         err = -ENOMEM;
 
-        msblk->stream = squashfs_decompressor_init(msblk);
-        if (msblk->stream == NULL)
-                goto failed_mount;
-
         msblk->block_cache = squashfs_cache_init("metadata",
                         SQUASHFS_CACHED_BLKS, SQUASHFS_METADATA_SIZE);
         if (msblk->block_cache == NULL)
@@ -215,6 +211,13 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent)
                 goto failed_mount;
         }
 
+        msblk->stream = squashfs_decompressor_init(sb, flags);
+        if (IS_ERR(msblk->stream)) {
+                err = PTR_ERR(msblk->stream);
+                msblk->stream = NULL;
+                goto failed_mount;
+        }
+
         /* Allocate and read id index table */
         msblk->id_table = squashfs_read_id_index_table(sb,
                 le64_to_cpu(sblk->id_table_start), le16_to_cpu(sblk->no_ids));
@@ -370,8 +373,8 @@ static void squashfs_put_super(struct super_block *sb)
 }
 
 
-static struct dentry *squashfs_mount(struct file_system_type *fs_type, int flags,
-                                const char *dev_name, void *data)
+static struct dentry *squashfs_mount(struct file_system_type *fs_type,
+                                int flags, const char *dev_name, void *data)
 {
         return mount_bdev(fs_type, flags, dev_name, data, squashfs_fill_super);
 }
diff --git a/fs/squashfs/xz_wrapper.c b/fs/squashfs/xz_wrapper.c
index c4eb40018256..aa47a286d1f8 100644
--- a/fs/squashfs/xz_wrapper.c
+++ b/fs/squashfs/xz_wrapper.c
@@ -26,10 +26,10 @@
 #include <linux/buffer_head.h>
 #include <linux/slab.h>
 #include <linux/xz.h>
+#include <linux/bitops.h>
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
-#include "squashfs_fs_i.h"
 #include "squashfs.h"
 #include "decompressor.h"
 
@@ -38,24 +38,57 @@ struct squashfs_xz {
         struct xz_buf buf;
 };
 
-static void *squashfs_xz_init(struct squashfs_sb_info *msblk)
+struct comp_opts {
+        __le32 dictionary_size;
+        __le32 flags;
+};
+
+static void *squashfs_xz_init(struct squashfs_sb_info *msblk, void *buff,
+        int len)
 {
-        int block_size = max_t(int, msblk->block_size, SQUASHFS_METADATA_SIZE);
+        struct comp_opts *comp_opts = buff;
+        struct squashfs_xz *stream;
+        int dict_size = msblk->block_size;
+        int err, n;
+
+        if (comp_opts) {
+                /* check compressor options are the expected length */
+                if (len < sizeof(*comp_opts)) {
+                        err = -EIO;
+                        goto failed;
+                }
 
-        struct squashfs_xz *stream = kmalloc(sizeof(*stream), GFP_KERNEL);
-        if (stream == NULL)
+                dict_size = le32_to_cpu(comp_opts->dictionary_size);
+
+                /* the dictionary size should be 2^n or 2^n+2^(n+1) */
+                n = ffs(dict_size) - 1;
+                if (dict_size != (1 << n) && dict_size != (1 << n) +
+                                                (1 << (n + 1))) {
+                        err = -EIO;
+                        goto failed;
+                }
+        }
+
+        dict_size = max_t(int, dict_size, SQUASHFS_METADATA_SIZE);
+
+        stream = kmalloc(sizeof(*stream), GFP_KERNEL);
+        if (stream == NULL) {
+                err = -ENOMEM;
                 goto failed;
+        }
 
-        stream->state = xz_dec_init(XZ_PREALLOC, block_size);
-        if (stream->state == NULL)
+        stream->state = xz_dec_init(XZ_PREALLOC, dict_size);
+        if (stream->state == NULL) {
+                kfree(stream);
+                err = -ENOMEM;
                 goto failed;
+        }
 
         return stream;
 
 failed:
-        ERROR("Failed to allocate xz workspace\n");
-        kfree(stream);
-        return NULL;
+        ERROR("Failed to initialise xz decompressor\n");
+        return ERR_PTR(err);
 }
 
 
diff --git a/fs/squashfs/zlib_wrapper.c b/fs/squashfs/zlib_wrapper.c
index 4661ae2b1cec..517688b32ffa 100644
--- a/fs/squashfs/zlib_wrapper.c
+++ b/fs/squashfs/zlib_wrapper.c
@@ -26,19 +26,19 @@
 #include <linux/buffer_head.h>
 #include <linux/slab.h>
 #include <linux/zlib.h>
+#include <linux/vmalloc.h>
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
 #include "squashfs.h"
 #include "decompressor.h"
 
-static void *zlib_init(struct squashfs_sb_info *dummy)
+static void *zlib_init(struct squashfs_sb_info *dummy, void *buff, int len)
 {
         z_stream *stream = kmalloc(sizeof(z_stream), GFP_KERNEL);
         if (stream == NULL)
                 goto failed;
-        stream->workspace = kmalloc(zlib_inflate_workspacesize(),
-                GFP_KERNEL);
+        stream->workspace = vmalloc(zlib_inflate_workspacesize());
         if (stream->workspace == NULL)
                 goto failed;
 
@@ -47,7 +47,7 @@ static void *zlib_init(struct squashfs_sb_info *dummy)
 failed:
         ERROR("Failed to allocate zlib workspace\n");
         kfree(stream);
-        return NULL;
+        return ERR_PTR(-ENOMEM);
 }
 
 
@@ -56,7 +56,7 @@ static void zlib_free(void *strm)
         z_stream *stream = strm;
 
         if (stream)
-                kfree(stream->workspace);
+                vfree(stream->workspace);
         kfree(stream);
 }
 
diff --git a/fs/super.c b/fs/super.c
index 4bae0ef6110e..e84864908264 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -910,29 +910,18 @@ struct dentry *mount_single(struct file_system_type *fs_type,
 }
 EXPORT_SYMBOL(mount_single);
 
-struct vfsmount *
-vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data)
+struct dentry *
+mount_fs(struct file_system_type *type, int flags, const char *name, void *data)
 {
-        struct vfsmount *mnt;
         struct dentry *root;
+        struct super_block *sb;
         char *secdata = NULL;
-        int error;
-
-        if (!type)
-                return ERR_PTR(-ENODEV);
-
-        error = -ENOMEM;
-        mnt = alloc_vfsmnt(name);
-        if (!mnt)
-                goto out;
-
-        if (flags & MS_KERNMOUNT)
-                mnt->mnt_flags = MNT_INTERNAL;
+        int error = -ENOMEM;
 
         if (data && !(type->fs_flags & FS_BINARY_MOUNTDATA)) {
                 secdata = alloc_secdata();
                 if (!secdata)
-                        goto out_mnt;
+                        goto out;
 
                 error = security_sb_copy_data(data, secdata);
                 if (error)
@@ -944,13 +933,12 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void
                 error = PTR_ERR(root);
                 goto out_free_secdata;
         }
-        mnt->mnt_root = root;
-        mnt->mnt_sb = root->d_sb;
-        BUG_ON(!mnt->mnt_sb);
-        WARN_ON(!mnt->mnt_sb->s_bdi);
-        mnt->mnt_sb->s_flags |= MS_BORN;
+        sb = root->d_sb;
+        BUG_ON(!sb);
+        WARN_ON(!sb->s_bdi);
+        sb->s_flags |= MS_BORN;
 
-        error = security_sb_kern_mount(mnt->mnt_sb, flags, secdata);
+        error = security_sb_kern_mount(sb, flags, secdata);
         if (error)
                 goto out_sb;
 
@@ -961,27 +949,21 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void
          * violate this rule. This warning should be either removed or
          * converted to a BUG() in 2.6.34.
          */
-        WARN((mnt->mnt_sb->s_maxbytes < 0), "%s set sb->s_maxbytes to "
-                "negative value (%lld)\n", type->name, mnt->mnt_sb->s_maxbytes);
+        WARN((sb->s_maxbytes < 0), "%s set sb->s_maxbytes to "
+                "negative value (%lld)\n", type->name, sb->s_maxbytes);
 
-        mnt->mnt_mountpoint = mnt->mnt_root;
-        mnt->mnt_parent = mnt;
-        up_write(&mnt->mnt_sb->s_umount);
+        up_write(&sb->s_umount);
         free_secdata(secdata);
-        return mnt;
+        return root;
 out_sb:
-        dput(mnt->mnt_root);
-        deactivate_locked_super(mnt->mnt_sb);
+        dput(root);
+        deactivate_locked_super(sb);
 out_free_secdata:
         free_secdata(secdata);
-out_mnt:
-        free_vfsmnt(mnt);
 out:
         return ERR_PTR(error);
 }
 
-EXPORT_SYMBOL_GPL(vfs_kern_mount);
-
 /**
  * freeze_super - lock the filesystem and force it into a consistent state
  * @sb: the super to lock
@@ -1071,49 +1053,3 @@ out:
         return 0;
 }
 EXPORT_SYMBOL(thaw_super);
-
-static struct vfsmount *fs_set_subtype(struct vfsmount *mnt, const char *fstype)
-{
-        int err;
-        const char *subtype = strchr(fstype, '.');
-        if (subtype) {
-                subtype++;
-                err = -EINVAL;
-                if (!subtype[0])
-                        goto err;
-        } else
-                subtype = "";
-
-        mnt->mnt_sb->s_subtype = kstrdup(subtype, GFP_KERNEL);
-        err = -ENOMEM;
-        if (!mnt->mnt_sb->s_subtype)
-                goto err;
-        return mnt;
-
- err:
-        mntput(mnt);
-        return ERR_PTR(err);
-}
-
-struct vfsmount *
-do_kern_mount(const char *fstype, int flags, const char *name, void *data)
-{
-        struct file_system_type *type = get_fs_type(fstype);
-        struct vfsmount *mnt;
-        if (!type)
-                return ERR_PTR(-ENODEV);
-        mnt = vfs_kern_mount(type, flags, name, data);
-        if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) &&
-            !mnt->mnt_sb->s_subtype)
-                mnt = fs_set_subtype(mnt, fstype);
-        put_filesystem(type);
-        return mnt;
-}
-EXPORT_SYMBOL_GPL(do_kern_mount);
-
-struct vfsmount *kern_mount_data(struct file_system_type *type, void *data)
-{
-        return vfs_kern_mount(type, MS_KERNMOUNT, type->name, data);
-}
-
-EXPORT_SYMBOL_GPL(kern_mount_data);
diff --git a/fs/sync.c b/fs/sync.c
index ba76b9623e7e..92ca208777d5 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -7,6 +7,7 @@
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/namei.h>
 #include <linux/sched.h>
 #include <linux/writeback.h>
 #include <linux/syscalls.h>
@@ -128,6 +129,29 @@ void emergency_sync(void)
         }
 }
 
+/*
+ * sync a single super
+ */
+SYSCALL_DEFINE1(syncfs, int, fd)
+{
+        struct file *file;
+        struct super_block *sb;
+        int ret;
+        int fput_needed;
+
+        file = fget_light(fd, &fput_needed);
+        if (!file)
+                return -EBADF;
+        sb = file->f_dentry->d_sb;
+
+        down_read(&sb->s_umount);
+        ret = sync_filesystem(sb);
+        up_read(&sb->s_umount);
+
+        fput_light(file, fput_needed);
+        return ret;
+}
+
 /**
  * vfs_fsync_range - helper to sync a range of data & metadata to disk
  * @file:               file to sync
diff --git a/fs/ubifs/Kconfig b/fs/ubifs/Kconfig
index 830e3f76f442..d7440904be17 100644
--- a/fs/ubifs/Kconfig
+++ b/fs/ubifs/Kconfig
@@ -44,29 +44,17 @@ config UBIFS_FS_ZLIB
 
 # Debugging-related stuff
 config UBIFS_FS_DEBUG
-        bool "Enable debugging"
+        bool "Enable debugging support"
         depends on UBIFS_FS
         select DEBUG_FS
         select KALLSYMS_ALL
         help
-          This option enables UBIFS debugging.
-
-config UBIFS_FS_DEBUG_MSG_LVL
-        int "Default message level (0 = no extra messages, 3 = lots)"
-        depends on UBIFS_FS_DEBUG
-        default "0"
-        help
-          This controls the amount of debugging messages produced by UBIFS.
-          If reporting bugs, please try to have available a full dump of the
-          messages at level 1 while the misbehaviour was occurring. Level 2
-          may become necessary if level 1 messages were not enough to find the
-          bug. Generally Level 3 should be avoided.
-
-config UBIFS_FS_DEBUG_CHKS
-        bool "Enable extra checks"
-        depends on UBIFS_FS_DEBUG
-        help
-          If extra checks are enabled UBIFS will check the consistency of its
-          internal data structures during operation. However, UBIFS performance
-          is dramatically slower when this option is selected especially if the
-          file system is large.
+          This option enables UBIFS debugging support. It makes sure various
+          assertions, self-checks, debugging messages and test modes are compiled
+          in (this all is compiled out otherwise). Assertions are light-weight
+          and this option also enables them. Self-checks, debugging messages and
+          test modes are switched off by default. Thus, it is safe and actually
+          recommended to have debugging support enabled, and it should not slow
+          down UBIFS. You can then further enable / disable individual  debugging
+          features using UBIFS module parameters and the corresponding sysfs
+          interfaces.
diff --git a/fs/ubifs/commit.c b/fs/ubifs/commit.c
index 02429d81ca33..b148fbc80f8d 100644
--- a/fs/ubifs/commit.c
+++ b/fs/ubifs/commit.c
@@ -48,6 +48,56 @@
 #include <linux/slab.h>
 #include "ubifs.h"
 
+/*
+ * nothing_to_commit - check if there is nothing to commit.
+ * @c: UBIFS file-system description object
+ *
+ * This is a helper function which checks if there is anything to commit. It is
+ * used as an optimization to avoid starting the commit if it is not really
+ * necessary. Indeed, the commit operation always assumes flash I/O (e.g.,
+ * writing the commit start node to the log), and it is better to avoid doing
+ * this unnecessarily. E.g., 'ubifs_sync_fs()' runs the commit, but if there is
+ * nothing to commit, it is more optimal to avoid any flash I/O.
+ *
+ * This function has to be called with @c->commit_sem locked for writing -
+ * this function does not take LPT/TNC locks because the @c->commit_sem
+ * guarantees that we have exclusive access to the TNC and LPT data structures.
+ *
+ * This function returns %1 if there is nothing to commit and %0 otherwise.
+ */
+static int nothing_to_commit(struct ubifs_info *c)
+{
+        /*
+         * During mounting or remounting from R/O mode to R/W mode we may
+         * commit for various recovery-related reasons.
+         */
+        if (c->mounting || c->remounting_rw)
+                return 0;
+
+        /*
+         * If the root TNC node is dirty, we definitely have something to
+         * commit.
+         */
+        if (c->zroot.znode && test_bit(DIRTY_ZNODE, &c->zroot.znode->flags))
+                return 0;
+
+        /*
+         * Even though the TNC is clean, the LPT tree may have dirty nodes. For
+         * example, this may happen if the budgeting subsystem invoked GC to
+         * make some free space, and the GC found an LEB with only dirty and
+         * free space. In this case GC would just change the lprops of this
+         * LEB (by turning all space into free space) and unmap it.
+         */
+        if (c->nroot && test_bit(DIRTY_CNODE, &c->nroot->flags))
+                return 0;
+
+        ubifs_assert(atomic_long_read(&c->dirty_zn_cnt) == 0);
+        ubifs_assert(c->dirty_pn_cnt == 0);
+        ubifs_assert(c->dirty_nn_cnt == 0);
+
+        return 1;
+}
+
 /**
  * do_commit - commit the journal.
  * @c: UBIFS file-system description object
@@ -70,6 +120,12 @@ static int do_commit(struct ubifs_info *c)
                 goto out_up;
         }
 
+        if (nothing_to_commit(c)) {
+                up_write(&c->commit_sem);
+                err = 0;
+                goto out_cancel;
+        }
+
         /* Sync all write buffers (necessary for recovery) */
         for (i = 0; i < c->jhead_cnt; i++) {
                 err = ubifs_wbuf_sync(&c->jheads[i].wbuf);
@@ -162,12 +218,12 @@ static int do_commit(struct ubifs_info *c)
         if (err)
                 goto out;
 
+out_cancel:
         spin_lock(&c->cs_lock);
         c->cmt_state = COMMIT_RESTING;
         wake_up(&c->cmt_wq);
         dbg_cmt("commit end");
         spin_unlock(&c->cs_lock);
-
         return 0;
 
 out_up:
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index 0bee4dbffc31..f25a7339f800 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -43,8 +43,8 @@ DEFINE_SPINLOCK(dbg_lock);
 static char dbg_key_buf0[128];
 static char dbg_key_buf1[128];
 
-unsigned int ubifs_msg_flags = UBIFS_MSG_FLAGS_DEFAULT;
-unsigned int ubifs_chk_flags = UBIFS_CHK_FLAGS_DEFAULT;
+unsigned int ubifs_msg_flags;
+unsigned int ubifs_chk_flags;
 unsigned int ubifs_tst_flags;
 
 module_param_named(debug_msgs, ubifs_msg_flags, uint, S_IRUGO | S_IWUSR);
@@ -810,16 +810,24 @@ void dbg_dump_leb(const struct ubifs_info *c, int lnum)
 {
         struct ubifs_scan_leb *sleb;
         struct ubifs_scan_node *snod;
+        void *buf;
 
         if (dbg_failure_mode)
                 return;
 
         printk(KERN_DEBUG "(pid %d) start dumping LEB %d\n",
                current->pid, lnum);
-        sleb = ubifs_scan(c, lnum, 0, c->dbg->buf, 0);
+
+        buf = __vmalloc(c->leb_size, GFP_NOFS, PAGE_KERNEL);
+        if (!buf) {
+                ubifs_err("cannot allocate memory for dumping LEB %d", lnum);
+                return;
+        }
+
+        sleb = ubifs_scan(c, lnum, 0, buf, 0);
         if (IS_ERR(sleb)) {
                 ubifs_err("scan error %d", (int)PTR_ERR(sleb));
-                return;
+                goto out;
         }
 
         printk(KERN_DEBUG "LEB %d has %d nodes ending at %d\n", lnum,
@@ -835,6 +843,9 @@ void dbg_dump_leb(const struct ubifs_info *c, int lnum)
         printk(KERN_DEBUG "(pid %d) finish dumping LEB %d\n",
                current->pid, lnum);
         ubifs_scan_destroy(sleb);
+
+out:
+        vfree(buf);
         return;
 }
 
@@ -2690,16 +2701,8 @@ int ubifs_debugging_init(struct ubifs_info *c)
         if (!c->dbg)
                 return -ENOMEM;
 
-        c->dbg->buf = vmalloc(c->leb_size);
-        if (!c->dbg->buf)
-                goto out;
-
         failure_mode_init(c);
         return 0;
-
-out:
-        kfree(c->dbg);
-        return -ENOMEM;
 }
 
 /**
@@ -2709,7 +2712,6 @@ out:
 void ubifs_debugging_exit(struct ubifs_info *c)
 {
         failure_mode_exit(c);
-        vfree(c->dbg->buf);
         kfree(c->dbg);
 }
 
@@ -2813,19 +2815,19 @@ int dbg_debugfs_init_fs(struct ubifs_info *c)
         }
 
         fname = "dump_lprops";
-        dent = debugfs_create_file(fname, S_IWUGO, d->dfs_dir, c, &dfs_fops);
+        dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, c, &dfs_fops);
         if (IS_ERR(dent))
                 goto out_remove;
         d->dfs_dump_lprops = dent;
 
         fname = "dump_budg";
-        dent = debugfs_create_file(fname, S_IWUGO, d->dfs_dir, c, &dfs_fops);
+        dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, c, &dfs_fops);
         if (IS_ERR(dent))
                 goto out_remove;
         d->dfs_dump_budg = dent;
 
         fname = "dump_tnc";
-        dent = debugfs_create_file(fname, S_IWUGO, d->dfs_dir, c, &dfs_fops);
+        dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, c, &dfs_fops);
         if (IS_ERR(dent))
                 goto out_remove;
         d->dfs_dump_tnc = dent;
diff --git a/fs/ubifs/debug.h b/fs/ubifs/debug.h
index 69ebe4729151..919f0de29d8f 100644
--- a/fs/ubifs/debug.h
+++ b/fs/ubifs/debug.h
@@ -27,7 +27,6 @@
 
 /**
  * ubifs_debug_info - per-FS debugging information.
- * @buf: a buffer of LEB size, used for various purposes
  * @old_zroot: old index root - used by 'dbg_check_old_index()'
  * @old_zroot_level: old index root level - used by 'dbg_check_old_index()'
  * @old_zroot_sqnum: old index root sqnum - used by 'dbg_check_old_index()'
@@ -54,7 +53,6 @@
  * dfs_dump_tnc: "dump TNC" debugfs knob
  */
 struct ubifs_debug_info {
-        void *buf;
         struct ubifs_zbranch old_zroot;
         int old_zroot_level;
         unsigned long long old_zroot_sqnum;
@@ -173,7 +171,7 @@ const char *dbg_key_str1(const struct ubifs_info *c,
 #define dbg_rcvry(fmt, ...) dbg_do_msg(UBIFS_MSG_RCVRY, fmt, ##__VA_ARGS__)
 
 /*
- * Debugging message type flags (must match msg_type_names in debug.c).
+ * Debugging message type flags.
  *
  * UBIFS_MSG_GEN: general messages
  * UBIFS_MSG_JNL: journal messages
@@ -205,14 +203,8 @@ enum {
         UBIFS_MSG_RCVRY = 0x1000,
 };
 
-/* Debugging message type flags for each default debug message level */
-#define UBIFS_MSG_LVL_0 0
-#define UBIFS_MSG_LVL_1 0x1
-#define UBIFS_MSG_LVL_2 0x7f
-#define UBIFS_MSG_LVL_3 0xffff
-
 /*
- * Debugging check flags (must match chk_names in debug.c).
+ * Debugging check flags.
  *
  * UBIFS_CHK_GEN: general checks
  * UBIFS_CHK_TNC: check TNC
@@ -233,7 +225,7 @@ enum {
 };
 
 /*
- * Special testing flags (must match tst_names in debug.c).
+ * Special testing flags.
  *
  * UBIFS_TST_FORCE_IN_THE_GAPS: force the use of in-the-gaps method
  * UBIFS_TST_RCVRY: failure mode for recovery testing
@@ -243,22 +235,6 @@ enum {
         UBIFS_TST_RCVRY             = 0x4,
 };
 
-#if CONFIG_UBIFS_FS_DEBUG_MSG_LVL == 1
-#define UBIFS_MSG_FLAGS_DEFAULT UBIFS_MSG_LVL_1
-#elif CONFIG_UBIFS_FS_DEBUG_MSG_LVL == 2
-#define UBIFS_MSG_FLAGS_DEFAULT UBIFS_MSG_LVL_2
-#elif CONFIG_UBIFS_FS_DEBUG_MSG_LVL == 3
-#define UBIFS_MSG_FLAGS_DEFAULT UBIFS_MSG_LVL_3
-#else
-#define UBIFS_MSG_FLAGS_DEFAULT UBIFS_MSG_LVL_0
-#endif
-
-#ifdef CONFIG_UBIFS_FS_DEBUG_CHKS
-#define UBIFS_CHK_FLAGS_DEFAULT 0xffffffff
-#else
-#define UBIFS_CHK_FLAGS_DEFAULT 0
-#endif
-
 extern spinlock_t dbg_lock;
 
 extern unsigned int ubifs_msg_flags;
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index d77db7e36484..28be1e6a65e8 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -448,10 +448,12 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping,
                 if (!(pos & ~PAGE_CACHE_MASK) && len == PAGE_CACHE_SIZE) {
                         /*
                          * We change whole page so no need to load it. But we
-                         * have to set the @PG_checked flag to make the further
-                         * code know that the page is new. This might be not
-                         * true, but it is better to budget more than to read
-                         * the page from the media.
+                         * do not know whether this page exists on the media or
+                         * not, so we assume the latter because it requires
+                         * larger budget. The assumption is that it is better
+                         * to budget a bit more than to read the page from the
+                         * media. Thus, we are setting the @PG_checked flag
+                         * here.
                          */
                         SetPageChecked(page);
                         skipped_read = 1;
@@ -559,6 +561,7 @@ static int ubifs_write_end(struct file *file, struct address_space *mapping,
                 dbg_gen("copied %d instead of %d, read page and repeat",
                         copied, len);
                 cancel_budget(c, page, ui, appending);
+                ClearPageChecked(page);
 
                 /*
                  * Return 0 to force VFS to repeat the whole operation, or the
diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c
index d82173182eeb..dfd168b7807e 100644
--- a/fs/ubifs/io.c
+++ b/fs/ubifs/io.c
@@ -31,6 +31,26 @@
  * buffer is full or when it is not used for some time (by timer). This is
  * similar to the mechanism is used by JFFS2.
  *
+ * UBIFS distinguishes between minimum write size (@c->min_io_size) and maximum
+ * write size (@c->max_write_size). The latter is the maximum amount of bytes
+ * the underlying flash is able to program at a time, and writing in
+ * @c->max_write_size units should presumably be faster. Obviously,
+ * @c->min_io_size <= @c->max_write_size. Write-buffers are of
+ * @c->max_write_size bytes in size for maximum performance. However, when a
+ * write-buffer is flushed, only the portion of it (aligned to @c->min_io_size
+ * boundary) which contains data is written, not the whole write-buffer,
+ * because this is more space-efficient.
+ *
+ * This optimization adds few complications to the code. Indeed, on the one
+ * hand, we want to write in optimal @c->max_write_size bytes chunks, which
+ * also means aligning writes at the @c->max_write_size bytes offsets. On the
+ * other hand, we do not want to waste space when synchronizing the write
+ * buffer, so during synchronization we writes in smaller chunks. And this makes
+ * the next write offset to be not aligned to @c->max_write_size bytes. So the
+ * have to make sure that the write-buffer offset (@wbuf->offs) becomes aligned
+ * to @c->max_write_size bytes again. We do this by temporarily shrinking
+ * write-buffer size (@wbuf->size).
+ *
  * Write-buffers are defined by 'struct ubifs_wbuf' objects and protected by
  * mutexes defined inside these objects. Since sometimes upper-level code
  * has to lock the write-buffer (e.g. journal space reservation code), many
@@ -46,8 +66,8 @@
  * UBIFS uses padding when it pads to the next min. I/O unit. In this case it
  * uses padding nodes or padding bytes, if the padding node does not fit.
  *
- * All UBIFS nodes are protected by CRC checksums and UBIFS checks all nodes
- * every time they are read from the flash media.
+ * All UBIFS nodes are protected by CRC checksums and UBIFS checks CRC when
+ * they are read from the flash media.
  */
 
 #include <linux/crc32.h>
@@ -88,8 +108,12 @@ void ubifs_ro_mode(struct ubifs_info *c, int err)
  * This function may skip data nodes CRC checking if @c->no_chk_data_crc is
  * true, which is controlled by corresponding UBIFS mount option. However, if
  * @must_chk_crc is true, then @c->no_chk_data_crc is ignored and CRC is
- * checked. Similarly, if @c->always_chk_crc is true, @c->no_chk_data_crc is
- * ignored and CRC is checked.
+ * checked. Similarly, if @c->mounting or @c->remounting_rw is true (we are
+ * mounting or re-mounting to R/W mode), @c->no_chk_data_crc is ignored and CRC
+ * is checked. This is because during mounting or re-mounting from R/O mode to
+ * R/W mode we may read journal nodes (when replying the journal or doing the
+ * recovery) and the journal nodes may potentially be corrupted, so checking is
+ * required.
  *
  * This function returns zero in case of success and %-EUCLEAN in case of bad
  * CRC or magic.
@@ -131,8 +155,8 @@ 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 (!must_chk_crc && type == UBIFS_DATA_NODE && !c->always_chk_crc &&
-             c->no_chk_data_crc)
+        if (!must_chk_crc && type == UBIFS_DATA_NODE && !c->mounting &&
+            !c->remounting_rw && c->no_chk_data_crc)
                 return 0;
 
         crc = crc32(UBIFS_CRC32_INIT, buf + 8, node_len - 8);
@@ -343,11 +367,17 @@ static void cancel_wbuf_timer_nolock(struct ubifs_wbuf *wbuf)
  *
  * This function synchronizes write-buffer @buf and returns zero in case of
  * success or a negative error code in case of failure.
+ *
+ * Note, although write-buffers are of @c->max_write_size, this function does
+ * not necessarily writes all @c->max_write_size bytes to the flash. Instead,
+ * if the write-buffer is only partially filled with data, only the used part
+ * of the write-buffer (aligned on @c->min_io_size boundary) is synchronized.
+ * This way we waste less space.
  */
 int ubifs_wbuf_sync_nolock(struct ubifs_wbuf *wbuf)
 {
         struct ubifs_info *c = wbuf->c;
-        int err, dirt;
+        int err, dirt, sync_len;
 
         cancel_wbuf_timer_nolock(wbuf);
         if (!wbuf->used || wbuf->lnum == -1)
@@ -357,27 +387,53 @@ int ubifs_wbuf_sync_nolock(struct ubifs_wbuf *wbuf)
         dbg_io("LEB %d:%d, %d bytes, jhead %s",
                wbuf->lnum, wbuf->offs, wbuf->used, dbg_jhead(wbuf->jhead));
         ubifs_assert(!(wbuf->avail & 7));
-        ubifs_assert(wbuf->offs + c->min_io_size <= c->leb_size);
+        ubifs_assert(wbuf->offs + wbuf->size <= c->leb_size);
+        ubifs_assert(wbuf->size >= c->min_io_size);
+        ubifs_assert(wbuf->size <= c->max_write_size);
+        ubifs_assert(wbuf->size % c->min_io_size == 0);
         ubifs_assert(!c->ro_media && !c->ro_mount);
+        if (c->leb_size - wbuf->offs >= c->max_write_size)
+                ubifs_assert(!((wbuf->offs + wbuf->size) % c->max_write_size ));
 
         if (c->ro_error)
                 return -EROFS;
 
-        ubifs_pad(c, wbuf->buf + wbuf->used, wbuf->avail);
+        /*
+         * Do not write whole write buffer but write only the minimum necessary
+         * amount of min. I/O units.
+         */
+        sync_len = ALIGN(wbuf->used, c->min_io_size);
+        dirt = sync_len - wbuf->used;
+        if (dirt)
+                ubifs_pad(c, wbuf->buf + wbuf->used, dirt);
         err = ubi_leb_write(c->ubi, wbuf->lnum, wbuf->buf, wbuf->offs,
-                            c->min_io_size, wbuf->dtype);
+                            sync_len, wbuf->dtype);
         if (err) {
                 ubifs_err("cannot write %d bytes to LEB %d:%d",
-                          c->min_io_size, wbuf->lnum, wbuf->offs);
+                          sync_len, wbuf->lnum, wbuf->offs);
                 dbg_dump_stack();
                 return err;
         }
 
-        dirt = wbuf->avail;
-
         spin_lock(&wbuf->lock);
-        wbuf->offs += c->min_io_size;
-        wbuf->avail = c->min_io_size;
+        wbuf->offs += sync_len;
+        /*
+         * Now @wbuf->offs is not necessarily aligned to @c->max_write_size.
+         * But our goal is to optimize writes and make sure we write in
+         * @c->max_write_size chunks and to @c->max_write_size-aligned offset.
+         * Thus, if @wbuf->offs is not aligned to @c->max_write_size now, make
+         * sure that @wbuf->offs + @wbuf->size is aligned to
+         * @c->max_write_size. This way we make sure that after next
+         * write-buffer flush we are again at the optimal offset (aligned to
+         * @c->max_write_size).
+         */
+        if (c->leb_size - wbuf->offs < c->max_write_size)
+                wbuf->size = c->leb_size - wbuf->offs;
+        else if (wbuf->offs & (c->max_write_size - 1))
+                wbuf->size = ALIGN(wbuf->offs, c->max_write_size) - wbuf->offs;
+        else
+                wbuf->size = c->max_write_size;
+        wbuf->avail = wbuf->size;
         wbuf->used = 0;
         wbuf->next_ino = 0;
         spin_unlock(&wbuf->lock);
@@ -420,7 +476,13 @@ int ubifs_wbuf_seek_nolock(struct ubifs_wbuf *wbuf, int lnum, int offs,
         spin_lock(&wbuf->lock);
         wbuf->lnum = lnum;
         wbuf->offs = offs;
-        wbuf->avail = c->min_io_size;
+        if (c->leb_size - wbuf->offs < c->max_write_size)
+                wbuf->size = c->leb_size - wbuf->offs;
+        else if (wbuf->offs & (c->max_write_size - 1))
+                wbuf->size = ALIGN(wbuf->offs, c->max_write_size) - wbuf->offs;
+        else
+                wbuf->size = c->max_write_size;
+        wbuf->avail = wbuf->size;
         wbuf->used = 0;
         spin_unlock(&wbuf->lock);
         wbuf->dtype = dtype;
@@ -500,8 +562,9 @@ out_timers:
  *
  * This function writes data to flash via write-buffer @wbuf. This means that
  * the last piece of the node won't reach the flash media immediately if it
- * does not take whole minimal I/O unit. Instead, the node will sit in RAM
- * until the write-buffer is synchronized (e.g., by timer).
+ * does not take whole max. write unit (@c->max_write_size). Instead, the node
+ * will sit in RAM until the write-buffer is synchronized (e.g., by timer, or
+ * because more data are appended to the write-buffer).
  *
  * This function returns zero in case of success and a negative error code in
  * case of failure. If the node cannot be written because there is no more
@@ -518,9 +581,14 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len)
         ubifs_assert(len > 0 && wbuf->lnum >= 0 && wbuf->lnum < c->leb_cnt);
         ubifs_assert(wbuf->offs >= 0 && wbuf->offs % c->min_io_size == 0);
         ubifs_assert(!(wbuf->offs & 7) && wbuf->offs <= c->leb_size);
-        ubifs_assert(wbuf->avail > 0 && wbuf->avail <= c->min_io_size);
+        ubifs_assert(wbuf->avail > 0 && wbuf->avail <= wbuf->size);
+        ubifs_assert(wbuf->size >= c->min_io_size);
+        ubifs_assert(wbuf->size <= c->max_write_size);
+        ubifs_assert(wbuf->size % c->min_io_size == 0);
         ubifs_assert(mutex_is_locked(&wbuf->io_mutex));
         ubifs_assert(!c->ro_media && !c->ro_mount);
+        if (c->leb_size - wbuf->offs >= c->max_write_size)
+                ubifs_assert(!((wbuf->offs + wbuf->size) % c->max_write_size ));
 
         if (c->leb_size - wbuf->offs - wbuf->used < aligned_len) {
                 err = -ENOSPC;
@@ -543,14 +611,18 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len)
                         dbg_io("flush jhead %s wbuf to LEB %d:%d",
                                dbg_jhead(wbuf->jhead), wbuf->lnum, wbuf->offs);
                         err = ubi_leb_write(c->ubi, wbuf->lnum, wbuf->buf,
-                                            wbuf->offs, c->min_io_size,
+                                            wbuf->offs, wbuf->size,
                                             wbuf->dtype);
                         if (err)
                                 goto out;
 
                         spin_lock(&wbuf->lock);
-                        wbuf->offs += c->min_io_size;
-                        wbuf->avail = c->min_io_size;
+                        wbuf->offs += wbuf->size;
+                        if (c->leb_size - wbuf->offs >= c->max_write_size)
+                                wbuf->size = c->max_write_size;
+                        else
+                                wbuf->size = c->leb_size - wbuf->offs;
+                        wbuf->avail = wbuf->size;
                         wbuf->used = 0;
                         wbuf->next_ino = 0;
                         spin_unlock(&wbuf->lock);
@@ -564,33 +636,57 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len)
                 goto exit;
         }
 
-        /*
-         * The node is large enough and does not fit entirely within current
-         * minimal I/O unit. We have to fill and flush write-buffer and switch
-         * to the next min. I/O unit.
-         */
-        dbg_io("flush jhead %s wbuf to LEB %d:%d",
-               dbg_jhead(wbuf->jhead), wbuf->lnum, wbuf->offs);
-        memcpy(wbuf->buf + wbuf->used, buf, wbuf->avail);
-        err = ubi_leb_write(c->ubi, wbuf->lnum, wbuf->buf, wbuf->offs,
-                            c->min_io_size, wbuf->dtype);
-        if (err)
-                goto out;
+        offs = wbuf->offs;
+        written = 0;
 
-        offs = wbuf->offs + c->min_io_size;
-        len -= wbuf->avail;
-        aligned_len -= wbuf->avail;
-        written = wbuf->avail;
+        if (wbuf->used) {
+                /*
+                 * The node is large enough and does not fit entirely within
+                 * current available space. We have to fill and flush
+                 * write-buffer and switch to the next max. write unit.
+                 */
+                dbg_io("flush jhead %s wbuf to LEB %d:%d",
+                       dbg_jhead(wbuf->jhead), wbuf->lnum, wbuf->offs);
+                memcpy(wbuf->buf + wbuf->used, buf, wbuf->avail);
+                err = ubi_leb_write(c->ubi, wbuf->lnum, wbuf->buf, wbuf->offs,
+                                    wbuf->size, wbuf->dtype);
+                if (err)
+                        goto out;
+
+                offs += wbuf->size;
+                len -= wbuf->avail;
+                aligned_len -= wbuf->avail;
+                written += wbuf->avail;
+        } else if (wbuf->offs & (c->max_write_size - 1)) {
+                /*
+                 * The write-buffer offset is not aligned to
+                 * @c->max_write_size and @wbuf->size is less than
+                 * @c->max_write_size. Write @wbuf->size bytes to make sure the
+                 * following writes are done in optimal @c->max_write_size
+                 * chunks.
+                 */
+                dbg_io("write %d bytes to LEB %d:%d",
+                       wbuf->size, wbuf->lnum, wbuf->offs);
+                err = ubi_leb_write(c->ubi, wbuf->lnum, buf, wbuf->offs,
+                                    wbuf->size, wbuf->dtype);
+                if (err)
+                        goto out;
+
+                offs += wbuf->size;
+                len -= wbuf->size;
+                aligned_len -= wbuf->size;
+                written += wbuf->size;
+        }
 
         /*
-         * The remaining data may take more whole min. I/O units, so write the
-         * remains multiple to min. I/O unit size directly to the flash media.
+         * The remaining data may take more whole max. write units, so write the
+         * remains multiple to max. write unit size directly to the flash media.
          * We align node length to 8-byte boundary because we anyway flash wbuf
          * if the remaining space is less than 8 bytes.
          */
-        n = aligned_len >> c->min_io_shift;
+        n = aligned_len >> c->max_write_shift;
         if (n) {
-                n <<= c->min_io_shift;
+                n <<= c->max_write_shift;
                 dbg_io("write %d bytes to LEB %d:%d", n, wbuf->lnum, offs);
                 err = ubi_leb_write(c->ubi, wbuf->lnum, buf + written, offs, n,
                                     wbuf->dtype);
@@ -606,14 +702,18 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len)
         if (aligned_len)
                 /*
                  * And now we have what's left and what does not take whole
-                 * min. I/O unit, so write it to the write-buffer and we are
+                 * max. write unit, so write it to the write-buffer and we are
                  * done.
                  */
                 memcpy(wbuf->buf, buf + written, len);
 
         wbuf->offs = offs;
+        if (c->leb_size - wbuf->offs >= c->max_write_size)
+                wbuf->size = c->max_write_size;
+        else
+                wbuf->size = c->leb_size - wbuf->offs;
+        wbuf->avail = wbuf->size - aligned_len;
         wbuf->used = aligned_len;
-        wbuf->avail = c->min_io_size - aligned_len;
         wbuf->next_ino = 0;
         spin_unlock(&wbuf->lock);
 
@@ -837,11 +937,11 @@ int ubifs_wbuf_init(struct ubifs_info *c, struct ubifs_wbuf *wbuf)
 {
         size_t size;
 
-        wbuf->buf = kmalloc(c->min_io_size, GFP_KERNEL);
+        wbuf->buf = kmalloc(c->max_write_size, GFP_KERNEL);
         if (!wbuf->buf)
                 return -ENOMEM;
 
-        size = (c->min_io_size / UBIFS_CH_SZ + 1) * sizeof(ino_t);
+        size = (c->max_write_size / UBIFS_CH_SZ + 1) * sizeof(ino_t);
         wbuf->inodes = kmalloc(size, GFP_KERNEL);
         if (!wbuf->inodes) {
                 kfree(wbuf->buf);
@@ -851,7 +951,14 @@ int ubifs_wbuf_init(struct ubifs_info *c, struct ubifs_wbuf *wbuf)
 
         wbuf->used = 0;
         wbuf->lnum = wbuf->offs = -1;
-        wbuf->avail = c->min_io_size;
+        /*
+         * If the LEB starts at the max. write size aligned address, then
+         * write-buffer size has to be set to @c->max_write_size. Otherwise,
+         * set it to something smaller so that it ends at the closest max.
+         * write size boundary.
+         */
+        size = c->max_write_size - (c->leb_start % c->max_write_size);
+        wbuf->avail = wbuf->size = size;
         wbuf->dtype = UBI_UNKNOWN;
         wbuf->sync_callback = NULL;
         mutex_init(&wbuf->io_mutex);
diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c
index 8aacd64957a2..548acf494afd 100644
--- a/fs/ubifs/ioctl.c
+++ b/fs/ubifs/ioctl.c
@@ -160,7 +160,7 @@ long ubifs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
                 if (IS_RDONLY(inode))
                         return -EROFS;
 
-                if (!is_owner_or_cap(inode))
+                if (!inode_owner_or_capable(inode))
                         return -EACCES;
 
                 if (get_user(flags, (int __user *) arg))
diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c
index 914f1bd89e57..aed25e864227 100644
--- a/fs/ubifs/journal.c
+++ b/fs/ubifs/journal.c
@@ -690,7 +690,7 @@ int ubifs_jnl_write_data(struct ubifs_info *c, const struct inode *inode,
 {
         struct ubifs_data_node *data;
         int err, lnum, offs, compr_type, out_len;
-        int dlen = UBIFS_DATA_NODE_SZ + UBIFS_BLOCK_SIZE * WORST_COMPR_FACTOR;
+        int dlen = COMPRESSED_DATA_NODE_BUF_SZ, allocated = 1;
         struct ubifs_inode *ui = ubifs_inode(inode);
 
         dbg_jnl("ino %lu, blk %u, len %d, key %s",
@@ -698,9 +698,19 @@ int ubifs_jnl_write_data(struct ubifs_info *c, const struct inode *inode,
                 DBGKEY(key));
         ubifs_assert(len <= UBIFS_BLOCK_SIZE);
 
-        data = kmalloc(dlen, GFP_NOFS);
-        if (!data)
-                return -ENOMEM;
+        data = kmalloc(dlen, GFP_NOFS | __GFP_NOWARN);
+        if (!data) {
+                /*
+                 * Fall-back to the write reserve buffer. Note, we might be
+                 * currently on the memory reclaim path, when the kernel is
+                 * trying to free some memory by writing out dirty pages. The
+                 * write reserve buffer helps us to guarantee that we are
+                 * always able to write the data.
+                 */
+                allocated = 0;
+                mutex_lock(&c->write_reserve_mutex);
+                data = c->write_reserve_buf;
+        }
 
         data->ch.node_type = UBIFS_DATA_NODE;
         key_write(c, key, &data->key);
@@ -736,7 +746,10 @@ int ubifs_jnl_write_data(struct ubifs_info *c, const struct inode *inode,
                 goto out_ro;
 
         finish_reservation(c);
-        kfree(data);
+        if (!allocated)
+                mutex_unlock(&c->write_reserve_mutex);
+        else
+                kfree(data);
         return 0;
 
 out_release:
@@ -745,7 +758,10 @@ out_ro:
         ubifs_ro_mode(c, err);
         finish_reservation(c);
 out_free:
-        kfree(data);
+        if (!allocated)
+                mutex_unlock(&c->write_reserve_mutex);
+        else
+                kfree(data);
         return err;
 }
 
diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c
index 4d4ca388889b..0ee0847f2421 100644
--- a/fs/ubifs/lprops.c
+++ b/fs/ubifs/lprops.c
@@ -1035,7 +1035,8 @@ static int scan_check_cb(struct ubifs_info *c,
         struct ubifs_scan_leb *sleb;
         struct ubifs_scan_node *snod;
         struct ubifs_lp_stats *lst = &data->lst;
-        int cat, lnum = lp->lnum, is_idx = 0, used = 0, free, dirty;
+        int cat, lnum = lp->lnum, is_idx = 0, used = 0, free, dirty, ret;
+        void *buf = NULL;
 
         cat = lp->flags & LPROPS_CAT_MASK;
         if (cat != LPROPS_UNCAT) {
@@ -1093,7 +1094,13 @@ static int scan_check_cb(struct ubifs_info *c,
                 }
         }
 
-        sleb = ubifs_scan(c, lnum, 0, c->dbg->buf, 0);
+        buf = __vmalloc(c->leb_size, GFP_NOFS, PAGE_KERNEL);
+        if (!buf) {
+                ubifs_err("cannot allocate memory to scan LEB %d", lnum);
+                goto out;
+        }
+
+        sleb = ubifs_scan(c, lnum, 0, buf, 0);
         if (IS_ERR(sleb)) {
                 /*
                  * After an unclean unmount, empty and freeable LEBs
@@ -1105,7 +1112,8 @@ static int scan_check_cb(struct ubifs_info *c,
                         lst->empty_lebs += 1;
                         lst->total_free += c->leb_size;
                         lst->total_dark += ubifs_calc_dark(c, c->leb_size);
-                        return LPT_SCAN_CONTINUE;
+                        ret = LPT_SCAN_CONTINUE;
+                        goto exit;
                 }
 
                 if (lp->free + lp->dirty == c->leb_size &&
@@ -1115,10 +1123,12 @@ static int scan_check_cb(struct ubifs_info *c,
                         lst->total_free  += lp->free;
                         lst->total_dirty += lp->dirty;
                         lst->total_dark  +=  ubifs_calc_dark(c, c->leb_size);
-                        return LPT_SCAN_CONTINUE;
+                        ret = LPT_SCAN_CONTINUE;
+                        goto exit;
                 }
                 data->err = PTR_ERR(sleb);
-                return LPT_SCAN_STOP;
+                ret = LPT_SCAN_STOP;
+                goto exit;
         }
 
         is_idx = -1;
@@ -1236,7 +1246,10 @@ static int scan_check_cb(struct ubifs_info *c,
         }
 
         ubifs_scan_destroy(sleb);
-        return LPT_SCAN_CONTINUE;
+        ret = LPT_SCAN_CONTINUE;
+exit:
+        vfree(buf);
+        return ret;
 
 out_print:
         ubifs_err("bad accounting of LEB %d: free %d, dirty %d flags %#x, "
@@ -1246,6 +1259,7 @@ out_print:
 out_destroy:
         ubifs_scan_destroy(sleb);
 out:
+        vfree(buf);
         data->err = -EINVAL;
         return LPT_SCAN_STOP;
 }
diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c
index 5c90dec5db0b..0c9c69bd983a 100644
--- a/fs/ubifs/lpt_commit.c
+++ b/fs/ubifs/lpt_commit.c
@@ -1628,29 +1628,35 @@ static int dbg_check_ltab_lnum(struct ubifs_info *c, int lnum)
 {
         int err, len = c->leb_size, dirty = 0, node_type, node_num, node_len;
         int ret;
-        void *buf = c->dbg->buf;
+        void *buf, *p;
 
         if (!(ubifs_chk_flags & UBIFS_CHK_LPROPS))
                 return 0;
 
+        buf = p = __vmalloc(c->leb_size, GFP_NOFS, PAGE_KERNEL);
+        if (!buf) {
+                ubifs_err("cannot allocate memory for ltab checking");
+                return 0;
+        }
+
         dbg_lp("LEB %d", lnum);
         err = ubi_read(c->ubi, lnum, buf, 0, c->leb_size);
         if (err) {
                 dbg_msg("ubi_read failed, LEB %d, error %d", lnum, err);
-                return err;
+                goto out;
         }
         while (1) {
-                if (!is_a_node(c, buf, len)) {
+                if (!is_a_node(c, p, len)) {
                         int i, pad_len;
 
-                        pad_len = get_pad_len(c, buf, len);
+                        pad_len = get_pad_len(c, p, len);
                         if (pad_len) {
-                                buf += pad_len;
+                                p += pad_len;
                                 len -= pad_len;
                                 dirty += pad_len;
                                 continue;
                         }
-                        if (!dbg_is_all_ff(buf, len)) {
+                        if (!dbg_is_all_ff(p, len)) {
                                 dbg_msg("invalid empty space in LEB %d at %d",
                                         lnum, c->leb_size - len);
                                 err = -EINVAL;
@@ -1668,16 +1674,21 @@ static int dbg_check_ltab_lnum(struct ubifs_info *c, int lnum)
                                         lnum, dirty, c->ltab[i].dirty);
                                 err = -EINVAL;
                         }
-                        return err;
+                        goto out;
                 }
-                node_type = get_lpt_node_type(c, buf, &node_num);
+                node_type = get_lpt_node_type(c, p, &node_num);
                 node_len = get_lpt_node_len(c, node_type);
                 ret = dbg_is_node_dirty(c, node_type, lnum, c->leb_size - len);
                 if (ret == 1)
                         dirty += node_len;
-                buf += node_len;
+                p += node_len;
                 len -= node_len;
         }
+
+        err = 0;
+out:
+        vfree(buf);
+        return err;
 }
 
 /**
@@ -1870,25 +1881,31 @@ int dbg_chk_lpt_sz(struct ubifs_info *c, int action, int len)
 static void dump_lpt_leb(const struct ubifs_info *c, int lnum)
 {
         int err, len = c->leb_size, node_type, node_num, node_len, offs;
-        void *buf = c->dbg->buf;
+        void *buf, *p;
 
         printk(KERN_DEBUG "(pid %d) start dumping LEB %d\n",
                current->pid, lnum);
+        buf = p = __vmalloc(c->leb_size, GFP_NOFS, PAGE_KERNEL);
+        if (!buf) {
+                ubifs_err("cannot allocate memory to dump LPT");
+                return;
+        }
+
         err = ubi_read(c->ubi, lnum, buf, 0, c->leb_size);
         if (err) {
                 ubifs_err("cannot read LEB %d, error %d", lnum, err);
-                return;
+                goto out;
         }
         while (1) {
                 offs = c->leb_size - len;
-                if (!is_a_node(c, buf, len)) {
+                if (!is_a_node(c, p, len)) {
                         int pad_len;
 
-                        pad_len = get_pad_len(c, buf, len);
+                        pad_len = get_pad_len(c, p, len);
                         if (pad_len) {
                                 printk(KERN_DEBUG "LEB %d:%d, pad %d bytes\n",
                                        lnum, offs, pad_len);
-                                buf += pad_len;
+                                p += pad_len;
                                 len -= pad_len;
                                 continue;
                         }
@@ -1898,7 +1915,7 @@ static void dump_lpt_leb(const struct ubifs_info *c, int lnum)
                         break;
                 }
 
-                node_type = get_lpt_node_type(c, buf, &node_num);
+                node_type = get_lpt_node_type(c, p, &node_num);
                 switch (node_type) {
                 case UBIFS_LPT_PNODE:
                 {
@@ -1923,7 +1940,7 @@ static void dump_lpt_leb(const struct ubifs_info *c, int lnum)
                         else
                                 printk(KERN_DEBUG "LEB %d:%d, nnode, ",
                                        lnum, offs);
-                        err = ubifs_unpack_nnode(c, buf, &nnode);
+                        err = ubifs_unpack_nnode(c, p, &nnode);
                         for (i = 0; i < UBIFS_LPT_FANOUT; i++) {
                                 printk(KERN_CONT "%d:%d", nnode.nbranch[i].lnum,
                                        nnode.nbranch[i].offs);
@@ -1944,15 +1961,18 @@ static void dump_lpt_leb(const struct ubifs_info *c, int lnum)
                         break;
                 default:
                         ubifs_err("LPT node type %d not recognized", node_type);
-                        return;
+                        goto out;
                 }
 
-                buf += node_len;
+                p += node_len;
                 len -= node_len;
         }
 
         printk(KERN_DEBUG "(pid %d) finish dumping LEB %d\n",
                current->pid, lnum);
+out:
+        vfree(buf);
+        return;
 }
 
 /**
diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c
index 82009c74b6a3..09df318e368f 100644
--- a/fs/ubifs/orphan.c
+++ b/fs/ubifs/orphan.c
@@ -892,15 +892,22 @@ static int dbg_read_orphans(struct check_info *ci, struct ubifs_scan_leb *sleb)
 static int dbg_scan_orphans(struct ubifs_info *c, struct check_info *ci)
 {
         int lnum, err = 0;
+        void *buf;
 
         /* Check no-orphans flag and skip this if no orphans */
         if (c->no_orphs)
                 return 0;
 
+        buf = __vmalloc(c->leb_size, GFP_NOFS, PAGE_KERNEL);
+        if (!buf) {
+                ubifs_err("cannot allocate memory to check orphans");
+                return 0;
+        }
+
         for (lnum = c->orph_first; lnum <= c->orph_last; lnum++) {
                 struct ubifs_scan_leb *sleb;
 
-                sleb = ubifs_scan(c, lnum, 0, c->dbg->buf, 0);
+                sleb = ubifs_scan(c, lnum, 0, buf, 0);
                 if (IS_ERR(sleb)) {
                         err = PTR_ERR(sleb);
                         break;
@@ -912,6 +919,7 @@ static int dbg_scan_orphans(struct ubifs_info *c, struct check_info *ci)
                         break;
         }
 
+        vfree(buf);
         return err;
 }
 
diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c
index 77e9b874b6c2..936f2cbfe6b6 100644
--- a/fs/ubifs/recovery.c
+++ b/fs/ubifs/recovery.c
@@ -28,6 +28,23 @@
  * UBIFS always cleans away all remnants of an unclean un-mount, so that
  * errors do not accumulate. However UBIFS defers recovery if it is mounted
  * read-only, and the flash is not modified in that case.
+ *
+ * The general UBIFS approach to the recovery is that it recovers from
+ * corruptions which could be caused by power cuts, but it refuses to recover
+ * from corruption caused by other reasons. And UBIFS tries to distinguish
+ * between these 2 reasons of corruptions and silently recover in the former
+ * case and loudly complain in the latter case.
+ *
+ * UBIFS writes only to erased LEBs, so it writes only to the flash space
+ * containing only 0xFFs. UBIFS also always writes strictly from the beginning
+ * of the LEB to the end. And UBIFS assumes that the underlying flash media
+ * writes in @c->max_write_size bytes at a time.
+ *
+ * Hence, if UBIFS finds a corrupted node at offset X, it expects only the min.
+ * I/O unit corresponding to offset X to contain corrupted data, all the
+ * following min. I/O units have to contain empty space (all 0xFFs). If this is
+ * not true, the corruption cannot be the result of a power cut, and UBIFS
+ * refuses to mount.
  */
 
 #include <linux/crc32.h>
@@ -362,8 +379,9 @@ int ubifs_write_rcvrd_mst_node(struct ubifs_info *c)
  * @offs: offset to check
  *
  * This function returns %1 if @offs was in the last write to the LEB whose data
- * is in @buf, otherwise %0 is returned.  The determination is made by checking
- * for subsequent empty space starting from the next @c->min_io_size boundary.
+ * is in @buf, otherwise %0 is returned. The determination is made by checking
+ * for subsequent empty space starting from the next @c->max_write_size
+ * boundary.
  */
 static int is_last_write(const struct ubifs_info *c, void *buf, int offs)
 {
@@ -371,10 +389,10 @@ static int is_last_write(const struct ubifs_info *c, void *buf, int offs)
         uint8_t *p;
 
         /*
-         * Round up to the next @c->min_io_size boundary i.e. @offs is in the
-         * last wbuf written. After that should be empty space.
+         * Round up to the next @c->max_write_size boundary i.e. @offs is in
+         * the last wbuf written. After that should be empty space.
          */
-        empty_offs = ALIGN(offs + 1, c->min_io_size);
+        empty_offs = ALIGN(offs + 1, c->max_write_size);
         check_len = c->leb_size - empty_offs;
         p = buf + empty_offs - offs;
         return is_empty(p, check_len);
@@ -429,7 +447,7 @@ static int no_more_nodes(const struct ubifs_info *c, void *buf, int len,
         int skip, dlen = le32_to_cpu(ch->len);
 
         /* Check for empty space after the corrupt node's common header */
-        skip = ALIGN(offs + UBIFS_CH_SZ, c->min_io_size) - offs;
+        skip = ALIGN(offs + UBIFS_CH_SZ, c->max_write_size) - offs;
         if (is_empty(buf + skip, len - skip))
                 return 1;
         /*
@@ -441,7 +459,7 @@ static int no_more_nodes(const struct ubifs_info *c, void *buf, int len,
                 return 0;
         }
         /* Now we know the corrupt node's length we can skip over it */
-        skip = ALIGN(offs + dlen, c->min_io_size) - offs;
+        skip = ALIGN(offs + dlen, c->max_write_size) - offs;
         /* After which there should be empty space */
         if (is_empty(buf + skip, len - skip))
                 return 1;
@@ -671,10 +689,14 @@ struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum,
                 } else {
                         int corruption = first_non_ff(buf, len);
 
+                        /*
+                         * See header comment for this file for more
+                         * explanations about the reasons we have this check.
+                         */
                         ubifs_err("corrupt empty space LEB %d:%d, corruption "
                                   "starts at %d", lnum, offs, corruption);
                         /* Make sure we dump interesting non-0xFF data */
-                        offs = corruption;
+                        offs += corruption;
                         buf += corruption;
                         goto corrupted;
                 }
@@ -836,12 +858,8 @@ struct ubifs_scan_leb *ubifs_recover_log_leb(struct ubifs_info *c, int lnum,
 static int recover_head(const struct ubifs_info *c, int lnum, int offs,
                         void *sbuf)
 {
-        int len, err;
+        int len = c->max_write_size, err;
 
-        if (c->min_io_size > 1)
-                len = c->min_io_size;
-        else
-                len = 512;
         if (offs + len > c->leb_size)
                 len = c->leb_size - offs;
 
diff --git a/fs/ubifs/scan.c b/fs/ubifs/scan.c
index 3e1ee57dbeaa..36216b46f772 100644
--- a/fs/ubifs/scan.c
+++ b/fs/ubifs/scan.c
@@ -328,7 +328,7 @@ struct ubifs_scan_leb *ubifs_scan(const struct ubifs_info *c, int lnum,
                 if (!quiet)
                         ubifs_err("empty space starts at non-aligned offset %d",
                                   offs);
-                goto corrupted;;
+                goto corrupted;
         }
 
         ubifs_end_scan(c, sleb, lnum, offs);
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 6e11c2975dcf..e5dc1e120e8d 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -512,9 +512,12 @@ static int init_constants_early(struct ubifs_info *c)
 
         c->leb_cnt = c->vi.size;
         c->leb_size = c->vi.usable_leb_size;
+        c->leb_start = c->di.leb_start;
         c->half_leb_size = c->leb_size / 2;
         c->min_io_size = c->di.min_io_size;
         c->min_io_shift = fls(c->min_io_size) - 1;
+        c->max_write_size = c->di.max_write_size;
+        c->max_write_shift = fls(c->max_write_size) - 1;
 
         if (c->leb_size < UBIFS_MIN_LEB_SZ) {
                 ubifs_err("too small LEBs (%d bytes), min. is %d bytes",
@@ -534,6 +537,18 @@ static int init_constants_early(struct ubifs_info *c)
         }
 
         /*
+         * Maximum write size has to be greater or equivalent to min. I/O
+         * size, and be multiple of min. I/O size.
+         */
+        if (c->max_write_size < c->min_io_size ||
+            c->max_write_size % c->min_io_size ||
+            !is_power_of_2(c->max_write_size)) {
+                ubifs_err("bad write buffer size %d for %d min. I/O unit",
+                          c->max_write_size, c->min_io_size);
+                return -EINVAL;
+        }
+
+        /*
          * UBIFS aligns all node to 8-byte boundary, so to make function in
          * io.c simpler, assume minimum I/O unit size to be 8 bytes if it is
          * less than 8.
@@ -541,6 +556,10 @@ static int init_constants_early(struct ubifs_info *c)
         if (c->min_io_size < 8) {
                 c->min_io_size = 8;
                 c->min_io_shift = 3;
+                if (c->max_write_size < c->min_io_size) {
+                        c->max_write_size = c->min_io_size;
+                        c->max_write_shift = c->min_io_shift;
+                }
         }
 
         c->ref_node_alsz = ALIGN(UBIFS_REF_NODE_SZ, c->min_io_size);
@@ -1202,11 +1221,14 @@ static int mount_ubifs(struct ubifs_info *c)
         if (c->bulk_read == 1)
                 bu_init(c);
 
-        /*
-         * We have to check all CRCs, even for data nodes, when we mount the FS
-         * (specifically, when we are replaying).
-         */
-        c->always_chk_crc = 1;
+        if (!c->ro_mount) {
+                c->write_reserve_buf = kmalloc(COMPRESSED_DATA_NODE_BUF_SZ,
+                                               GFP_KERNEL);
+                if (!c->write_reserve_buf)
+                        goto out_free;
+        }
+
+        c->mounting = 1;
 
         err = ubifs_read_superblock(c);
         if (err)
@@ -1382,7 +1404,7 @@ static int mount_ubifs(struct ubifs_info *c)
         if (err)
                 goto out_infos;
 
-        c->always_chk_crc = 0;
+        c->mounting = 0;
 
         ubifs_msg("mounted UBI device %d, volume %d, name \"%s\"",
                   c->vi.ubi_num, c->vi.vol_id, c->vi.name);
@@ -1403,6 +1425,7 @@ static int mount_ubifs(struct ubifs_info *c)
 
         dbg_msg("compiled on:         " __DATE__ " at " __TIME__);
         dbg_msg("min. I/O unit size:  %d bytes", c->min_io_size);
+        dbg_msg("max. write size:     %d bytes", c->max_write_size);
         dbg_msg("LEB size:            %d bytes (%d KiB)",
                 c->leb_size, c->leb_size >> 10);
         dbg_msg("data journal heads:  %d",
@@ -1432,9 +1455,9 @@ static int mount_ubifs(struct ubifs_info *c)
                 UBIFS_TRUN_NODE_SZ, UBIFS_SB_NODE_SZ, UBIFS_MST_NODE_SZ);
         dbg_msg("node sizes:          ref %zu, cmt. start %zu, orph %zu",
                 UBIFS_REF_NODE_SZ, UBIFS_CS_NODE_SZ, UBIFS_ORPH_NODE_SZ);
-        dbg_msg("max. node sizes:     data %zu, inode %zu dentry %zu",
+        dbg_msg("max. node sizes:     data %zu, inode %zu dentry %zu, idx %d",
                 UBIFS_MAX_DATA_NODE_SZ, UBIFS_MAX_INO_NODE_SZ,
-                UBIFS_MAX_DENT_NODE_SZ);
+                UBIFS_MAX_DENT_NODE_SZ, ubifs_idx_node_sz(c, c->fanout));
         dbg_msg("dead watermark:      %d", c->dead_wm);
         dbg_msg("dark watermark:      %d", c->dark_wm);
         dbg_msg("LEB overhead:        %d", c->leb_overhead);
@@ -1474,6 +1497,7 @@ out_wbufs:
 out_cbuf:
         kfree(c->cbuf);
 out_free:
+        kfree(c->write_reserve_buf);
         kfree(c->bu.buf);
         vfree(c->ileb_buf);
         vfree(c->sbuf);
@@ -1512,6 +1536,7 @@ static void ubifs_umount(struct ubifs_info *c)
         kfree(c->cbuf);
         kfree(c->rcvrd_mst_node);
         kfree(c->mst_node);
+        kfree(c->write_reserve_buf);
         kfree(c->bu.buf);
         vfree(c->ileb_buf);
         vfree(c->sbuf);
@@ -1543,7 +1568,6 @@ static int ubifs_remount_rw(struct ubifs_info *c)
         mutex_lock(&c->umount_mutex);
         dbg_save_space_info(c);
         c->remounting_rw = 1;
-        c->always_chk_crc = 1;
 
         err = check_free_space(c);
         if (err)
@@ -1598,6 +1622,10 @@ static int ubifs_remount_rw(struct ubifs_info *c)
                 goto out;
         }
 
+        c->write_reserve_buf = kmalloc(COMPRESSED_DATA_NODE_BUF_SZ, GFP_KERNEL);
+        if (!c->write_reserve_buf)
+                goto out;
+
         err = ubifs_lpt_init(c, 0, 1);
         if (err)
                 goto out;
@@ -1650,7 +1678,6 @@ static int ubifs_remount_rw(struct ubifs_info *c)
         dbg_gen("re-mounted read-write");
         c->ro_mount = 0;
         c->remounting_rw = 0;
-        c->always_chk_crc = 0;
         err = dbg_check_space_info(c);
         mutex_unlock(&c->umount_mutex);
         return err;
@@ -1663,11 +1690,12 @@ out:
                 c->bgt = NULL;
         }
         free_wbufs(c);
+        kfree(c->write_reserve_buf);
+        c->write_reserve_buf = NULL;
         vfree(c->ileb_buf);
         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;
 }
@@ -1707,6 +1735,8 @@ static void ubifs_remount_ro(struct ubifs_info *c)
         free_wbufs(c);
         vfree(c->orph_buf);
         c->orph_buf = NULL;
+        kfree(c->write_reserve_buf);
+        c->write_reserve_buf = NULL;
         vfree(c->ileb_buf);
         c->ileb_buf = NULL;
         ubifs_lpt_free(c, 1);
@@ -1937,6 +1967,7 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
         mutex_init(&c->mst_mutex);
         mutex_init(&c->umount_mutex);
         mutex_init(&c->bu_mutex);
+        mutex_init(&c->write_reserve_mutex);
         init_waitqueue_head(&c->cmt_wq);
         c->buds = RB_ROOT;
         c->old_idx = RB_ROOT;
@@ -1954,6 +1985,7 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
         INIT_LIST_HEAD(&c->old_buds);
         INIT_LIST_HEAD(&c->orph_list);
         INIT_LIST_HEAD(&c->orph_new);
+        c->no_chk_data_crc = 1;
 
         c->vfs_sb = sb;
         c->highest_inum = UBIFS_FIRST_INO;
diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c
index ad9cf0133622..de485979ca39 100644
--- a/fs/ubifs/tnc.c
+++ b/fs/ubifs/tnc.c
@@ -447,8 +447,11 @@ static int tnc_read_node_nm(struct ubifs_info *c, struct ubifs_zbranch *zbr,
  *
  * Note, this function does not check CRC of data nodes if @c->no_chk_data_crc
  * is true (it is controlled by corresponding mount option). However, if
- * @c->always_chk_crc is true, @c->no_chk_data_crc is ignored and CRC is always
- * checked.
+ * @c->mounting or @c->remounting_rw is true (we are mounting or re-mounting to
+ * R/W mode), @c->no_chk_data_crc is ignored and CRC is checked. This is
+ * because during mounting or re-mounting from R/O mode to R/W mode we may read
+ * journal nodes (when replying the journal or doing the recovery) and the
+ * journal nodes may potentially be corrupted, so checking is required.
  */
 static int try_read_node(const struct ubifs_info *c, void *buf, int type,
                          int len, int lnum, int offs)
@@ -476,7 +479,8 @@ 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 && c->no_chk_data_crc)
+        if (type == UBIFS_DATA_NODE && c->no_chk_data_crc && !c->mounting &&
+            !c->remounting_rw)
                 return 1;
 
         crc = crc32(UBIFS_CRC32_INIT, buf + 8, node_len - 8);
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index 381d6b207a52..8c40ad3c6721 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -151,6 +151,12 @@
  */
 #define WORST_COMPR_FACTOR 2
 
+/*
+ * How much memory is needed for a buffer where we comress a data node.
+ */
+#define COMPRESSED_DATA_NODE_BUF_SZ \
+        (UBIFS_DATA_NODE_SZ + UBIFS_BLOCK_SIZE * WORST_COMPR_FACTOR)
+
 /* Maximum expected tree height for use by bottom_up_buf */
 #define BOTTOM_UP_HEIGHT 64
 
@@ -646,6 +652,7 @@ typedef int (*ubifs_lpt_scan_callback)(struct ubifs_info *c,
  * @offs: write-buffer offset in this logical eraseblock
  * @avail: number of bytes available in the write-buffer
  * @used:  number of used bytes in the write-buffer
+ * @size: write-buffer size (in [@c->min_io_size, @c->max_write_size] range)
  * @dtype: type of data stored in this LEB (%UBI_LONGTERM, %UBI_SHORTTERM,
  * %UBI_UNKNOWN)
  * @jhead: journal head the mutex belongs to (note, needed only to shut lockdep
@@ -680,6 +687,7 @@ struct ubifs_wbuf {
         int offs;
         int avail;
         int used;
+        int size;
         int dtype;
         int jhead;
         int (*sync_callback)(struct ubifs_info *c, int lnum, int free, int pad);
@@ -1003,6 +1011,11 @@ struct ubifs_debug_info;
  * @bu_mutex: protects the pre-allocated bulk-read buffer and @c->bu
  * @bu: pre-allocated bulk-read information
  *
+ * @write_reserve_mutex: protects @write_reserve_buf
+ * @write_reserve_buf: on the write path we allocate memory, which might
+ *                     sometimes be unavailable, in which case we use this
+ *                     write reserve buffer
+ *
  * @log_lebs: number of logical eraseblocks in the log
  * @log_bytes: log size in bytes
  * @log_last: last LEB of the log
@@ -1024,7 +1037,12 @@ struct ubifs_debug_info;
  *
  * @min_io_size: minimal input/output unit size
  * @min_io_shift: number of bits in @min_io_size minus one
+ * @max_write_size: maximum amount of bytes the underlying flash can write at a
+ *                  time (MTD write buffer size)
+ * @max_write_shift: number of bits in @max_write_size minus one
  * @leb_size: logical eraseblock size in bytes
+ * @leb_start: starting offset of logical eraseblocks within physical
+ *             eraseblocks
  * @half_leb_size: half LEB size
  * @idx_leb_size: how many bytes of an LEB are effectively available when it is
  *                used to store indexing nodes (@leb_size - @max_idx_node_sz)
@@ -1166,22 +1184,21 @@ struct ubifs_debug_info;
  * @rp_uid: reserved pool user ID
  * @rp_gid: reserved pool group ID
  *
- * @empty: if the UBI device is empty
+ * @empty: %1 if the UBI device is empty
+ * @need_recovery: %1 if the file-system needs recovery
+ * @replaying: %1 during journal replay
+ * @mounting: %1 while mounting
+ * @remounting_rw: %1 while re-mounting from R/O mode to R/W mode
  * @replay_tree: temporary tree used during journal replay
  * @replay_list: temporary list used during journal replay
  * @replay_buds: list of buds to replay
  * @cs_sqnum: sequence number of first node in the log (commit start node)
  * @replay_sqnum: sequence number of node currently being replayed
- * @need_recovery: file-system needs recovery
- * @replaying: set to %1 during journal replay
  * @unclean_leb_list: LEBs to recover when re-mounting R/O mounted FS to R/W
  *                    mode
  * @rcvrd_mst_node: recovered master node to write when re-mounting R/O mounted
  *                  FS to R/W mode
  * @size_tree: inode size information for recovery
- * @remounting_rw: set while re-mounting from R/O mode to R/W mode
- * @always_chk_crc: always check CRCs (while mounting and remounting to R/W
- *                  mode)
  * @mount_opts: UBIFS-specific mount options
  *
  * @dbg: debugging-related information
@@ -1250,6 +1267,9 @@ struct ubifs_info {
         struct mutex bu_mutex;
         struct bu_info bu;
 
+        struct mutex write_reserve_mutex;
+        void *write_reserve_buf;
+
         int log_lebs;
         long long log_bytes;
         int log_last;
@@ -1271,7 +1291,10 @@ struct ubifs_info {
 
         int min_io_size;
         int min_io_shift;
+        int max_write_size;
+        int max_write_shift;
         int leb_size;
+        int leb_start;
         int half_leb_size;
         int idx_leb_size;
         int leb_cnt;
@@ -1402,19 +1425,19 @@ struct ubifs_info {
         gid_t rp_gid;
 
         /* The below fields are used only during mounting and re-mounting */
-        int empty;
+        unsigned int empty:1;
+        unsigned int need_recovery:1;
+        unsigned int replaying:1;
+        unsigned int mounting:1;
+        unsigned int remounting_rw:1;
         struct rb_root replay_tree;
         struct list_head replay_list;
         struct list_head replay_buds;
         unsigned long long cs_sqnum;
         unsigned long long replay_sqnum;
-        int need_recovery;
-        int replaying;
         struct list_head unclean_leb_list;
         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
diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c
index 8994dd041660..95518a9f589e 100644
--- a/fs/udf/balloc.c
+++ b/fs/udf/balloc.c
@@ -27,11 +27,10 @@
 #include "udf_i.h"
 #include "udf_sb.h"
 
-#define udf_clear_bit(nr, addr) ext2_clear_bit(nr, addr)
-#define udf_set_bit(nr, addr) ext2_set_bit(nr, addr)
-#define udf_test_bit(nr, addr) ext2_test_bit(nr, addr)
-#define udf_find_next_one_bit(addr, size, offset) \
-                ext2_find_next_bit((unsigned long *)(addr), size, offset)
+#define udf_clear_bit   __test_and_clear_bit_le
+#define udf_set_bit     __test_and_set_bit_le
+#define udf_test_bit    test_bit_le
+#define udf_find_next_one_bit   find_next_bit_le
 
 static int read_block_bitmap(struct super_block *sb,
                              struct udf_bitmap *bitmap, unsigned int block,
diff --git a/fs/ufs/util.h b/fs/ufs/util.h
index 9f8775ce381c..954175928240 100644
--- a/fs/ufs/util.h
+++ b/fs/ufs/util.h
@@ -408,7 +408,7 @@ static inline unsigned _ubh_find_next_zero_bit_(
         for (;;) {
                 count = min_t(unsigned int, size + offset, uspi->s_bpf);
                 size -= count - offset;
-                pos = ext2_find_next_zero_bit (ubh->bh[base]->b_data, count, offset);
+                pos = find_next_zero_bit_le(ubh->bh[base]->b_data, count, offset);
                 if (pos < count || !size)
                         break;
                 base++;
diff --git a/fs/utimes.c b/fs/utimes.c
index 179b58690657..ba653f3dc1bc 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -95,7 +95,7 @@ static int utimes_common(struct path *path, struct timespec *times)
                 if (IS_IMMUTABLE(inode))
                         goto mnt_drop_write_and_out;
 
-                if (!is_owner_or_cap(inode)) {
+                if (!inode_owner_or_capable(inode)) {
                         error = inode_permission(inode, MAY_WRITE);
                         if (error)
                                 goto mnt_drop_write_and_out;
diff --git a/fs/xattr.c b/fs/xattr.c
index 01bb8135e14a..a19acdb81cd1 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -59,7 +59,7 @@ xattr_permission(struct inode *inode, const char *name, int mask)
                 if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
                         return -EPERM;
                 if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) &&
-                    (mask & MAY_WRITE) && !is_owner_or_cap(inode))
+                    (mask & MAY_WRITE) && !inode_owner_or_capable(inode))
                         return -EPERM;
         }
 
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index faca44997099..284a7c89697e 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -16,14 +16,11 @@
 # Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 #
 
-EXTRA_CFLAGS +=  -I$(src) -I$(src)/linux-2.6
+ccflags-y := -I$(src) -I$(src)/linux-2.6
+ccflags-$(CONFIG_XFS_DEBUG) += -g
 
 XFS_LINUX := linux-2.6
 
-ifeq ($(CONFIG_XFS_DEBUG),y)
-        EXTRA_CFLAGS += -g
-endif
-
 obj-$(CONFIG_XFS_FS)            += xfs.o
 
 xfs-y                           += linux-2.6/xfs_trace.o
@@ -105,11 +102,10 @@ xfs-y				+= $(addprefix $(XFS_LINUX)/, \
                                    xfs_globals.o \
                                    xfs_ioctl.o \
                                    xfs_iops.o \
+                                   xfs_message.o \
                                    xfs_super.o \
                                    xfs_sync.o \
                                    xfs_xattr.o)
 
 # Objects in support/
-xfs-y                           += $(addprefix support/, \
-                                   debug.o \
-                                   uuid.o)
+xfs-y                           += support/uuid.o
diff --git a/fs/xfs/linux-2.6/kmem.c b/fs/xfs/linux-2.6/kmem.c
index 666c9db48eb6..a907de565db3 100644
--- a/fs/xfs/linux-2.6/kmem.c
+++ b/fs/xfs/linux-2.6/kmem.c
@@ -23,6 +23,7 @@
 #include <linux/backing-dev.h>
 #include "time.h"
 #include "kmem.h"
+#include "xfs_message.h"
 
 /*
  * Greedy allocation.  May fail and may return vmalloced memory.
@@ -56,8 +57,8 @@ kmem_alloc(size_t size, unsigned int __nocast flags)
                 if (ptr || (flags & (KM_MAYFAIL|KM_NOSLEEP)))
                         return ptr;
                 if (!(++retries % 100))
-                        printk(KERN_ERR "XFS: possible memory allocation "
-                                        "deadlock in %s (mode:0x%x)\n",
+                        xfs_err(NULL,
+                "possible memory allocation deadlock in %s (mode:0x%x)",
                                         __func__, lflags);
                 congestion_wait(BLK_RW_ASYNC, HZ/50);
         } while (1);
@@ -112,8 +113,8 @@ kmem_zone_alloc(kmem_zone_t *zone, unsigned int __nocast flags)
                 if (ptr || (flags & (KM_MAYFAIL|KM_NOSLEEP)))
                         return ptr;
                 if (!(++retries % 100))
-                        printk(KERN_ERR "XFS: possible memory allocation "
-                                        "deadlock in %s (mode:0x%x)\n",
+                        xfs_err(NULL,
+                "possible memory allocation deadlock in %s (mode:0x%x)",
                                         __func__, lflags);
                 congestion_wait(BLK_RW_ASYNC, HZ/50);
         } while (1);
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index ec7bbb5645b6..8c5c87277456 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -854,7 +854,7 @@ xfs_aops_discard_page(
         if (XFS_FORCED_SHUTDOWN(ip->i_mount))
                 goto out_invalidate;
 
-        xfs_fs_cmn_err(CE_ALERT, ip->i_mount,
+        xfs_alert(ip->i_mount,
                 "page discard on page %p, inode 0x%llx, offset %llu.",
                         page, ip->i_ino, offset);
 
@@ -872,7 +872,7 @@ xfs_aops_discard_page(
                 if (error) {
                         /* something screwed, just bail */
                         if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
-                                xfs_fs_cmn_err(CE_ALERT, ip->i_mount,
+                                xfs_alert(ip->i_mount,
                         "page discard unable to remove delalloc mapping.");
                         }
                         break;
@@ -1411,7 +1411,7 @@ xfs_vm_write_failed(
                 if (error) {
                         /* something screwed, just bail */
                         if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
-                                xfs_fs_cmn_err(CE_ALERT, ip->i_mount,
+                                xfs_alert(ip->i_mount,
                         "xfs_vm_write_failed: unable to clean up ino %lld",
                                                 ip->i_ino);
                         }
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index f83a4c830a65..5cb230f2cb4f 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -401,9 +401,8 @@ _xfs_buf_lookup_pages(
                          * handle buffer allocation failures we can't do much.
                          */
                         if (!(++retries % 100))
-                                printk(KERN_ERR
-                                        "XFS: possible memory allocation "
-                                        "deadlock in %s (mode:0x%x)\n",
+                                xfs_err(NULL,
+                "possible memory allocation deadlock in %s (mode:0x%x)",
                                         __func__, gfp_mask);
 
                         XFS_STATS_INC(xb_page_retries);
@@ -615,8 +614,8 @@ xfs_buf_get(
         if (!(bp->b_flags & XBF_MAPPED)) {
                 error = _xfs_buf_map_pages(bp, flags);
                 if (unlikely(error)) {
-                        printk(KERN_WARNING "%s: failed to map pages\n",
-                                        __func__);
+                        xfs_warn(target->bt_mount,
+                                "%s: failed to map pages\n", __func__);
                         goto no_buffer;
                 }
         }
@@ -850,8 +849,8 @@ xfs_buf_get_uncached(
 
         error = _xfs_buf_map_pages(bp, XBF_MAPPED);
         if (unlikely(error)) {
-                printk(KERN_WARNING "%s: failed to map pages\n",
-                                __func__);
+                xfs_warn(target->bt_mount,
+                        "%s: failed to map pages\n", __func__);
                 goto fail_free_mem;
         }
 
@@ -1617,8 +1616,8 @@ xfs_setsize_buftarg_flags(
         btp->bt_smask = sectorsize - 1;
 
         if (set_blocksize(btp->bt_bdev, sectorsize)) {
-                printk(KERN_WARNING
-                        "XFS: Cannot set_blocksize to %u on device %s\n",
+                xfs_warn(btp->bt_mount,
+                        "Cannot set_blocksize to %u on device %s\n",
                         sectorsize, XFS_BUFTARG_NAME(btp));
                 return EINVAL;
         }
diff --git a/fs/xfs/linux-2.6/xfs_linux.h b/fs/xfs/linux-2.6/xfs_linux.h
index 096494997747..244be9cbfe78 100644
--- a/fs/xfs/linux-2.6/xfs_linux.h
+++ b/fs/xfs/linux-2.6/xfs_linux.h
@@ -39,7 +39,6 @@
 #include <mrlock.h>
 #include <time.h>
 
-#include <support/debug.h>
 #include <support/uuid.h>
 
 #include <linux/semaphore.h>
@@ -86,6 +85,7 @@
 #include <xfs_aops.h>
 #include <xfs_super.h>
 #include <xfs_buf.h>
+#include <xfs_message.h>
 
 /*
  * Feature macros (disable/enable)
@@ -280,4 +280,25 @@ static inline __uint64_t howmany_64(__uint64_t x, __uint32_t y)
 #define __arch_pack
 #endif
 
+#define ASSERT_ALWAYS(expr)     \
+        (unlikely(expr) ? (void)0 : assfail(#expr, __FILE__, __LINE__))
+
+#ifndef DEBUG
+#define ASSERT(expr)    ((void)0)
+
+#ifndef STATIC
+# define STATIC static noinline
+#endif
+
+#else /* DEBUG */
+
+#define ASSERT(expr)    \
+        (unlikely(expr) ? (void)0 : assfail(#expr, __FILE__, __LINE__))
+
+#ifndef STATIC
+# define STATIC noinline
+#endif
+
+#endif /* DEBUG */
+
 #endif /* __XFS_LINUX__ */
diff --git a/fs/xfs/linux-2.6/xfs_message.c b/fs/xfs/linux-2.6/xfs_message.c
new file mode 100644
index 000000000000..508e06fd7d1e
--- /dev/null
+++ b/fs/xfs/linux-2.6/xfs_message.c
@@ -0,0 +1,133 @@
+/*
+ * Copyright (c) 2011 Red Hat, Inc.  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.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  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 the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_types.h"
+#include "xfs_log.h"
+#include "xfs_inum.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_ag.h"
+#include "xfs_mount.h"
+
+/*
+ * XFS logging functions
+ */
+static int
+__xfs_printk(
+        const char              *level,
+        const struct xfs_mount  *mp,
+        struct va_format        *vaf)
+{
+        if (mp && mp->m_fsname)
+                return printk("%sXFS (%s): %pV\n", level, mp->m_fsname, vaf);
+        return printk("%sXFS: %pV\n", level, vaf);
+}
+
+int xfs_printk(
+        const char              *level,
+        const struct xfs_mount  *mp,
+        const char              *fmt, ...)
+{
+        struct va_format        vaf;
+        va_list                 args;
+        int                      r;
+
+        va_start(args, fmt);
+
+        vaf.fmt = fmt;
+        vaf.va = &args;
+
+        r = __xfs_printk(level, mp, &vaf);
+        va_end(args);
+
+        return r;
+}
+
+#define define_xfs_printk_level(func, kern_level)               \
+int func(const struct xfs_mount *mp, const char *fmt, ...)      \
+{                                                               \
+        struct va_format        vaf;                            \
+        va_list                 args;                           \
+        int                     r;                              \
+                                                                \
+        va_start(args, fmt);                                    \
+                                                                \
+        vaf.fmt = fmt;                                          \
+        vaf.va = &args;                                         \
+                                                                \
+        r = __xfs_printk(kern_level, mp, &vaf);                 \
+        va_end(args);                                           \
+                                                                \
+        return r;                                               \
+}                                                               \
+
+define_xfs_printk_level(xfs_emerg, KERN_EMERG);
+define_xfs_printk_level(xfs_alert, KERN_ALERT);
+define_xfs_printk_level(xfs_crit, KERN_CRIT);
+define_xfs_printk_level(xfs_err, KERN_ERR);
+define_xfs_printk_level(xfs_warn, KERN_WARNING);
+define_xfs_printk_level(xfs_notice, KERN_NOTICE);
+define_xfs_printk_level(xfs_info, KERN_INFO);
+#ifdef DEBUG
+define_xfs_printk_level(xfs_debug, KERN_DEBUG);
+#endif
+
+int
+xfs_alert_tag(
+        const struct xfs_mount  *mp,
+        int                     panic_tag,
+        const char              *fmt, ...)
+{
+        struct va_format        vaf;
+        va_list                 args;
+        int                     do_panic = 0;
+        int                     r;
+
+        if (xfs_panic_mask && (xfs_panic_mask & panic_tag)) {
+                xfs_printk(KERN_ALERT, mp,
+                        "XFS: Transforming an alert into a BUG.");
+                do_panic = 1;
+        }
+
+        va_start(args, fmt);
+
+        vaf.fmt = fmt;
+        vaf.va = &args;
+
+        r = __xfs_printk(KERN_ALERT, mp, &vaf);
+        va_end(args);
+
+        BUG_ON(do_panic);
+
+        return r;
+}
+
+void
+assfail(char *expr, char *file, int line)
+{
+        xfs_emerg(NULL, "Assertion failed: %s, file: %s, line: %d",
+                expr, file, line);
+        BUG();
+}
+
+void
+xfs_hex_dump(void *p, int length)
+{
+        print_hex_dump(KERN_ALERT, "", DUMP_PREFIX_ADDRESS, 16, 1, p, length, 1);
+}
diff --git a/fs/xfs/linux-2.6/xfs_message.h b/fs/xfs/linux-2.6/xfs_message.h
new file mode 100644
index 000000000000..e77ffa16745b
--- /dev/null
+++ b/fs/xfs/linux-2.6/xfs_message.h
@@ -0,0 +1,38 @@
+#ifndef __XFS_MESSAGE_H
+#define __XFS_MESSAGE_H 1
+
+struct xfs_mount;
+
+extern int xfs_printk(const char *level, const struct xfs_mount *mp,
+                      const char *fmt, ...)
+        __attribute__ ((format (printf, 3, 4)));
+extern int xfs_emerg(const struct xfs_mount *mp, const char *fmt, ...)
+        __attribute__ ((format (printf, 2, 3)));
+extern int xfs_alert(const struct xfs_mount *mp, const char *fmt, ...)
+        __attribute__ ((format (printf, 2, 3)));
+extern int xfs_alert_tag(const struct xfs_mount *mp, int tag,
+                         const char *fmt, ...)
+        __attribute__ ((format (printf, 3, 4)));
+extern int xfs_crit(const struct xfs_mount *mp, const char *fmt, ...)
+        __attribute__ ((format (printf, 2, 3)));
+extern int xfs_err(const struct xfs_mount *mp, const char *fmt, ...)
+        __attribute__ ((format (printf, 2, 3)));
+extern int xfs_warn(const struct xfs_mount *mp, const char *fmt, ...)
+        __attribute__ ((format (printf, 2, 3)));
+extern int xfs_notice(const struct xfs_mount *mp, const char *fmt, ...)
+        __attribute__ ((format (printf, 2, 3)));
+extern int xfs_info(const struct xfs_mount *mp, const char *fmt, ...)
+        __attribute__ ((format (printf, 2, 3)));
+
+#ifdef DEBUG
+extern int xfs_debug(const struct xfs_mount *mp, const char *fmt, ...)
+        __attribute__ ((format (printf, 2, 3)));
+#else
+#define xfs_debug(mp, fmt, ...) (0)
+#endif
+
+extern void assfail(char *expr, char *f, int l);
+
+extern void xfs_hex_dump(void *p, int length);
+
+#endif  /* __XFS_MESSAGE_H */
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 9731898083ae..818c4cf2de86 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -173,6 +173,15 @@ xfs_parseargs(
         __uint8_t               iosizelog = 0;
 
         /*
+         * set up the mount name first so all the errors will refer to the
+         * correct device.
+         */
+        mp->m_fsname = kstrndup(sb->s_id, MAXNAMELEN, GFP_KERNEL);
+        if (!mp->m_fsname)
+                return ENOMEM;
+        mp->m_fsname_len = strlen(mp->m_fsname) + 1;
+
+        /*
          * Copy binary VFS mount flags we are interested in.
          */
         if (sb->s_flags & MS_RDONLY)
@@ -189,6 +198,7 @@ xfs_parseargs(
         mp->m_flags |= XFS_MOUNT_BARRIER;
         mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
         mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
+        mp->m_flags |= XFS_MOUNT_DELAYLOG;
 
         /*
          * These can be overridden by the mount option parsing.
@@ -207,24 +217,21 @@ xfs_parseargs(
 
                 if (!strcmp(this_char, MNTOPT_LOGBUFS)) {
                         if (!value || !*value) {
-                                cmn_err(CE_WARN,
-                                        "XFS: %s option requires an argument",
+                                xfs_warn(mp, "%s option requires an argument",
                                         this_char);
                                 return EINVAL;
                         }
                         mp->m_logbufs = simple_strtoul(value, &eov, 10);
                 } else if (!strcmp(this_char, MNTOPT_LOGBSIZE)) {
                         if (!value || !*value) {
-                                cmn_err(CE_WARN,
-                                        "XFS: %s option requires an argument",
+                                xfs_warn(mp, "%s option requires an argument",
                                         this_char);
                                 return EINVAL;
                         }
                         mp->m_logbsize = suffix_strtoul(value, &eov, 10);
                 } else if (!strcmp(this_char, MNTOPT_LOGDEV)) {
                         if (!value || !*value) {
-                                cmn_err(CE_WARN,
-                                        "XFS: %s option requires an argument",
+                                xfs_warn(mp, "%s option requires an argument",
                                         this_char);
                                 return EINVAL;
                         }
@@ -232,14 +239,12 @@ xfs_parseargs(
                         if (!mp->m_logname)
                                 return ENOMEM;
                 } else if (!strcmp(this_char, MNTOPT_MTPT)) {
-                        cmn_err(CE_WARN,
-                                "XFS: %s option not allowed on this system",
+                        xfs_warn(mp, "%s option not allowed on this system",
                                 this_char);
                         return EINVAL;
                 } else if (!strcmp(this_char, MNTOPT_RTDEV)) {
                         if (!value || !*value) {
-                                cmn_err(CE_WARN,
-                                        "XFS: %s option requires an argument",
+                                xfs_warn(mp, "%s option requires an argument",
                                         this_char);
                                 return EINVAL;
                         }
@@ -248,8 +253,7 @@ xfs_parseargs(
                                 return ENOMEM;
                 } else if (!strcmp(this_char, MNTOPT_BIOSIZE)) {
                         if (!value || !*value) {
-                                cmn_err(CE_WARN,
-                                        "XFS: %s option requires an argument",
+                                xfs_warn(mp, "%s option requires an argument",
                                         this_char);
                                 return EINVAL;
                         }
@@ -257,8 +261,7 @@ xfs_parseargs(
                         iosizelog = ffs(iosize) - 1;
                 } else if (!strcmp(this_char, MNTOPT_ALLOCSIZE)) {
                         if (!value || !*value) {
-                                cmn_err(CE_WARN,
-                                        "XFS: %s option requires an argument",
+                                xfs_warn(mp, "%s option requires an argument",
                                         this_char);
                                 return EINVAL;
                         }
@@ -280,16 +283,14 @@ xfs_parseargs(
                         mp->m_flags |= XFS_MOUNT_SWALLOC;
                 } else if (!strcmp(this_char, MNTOPT_SUNIT)) {
                         if (!value || !*value) {
-                                cmn_err(CE_WARN,
-                                        "XFS: %s option requires an argument",
+                                xfs_warn(mp, "%s option requires an argument",
                                         this_char);
                                 return EINVAL;
                         }
                         dsunit = simple_strtoul(value, &eov, 10);
                 } else if (!strcmp(this_char, MNTOPT_SWIDTH)) {
                         if (!value || !*value) {
-                                cmn_err(CE_WARN,
-                                        "XFS: %s option requires an argument",
+                                xfs_warn(mp, "%s option requires an argument",
                                         this_char);
                                 return EINVAL;
                         }
@@ -297,8 +298,7 @@ xfs_parseargs(
                 } else if (!strcmp(this_char, MNTOPT_64BITINODE)) {
                         mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
 #if !XFS_BIG_INUMS
-                        cmn_err(CE_WARN,
-                                "XFS: %s option not allowed on this system",
+                        xfs_warn(mp, "%s option not allowed on this system",
                                 this_char);
                         return EINVAL;
 #endif
@@ -356,20 +356,19 @@ xfs_parseargs(
                 } else if (!strcmp(this_char, MNTOPT_NODELAYLOG)) {
                         mp->m_flags &= ~XFS_MOUNT_DELAYLOG;
                 } else if (!strcmp(this_char, "ihashsize")) {
-                        cmn_err(CE_WARN,
-        "XFS: ihashsize no longer used, option is deprecated.");
+                        xfs_warn(mp,
+        "ihashsize no longer used, option is deprecated.");
                 } else if (!strcmp(this_char, "osyncisdsync")) {
-                        cmn_err(CE_WARN,
-        "XFS: osyncisdsync has no effect, option is deprecated.");
+                        xfs_warn(mp,
+        "osyncisdsync has no effect, option is deprecated.");
                 } else if (!strcmp(this_char, "osyncisosync")) {
-                        cmn_err(CE_WARN,
-        "XFS: osyncisosync has no effect, option is deprecated.");
+                        xfs_warn(mp,
+        "osyncisosync has no effect, option is deprecated.");
                 } else if (!strcmp(this_char, "irixsgid")) {
-                        cmn_err(CE_WARN,
-        "XFS: irixsgid is now a sysctl(2) variable, option is deprecated.");
+                        xfs_warn(mp,
+        "irixsgid is now a sysctl(2) variable, option is deprecated.");
                 } else {
-                        cmn_err(CE_WARN,
-                                "XFS: unknown mount option [%s].", this_char);
+                        xfs_warn(mp, "unknown mount option [%s].", this_char);
                         return EINVAL;
                 }
         }
@@ -379,40 +378,37 @@ xfs_parseargs(
          */
         if ((mp->m_flags & XFS_MOUNT_NORECOVERY) &&
             !(mp->m_flags & XFS_MOUNT_RDONLY)) {
-                cmn_err(CE_WARN, "XFS: no-recovery mounts must be read-only.");
+                xfs_warn(mp, "no-recovery mounts must be read-only.");
                 return EINVAL;
         }
 
         if ((mp->m_flags & XFS_MOUNT_NOALIGN) && (dsunit || dswidth)) {
-                cmn_err(CE_WARN,
-        "XFS: sunit and swidth options incompatible with the noalign option");
+                xfs_warn(mp,
+        "sunit and swidth options incompatible with the noalign option");
                 return EINVAL;
         }
 
 #ifndef CONFIG_XFS_QUOTA
         if (XFS_IS_QUOTA_RUNNING(mp)) {
-                cmn_err(CE_WARN,
-                        "XFS: quota support not available in this kernel.");
+                xfs_warn(mp, "quota support not available in this kernel.");
                 return EINVAL;
         }
 #endif
 
         if ((mp->m_qflags & (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE)) &&
             (mp->m_qflags & (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE))) {
-                cmn_err(CE_WARN,
-                        "XFS: cannot mount with both project and group quota");
+                xfs_warn(mp, "cannot mount with both project and group quota");
                 return EINVAL;
         }
 
         if ((dsunit && !dswidth) || (!dsunit && dswidth)) {
-                cmn_err(CE_WARN,
-                        "XFS: sunit and swidth must be specified together");
+                xfs_warn(mp, "sunit and swidth must be specified together");
                 return EINVAL;
         }
 
         if (dsunit && (dswidth % dsunit != 0)) {
-                cmn_err(CE_WARN,
-        "XFS: stripe width (%d) must be a multiple of the stripe unit (%d)",
+                xfs_warn(mp,
+        "stripe width (%d) must be a multiple of the stripe unit (%d)",
                         dswidth, dsunit);
                 return EINVAL;
         }
@@ -438,8 +434,7 @@ done:
             mp->m_logbufs != 0 &&
             (mp->m_logbufs < XLOG_MIN_ICLOGS ||
              mp->m_logbufs > XLOG_MAX_ICLOGS)) {
-                cmn_err(CE_WARN,
-                        "XFS: invalid logbufs value: %d [not %d-%d]",
+                xfs_warn(mp, "invalid logbufs value: %d [not %d-%d]",
                         mp->m_logbufs, XLOG_MIN_ICLOGS, XLOG_MAX_ICLOGS);
                 return XFS_ERROR(EINVAL);
         }
@@ -448,22 +443,16 @@ done:
             (mp->m_logbsize < XLOG_MIN_RECORD_BSIZE ||
              mp->m_logbsize > XLOG_MAX_RECORD_BSIZE ||
              !is_power_of_2(mp->m_logbsize))) {
-                cmn_err(CE_WARN,
-        "XFS: invalid logbufsize: %d [not 16k,32k,64k,128k or 256k]",
+                xfs_warn(mp,
+                        "invalid logbufsize: %d [not 16k,32k,64k,128k or 256k]",
                         mp->m_logbsize);
                 return XFS_ERROR(EINVAL);
         }
 
-        mp->m_fsname = kstrndup(sb->s_id, MAXNAMELEN, GFP_KERNEL);
-        if (!mp->m_fsname)
-                return ENOMEM;
-        mp->m_fsname_len = strlen(mp->m_fsname) + 1;
-
         if (iosizelog) {
                 if (iosizelog > XFS_MAX_IO_LOG ||
                     iosizelog < XFS_MIN_IO_LOG) {
-                        cmn_err(CE_WARN,
-                "XFS: invalid log iosize: %d [not %d-%d]",
+                        xfs_warn(mp, "invalid log iosize: %d [not %d-%d]",
                                 iosizelog, XFS_MIN_IO_LOG,
                                 XFS_MAX_IO_LOG);
                         return XFS_ERROR(EINVAL);
@@ -610,7 +599,7 @@ xfs_blkdev_get(
                                     mp);
         if (IS_ERR(*bdevp)) {
                 error = PTR_ERR(*bdevp);
-                printk("XFS: Invalid device [%s], error=%d\n", name, error);
+                xfs_warn(mp, "Invalid device [%s], error=%d\n", name, error);
         }
 
         return -error;
@@ -664,23 +653,23 @@ xfs_mountfs_check_barriers(xfs_mount_t *mp)
         int error;
 
         if (mp->m_logdev_targp != mp->m_ddev_targp) {
-                xfs_fs_cmn_err(CE_NOTE, mp,
+                xfs_notice(mp,
                   "Disabling barriers, not supported with external log device");
                 mp->m_flags &= ~XFS_MOUNT_BARRIER;
                 return;
         }
 
         if (xfs_readonly_buftarg(mp->m_ddev_targp)) {
-                xfs_fs_cmn_err(CE_NOTE, mp,
-                  "Disabling barriers, underlying device is readonly");
+                xfs_notice(mp,
+                        "Disabling barriers, underlying device is readonly");
                 mp->m_flags &= ~XFS_MOUNT_BARRIER;
                 return;
         }
 
         error = xfs_barrier_test(mp);
         if (error) {
-                xfs_fs_cmn_err(CE_NOTE, mp,
-                  "Disabling barriers, trial barrier write failed");
+                xfs_notice(mp,
+                        "Disabling barriers, trial barrier write failed");
                 mp->m_flags &= ~XFS_MOUNT_BARRIER;
                 return;
         }
@@ -743,8 +732,8 @@ xfs_open_devices(
                         goto out_close_logdev;
 
                 if (rtdev == ddev || rtdev == logdev) {
-                        cmn_err(CE_WARN,
-        "XFS: Cannot mount filesystem with identical rtdev and ddev/logdev.");
+                        xfs_warn(mp,
+        "Cannot mount filesystem with identical rtdev and ddev/logdev.");
                         error = EINVAL;
                         goto out_close_rtdev;
                 }
@@ -1345,8 +1334,8 @@ xfs_fs_remount(
                          * options that we can't actually change.
                          */
 #if 0
-                        printk(KERN_INFO
-        "XFS: mount option \"%s\" not supported for remount\n", p);
+                        xfs_info(mp,
+                "mount option \"%s\" not supported for remount\n", p);
                         return -EINVAL;
 #else
                         break;
@@ -1367,8 +1356,7 @@ xfs_fs_remount(
                 if (mp->m_update_flags) {
                         error = xfs_mount_log_sb(mp, mp->m_update_flags);
                         if (error) {
-                                cmn_err(CE_WARN,
-                                        "XFS: failed to write sb changes");
+                                xfs_warn(mp, "failed to write sb changes");
                                 return error;
                         }
                         mp->m_update_flags = 0;
@@ -1452,15 +1440,15 @@ xfs_finish_flags(
                         mp->m_logbsize = mp->m_sb.sb_logsunit;
                 } else if (mp->m_logbsize > 0 &&
                            mp->m_logbsize < mp->m_sb.sb_logsunit) {
-                        cmn_err(CE_WARN,
-        "XFS: logbuf size must be greater than or equal to log stripe size");
+                        xfs_warn(mp,
+                "logbuf size must be greater than or equal to log stripe size");
                         return XFS_ERROR(EINVAL);
                 }
         } else {
                 /* Fail a mount if the logbuf is larger than 32K */
                 if (mp->m_logbsize > XLOG_BIG_RECORD_BSIZE) {
-                        cmn_err(CE_WARN,
-        "XFS: logbuf size for version 1 logs must be 16K or 32K");
+                        xfs_warn(mp,
+                "logbuf size for version 1 logs must be 16K or 32K");
                         return XFS_ERROR(EINVAL);
                 }
         }
@@ -1477,8 +1465,8 @@ xfs_finish_flags(
          * prohibit r/w mounts of read-only filesystems
          */
         if ((mp->m_sb.sb_flags & XFS_SBF_READONLY) && !ronly) {
-                cmn_err(CE_WARN,
-        "XFS: cannot mount a read-only filesystem as read-write");
+                xfs_warn(mp,
+                        "cannot mount a read-only filesystem as read-write");
                 return XFS_ERROR(EROFS);
         }
 
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index e22f0057d21f..6c10f1d2e3d3 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -425,8 +425,7 @@ xfs_quiesce_attr(
         /* Push the superblock and write an unmount record */
         error = xfs_log_sbcount(mp, 1);
         if (error)
-                xfs_fs_cmn_err(CE_WARN, mp,
-                                "xfs_attr_quiesce: failed to log sb changes. "
+                xfs_warn(mp, "xfs_attr_quiesce: failed to log sb changes. "
                                 "Frozen image may not be consistent.");
         xfs_log_unmount_write(mp);
         xfs_unmountfs_writesb(mp);
@@ -806,7 +805,7 @@ xfs_reclaim_inode(
          * pass on the error.
          */
         if (error && error != EAGAIN && !XFS_FORCED_SHUTDOWN(ip->i_mount)) {
-                xfs_fs_cmn_err(CE_WARN, ip->i_mount,
+                xfs_warn(ip->i_mount,
                         "inode 0x%llx background reclaim flush failed with %d",
                         (long long)ip->i_ino, error);
         }
diff --git a/fs/xfs/linux-2.6/xfs_sysctl.c b/fs/xfs/linux-2.6/xfs_sysctl.c
index ee3cee097e7e..ee2d2adaa438 100644
--- a/fs/xfs/linux-2.6/xfs_sysctl.c
+++ b/fs/xfs/linux-2.6/xfs_sysctl.c
@@ -37,7 +37,7 @@ xfs_stats_clear_proc_handler(
         ret = proc_dointvec_minmax(ctl, write, buffer, lenp, ppos);
 
         if (!ret && write && *valp) {
-                printk("XFS Clearing xfsstats\n");
+                xfs_notice(NULL, "Clearing xfsstats");
                 for_each_possible_cpu(c) {
                         preempt_disable();
                         /* save vn_active, it's a universal truth! */
diff --git a/fs/xfs/quota/xfs_dquot.c b/fs/xfs/quota/xfs_dquot.c
index d22aa3103106..7e2416478503 100644
--- a/fs/xfs/quota/xfs_dquot.c
+++ b/fs/xfs/quota/xfs_dquot.c
@@ -544,9 +544,10 @@ xfs_qm_dqtobp(
         /*
          * A simple sanity check in case we got a corrupted dquot...
          */
-        if (xfs_qm_dqcheck(ddq, id, dqp->dq_flags & XFS_DQ_ALLTYPES,
+        error = xfs_qm_dqcheck(mp, ddq, id, dqp->dq_flags & XFS_DQ_ALLTYPES,
                            flags & (XFS_QMOPT_DQREPAIR|XFS_QMOPT_DOWARN),
-                           "dqtobp")) {
+                           "dqtobp");
+        if (error) {
                 if (!(flags & XFS_QMOPT_DQREPAIR)) {
                         xfs_trans_brelse(tp, bp);
                         return XFS_ERROR(EIO);
@@ -827,7 +828,7 @@ xfs_qm_dqget(
         if (xfs_do_dqerror) {
                 if ((xfs_dqerror_target == mp->m_ddev_targp) &&
                     (xfs_dqreq_num++ % xfs_dqerror_mod) == 0) {
-                        cmn_err(CE_DEBUG, "Returning error in dqget");
+                        xfs_debug(mp, "Returning error in dqget");
                         return (EIO);
                 }
         }
@@ -1207,8 +1208,9 @@ xfs_qm_dqflush(
         /*
          * A simple sanity check in case we got a corrupted dquot..
          */
-        if (xfs_qm_dqcheck(&dqp->q_core, be32_to_cpu(ddqp->d_id), 0,
-                           XFS_QMOPT_DOWARN, "dqflush (incore copy)")) {
+        error = xfs_qm_dqcheck(mp, &dqp->q_core, be32_to_cpu(ddqp->d_id), 0,
+                           XFS_QMOPT_DOWARN, "dqflush (incore copy)");
+        if (error) {
                 xfs_buf_relse(bp);
                 xfs_dqfunlock(dqp);
                 xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
@@ -1391,8 +1393,8 @@ xfs_qm_dqpurge(
                  */
                 error = xfs_qm_dqflush(dqp, SYNC_WAIT);
                 if (error)
-                        xfs_fs_cmn_err(CE_WARN, mp,
-                                "xfs_qm_dqpurge: dquot %p flush failed", dqp);
+                        xfs_warn(mp, "%s: dquot %p flush failed",
+                                __func__, dqp);
                 xfs_dqflock(dqp);
         }
         ASSERT(atomic_read(&dqp->q_pincount) == 0);
@@ -1425,36 +1427,38 @@ xfs_qm_dqpurge(
 void
 xfs_qm_dqprint(xfs_dquot_t *dqp)
 {
-        cmn_err(CE_DEBUG, "-----------KERNEL DQUOT----------------");
-        cmn_err(CE_DEBUG, "---- dquotID =  %d",
+        struct xfs_mount        *mp = dqp->q_mount;
+
+        xfs_debug(mp, "-----------KERNEL DQUOT----------------");
+        xfs_debug(mp, "---- dquotID =  %d",
                 (int)be32_to_cpu(dqp->q_core.d_id));
-        cmn_err(CE_DEBUG, "---- type    =  %s", DQFLAGTO_TYPESTR(dqp));
-        cmn_err(CE_DEBUG, "---- fs      =  0x%p", dqp->q_mount);
-        cmn_err(CE_DEBUG, "---- blkno   =  0x%x", (int) dqp->q_blkno);
-        cmn_err(CE_DEBUG, "---- boffset =  0x%x", (int) dqp->q_bufoffset);
-        cmn_err(CE_DEBUG, "---- blkhlimit =  %Lu (0x%x)",
+        xfs_debug(mp, "---- type    =  %s", DQFLAGTO_TYPESTR(dqp));
+        xfs_debug(mp, "---- fs      =  0x%p", dqp->q_mount);
+        xfs_debug(mp, "---- blkno   =  0x%x", (int) dqp->q_blkno);
+        xfs_debug(mp, "---- boffset =  0x%x", (int) dqp->q_bufoffset);
+        xfs_debug(mp, "---- blkhlimit =  %Lu (0x%x)",
                 be64_to_cpu(dqp->q_core.d_blk_hardlimit),
                 (int)be64_to_cpu(dqp->q_core.d_blk_hardlimit));
-        cmn_err(CE_DEBUG, "---- blkslimit =  %Lu (0x%x)",
+        xfs_debug(mp, "---- blkslimit =  %Lu (0x%x)",
                 be64_to_cpu(dqp->q_core.d_blk_softlimit),
                 (int)be64_to_cpu(dqp->q_core.d_blk_softlimit));
-        cmn_err(CE_DEBUG, "---- inohlimit =  %Lu (0x%x)",
+        xfs_debug(mp, "---- inohlimit =  %Lu (0x%x)",
                 be64_to_cpu(dqp->q_core.d_ino_hardlimit),
                 (int)be64_to_cpu(dqp->q_core.d_ino_hardlimit));
-        cmn_err(CE_DEBUG, "---- inoslimit =  %Lu (0x%x)",
+        xfs_debug(mp, "---- inoslimit =  %Lu (0x%x)",
                 be64_to_cpu(dqp->q_core.d_ino_softlimit),
                 (int)be64_to_cpu(dqp->q_core.d_ino_softlimit));
-        cmn_err(CE_DEBUG, "---- bcount  =  %Lu (0x%x)",
+        xfs_debug(mp, "---- bcount  =  %Lu (0x%x)",
                 be64_to_cpu(dqp->q_core.d_bcount),
                 (int)be64_to_cpu(dqp->q_core.d_bcount));
-        cmn_err(CE_DEBUG, "---- icount  =  %Lu (0x%x)",
+        xfs_debug(mp, "---- icount  =  %Lu (0x%x)",
                 be64_to_cpu(dqp->q_core.d_icount),
                 (int)be64_to_cpu(dqp->q_core.d_icount));
-        cmn_err(CE_DEBUG, "---- btimer  =  %d",
+        xfs_debug(mp, "---- btimer  =  %d",
                 (int)be32_to_cpu(dqp->q_core.d_btimer));
-        cmn_err(CE_DEBUG, "---- itimer  =  %d",
+        xfs_debug(mp, "---- itimer  =  %d",
                 (int)be32_to_cpu(dqp->q_core.d_itimer));
-        cmn_err(CE_DEBUG, "---------------------------");
+        xfs_debug(mp, "---------------------------");
 }
 #endif
 
diff --git a/fs/xfs/quota/xfs_dquot_item.c b/fs/xfs/quota/xfs_dquot_item.c
index 2a1f3dc10a02..9e0e2fa3f2c8 100644
--- a/fs/xfs/quota/xfs_dquot_item.c
+++ b/fs/xfs/quota/xfs_dquot_item.c
@@ -136,9 +136,8 @@ xfs_qm_dquot_logitem_push(
          */
         error = xfs_qm_dqflush(dqp, 0);
         if (error)
-                xfs_fs_cmn_err(CE_WARN, dqp->q_mount,
-                        "xfs_qm_dquot_logitem_push: push error %d on dqp %p",
-                        error, dqp);
+                xfs_warn(dqp->q_mount, "%s: push error %d on dqp %p",
+                        __func__, error, dqp);
         xfs_dqunlock(dqp);
 }
 
diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c
index 206a2815ced6..254ee062bd7d 100644
--- a/fs/xfs/quota/xfs_qm.c
+++ b/fs/xfs/quota/xfs_qm.c
@@ -80,7 +80,7 @@ xfs_qm_dquot_list_print(
         int             i = 0;
 
         list_for_each_entry(dqp, &mp->m_quotainfo->qi_dqlist_lock, qi_mplist) {
-                cmn_err(CE_DEBUG, "   %d. \"%d (%s)\"   "
+                xfs_debug(mp, "   %d. \"%d (%s)\"   "
                                   "bcnt = %lld, icnt = %lld, refs = %d",
                         i++, be32_to_cpu(dqp->q_core.d_id),
                         DQFLAGTO_TYPESTR(dqp),
@@ -205,7 +205,7 @@ xfs_qm_destroy(
         list_for_each_entry_safe(dqp, n, &xqm->qm_dqfrlist, q_freelist) {
                 xfs_dqlock(dqp);
 #ifdef QUOTADEBUG
-                cmn_err(CE_DEBUG, "FREELIST destroy 0x%p", dqp);
+                xfs_debug(dqp->q_mount, "FREELIST destroy 0x%p", dqp);
 #endif
                 list_del_init(&dqp->q_freelist);
                 xfs_Gqm->qm_dqfrlist_cnt--;
@@ -341,9 +341,7 @@ xfs_qm_mount_quotas(
          * quotas immediately.
          */
         if (mp->m_sb.sb_rextents) {
-                cmn_err(CE_NOTE,
-                        "Cannot turn on quotas for realtime filesystem %s",
-                        mp->m_fsname);
+                xfs_notice(mp, "Cannot turn on quotas for realtime filesystem");
                 mp->m_qflags = 0;
                 goto write_changes;
         }
@@ -402,14 +400,13 @@ xfs_qm_mount_quotas(
                          * off, but the on disk superblock doesn't know that !
                          */
                         ASSERT(!(XFS_IS_QUOTA_RUNNING(mp)));
-                        xfs_fs_cmn_err(CE_ALERT, mp,
-                                "XFS mount_quotas: Superblock update failed!");
+                        xfs_alert(mp, "%s: Superblock update failed!",
+                                __func__);
                 }
         }
 
         if (error) {
-                xfs_fs_cmn_err(CE_WARN, mp,
-                        "Failed to initialize disk quotas.");
+                xfs_warn(mp, "Failed to initialize disk quotas.");
                 return;
         }
 
@@ -1230,13 +1227,6 @@ xfs_qm_qino_alloc(
         }
 
         /*
-         * Keep an extra reference to this quota inode. This inode is
-         * locked exclusively and joined to the transaction already.
-         */
-        ASSERT(xfs_isilocked(*ip, XFS_ILOCK_EXCL));
-        IHOLD(*ip);
-
-        /*
          * Make the changes in the superblock, and log those too.
          * sbfields arg may contain fields other than *QUOTINO;
          * VERSIONNUM for example.
@@ -1264,7 +1254,7 @@ xfs_qm_qino_alloc(
         xfs_mod_sb(tp, sbfields);
 
         if ((error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES))) {
-                xfs_fs_cmn_err(CE_ALERT, mp, "XFS qino_alloc failed!");
+                xfs_alert(mp, "%s failed (error %d)!", __func__, error);
                 return error;
         }
         return 0;
@@ -1299,7 +1289,7 @@ xfs_qm_reset_dqcounts(
                  * output any warnings because it's perfectly possible to
                  * find uninitialised dquot blks. See comment in xfs_qm_dqcheck.
                  */
-                (void) xfs_qm_dqcheck(ddq, id+j, type, XFS_QMOPT_DQREPAIR,
+                (void) xfs_qm_dqcheck(mp, ddq, id+j, type, XFS_QMOPT_DQREPAIR,
                                       "xfs_quotacheck");
                 ddq->d_bcount = 0;
                 ddq->d_icount = 0;
@@ -1676,7 +1666,7 @@ xfs_qm_quotacheck(
          */
         ASSERT(list_empty(&mp->m_quotainfo->qi_dqlist));
 
-        cmn_err(CE_NOTE, "XFS quotacheck %s: Please wait.", mp->m_fsname);
+        xfs_notice(mp, "Quotacheck needed: Please wait.");
 
         /*
          * First we go thru all the dquots on disk, USR and GRP/PRJ, and reset
@@ -1754,9 +1744,9 @@ xfs_qm_quotacheck(
 
  error_return:
         if (error) {
-                cmn_err(CE_WARN, "XFS quotacheck %s: Unsuccessful (Error %d): "
-                        "Disabling quotas.",
-                        mp->m_fsname, error);
+                xfs_warn(mp,
+        "Quotacheck: Unsuccessful (Error %d): Disabling quotas.",
+                        error);
                 /*
                  * We must turn off quotas.
                  */
@@ -1764,12 +1754,11 @@ xfs_qm_quotacheck(
                 ASSERT(xfs_Gqm != NULL);
                 xfs_qm_destroy_quotainfo(mp);
                 if (xfs_mount_reset_sbqflags(mp)) {
-                        cmn_err(CE_WARN, "XFS quotacheck %s: "
-                                "Failed to reset quota flags.", mp->m_fsname);
+                        xfs_warn(mp,
+                                "Quotacheck: Failed to reset quota flags.");
                 }
-        } else {
-                cmn_err(CE_NOTE, "XFS quotacheck %s: Done.", mp->m_fsname);
-        }
+        } else
+                xfs_notice(mp, "Quotacheck: Done.");
         return (error);
 }
 
@@ -1937,8 +1926,8 @@ again:
                          */
                         error = xfs_qm_dqflush(dqp, 0);
                         if (error) {
-                                xfs_fs_cmn_err(CE_WARN, mp,
-                        "xfs_qm_dqreclaim: dquot %p flush failed", dqp);
+                                xfs_warn(mp, "%s: dquot %p flush failed",
+                                        __func__, dqp);
                         }
                         goto dqunlock;
                 }
@@ -2115,7 +2104,7 @@ xfs_qm_write_sb_changes(
         int             error;
 
 #ifdef QUOTADEBUG
-        cmn_err(CE_NOTE, "Writing superblock quota changes :%s", mp->m_fsname);
+        xfs_notice(mp, "Writing superblock quota changes");
 #endif
         tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SBCHANGE);
         if ((error = xfs_trans_reserve(tp, 0,
diff --git a/fs/xfs/quota/xfs_qm_bhv.c b/fs/xfs/quota/xfs_qm_bhv.c
index 45b5cb1788ab..774d7ec6df8e 100644
--- a/fs/xfs/quota/xfs_qm_bhv.c
+++ b/fs/xfs/quota/xfs_qm_bhv.c
@@ -119,8 +119,7 @@ xfs_qm_newmount(
              (gquotaondisk && !XFS_IS_GQUOTA_ON(mp)) ||
             (!gquotaondisk &&  XFS_IS_OQUOTA_ON(mp)))  &&
             xfs_dev_is_read_only(mp, "changing quota state")) {
-                cmn_err(CE_WARN,
-                        "XFS: please mount with%s%s%s%s.",
+                xfs_warn(mp, "please mount with%s%s%s%s.",
                         (!quotaondisk ? "out quota" : ""),
                         (uquotaondisk ? " usrquota" : ""),
                         (pquotaondisk ? " prjquota" : ""),
diff --git a/fs/xfs/quota/xfs_qm_syscalls.c b/fs/xfs/quota/xfs_qm_syscalls.c
index bdebc183223e..c82f06778a27 100644
--- a/fs/xfs/quota/xfs_qm_syscalls.c
+++ b/fs/xfs/quota/xfs_qm_syscalls.c
@@ -41,12 +41,6 @@
 #include "xfs_qm.h"
 #include "xfs_trace.h"
 
-#ifdef DEBUG
-# define qdprintk(s, args...)   cmn_err(CE_DEBUG, s, ## args)
-#else
-# define qdprintk(s, args...)   do { } while (0)
-#endif
-
 STATIC int      xfs_qm_log_quotaoff(xfs_mount_t *, xfs_qoff_logitem_t **, uint);
 STATIC int      xfs_qm_log_quotaoff_end(xfs_mount_t *, xfs_qoff_logitem_t *,
                                         uint);
@@ -294,7 +288,8 @@ xfs_qm_scall_trunc_qfiles(
         int             error = 0, error2 = 0;
 
         if (!xfs_sb_version_hasquota(&mp->m_sb) || flags == 0) {
-                qdprintk("qtrunc flags=%x m_qflags=%x\n", flags, mp->m_qflags);
+                xfs_debug(mp, "%s: flags=%x m_qflags=%x\n",
+                        __func__, flags, mp->m_qflags);
                 return XFS_ERROR(EINVAL);
         }
 
@@ -331,7 +326,8 @@ xfs_qm_scall_quotaon(
         sbflags = 0;
 
         if (flags == 0) {
-                qdprintk("quotaon: zero flags, m_qflags=%x\n", mp->m_qflags);
+                xfs_debug(mp, "%s: zero flags, m_qflags=%x\n",
+                        __func__, mp->m_qflags);
                 return XFS_ERROR(EINVAL);
         }
 
@@ -352,8 +348,9 @@ xfs_qm_scall_quotaon(
             (flags & XFS_GQUOTA_ACCT) == 0 &&
             (mp->m_sb.sb_qflags & XFS_GQUOTA_ACCT) == 0 &&
             (flags & XFS_OQUOTA_ENFD))) {
-                qdprintk("Can't enforce without acct, flags=%x sbflags=%x\n",
-                        flags, mp->m_sb.sb_qflags);
+                xfs_debug(mp,
+                        "%s: Can't enforce without acct, flags=%x sbflags=%x\n",
+                        __func__, flags, mp->m_sb.sb_qflags);
                 return XFS_ERROR(EINVAL);
         }
         /*
@@ -541,7 +538,7 @@ xfs_qm_scall_setqlim(
                         q->qi_bsoftlimit = soft;
                 }
         } else {
-                qdprintk("blkhard %Ld < blksoft %Ld\n", hard, soft);
+                xfs_debug(mp, "blkhard %Ld < blksoft %Ld\n", hard, soft);
         }
         hard = (newlim->d_fieldmask & FS_DQ_RTBHARD) ?
                 (xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_rtb_hardlimit) :
@@ -557,7 +554,7 @@ xfs_qm_scall_setqlim(
                         q->qi_rtbsoftlimit = soft;
                 }
         } else {
-                qdprintk("rtbhard %Ld < rtbsoft %Ld\n", hard, soft);
+                xfs_debug(mp, "rtbhard %Ld < rtbsoft %Ld\n", hard, soft);
         }
 
         hard = (newlim->d_fieldmask & FS_DQ_IHARD) ?
@@ -574,7 +571,7 @@ xfs_qm_scall_setqlim(
                         q->qi_isoftlimit = soft;
                 }
         } else {
-                qdprintk("ihard %Ld < isoft %Ld\n", hard, soft);
+                xfs_debug(mp, "ihard %Ld < isoft %Ld\n", hard, soft);
         }
 
         /*
@@ -939,10 +936,11 @@ struct mutex  qcheck_lock;
 #define DQTEST_LIST_PRINT(l, NXT, title) \
 { \
           xfs_dqtest_t  *dqp; int i = 0;\
-          cmn_err(CE_DEBUG, "%s (#%d)", title, (int) (l)->qh_nelems); \
+          xfs_debug(NULL, "%s (#%d)", title, (int) (l)->qh_nelems); \
           for (dqp = (xfs_dqtest_t *)(l)->qh_next; dqp != NULL; \
                dqp = (xfs_dqtest_t *)dqp->NXT) { \
-                cmn_err(CE_DEBUG, "  %d. \"%d (%s)\"  bcnt = %d, icnt = %d", \
+                xfs_debug(dqp->q_mount,         \
+                        "  %d. \"%d (%s)\"  bcnt = %d, icnt = %d", \
                          ++i, dqp->d_id, DQFLAGTO_TYPESTR(dqp),      \
                          dqp->d_bcount, dqp->d_icount); } \
 }
@@ -966,16 +964,17 @@ xfs_qm_hashinsert(xfs_dqhash_t *h, xfs_dqtest_t *dqp)
 }
 STATIC void
 xfs_qm_dqtest_print(
-        xfs_dqtest_t    *d)
+        struct xfs_mount        *mp,
+        struct dqtest           *d)
 {
-        cmn_err(CE_DEBUG, "-----------DQTEST DQUOT----------------");
-        cmn_err(CE_DEBUG, "---- dquot ID = %d", d->d_id);
-        cmn_err(CE_DEBUG, "---- fs       = 0x%p", d->q_mount);
-        cmn_err(CE_DEBUG, "---- bcount   = %Lu (0x%x)",
+        xfs_debug(mp, "-----------DQTEST DQUOT----------------");
+        xfs_debug(mp, "---- dquot ID = %d", d->d_id);
+        xfs_debug(mp, "---- fs       = 0x%p", d->q_mount);
+        xfs_debug(mp, "---- bcount   = %Lu (0x%x)",
                 d->d_bcount, (int)d->d_bcount);
-        cmn_err(CE_DEBUG, "---- icount   = %Lu (0x%x)",
+        xfs_debug(mp, "---- icount   = %Lu (0x%x)",
                 d->d_icount, (int)d->d_icount);
-        cmn_err(CE_DEBUG, "---------------------------");
+        xfs_debug(mp, "---------------------------");
 }
 
 STATIC void
@@ -989,12 +988,14 @@ xfs_qm_dqtest_failed(
 {
         qmtest_nfails++;
         if (error)
-                cmn_err(CE_DEBUG, "quotacheck failed id=%d, err=%d\nreason: %s",
-                       d->d_id, error, reason);
+                xfs_debug(dqp->q_mount,
+                        "quotacheck failed id=%d, err=%d\nreason: %s",
+                        d->d_id, error, reason);
         else
-                cmn_err(CE_DEBUG, "quotacheck failed id=%d (%s) [%d != %d]",
-                       d->d_id, reason, (int)a, (int)b);
-        xfs_qm_dqtest_print(d);
+                xfs_debug(dqp->q_mount,
+                        "quotacheck failed id=%d (%s) [%d != %d]",
+                        d->d_id, reason, (int)a, (int)b);
+        xfs_qm_dqtest_print(dqp->q_mount, d);
         if (dqp)
                 xfs_qm_dqprint(dqp);
 }
@@ -1021,9 +1022,9 @@ xfs_dqtest_cmp2(
             be64_to_cpu(dqp->q_core.d_bcount) >=
             be64_to_cpu(dqp->q_core.d_blk_softlimit)) {
                 if (!dqp->q_core.d_btimer && dqp->q_core.d_id) {
-                        cmn_err(CE_DEBUG,
-                                "%d [%s] [0x%p] BLK TIMER NOT STARTED",
-                                d->d_id, DQFLAGTO_TYPESTR(d), d->q_mount);
+                        xfs_debug(dqp->q_mount,
+                                "%d [%s] BLK TIMER NOT STARTED",
+                                d->d_id, DQFLAGTO_TYPESTR(d));
                         err++;
                 }
         }
@@ -1031,16 +1032,16 @@ xfs_dqtest_cmp2(
             be64_to_cpu(dqp->q_core.d_icount) >=
             be64_to_cpu(dqp->q_core.d_ino_softlimit)) {
                 if (!dqp->q_core.d_itimer && dqp->q_core.d_id) {
-                        cmn_err(CE_DEBUG,
-                                "%d [%s] [0x%p] INO TIMER NOT STARTED",
-                                d->d_id, DQFLAGTO_TYPESTR(d), d->q_mount);
+                        xfs_debug(dqp->q_mount,
+                                "%d [%s] INO TIMER NOT STARTED",
+                                d->d_id, DQFLAGTO_TYPESTR(d));
                         err++;
                 }
         }
 #ifdef QUOTADEBUG
         if (!err) {
-                cmn_err(CE_DEBUG, "%d [%s] [0x%p] qchecked",
-                        d->d_id, DQFLAGTO_TYPESTR(d), d->q_mount);
+                xfs_debug(dqp->q_mount, "%d [%s] qchecked",
+                        d->d_id, DQFLAGTO_TYPESTR(d));
         }
 #endif
         return (err);
@@ -1137,8 +1138,8 @@ xfs_qm_internalqcheck_adjust(
 
         if (ino == mp->m_sb.sb_uquotino || ino == mp->m_sb.sb_gquotino) {
                 *res = BULKSTAT_RV_NOTHING;
-                qdprintk("internalqcheck: ino=%llu, uqino=%llu, gqino=%llu\n",
-                        (unsigned long long) ino,
+                xfs_debug(mp, "%s: ino=%llu, uqino=%llu, gqino=%llu\n",
+                        __func__, (unsigned long long) ino,
                         (unsigned long long) mp->m_sb.sb_uquotino,
                         (unsigned long long) mp->m_sb.sb_gquotino);
                 return XFS_ERROR(EINVAL);
@@ -1223,12 +1224,12 @@ xfs_qm_internalqcheck(
                                  xfs_qm_internalqcheck_adjust,
                                  0, NULL, &done);
                 if (error) {
-                        cmn_err(CE_DEBUG, "Bulkstat returned error 0x%x", error);
+                        xfs_debug(mp, "Bulkstat returned error 0x%x", error);
                         break;
                 }
         } while (!done);
 
-        cmn_err(CE_DEBUG, "Checking results against system dquots");
+        xfs_debug(mp, "Checking results against system dquots");
         for (i = 0; i < qmtest_hashmask; i++) {
                 xfs_dqtest_t    *d, *n;
                 xfs_dqhash_t    *h;
@@ -1246,10 +1247,10 @@ xfs_qm_internalqcheck(
         }
 
         if (qmtest_nfails) {
-                cmn_err(CE_DEBUG, "******** quotacheck failed  ********");
-                cmn_err(CE_DEBUG, "failures = %d", qmtest_nfails);
+                xfs_debug(mp, "******** quotacheck failed  ********");
+                xfs_debug(mp, "failures = %d", qmtest_nfails);
         } else {
-                cmn_err(CE_DEBUG, "******** quotacheck successful! ********");
+                xfs_debug(mp, "******** quotacheck successful! ********");
         }
         kmem_free(qmtest_udqtab);
         kmem_free(qmtest_gdqtab);
diff --git a/fs/xfs/quota/xfs_trans_dquot.c b/fs/xfs/quota/xfs_trans_dquot.c
index 7de91d1b75c0..2a3648731331 100644
--- a/fs/xfs/quota/xfs_trans_dquot.c
+++ b/fs/xfs/quota/xfs_trans_dquot.c
@@ -643,8 +643,9 @@ xfs_trans_dqresv(
              (XFS_IS_OQUOTA_ENFORCED(dqp->q_mount) &&
               (XFS_QM_ISPDQ(dqp) || XFS_QM_ISGDQ(dqp))))) {
 #ifdef QUOTADEBUG
-                cmn_err(CE_DEBUG, "BLK Res: nblks=%ld + resbcount=%Ld"
-                          " > hardlimit=%Ld?", nblks, *resbcountp, hardlimit);
+                xfs_debug(mp,
+                        "BLK Res: nblks=%ld + resbcount=%Ld > hardlimit=%Ld?",
+                        nblks, *resbcountp, hardlimit);
 #endif
                 if (nblks > 0) {
                         /*
diff --git a/fs/xfs/support/debug.c b/fs/xfs/support/debug.c
deleted file mode 100644
index 0df88897ef84..000000000000
--- a/fs/xfs/support/debug.c
+++ /dev/null
@@ -1,107 +0,0 @@
-/*
- * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
- * 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.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  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 the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#include <xfs.h>
-#include "debug.h"
-
-/* xfs_mount.h drags a lot of crap in, sorry.. */
-#include "xfs_sb.h"
-#include "xfs_inum.h"
-#include "xfs_ag.h"
-#include "xfs_mount.h"
-#include "xfs_error.h"
-
-void
-cmn_err(
-        const char      *lvl,
-        const char      *fmt,
-        ...)
-{
-        struct va_format vaf;
-        va_list         args;
-
-        va_start(args, fmt);
-        vaf.fmt = fmt;
-        vaf.va = &args;
-
-        printk("%s%pV", lvl, &vaf);
-        va_end(args);
-
-        BUG_ON(strncmp(lvl, KERN_EMERG, strlen(KERN_EMERG)) == 0);
-}
-
-void
-xfs_fs_cmn_err(
-        const char              *lvl,
-        struct xfs_mount        *mp,
-        const char              *fmt,
-        ...)
-{
-        struct va_format        vaf;
-        va_list                 args;
-
-        va_start(args, fmt);
-        vaf.fmt = fmt;
-        vaf.va = &args;
-
-        printk("%sFilesystem %s: %pV", lvl, mp->m_fsname, &vaf);
-        va_end(args);
-
-        BUG_ON(strncmp(lvl, KERN_EMERG, strlen(KERN_EMERG)) == 0);
-}
-
-/* All callers to xfs_cmn_err use CE_ALERT, so don't bother testing lvl */
-void
-xfs_cmn_err(
-        int                     panic_tag,
-        const char              *lvl,
-        struct xfs_mount        *mp,
-        const char              *fmt,
-        ...)
-{
-        struct va_format        vaf;
-        va_list                 args;
-        int                     do_panic = 0;
-
-        if (xfs_panic_mask && (xfs_panic_mask & panic_tag)) {
-                printk(KERN_ALERT "XFS: Transforming an alert into a BUG.");
-                do_panic = 1;
-        }
-
-        va_start(args, fmt);
-        vaf.fmt = fmt;
-        vaf.va = &args;
-
-        printk(KERN_ALERT "Filesystem %s: %pV", mp->m_fsname, &vaf);
-        va_end(args);
-
-        BUG_ON(do_panic);
-}
-
-void
-assfail(char *expr, char *file, int line)
-{
-        printk(KERN_CRIT "Assertion failed: %s, file: %s, line: %d\n", expr,
-               file, line);
-        BUG();
-}
-
-void
-xfs_hex_dump(void *p, int length)
-{
-        print_hex_dump(KERN_ALERT, "", DUMP_PREFIX_ADDRESS, 16, 1, p, length, 1);
-}
diff --git a/fs/xfs/support/debug.h b/fs/xfs/support/debug.h
deleted file mode 100644
index 05699f67d475..000000000000
--- a/fs/xfs/support/debug.h
+++ /dev/null
@@ -1,61 +0,0 @@
-/*
- * Copyright (c) 2000-2005 Silicon Graphics, Inc.
- * 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.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  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 the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#ifndef __XFS_SUPPORT_DEBUG_H__
-#define __XFS_SUPPORT_DEBUG_H__
-
-#include <stdarg.h>
-
-struct xfs_mount;
-
-#define CE_DEBUG        KERN_DEBUG
-#define CE_CONT         KERN_INFO
-#define CE_NOTE         KERN_NOTICE
-#define CE_WARN         KERN_WARNING
-#define CE_ALERT        KERN_ALERT
-#define CE_PANIC        KERN_EMERG
-
-void cmn_err(const char *lvl, const char *fmt, ...)
-                __attribute__ ((format (printf, 2, 3)));
-void xfs_fs_cmn_err( const char *lvl, struct xfs_mount *mp,
-                const char *fmt, ...) __attribute__ ((format (printf, 3, 4)));
-void xfs_cmn_err( int panic_tag, const char *lvl, struct xfs_mount *mp,
-                const char *fmt, ...) __attribute__ ((format (printf, 4, 5)));
-
-extern void assfail(char *expr, char *f, int l);
-
-#define ASSERT_ALWAYS(expr)     \
-        (unlikely(expr) ? (void)0 : assfail(#expr, __FILE__, __LINE__))
-
-#ifndef DEBUG
-#define ASSERT(expr)    ((void)0)
-
-#ifndef STATIC
-# define STATIC static noinline
-#endif
-
-#else /* DEBUG */
-
-#define ASSERT(expr)    \
-        (unlikely(expr) ? (void)0 : assfail(#expr, __FILE__, __LINE__))
-
-#ifndef STATIC
-# define STATIC noinline
-#endif
-
-#endif /* DEBUG */
-#endif  /* __XFS_SUPPORT_DEBUG_H__ */
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index f3227984a9bf..4bc3c649aee4 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -147,10 +147,9 @@ xfs_alloc_get_rec(
  */
 STATIC void
 xfs_alloc_compute_aligned(
+        xfs_alloc_arg_t *args,          /* allocation argument structure */
         xfs_agblock_t   foundbno,       /* starting block in found extent */
         xfs_extlen_t    foundlen,       /* length in found extent */
-        xfs_extlen_t    alignment,      /* alignment for allocation */
-        xfs_extlen_t    minlen,         /* minimum length for allocation */
         xfs_agblock_t   *resbno,        /* result block number */
         xfs_extlen_t    *reslen)        /* result length */
 {
@@ -158,8 +157,8 @@ xfs_alloc_compute_aligned(
         xfs_extlen_t    diff;
         xfs_extlen_t    len;
 
-        if (alignment > 1 && foundlen >= minlen) {
-                bno = roundup(foundbno, alignment);
+        if (args->alignment > 1 && foundlen >= args->minlen) {
+                bno = roundup(foundbno, args->alignment);
                 diff = bno - foundbno;
                 len = diff >= foundlen ? 0 : foundlen - diff;
         } else {
@@ -464,6 +463,27 @@ xfs_alloc_read_agfl(
         return 0;
 }
 
+STATIC int
+xfs_alloc_update_counters(
+        struct xfs_trans        *tp,
+        struct xfs_perag        *pag,
+        struct xfs_buf          *agbp,
+        long                    len)
+{
+        struct xfs_agf          *agf = XFS_BUF_TO_AGF(agbp);
+
+        pag->pagf_freeblks += len;
+        be32_add_cpu(&agf->agf_freeblks, len);
+
+        xfs_trans_agblocks_delta(tp, len);
+        if (unlikely(be32_to_cpu(agf->agf_freeblks) >
+                     be32_to_cpu(agf->agf_length)))
+                return EFSCORRUPTED;
+
+        xfs_alloc_log_agf(tp, agbp, XFS_AGF_FREEBLKS);
+        return 0;
+}
+
 /*
  * Allocation group level functions.
  */
@@ -505,49 +525,44 @@ xfs_alloc_ag_vextent(
                 ASSERT(0);
                 /* NOTREACHED */
         }
-        if (error)
+
+        if (error || args->agbno == NULLAGBLOCK)
                 return error;
-        /*
-         * If the allocation worked, need to change the agf structure
-         * (and log it), and the superblock.
-         */
-        if (args->agbno != NULLAGBLOCK) {
-                xfs_agf_t       *agf;   /* allocation group freelist header */
-                long            slen = (long)args->len;
 
-                ASSERT(args->len >= args->minlen && args->len <= args->maxlen);
-                ASSERT(!(args->wasfromfl) || !args->isfl);
-                ASSERT(args->agbno % args->alignment == 0);
-                if (!(args->wasfromfl)) {
-
-                        agf = XFS_BUF_TO_AGF(args->agbp);
-                        be32_add_cpu(&agf->agf_freeblks, -(args->len));
-                        xfs_trans_agblocks_delta(args->tp,
-                                                 -((long)(args->len)));
-                        args->pag->pagf_freeblks -= args->len;
-                        ASSERT(be32_to_cpu(agf->agf_freeblks) <=
-                                be32_to_cpu(agf->agf_length));
-                        xfs_alloc_log_agf(args->tp, args->agbp,
-                                                XFS_AGF_FREEBLKS);
-                        /*
-                         * Search the busylist for these blocks and mark the
-                         * transaction as synchronous if blocks are found. This
-                         * avoids the need to block due to a synchronous log
-                         * force to ensure correct ordering as the synchronous
-                         * transaction will guarantee that for us.
-                         */
-                        if (xfs_alloc_busy_search(args->mp, args->agno,
-                                                args->agbno, args->len))
-                                xfs_trans_set_sync(args->tp);
-                }
-                if (!args->isfl)
-                        xfs_trans_mod_sb(args->tp,
-                                args->wasdel ? XFS_TRANS_SB_RES_FDBLOCKS :
-                                        XFS_TRANS_SB_FDBLOCKS, -slen);
-                XFS_STATS_INC(xs_allocx);
-                XFS_STATS_ADD(xs_allocb, args->len);
+        ASSERT(args->len >= args->minlen);
+        ASSERT(args->len <= args->maxlen);
+        ASSERT(!args->wasfromfl || !args->isfl);
+        ASSERT(args->agbno % args->alignment == 0);
+
+        if (!args->wasfromfl) {
+                error = xfs_alloc_update_counters(args->tp, args->pag,
+                                                  args->agbp,
+                                                  -((long)(args->len)));
+                if (error)
+                        return error;
+
+                /*
+                 * Search the busylist for these blocks and mark the
+                 * transaction as synchronous if blocks are found. This
+                 * avoids the need to block due to a synchronous log
+                 * force to ensure correct ordering as the synchronous
+                 * transaction will guarantee that for us.
+                 */
+                if (xfs_alloc_busy_search(args->mp, args->agno,
+                                        args->agbno, args->len))
+                        xfs_trans_set_sync(args->tp);
         }
-        return 0;
+
+        if (!args->isfl) {
+                xfs_trans_mod_sb(args->tp, args->wasdel ?
+                                 XFS_TRANS_SB_RES_FDBLOCKS :
+                                 XFS_TRANS_SB_FDBLOCKS,
+                                 -((long)(args->len)));
+        }
+
+        XFS_STATS_INC(xs_allocx);
+        XFS_STATS_ADD(xs_allocb, args->len);
+        return error;
 }
 
 /*
@@ -693,8 +708,7 @@ xfs_alloc_find_best_extent(
                 if (error)
                         goto error0;
                 XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-                xfs_alloc_compute_aligned(*sbno, *slen, args->alignment,
-                                          args->minlen, &bno, slena);
+                xfs_alloc_compute_aligned(args, *sbno, *slen, &bno, slena);
 
                 /*
                  * The good extent is closer than this one.
@@ -866,8 +880,8 @@ xfs_alloc_ag_vextent_near(
                         if ((error = xfs_alloc_get_rec(cnt_cur, &ltbno, &ltlen, &i)))
                                 goto error0;
                         XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-                        xfs_alloc_compute_aligned(ltbno, ltlen, args->alignment,
-                                        args->minlen, &ltbnoa, &ltlena);
+                        xfs_alloc_compute_aligned(args, ltbno, ltlen,
+                                                  &ltbnoa, &ltlena);
                         if (ltlena < args->minlen)
                                 continue;
                         args->len = XFS_EXTLEN_MIN(ltlena, args->maxlen);
@@ -987,8 +1001,8 @@ xfs_alloc_ag_vextent_near(
                         if ((error = xfs_alloc_get_rec(bno_cur_lt, &ltbno, &ltlen, &i)))
                                 goto error0;
                         XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-                        xfs_alloc_compute_aligned(ltbno, ltlen, args->alignment,
-                                        args->minlen, &ltbnoa, &ltlena);
+                        xfs_alloc_compute_aligned(args, ltbno, ltlen,
+                                                  &ltbnoa, &ltlena);
                         if (ltlena >= args->minlen)
                                 break;
                         if ((error = xfs_btree_decrement(bno_cur_lt, 0, &i)))
@@ -1003,8 +1017,8 @@ xfs_alloc_ag_vextent_near(
                         if ((error = xfs_alloc_get_rec(bno_cur_gt, &gtbno, &gtlen, &i)))
                                 goto error0;
                         XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-                        xfs_alloc_compute_aligned(gtbno, gtlen, args->alignment,
-                                        args->minlen, &gtbnoa, &gtlena);
+                        xfs_alloc_compute_aligned(args, gtbno, gtlen,
+                                                  &gtbnoa, &gtlena);
                         if (gtlena >= args->minlen)
                                 break;
                         if ((error = xfs_btree_increment(bno_cur_gt, 0, &i)))
@@ -1183,8 +1197,7 @@ xfs_alloc_ag_vextent_size(
          * once aligned; if not, we search left for something better.
          * This can't happen in the second case above.
          */
-        xfs_alloc_compute_aligned(fbno, flen, args->alignment, args->minlen,
-                &rbno, &rlen);
+        xfs_alloc_compute_aligned(args, fbno, flen, &rbno, &rlen);
         rlen = XFS_EXTLEN_MIN(args->maxlen, rlen);
         XFS_WANT_CORRUPTED_GOTO(rlen == 0 ||
                         (rlen <= flen && rbno + rlen <= fbno + flen), error0);
@@ -1209,8 +1222,8 @@ xfs_alloc_ag_vextent_size(
                         XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
                         if (flen < bestrlen)
                                 break;
-                        xfs_alloc_compute_aligned(fbno, flen, args->alignment,
-                                args->minlen, &rbno, &rlen);
+                        xfs_alloc_compute_aligned(args, fbno, flen,
+                                                  &rbno, &rlen);
                         rlen = XFS_EXTLEN_MIN(args->maxlen, rlen);
                         XFS_WANT_CORRUPTED_GOTO(rlen == 0 ||
                                 (rlen <= flen && rbno + rlen <= fbno + flen),
@@ -1388,6 +1401,7 @@ xfs_free_ag_extent(
         xfs_mount_t     *mp;            /* mount point struct for filesystem */
         xfs_agblock_t   nbno;           /* new starting block of freespace */
         xfs_extlen_t    nlen;           /* new length of freespace */
+        xfs_perag_t     *pag;           /* per allocation group data */
 
         mp = tp->t_mountp;
         /*
@@ -1586,30 +1600,20 @@ xfs_free_ag_extent(
         XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
         xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
         cnt_cur = NULL;
+
         /*
          * Update the freespace totals in the ag and superblock.
          */
-        {
-                xfs_agf_t       *agf;
-                xfs_perag_t     *pag;           /* per allocation group data */
-
-                pag = xfs_perag_get(mp, agno);
-                pag->pagf_freeblks += len;
-                xfs_perag_put(pag);
-
-                agf = XFS_BUF_TO_AGF(agbp);
-                be32_add_cpu(&agf->agf_freeblks, len);
-                xfs_trans_agblocks_delta(tp, len);
-                XFS_WANT_CORRUPTED_GOTO(
-                        be32_to_cpu(agf->agf_freeblks) <=
-                        be32_to_cpu(agf->agf_length),
-                        error0);
-                xfs_alloc_log_agf(tp, agbp, XFS_AGF_FREEBLKS);
-                if (!isfl)
-                        xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, (long)len);
-                XFS_STATS_INC(xs_freex);
-                XFS_STATS_ADD(xs_freeb, len);
-        }
+        pag = xfs_perag_get(mp, agno);
+        error = xfs_alloc_update_counters(tp, pag, agbp, len);
+        xfs_perag_put(pag);
+        if (error)
+                goto error0;
+
+        if (!isfl)
+                xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, (long)len);
+        XFS_STATS_INC(xs_freex);
+        XFS_STATS_ADD(xs_freeb, len);
 
         trace_xfs_free_extent(mp, agno, bno, len, isfl, haveleft, haveright);
 
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index dc3afd7739ff..fa00788de2f5 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -2365,6 +2365,13 @@ xfs_bmap_rtalloc(
          */
         if (ralen * mp->m_sb.sb_rextsize >= MAXEXTLEN)
                 ralen = MAXEXTLEN / mp->m_sb.sb_rextsize;
+
+        /*
+         * Lock out other modifications to the RT bitmap inode.
+         */
+        xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL);
+        xfs_trans_ijoin_ref(ap->tp, mp->m_rbmip, XFS_ILOCK_EXCL);
+
         /*
          * If it's an allocation to an empty file at offset 0,
          * pick an extent that will space things out in the rt area.
@@ -3519,7 +3526,7 @@ xfs_bmap_search_extents(
 
         if (unlikely(!(gotp->br_startblock) && (*lastxp != NULLEXTNUM) &&
                      !(XFS_IS_REALTIME_INODE(ip) && fork == XFS_DATA_FORK))) {
-                xfs_cmn_err(XFS_PTAG_FSBLOCK_ZERO, CE_ALERT, ip->i_mount,
+                xfs_alert_tag(ip->i_mount, XFS_PTAG_FSBLOCK_ZERO,
                                 "Access to block zero in inode %llu "
                                 "start_block: %llx start_off: %llx "
                                 "blkcnt: %llx extent-state: %x lastx: %x\n",
@@ -4193,12 +4200,11 @@ xfs_bmap_read_extents(
                 num_recs = xfs_btree_get_numrecs(block);
                 if (unlikely(i + num_recs > room)) {
                         ASSERT(i + num_recs <= room);
-                        xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
+                        xfs_warn(ip->i_mount,
                                 "corrupt dinode %Lu, (btree extents).",
                                 (unsigned long long) ip->i_ino);
-                        XFS_ERROR_REPORT("xfs_bmap_read_extents(1)",
-                                         XFS_ERRLEVEL_LOW,
-                                        ip->i_mount);
+                        XFS_CORRUPTION_ERROR("xfs_bmap_read_extents(1)",
+                                XFS_ERRLEVEL_LOW, ip->i_mount, block);
                         goto error0;
                 }
                 XFS_WANT_CORRUPTED_GOTO(
@@ -5772,7 +5778,7 @@ xfs_check_block(
                         else
                                 thispa = XFS_BMBT_PTR_ADDR(mp, block, j, dmxr);
                         if (*thispa == *pp) {
-                                cmn_err(CE_WARN, "%s: thispa(%d) == pp(%d) %Ld",
+                                xfs_warn(mp, "%s: thispa(%d) == pp(%d) %Ld",
                                         __func__, j, i,
                                         (unsigned long long)be64_to_cpu(*thispa));
                                 panic("%s: ptrs are equal in node\n",
@@ -5937,11 +5943,11 @@ xfs_bmap_check_leaf_extents(
         return;
 
 error0:
-        cmn_err(CE_WARN, "%s: at error0", __func__);
+        xfs_warn(mp, "%s: at error0", __func__);
         if (bp_release)
                 xfs_trans_brelse(NULL, bp);
 error_norelse:
-        cmn_err(CE_WARN, "%s: BAD after btree leaves for %d extents",
+        xfs_warn(mp, "%s: BAD after btree leaves for %d extents",
                 __func__, i);
         panic("%s: CORRUPTED BTREE OR SOMETHING", __func__);
         return;
@@ -6144,7 +6150,7 @@ xfs_bmap_punch_delalloc_range(
                 if (error) {
                         /* something screwed, just bail */
                         if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
-                                xfs_fs_cmn_err(CE_ALERT, ip->i_mount,
+                                xfs_alert(ip->i_mount,
                         "Failed delalloc mapping lookup ino %lld fsb %lld.",
                                                 ip->i_ino, start_fsb);
                         }
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 6f8c21ce0d6d..e5413d96f1af 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -130,10 +130,12 @@ xfs_buf_item_log_check(
         orig = bip->bli_orig;
         buffer = XFS_BUF_PTR(bp);
         for (x = 0; x < XFS_BUF_COUNT(bp); x++) {
-                if (orig[x] != buffer[x] && !btst(bip->bli_logged, x))
-                        cmn_err(CE_PANIC,
-        "xfs_buf_item_log_check bip %x buffer %x orig %x index %d",
-                                bip, bp, orig, x);
+                if (orig[x] != buffer[x] && !btst(bip->bli_logged, x)) {
+                        xfs_emerg(bp->b_mount,
+                                "%s: bip %x buffer %x orig %x index %d",
+                                __func__, bip, bp, orig, x);
+                        ASSERT(0);
+                }
         }
 }
 #else
@@ -983,10 +985,9 @@ xfs_buf_iodone_callbacks(
         if (XFS_BUF_TARGET(bp) != lasttarg ||
             time_after(jiffies, (lasttime + 5*HZ))) {
                 lasttime = jiffies;
-                cmn_err(CE_ALERT, "Device %s, XFS metadata write error"
-                                " block 0x%llx in %s",
+                xfs_alert(mp, "Device %s: metadata write error block 0x%llx",
                         XFS_BUFTARG_NAME(XFS_BUF_TARGET(bp)),
-                      (__uint64_t)XFS_BUF_ADDR(bp), mp->m_fsname);
+                      (__uint64_t)XFS_BUF_ADDR(bp));
         }
         lasttarg = XFS_BUF_TARGET(bp);
 
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index 1c00bedb3175..6102ac6d1dff 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -1995,13 +1995,12 @@ xfs_da_do_buf(
                 error = mappedbno == -2 ? 0 : XFS_ERROR(EFSCORRUPTED);
                 if (unlikely(error == EFSCORRUPTED)) {
                         if (xfs_error_level >= XFS_ERRLEVEL_LOW) {
-                                cmn_err(CE_ALERT, "xfs_da_do_buf: bno %lld\n",
-                                        (long long)bno);
-                                cmn_err(CE_ALERT, "dir: inode %lld\n",
+                                xfs_alert(mp, "%s: bno %lld dir: inode %lld",
+                                        __func__, (long long)bno,
                                         (long long)dp->i_ino);
                                 for (i = 0; i < nmap; i++) {
-                                        cmn_err(CE_ALERT,
-                                                "[%02d] br_startoff %lld br_startblock %lld br_blockcount %lld br_state %d\n",
+                                        xfs_alert(mp,
+"[%02d] br_startoff %lld br_startblock %lld br_blockcount %lld br_state %d",
                                                 i,
                                                 (long long)mapp[i].br_startoff,
                                                 (long long)mapp[i].br_startblock,
diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c
index e60490bc00a6..be628677c288 100644
--- a/fs/xfs/xfs_dfrag.c
+++ b/fs/xfs/xfs_dfrag.c
@@ -270,9 +270,9 @@ xfs_swap_extents(
         /* check inode formats now that data is flushed */
         error = xfs_swap_extents_check_format(ip, tip);
         if (error) {
-                xfs_fs_cmn_err(CE_NOTE, mp,
+                xfs_notice(mp,
                     "%s: inode 0x%llx format is incompatible for exchanging.",
-                                __FILE__, ip->i_ino);
+                                __func__, ip->i_ino);
                 goto out_unlock;
         }
 
diff --git a/fs/xfs/xfs_dir2.c b/fs/xfs/xfs_dir2.c
index a1321bc7f192..dba7a71cedf3 100644
--- a/fs/xfs/xfs_dir2.c
+++ b/fs/xfs/xfs_dir2.c
@@ -159,7 +159,7 @@ xfs_dir_ino_validate(
                 XFS_AGINO_TO_INO(mp, agno, agino) == ino;
         if (unlikely(XFS_TEST_ERROR(!ino_ok, mp, XFS_ERRTAG_DIR_INO_VALIDATE,
                         XFS_RANDOM_DIR_INO_VALIDATE))) {
-                xfs_fs_cmn_err(CE_WARN, mp, "Invalid inode number 0x%Lx",
+                xfs_warn(mp, "Invalid inode number 0x%Lx",
                                 (unsigned long long) ino);
                 XFS_ERROR_REPORT("xfs_dir_ino_validate", XFS_ERRLEVEL_LOW, mp);
                 return XFS_ERROR(EFSCORRUPTED);
diff --git a/fs/xfs/xfs_dir2_node.c b/fs/xfs/xfs_dir2_node.c
index f9a0864b696a..a0aab7d3294f 100644
--- a/fs/xfs/xfs_dir2_node.c
+++ b/fs/xfs/xfs_dir2_node.c
@@ -899,10 +899,9 @@ xfs_dir2_leafn_rebalance(
         if(blk2->index < 0) {
                 state->inleaf = 1;
                 blk2->index = 0;
-                cmn_err(CE_ALERT,
-                        "xfs_dir2_leafn_rebalance: picked the wrong leaf? reverting original leaf: "
-                        "blk1->index %d\n",
-                        blk1->index);
+                xfs_alert(args->dp->i_mount,
+        "%s: picked the wrong leaf? reverting original leaf: blk1->index %d\n",
+                        __func__, blk1->index);
         }
 }
 
@@ -1641,26 +1640,22 @@ xfs_dir2_node_addname_int(
                         }
 
                         if (unlikely(xfs_dir2_db_to_fdb(mp, dbno) != fbno)) {
-                                cmn_err(CE_ALERT,
-                                        "xfs_dir2_node_addname_int: dir ino "
-                                        "%llu needed freesp block %lld for\n"
-                                        "  data block %lld, got %lld\n"
-                                        "  ifbno %llu lastfbno %d\n",
-                                        (unsigned long long)dp->i_ino,
+                                xfs_alert(mp,
+                        "%s: dir ino " "%llu needed freesp block %lld for\n"
+                        "  data block %lld, got %lld ifbno %llu lastfbno %d",
+                                        __func__, (unsigned long long)dp->i_ino,
                                         (long long)xfs_dir2_db_to_fdb(mp, dbno),
                                         (long long)dbno, (long long)fbno,
                                         (unsigned long long)ifbno, lastfbno);
                                 if (fblk) {
-                                        cmn_err(CE_ALERT,
-                                                " fblk 0x%p blkno %llu "
-                                                "index %d magic 0x%x\n",
+                                        xfs_alert(mp,
+                                " fblk 0x%p blkno %llu index %d magic 0x%x",
                                                 fblk,
                                                 (unsigned long long)fblk->blkno,
                                                 fblk->index,
                                                 fblk->magic);
                                 } else {
-                                        cmn_err(CE_ALERT,
-                                                " ... fblk is NULL\n");
+                                        xfs_alert(mp, " ... fblk is NULL");
                                 }
                                 XFS_ERROR_REPORT("xfs_dir2_node_addname_int",
                                                  XFS_ERRLEVEL_LOW, mp);
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index 4c7db74a05f7..39f06336b99d 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -48,7 +48,7 @@ xfs_error_trap(int e)
                         break;
                 if (e != xfs_etrap[i])
                         continue;
-                cmn_err(CE_NOTE, "xfs_error_trap: error %d", e);
+                xfs_notice(NULL, "%s: error %d", __func__, e);
                 BUG();
                 break;
         }
@@ -74,7 +74,7 @@ xfs_error_test(int error_tag, int *fsidp, char *expression,
 
         for (i = 0; i < XFS_NUM_INJECT_ERROR; i++)  {
                 if (xfs_etest[i] == error_tag && xfs_etest_fsid[i] == fsid) {
-                        cmn_err(CE_WARN,
+                        xfs_warn(NULL,
         "Injecting error (%s) at file %s, line %d, on filesystem \"%s\"",
                                 expression, file, line, xfs_etest_fsname[i]);
                         return 1;
@@ -95,14 +95,14 @@ xfs_errortag_add(int error_tag, xfs_mount_t *mp)
 
         for (i = 0; i < XFS_NUM_INJECT_ERROR; i++)  {
                 if (xfs_etest_fsid[i] == fsid && xfs_etest[i] == error_tag) {
-                        cmn_err(CE_WARN, "XFS error tag #%d on", error_tag);
+                        xfs_warn(mp, "error tag #%d on", error_tag);
                         return 0;
                 }
         }
 
         for (i = 0; i < XFS_NUM_INJECT_ERROR; i++)  {
                 if (xfs_etest[i] == 0) {
-                        cmn_err(CE_WARN, "Turned on XFS error tag #%d",
+                        xfs_warn(mp, "Turned on XFS error tag #%d",
                                 error_tag);
                         xfs_etest[i] = error_tag;
                         xfs_etest_fsid[i] = fsid;
@@ -114,7 +114,7 @@ xfs_errortag_add(int error_tag, xfs_mount_t *mp)
                 }
         }
 
-        cmn_err(CE_WARN, "error tag overflow, too many turned on");
+        xfs_warn(mp, "error tag overflow, too many turned on");
 
         return 1;
 }
@@ -133,7 +133,7 @@ xfs_errortag_clearall(xfs_mount_t *mp, int loud)
                 if ((fsid == 0LL || xfs_etest_fsid[i] == fsid) &&
                      xfs_etest[i] != 0) {
                         cleared = 1;
-                        cmn_err(CE_WARN, "Clearing XFS error tag #%d",
+                        xfs_warn(mp, "Clearing XFS error tag #%d",
                                 xfs_etest[i]);
                         xfs_etest[i] = 0;
                         xfs_etest_fsid[i] = 0LL;
@@ -144,9 +144,7 @@ xfs_errortag_clearall(xfs_mount_t *mp, int loud)
         }
 
         if (loud || cleared)
-                cmn_err(CE_WARN,
-                        "Cleared all XFS error tags for filesystem \"%s\"",
-                        mp->m_fsname);
+                xfs_warn(mp, "Cleared all XFS error tags for filesystem");
 
         return 0;
 }
@@ -162,9 +160,8 @@ xfs_error_report(
         inst_t                  *ra)
 {
         if (level <= xfs_error_level) {
-                xfs_cmn_err(XFS_PTAG_ERROR_REPORT,
-                            CE_ALERT, mp,
-                "XFS internal error %s at line %d of file %s.  Caller 0x%p\n",
+                xfs_alert_tag(mp, XFS_PTAG_ERROR_REPORT,
+                "Internal error %s at line %d of file %s.  Caller 0x%p\n",
                             tag, linenum, filename, ra);
 
                 xfs_stack_trace();
@@ -184,4 +181,5 @@ xfs_corruption_error(
         if (level <= xfs_error_level)
                 xfs_hex_dump(p, 16);
         xfs_error_report(tag, level, mp, filename, linenum, ra);
+        xfs_alert(mp, "Corruption detected. Unmount and run xfs_repair");
 }
diff --git a/fs/xfs/xfs_error.h b/fs/xfs/xfs_error.h
index 10dce5475f02..079a367f44ee 100644
--- a/fs/xfs/xfs_error.h
+++ b/fs/xfs/xfs_error.h
@@ -145,10 +145,8 @@ extern int xfs_errortag_clearall(struct xfs_mount *mp, int loud);
 #endif /* DEBUG */
 
 /*
- * XFS panic tags -- allow a call to xfs_cmn_err() be turned into
- *                      a panic by setting xfs_panic_mask in a
- *                      sysctl.  update xfs_max[XFS_PARAM] if
- *                      more are added.
+ * XFS panic tags -- allow a call to xfs_alert_tag() be turned into
+ *                      a panic by setting xfs_panic_mask in a sysctl.
  */
 #define         XFS_NO_PTAG                     0
 #define         XFS_PTAG_IFLUSH                 0x00000001
@@ -160,17 +158,4 @@ extern int xfs_errortag_clearall(struct xfs_mount *mp, int loud);
 #define         XFS_PTAG_SHUTDOWN_LOGERROR      0x00000040
 #define         XFS_PTAG_FSBLOCK_ZERO           0x00000080
 
-struct xfs_mount;
-
-extern void xfs_hex_dump(void *p, int length);
-
-#define xfs_fs_repair_cmn_err(level, mp, fmt, args...) \
-        xfs_fs_cmn_err(level, mp, fmt "  Unmount and run xfs_repair.", ## args)
-
-#define xfs_fs_mount_cmn_err(f, fmt, args...) \
-        do { \
-                if (!(f & XFS_MFSI_QUIET))      \
-                        cmn_err(CE_WARN, "XFS: " fmt, ## args); \
-        } while (0)
-
 #endif  /* __XFS_ERROR_H__ */
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 85668efb3e3e..9153d2c77caf 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -385,8 +385,8 @@ xfs_growfs_data_private(
                                   XFS_AGB_TO_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
                                   XFS_FSS_TO_BB(mp, 1), 0, &bp);
                 if (error) {
-                        xfs_fs_cmn_err(CE_WARN, mp,
-                        "error %d reading secondary superblock for ag %d",
+                        xfs_warn(mp,
+                "error %d reading secondary superblock for ag %d",
                                 error, agno);
                         break;
                 }
@@ -399,7 +399,7 @@ xfs_growfs_data_private(
                 if (!(error = xfs_bwrite(mp, bp))) {
                         continue;
                 } else {
-                        xfs_fs_cmn_err(CE_WARN, mp,
+                        xfs_warn(mp,
                 "write error %d updating secondary superblock for ag %d",
                                 error, agno);
                         break; /* no point in continuing */
diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c
index 0626a32c3447..84ebeec16642 100644
--- a/fs/xfs/xfs_ialloc.c
+++ b/fs/xfs/xfs_ialloc.c
@@ -1055,28 +1055,23 @@ xfs_difree(
          */
         agno = XFS_INO_TO_AGNO(mp, inode);
         if (agno >= mp->m_sb.sb_agcount)  {
-                cmn_err(CE_WARN,
-                        "xfs_difree: agno >= mp->m_sb.sb_agcount (%d >= %d) on %s.  Returning EINVAL.",
-                        agno, mp->m_sb.sb_agcount, mp->m_fsname);
+                xfs_warn(mp, "%s: agno >= mp->m_sb.sb_agcount (%d >= %d).",
+                        __func__, agno, mp->m_sb.sb_agcount);
                 ASSERT(0);
                 return XFS_ERROR(EINVAL);
         }
         agino = XFS_INO_TO_AGINO(mp, inode);
         if (inode != XFS_AGINO_TO_INO(mp, agno, agino))  {
-                cmn_err(CE_WARN,
-                        "xfs_difree: inode != XFS_AGINO_TO_INO() "
-                        "(%llu != %llu) on %s.  Returning EINVAL.",
-                        (unsigned long long)inode,
-                        (unsigned long long)XFS_AGINO_TO_INO(mp, agno, agino),
-                        mp->m_fsname);
+                xfs_warn(mp, "%s: inode != XFS_AGINO_TO_INO() (%llu != %llu).",
+                        __func__, (unsigned long long)inode,
+                        (unsigned long long)XFS_AGINO_TO_INO(mp, agno, agino));
                 ASSERT(0);
                 return XFS_ERROR(EINVAL);
         }
         agbno = XFS_AGINO_TO_AGBNO(mp, agino);
         if (agbno >= mp->m_sb.sb_agblocks)  {
-                cmn_err(CE_WARN,
-                        "xfs_difree: agbno >= mp->m_sb.sb_agblocks (%d >= %d) on %s.  Returning EINVAL.",
-                        agbno, mp->m_sb.sb_agblocks, mp->m_fsname);
+                xfs_warn(mp, "%s: agbno >= mp->m_sb.sb_agblocks (%d >= %d).",
+                        __func__, agbno, mp->m_sb.sb_agblocks);
                 ASSERT(0);
                 return XFS_ERROR(EINVAL);
         }
@@ -1085,9 +1080,8 @@ xfs_difree(
          */
         error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
         if (error) {
-                cmn_err(CE_WARN,
-                        "xfs_difree: xfs_ialloc_read_agi() returned an error %d on %s.  Returning error.",
-                        error, mp->m_fsname);
+                xfs_warn(mp, "%s: xfs_ialloc_read_agi() returned error %d.",
+                        __func__, error);
                 return error;
         }
         agi = XFS_BUF_TO_AGI(agbp);
@@ -1106,17 +1100,15 @@ xfs_difree(
          * Look for the entry describing this inode.
          */
         if ((error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &i))) {
-                cmn_err(CE_WARN,
-                        "xfs_difree: xfs_inobt_lookup returned()  an error %d on %s.  Returning error.",
-                        error, mp->m_fsname);
+                xfs_warn(mp, "%s: xfs_inobt_lookup() returned error %d.",
+                        __func__, error);
                 goto error0;
         }
         XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
         error = xfs_inobt_get_rec(cur, &rec, &i);
         if (error) {
-                cmn_err(CE_WARN,
-                        "xfs_difree: xfs_inobt_get_rec()  returned an error %d on %s.  Returning error.",
-                        error, mp->m_fsname);
+                xfs_warn(mp, "%s: xfs_inobt_get_rec() returned error %d.",
+                        __func__, error);
                 goto error0;
         }
         XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
@@ -1157,8 +1149,8 @@ xfs_difree(
                 xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -(ilen - 1));
 
                 if ((error = xfs_btree_delete(cur, &i))) {
-                        cmn_err(CE_WARN, "xfs_difree: xfs_btree_delete returned an error %d on %s.\n",
-                                error, mp->m_fsname);
+                        xfs_warn(mp, "%s: xfs_btree_delete returned error %d.",
+                                __func__, error);
                         goto error0;
                 }
 
@@ -1170,9 +1162,8 @@ xfs_difree(
 
                 error = xfs_inobt_update(cur, &rec);
                 if (error) {
-                        cmn_err(CE_WARN,
-        "xfs_difree: xfs_inobt_update returned an error %d on %s.",
-                                error, mp->m_fsname);
+                        xfs_warn(mp, "%s: xfs_inobt_update returned error %d.",
+                                __func__, error);
                         goto error0;
                 }
 
@@ -1218,10 +1209,9 @@ xfs_imap_lookup(
 
         error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
         if (error) {
-                xfs_fs_cmn_err(CE_ALERT, mp, "xfs_imap: "
-                                "xfs_ialloc_read_agi() returned "
-                                "error %d, agno %d",
-                                error, agno);
+                xfs_alert(mp,
+                        "%s: xfs_ialloc_read_agi() returned error %d, agno %d",
+                        __func__, error, agno);
                 return error;
         }
 
@@ -1299,24 +1289,21 @@ xfs_imap(
                 if (flags & XFS_IGET_UNTRUSTED)
                         return XFS_ERROR(EINVAL);
                 if (agno >= mp->m_sb.sb_agcount) {
-                        xfs_fs_cmn_err(CE_ALERT, mp,
-                                        "xfs_imap: agno (%d) >= "
-                                        "mp->m_sb.sb_agcount (%d)",
-                                        agno,  mp->m_sb.sb_agcount);
+                        xfs_alert(mp,
+                                "%s: agno (%d) >= mp->m_sb.sb_agcount (%d)",
+                                __func__, agno, mp->m_sb.sb_agcount);
                 }
                 if (agbno >= mp->m_sb.sb_agblocks) {
-                        xfs_fs_cmn_err(CE_ALERT, mp,
-                                        "xfs_imap: agbno (0x%llx) >= "
-                                        "mp->m_sb.sb_agblocks (0x%lx)",
-                                        (unsigned long long) agbno,
-                                        (unsigned long) mp->m_sb.sb_agblocks);
+                        xfs_alert(mp,
+                "%s: agbno (0x%llx) >= mp->m_sb.sb_agblocks (0x%lx)",
+                                __func__, (unsigned long long)agbno,
+                                (unsigned long)mp->m_sb.sb_agblocks);
                 }
                 if (ino != XFS_AGINO_TO_INO(mp, agno, agino)) {
-                        xfs_fs_cmn_err(CE_ALERT, mp,
-                                        "xfs_imap: ino (0x%llx) != "
-                                        "XFS_AGINO_TO_INO(mp, agno, agino) "
-                                        "(0x%llx)",
-                                        ino, XFS_AGINO_TO_INO(mp, agno, agino));
+                        xfs_alert(mp,
+                "%s: ino (0x%llx) != XFS_AGINO_TO_INO() (0x%llx)",
+                                __func__, ino,
+                                XFS_AGINO_TO_INO(mp, agno, agino));
                 }
                 xfs_stack_trace();
 #endif /* DEBUG */
@@ -1388,10 +1375,9 @@ out_map:
          */
         if ((imap->im_blkno + imap->im_len) >
             XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)) {
-                xfs_fs_cmn_err(CE_ALERT, mp, "xfs_imap: "
-                        "(imap->im_blkno (0x%llx) + imap->im_len (0x%llx)) > "
-                        " XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) (0x%llx)",
-                        (unsigned long long) imap->im_blkno,
+                xfs_alert(mp,
+        "%s: (im_blkno (0x%llx) + im_len (0x%llx)) > sb_dblocks (0x%llx)",
+                        __func__, (unsigned long long) imap->im_blkno,
                         (unsigned long long) imap->im_len,
                         XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks));
                 return XFS_ERROR(EINVAL);
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index be7cf625421f..da871f532236 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -110,8 +110,8 @@ xfs_inobp_check(
                 dip = (xfs_dinode_t *)xfs_buf_offset(bp,
                                         i * mp->m_sb.sb_inodesize);
                 if (!dip->di_next_unlinked)  {
-                        xfs_fs_cmn_err(CE_ALERT, mp,
-                                "Detected a bogus zero next_unlinked field in incore inode buffer 0x%p.  About to pop an ASSERT.",
+                        xfs_alert(mp,
+        "Detected bogus zero next_unlinked field in incore inode buffer 0x%p.",
                                 bp);
                         ASSERT(dip->di_next_unlinked);
                 }
@@ -142,10 +142,9 @@ xfs_imap_to_bp(
                                    (int)imap->im_len, buf_flags, &bp);
         if (error) {
                 if (error != EAGAIN) {
-                        cmn_err(CE_WARN,
-                                "xfs_imap_to_bp: xfs_trans_read_buf()returned "
-                                "an error %d on %s.  Returning error.",
-                                error, mp->m_fsname);
+                        xfs_warn(mp,
+                                "%s: xfs_trans_read_buf() returned error %d.",
+                                __func__, error);
                 } else {
                         ASSERT(buf_flags & XBF_TRYLOCK);
                 }
@@ -180,12 +179,11 @@ xfs_imap_to_bp(
                         XFS_CORRUPTION_ERROR("xfs_imap_to_bp",
                                                 XFS_ERRLEVEL_HIGH, mp, dip);
 #ifdef DEBUG
-                        cmn_err(CE_PANIC,
-                                        "Device %s - bad inode magic/vsn "
-                                        "daddr %lld #%d (magic=%x)",
-                                XFS_BUFTARG_NAME(mp->m_ddev_targp),
+                        xfs_emerg(mp,
+                                "bad inode magic/vsn daddr %lld #%d (magic=%x)",
                                 (unsigned long long)imap->im_blkno, i,
                                 be16_to_cpu(dip->di_magic));
+                        ASSERT(0);
 #endif
                         xfs_trans_brelse(tp, bp);
                         return XFS_ERROR(EFSCORRUPTED);
@@ -317,7 +315,7 @@ xfs_iformat(
         if (unlikely(be32_to_cpu(dip->di_nextents) +
                      be16_to_cpu(dip->di_anextents) >
                      be64_to_cpu(dip->di_nblocks))) {
-                xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
+                xfs_warn(ip->i_mount,
                         "corrupt dinode %Lu, extent total = %d, nblocks = %Lu.",
                         (unsigned long long)ip->i_ino,
                         (int)(be32_to_cpu(dip->di_nextents) +
@@ -330,8 +328,7 @@ xfs_iformat(
         }
 
         if (unlikely(dip->di_forkoff > ip->i_mount->m_sb.sb_inodesize)) {
-                xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
-                        "corrupt dinode %Lu, forkoff = 0x%x.",
+                xfs_warn(ip->i_mount, "corrupt dinode %Lu, forkoff = 0x%x.",
                         (unsigned long long)ip->i_ino,
                         dip->di_forkoff);
                 XFS_CORRUPTION_ERROR("xfs_iformat(2)", XFS_ERRLEVEL_LOW,
@@ -341,7 +338,7 @@ xfs_iformat(
 
         if (unlikely((ip->i_d.di_flags & XFS_DIFLAG_REALTIME) &&
                      !ip->i_mount->m_rtdev_targp)) {
-                xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
+                xfs_warn(ip->i_mount,
                         "corrupt dinode %Lu, has realtime flag set.",
                         ip->i_ino);
                 XFS_CORRUPTION_ERROR("xfs_iformat(realtime)",
@@ -373,9 +370,8 @@ xfs_iformat(
                          * no local regular files yet
                          */
                         if (unlikely((be16_to_cpu(dip->di_mode) & S_IFMT) == S_IFREG)) {
-                                xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
-                                        "corrupt inode %Lu "
-                                        "(local format for regular file).",
+                                xfs_warn(ip->i_mount,
+                        "corrupt inode %Lu (local format for regular file).",
                                         (unsigned long long) ip->i_ino);
                                 XFS_CORRUPTION_ERROR("xfs_iformat(4)",
                                                      XFS_ERRLEVEL_LOW,
@@ -385,9 +381,8 @@ xfs_iformat(
 
                         di_size = be64_to_cpu(dip->di_size);
                         if (unlikely(di_size > XFS_DFORK_DSIZE(dip, ip->i_mount))) {
-                                xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
-                                        "corrupt inode %Lu "
-                                        "(bad size %Ld for local inode).",
+                                xfs_warn(ip->i_mount,
+                        "corrupt inode %Lu (bad size %Ld for local inode).",
                                         (unsigned long long) ip->i_ino,
                                         (long long) di_size);
                                 XFS_CORRUPTION_ERROR("xfs_iformat(5)",
@@ -431,9 +426,8 @@ xfs_iformat(
                 size = be16_to_cpu(atp->hdr.totsize);
 
                 if (unlikely(size < sizeof(struct xfs_attr_sf_hdr))) {
-                        xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
-                                "corrupt inode %Lu "
-                                "(bad attr fork size %Ld).",
+                        xfs_warn(ip->i_mount,
+                                "corrupt inode %Lu (bad attr fork size %Ld).",
                                 (unsigned long long) ip->i_ino,
                                 (long long) size);
                         XFS_CORRUPTION_ERROR("xfs_iformat(8)",
@@ -488,9 +482,8 @@ xfs_iformat_local(
          * kmem_alloc() or memcpy() below.
          */
         if (unlikely(size > XFS_DFORK_SIZE(dip, ip->i_mount, whichfork))) {
-                xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
-                        "corrupt inode %Lu "
-                        "(bad size %d for local fork, size = %d).",
+                xfs_warn(ip->i_mount,
+        "corrupt inode %Lu (bad size %d for local fork, size = %d).",
                         (unsigned long long) ip->i_ino, size,
                         XFS_DFORK_SIZE(dip, ip->i_mount, whichfork));
                 XFS_CORRUPTION_ERROR("xfs_iformat_local", XFS_ERRLEVEL_LOW,
@@ -547,8 +540,7 @@ xfs_iformat_extents(
          * kmem_alloc() or memcpy() below.
          */
         if (unlikely(size < 0 || size > XFS_DFORK_SIZE(dip, ip->i_mount, whichfork))) {
-                xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
-                        "corrupt inode %Lu ((a)extents = %d).",
+                xfs_warn(ip->i_mount, "corrupt inode %Lu ((a)extents = %d).",
                         (unsigned long long) ip->i_ino, nex);
                 XFS_CORRUPTION_ERROR("xfs_iformat_extents(1)", XFS_ERRLEVEL_LOW,
                                      ip->i_mount, dip);
@@ -623,11 +615,10 @@ xfs_iformat_btree(
             || XFS_BMDR_SPACE_CALC(nrecs) >
                         XFS_DFORK_SIZE(dip, ip->i_mount, whichfork)
             || XFS_IFORK_NEXTENTS(ip, whichfork) > ip->i_d.di_nblocks)) {
-                xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
-                        "corrupt inode %Lu (btree).",
+                xfs_warn(ip->i_mount, "corrupt inode %Lu (btree).",
                         (unsigned long long) ip->i_ino);
-                XFS_ERROR_REPORT("xfs_iformat_btree", XFS_ERRLEVEL_LOW,
-                                 ip->i_mount);
+                XFS_CORRUPTION_ERROR("xfs_iformat_btree", XFS_ERRLEVEL_LOW,
+                                 ip->i_mount, dip);
                 return XFS_ERROR(EFSCORRUPTED);
         }
 
@@ -813,11 +804,9 @@ xfs_iread(
          */
         if (be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC) {
 #ifdef DEBUG
-                xfs_fs_cmn_err(CE_ALERT, mp, "xfs_iread: "
-                                "dip->di_magic (0x%x) != "
-                                "XFS_DINODE_MAGIC (0x%x)",
-                                be16_to_cpu(dip->di_magic),
-                                XFS_DINODE_MAGIC);
+                xfs_alert(mp,
+                        "%s: dip->di_magic (0x%x) != XFS_DINODE_MAGIC (0x%x)",
+                        __func__, be16_to_cpu(dip->di_magic), XFS_DINODE_MAGIC);
 #endif /* DEBUG */
                 error = XFS_ERROR(EINVAL);
                 goto out_brelse;
@@ -835,9 +824,8 @@ xfs_iread(
                 error = xfs_iformat(ip, dip);
                 if (error)  {
 #ifdef DEBUG
-                        xfs_fs_cmn_err(CE_ALERT, mp, "xfs_iread: "
-                                        "xfs_iformat() returned error %d",
-                                        error);
+                        xfs_alert(mp, "%s: xfs_iformat() returned error %d",
+                                __func__, error);
 #endif /* DEBUG */
                         goto out_brelse;
                 }
@@ -1016,8 +1004,8 @@ xfs_ialloc(
          * This is because we're setting fields here we need
          * to prevent others from looking at until we're done.
          */
-        error = xfs_trans_iget(tp->t_mountp, tp, ino,
-                                XFS_IGET_CREATE, XFS_ILOCK_EXCL, &ip);
+        error = xfs_iget(tp->t_mountp, tp, ino, XFS_IGET_CREATE,
+                         XFS_ILOCK_EXCL, &ip);
         if (error)
                 return error;
         ASSERT(ip != NULL);
@@ -1166,6 +1154,7 @@ xfs_ialloc(
         /*
          * Log the new values stuffed into the inode.
          */
+        xfs_trans_ijoin_ref(tp, ip, XFS_ILOCK_EXCL);
         xfs_trans_log_inode(tp, ip, flags);
 
         /* now that we have an i_mode we can setup inode ops and unlock */
@@ -1820,9 +1809,8 @@ xfs_iunlink_remove(
                  */
                 error = xfs_itobp(mp, tp, ip, &dip, &ibp, XBF_LOCK);
                 if (error) {
-                        cmn_err(CE_WARN,
-                                "xfs_iunlink_remove: xfs_itobp()  returned an error %d on %s.  Returning error.",
-                                error, mp->m_fsname);
+                        xfs_warn(mp, "%s: xfs_itobp() returned error %d.",
+                                __func__, error);
                         return error;
                 }
                 next_agino = be32_to_cpu(dip->di_next_unlinked);
@@ -1867,9 +1855,9 @@ xfs_iunlink_remove(
                         error = xfs_inotobp(mp, tp, next_ino, &last_dip,
                                             &last_ibp, &last_offset, 0);
                         if (error) {
-                                cmn_err(CE_WARN,
-                        "xfs_iunlink_remove: xfs_inotobp()  returned an error %d on %s.  Returning error.",
-                                        error, mp->m_fsname);
+                                xfs_warn(mp,
+                                        "%s: xfs_inotobp() returned error %d.",
+                                        __func__, error);
                                 return error;
                         }
                         next_agino = be32_to_cpu(last_dip->di_next_unlinked);
@@ -1882,9 +1870,8 @@ xfs_iunlink_remove(
                  */
                 error = xfs_itobp(mp, tp, ip, &dip, &ibp, XBF_LOCK);
                 if (error) {
-                        cmn_err(CE_WARN,
-                                "xfs_iunlink_remove: xfs_itobp()  returned an error %d on %s.  Returning error.",
-                                error, mp->m_fsname);
+                        xfs_warn(mp, "%s: xfs_itobp(2) returned error %d.",
+                                __func__, error);
                         return error;
                 }
                 next_agino = be32_to_cpu(dip->di_next_unlinked);
@@ -2939,16 +2926,16 @@ xfs_iflush_int(
 
         if (XFS_TEST_ERROR(be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC,
                                mp, XFS_ERRTAG_IFLUSH_1, XFS_RANDOM_IFLUSH_1)) {
-                xfs_cmn_err(XFS_PTAG_IFLUSH, CE_ALERT, mp,
-                    "xfs_iflush: Bad inode %Lu magic number 0x%x, ptr 0x%p",
-                        ip->i_ino, be16_to_cpu(dip->di_magic), dip);
+                xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
+                        "%s: Bad inode %Lu magic number 0x%x, ptr 0x%p",
+                        __func__, ip->i_ino, be16_to_cpu(dip->di_magic), dip);
                 goto corrupt_out;
         }
         if (XFS_TEST_ERROR(ip->i_d.di_magic != XFS_DINODE_MAGIC,
                                 mp, XFS_ERRTAG_IFLUSH_2, XFS_RANDOM_IFLUSH_2)) {
-                xfs_cmn_err(XFS_PTAG_IFLUSH, CE_ALERT, mp,
-                        "xfs_iflush: Bad inode %Lu, ptr 0x%p, magic number 0x%x",
-                        ip->i_ino, ip, ip->i_d.di_magic);
+                xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
+                        "%s: Bad inode %Lu, ptr 0x%p, magic number 0x%x",
+                        __func__, ip->i_ino, ip, ip->i_d.di_magic);
                 goto corrupt_out;
         }
         if ((ip->i_d.di_mode & S_IFMT) == S_IFREG) {
@@ -2956,9 +2943,9 @@ xfs_iflush_int(
                     (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) &&
                     (ip->i_d.di_format != XFS_DINODE_FMT_BTREE),
                     mp, XFS_ERRTAG_IFLUSH_3, XFS_RANDOM_IFLUSH_3)) {
-                        xfs_cmn_err(XFS_PTAG_IFLUSH, CE_ALERT, mp,
-                                "xfs_iflush: Bad regular inode %Lu, ptr 0x%p",
-                                ip->i_ino, ip);
+                        xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
+                                "%s: Bad regular inode %Lu, ptr 0x%p",
+                                __func__, ip->i_ino, ip);
                         goto corrupt_out;
                 }
         } else if ((ip->i_d.di_mode & S_IFMT) == S_IFDIR) {
@@ -2967,28 +2954,28 @@ xfs_iflush_int(
                     (ip->i_d.di_format != XFS_DINODE_FMT_BTREE) &&
                     (ip->i_d.di_format != XFS_DINODE_FMT_LOCAL),
                     mp, XFS_ERRTAG_IFLUSH_4, XFS_RANDOM_IFLUSH_4)) {
-                        xfs_cmn_err(XFS_PTAG_IFLUSH, CE_ALERT, mp,
-                                "xfs_iflush: Bad directory inode %Lu, ptr 0x%p",
-                                ip->i_ino, ip);
+                        xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
+                                "%s: Bad directory inode %Lu, ptr 0x%p",
+                                __func__, ip->i_ino, ip);
                         goto corrupt_out;
                 }
         }
         if (XFS_TEST_ERROR(ip->i_d.di_nextents + ip->i_d.di_anextents >
                                 ip->i_d.di_nblocks, mp, XFS_ERRTAG_IFLUSH_5,
                                 XFS_RANDOM_IFLUSH_5)) {
-                xfs_cmn_err(XFS_PTAG_IFLUSH, CE_ALERT, mp,
-                        "xfs_iflush: detected corrupt incore inode %Lu, total extents = %d, nblocks = %Ld, ptr 0x%p",
-                        ip->i_ino,
+                xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
+                        "%s: detected corrupt incore inode %Lu, "
+                        "total extents = %d, nblocks = %Ld, ptr 0x%p",
+                        __func__, ip->i_ino,
                         ip->i_d.di_nextents + ip->i_d.di_anextents,
-                        ip->i_d.di_nblocks,
-                        ip);
+                        ip->i_d.di_nblocks, ip);
                 goto corrupt_out;
         }
         if (XFS_TEST_ERROR(ip->i_d.di_forkoff > mp->m_sb.sb_inodesize,
                                 mp, XFS_ERRTAG_IFLUSH_6, XFS_RANDOM_IFLUSH_6)) {
-                xfs_cmn_err(XFS_PTAG_IFLUSH, CE_ALERT, mp,
-                        "xfs_iflush: bad inode %Lu, forkoff 0x%x, ptr 0x%p",
-                        ip->i_ino, ip->i_d.di_forkoff, ip);
+                xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
+                        "%s: bad inode %Lu, forkoff 0x%x, ptr 0x%p",
+                        __func__, ip->i_ino, ip->i_d.di_forkoff, ip);
                 goto corrupt_out;
         }
         /*
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 5c95fa8ec11d..f753200cef8d 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -409,28 +409,35 @@ static inline void xfs_ifunlock(xfs_inode_t *ip)
 /*
  * Flags for lockdep annotations.
  *
- * XFS_I[O]LOCK_PARENT - for operations that require locking two inodes
- * (ie directory operations that require locking a directory inode and
- * an entry inode).  The first inode gets locked with this flag so it
- * gets a lockdep subclass of 1 and the second lock will have a lockdep
- * subclass of 0.
+ * XFS_LOCK_PARENT - for directory operations that require locking a
+ * parent directory inode and a child entry inode.  The parent gets locked
+ * with this flag so it gets a lockdep subclass of 1 and the child entry
+ * lock will have a lockdep subclass of 0.
+ *
+ * XFS_LOCK_RTBITMAP/XFS_LOCK_RTSUM - the realtime device bitmap and summary
+ * inodes do not participate in the normal lock order, and thus have their
+ * own subclasses.
  *
  * XFS_LOCK_INUMORDER - for locking several inodes at the some time
  * with xfs_lock_inodes().  This flag is used as the starting subclass
  * and each subsequent lock acquired will increment the subclass by one.
- * So the first lock acquired will have a lockdep subclass of 2, the
- * second lock will have a lockdep subclass of 3, and so on. It is
+ * So the first lock acquired will have a lockdep subclass of 4, the
+ * second lock will have a lockdep subclass of 5, and so on. It is
  * the responsibility of the class builder to shift this to the correct
  * portion of the lock_mode lockdep mask.
  */
 #define XFS_LOCK_PARENT         1
-#define XFS_LOCK_INUMORDER      2
+#define XFS_LOCK_RTBITMAP       2
+#define XFS_LOCK_RTSUM          3
+#define XFS_LOCK_INUMORDER      4
 
 #define XFS_IOLOCK_SHIFT        16
 #define XFS_IOLOCK_PARENT       (XFS_LOCK_PARENT << XFS_IOLOCK_SHIFT)
 
 #define XFS_ILOCK_SHIFT         24
 #define XFS_ILOCK_PARENT        (XFS_LOCK_PARENT << XFS_ILOCK_SHIFT)
+#define XFS_ILOCK_RTBITMAP      (XFS_LOCK_RTBITMAP << XFS_ILOCK_SHIFT)
+#define XFS_ILOCK_RTSUM         (XFS_LOCK_RTSUM << XFS_ILOCK_SHIFT)
 
 #define XFS_IOLOCK_DEP_MASK     0x00ff0000
 #define XFS_ILOCK_DEP_MASK      0xff000000
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 8a0f044750c3..091d82b94c4d 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -101,11 +101,11 @@ xfs_iomap_eof_align_last_fsb(
 }
 
 STATIC int
-xfs_cmn_err_fsblock_zero(
+xfs_alert_fsblock_zero(
         xfs_inode_t     *ip,
         xfs_bmbt_irec_t *imap)
 {
-        xfs_cmn_err(XFS_PTAG_FSBLOCK_ZERO, CE_ALERT, ip->i_mount,
+        xfs_alert_tag(ip->i_mount, XFS_PTAG_FSBLOCK_ZERO,
                         "Access to block zero in inode %llu "
                         "start_block: %llx start_off: %llx "
                         "blkcnt: %llx extent-state: %x\n",
@@ -246,7 +246,7 @@ xfs_iomap_write_direct(
         }
 
         if (!(imap->br_startblock || XFS_IS_REALTIME_INODE(ip))) {
-                error = xfs_cmn_err_fsblock_zero(ip, imap);
+                error = xfs_alert_fsblock_zero(ip, imap);
                 goto error_out;
         }
 
@@ -464,7 +464,7 @@ retry:
         }
 
         if (!(imap[0].br_startblock || XFS_IS_REALTIME_INODE(ip)))
-                return xfs_cmn_err_fsblock_zero(ip, &imap[0]);
+                return xfs_alert_fsblock_zero(ip, &imap[0]);
 
         *ret_imap = imap[0];
         return 0;
@@ -614,7 +614,7 @@ xfs_iomap_write_allocate(
                  * covers at least part of the callers request
                  */
                 if (!(imap->br_startblock || XFS_IS_REALTIME_INODE(ip)))
-                        return xfs_cmn_err_fsblock_zero(ip, imap);
+                        return xfs_alert_fsblock_zero(ip, imap);
 
                 if ((offset_fsb >= imap->br_startoff) &&
                     (offset_fsb < (imap->br_startoff +
@@ -724,7 +724,7 @@ xfs_iomap_write_unwritten(
                         return XFS_ERROR(error);
 
                 if (!(imap.br_startblock || XFS_IS_REALTIME_INODE(ip)))
-                        return xfs_cmn_err_fsblock_zero(ip, &imap);
+                        return xfs_alert_fsblock_zero(ip, &imap);
 
                 if ((numblks_fsb = imap.br_blockcount) == 0) {
                         /*
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index ae6fef1ff563..25efa9b8a602 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -374,11 +374,10 @@ xfs_log_mount(
         int             error;
 
         if (!(mp->m_flags & XFS_MOUNT_NORECOVERY))
-                cmn_err(CE_NOTE, "XFS mounting filesystem %s", mp->m_fsname);
+                xfs_notice(mp, "Mounting Filesystem");
         else {
-                cmn_err(CE_NOTE,
-                        "Mounting filesystem \"%s\" in no-recovery mode.  Filesystem will be inconsistent.",
-                        mp->m_fsname);
+                xfs_notice(mp,
+"Mounting filesystem in no-recovery mode.  Filesystem will be inconsistent.");
                 ASSERT(mp->m_flags & XFS_MOUNT_RDONLY);
         }
 
@@ -393,7 +392,7 @@ xfs_log_mount(
          */
         error = xfs_trans_ail_init(mp);
         if (error) {
-                cmn_err(CE_WARN, "XFS: AIL initialisation failed: error %d", error);
+                xfs_warn(mp, "AIL initialisation failed: error %d", error);
                 goto out_free_log;
         }
         mp->m_log->l_ailp = mp->m_ail;
@@ -413,7 +412,8 @@ xfs_log_mount(
                 if (readonly)
                         mp->m_flags |= XFS_MOUNT_RDONLY;
                 if (error) {
-                        cmn_err(CE_WARN, "XFS: log mount/recovery failed: error %d", error);
+                        xfs_warn(mp, "log mount/recovery failed: error %d",
+                                error);
                         goto out_destroy_ail;
                 }
         }
@@ -542,10 +542,8 @@ xfs_log_unmount_write(xfs_mount_t *mp)
                          */
                 }
 
-                if (error) {
-                        xfs_fs_cmn_err(CE_ALERT, mp,
-                                "xfs_log_unmount: unmount record failed");
-                }
+                if (error)
+                        xfs_alert(mp, "%s: unmount record failed", __func__);
 
 
                 spin_lock(&log->l_icloglock);
@@ -852,7 +850,7 @@ xlog_space_left(
                  * In this case we just want to return the size of the
                  * log as the amount of space left.
                  */
-                xfs_fs_cmn_err(CE_ALERT, log->l_mp,
+                xfs_alert(log->l_mp,
                         "xlog_space_left: head behind tail\n"
                         "  tail_cycle = %d, tail_bytes = %d\n"
                         "  GH   cycle = %d, GH   bytes = %d",
@@ -1001,7 +999,7 @@ xlog_alloc_log(xfs_mount_t	*mp,
 
         log = kmem_zalloc(sizeof(xlog_t), KM_MAYFAIL);
         if (!log) {
-                xlog_warn("XFS: Log allocation failed: No memory!");
+                xfs_warn(mp, "Log allocation failed: No memory!");
                 goto out;
         }
 
@@ -1029,24 +1027,24 @@ xlog_alloc_log(xfs_mount_t	*mp,
         if (xfs_sb_version_hassector(&mp->m_sb)) {
                 log2_size = mp->m_sb.sb_logsectlog;
                 if (log2_size < BBSHIFT) {
-                        xlog_warn("XFS: Log sector size too small "
-                                "(0x%x < 0x%x)", log2_size, BBSHIFT);
+                        xfs_warn(mp, "Log sector size too small (0x%x < 0x%x)",
+                                log2_size, BBSHIFT);
                         goto out_free_log;
                 }
 
                 log2_size -= BBSHIFT;
                 if (log2_size > mp->m_sectbb_log) {
-                        xlog_warn("XFS: Log sector size too large "
-                                "(0x%x > 0x%x)", log2_size, mp->m_sectbb_log);
+                        xfs_warn(mp, "Log sector size too large (0x%x > 0x%x)",
+                                log2_size, mp->m_sectbb_log);
                         goto out_free_log;
                 }
 
                 /* for larger sector sizes, must have v2 or external log */
                 if (log2_size && log->l_logBBstart > 0 &&
                             !xfs_sb_version_haslogv2(&mp->m_sb)) {
-
-                        xlog_warn("XFS: log sector size (0x%x) invalid "
-                                  "for configuration.", log2_size);
+                        xfs_warn(mp,
+                "log sector size (0x%x) invalid for configuration.",
+                                log2_size);
                         goto out_free_log;
                 }
         }
@@ -1563,38 +1561,36 @@ xlog_print_tic_res(
             "SWAPEXT"
         };
 
-        xfs_fs_cmn_err(CE_WARN, mp,
-                        "xfs_log_write: reservation summary:\n"
-                        "  trans type  = %s (%u)\n"
-                        "  unit res    = %d bytes\n"
-                        "  current res = %d bytes\n"
-                        "  total reg   = %u bytes (o/flow = %u bytes)\n"
-                        "  ophdrs      = %u (ophdr space = %u bytes)\n"
-                        "  ophdr + reg = %u bytes\n"
-                        "  num regions = %u\n",
-                        ((ticket->t_trans_type <= 0 ||
-                          ticket->t_trans_type > XFS_TRANS_TYPE_MAX) ?
-                          "bad-trans-type" : trans_type_str[ticket->t_trans_type-1]),
-                        ticket->t_trans_type,
-                        ticket->t_unit_res,
-                        ticket->t_curr_res,
-                        ticket->t_res_arr_sum, ticket->t_res_o_flow,
-                        ticket->t_res_num_ophdrs, ophdr_spc,
-                        ticket->t_res_arr_sum + 
-                        ticket->t_res_o_flow + ophdr_spc,
-                        ticket->t_res_num);
+        xfs_warn(mp,
+                "xfs_log_write: reservation summary:\n"
+                "  trans type  = %s (%u)\n"
+                "  unit res    = %d bytes\n"
+                "  current res = %d bytes\n"
+                "  total reg   = %u bytes (o/flow = %u bytes)\n"
+                "  ophdrs      = %u (ophdr space = %u bytes)\n"
+                "  ophdr + reg = %u bytes\n"
+                "  num regions = %u\n",
+                ((ticket->t_trans_type <= 0 ||
+                  ticket->t_trans_type > XFS_TRANS_TYPE_MAX) ?
+                  "bad-trans-type" : trans_type_str[ticket->t_trans_type-1]),
+                ticket->t_trans_type,
+                ticket->t_unit_res,
+                ticket->t_curr_res,
+                ticket->t_res_arr_sum, ticket->t_res_o_flow,
+                ticket->t_res_num_ophdrs, ophdr_spc,
+                ticket->t_res_arr_sum +
+                ticket->t_res_o_flow + ophdr_spc,
+                ticket->t_res_num);
 
         for (i = 0; i < ticket->t_res_num; i++) {
-                uint r_type = ticket->t_res_arr[i].r_type; 
-                cmn_err(CE_WARN,
-                            "region[%u]: %s - %u bytes\n",
-                            i, 
+                uint r_type = ticket->t_res_arr[i].r_type;
+                xfs_warn(mp, "region[%u]: %s - %u bytes\n", i,
                             ((r_type <= 0 || r_type > XLOG_REG_TYPE_MAX) ?
                             "bad-rtype" : res_type_str[r_type-1]),
                             ticket->t_res_arr[i].r_len);
         }
 
-        xfs_cmn_err(XFS_PTAG_LOGRES, CE_ALERT, mp,
+        xfs_alert_tag(mp, XFS_PTAG_LOGRES,
                 "xfs_log_write: reservation ran out. Need to up reservation");
         xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 }
@@ -1682,7 +1678,7 @@ xlog_write_setup_ophdr(
         case XFS_LOG:
                 break;
         default:
-                xfs_fs_cmn_err(CE_WARN, log->l_mp,
+                xfs_warn(log->l_mp,
                         "Bad XFS transaction clientid 0x%x in ticket 0x%p",
                         ophdr->oh_clientid, ticket);
                 return NULL;
@@ -2264,7 +2260,7 @@ xlog_state_do_callback(
                 if (repeats > 5000) {
                         flushcnt += repeats;
                         repeats = 0;
-                        xfs_fs_cmn_err(CE_WARN, log->l_mp,
+                        xfs_warn(log->l_mp,
                                 "%s: possible infinite loop (%d iterations)",
                                 __func__, flushcnt);
                 }
@@ -3052,10 +3048,8 @@ xfs_log_force(
         int     error;
 
         error = _xfs_log_force(mp, flags, NULL);
-        if (error) {
-                xfs_fs_cmn_err(CE_WARN, mp, "xfs_log_force: "
-                        "error %d returned.", error);
-        }
+        if (error)
+                xfs_warn(mp, "%s: error %d returned.", __func__, error);
 }
 
 /*
@@ -3204,10 +3198,8 @@ xfs_log_force_lsn(
         int     error;
 
         error = _xfs_log_force_lsn(mp, lsn, flags, NULL);
-        if (error) {
-                xfs_fs_cmn_err(CE_WARN, mp, "xfs_log_force: "
-                        "error %d returned.", error);
-        }
+        if (error)
+                xfs_warn(mp, "%s: error %d returned.", __func__, error);
 }
 
 /*
@@ -3412,7 +3404,7 @@ xlog_verify_dest_ptr(
         }
 
         if (!good_ptr)
-                xlog_panic("xlog_verify_dest_ptr: invalid ptr");
+                xfs_emerg(log->l_mp, "%s: invalid ptr", __func__);
 }
 
 STATIC void
@@ -3448,16 +3440,16 @@ xlog_verify_tail_lsn(xlog_t	    *log,
         blocks =
             log->l_logBBsize - (log->l_prev_block - BLOCK_LSN(tail_lsn));
         if (blocks < BTOBB(iclog->ic_offset)+BTOBB(log->l_iclog_hsize))
-            xlog_panic("xlog_verify_tail_lsn: ran out of log space");
+                xfs_emerg(log->l_mp, "%s: ran out of log space", __func__);
     } else {
         ASSERT(CYCLE_LSN(tail_lsn)+1 == log->l_prev_cycle);
 
         if (BLOCK_LSN(tail_lsn) == log->l_prev_block)
-            xlog_panic("xlog_verify_tail_lsn: tail wrapped");
+                xfs_emerg(log->l_mp, "%s: tail wrapped", __func__);
 
         blocks = BLOCK_LSN(tail_lsn) - log->l_prev_block;
         if (blocks < BTOBB(iclog->ic_offset) + 1)
-            xlog_panic("xlog_verify_tail_lsn: ran out of log space");
+                xfs_emerg(log->l_mp, "%s: ran out of log space", __func__);
     }
 }       /* xlog_verify_tail_lsn */
 
@@ -3497,22 +3489,23 @@ xlog_verify_iclog(xlog_t	 *log,
         icptr = log->l_iclog;
         for (i=0; i < log->l_iclog_bufs; i++) {
                 if (icptr == NULL)
-                        xlog_panic("xlog_verify_iclog: invalid ptr");
+                        xfs_emerg(log->l_mp, "%s: invalid ptr", __func__);
                 icptr = icptr->ic_next;
         }
         if (icptr != log->l_iclog)
-                xlog_panic("xlog_verify_iclog: corrupt iclog ring");
+                xfs_emerg(log->l_mp, "%s: corrupt iclog ring", __func__);
         spin_unlock(&log->l_icloglock);
 
         /* check log magic numbers */
         if (be32_to_cpu(iclog->ic_header.h_magicno) != XLOG_HEADER_MAGIC_NUM)
-                xlog_panic("xlog_verify_iclog: invalid magic num");
+                xfs_emerg(log->l_mp, "%s: invalid magic num", __func__);
 
         ptr = (xfs_caddr_t) &iclog->ic_header;
         for (ptr += BBSIZE; ptr < ((xfs_caddr_t)&iclog->ic_header) + count;
              ptr += BBSIZE) {
                 if (be32_to_cpu(*(__be32 *)ptr) == XLOG_HEADER_MAGIC_NUM)
-                        xlog_panic("xlog_verify_iclog: unexpected magic num");
+                        xfs_emerg(log->l_mp, "%s: unexpected magic num",
+                                __func__);
         }
 
         /* check fields */
@@ -3542,9 +3535,10 @@ xlog_verify_iclog(xlog_t	 *log,
                         }
                 }
                 if (clientid != XFS_TRANSACTION && clientid != XFS_LOG)
-                        cmn_err(CE_WARN, "xlog_verify_iclog: "
-                                "invalid clientid %d op 0x%p offset 0x%lx",
-                                clientid, ophead, (unsigned long)field_offset);
+                        xfs_warn(log->l_mp,
+                                "%s: invalid clientid %d op 0x%p offset 0x%lx",
+                                __func__, clientid, ophead,
+                                (unsigned long)field_offset);
 
                 /* check length */
                 field_offset = (__psint_t)
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index d5f8be8f4bf6..15dbf1f9c2be 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -87,10 +87,6 @@ static inline uint xlog_get_client_id(__be32 i)
         return be32_to_cpu(i) >> 24;
 }
 
-#define xlog_panic(args...)     cmn_err(CE_PANIC, ## args)
-#define xlog_exit(args...)      cmn_err(CE_PANIC, ## args)
-#define xlog_warn(args...)      cmn_err(CE_WARN, ## args)
-
 /*
  * In core log state
  */
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index aa0ebb776903..0c4a5618e7af 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -92,7 +92,7 @@ xlog_get_bp(
         int             nbblks)
 {
         if (!xlog_buf_bbcount_valid(log, nbblks)) {
-                xlog_warn("XFS: Invalid block length (0x%x) given for buffer",
+                xfs_warn(log->l_mp, "Invalid block length (0x%x) for buffer",
                         nbblks);
                 XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_HIGH, log->l_mp);
                 return NULL;
@@ -160,7 +160,7 @@ xlog_bread_noalign(
         int             error;
 
         if (!xlog_buf_bbcount_valid(log, nbblks)) {
-                xlog_warn("XFS: Invalid block length (0x%x) given for buffer",
+                xfs_warn(log->l_mp, "Invalid block length (0x%x) for buffer",
                         nbblks);
                 XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_HIGH, log->l_mp);
                 return EFSCORRUPTED;
@@ -219,7 +219,7 @@ xlog_bwrite(
         int             error;
 
         if (!xlog_buf_bbcount_valid(log, nbblks)) {
-                xlog_warn("XFS: Invalid block length (0x%x) given for buffer",
+                xfs_warn(log->l_mp, "Invalid block length (0x%x) for buffer",
                         nbblks);
                 XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_HIGH, log->l_mp);
                 return EFSCORRUPTED;
@@ -254,9 +254,9 @@ xlog_header_check_dump(
         xfs_mount_t             *mp,
         xlog_rec_header_t       *head)
 {
-        cmn_err(CE_DEBUG, "%s:  SB : uuid = %pU, fmt = %d\n",
+        xfs_debug(mp, "%s:  SB : uuid = %pU, fmt = %d\n",
                 __func__, &mp->m_sb.sb_uuid, XLOG_FMT);
-        cmn_err(CE_DEBUG, "    log : uuid = %pU, fmt = %d\n",
+        xfs_debug(mp, "    log : uuid = %pU, fmt = %d\n",
                 &head->h_fs_uuid, be32_to_cpu(head->h_fmt));
 }
 #else
@@ -279,15 +279,15 @@ xlog_header_check_recover(
          * a dirty log created in IRIX.
          */
         if (unlikely(be32_to_cpu(head->h_fmt) != XLOG_FMT)) {
-                xlog_warn(
-        "XFS: dirty log written in incompatible format - can't recover");
+                xfs_warn(mp,
+        "dirty log written in incompatible format - can't recover");
                 xlog_header_check_dump(mp, head);
                 XFS_ERROR_REPORT("xlog_header_check_recover(1)",
                                  XFS_ERRLEVEL_HIGH, mp);
                 return XFS_ERROR(EFSCORRUPTED);
         } else if (unlikely(!uuid_equal(&mp->m_sb.sb_uuid, &head->h_fs_uuid))) {
-                xlog_warn(
-        "XFS: dirty log entry has mismatched uuid - can't recover");
+                xfs_warn(mp,
+        "dirty log entry has mismatched uuid - can't recover");
                 xlog_header_check_dump(mp, head);
                 XFS_ERROR_REPORT("xlog_header_check_recover(2)",
                                  XFS_ERRLEVEL_HIGH, mp);
@@ -312,9 +312,9 @@ xlog_header_check_mount(
                  * h_fs_uuid is nil, we assume this log was last mounted
                  * by IRIX and continue.
                  */
-                xlog_warn("XFS: nil uuid in log - IRIX style log");
+                xfs_warn(mp, "nil uuid in log - IRIX style log");
         } else if (unlikely(!uuid_equal(&mp->m_sb.sb_uuid, &head->h_fs_uuid))) {
-                xlog_warn("XFS: log has mismatched uuid - can't recover");
+                xfs_warn(mp, "log has mismatched uuid - can't recover");
                 xlog_header_check_dump(mp, head);
                 XFS_ERROR_REPORT("xlog_header_check_mount",
                                  XFS_ERRLEVEL_HIGH, mp);
@@ -490,8 +490,8 @@ xlog_find_verify_log_record(
         for (i = (*last_blk) - 1; i >= 0; i--) {
                 if (i < start_blk) {
                         /* valid log record not found */
-                        xlog_warn(
-                "XFS: Log inconsistent (didn't find previous header)");
+                        xfs_warn(log->l_mp,
+                "Log inconsistent (didn't find previous header)");
                         ASSERT(0);
                         error = XFS_ERROR(EIO);
                         goto out;
@@ -591,12 +591,12 @@ xlog_find_head(
                          * mkfs etc write a dummy unmount record to a fresh
                          * log so we can store the uuid in there
                          */
-                        xlog_warn("XFS: totally zeroed log");
+                        xfs_warn(log->l_mp, "totally zeroed log");
                 }
 
                 return 0;
         } else if (error) {
-                xlog_warn("XFS: empty log check failed");
+                xfs_warn(log->l_mp, "empty log check failed");
                 return error;
         }
 
@@ -819,7 +819,7 @@ validate_head:
         xlog_put_bp(bp);
 
         if (error)
-            xlog_warn("XFS: failed to find log head");
+                xfs_warn(log->l_mp, "failed to find log head");
         return error;
 }
 
@@ -912,7 +912,7 @@ xlog_find_tail(
                 }
         }
         if (!found) {
-                xlog_warn("XFS: xlog_find_tail: couldn't find sync record");
+                xfs_warn(log->l_mp, "%s: couldn't find sync record", __func__);
                 ASSERT(0);
                 return XFS_ERROR(EIO);
         }
@@ -1028,7 +1028,7 @@ done:
         xlog_put_bp(bp);
 
         if (error)
-                xlog_warn("XFS: failed to locate log tail");
+                xfs_warn(log->l_mp, "failed to locate log tail");
         return error;
 }
 
@@ -1092,7 +1092,8 @@ xlog_find_zeroed(
                  * the first block must be 1. If it's not, maybe we're
                  * not looking at a log... Bail out.
                  */
-                xlog_warn("XFS: Log inconsistent or not a log (last==0, first!=1)");
+                xfs_warn(log->l_mp,
+                        "Log inconsistent or not a log (last==0, first!=1)");
                 return XFS_ERROR(EINVAL);
         }
 
@@ -1506,8 +1507,8 @@ xlog_recover_add_to_trans(
         if (list_empty(&trans->r_itemq)) {
                 /* we need to catch log corruptions here */
                 if (*(uint *)dp != XFS_TRANS_HEADER_MAGIC) {
-                        xlog_warn("XFS: xlog_recover_add_to_trans: "
-                                  "bad header magic number");
+                        xfs_warn(log->l_mp, "%s: bad header magic number",
+                                __func__);
                         ASSERT(0);
                         return XFS_ERROR(EIO);
                 }
@@ -1534,8 +1535,8 @@ xlog_recover_add_to_trans(
         if (item->ri_total == 0) {              /* first region to be added */
                 if (in_f->ilf_size == 0 ||
                     in_f->ilf_size > XLOG_MAX_REGIONS_IN_ITEM) {
-                        xlog_warn(
-        "XFS: bad number of regions (%d) in inode log format",
+                        xfs_warn(log->l_mp,
+                "bad number of regions (%d) in inode log format",
                                   in_f->ilf_size);
                         ASSERT(0);
                         return XFS_ERROR(EIO);
@@ -1592,8 +1593,9 @@ xlog_recover_reorder_trans(
                         list_move_tail(&item->ri_list, &trans->r_itemq);
                         break;
                 default:
-                        xlog_warn(
-        "XFS: xlog_recover_reorder_trans: unrecognized type of log operation");
+                        xfs_warn(log->l_mp,
+                                "%s: unrecognized type of log operation",
+                                __func__);
                         ASSERT(0);
                         return XFS_ERROR(EIO);
                 }
@@ -1803,8 +1805,9 @@ xlog_recover_do_inode_buffer(
                 logged_nextp = item->ri_buf[item_index].i_addr +
                                 next_unlinked_offset - reg_buf_offset;
                 if (unlikely(*logged_nextp == 0)) {
-                        xfs_fs_cmn_err(CE_ALERT, mp,
-                                "bad inode buffer log record (ptr = 0x%p, bp = 0x%p).  XFS trying to replay bad (0) inode di_next_unlinked field",
+                        xfs_alert(mp,
+                "Bad inode buffer log record (ptr = 0x%p, bp = 0x%p). "
+                "Trying to replay bad (0) inode di_next_unlinked field.",
                                 item, bp);
                         XFS_ERROR_REPORT("xlog_recover_do_inode_buf",
                                          XFS_ERRLEVEL_LOW, mp);
@@ -1863,17 +1866,17 @@ xlog_recover_do_reg_buffer(
                 if (buf_f->blf_flags &
                    (XFS_BLF_UDQUOT_BUF|XFS_BLF_PDQUOT_BUF|XFS_BLF_GDQUOT_BUF)) {
                         if (item->ri_buf[i].i_addr == NULL) {
-                                cmn_err(CE_ALERT,
+                                xfs_alert(mp,
                                         "XFS: NULL dquot in %s.", __func__);
                                 goto next;
                         }
                         if (item->ri_buf[i].i_len < sizeof(xfs_disk_dquot_t)) {
-                                cmn_err(CE_ALERT,
+                                xfs_alert(mp,
                                         "XFS: dquot too small (%d) in %s.",
                                         item->ri_buf[i].i_len, __func__);
                                 goto next;
                         }
-                        error = xfs_qm_dqcheck(item->ri_buf[i].i_addr,
+                        error = xfs_qm_dqcheck(mp, item->ri_buf[i].i_addr,
                                                -1, 0, XFS_QMOPT_DOWARN,
                                                "dquot_buf_recover");
                         if (error)
@@ -1898,6 +1901,7 @@ xlog_recover_do_reg_buffer(
  */
 int
 xfs_qm_dqcheck(
+        struct xfs_mount *mp,
         xfs_disk_dquot_t *ddq,
         xfs_dqid_t       id,
         uint             type,    /* used only when IO_dorepair is true */
@@ -1924,14 +1928,14 @@ xfs_qm_dqcheck(
          */
         if (be16_to_cpu(ddq->d_magic) != XFS_DQUOT_MAGIC) {
                 if (flags & XFS_QMOPT_DOWARN)
-                        cmn_err(CE_ALERT,
+                        xfs_alert(mp,
                         "%s : XFS dquot ID 0x%x, magic 0x%x != 0x%x",
                         str, id, be16_to_cpu(ddq->d_magic), XFS_DQUOT_MAGIC);
                 errs++;
         }
         if (ddq->d_version != XFS_DQUOT_VERSION) {
                 if (flags & XFS_QMOPT_DOWARN)
-                        cmn_err(CE_ALERT,
+                        xfs_alert(mp,
                         "%s : XFS dquot ID 0x%x, version 0x%x != 0x%x",
                         str, id, ddq->d_version, XFS_DQUOT_VERSION);
                 errs++;
@@ -1941,7 +1945,7 @@ xfs_qm_dqcheck(
             ddq->d_flags != XFS_DQ_PROJ &&
             ddq->d_flags != XFS_DQ_GROUP) {
                 if (flags & XFS_QMOPT_DOWARN)
-                        cmn_err(CE_ALERT,
+                        xfs_alert(mp,
                         "%s : XFS dquot ID 0x%x, unknown flags 0x%x",
                         str, id, ddq->d_flags);
                 errs++;
@@ -1949,7 +1953,7 @@ xfs_qm_dqcheck(
 
         if (id != -1 && id != be32_to_cpu(ddq->d_id)) {
                 if (flags & XFS_QMOPT_DOWARN)
-                        cmn_err(CE_ALERT,
+                        xfs_alert(mp,
                         "%s : ondisk-dquot 0x%p, ID mismatch: "
                         "0x%x expected, found id 0x%x",
                         str, ddq, id, be32_to_cpu(ddq->d_id));
@@ -1962,9 +1966,8 @@ xfs_qm_dqcheck(
                                 be64_to_cpu(ddq->d_blk_softlimit)) {
                         if (!ddq->d_btimer) {
                                 if (flags & XFS_QMOPT_DOWARN)
-                                        cmn_err(CE_ALERT,
-                                        "%s : Dquot ID 0x%x (0x%p) "
-                                        "BLK TIMER NOT STARTED",
+                                        xfs_alert(mp,
+                        "%s : Dquot ID 0x%x (0x%p) BLK TIMER NOT STARTED",
                                         str, (int)be32_to_cpu(ddq->d_id), ddq);
                                 errs++;
                         }
@@ -1974,9 +1977,8 @@ xfs_qm_dqcheck(
                                 be64_to_cpu(ddq->d_ino_softlimit)) {
                         if (!ddq->d_itimer) {
                                 if (flags & XFS_QMOPT_DOWARN)
-                                        cmn_err(CE_ALERT,
-                                        "%s : Dquot ID 0x%x (0x%p) "
-                                        "INODE TIMER NOT STARTED",
+                                        xfs_alert(mp,
+                        "%s : Dquot ID 0x%x (0x%p) INODE TIMER NOT STARTED",
                                         str, (int)be32_to_cpu(ddq->d_id), ddq);
                                 errs++;
                         }
@@ -1986,9 +1988,8 @@ xfs_qm_dqcheck(
                                 be64_to_cpu(ddq->d_rtb_softlimit)) {
                         if (!ddq->d_rtbtimer) {
                                 if (flags & XFS_QMOPT_DOWARN)
-                                        cmn_err(CE_ALERT,
-                                        "%s : Dquot ID 0x%x (0x%p) "
-                                        "RTBLK TIMER NOT STARTED",
+                                        xfs_alert(mp,
+                        "%s : Dquot ID 0x%x (0x%p) RTBLK TIMER NOT STARTED",
                                         str, (int)be32_to_cpu(ddq->d_id), ddq);
                                 errs++;
                         }
@@ -1999,7 +2000,7 @@ xfs_qm_dqcheck(
                 return errs;
 
         if (flags & XFS_QMOPT_DOWARN)
-                cmn_err(CE_NOTE, "Re-initializing dquot ID 0x%x", id);
+                xfs_notice(mp, "Re-initializing dquot ID 0x%x", id);
 
         /*
          * Typically, a repair is only requested by quotacheck.
@@ -2218,9 +2219,9 @@ xlog_recover_inode_pass2(
          */
         if (unlikely(be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC)) {
                 xfs_buf_relse(bp);
-                xfs_fs_cmn_err(CE_ALERT, mp,
-                        "xfs_inode_recover: Bad inode magic number, dino ptr = 0x%p, dino bp = 0x%p, ino = %Ld",
-                        dip, bp, in_f->ilf_ino);
+                xfs_alert(mp,
+        "%s: Bad inode magic number, dip = 0x%p, dino bp = 0x%p, ino = %Ld",
+                        __func__, dip, bp, in_f->ilf_ino);
                 XFS_ERROR_REPORT("xlog_recover_inode_pass2(1)",
                                  XFS_ERRLEVEL_LOW, mp);
                 error = EFSCORRUPTED;
@@ -2229,9 +2230,9 @@ xlog_recover_inode_pass2(
         dicp = item->ri_buf[1].i_addr;
         if (unlikely(dicp->di_magic != XFS_DINODE_MAGIC)) {
                 xfs_buf_relse(bp);
-                xfs_fs_cmn_err(CE_ALERT, mp,
-                        "xfs_inode_recover: Bad inode log record, rec ptr 0x%p, ino %Ld",
-                        item, in_f->ilf_ino);
+                xfs_alert(mp,
+                        "%s: Bad inode log record, rec ptr 0x%p, ino %Ld",
+                        __func__, item, in_f->ilf_ino);
                 XFS_ERROR_REPORT("xlog_recover_inode_pass2(2)",
                                  XFS_ERRLEVEL_LOW, mp);
                 error = EFSCORRUPTED;
@@ -2263,9 +2264,10 @@ xlog_recover_inode_pass2(
                         XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(3)",
                                          XFS_ERRLEVEL_LOW, mp, dicp);
                         xfs_buf_relse(bp);
-                        xfs_fs_cmn_err(CE_ALERT, mp,
-                                "xfs_inode_recover: Bad regular inode log record, rec ptr 0x%p, ino ptr = 0x%p, ino bp = 0x%p, ino %Ld",
-                                item, dip, bp, in_f->ilf_ino);
+                        xfs_alert(mp,
+                "%s: Bad regular inode log record, rec ptr 0x%p, "
+                "ino ptr = 0x%p, ino bp = 0x%p, ino %Ld",
+                                __func__, item, dip, bp, in_f->ilf_ino);
                         error = EFSCORRUPTED;
                         goto error;
                 }
@@ -2276,9 +2278,10 @@ xlog_recover_inode_pass2(
                         XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(4)",
                                              XFS_ERRLEVEL_LOW, mp, dicp);
                         xfs_buf_relse(bp);
-                        xfs_fs_cmn_err(CE_ALERT, mp,
-                                "xfs_inode_recover: Bad dir inode log record, rec ptr 0x%p, ino ptr = 0x%p, ino bp = 0x%p, ino %Ld",
-                                item, dip, bp, in_f->ilf_ino);
+                        xfs_alert(mp,
+                "%s: Bad dir inode log record, rec ptr 0x%p, "
+                "ino ptr = 0x%p, ino bp = 0x%p, ino %Ld",
+                                __func__, item, dip, bp, in_f->ilf_ino);
                         error = EFSCORRUPTED;
                         goto error;
                 }
@@ -2287,9 +2290,10 @@ xlog_recover_inode_pass2(
                 XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(5)",
                                      XFS_ERRLEVEL_LOW, mp, dicp);
                 xfs_buf_relse(bp);
-                xfs_fs_cmn_err(CE_ALERT, mp,
-                        "xfs_inode_recover: Bad inode log record, rec ptr 0x%p, dino ptr 0x%p, dino bp 0x%p, ino %Ld, total extents = %d, nblocks = %Ld",
-                        item, dip, bp, in_f->ilf_ino,
+                xfs_alert(mp,
+        "%s: Bad inode log record, rec ptr 0x%p, dino ptr 0x%p, "
+        "dino bp 0x%p, ino %Ld, total extents = %d, nblocks = %Ld",
+                        __func__, item, dip, bp, in_f->ilf_ino,
                         dicp->di_nextents + dicp->di_anextents,
                         dicp->di_nblocks);
                 error = EFSCORRUPTED;
@@ -2299,8 +2303,9 @@ xlog_recover_inode_pass2(
                 XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(6)",
                                      XFS_ERRLEVEL_LOW, mp, dicp);
                 xfs_buf_relse(bp);
-                xfs_fs_cmn_err(CE_ALERT, mp,
-                        "xfs_inode_recover: Bad inode log rec ptr 0x%p, dino ptr 0x%p, dino bp 0x%p, ino %Ld, forkoff 0x%x",
+                xfs_alert(mp,
+        "%s: Bad inode log record, rec ptr 0x%p, dino ptr 0x%p, "
+        "dino bp 0x%p, ino %Ld, forkoff 0x%x", __func__,
                         item, dip, bp, in_f->ilf_ino, dicp->di_forkoff);
                 error = EFSCORRUPTED;
                 goto error;
@@ -2309,9 +2314,9 @@ xlog_recover_inode_pass2(
                 XFS_CORRUPTION_ERROR("xlog_recover_inode_pass2(7)",
                                      XFS_ERRLEVEL_LOW, mp, dicp);
                 xfs_buf_relse(bp);
-                xfs_fs_cmn_err(CE_ALERT, mp,
-                        "xfs_inode_recover: Bad inode log record length %d, rec ptr 0x%p",
-                        item->ri_buf[1].i_len, item);
+                xfs_alert(mp,
+                        "%s: Bad inode log record length %d, rec ptr 0x%p",
+                        __func__, item->ri_buf[1].i_len, item);
                 error = EFSCORRUPTED;
                 goto error;
         }
@@ -2398,7 +2403,7 @@ xlog_recover_inode_pass2(
                         break;
 
                 default:
-                        xlog_warn("XFS: xlog_recover_inode_pass2: Invalid flag");
+                        xfs_warn(log->l_mp, "%s: Invalid flag", __func__);
                         ASSERT(0);
                         xfs_buf_relse(bp);
                         error = EIO;
@@ -2467,13 +2472,11 @@ xlog_recover_dquot_pass2(
 
         recddq = item->ri_buf[1].i_addr;
         if (recddq == NULL) {
-                cmn_err(CE_ALERT,
-                        "XFS: NULL dquot in %s.", __func__);
+                xfs_alert(log->l_mp, "NULL dquot in %s.", __func__);
                 return XFS_ERROR(EIO);
         }
         if (item->ri_buf[1].i_len < sizeof(xfs_disk_dquot_t)) {
-                cmn_err(CE_ALERT,
-                        "XFS: dquot too small (%d) in %s.",
+                xfs_alert(log->l_mp, "dquot too small (%d) in %s.",
                         item->ri_buf[1].i_len, __func__);
                 return XFS_ERROR(EIO);
         }
@@ -2498,12 +2501,10 @@ xlog_recover_dquot_pass2(
          */
         dq_f = item->ri_buf[0].i_addr;
         ASSERT(dq_f);
-        if ((error = xfs_qm_dqcheck(recddq,
-                           dq_f->qlf_id,
-                           0, XFS_QMOPT_DOWARN,
-                           "xlog_recover_dquot_pass2 (log copy)"))) {
+        error = xfs_qm_dqcheck(mp, recddq, dq_f->qlf_id, 0, XFS_QMOPT_DOWARN,
+                           "xlog_recover_dquot_pass2 (log copy)");
+        if (error)
                 return XFS_ERROR(EIO);
-        }
         ASSERT(dq_f->qlf_len == 1);
 
         error = xfs_read_buf(mp, mp->m_ddev_targp,
@@ -2523,8 +2524,9 @@ xlog_recover_dquot_pass2(
          * was among a chunk of dquots created earlier, and we did some
          * minimal initialization then.
          */
-        if (xfs_qm_dqcheck(ddq, dq_f->qlf_id, 0, XFS_QMOPT_DOWARN,
-                           "xlog_recover_dquot_pass2")) {
+        error = xfs_qm_dqcheck(mp, ddq, dq_f->qlf_id, 0, XFS_QMOPT_DOWARN,
+                           "xlog_recover_dquot_pass2");
+        if (error) {
                 xfs_buf_relse(bp);
                 return XFS_ERROR(EIO);
         }
@@ -2676,9 +2678,8 @@ xlog_recover_commit_pass1(
                 /* nothing to do in pass 1 */
                 return 0;
         default:
-                xlog_warn(
-        "XFS: invalid item type (%d) xlog_recover_commit_pass1",
-                        ITEM_TYPE(item));
+                xfs_warn(log->l_mp, "%s: invalid item type (%d)",
+                        __func__, ITEM_TYPE(item));
                 ASSERT(0);
                 return XFS_ERROR(EIO);
         }
@@ -2707,9 +2708,8 @@ xlog_recover_commit_pass2(
                 /* nothing to do in pass2 */
                 return 0;
         default:
-                xlog_warn(
-        "XFS: invalid item type (%d) xlog_recover_commit_pass2",
-                        ITEM_TYPE(item));
+                xfs_warn(log->l_mp, "%s: invalid item type (%d)",
+                        __func__, ITEM_TYPE(item));
                 ASSERT(0);
                 return XFS_ERROR(EIO);
         }
@@ -2751,10 +2751,11 @@ xlog_recover_commit_trans(
 
 STATIC int
 xlog_recover_unmount_trans(
+        struct log              *log,
         xlog_recover_t          *trans)
 {
         /* Do nothing now */
-        xlog_warn("XFS: xlog_recover_unmount_trans: Unmount LR");
+        xfs_warn(log->l_mp, "%s: Unmount LR", __func__);
         return 0;
 }
 
@@ -2797,8 +2798,8 @@ xlog_recover_process_data(
                 dp += sizeof(xlog_op_header_t);
                 if (ohead->oh_clientid != XFS_TRANSACTION &&
                     ohead->oh_clientid != XFS_LOG) {
-                        xlog_warn(
-                "XFS: xlog_recover_process_data: bad clientid");
+                        xfs_warn(log->l_mp, "%s: bad clientid 0x%x",
+                                        __func__, ohead->oh_clientid);
                         ASSERT(0);
                         return (XFS_ERROR(EIO));
                 }
@@ -2811,8 +2812,8 @@ xlog_recover_process_data(
                                         be64_to_cpu(rhead->h_lsn));
                 } else {
                         if (dp + be32_to_cpu(ohead->oh_len) > lp) {
-                                xlog_warn(
-                        "XFS: xlog_recover_process_data: bad length");
+                                xfs_warn(log->l_mp, "%s: bad length 0x%x",
+                                        __func__, be32_to_cpu(ohead->oh_len));
                                 WARN_ON(1);
                                 return (XFS_ERROR(EIO));
                         }
@@ -2825,7 +2826,7 @@ xlog_recover_process_data(
                                                                 trans, pass);
                                 break;
                         case XLOG_UNMOUNT_TRANS:
-                                error = xlog_recover_unmount_trans(trans);
+                                error = xlog_recover_unmount_trans(log, trans);
                                 break;
                         case XLOG_WAS_CONT_TRANS:
                                 error = xlog_recover_add_to_cont_trans(log,
@@ -2833,8 +2834,8 @@ xlog_recover_process_data(
                                                 be32_to_cpu(ohead->oh_len));
                                 break;
                         case XLOG_START_TRANS:
-                                xlog_warn(
-                        "XFS: xlog_recover_process_data: bad transaction");
+                                xfs_warn(log->l_mp, "%s: bad transaction",
+                                        __func__);
                                 ASSERT(0);
                                 error = XFS_ERROR(EIO);
                                 break;
@@ -2844,8 +2845,8 @@ xlog_recover_process_data(
                                                 dp, be32_to_cpu(ohead->oh_len));
                                 break;
                         default:
-                                xlog_warn(
-                        "XFS: xlog_recover_process_data: bad flag");
+                                xfs_warn(log->l_mp, "%s: bad flag 0x%x",
+                                        __func__, flags);
                                 ASSERT(0);
                                 error = XFS_ERROR(EIO);
                                 break;
@@ -3030,8 +3031,7 @@ xlog_recover_clear_agi_bucket(
 out_abort:
         xfs_trans_cancel(tp, XFS_TRANS_ABORT);
 out_error:
-        xfs_fs_cmn_err(CE_WARN, mp, "xlog_recover_clear_agi_bucket: "
-                        "failed to clear agi %d. Continuing.", agno);
+        xfs_warn(mp, "%s: failed to clear agi %d. Continuing.", __func__, agno);
         return;
 }
 
@@ -3282,7 +3282,7 @@ xlog_valid_rec_header(
         if (unlikely(
             (!rhead->h_version ||
             (be32_to_cpu(rhead->h_version) & (~XLOG_VERSION_OKBITS))))) {
-                xlog_warn("XFS: %s: unrecognised log version (%d).",
+                xfs_warn(log->l_mp, "%s: unrecognised log version (%d).",
                         __func__, be32_to_cpu(rhead->h_version));
                 return XFS_ERROR(EIO);
         }
@@ -3740,10 +3740,9 @@ xlog_recover(
                         return error;
                 }
 
-                cmn_err(CE_NOTE,
-                        "Starting XFS recovery on filesystem: %s (logdev: %s)",
-                        log->l_mp->m_fsname, log->l_mp->m_logname ?
-                        log->l_mp->m_logname : "internal");
+                xfs_notice(log->l_mp, "Starting recovery (logdev: %s)",
+                                log->l_mp->m_logname ? log->l_mp->m_logname
+                                                     : "internal");
 
                 error = xlog_do_recover(log, head_blk, tail_blk);
                 log->l_flags |= XLOG_RECOVERY_NEEDED;
@@ -3776,9 +3775,7 @@ xlog_recover_finish(
                 int     error;
                 error = xlog_recover_process_efis(log);
                 if (error) {
-                        cmn_err(CE_ALERT,
-                                "Failed to recover EFIs on filesystem: %s",
-                                log->l_mp->m_fsname);
+                        xfs_alert(log->l_mp, "Failed to recover EFIs");
                         return error;
                 }
                 /*
@@ -3793,15 +3790,12 @@ xlog_recover_finish(
 
                 xlog_recover_check_summary(log);
 
-                cmn_err(CE_NOTE,
-                        "Ending XFS recovery on filesystem: %s (logdev: %s)",
-                        log->l_mp->m_fsname, log->l_mp->m_logname ?
-                        log->l_mp->m_logname : "internal");
+                xfs_notice(log->l_mp, "Ending recovery (logdev: %s)",
+                                log->l_mp->m_logname ? log->l_mp->m_logname
+                                                     : "internal");
                 log->l_flags &= ~XLOG_RECOVERY_NEEDED;
         } else {
-                cmn_err(CE_DEBUG,
-                        "Ending clean XFS mount for filesystem: %s\n",
-                        log->l_mp->m_fsname);
+                xfs_info(log->l_mp, "Ending clean mount");
         }
         return 0;
 }
@@ -3834,10 +3828,8 @@ xlog_recover_check_summary(
         for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
                 error = xfs_read_agf(mp, NULL, agno, 0, &agfbp);
                 if (error) {
-                        xfs_fs_cmn_err(CE_ALERT, mp,
-                                        "xlog_recover_check_summary(agf)"
-                                        "agf read failed agno %d error %d",
-                                                        agno, error);
+                        xfs_alert(mp, "%s agf read failed agno %d error %d",
+                                                __func__, agno, error);
                 } else {
                         agfp = XFS_BUF_TO_AGF(agfbp);
                         freeblks += be32_to_cpu(agfp->agf_freeblks) +
@@ -3846,7 +3838,10 @@ xlog_recover_check_summary(
                 }
 
                 error = xfs_read_agi(mp, NULL, agno, &agibp);
-                if (!error) {
+                if (error) {
+                        xfs_alert(mp, "%s agi read failed agno %d error %d",
+                                                __func__, agno, error);
+                } else {
                         struct xfs_agi  *agi = XFS_BUF_TO_AGI(agibp);
 
                         itotal += be32_to_cpu(agi->agi_count);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index d447aef84bc3..bb3f9a7b24ed 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -133,9 +133,7 @@ xfs_uuid_mount(
                 return 0;
 
         if (uuid_is_nil(uuid)) {
-                cmn_err(CE_WARN,
-                        "XFS: Filesystem %s has nil UUID - can't mount",
-                        mp->m_fsname);
+                xfs_warn(mp, "Filesystem has nil UUID - can't mount");
                 return XFS_ERROR(EINVAL);
         }
 
@@ -163,8 +161,7 @@ xfs_uuid_mount(
 
  out_duplicate:
         mutex_unlock(&xfs_uuid_table_mutex);
-        cmn_err(CE_WARN, "XFS: Filesystem %s has duplicate UUID - can't mount",
-                         mp->m_fsname);
+        xfs_warn(mp, "Filesystem has duplicate UUID - can't mount");
         return XFS_ERROR(EINVAL);
 }
 
@@ -311,6 +308,8 @@ xfs_mount_validate_sb(
         xfs_sb_t        *sbp,
         int             flags)
 {
+        int             loud = !(flags & XFS_MFSI_QUIET);
+
         /*
          * If the log device and data device have the
          * same device number, the log is internal.
@@ -319,28 +318,32 @@ xfs_mount_validate_sb(
          * a volume filesystem in a non-volume manner.
          */
         if (sbp->sb_magicnum != XFS_SB_MAGIC) {
-                xfs_fs_mount_cmn_err(flags, "bad magic number");
+                if (loud)
+                        xfs_warn(mp, "bad magic number");
                 return XFS_ERROR(EWRONGFS);
         }
 
         if (!xfs_sb_good_version(sbp)) {
-                xfs_fs_mount_cmn_err(flags, "bad version");
+                if (loud)
+                        xfs_warn(mp, "bad version");
                 return XFS_ERROR(EWRONGFS);
         }
 
         if (unlikely(
             sbp->sb_logstart == 0 && mp->m_logdev_targp == mp->m_ddev_targp)) {
-                xfs_fs_mount_cmn_err(flags,
-                        "filesystem is marked as having an external log; "
-                        "specify logdev on the\nmount command line.");
+                if (loud)
+                        xfs_warn(mp,
+                "filesystem is marked as having an external log; "
+                "specify logdev on the mount command line.");
                 return XFS_ERROR(EINVAL);
         }
 
         if (unlikely(
             sbp->sb_logstart != 0 && mp->m_logdev_targp != mp->m_ddev_targp)) {
-                xfs_fs_mount_cmn_err(flags,
-                        "filesystem is marked as having an internal log; "
-                        "do not specify logdev on\nthe mount command line.");
+                if (loud)
+                        xfs_warn(mp,
+                "filesystem is marked as having an internal log; "
+                "do not specify logdev on the mount command line.");
                 return XFS_ERROR(EINVAL);
         }
 
@@ -369,7 +372,8 @@ xfs_mount_validate_sb(
             (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE)  ||
             (sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE)  ||
             (sbp->sb_imax_pct > 100 /* zero sb_imax_pct is valid */))) {
-                xfs_fs_mount_cmn_err(flags, "SB sanity check 1 failed");
+                if (loud)
+                        xfs_warn(mp, "SB sanity check 1 failed");
                 return XFS_ERROR(EFSCORRUPTED);
         }
 
@@ -382,7 +386,8 @@ xfs_mount_validate_sb(
              (xfs_drfsbno_t)sbp->sb_agcount * sbp->sb_agblocks ||
             sbp->sb_dblocks < (xfs_drfsbno_t)(sbp->sb_agcount - 1) *
                               sbp->sb_agblocks + XFS_MIN_AG_BLOCKS)) {
-                xfs_fs_mount_cmn_err(flags, "SB sanity check 2 failed");
+                if (loud)
+                        xfs_warn(mp, "SB sanity check 2 failed");
                 return XFS_ERROR(EFSCORRUPTED);
         }
 
@@ -390,12 +395,12 @@ xfs_mount_validate_sb(
          * Until this is fixed only page-sized or smaller data blocks work.
          */
         if (unlikely(sbp->sb_blocksize > PAGE_SIZE)) {
-                xfs_fs_mount_cmn_err(flags,
-                        "file system with blocksize %d bytes",
-                        sbp->sb_blocksize);
-                xfs_fs_mount_cmn_err(flags,
-                        "only pagesize (%ld) or less will currently work.",
-                        PAGE_SIZE);
+                if (loud) {
+                        xfs_warn(mp,
+                "File system with blocksize %d bytes. "
+                "Only pagesize (%ld) or less will currently work.",
+                                sbp->sb_blocksize, PAGE_SIZE);
+                }
                 return XFS_ERROR(ENOSYS);
         }
 
@@ -409,21 +414,23 @@ xfs_mount_validate_sb(
         case 2048:
                 break;
         default:
-                xfs_fs_mount_cmn_err(flags,
-                        "inode size of %d bytes not supported",
-                        sbp->sb_inodesize);
+                if (loud)
+                        xfs_warn(mp, "inode size of %d bytes not supported",
+                                sbp->sb_inodesize);
                 return XFS_ERROR(ENOSYS);
         }
 
         if (xfs_sb_validate_fsb_count(sbp, sbp->sb_dblocks) ||
             xfs_sb_validate_fsb_count(sbp, sbp->sb_rblocks)) {
-                xfs_fs_mount_cmn_err(flags,
-                        "file system too large to be mounted on this system.");
+                if (loud)
+                        xfs_warn(mp,
+                "file system too large to be mounted on this system.");
                 return XFS_ERROR(EFBIG);
         }
 
         if (unlikely(sbp->sb_inprogress)) {
-                xfs_fs_mount_cmn_err(flags, "file system busy");
+                if (loud)
+                        xfs_warn(mp, "file system busy");
                 return XFS_ERROR(EFSCORRUPTED);
         }
 
@@ -431,8 +438,9 @@ xfs_mount_validate_sb(
          * Version 1 directory format has never worked on Linux.
          */
         if (unlikely(!xfs_sb_version_hasdirv2(sbp))) {
-                xfs_fs_mount_cmn_err(flags,
-                        "file system using version 1 directory format");
+                if (loud)
+                        xfs_warn(mp,
+                                "file system using version 1 directory format");
                 return XFS_ERROR(ENOSYS);
         }
 
@@ -673,6 +681,7 @@ xfs_readsb(xfs_mount_t *mp, int flags)
         unsigned int    sector_size;
         xfs_buf_t       *bp;
         int             error;
+        int             loud = !(flags & XFS_MFSI_QUIET);
 
         ASSERT(mp->m_sb_bp == NULL);
         ASSERT(mp->m_ddev_targp != NULL);
@@ -688,7 +697,8 @@ reread:
         bp = xfs_buf_read_uncached(mp, mp->m_ddev_targp,
                                         XFS_SB_DADDR, sector_size, 0);
         if (!bp) {
-                xfs_fs_mount_cmn_err(flags, "SB buffer read failed");
+                if (loud)
+                        xfs_warn(mp, "SB buffer read failed");
                 return EIO;
         }
 
@@ -699,7 +709,8 @@ reread:
         xfs_sb_from_disk(&mp->m_sb, XFS_BUF_TO_SBP(bp));
         error = xfs_mount_validate_sb(mp, &(mp->m_sb), flags);
         if (error) {
-                xfs_fs_mount_cmn_err(flags, "SB validate failed");
+                if (loud)
+                        xfs_warn(mp, "SB validate failed");
                 goto release_buf;
         }
 
@@ -707,9 +718,9 @@ reread:
          * We must be able to do sector-sized and sector-aligned IO.
          */
         if (sector_size > mp->m_sb.sb_sectsize) {
-                xfs_fs_mount_cmn_err(flags,
-                        "device supports only %u byte sectors (not %u)",
-                        sector_size, mp->m_sb.sb_sectsize);
+                if (loud)
+                        xfs_warn(mp, "device supports %u byte sectors (not %u)",
+                                sector_size, mp->m_sb.sb_sectsize);
                 error = ENOSYS;
                 goto release_buf;
         }
@@ -853,8 +864,7 @@ xfs_update_alignment(xfs_mount_t *mp)
                 if ((BBTOB(mp->m_dalign) & mp->m_blockmask) ||
                     (BBTOB(mp->m_swidth) & mp->m_blockmask)) {
                         if (mp->m_flags & XFS_MOUNT_RETERR) {
-                                cmn_err(CE_WARN,
-                                        "XFS: alignment check 1 failed");
+                                xfs_warn(mp, "alignment check 1 failed");
                                 return XFS_ERROR(EINVAL);
                         }
                         mp->m_dalign = mp->m_swidth = 0;
@@ -867,8 +877,9 @@ xfs_update_alignment(xfs_mount_t *mp)
                                 if (mp->m_flags & XFS_MOUNT_RETERR) {
                                         return XFS_ERROR(EINVAL);
                                 }
-                                xfs_fs_cmn_err(CE_WARN, mp,
-"stripe alignment turned off: sunit(%d)/swidth(%d) incompatible with agsize(%d)",
+                                xfs_warn(mp,
+                "stripe alignment turned off: sunit(%d)/swidth(%d) "
+                "incompatible with agsize(%d)",
                                         mp->m_dalign, mp->m_swidth,
                                         sbp->sb_agblocks);
 
@@ -878,9 +889,9 @@ xfs_update_alignment(xfs_mount_t *mp)
                                 mp->m_swidth = XFS_BB_TO_FSBT(mp, mp->m_swidth);
                         } else {
                                 if (mp->m_flags & XFS_MOUNT_RETERR) {
-                                        xfs_fs_cmn_err(CE_WARN, mp,
-"stripe alignment turned off: sunit(%d) less than bsize(%d)",
-                                                mp->m_dalign,
+                                        xfs_warn(mp,
+                "stripe alignment turned off: sunit(%d) less than bsize(%d)",
+                                                mp->m_dalign,
                                                 mp->m_blockmask +1);
                                         return XFS_ERROR(EINVAL);
                                 }
@@ -1026,14 +1037,14 @@ xfs_check_sizes(xfs_mount_t *mp)
 
         d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
         if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_dblocks) {
-                cmn_err(CE_WARN, "XFS: filesystem size mismatch detected");
+                xfs_warn(mp, "filesystem size mismatch detected");
                 return XFS_ERROR(EFBIG);
         }
         bp = xfs_buf_read_uncached(mp, mp->m_ddev_targp,
                                         d - XFS_FSS_TO_BB(mp, 1),
                                         BBTOB(XFS_FSS_TO_BB(mp, 1)), 0);
         if (!bp) {
-                cmn_err(CE_WARN, "XFS: last sector read failed");
+                xfs_warn(mp, "last sector read failed");
                 return EIO;
         }
         xfs_buf_relse(bp);
@@ -1041,14 +1052,14 @@ xfs_check_sizes(xfs_mount_t *mp)
         if (mp->m_logdev_targp != mp->m_ddev_targp) {
                 d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
                 if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_logblocks) {
-                        cmn_err(CE_WARN, "XFS: log size mismatch detected");
+                        xfs_warn(mp, "log size mismatch detected");
                         return XFS_ERROR(EFBIG);
                 }
                 bp = xfs_buf_read_uncached(mp, mp->m_logdev_targp,
                                         d - XFS_FSB_TO_BB(mp, 1),
                                         XFS_FSB_TO_B(mp, 1), 0);
                 if (!bp) {
-                        cmn_err(CE_WARN, "XFS: log device read failed");
+                        xfs_warn(mp, "log device read failed");
                         return EIO;
                 }
                 xfs_buf_relse(bp);
@@ -1086,7 +1097,7 @@ xfs_mount_reset_sbqflags(
                 return 0;
 
 #ifdef QUOTADEBUG
-        xfs_fs_cmn_err(CE_NOTE, mp, "Writing superblock quota changes");
+        xfs_notice(mp, "Writing superblock quota changes");
 #endif
 
         tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SBCHANGE);
@@ -1094,8 +1105,7 @@ xfs_mount_reset_sbqflags(
                                       XFS_DEFAULT_LOG_COUNT);
         if (error) {
                 xfs_trans_cancel(tp, 0);
-                xfs_fs_cmn_err(CE_ALERT, mp,
-                        "xfs_mount_reset_sbqflags: Superblock update failed!");
+                xfs_alert(mp, "%s: Superblock update failed!", __func__);
                 return error;
         }
 
@@ -1161,8 +1171,7 @@ xfs_mountfs(
          * transaction subsystem is online.
          */
         if (xfs_sb_has_mismatched_features2(sbp)) {
-                cmn_err(CE_WARN,
-                        "XFS: correcting sb_features alignment problem");
+                xfs_warn(mp, "correcting sb_features alignment problem");
                 sbp->sb_features2 |= sbp->sb_bad_features2;
                 sbp->sb_bad_features2 = sbp->sb_features2;
                 mp->m_update_flags |= XFS_SB_FEATURES2 | XFS_SB_BAD_FEATURES2;
@@ -1241,7 +1250,7 @@ xfs_mountfs(
          */
         error = xfs_rtmount_init(mp);
         if (error) {
-                cmn_err(CE_WARN, "XFS: RT mount failed");
+                xfs_warn(mp, "RT mount failed");
                 goto out_remove_uuid;
         }
 
@@ -1272,12 +1281,12 @@ xfs_mountfs(
         INIT_RADIX_TREE(&mp->m_perag_tree, GFP_ATOMIC);
         error = xfs_initialize_perag(mp, sbp->sb_agcount, &mp->m_maxagi);
         if (error) {
-                cmn_err(CE_WARN, "XFS: Failed per-ag init: %d", error);
+                xfs_warn(mp, "Failed per-ag init: %d", error);
                 goto out_remove_uuid;
         }
 
         if (!sbp->sb_logblocks) {
-                cmn_err(CE_WARN, "XFS: no log defined");
+                xfs_warn(mp, "no log defined");
                 XFS_ERROR_REPORT("xfs_mountfs", XFS_ERRLEVEL_LOW, mp);
                 error = XFS_ERROR(EFSCORRUPTED);
                 goto out_free_perag;
@@ -1290,7 +1299,7 @@ xfs_mountfs(
                               XFS_FSB_TO_DADDR(mp, sbp->sb_logstart),
                               XFS_FSB_TO_BB(mp, sbp->sb_logblocks));
         if (error) {
-                cmn_err(CE_WARN, "XFS: log mount failed");
+                xfs_warn(mp, "log mount failed");
                 goto out_free_perag;
         }
 
@@ -1327,16 +1336,14 @@ xfs_mountfs(
          */
         error = xfs_iget(mp, NULL, sbp->sb_rootino, 0, XFS_ILOCK_EXCL, &rip);
         if (error) {
-                cmn_err(CE_WARN, "XFS: failed to read root inode");
+                xfs_warn(mp, "failed to read root inode");
                 goto out_log_dealloc;
         }
 
         ASSERT(rip != NULL);
 
         if (unlikely((rip->i_d.di_mode & S_IFMT) != S_IFDIR)) {
-                cmn_err(CE_WARN, "XFS: corrupted root inode");
-                cmn_err(CE_WARN, "Device %s - root %llu is not a directory",
-                        XFS_BUFTARG_NAME(mp->m_ddev_targp),
+                xfs_warn(mp, "corrupted root inode %llu: not a directory",
                         (unsigned long long)rip->i_ino);
                 xfs_iunlock(rip, XFS_ILOCK_EXCL);
                 XFS_ERROR_REPORT("xfs_mountfs_int(2)", XFS_ERRLEVEL_LOW,
@@ -1356,7 +1363,7 @@ xfs_mountfs(
                 /*
                  * Free up the root inode.
                  */
-                cmn_err(CE_WARN, "XFS: failed to read RT inodes");
+                xfs_warn(mp, "failed to read RT inodes");
                 goto out_rele_rip;
         }
 
@@ -1368,7 +1375,7 @@ xfs_mountfs(
         if (mp->m_update_flags && !(mp->m_flags & XFS_MOUNT_RDONLY)) {
                 error = xfs_mount_log_sb(mp, mp->m_update_flags);
                 if (error) {
-                        cmn_err(CE_WARN, "XFS: failed to write sb changes");
+                        xfs_warn(mp, "failed to write sb changes");
                         goto out_rtunmount;
                 }
         }
@@ -1389,10 +1396,7 @@ xfs_mountfs(
                  * quotachecked license.
                  */
                 if (mp->m_sb.sb_qflags & XFS_ALL_QUOTA_ACCT) {
-                        cmn_err(CE_NOTE,
-                                "XFS: resetting qflags for filesystem %s",
-                                mp->m_fsname);
-
+                        xfs_notice(mp, "resetting quota flags");
                         error = xfs_mount_reset_sbqflags(mp);
                         if (error)
                                 return error;
@@ -1406,7 +1410,7 @@ xfs_mountfs(
          */
         error = xfs_log_mount_finish(mp);
         if (error) {
-                cmn_err(CE_WARN, "XFS: log mount finish failed");
+                xfs_warn(mp, "log mount finish failed");
                 goto out_rtunmount;
         }
 
@@ -1435,8 +1439,8 @@ xfs_mountfs(
                 resblks = xfs_default_resblks(mp);
                 error = xfs_reserve_blocks(mp, &resblks, NULL);
                 if (error)
-                        cmn_err(CE_WARN, "XFS: Unable to allocate reserve "
-                                "blocks. Continuing without a reserve pool.");
+                        xfs_warn(mp,
+        "Unable to allocate reserve blocks. Continuing without reserve pool.");
         }
 
         return 0;
@@ -1525,12 +1529,12 @@ xfs_unmountfs(
         resblks = 0;
         error = xfs_reserve_blocks(mp, &resblks, NULL);
         if (error)
-                cmn_err(CE_WARN, "XFS: Unable to free reserved block pool. "
+                xfs_warn(mp, "Unable to free reserved block pool. "
                                 "Freespace may not be correct on next mount.");
 
         error = xfs_log_sbcount(mp, 1);
         if (error)
-                cmn_err(CE_WARN, "XFS: Unable to update superblock counters. "
+                xfs_warn(mp, "Unable to update superblock counters. "
                                 "Freespace may not be correct on next mount.");
         xfs_unmountfs_writesb(mp);
         xfs_unmountfs_wait(mp);                 /* wait for async bufs */
@@ -2013,10 +2017,8 @@ xfs_dev_is_read_only(
         if (xfs_readonly_buftarg(mp->m_ddev_targp) ||
             xfs_readonly_buftarg(mp->m_logdev_targp) ||
             (mp->m_rtdev_targp && xfs_readonly_buftarg(mp->m_rtdev_targp))) {
-                cmn_err(CE_NOTE,
-                        "XFS: %s required on read-only device.", message);
-                cmn_err(CE_NOTE,
-                        "XFS: write access unavailable, cannot proceed.");
+                xfs_notice(mp, "%s required on read-only device.", message);
+                xfs_notice(mp, "write access unavailable, cannot proceed.");
                 return EROFS;
         }
         return 0;
diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h
index 9bb6eda4cd21..a595f29567fe 100644
--- a/fs/xfs/xfs_quota.h
+++ b/fs/xfs/xfs_quota.h
@@ -382,7 +382,8 @@ static inline int xfs_qm_sync(struct xfs_mount *mp, int flags)
         xfs_trans_reserve_quota_bydquots(tp, mp, ud, gd, nb, ni, \
                                 f | XFS_QMOPT_RES_REGBLKS)
 
-extern int xfs_qm_dqcheck(xfs_disk_dquot_t *, xfs_dqid_t, uint, uint, char *);
+extern int xfs_qm_dqcheck(struct xfs_mount *, xfs_disk_dquot_t *,
+                                xfs_dqid_t, uint, uint, char *);
 extern int xfs_mount_reset_sbqflags(struct xfs_mount *);
 
 #endif  /* __KERNEL__ */
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 12a191385310..8f76fdff4f46 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -76,7 +76,7 @@ xfs_growfs_rt_alloc(
         xfs_mount_t     *mp,            /* file system mount point */
         xfs_extlen_t    oblocks,        /* old count of blocks */
         xfs_extlen_t    nblocks,        /* new count of blocks */
-        xfs_ino_t       ino)            /* inode number (bitmap/summary) */
+        xfs_inode_t     *ip)            /* inode (bitmap/summary) */
 {
         xfs_fileoff_t   bno;            /* block number in file */
         xfs_buf_t       *bp;            /* temporary buffer for zeroing */
@@ -86,7 +86,6 @@ xfs_growfs_rt_alloc(
         xfs_fsblock_t   firstblock;     /* first block allocated in xaction */
         xfs_bmap_free_t flist;          /* list of freed blocks */
         xfs_fsblock_t   fsbno;          /* filesystem block for bno */
-        xfs_inode_t     *ip;            /* pointer to incore inode */
         xfs_bmbt_irec_t map;            /* block map output */
         int             nmap;           /* number of block maps */
         int             resblks;        /* space reservation */
@@ -112,9 +111,9 @@ xfs_growfs_rt_alloc(
                 /*
                  * Lock the inode.
                  */
-                if ((error = xfs_trans_iget(mp, tp, ino, 0,
-                                                XFS_ILOCK_EXCL, &ip)))
-                        goto error_cancel;
+                xfs_ilock(ip, XFS_ILOCK_EXCL);
+                xfs_trans_ijoin_ref(tp, ip, XFS_ILOCK_EXCL);
+
                 xfs_bmap_init(&flist, &firstblock);
                 /*
                  * Allocate blocks to the bitmap file.
@@ -155,9 +154,8 @@ xfs_growfs_rt_alloc(
                         /*
                          * Lock the bitmap inode.
                          */
-                        if ((error = xfs_trans_iget(mp, tp, ino, 0,
-                                                        XFS_ILOCK_EXCL, &ip)))
-                                goto error_cancel;
+                        xfs_ilock(ip, XFS_ILOCK_EXCL);
+                        xfs_trans_ijoin_ref(tp, ip, XFS_ILOCK_EXCL);
                         /*
                          * Get a buffer for the block.
                          */
@@ -1854,7 +1852,6 @@ xfs_growfs_rt(
         xfs_rtblock_t   bmbno;          /* bitmap block number */
         xfs_buf_t       *bp;            /* temporary buffer */
         int             error;          /* error return value */
-        xfs_inode_t     *ip;            /* bitmap inode, used as lock */
         xfs_mount_t     *nmp;           /* new (fake) mount structure */
         xfs_drfsbno_t   nrblocks;       /* new number of realtime blocks */
         xfs_extlen_t    nrbmblocks;     /* new number of rt bitmap blocks */
@@ -1918,11 +1915,11 @@ xfs_growfs_rt(
         /*
          * Allocate space to the bitmap and summary files, as necessary.
          */
-        if ((error = xfs_growfs_rt_alloc(mp, rbmblocks, nrbmblocks,
-                        mp->m_sb.sb_rbmino)))
+        error = xfs_growfs_rt_alloc(mp, rbmblocks, nrbmblocks, mp->m_rbmip);
+        if (error)
                 return error;
-        if ((error = xfs_growfs_rt_alloc(mp, rsumblocks, nrsumblocks,
-                        mp->m_sb.sb_rsumino)))
+        error = xfs_growfs_rt_alloc(mp, rsumblocks, nrsumblocks, mp->m_rsumip);
+        if (error)
                 return error;
         /*
          * Allocate a new (fake) mount/sb.
@@ -1972,10 +1969,8 @@ xfs_growfs_rt(
                 /*
                  * Lock out other callers by grabbing the bitmap inode lock.
                  */
-                if ((error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rbmino, 0,
-                                                XFS_ILOCK_EXCL, &ip)))
-                        goto error_cancel;
-                ASSERT(ip == mp->m_rbmip);
+                xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL);
+                xfs_trans_ijoin_ref(tp, mp->m_rbmip, XFS_ILOCK_EXCL);
                 /*
                  * Update the bitmap inode's size.
                  */
@@ -1986,10 +1981,8 @@ xfs_growfs_rt(
                 /*
                  * Get the summary inode into the transaction.
                  */
-                if ((error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rsumino, 0,
-                                                XFS_ILOCK_EXCL, &ip)))
-                        goto error_cancel;
-                ASSERT(ip == mp->m_rsumip);
+                xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL);
+                xfs_trans_ijoin_ref(tp, mp->m_rsumip, XFS_ILOCK_EXCL);
                 /*
                  * Update the summary inode's size.
                  */
@@ -2075,15 +2068,15 @@ xfs_rtallocate_extent(
         xfs_extlen_t    prod,           /* extent product factor */
         xfs_rtblock_t   *rtblock)       /* out: start block allocated */
 {
+        xfs_mount_t     *mp = tp->t_mountp;
         int             error;          /* error value */
-        xfs_inode_t     *ip;            /* inode for bitmap file */
-        xfs_mount_t     *mp;            /* file system mount structure */
         xfs_rtblock_t   r;              /* result allocated block */
         xfs_fsblock_t   sb;             /* summary file block number */
         xfs_buf_t       *sumbp;         /* summary file block buffer */
 
+        ASSERT(xfs_isilocked(mp->m_rbmip, XFS_ILOCK_EXCL));
         ASSERT(minlen > 0 && minlen <= maxlen);
-        mp = tp->t_mountp;
+
         /*
          * If prod is set then figure out what to do to minlen and maxlen.
          */
@@ -2099,12 +2092,7 @@ xfs_rtallocate_extent(
                         return 0;
                 }
         }
-        /*
-         * Lock out other callers by grabbing the bitmap inode lock.
-         */
-        if ((error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rbmino, 0,
-                                        XFS_ILOCK_EXCL, &ip)))
-                return error;
+
         sumbp = NULL;
         /*
          * Allocate by size, or near another block, or exactly at some block.
@@ -2123,11 +2111,12 @@ xfs_rtallocate_extent(
                                 len, &sumbp, &sb, prod, &r);
                 break;
         default:
+                error = EIO;
                 ASSERT(0);
         }
-        if (error) {
+        if (error)
                 return error;
-        }
+
         /*
          * If it worked, update the superblock.
          */
@@ -2155,7 +2144,6 @@ xfs_rtfree_extent(
         xfs_extlen_t    len)            /* length of extent freed */
 {
         int             error;          /* error value */
-        xfs_inode_t     *ip;            /* bitmap file inode */
         xfs_mount_t     *mp;            /* file system mount structure */
         xfs_fsblock_t   sb;             /* summary file block number */
         xfs_buf_t       *sumbp;         /* summary file block buffer */
@@ -2164,9 +2152,9 @@ xfs_rtfree_extent(
         /*
          * Synchronize by locking the bitmap inode.
          */
-        if ((error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rbmino, 0,
-                                        XFS_ILOCK_EXCL, &ip)))
-                return error;
+        xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL);
+        xfs_trans_ijoin_ref(tp, mp->m_rbmip, XFS_ILOCK_EXCL);
+
 #if defined(__KERNEL__) && defined(DEBUG)
         /*
          * Check to see that this whole range is currently allocated.
@@ -2199,10 +2187,10 @@ xfs_rtfree_extent(
          */
         if (tp->t_frextents_delta + mp->m_sb.sb_frextents ==
             mp->m_sb.sb_rextents) {
-                if (!(ip->i_d.di_flags & XFS_DIFLAG_NEWRTBM))
-                        ip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM;
-                *(__uint64_t *)&ip->i_d.di_atime = 0;
-                xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+                if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM))
+                        mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM;
+                *(__uint64_t *)&mp->m_rbmip->i_d.di_atime = 0;
+                xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE);
         }
         return 0;
 }
@@ -2222,8 +2210,8 @@ xfs_rtmount_init(
         if (sbp->sb_rblocks == 0)
                 return 0;
         if (mp->m_rtdev_targp == NULL) {
-                cmn_err(CE_WARN,
-        "XFS: This filesystem has a realtime volume, use rtdev=device option");
+                xfs_warn(mp,
+        "Filesystem has a realtime volume, use rtdev=device option");
                 return XFS_ERROR(ENODEV);
         }
         mp->m_rsumlevels = sbp->sb_rextslog + 1;
@@ -2237,7 +2225,7 @@ xfs_rtmount_init(
          */
         d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks);
         if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_rblocks) {
-                cmn_err(CE_WARN, "XFS: realtime mount -- %llu != %llu",
+                xfs_warn(mp, "realtime mount -- %llu != %llu",
                         (unsigned long long) XFS_BB_TO_FSB(mp, d),
                         (unsigned long long) mp->m_sb.sb_rblocks);
                 return XFS_ERROR(EFBIG);
@@ -2246,7 +2234,7 @@ xfs_rtmount_init(
                                         d - XFS_FSB_TO_BB(mp, 1),
                                         XFS_FSB_TO_B(mp, 1), 0);
         if (!bp) {
-                cmn_err(CE_WARN, "XFS: realtime device size check failed");
+                xfs_warn(mp, "realtime device size check failed");
                 return EIO;
         }
         xfs_buf_relse(bp);
@@ -2306,20 +2294,16 @@ xfs_rtpick_extent(
         xfs_rtblock_t   *pick)          /* result rt extent */
 {
         xfs_rtblock_t   b;              /* result block */
-        int             error;          /* error return value */
-        xfs_inode_t     *ip;            /* bitmap incore inode */
         int             log2;           /* log of sequence number */
         __uint64_t      resid;          /* residual after log removed */
         __uint64_t      seq;            /* sequence number of file creation */
         __uint64_t      *seqp;          /* pointer to seqno in inode */
 
-        if ((error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rbmino, 0,
-                                        XFS_ILOCK_EXCL, &ip)))
-                return error;
-        ASSERT(ip == mp->m_rbmip);
-        seqp = (__uint64_t *)&ip->i_d.di_atime;
-        if (!(ip->i_d.di_flags & XFS_DIFLAG_NEWRTBM)) {
-                ip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM;
+        ASSERT(xfs_isilocked(mp->m_rbmip, XFS_ILOCK_EXCL));
+
+        seqp = (__uint64_t *)&mp->m_rbmip->i_d.di_atime;
+        if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM)) {
+                mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM;
                 *seqp = 0;
         }
         seq = *seqp;
@@ -2335,7 +2319,7 @@ xfs_rtpick_extent(
                         b = mp->m_sb.sb_rextents - len;
         }
         *seqp = seq + 1;
-        xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+        xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE);
         *pick = b;
         return 0;
 }
diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h
index ff614c29b441..09e1f4f35e97 100644
--- a/fs/xfs/xfs_rtalloc.h
+++ b/fs/xfs/xfs_rtalloc.h
@@ -154,7 +154,7 @@ xfs_rtmount_init(
         if (mp->m_sb.sb_rblocks == 0)
                 return 0;
 
-        cmn_err(CE_WARN, "XFS: Not built with CONFIG_XFS_RT");
+        xfs_warn(mp, "Not built with CONFIG_XFS_RT");
         return ENOSYS;
 }
 # define xfs_rtmount_inodes(m)  (((mp)->m_sb.sb_rblocks == 0)? 0 : (ENOSYS))
diff --git a/fs/xfs/xfs_rw.c b/fs/xfs/xfs_rw.c
index 56861d5daaef..d6d6fdfe9422 100644
--- a/fs/xfs/xfs_rw.c
+++ b/fs/xfs/xfs_rw.c
@@ -49,9 +49,9 @@ xfs_do_force_shutdown(
         logerror = flags & SHUTDOWN_LOG_IO_ERROR;
 
         if (!(flags & SHUTDOWN_FORCE_UMOUNT)) {
-                cmn_err(CE_NOTE, "xfs_force_shutdown(%s,0x%x) called from "
-                                 "line %d of file %s.  Return address = 0x%p",
-                        mp->m_fsname, flags, lnnum, fname, __return_address);
+                xfs_notice(mp,
+        "%s(0x%x) called from line %d of file %s.  Return address = 0x%p",
+                        __func__, flags, lnnum, fname, __return_address);
         }
         /*
          * No need to duplicate efforts.
@@ -69,30 +69,25 @@ xfs_do_force_shutdown(
                 return;
 
         if (flags & SHUTDOWN_CORRUPT_INCORE) {
-                xfs_cmn_err(XFS_PTAG_SHUTDOWN_CORRUPT, CE_ALERT, mp,
-    "Corruption of in-memory data detected.  Shutting down filesystem: %s",
-                        mp->m_fsname);
-                if (XFS_ERRLEVEL_HIGH <= xfs_error_level) {
+                xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_CORRUPT,
+    "Corruption of in-memory data detected.  Shutting down filesystem");
+                if (XFS_ERRLEVEL_HIGH <= xfs_error_level)
                         xfs_stack_trace();
-                }
         } else if (!(flags & SHUTDOWN_FORCE_UMOUNT)) {
                 if (logerror) {
-                        xfs_cmn_err(XFS_PTAG_SHUTDOWN_LOGERROR, CE_ALERT, mp,
-                "Log I/O Error Detected.  Shutting down filesystem: %s",
-                                mp->m_fsname);
+                        xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_LOGERROR,
+                "Log I/O Error Detected.  Shutting down filesystem");
                 } else if (flags & SHUTDOWN_DEVICE_REQ) {
-                        xfs_cmn_err(XFS_PTAG_SHUTDOWN_IOERROR, CE_ALERT, mp,
-                "All device paths lost.  Shutting down filesystem: %s",
-                                mp->m_fsname);
+                        xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_IOERROR,
+                "All device paths lost.  Shutting down filesystem");
                 } else if (!(flags & SHUTDOWN_REMOTE_REQ)) {
-                        xfs_cmn_err(XFS_PTAG_SHUTDOWN_IOERROR, CE_ALERT, mp,
-                "I/O Error Detected.  Shutting down filesystem: %s",
-                                mp->m_fsname);
+                        xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_IOERROR,
+                "I/O Error Detected. Shutting down filesystem");
                 }
         }
         if (!(flags & SHUTDOWN_FORCE_UMOUNT)) {
-                cmn_err(CE_ALERT, "Please umount the filesystem, "
-                                  "and rectify the problem(s)");
+                xfs_alert(mp,
+        "Please umount the filesystem and rectify the problem(s)");
         }
 }
 
@@ -106,10 +101,9 @@ xfs_ioerror_alert(
         xfs_buf_t               *bp,
         xfs_daddr_t             blkno)
 {
-        cmn_err(CE_ALERT,
- "I/O error in filesystem (\"%s\") meta-data dev %s block 0x%llx"
- "       (\"%s\") error %d buf count %zd",
-                (!mp || !mp->m_fsname) ? "(fs name not set)" : mp->m_fsname,
+        xfs_alert(mp,
+                 "I/O error occurred: meta-data dev %s block 0x%llx"
+                 "       (\"%s\") error %d buf count %zd",
                 XFS_BUFTARG_NAME(XFS_BUF_TARGET(bp)),
                 (__uint64_t)blkno, func,
                 XFS_BUF_GETERROR(bp), XFS_BUF_COUNT(bp));
@@ -173,17 +167,9 @@ xfs_extlen_t
 xfs_get_extsz_hint(
         struct xfs_inode        *ip)
 {
-        xfs_extlen_t            extsz;
-
-        if (unlikely(XFS_IS_REALTIME_INODE(ip))) {
-                extsz = (ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE)
-                                ? ip->i_d.di_extsize
-                                : ip->i_mount->m_sb.sb_rextsize;
-                ASSERT(extsz);
-        } else {
-                extsz = (ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE)
-                                ? ip->i_d.di_extsize : 0;
-        }
-
-        return extsz;
+        if ((ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE) && ip->i_d.di_extsize)
+                return ip->i_d.di_extsize;
+        if (XFS_IS_REALTIME_INODE(ip))
+                return ip->i_mount->m_sb.sb_rextsize;
+        return 0;
 }
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index c2042b736b81..06a9759b6352 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -469,8 +469,6 @@ void		xfs_trans_inode_buf(xfs_trans_t *, struct xfs_buf *);
 void            xfs_trans_stale_inode_buf(xfs_trans_t *, struct xfs_buf *);
 void            xfs_trans_dquot_buf(xfs_trans_t *, struct xfs_buf *, uint);
 void            xfs_trans_inode_alloc_buf(xfs_trans_t *, struct xfs_buf *);
-int             xfs_trans_iget(struct xfs_mount *, xfs_trans_t *,
-                               xfs_ino_t , uint, uint, struct xfs_inode **);
 void            xfs_trans_ichgtime(struct xfs_trans *, struct xfs_inode *, int);
 void            xfs_trans_ijoin_ref(struct xfs_trans *, struct xfs_inode *, uint);
 void            xfs_trans_ijoin(struct xfs_trans *, struct xfs_inode *);
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index c5bbbc45db91..12aff9584e29 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -563,7 +563,7 @@ xfs_trans_ail_delete_bulk(
 
                         spin_unlock(&ailp->xa_lock);
                         if (!XFS_FORCED_SHUTDOWN(mp)) {
-                                xfs_cmn_err(XFS_PTAG_AILDELETE, CE_ALERT, mp,
+                                xfs_alert_tag(mp, XFS_PTAG_AILDELETE,
                 "%s: attempting to delete a log item that is not in the AIL",
                                                 __func__);
                                 xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index c47918c302a5..3bea66132334 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -305,7 +305,7 @@ xfs_trans_read_buf(
                         if (xfs_error_target == target) {
                                 if (((xfs_req_num++) % xfs_error_mod) == 0) {
                                         xfs_buf_relse(bp);
-                                        cmn_err(CE_DEBUG, "Returning error!\n");
+                                        xfs_debug(mp, "Returning error!");
                                         return XFS_ERROR(EIO);
                                 }
                         }
@@ -403,7 +403,7 @@ xfs_trans_read_buf(
                                 xfs_force_shutdown(tp->t_mountp,
                                                    SHUTDOWN_META_IO_ERROR);
                                 xfs_buf_relse(bp);
-                                cmn_err(CE_DEBUG, "Returning trans error!\n");
+                                xfs_debug(mp, "Returning trans error!");
                                 return XFS_ERROR(EIO);
                         }
                 }
@@ -427,7 +427,7 @@ shutdown_abort:
          */
 #if defined(DEBUG)
         if (XFS_BUF_ISSTALE(bp) && XFS_BUF_ISDELAYWRITE(bp))
-                cmn_err(CE_NOTE, "about to pop assert, bp == 0x%p", bp);
+                xfs_notice(mp, "about to pop assert, bp == 0x%p", bp);
 #endif
         ASSERT((XFS_BUF_BFLAGS(bp) & (XBF_STALE|XBF_DELWRI)) !=
                                      (XBF_STALE|XBF_DELWRI));
diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c
index ccb34532768b..16084d8ea231 100644
--- a/fs/xfs/xfs_trans_inode.c
+++ b/fs/xfs/xfs_trans_inode.c
@@ -44,28 +44,6 @@ xfs_trans_inode_broot_debug(
 #endif
 
 /*
- * Get an inode and join it to the transaction.
- */
-int
-xfs_trans_iget(
-        xfs_mount_t     *mp,
-        xfs_trans_t     *tp,
-        xfs_ino_t       ino,
-        uint            flags,
-        uint            lock_flags,
-        xfs_inode_t     **ipp)
-{
-        int                     error;
-
-        error = xfs_iget(mp, tp, ino, flags, lock_flags, ipp);
-        if (!error && tp) {
-                xfs_trans_ijoin(tp, *ipp);
-                (*ipp)->i_itemp->ili_lock_flags = lock_flags;
-        }
-        return error;
-}
-
-/*
  * Add a locked inode to the transaction.
  *
  * The inode must be locked, and it cannot be associated with any transaction.
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index d8e6f8cd6f0c..37d8146ee15b 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -1189,9 +1189,8 @@ xfs_inactive(
                  * inode might be lost for a long time or forever.
                  */
                 if (!XFS_FORCED_SHUTDOWN(mp)) {
-                        cmn_err(CE_NOTE,
-                "xfs_inactive:  xfs_ifree() returned an error = %d on %s",
-                                error, mp->m_fsname);
+                        xfs_notice(mp, "%s: xfs_ifree returned error %d",
+                                __func__, error);
                         xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
                 }
                 xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
@@ -1208,12 +1207,12 @@ xfs_inactive(
                  */
                 error = xfs_bmap_finish(&tp,  &free_list, &committed);
                 if (error)
-                        xfs_fs_cmn_err(CE_NOTE, mp, "xfs_inactive: "
-                                "xfs_bmap_finish() returned error %d", error);
+                        xfs_notice(mp, "%s: xfs_bmap_finish returned error %d",
+                                __func__, error);
                 error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
                 if (error)
-                        xfs_fs_cmn_err(CE_NOTE, mp, "xfs_inactive: "
-                                "xfs_trans_commit() returned error %d", error);
+                        xfs_notice(mp, "%s: xfs_trans_commit returned error %d",
+                                __func__, error);
         }
 
         /*
@@ -1310,7 +1309,7 @@ xfs_create(
         error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
                         XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp);
         if (error)
-                goto std_return;
+                return error;
 
         if (is_dir) {
                 rdev = 0;
@@ -1390,12 +1389,6 @@ xfs_create(
         }
 
         /*
-         * At this point, we've gotten a newly allocated inode.
-         * It is locked (and joined to the transaction).
-         */
-        ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-
-        /*
          * Now we join the directory inode to the transaction.  We do not do it
          * earlier because xfs_dir_ialloc might commit the previous transaction
          * (and release all the locks).  An error from here on will result in
@@ -1440,22 +1433,13 @@ xfs_create(
          */
         xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp);
 
-        /*
-         * xfs_trans_commit normally decrements the vnode ref count
-         * when it unlocks the inode. Since we want to return the
-         * vnode to the caller, we bump the vnode ref count now.
-         */
-        IHOLD(ip);
-
         error = xfs_bmap_finish(&tp, &free_list, &committed);
         if (error)
-                goto out_abort_rele;
+                goto out_bmap_cancel;
 
         error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
-        if (error) {
-                IRELE(ip);
-                goto out_dqrele;
-        }
+        if (error)
+                goto out_release_inode;
 
         xfs_qm_dqrele(udqp);
         xfs_qm_dqrele(gdqp);
@@ -1469,27 +1453,21 @@ xfs_create(
         cancel_flags |= XFS_TRANS_ABORT;
  out_trans_cancel:
         xfs_trans_cancel(tp, cancel_flags);
- out_dqrele:
+ out_release_inode:
+        /*
+         * Wait until after the current transaction is aborted to
+         * release the inode.  This prevents recursive transactions
+         * and deadlocks from xfs_inactive.
+         */
+        if (ip)
+                IRELE(ip);
+
         xfs_qm_dqrele(udqp);
         xfs_qm_dqrele(gdqp);
 
         if (unlock_dp_on_error)
                 xfs_iunlock(dp, XFS_ILOCK_EXCL);
- std_return:
         return error;
-
- out_abort_rele:
-        /*
-         * Wait until after the current transaction is aborted to
-         * release the inode.  This prevents recursive transactions
-         * and deadlocks from xfs_inactive.
-         */
-        xfs_bmap_cancel(&free_list);
-        cancel_flags |= XFS_TRANS_ABORT;
-        xfs_trans_cancel(tp, cancel_flags);
-        IRELE(ip);
-        unlock_dp_on_error = B_FALSE;
-        goto out_dqrele;
 }
 
 #ifdef DEBUG
@@ -2114,9 +2092,8 @@ xfs_symlink(
                                   XFS_BMAPI_WRITE | XFS_BMAPI_METADATA,
                                   &first_block, resblks, mval, &nmaps,
                                   &free_list);
-                if (error) {
-                        goto error1;
-                }
+                if (error)
+                        goto error2;
 
                 if (resblks)
                         resblks -= fs_blocks;
@@ -2148,7 +2125,7 @@ xfs_symlink(
         error = xfs_dir_createname(tp, dp, link_name, ip->i_ino,
                                         &first_block, &free_list, resblks);
         if (error)
-                goto error1;
+                goto error2;
         xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
         xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
 
@@ -2161,13 +2138,6 @@ xfs_symlink(
                 xfs_trans_set_sync(tp);
         }
 
-        /*
-         * xfs_trans_commit normally decrements the vnode ref count
-         * when it unlocks the inode. Since we want to return the
-         * vnode to the caller, we bump the vnode ref count now.
-         */
-        IHOLD(ip);
-
         error = xfs_bmap_finish(&tp, &free_list, &committed);
         if (error) {
                 goto error2;