Merge commit 'v2.6.27-rc3' into x86/prototypes

Conflicts:

	include/asm-x86/dma-mapping.h

Signed-off-by: Ingo Molnar <mingo@elte.hu>

360 files changed, 11432 insertions, 8086 deletions

diff --git a/fs/Kconfig b/fs/Kconfig
index 37db79a2ff95..d3873583360b 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -902,65 +902,7 @@ endif # BLOCK
 
 menu "Pseudo filesystems"
 
-config PROC_FS
-        bool "/proc file system support" if EMBEDDED
-        default y
-        help
-          This is a virtual file system providing information about the status
-          of the system. "Virtual" means that it doesn't take up any space on
-          your hard disk: the files are created on the fly by the kernel when
-          you try to access them. Also, you cannot read the files with older
-          version of the program less: you need to use more or cat.
-
-          It's totally cool; for example, "cat /proc/interrupts" gives
-          information about what the different IRQs are used for at the moment
-          (there is a small number of Interrupt ReQuest lines in your computer
-          that are used by the attached devices to gain the CPU's attention --
-          often a source of trouble if two devices are mistakenly configured
-          to use the same IRQ). The program procinfo to display some
-          information about your system gathered from the /proc file system.
-
-          Before you can use the /proc file system, it has to be mounted,
-          meaning it has to be given a location in the directory hierarchy.
-          That location should be /proc. A command such as "mount -t proc proc
-          /proc" or the equivalent line in /etc/fstab does the job.
-
-          The /proc file system is explained in the file
-          <file:Documentation/filesystems/proc.txt> and on the proc(5) manpage
-          ("man 5 proc").
-
-          This option will enlarge your kernel by about 67 KB. Several
-          programs depend on this, so everyone should say Y here.
-
-config PROC_KCORE
-        bool "/proc/kcore support" if !ARM
-        depends on PROC_FS && MMU
-
-config PROC_VMCORE
-        bool "/proc/vmcore support (EXPERIMENTAL)"
-        depends on PROC_FS && CRASH_DUMP
-        default y
-        help
-        Exports the dump image of crashed kernel in ELF format.
-
-config PROC_SYSCTL
-        bool "Sysctl support (/proc/sys)" if EMBEDDED
-        depends on PROC_FS
-        select SYSCTL
-        default y
-        ---help---
-          The sysctl interface provides a means of dynamically changing
-          certain kernel parameters and variables on the fly without requiring
-          a recompile of the kernel or reboot of the system.  The primary
-          interface is through /proc/sys.  If you say Y here a tree of
-          modifiable sysctl entries will be generated beneath the
-          /proc/sys directory. They are explained in the files
-          in <file:Documentation/sysctl/>.  Note that enabling this
-          option will enlarge the kernel by at least 8 KB.
-
-          As it is generally a good thing, you should say Y here unless
-          building a kernel for install/rescue disks or your system is very
-          limited in memory.
+source "fs/proc/Kconfig"
 
 config SYSFS
         bool "sysfs file system support" if EMBEDDED
@@ -1441,6 +1383,19 @@ config MINIX_FS
           partition (the one containing the directory /) cannot be compiled as
           a module.
 
+config OMFS_FS
+        tristate "SonicBlue Optimized MPEG File System support"
+        depends on BLOCK
+        select CRC_ITU_T
+        help
+          This is the proprietary file system used by the Rio Karma music
+          player and ReplayTV DVR.  Despite the name, this filesystem is not
+          more efficient than a standard FS for MPEG files, in fact likely
+          the opposite is true.  Say Y if you have either of these devices
+          and wish to mount its disk.
+
+          To compile this file system support as a module, choose M here: the
+          module will be called omfs.  If unsure, say N.
 
 config HPFS_FS
         tristate "OS/2 HPFS file system support"
@@ -2093,20 +2048,6 @@ config CODA_FS
           To compile the coda client support as a module, choose M here: the
           module will be called coda.
 
-config CODA_FS_OLD_API
-        bool "Use 96-bit Coda file identifiers"
-        depends on CODA_FS
-        help
-          A new kernel-userspace API had to be introduced for Coda v6.0
-          to support larger 128-bit file identifiers as needed by the
-          new realms implementation.
-
-          However this new API is not backward compatible with older
-          clients. If you really need to run the old Coda userspace
-          cache manager then say Y.
-
-          For most cases you probably want to say N.
-
 config AFS_FS
         tristate "Andrew File System support (AFS) (EXPERIMENTAL)"
         depends on INET && EXPERIMENTAL
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt
index 3263084eef9e..4a551af6f3fc 100644
--- a/fs/Kconfig.binfmt
+++ b/fs/Kconfig.binfmt
@@ -30,7 +30,7 @@ config COMPAT_BINFMT_ELF
 config BINFMT_ELF_FDPIC
         bool "Kernel support for FDPIC ELF binaries"
         default y
-        depends on (FRV || BLACKFIN)
+        depends on (FRV || BLACKFIN || (SUPERH32 && !MMU))
         help
           ELF FDPIC binaries are based on ELF, but allow the individual load
           segments of a binary to be located in memory independently of each
diff --git a/fs/Makefile b/fs/Makefile
index 3b2178b4bb66..a1482a5eff15 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -111,6 +111,7 @@ obj-$(CONFIG_ADFS_FS)		+= adfs/
 obj-$(CONFIG_FUSE_FS)           += fuse/
 obj-$(CONFIG_UDF_FS)            += udf/
 obj-$(CONFIG_SUN_OPENPROMFS)    += openpromfs/
+obj-$(CONFIG_OMFS_FS)           += omfs/
 obj-$(CONFIG_JFS_FS)            += jfs/
 obj-$(CONFIG_XFS_FS)            += xfs/
 obj-$(CONFIG_9P_FS)             += 9p/
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index 9e421eeb672b..26f3b43726bb 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -249,7 +249,7 @@ static void adfs_destroy_inode(struct inode *inode)
         kmem_cache_free(adfs_inode_cachep, ADFS_I(inode));
 }
 
-static void init_once(struct kmem_cache *cachep, void *foo)
+static void init_once(void *foo)
 {
         struct adfs_inode_info *ei = (struct adfs_inode_info *) foo;
 
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index 223b1917093e..e9ec915f7553 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -2,6 +2,7 @@
 #include <linux/fs.h>
 #include <linux/buffer_head.h>
 #include <linux/amigaffs.h>
+#include <linux/mutex.h>
 
 /* AmigaOS allows file names with up to 30 characters length.
  * Names longer than that will be silently truncated. If you
@@ -98,7 +99,7 @@ struct affs_sb_info {
         gid_t s_gid;                    /* gid to override */
         umode_t s_mode;                 /* mode to override */
         struct buffer_head *s_root_bh;  /* Cached root block. */
-        struct semaphore s_bmlock;      /* Protects bitmap access. */
+        struct mutex s_bmlock;          /* Protects bitmap access. */
         struct affs_bm_info *s_bitmap;  /* Bitmap infos. */
         u32 s_bmap_count;               /* # of bitmap blocks. */
         u32 s_bmap_bits;                /* # of bits in one bitmap blocks */
diff --git a/fs/affs/bitmap.c b/fs/affs/bitmap.c
index c4a5ad09ddf2..dc5ef14bdc1c 100644
--- a/fs/affs/bitmap.c
+++ b/fs/affs/bitmap.c
@@ -45,14 +45,14 @@ affs_count_free_blocks(struct super_block *sb)
         if (sb->s_flags & MS_RDONLY)
                 return 0;
 
-        down(&AFFS_SB(sb)->s_bmlock);
+        mutex_lock(&AFFS_SB(sb)->s_bmlock);
 
         bm = AFFS_SB(sb)->s_bitmap;
         free = 0;
         for (i = AFFS_SB(sb)->s_bmap_count; i > 0; bm++, i--)
                 free += bm->bm_free;
 
-        up(&AFFS_SB(sb)->s_bmlock);
+        mutex_unlock(&AFFS_SB(sb)->s_bmlock);
 
         return free;
 }
@@ -76,7 +76,7 @@ affs_free_block(struct super_block *sb, u32 block)
         bit     = blk % sbi->s_bmap_bits;
         bm      = &sbi->s_bitmap[bmap];
 
-        down(&sbi->s_bmlock);
+        mutex_lock(&sbi->s_bmlock);
 
         bh = sbi->s_bmap_bh;
         if (sbi->s_last_bmap != bmap) {
@@ -105,19 +105,19 @@ affs_free_block(struct super_block *sb, u32 block)
         sb->s_dirt = 1;
         bm->bm_free++;
 
-        up(&sbi->s_bmlock);
+        mutex_unlock(&sbi->s_bmlock);
         return;
 
 err_free:
         affs_warning(sb,"affs_free_block","Trying to free block %u which is already free", block);
-        up(&sbi->s_bmlock);
+        mutex_unlock(&sbi->s_bmlock);
         return;
 
 err_bh_read:
         affs_error(sb,"affs_free_block","Cannot read bitmap block %u", bm->bm_key);
         sbi->s_bmap_bh = NULL;
         sbi->s_last_bmap = ~0;
-        up(&sbi->s_bmlock);
+        mutex_unlock(&sbi->s_bmlock);
         return;
 
 err_range:
@@ -168,7 +168,7 @@ affs_alloc_block(struct inode *inode, u32 goal)
         bmap = blk / sbi->s_bmap_bits;
         bm = &sbi->s_bitmap[bmap];
 
-        down(&sbi->s_bmlock);
+        mutex_lock(&sbi->s_bmlock);
 
         if (bm->bm_free)
                 goto find_bmap_bit;
@@ -249,7 +249,7 @@ find_bit:
         mark_buffer_dirty(bh);
         sb->s_dirt = 1;
 
-        up(&sbi->s_bmlock);
+        mutex_unlock(&sbi->s_bmlock);
 
         pr_debug("%d\n", blk);
         return blk;
@@ -259,7 +259,7 @@ err_bh_read:
         sbi->s_bmap_bh = NULL;
         sbi->s_last_bmap = ~0;
 err_full:
-        up(&sbi->s_bmlock);
+        mutex_unlock(&sbi->s_bmlock);
         pr_debug("failed\n");
         return 0;
 }
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 6eac7bdeec94..1377b1240b6e 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -46,8 +46,6 @@ const struct inode_operations affs_file_inode_operations = {
 static int
 affs_file_open(struct inode *inode, struct file *filp)
 {
-        if (atomic_read(&filp->f_count) != 1)
-                return 0;
         pr_debug("AFFS: open(%lu,%d)\n",
                  inode->i_ino, atomic_read(&AFFS_I(inode)->i_opencnt));
         atomic_inc(&AFFS_I(inode)->i_opencnt);
@@ -57,8 +55,6 @@ affs_file_open(struct inode *inode, struct file *filp)
 static int
 affs_file_release(struct inode *inode, struct file *filp)
 {
-        if (atomic_read(&filp->f_count) != 0)
-                return 0;
         pr_debug("AFFS: release(%lu, %d)\n",
                  inode->i_ino, atomic_read(&AFFS_I(inode)->i_opencnt));
 
diff --git a/fs/affs/super.c b/fs/affs/super.c
index d214837d5e42..3a89094f93d0 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -90,7 +90,7 @@ static void affs_destroy_inode(struct inode *inode)
         kmem_cache_free(affs_inode_cachep, AFFS_I(inode));
 }
 
-static void init_once(struct kmem_cache *cachep, void *foo)
+static void init_once(void *foo)
 {
         struct affs_inode_info *ei = (struct affs_inode_info *) foo;
 
@@ -290,7 +290,7 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent)
         if (!sbi)
                 return -ENOMEM;
         sb->s_fs_info = sbi;
-        init_MUTEX(&sbi->s_bmlock);
+        mutex_init(&sbi->s_bmlock);
 
         if (!parse_options(data,&uid,&gid,&i,&reserved,&root_block,
                                 &blocksize,&sbi->s_prefix,
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 7102824ba847..3cb6920ff30b 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -469,8 +469,6 @@ extern bool afs_cm_incoming_call(struct afs_call *);
 extern const struct inode_operations afs_dir_inode_operations;
 extern const struct file_operations afs_dir_file_operations;
 
-extern int afs_permission(struct inode *, int, struct nameidata *);
-
 /*
  * file.c
  */
@@ -605,7 +603,7 @@ extern void afs_clear_permits(struct afs_vnode *);
 extern void afs_cache_permit(struct afs_vnode *, struct key *, long);
 extern void afs_zap_permits(struct rcu_head *);
 extern struct key *afs_request_key(struct afs_cell *);
-extern int afs_permission(struct inode *, int, struct nameidata *);
+extern int afs_permission(struct inode *, int);
 
 /*
  * server.c
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index 2f5503902c37..78db4953a800 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -232,7 +232,7 @@ static void *afs_mntpt_follow_link(struct dentry *dentry, struct nameidata *nd)
         }
 
         mntget(newmnt);
-        err = do_add_mount(newmnt, nd, MNT_SHRINKABLE, &afs_vfsmounts);
+        err = do_add_mount(newmnt, &nd->path, MNT_SHRINKABLE, &afs_vfsmounts);
         switch (err) {
         case 0:
                 path_put(&nd->path);
diff --git a/fs/afs/security.c b/fs/afs/security.c
index 3bcbeceba1bb..3ef504370034 100644
--- a/fs/afs/security.c
+++ b/fs/afs/security.c
@@ -284,7 +284,7 @@ static int afs_check_permit(struct afs_vnode *vnode, struct key *key,
  * - AFS ACLs are attached to directories only, and a file is controlled by its
  *   parent directory's ACL
  */
-int afs_permission(struct inode *inode, int mask, struct nameidata *nd)
+int afs_permission(struct inode *inode, int mask)
 {
         struct afs_vnode *vnode = AFS_FS_I(inode);
         afs_access_t uninitialized_var(access);
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 7e3faeef6818..250d8c4d66e4 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -27,7 +27,7 @@
 
 #define AFS_FS_MAGIC 0x6B414653 /* 'kAFS' */
 
-static void afs_i_init_once(struct kmem_cache *cachep, void *foo);
+static void afs_i_init_once(void *foo);
 static int afs_get_sb(struct file_system_type *fs_type,
                       int flags, const char *dev_name,
                       void *data, struct vfsmount *mnt);
@@ -449,7 +449,7 @@ static void afs_put_super(struct super_block *sb)
 /*
  * initialise an inode cache slab element prior to any use
  */
-static void afs_i_init_once(struct kmem_cache *cachep, void *_vnode)
+static void afs_i_init_once(void *_vnode)
 {
         struct afs_vnode *vnode = _vnode;
 
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 9a849ad3c489..065b4e10681a 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -404,7 +404,7 @@ static int afs_write_back_from_locked_page(struct afs_writeback *wb,
                         page = pages[loop];
                         if (page->index > wb->last)
                                 break;
-                        if (TestSetPageLocked(page))
+                        if (!trylock_page(page))
                                 break;
                         if (!PageDirty(page) ||
                             page_private(page) != (unsigned long) wb) {
diff --git a/fs/aio.c b/fs/aio.c
index 0fb3117ddd93..f658441d5666 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -512,8 +512,8 @@ static void aio_fput_routine(struct work_struct *data)
  */
 static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
 {
-        dprintk(KERN_DEBUG "aio_put(%p): f_count=%d\n",
-                req, atomic_read(&req->ki_filp->f_count));
+        dprintk(KERN_DEBUG "aio_put(%p): f_count=%ld\n",
+                req, atomic_long_read(&req->ki_filp->f_count));
 
         assert_spin_locked(&ctx->ctx_lock);
 
@@ -528,7 +528,7 @@ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
         /* Must be done under the lock to serialise against cancellation.
          * Call this aio_fput as it duplicates fput via the fput_work.
          */
-        if (unlikely(atomic_dec_and_test(&req->ki_filp->f_count))) {
+        if (unlikely(atomic_long_dec_and_test(&req->ki_filp->f_count))) {
                 get_ioctx(ctx);
                 spin_lock(&fput_lock);
                 list_add(&req->ki_list, &fput_head);
@@ -586,7 +586,6 @@ static void use_mm(struct mm_struct *mm)
         struct task_struct *tsk = current;
 
         task_lock(tsk);
-        tsk->flags |= PF_BORROWED_MM;
         active_mm = tsk->active_mm;
         atomic_inc(&mm->mm_count);
         tsk->mm = mm;
@@ -610,7 +609,6 @@ static void unuse_mm(struct mm_struct *mm)
         struct task_struct *tsk = current;
 
         task_lock(tsk);
-        tsk->flags &= ~PF_BORROWED_MM;
         tsk->mm = NULL;
         /* active_mm is still 'mm' */
         enter_lazy_tlb(mm, tsk);
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 977ef208c051..3662dd44896b 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -58,8 +58,9 @@ static struct dentry_operations anon_inodefs_dentry_operations = {
  *                    of the file
  *
  * @name:    [in]    name of the "class" of the new file
- * @fops     [in]    file operations for the new file
- * @priv     [in]    private data for the new file (will be file's private_data)
+ * @fops:    [in]    file operations for the new file
+ * @priv:    [in]    private data for the new file (will be file's private_data)
+ * @flags:   [in]    flags
  *
  * Creates a new file by hooking it on a single inode. This is useful for files
  * that do not need to have a full-fledged inode in order to operate correctly.
@@ -68,7 +69,7 @@ static struct dentry_operations anon_inodefs_dentry_operations = {
  * setup.  Returns new descriptor or -error.
  */
 int anon_inode_getfd(const char *name, const struct file_operations *fops,
-                     void *priv)
+                     void *priv, int flags)
 {
         struct qstr this;
         struct dentry *dentry;
@@ -78,7 +79,7 @@ int anon_inode_getfd(const char *name, const struct file_operations *fops,
         if (IS_ERR(anon_inode_inode))
                 return -ENODEV;
 
-        error = get_unused_fd();
+        error = get_unused_fd_flags(flags);
         if (error < 0)
                 return error;
         fd = error;
@@ -115,7 +116,7 @@ int anon_inode_getfd(const char *name, const struct file_operations *fops,
         file->f_mapping = anon_inode_inode->i_mapping;
 
         file->f_pos = 0;
-        file->f_flags = O_RDWR;
+        file->f_flags = O_RDWR | (flags & O_NONBLOCK);
         file->f_version = 0;
         file->private_data = priv;
 
diff --git a/fs/attr.c b/fs/attr.c
index 966b73e25f82..26c71ba1eed4 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -51,7 +51,7 @@ int inode_change_ok(struct inode *inode, struct iattr *attr)
         }
 
         /* Check for setting the inode time. */
-        if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET)) {
+        if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)) {
                 if (!is_owner_or_cap(inode))
                         goto error;
         }
@@ -108,6 +108,11 @@ int notify_change(struct dentry * dentry, struct iattr * attr)
         struct timespec now;
         unsigned int ia_valid = attr->ia_valid;
 
+        if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) {
+                if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
+                        return -EPERM;
+        }
+
         now = current_fs_time(inode->i_sb);
 
         attr->ia_ctime = now;
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index c3d352d7fa93..69a2f5c92319 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -52,7 +52,10 @@ struct autofs_info {
 
         int             flags;
 
-        struct list_head rehash;
+        struct completion expire_complete;
+
+        struct list_head active;
+        struct list_head expiring;
 
         struct autofs_sb_info *sbi;
         unsigned long last_used;
@@ -68,15 +71,14 @@ struct autofs_info {
 };
 
 #define AUTOFS_INF_EXPIRING     (1<<0) /* dentry is in the process of expiring */
+#define AUTOFS_INF_MOUNTPOINT   (1<<1) /* mountpoint status for direct expire */
 
 struct autofs_wait_queue {
         wait_queue_head_t queue;
         struct autofs_wait_queue *next;
         autofs_wqt_t wait_queue_token;
         /* We use the following to see what we are waiting for */
-        unsigned int hash;
-        unsigned int len;
-        char *name;
+        struct qstr name;
         u32 dev;
         u64 ino;
         uid_t uid;
@@ -85,7 +87,7 @@ struct autofs_wait_queue {
         pid_t tgid;
         /* This is for status reporting upon return */
         int status;
-        atomic_t wait_ctr;
+        unsigned int wait_ctr;
 };
 
 #define AUTOFS_SBI_MAGIC 0x6d4a556d
@@ -112,8 +114,9 @@ struct autofs_sb_info {
         struct mutex wq_mutex;
         spinlock_t fs_lock;
         struct autofs_wait_queue *queues; /* Wait queue pointer */
-        spinlock_t rehash_lock;
-        struct list_head rehash_list;
+        spinlock_t lookup_lock;
+        struct list_head active_list;
+        struct list_head expiring_list;
 };
 
 static inline struct autofs_sb_info *autofs4_sbi(struct super_block *sb)
@@ -138,18 +141,14 @@ static inline int autofs4_oz_mode(struct autofs_sb_info *sbi) {
 static inline int autofs4_ispending(struct dentry *dentry)
 {
         struct autofs_info *inf = autofs4_dentry_ino(dentry);
-        int pending = 0;
 
         if (dentry->d_flags & DCACHE_AUTOFS_PENDING)
                 return 1;
 
-        if (inf) {
-                spin_lock(&inf->sbi->fs_lock);
-                pending = inf->flags & AUTOFS_INF_EXPIRING;
-                spin_unlock(&inf->sbi->fs_lock);
-        }
+        if (inf->flags & AUTOFS_INF_EXPIRING)
+                return 1;
 
-        return pending;
+        return 0;
 }
 
 static inline void autofs4_copy_atime(struct file *src, struct file *dst)
@@ -164,6 +163,7 @@ void autofs4_free_ino(struct autofs_info *);
 
 /* Expiration */
 int is_autofs4_dentry(struct dentry *);
+int autofs4_expire_wait(struct dentry *dentry);
 int autofs4_expire_run(struct super_block *, struct vfsmount *,
                         struct autofs_sb_info *,
                         struct autofs_packet_expire __user *);
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 894fee54d4d8..cdabb796ff01 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -259,13 +259,15 @@ static struct dentry *autofs4_expire_direct(struct super_block *sb,
         now = jiffies;
         timeout = sbi->exp_timeout;
 
-        /* Lock the tree as we must expire as a whole */
         spin_lock(&sbi->fs_lock);
         if (!autofs4_direct_busy(mnt, root, timeout, do_now)) {
                 struct autofs_info *ino = autofs4_dentry_ino(root);
-
-                /* Set this flag early to catch sys_chdir and the like */
+                if (d_mountpoint(root)) {
+                        ino->flags |= AUTOFS_INF_MOUNTPOINT;
+                        root->d_mounted--;
+                }
                 ino->flags |= AUTOFS_INF_EXPIRING;
+                init_completion(&ino->expire_complete);
                 spin_unlock(&sbi->fs_lock);
                 return root;
         }
@@ -292,6 +294,8 @@ static struct dentry *autofs4_expire_indirect(struct super_block *sb,
         struct list_head *next;
         int do_now = how & AUTOFS_EXP_IMMEDIATE;
         int exp_leaves = how & AUTOFS_EXP_LEAVES;
+        struct autofs_info *ino;
+        unsigned int ino_count;
 
         if (!root)
                 return NULL;
@@ -316,6 +320,9 @@ static struct dentry *autofs4_expire_indirect(struct super_block *sb,
                 dentry = dget(dentry);
                 spin_unlock(&dcache_lock);
 
+                spin_lock(&sbi->fs_lock);
+                ino = autofs4_dentry_ino(dentry);
+
                 /*
                  * Case 1: (i) indirect mount or top level pseudo direct mount
                  *         (autofs-4.1).
@@ -326,6 +333,11 @@ static struct dentry *autofs4_expire_indirect(struct super_block *sb,
                         DPRINTK("checking mountpoint %p %.*s",
                                 dentry, (int)dentry->d_name.len, dentry->d_name.name);
 
+                        /* Path walk currently on this dentry? */
+                        ino_count = atomic_read(&ino->count) + 2;
+                        if (atomic_read(&dentry->d_count) > ino_count)
+                                goto next;
+
                         /* Can we umount this guy */
                         if (autofs4_mount_busy(mnt, dentry))
                                 goto next;
@@ -343,23 +355,25 @@ static struct dentry *autofs4_expire_indirect(struct super_block *sb,
 
                 /* Case 2: tree mount, expire iff entire tree is not busy */
                 if (!exp_leaves) {
-                        /* Lock the tree as we must expire as a whole */
-                        spin_lock(&sbi->fs_lock);
-                        if (!autofs4_tree_busy(mnt, dentry, timeout, do_now)) {
-                                struct autofs_info *inf = autofs4_dentry_ino(dentry);
+                        /* Path walk currently on this dentry? */
+                        ino_count = atomic_read(&ino->count) + 1;
+                        if (atomic_read(&dentry->d_count) > ino_count)
+                                goto next;
 
-                                /* Set this flag early to catch sys_chdir and the like */
-                                inf->flags |= AUTOFS_INF_EXPIRING;
-                                spin_unlock(&sbi->fs_lock);
+                        if (!autofs4_tree_busy(mnt, dentry, timeout, do_now)) {
                                 expired = dentry;
                                 goto found;
                         }
-                        spin_unlock(&sbi->fs_lock);
                 /*
                  * Case 3: pseudo direct mount, expire individual leaves
                  *         (autofs-4.1).
                  */
                 } else {
+                        /* Path walk currently on this dentry? */
+                        ino_count = atomic_read(&ino->count) + 1;
+                        if (atomic_read(&dentry->d_count) > ino_count)
+                                goto next;
+
                         expired = autofs4_check_leaves(mnt, dentry, timeout, do_now);
                         if (expired) {
                                 dput(dentry);
@@ -367,6 +381,7 @@ static struct dentry *autofs4_expire_indirect(struct super_block *sb,
                         }
                 }
 next:
+                spin_unlock(&sbi->fs_lock);
                 dput(dentry);
                 spin_lock(&dcache_lock);
                 next = next->next;
@@ -377,12 +392,45 @@ next:
 found:
         DPRINTK("returning %p %.*s",
                 expired, (int)expired->d_name.len, expired->d_name.name);
+        ino = autofs4_dentry_ino(expired);
+        ino->flags |= AUTOFS_INF_EXPIRING;
+        init_completion(&ino->expire_complete);
+        spin_unlock(&sbi->fs_lock);
         spin_lock(&dcache_lock);
         list_move(&expired->d_parent->d_subdirs, &expired->d_u.d_child);
         spin_unlock(&dcache_lock);
         return expired;
 }
 
+int autofs4_expire_wait(struct dentry *dentry)
+{
+        struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
+        struct autofs_info *ino = autofs4_dentry_ino(dentry);
+        int status;
+
+        /* Block on any pending expire */
+        spin_lock(&sbi->fs_lock);
+        if (ino->flags & AUTOFS_INF_EXPIRING) {
+                spin_unlock(&sbi->fs_lock);
+
+                DPRINTK("waiting for expire %p name=%.*s",
+                         dentry, dentry->d_name.len, dentry->d_name.name);
+
+                status = autofs4_wait(sbi, dentry, NFY_NONE);
+                wait_for_completion(&ino->expire_complete);
+
+                DPRINTK("expire done status=%d", status);
+
+                if (d_unhashed(dentry))
+                        return -EAGAIN;
+
+                return status;
+        }
+        spin_unlock(&sbi->fs_lock);
+
+        return 0;
+}
+
 /* Perform an expiry operation */
 int autofs4_expire_run(struct super_block *sb,
                       struct vfsmount *mnt,
@@ -390,7 +438,9 @@ int autofs4_expire_run(struct super_block *sb,
                       struct autofs_packet_expire __user *pkt_p)
 {
         struct autofs_packet_expire pkt;
+        struct autofs_info *ino;
         struct dentry *dentry;
+        int ret = 0;
 
         memset(&pkt,0,sizeof pkt);
 
@@ -406,9 +456,15 @@ int autofs4_expire_run(struct super_block *sb,
         dput(dentry);
 
         if ( copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire)) )
-                return -EFAULT;
+                ret = -EFAULT;
 
-        return 0;
+        spin_lock(&sbi->fs_lock);
+        ino = autofs4_dentry_ino(dentry);
+        ino->flags &= ~AUTOFS_INF_EXPIRING;
+        complete_all(&ino->expire_complete);
+        spin_unlock(&sbi->fs_lock);
+
+        return ret;
 }
 
 /* Call repeatedly until it returns -EAGAIN, meaning there's nothing
@@ -433,9 +489,16 @@ int autofs4_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 
                 /* This is synchronous because it makes the daemon a
                    little easier */
-                ino->flags |= AUTOFS_INF_EXPIRING;
                 ret = autofs4_wait(sbi, dentry, NFY_EXPIRE);
+
+                spin_lock(&sbi->fs_lock);
+                if (ino->flags & AUTOFS_INF_MOUNTPOINT) {
+                        sb->s_root->d_mounted++;
+                        ino->flags &= ~AUTOFS_INF_MOUNTPOINT;
+                }
                 ino->flags &= ~AUTOFS_INF_EXPIRING;
+                complete_all(&ino->expire_complete);
+                spin_unlock(&sbi->fs_lock);
                 dput(dentry);
         }
 
diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c
index 2fdcf5e1d236..7bb3e5ba0537 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -24,8 +24,10 @@
 
 static void ino_lnkfree(struct autofs_info *ino)
 {
-        kfree(ino->u.symlink);
-        ino->u.symlink = NULL;
+        if (ino->u.symlink) {
+                kfree(ino->u.symlink);
+                ino->u.symlink = NULL;
+        }
 }
 
 struct autofs_info *autofs4_init_ino(struct autofs_info *ino,
@@ -41,16 +43,18 @@ struct autofs_info *autofs4_init_ino(struct autofs_info *ino,
         if (ino == NULL)
                 return NULL;
 
-        ino->flags = 0;
-        ino->mode = mode;
-        ino->inode = NULL;
-        ino->dentry = NULL;
-        ino->size = 0;
-
-        INIT_LIST_HEAD(&ino->rehash);
+        if (!reinit) {
+                ino->flags = 0;
+                ino->inode = NULL;
+                ino->dentry = NULL;
+                ino->size = 0;
+                INIT_LIST_HEAD(&ino->active);
+                INIT_LIST_HEAD(&ino->expiring);
+                atomic_set(&ino->count, 0);
+        }
 
+        ino->mode = mode;
         ino->last_used = jiffies;
-        atomic_set(&ino->count, 0);
 
         ino->sbi = sbi;
 
@@ -159,8 +163,8 @@ void autofs4_kill_sb(struct super_block *sb)
         if (!sbi)
                 goto out_kill_sb;
 
-        if (!sbi->catatonic)
-                autofs4_catatonic_mode(sbi); /* Free wait queues, close pipe */
+        /* Free wait queues, close pipe */
+        autofs4_catatonic_mode(sbi);
 
         /* Clean up and release dangling references */
         autofs4_force_release(sbi);
@@ -338,8 +342,9 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
         mutex_init(&sbi->wq_mutex);
         spin_lock_init(&sbi->fs_lock);
         sbi->queues = NULL;
-        spin_lock_init(&sbi->rehash_lock);
-        INIT_LIST_HEAD(&sbi->rehash_list);
+        spin_lock_init(&sbi->lookup_lock);
+        INIT_LIST_HEAD(&sbi->active_list);
+        INIT_LIST_HEAD(&sbi->expiring_list);
         s->s_blocksize = 1024;
         s->s_blocksize_bits = 10;
         s->s_magic = AUTOFS_SUPER_MAGIC;
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index edf5b6bddb52..bcfb2dc0a61b 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -25,25 +25,25 @@ static int autofs4_dir_rmdir(struct inode *,struct dentry *);
 static int autofs4_dir_mkdir(struct inode *,struct dentry *,int);
 static int autofs4_root_ioctl(struct inode *, struct file *,unsigned int,unsigned long);
 static int autofs4_dir_open(struct inode *inode, struct file *file);
-static int autofs4_dir_close(struct inode *inode, struct file *file);
-static int autofs4_dir_readdir(struct file * filp, void * dirent, filldir_t filldir);
-static int autofs4_root_readdir(struct file * filp, void * dirent, filldir_t filldir);
 static struct dentry *autofs4_lookup(struct inode *,struct dentry *, struct nameidata *);
 static void *autofs4_follow_link(struct dentry *, struct nameidata *);
 
+#define TRIGGER_FLAGS   (LOOKUP_CONTINUE | LOOKUP_DIRECTORY)
+#define TRIGGER_INTENTS (LOOKUP_OPEN | LOOKUP_CREATE)
+
 const struct file_operations autofs4_root_operations = {
         .open           = dcache_dir_open,
         .release        = dcache_dir_close,
         .read           = generic_read_dir,
-        .readdir        = autofs4_root_readdir,
+        .readdir        = dcache_readdir,
         .ioctl          = autofs4_root_ioctl,
 };
 
 const struct file_operations autofs4_dir_operations = {
         .open           = autofs4_dir_open,
-        .release        = autofs4_dir_close,
+        .release        = dcache_dir_close,
         .read           = generic_read_dir,
-        .readdir        = autofs4_dir_readdir,
+        .readdir        = dcache_readdir,
 };
 
 const struct inode_operations autofs4_indirect_root_inode_operations = {
@@ -70,42 +70,10 @@ const struct inode_operations autofs4_dir_inode_operations = {
         .rmdir          = autofs4_dir_rmdir,
 };
 
-static int autofs4_root_readdir(struct file *file, void *dirent,
-                                filldir_t filldir)
-{
-        struct autofs_sb_info *sbi = autofs4_sbi(file->f_path.dentry->d_sb);
-        int oz_mode = autofs4_oz_mode(sbi);
-
-        DPRINTK("called, filp->f_pos = %lld", file->f_pos);
-
-        /*
-         * Don't set reghost flag if:
-         * 1) f_pos is larger than zero -- we've already been here.
-         * 2) we haven't even enabled reghosting in the 1st place.
-         * 3) this is the daemon doing a readdir
-         */
-        if (oz_mode && file->f_pos == 0 && sbi->reghost_enabled)
-                sbi->needs_reghost = 1;
-
-        DPRINTK("needs_reghost = %d", sbi->needs_reghost);
-
-        return dcache_readdir(file, dirent, filldir);
-}
-
 static int autofs4_dir_open(struct inode *inode, struct file *file)
 {
         struct dentry *dentry = file->f_path.dentry;
-        struct vfsmount *mnt = file->f_path.mnt;
         struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
-        struct dentry *cursor;
-        int status;
-
-        status = dcache_dir_open(inode, file);
-        if (status)
-                goto out;
-
-        cursor = file->private_data;
-        cursor->d_fsdata = NULL;
 
         DPRINTK("file=%p dentry=%p %.*s",
                 file, dentry, dentry->d_name.len, dentry->d_name.name);
@@ -113,159 +81,32 @@ static int autofs4_dir_open(struct inode *inode, struct file *file)
         if (autofs4_oz_mode(sbi))
                 goto out;
 
-        if (autofs4_ispending(dentry)) {
-                DPRINTK("dentry busy");
-                dcache_dir_close(inode, file);
-                status = -EBUSY;
-                goto out;
-        }
-
-        status = -ENOENT;
-        if (!d_mountpoint(dentry) && dentry->d_op && dentry->d_op->d_revalidate) {
-                struct nameidata nd;
-                int empty, ret;
-
-                /* In case there are stale directory dentrys from a failed mount */
-                spin_lock(&dcache_lock);
-                empty = list_empty(&dentry->d_subdirs);
+        /*
+         * An empty directory in an autofs file system is always a
+         * mount point. The daemon must have failed to mount this
+         * during lookup so it doesn't exist. This can happen, for
+         * example, if user space returns an incorrect status for a
+         * mount request. Otherwise we're doing a readdir on the
+         * autofs file system so just let the libfs routines handle
+         * it.
+         */
+        spin_lock(&dcache_lock);
+        if (!d_mountpoint(dentry) && __simple_empty(dentry)) {
                 spin_unlock(&dcache_lock);
-
-                if (!empty)
-                        d_invalidate(dentry);
-
-                nd.flags = LOOKUP_DIRECTORY;
-                ret = (dentry->d_op->d_revalidate)(dentry, &nd);
-
-                if (ret <= 0) {
-                        if (ret < 0)
-                                status = ret;
-                        dcache_dir_close(inode, file);
-                        goto out;
-                }
+                return -ENOENT;
         }
+        spin_unlock(&dcache_lock);
 
-        if (d_mountpoint(dentry)) {
-                struct file *fp = NULL;
-                struct path fp_path = { .dentry = dentry, .mnt = mnt };
-
-                path_get(&fp_path);
-
-                if (!autofs4_follow_mount(&fp_path.mnt, &fp_path.dentry)) {
-                        path_put(&fp_path);
-                        dcache_dir_close(inode, file);
-                        goto out;
-                }
-
-                fp = dentry_open(fp_path.dentry, fp_path.mnt, file->f_flags);
-                status = PTR_ERR(fp);
-                if (IS_ERR(fp)) {
-                        dcache_dir_close(inode, file);
-                        goto out;
-                }
-                cursor->d_fsdata = fp;
-        }
-        return 0;
-out:
-        return status;
-}
-
-static int autofs4_dir_close(struct inode *inode, struct file *file)
-{
-        struct dentry *dentry = file->f_path.dentry;
-        struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
-        struct dentry *cursor = file->private_data;
-        int status = 0;
-
-        DPRINTK("file=%p dentry=%p %.*s",
-                file, dentry, dentry->d_name.len, dentry->d_name.name);
-
-        if (autofs4_oz_mode(sbi))
-                goto out;
-
-        if (autofs4_ispending(dentry)) {
-                DPRINTK("dentry busy");
-                status = -EBUSY;
-                goto out;
-        }
-
-        if (d_mountpoint(dentry)) {
-                struct file *fp = cursor->d_fsdata;
-                if (!fp) {
-                        status = -ENOENT;
-                        goto out;
-                }
-                filp_close(fp, current->files);
-        }
-out:
-        dcache_dir_close(inode, file);
-        return status;
-}
-
-static int autofs4_dir_readdir(struct file *file, void *dirent, filldir_t filldir)
-{
-        struct dentry *dentry = file->f_path.dentry;
-        struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
-        struct dentry *cursor = file->private_data;
-        int status;
-
-        DPRINTK("file=%p dentry=%p %.*s",
-                file, dentry, dentry->d_name.len, dentry->d_name.name);
-
-        if (autofs4_oz_mode(sbi))
-                goto out;
-
-        if (autofs4_ispending(dentry)) {
-                DPRINTK("dentry busy");
-                return -EBUSY;
-        }
-
-        if (d_mountpoint(dentry)) {
-                struct file *fp = cursor->d_fsdata;
-
-                if (!fp)
-                        return -ENOENT;
-
-                if (!fp->f_op || !fp->f_op->readdir)
-                        goto out;
-
-                status = vfs_readdir(fp, filldir, dirent);
-                file->f_pos = fp->f_pos;
-                if (status)
-                        autofs4_copy_atime(file, fp);
-                return status;
-        }
 out:
-        return dcache_readdir(file, dirent, filldir);
+        return dcache_dir_open(inode, file);
 }
 
 static int try_to_fill_dentry(struct dentry *dentry, int flags)
 {
         struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
         struct autofs_info *ino = autofs4_dentry_ino(dentry);
-        struct dentry *new;
         int status;
 
-        /* Block on any pending expiry here; invalidate the dentry
-           when expiration is done to trigger mount request with a new
-           dentry */
-        if (ino && (ino->flags & AUTOFS_INF_EXPIRING)) {
-                DPRINTK("waiting for expire %p name=%.*s",
-                         dentry, dentry->d_name.len, dentry->d_name.name);
-
-                status = autofs4_wait(sbi, dentry, NFY_NONE);
-
-                DPRINTK("expire done status=%d", status);
-
-                /*
-                 * If the directory still exists the mount request must
-                 * continue otherwise it can't be followed at the right
-                 * time during the walk.
-                 */
-                status = d_invalidate(dentry);
-                if (status != -EBUSY)
-                        return -EAGAIN;
-        }
-
         DPRINTK("dentry=%p %.*s ino=%p",
                  dentry, dentry->d_name.len, dentry->d_name.name, dentry->d_inode);
 
@@ -292,7 +133,8 @@ static int try_to_fill_dentry(struct dentry *dentry, int flags)
                         return status;
                 }
         /* Trigger mount for path component or follow link */
-        } else if (flags & (LOOKUP_CONTINUE | LOOKUP_DIRECTORY) ||
+        } else if (dentry->d_flags & DCACHE_AUTOFS_PENDING ||
+                        flags & (TRIGGER_FLAGS | TRIGGER_INTENTS) ||
                         current->link_count) {
                 DPRINTK("waiting for mount name=%.*s",
                         dentry->d_name.len, dentry->d_name.name);
@@ -320,26 +162,6 @@ static int try_to_fill_dentry(struct dentry *dentry, int flags)
         dentry->d_flags &= ~DCACHE_AUTOFS_PENDING;
         spin_unlock(&dentry->d_lock);
 
-        /*
-         * The dentry that is passed in from lookup may not be the one
-         * we end up using, as mkdir can create a new one.  If this
-         * happens, and another process tries the lookup at the same time,
-         * it will set the PENDING flag on this new dentry, but add itself
-         * to our waitq.  Then, if after the lookup succeeds, the first
-         * process that requested the mount performs another lookup of the
-         * same directory, it will show up as still pending!  So, we need
-         * to redo the lookup here and clear pending on that dentry.
-         */
-        if (d_unhashed(dentry)) {
-                new = d_lookup(dentry->d_parent, &dentry->d_name);
-                if (new) {
-                        spin_lock(&new->d_lock);
-                        new->d_flags &= ~DCACHE_AUTOFS_PENDING;
-                        spin_unlock(&new->d_lock);
-                        dput(new);
-                }
-        }
-
         return 0;
 }
 
@@ -355,51 +177,63 @@ static void *autofs4_follow_link(struct dentry *dentry, struct nameidata *nd)
         DPRINTK("dentry=%p %.*s oz_mode=%d nd->flags=%d",
                 dentry, dentry->d_name.len, dentry->d_name.name, oz_mode,
                 nd->flags);
-
-        /* If it's our master or we shouldn't trigger a mount we're done */
-        lookup_type = nd->flags & (LOOKUP_CONTINUE | LOOKUP_DIRECTORY);
-        if (oz_mode || !lookup_type)
+        /*
+         * For an expire of a covered direct or offset mount we need
+         * to beeak out of follow_down() at the autofs mount trigger
+         * (d_mounted--), so we can see the expiring flag, and manage
+         * the blocking and following here until the expire is completed.
+         */
+        if (oz_mode) {
+                spin_lock(&sbi->fs_lock);
+                if (ino->flags & AUTOFS_INF_EXPIRING) {
+                        spin_unlock(&sbi->fs_lock);
+                        /* Follow down to our covering mount. */
+                        if (!follow_down(&nd->path.mnt, &nd->path.dentry))
+                                goto done;
+                        goto follow;
+                }
+                spin_unlock(&sbi->fs_lock);
                 goto done;
+        }
 
-        /* If an expire request is pending wait for it. */
-        if (ino && (ino->flags & AUTOFS_INF_EXPIRING)) {
-                DPRINTK("waiting for active request %p name=%.*s",
-                        dentry, dentry->d_name.len, dentry->d_name.name);
-
-                status = autofs4_wait(sbi, dentry, NFY_NONE);
+        /* If an expire request is pending everyone must wait. */
+        autofs4_expire_wait(dentry);
 
-                DPRINTK("request done status=%d", status);
-        }
+        /* We trigger a mount for almost all flags */
+        lookup_type = nd->flags & (TRIGGER_FLAGS | TRIGGER_INTENTS);
+        if (!(lookup_type || dentry->d_flags & DCACHE_AUTOFS_PENDING))
+                goto follow;
 
         /*
-         * If the dentry contains directories then it is an
-         * autofs multi-mount with no root mount offset. So
-         * don't try to mount it again.
+         * If the dentry contains directories then it is an autofs
+         * multi-mount with no root mount offset. So don't try to
+         * mount it again.
          */
         spin_lock(&dcache_lock);
-        if (!d_mountpoint(dentry) && __simple_empty(dentry)) {
+        if (dentry->d_flags & DCACHE_AUTOFS_PENDING ||
+            (!d_mountpoint(dentry) && __simple_empty(dentry))) {
                 spin_unlock(&dcache_lock);
 
                 status = try_to_fill_dentry(dentry, 0);
                 if (status)
                         goto out_error;
 
-                /*
-                 * The mount succeeded but if there is no root mount
-                 * it must be an autofs multi-mount with no root offset
-                 * so we don't need to follow the mount.
-                 */
-                if (d_mountpoint(dentry)) {
-                        if (!autofs4_follow_mount(&nd->path.mnt,
-                                                  &nd->path.dentry)) {
-                                status = -ENOENT;
-                                goto out_error;
-                        }
-                }
-
-                goto done;
+                goto follow;
         }
         spin_unlock(&dcache_lock);
+follow:
+        /*
+         * If there is no root mount it must be an autofs
+         * multi-mount with no root offset so we don't need
+         * to follow it.
+         */
+        if (d_mountpoint(dentry)) {
+                if (!autofs4_follow_mount(&nd->path.mnt,
+                                          &nd->path.dentry)) {
+                        status = -ENOENT;
+                        goto out_error;
+                }
+        }
 
 done:
         return NULL;
@@ -424,12 +258,23 @@ static int autofs4_revalidate(struct dentry *dentry, struct nameidata *nd)
         int status = 1;
 
         /* Pending dentry */
+        spin_lock(&sbi->fs_lock);
         if (autofs4_ispending(dentry)) {
                 /* The daemon never causes a mount to trigger */
+                spin_unlock(&sbi->fs_lock);
+
                 if (oz_mode)
                         return 1;
 
                 /*
+                 * If the directory has gone away due to an expire
+                 * we have been called as ->d_revalidate() and so
+                 * we need to return false and proceed to ->lookup().
+                 */
+                if (autofs4_expire_wait(dentry) == -EAGAIN)
+                        return 0;
+
+                /*
                  * A zero status is success otherwise we have a
                  * negative error code.
                  */
@@ -437,17 +282,9 @@ static int autofs4_revalidate(struct dentry *dentry, struct nameidata *nd)
                 if (status == 0)
                         return 1;
 
-                /*
-                 * A status of EAGAIN here means that the dentry has gone
-                 * away while waiting for an expire to complete. If we are
-                 * racing with expire lookup will wait for it so this must
-                 * be a revalidate and we need to send it to lookup.
-                 */
-                if (status == -EAGAIN)
-                        return 0;
-
                 return status;
         }
+        spin_unlock(&sbi->fs_lock);
 
         /* Negative dentry.. invalidate if "old" */
         if (dentry->d_inode == NULL)
@@ -461,6 +298,7 @@ static int autofs4_revalidate(struct dentry *dentry, struct nameidata *nd)
                 DPRINTK("dentry=%p %.*s, emptydir",
                          dentry, dentry->d_name.len, dentry->d_name.name);
                 spin_unlock(&dcache_lock);
+
                 /* The daemon never causes a mount to trigger */
                 if (oz_mode)
                         return 1;
@@ -493,10 +331,12 @@ void autofs4_dentry_release(struct dentry *de)
                 struct autofs_sb_info *sbi = autofs4_sbi(de->d_sb);
 
                 if (sbi) {
-                        spin_lock(&sbi->rehash_lock);
-                        if (!list_empty(&inf->rehash))
-                                list_del(&inf->rehash);
-                        spin_unlock(&sbi->rehash_lock);
+                        spin_lock(&sbi->lookup_lock);
+                        if (!list_empty(&inf->active))
+                                list_del(&inf->active);
+                        if (!list_empty(&inf->expiring))
+                                list_del(&inf->expiring);
+                        spin_unlock(&sbi->lookup_lock);
                 }
 
                 inf->dentry = NULL;
@@ -518,7 +358,7 @@ static struct dentry_operations autofs4_dentry_operations = {
         .d_release      = autofs4_dentry_release,
 };
 
-static struct dentry *autofs4_lookup_unhashed(struct autofs_sb_info *sbi, struct dentry *parent, struct qstr *name)
+static struct dentry *autofs4_lookup_active(struct autofs_sb_info *sbi, struct dentry *parent, struct qstr *name)
 {
         unsigned int len = name->len;
         unsigned int hash = name->hash;
@@ -526,14 +366,66 @@ static struct dentry *autofs4_lookup_unhashed(struct autofs_sb_info *sbi, struct
         struct list_head *p, *head;
 
         spin_lock(&dcache_lock);
-        spin_lock(&sbi->rehash_lock);
-        head = &sbi->rehash_list;
+        spin_lock(&sbi->lookup_lock);
+        head = &sbi->active_list;
         list_for_each(p, head) {
                 struct autofs_info *ino;
                 struct dentry *dentry;
                 struct qstr *qstr;
 
-                ino = list_entry(p, struct autofs_info, rehash);
+                ino = list_entry(p, struct autofs_info, active);
+                dentry = ino->dentry;
+
+                spin_lock(&dentry->d_lock);
+
+                /* Already gone? */
+                if (atomic_read(&dentry->d_count) == 0)
+                        goto next;
+
+                qstr = &dentry->d_name;
+
+                if (dentry->d_name.hash != hash)
+                        goto next;
+                if (dentry->d_parent != parent)
+                        goto next;
+
+                if (qstr->len != len)
+                        goto next;
+                if (memcmp(qstr->name, str, len))
+                        goto next;
+
+                if (d_unhashed(dentry)) {
+                        dget(dentry);
+                        spin_unlock(&dentry->d_lock);
+                        spin_unlock(&sbi->lookup_lock);
+                        spin_unlock(&dcache_lock);
+                        return dentry;
+                }
+next:
+                spin_unlock(&dentry->d_lock);
+        }
+        spin_unlock(&sbi->lookup_lock);
+        spin_unlock(&dcache_lock);
+
+        return NULL;
+}
+
+static struct dentry *autofs4_lookup_expiring(struct autofs_sb_info *sbi, struct dentry *parent, struct qstr *name)
+{
+        unsigned int len = name->len;
+        unsigned int hash = name->hash;
+        const unsigned char *str = name->name;
+        struct list_head *p, *head;
+
+        spin_lock(&dcache_lock);
+        spin_lock(&sbi->lookup_lock);
+        head = &sbi->expiring_list;
+        list_for_each(p, head) {
+                struct autofs_info *ino;
+                struct dentry *dentry;
+                struct qstr *qstr;
+
+                ino = list_entry(p, struct autofs_info, expiring);
                 dentry = ino->dentry;
 
                 spin_lock(&dentry->d_lock);
@@ -555,33 +447,16 @@ static struct dentry *autofs4_lookup_unhashed(struct autofs_sb_info *sbi, struct
                         goto next;
 
                 if (d_unhashed(dentry)) {
-                        struct inode *inode = dentry->d_inode;
-
-                        ino = autofs4_dentry_ino(dentry);
-                        list_del_init(&ino->rehash);
                         dget(dentry);
-                        /*
-                         * Make the rehashed dentry negative so the VFS
-                         * behaves as it should.
-                         */
-                        if (inode) {
-                                dentry->d_inode = NULL;
-                                list_del_init(&dentry->d_alias);
-                                spin_unlock(&dentry->d_lock);
-                                spin_unlock(&sbi->rehash_lock);
-                                spin_unlock(&dcache_lock);
-                                iput(inode);
-                                return dentry;
-                        }
                         spin_unlock(&dentry->d_lock);
-                        spin_unlock(&sbi->rehash_lock);
+                        spin_unlock(&sbi->lookup_lock);
                         spin_unlock(&dcache_lock);
                         return dentry;
                 }
 next:
                 spin_unlock(&dentry->d_lock);
         }
-        spin_unlock(&sbi->rehash_lock);
+        spin_unlock(&sbi->lookup_lock);
         spin_unlock(&dcache_lock);
 
         return NULL;
@@ -591,7 +466,8 @@ next:
 static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
 {
         struct autofs_sb_info *sbi;
-        struct dentry *unhashed;
+        struct autofs_info *ino;
+        struct dentry *expiring, *unhashed;
         int oz_mode;
 
         DPRINTK("name = %.*s",
@@ -607,8 +483,26 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, s
         DPRINTK("pid = %u, pgrp = %u, catatonic = %d, oz_mode = %d",
                  current->pid, task_pgrp_nr(current), sbi->catatonic, oz_mode);
 
-        unhashed = autofs4_lookup_unhashed(sbi, dentry->d_parent, &dentry->d_name);
-        if (!unhashed) {
+        expiring = autofs4_lookup_expiring(sbi, dentry->d_parent, &dentry->d_name);
+        if (expiring) {
+                /*
+                 * If we are racing with expire the request might not
+                 * be quite complete but the directory has been removed
+                 * so it must have been successful, so just wait for it.
+                 */
+                ino = autofs4_dentry_ino(expiring);
+                autofs4_expire_wait(expiring);
+                spin_lock(&sbi->lookup_lock);
+                if (!list_empty(&ino->expiring))
+                        list_del_init(&ino->expiring);
+                spin_unlock(&sbi->lookup_lock);
+                dput(expiring);
+        }
+
+        unhashed = autofs4_lookup_active(sbi, dentry->d_parent, &dentry->d_name);
+        if (unhashed)
+                dentry = unhashed;
+        else {
                 /*
                  * Mark the dentry incomplete but don't hash it. We do this
                  * to serialize our inode creation operations (symlink and
@@ -622,39 +516,34 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, s
                  */
                 dentry->d_op = &autofs4_root_dentry_operations;
 
-                dentry->d_fsdata = NULL;
-                d_instantiate(dentry, NULL);
-        } else {
-                struct autofs_info *ino = autofs4_dentry_ino(unhashed);
-                DPRINTK("rehash %p with %p", dentry, unhashed);
                 /*
-                 * If we are racing with expire the request might not
-                 * be quite complete but the directory has been removed
-                 * so it must have been successful, so just wait for it.
-                 * We need to ensure the AUTOFS_INF_EXPIRING flag is clear
-                 * before continuing as revalidate may fail when calling
-                 * try_to_fill_dentry (returning EAGAIN) if we don't.
+                 * And we need to ensure that the same dentry is used for
+                 * all following lookup calls until it is hashed so that
+                 * the dentry flags are persistent throughout the request.
                  */
-                while (ino && (ino->flags & AUTOFS_INF_EXPIRING)) {
-                        DPRINTK("wait for incomplete expire %p name=%.*s",
-                                unhashed, unhashed->d_name.len,
-                                unhashed->d_name.name);
-                        autofs4_wait(sbi, unhashed, NFY_NONE);
-                        DPRINTK("request completed");
-                }
-                dentry = unhashed;
+                ino = autofs4_init_ino(NULL, sbi, 0555);
+                if (!ino)
+                        return ERR_PTR(-ENOMEM);
+
+                dentry->d_fsdata = ino;
+                ino->dentry = dentry;
+
+                spin_lock(&sbi->lookup_lock);
+                list_add(&ino->active, &sbi->active_list);
+                spin_unlock(&sbi->lookup_lock);
+
+                d_instantiate(dentry, NULL);
         }
 
         if (!oz_mode) {
                 spin_lock(&dentry->d_lock);
                 dentry->d_flags |= DCACHE_AUTOFS_PENDING;
                 spin_unlock(&dentry->d_lock);
-        }
-
-        if (dentry->d_op && dentry->d_op->d_revalidate) {
-                mutex_unlock(&dir->i_mutex);
-                (dentry->d_op->d_revalidate)(dentry, nd);
-                mutex_lock(&dir->i_mutex);
+                if (dentry->d_op && dentry->d_op->d_revalidate) {
+                        mutex_unlock(&dir->i_mutex);
+                        (dentry->d_op->d_revalidate)(dentry, nd);
+                        mutex_lock(&dir->i_mutex);
+                }
         }
 
         /*
@@ -673,9 +562,11 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, s
                             return ERR_PTR(-ERESTARTNOINTR);
                         }
                 }
-                spin_lock(&dentry->d_lock);
-                dentry->d_flags &= ~DCACHE_AUTOFS_PENDING;
-                spin_unlock(&dentry->d_lock);
+                if (!oz_mode) {
+                        spin_lock(&dentry->d_lock);
+                        dentry->d_flags &= ~DCACHE_AUTOFS_PENDING;
+                        spin_unlock(&dentry->d_lock);
+                }
         }
 
         /*
@@ -706,7 +597,7 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, s
         }
 
         if (unhashed)
-                return dentry;
+                return unhashed;
 
         return NULL;
 }
@@ -728,20 +619,31 @@ static int autofs4_dir_symlink(struct inode *dir,
                 return -EACCES;
 
         ino = autofs4_init_ino(ino, sbi, S_IFLNK | 0555);
-        if (ino == NULL)
-                return -ENOSPC;
+        if (!ino)
+                return -ENOMEM;
 
-        ino->size = strlen(symname);
-        ino->u.symlink = cp = kmalloc(ino->size + 1, GFP_KERNEL);
+        spin_lock(&sbi->lookup_lock);
+        if (!list_empty(&ino->active))
+                list_del_init(&ino->active);
+        spin_unlock(&sbi->lookup_lock);
 
-        if (cp == NULL) {
-                kfree(ino);
-                return -ENOSPC;
+        ino->size = strlen(symname);
+        cp = kmalloc(ino->size + 1, GFP_KERNEL);
+        if (!cp) {
+                if (!dentry->d_fsdata)
+                        kfree(ino);
+                return -ENOMEM;
         }
 
         strcpy(cp, symname);
 
         inode = autofs4_get_inode(dir->i_sb, ino);
+        if (!inode) {
+                kfree(cp);
+                if (!dentry->d_fsdata)
+                        kfree(ino);
+                return -ENOMEM;
+        }
         d_add(dentry, inode);
 
         if (dir == dir->i_sb->s_root->d_inode)
@@ -757,6 +659,7 @@ static int autofs4_dir_symlink(struct inode *dir,
                 atomic_inc(&p_ino->count);
         ino->inode = inode;
 
+        ino->u.symlink = cp;
         dir->i_mtime = CURRENT_TIME;
 
         return 0;
@@ -769,9 +672,8 @@ static int autofs4_dir_symlink(struct inode *dir,
  * that the file no longer exists. However, doing that means that the
  * VFS layer can turn the dentry into a negative dentry.  We don't want
  * this, because the unlink is probably the result of an expire.
- * We simply d_drop it and add it to a rehash candidates list in the
- * super block, which allows the dentry lookup to reuse it retaining
- * the flags, such as expire in progress, in case we're racing with expire.
+ * We simply d_drop it and add it to a expiring list in the super block,
+ * which allows the dentry lookup to check for an incomplete expire.
  *
  * If a process is blocked on the dentry waiting for the expire to finish,
  * it will invalidate the dentry and try to mount with a new one.
@@ -801,9 +703,10 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry)
         dir->i_mtime = CURRENT_TIME;
 
         spin_lock(&dcache_lock);
-        spin_lock(&sbi->rehash_lock);
-        list_add(&ino->rehash, &sbi->rehash_list);
-        spin_unlock(&sbi->rehash_lock);
+        spin_lock(&sbi->lookup_lock);
+        if (list_empty(&ino->expiring))
+                list_add(&ino->expiring, &sbi->expiring_list);
+        spin_unlock(&sbi->lookup_lock);
         spin_lock(&dentry->d_lock);
         __d_drop(dentry);
         spin_unlock(&dentry->d_lock);
@@ -829,9 +732,10 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry)
                 spin_unlock(&dcache_lock);
                 return -ENOTEMPTY;
         }
-        spin_lock(&sbi->rehash_lock);
-        list_add(&ino->rehash, &sbi->rehash_list);
-        spin_unlock(&sbi->rehash_lock);
+        spin_lock(&sbi->lookup_lock);
+        if (list_empty(&ino->expiring))
+                list_add(&ino->expiring, &sbi->expiring_list);
+        spin_unlock(&sbi->lookup_lock);
         spin_lock(&dentry->d_lock);
         __d_drop(dentry);
         spin_unlock(&dentry->d_lock);
@@ -866,10 +770,20 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, int mode)
                 dentry, dentry->d_name.len, dentry->d_name.name);
 
         ino = autofs4_init_ino(ino, sbi, S_IFDIR | 0555);
-        if (ino == NULL)
-                return -ENOSPC;
+        if (!ino)
+                return -ENOMEM;
+
+        spin_lock(&sbi->lookup_lock);
+        if (!list_empty(&ino->active))
+                list_del_init(&ino->active);
+        spin_unlock(&sbi->lookup_lock);
 
         inode = autofs4_get_inode(dir->i_sb, ino);
+        if (!inode) {
+                if (!dentry->d_fsdata)
+                        kfree(ino);
+                return -ENOMEM;
+        }
         d_add(dentry, inode);
 
         if (dir == dir->i_sb->s_root->d_inode)
@@ -922,44 +836,6 @@ static inline int autofs4_get_protosubver(struct autofs_sb_info *sbi, int __user
 }
 
 /*
- * Tells the daemon whether we need to reghost or not. Also, clears
- * the reghost_needed flag.
- */
-static inline int autofs4_ask_reghost(struct autofs_sb_info *sbi, int __user *p)
-{
-        int status;
-
-        DPRINTK("returning %d", sbi->needs_reghost);
-
-        status = put_user(sbi->needs_reghost, p);
-        if (status)
-                return status;
-
-        sbi->needs_reghost = 0;
-        return 0;
-}
-
-/*
- * Enable / Disable reghosting ioctl() operation
- */
-static inline int autofs4_toggle_reghost(struct autofs_sb_info *sbi, int __user *p)
-{
-        int status;
-        int val;
-
-        status = get_user(val, p);
-
-        DPRINTK("reghost = %d", val);
-
-        if (status)
-                return status;
-
-        /* turn on/off reghosting, with the val */
-        sbi->reghost_enabled = val;
-        return 0;
-}
-
-/*
 * Tells the daemon whether it can umount the autofs mount.
 */
 static inline int autofs4_ask_umount(struct vfsmount *mnt, int __user *p)
@@ -1023,11 +899,6 @@ static int autofs4_root_ioctl(struct inode *inode, struct file *filp,
         case AUTOFS_IOC_SETTIMEOUT:
                 return autofs4_get_set_timeout(sbi, p);
 
-        case AUTOFS_IOC_TOGGLEREGHOST:
-                return autofs4_toggle_reghost(sbi, p);
-        case AUTOFS_IOC_ASKREGHOST:
-                return autofs4_ask_reghost(sbi, p);
-
         case AUTOFS_IOC_ASKUMOUNT:
                 return autofs4_ask_umount(filp->f_path.mnt, p);
 
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 75e5955c3f6d..35216d18d8b5 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -28,6 +28,12 @@ void autofs4_catatonic_mode(struct autofs_sb_info *sbi)
 {
         struct autofs_wait_queue *wq, *nwq;
 
+        mutex_lock(&sbi->wq_mutex);
+        if (sbi->catatonic) {
+                mutex_unlock(&sbi->wq_mutex);
+                return;
+        }
+
         DPRINTK("entering catatonic mode");
 
         sbi->catatonic = 1;
@@ -36,13 +42,18 @@ void autofs4_catatonic_mode(struct autofs_sb_info *sbi)
         while (wq) {
                 nwq = wq->next;
                 wq->status = -ENOENT; /* Magic is gone - report failure */
-                kfree(wq->name);
-                wq->name = NULL;
+                if (wq->name.name) {
+                        kfree(wq->name.name);
+                        wq->name.name = NULL;
+                }
+                wq->wait_ctr--;
                 wake_up_interruptible(&wq->queue);
                 wq = nwq;
         }
         fput(sbi->pipe);        /* Close the pipe */
         sbi->pipe = NULL;
+        sbi->pipefd = -1;
+        mutex_unlock(&sbi->wq_mutex);
 }
 
 static int autofs4_write(struct file *file, const void *addr, int bytes)
@@ -89,10 +100,11 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
                 union autofs_packet_union v4_pkt;
                 union autofs_v5_packet_union v5_pkt;
         } pkt;
+        struct file *pipe = NULL;
         size_t pktsz;
 
         DPRINTK("wait id = 0x%08lx, name = %.*s, type=%d",
-                wq->wait_queue_token, wq->len, wq->name, type);
+                wq->wait_queue_token, wq->name.len, wq->name.name, type);
 
         memset(&pkt,0,sizeof pkt); /* For security reasons */
 
@@ -107,9 +119,9 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
                 pktsz = sizeof(*mp);
 
                 mp->wait_queue_token = wq->wait_queue_token;
-                mp->len = wq->len;
-                memcpy(mp->name, wq->name, wq->len);
-                mp->name[wq->len] = '\0';
+                mp->len = wq->name.len;
+                memcpy(mp->name, wq->name.name, wq->name.len);
+                mp->name[wq->name.len] = '\0';
                 break;
         }
         case autofs_ptype_expire_multi:
@@ -119,9 +131,9 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
                 pktsz = sizeof(*ep);
 
                 ep->wait_queue_token = wq->wait_queue_token;
-                ep->len = wq->len;
-                memcpy(ep->name, wq->name, wq->len);
-                ep->name[wq->len] = '\0';
+                ep->len = wq->name.len;
+                memcpy(ep->name, wq->name.name, wq->name.len);
+                ep->name[wq->name.len] = '\0';
                 break;
         }
         /*
@@ -138,9 +150,9 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
                 pktsz = sizeof(*packet);
 
                 packet->wait_queue_token = wq->wait_queue_token;
-                packet->len = wq->len;
-                memcpy(packet->name, wq->name, wq->len);
-                packet->name[wq->len] = '\0';
+                packet->len = wq->name.len;
+                memcpy(packet->name, wq->name.name, wq->name.len);
+                packet->name[wq->name.len] = '\0';
                 packet->dev = wq->dev;
                 packet->ino = wq->ino;
                 packet->uid = wq->uid;
@@ -154,8 +166,19 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
                 return;
         }
 
-        if (autofs4_write(sbi->pipe, &pkt, pktsz))
-                autofs4_catatonic_mode(sbi);
+        /* Check if we have become catatonic */
+        mutex_lock(&sbi->wq_mutex);
+        if (!sbi->catatonic) {
+                pipe = sbi->pipe;
+                get_file(pipe);
+        }
+        mutex_unlock(&sbi->wq_mutex);
+
+        if (pipe) {
+                if (autofs4_write(pipe, &pkt, pktsz))
+                        autofs4_catatonic_mode(sbi);
+                fput(pipe);
+        }
 }
 
 static int autofs4_getpath(struct autofs_sb_info *sbi,
@@ -191,58 +214,55 @@ static int autofs4_getpath(struct autofs_sb_info *sbi,
 }
 
 static struct autofs_wait_queue *
-autofs4_find_wait(struct autofs_sb_info *sbi,
-                  char *name, unsigned int hash, unsigned int len)
+autofs4_find_wait(struct autofs_sb_info *sbi, struct qstr *qstr)
 {
         struct autofs_wait_queue *wq;
 
         for (wq = sbi->queues; wq; wq = wq->next) {
-                if (wq->hash == hash &&
-                    wq->len == len &&
-                    wq->name && !memcmp(wq->name, name, len))
+                if (wq->name.hash == qstr->hash &&
+                    wq->name.len == qstr->len &&
+                    wq->name.name &&
+                         !memcmp(wq->name.name, qstr->name, qstr->len))
                         break;
         }
         return wq;
 }
 
-int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
-                enum autofs_notify notify)
+/*
+ * Check if we have a valid request.
+ * Returns
+ * 1 if the request should continue.
+ *   In this case we can return an autofs_wait_queue entry if one is
+ *   found or NULL to idicate a new wait needs to be created.
+ * 0 or a negative errno if the request shouldn't continue.
+ */
+static int validate_request(struct autofs_wait_queue **wait,
+                            struct autofs_sb_info *sbi,
+                            struct qstr *qstr,
+                            struct dentry*dentry, enum autofs_notify notify)
 {
-        struct autofs_info *ino;
         struct autofs_wait_queue *wq;
-        char *name;
-        unsigned int len = 0;
-        unsigned int hash = 0;
-        int status, type;
-
-        /* In catatonic mode, we don't wait for nobody */
-        if (sbi->catatonic)
-                return -ENOENT;
-        
-        name = kmalloc(NAME_MAX + 1, GFP_KERNEL);
-        if (!name)
-                return -ENOMEM;
+        struct autofs_info *ino;
 
-        /* If this is a direct mount request create a dummy name */
-        if (IS_ROOT(dentry) && (sbi->type & AUTOFS_TYPE_DIRECT))
-                len = sprintf(name, "%p", dentry);
-        else {
-                len = autofs4_getpath(sbi, dentry, &name);
-                if (!len) {
-                        kfree(name);
-                        return -ENOENT;
-                }
+        /* Wait in progress, continue; */
+        wq = autofs4_find_wait(sbi, qstr);
+        if (wq) {
+                *wait = wq;
+                return 1;
         }
-        hash = full_name_hash(name, len);
 
-        if (mutex_lock_interruptible(&sbi->wq_mutex)) {
-                kfree(name);
-                return -EINTR;
-        }
+        *wait = NULL;
 
-        wq = autofs4_find_wait(sbi, name, hash, len);
+        /* If we don't yet have any info this is a new request */
         ino = autofs4_dentry_ino(dentry);
-        if (!wq && ino && notify == NFY_NONE) {
+        if (!ino)
+                return 1;
+
+        /*
+         * If we've been asked to wait on an existing expire (NFY_NONE)
+         * but there is no wait in the queue ...
+         */
+        if (notify == NFY_NONE) {
                 /*
                  * Either we've betean the pending expire to post it's
                  * wait or it finished while we waited on the mutex.
@@ -253,13 +273,14 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
                 while (ino->flags & AUTOFS_INF_EXPIRING) {
                         mutex_unlock(&sbi->wq_mutex);
                         schedule_timeout_interruptible(HZ/10);
-                        if (mutex_lock_interruptible(&sbi->wq_mutex)) {
-                                kfree(name);
+                        if (mutex_lock_interruptible(&sbi->wq_mutex))
                                 return -EINTR;
+
+                        wq = autofs4_find_wait(sbi, qstr);
+                        if (wq) {
+                                *wait = wq;
+                                return 1;
                         }
-                        wq = autofs4_find_wait(sbi, name, hash, len);
-                        if (wq)
-                                break;
                 }
 
                 /*
@@ -267,18 +288,96 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
                  * cases where we wait on NFY_NONE neither depend on the
                  * return status of the wait.
                  */
-                if (!wq) {
+                return 0;
+        }
+
+        /*
+         * If we've been asked to trigger a mount and the request
+         * completed while we waited on the mutex ...
+         */
+        if (notify == NFY_MOUNT) {
+                /*
+                 * If the dentry isn't hashed just go ahead and try the
+                 * mount again with a new wait (not much else we can do).
+                */
+                if (!d_unhashed(dentry)) {
+                        /*
+                         * But if the dentry is hashed, that means that we
+                         * got here through the revalidate path.  Thus, we
+                         * need to check if the dentry has been mounted
+                         * while we waited on the wq_mutex. If it has,
+                         * simply return success.
+                         */
+                        if (d_mountpoint(dentry))
+                                return 0;
+                }
+        }
+
+        return 1;
+}
+
+int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
+                enum autofs_notify notify)
+{
+        struct autofs_wait_queue *wq;
+        struct qstr qstr;
+        char *name;
+        int status, ret, type;
+
+        /* In catatonic mode, we don't wait for nobody */
+        if (sbi->catatonic)
+                return -ENOENT;
+
+        if (!dentry->d_inode) {
+                /*
+                 * A wait for a negative dentry is invalid for certain
+                 * cases. A direct or offset mount "always" has its mount
+                 * point directory created and so the request dentry must
+                 * be positive or the map key doesn't exist. The situation
+                 * is very similar for indirect mounts except only dentrys
+                 * in the root of the autofs file system may be negative.
+                 */
+                if (sbi->type & (AUTOFS_TYPE_DIRECT|AUTOFS_TYPE_OFFSET))
+                        return -ENOENT;
+                else if (!IS_ROOT(dentry->d_parent))
+                        return -ENOENT;
+        }
+
+        name = kmalloc(NAME_MAX + 1, GFP_KERNEL);
+        if (!name)
+                return -ENOMEM;
+
+        /* If this is a direct mount request create a dummy name */
+        if (IS_ROOT(dentry) && (sbi->type & AUTOFS_TYPE_DIRECT))
+                qstr.len = sprintf(name, "%p", dentry);
+        else {
+                qstr.len = autofs4_getpath(sbi, dentry, &name);
+                if (!qstr.len) {
                         kfree(name);
-                        mutex_unlock(&sbi->wq_mutex);
-                        return 0;
+                        return -ENOENT;
                 }
         }
+        qstr.name = name;
+        qstr.hash = full_name_hash(name, qstr.len);
+
+        if (mutex_lock_interruptible(&sbi->wq_mutex)) {
+                kfree(qstr.name);
+                return -EINTR;
+        }
+
+        ret = validate_request(&wq, sbi, &qstr, dentry, notify);
+        if (ret <= 0) {
+                if (ret == 0)
+                        mutex_unlock(&sbi->wq_mutex);
+                kfree(qstr.name);
+                return ret;
+        }
 
         if (!wq) {
                 /* Create a new wait queue */
                 wq = kmalloc(sizeof(struct autofs_wait_queue),GFP_KERNEL);
                 if (!wq) {
-                        kfree(name);
+                        kfree(qstr.name);
                         mutex_unlock(&sbi->wq_mutex);
                         return -ENOMEM;
                 }
@@ -289,9 +388,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
                 wq->next = sbi->queues;
                 sbi->queues = wq;
                 init_waitqueue_head(&wq->queue);
-                wq->hash = hash;
-                wq->name = name;
-                wq->len = len;
+                memcpy(&wq->name, &qstr, sizeof(struct qstr));
                 wq->dev = autofs4_get_dev(sbi);
                 wq->ino = autofs4_get_ino(sbi);
                 wq->uid = current->uid;
@@ -299,7 +396,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
                 wq->pid = current->pid;
                 wq->tgid = current->tgid;
                 wq->status = -EINTR; /* Status return if interrupted */
-                atomic_set(&wq->wait_ctr, 2);
+                wq->wait_ctr = 2;
                 mutex_unlock(&sbi->wq_mutex);
 
                 if (sbi->version < 5) {
@@ -319,28 +416,25 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
                 }
 
                 DPRINTK("new wait id = 0x%08lx, name = %.*s, nfy=%d\n",
-                        (unsigned long) wq->wait_queue_token, wq->len, wq->name, notify);
+                        (unsigned long) wq->wait_queue_token, wq->name.len,
+                        wq->name.name, notify);
 
                 /* autofs4_notify_daemon() may block */
                 autofs4_notify_daemon(sbi, wq, type);
         } else {
-                atomic_inc(&wq->wait_ctr);
+                wq->wait_ctr++;
                 mutex_unlock(&sbi->wq_mutex);
-                kfree(name);
+                kfree(qstr.name);
                 DPRINTK("existing wait id = 0x%08lx, name = %.*s, nfy=%d",
-                        (unsigned long) wq->wait_queue_token, wq->len, wq->name, notify);
-        }
-
-        /* wq->name is NULL if and only if the lock is already released */
-
-        if (sbi->catatonic) {
-                /* We might have slept, so check again for catatonic mode */
-                wq->status = -ENOENT;
-                kfree(wq->name);
-                wq->name = NULL;
+                        (unsigned long) wq->wait_queue_token, wq->name.len,
+                        wq->name.name, notify);
         }
 
-        if (wq->name) {
+        /*
+         * wq->name.name is NULL iff the lock is already released
+         * or the mount has been made catatonic.
+         */
+        if (wq->name.name) {
                 /* Block all but "shutdown" signals while waiting */
                 sigset_t oldset;
                 unsigned long irqflags;
@@ -351,7 +445,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
                 recalc_sigpending();
                 spin_unlock_irqrestore(&current->sighand->siglock, irqflags);
 
-                wait_event_interruptible(wq->queue, wq->name == NULL);
+                wait_event_interruptible(wq->queue, wq->name.name == NULL);
 
                 spin_lock_irqsave(&current->sighand->siglock, irqflags);
                 current->blocked = oldset;
@@ -364,8 +458,10 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
         status = wq->status;
 
         /* Are we the last process to need status? */
-        if (atomic_dec_and_test(&wq->wait_ctr))
+        mutex_lock(&sbi->wq_mutex);
+        if (!--wq->wait_ctr)
                 kfree(wq);
+        mutex_unlock(&sbi->wq_mutex);
 
         return status;
 }
@@ -387,16 +483,13 @@ int autofs4_wait_release(struct autofs_sb_info *sbi, autofs_wqt_t wait_queue_tok
         }
 
         *wql = wq->next;        /* Unlink from chain */
-        mutex_unlock(&sbi->wq_mutex);
-        kfree(wq->name);
-        wq->name = NULL;        /* Do not wait on this queue */
-
+        kfree(wq->name.name);
+        wq->name.name = NULL;   /* Do not wait on this queue */
         wq->status = status;
-
-        if (atomic_dec_and_test(&wq->wait_ctr)) /* Is anyone still waiting for this guy? */
+        wake_up_interruptible(&wq->queue);
+        if (!--wq->wait_ctr)
                 kfree(wq);
-        else
-                wake_up_interruptible(&wq->queue);
+        mutex_unlock(&sbi->wq_mutex);
 
         return 0;
 }
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index f1c2ea8342f5..5f1538c03b1b 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -243,8 +243,7 @@ static int bad_inode_readlink(struct dentry *dentry, char __user *buffer,
         return -EIO;
 }
 
-static int bad_inode_permission(struct inode *inode, int mask,
-                        struct nameidata *nd)
+static int bad_inode_permission(struct inode *inode, int mask)
 {
         return -EIO;
 }
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index e8717de3bab3..02c6e62b72f8 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -289,7 +289,7 @@ befs_destroy_inode(struct inode *inode)
         kmem_cache_free(befs_inode_cachep, BEFS_I(inode));
 }
 
-static void init_once(struct kmem_cache *cachep, void *foo)
+static void init_once(void *foo)
 {
         struct befs_inode_info *bi = (struct befs_inode_info *) foo;
 
diff --git a/fs/bfs/bfs.h b/fs/bfs/bfs.h
index 70f5d3a8eede..7109e451abf7 100644
--- a/fs/bfs/bfs.h
+++ b/fs/bfs/bfs.h
@@ -16,8 +16,9 @@ struct bfs_sb_info {
         unsigned long si_freei;
         unsigned long si_lf_eblk;
         unsigned long si_lasti;
-        unsigned long * si_imap;
-        struct buffer_head * si_sbh;            /* buffer header w/superblock */
+        unsigned long *si_imap;
+        struct buffer_head *si_sbh;             /* buffer header w/superblock */
+        struct mutex bfs_lock;
 };
 
 /*
diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c
index 034950cb3cbe..87ee5ccee348 100644
--- a/fs/bfs/dir.c
+++ b/fs/bfs/dir.c
@@ -32,16 +32,17 @@ static int bfs_readdir(struct file *f, void *dirent, filldir_t filldir)
         struct inode *dir = f->f_path.dentry->d_inode;
         struct buffer_head *bh;
         struct bfs_dirent *de;
+        struct bfs_sb_info *info = BFS_SB(dir->i_sb);
         unsigned int offset;
         int block;
 
-        lock_kernel();
+        mutex_lock(&info->bfs_lock);
 
         if (f->f_pos & (BFS_DIRENT_SIZE - 1)) {
                 printf("Bad f_pos=%08lx for %s:%08lx\n",
                                         (unsigned long)f->f_pos,
                                         dir->i_sb->s_id, dir->i_ino);
-                unlock_kernel();
+                mutex_unlock(&info->bfs_lock);
                 return -EBADF;
         }
 
@@ -61,7 +62,7 @@ static int bfs_readdir(struct file *f, void *dirent, filldir_t filldir)
                                                 le16_to_cpu(de->ino),
                                                 DT_UNKNOWN) < 0) {
                                         brelse(bh);
-                                        unlock_kernel();
+                                        mutex_unlock(&info->bfs_lock);
                                         return 0;
                                 }
                         }
@@ -71,7 +72,7 @@ static int bfs_readdir(struct file *f, void *dirent, filldir_t filldir)
                 brelse(bh);
         }
 
-        unlock_kernel();
+        mutex_unlock(&info->bfs_lock);
         return 0;       
 }
 
@@ -95,10 +96,10 @@ static int bfs_create(struct inode *dir, struct dentry *dentry, int mode,
         inode = new_inode(s);
         if (!inode)
                 return -ENOSPC;
-        lock_kernel();
+        mutex_lock(&info->bfs_lock);
         ino = find_first_zero_bit(info->si_imap, info->si_lasti);
         if (ino > info->si_lasti) {
-                unlock_kernel();
+                mutex_unlock(&info->bfs_lock);
                 iput(inode);
                 return -ENOSPC;
         }
@@ -125,10 +126,10 @@ static int bfs_create(struct inode *dir, struct dentry *dentry, int mode,
         if (err) {
                 inode_dec_link_count(inode);
                 iput(inode);
-                unlock_kernel();
+                mutex_unlock(&info->bfs_lock);
                 return err;
         }
-        unlock_kernel();
+        mutex_unlock(&info->bfs_lock);
         d_instantiate(dentry, inode);
         return 0;
 }
@@ -139,22 +140,23 @@ static struct dentry *bfs_lookup(struct inode *dir, struct dentry *dentry,
         struct inode *inode = NULL;
         struct buffer_head *bh;
         struct bfs_dirent *de;
+        struct bfs_sb_info *info = BFS_SB(dir->i_sb);
 
         if (dentry->d_name.len > BFS_NAMELEN)
                 return ERR_PTR(-ENAMETOOLONG);
 
-        lock_kernel();
+        mutex_lock(&info->bfs_lock);
         bh = bfs_find_entry(dir, dentry->d_name.name, dentry->d_name.len, &de);
         if (bh) {
                 unsigned long ino = (unsigned long)le16_to_cpu(de->ino);
                 brelse(bh);
                 inode = bfs_iget(dir->i_sb, ino);
                 if (IS_ERR(inode)) {
-                        unlock_kernel();
+                        mutex_unlock(&info->bfs_lock);
                         return ERR_CAST(inode);
                 }
         }
-        unlock_kernel();
+        mutex_unlock(&info->bfs_lock);
         d_add(dentry, inode);
         return NULL;
 }
@@ -163,13 +165,14 @@ static int bfs_link(struct dentry *old, struct inode *dir,
                                                 struct dentry *new)
 {
         struct inode *inode = old->d_inode;
+        struct bfs_sb_info *info = BFS_SB(inode->i_sb);
         int err;
 
-        lock_kernel();
+        mutex_lock(&info->bfs_lock);
         err = bfs_add_entry(dir, new->d_name.name, new->d_name.len,
                                                         inode->i_ino);
         if (err) {
-                unlock_kernel();
+                mutex_unlock(&info->bfs_lock);
                 return err;
         }
         inc_nlink(inode);
@@ -177,19 +180,19 @@ static int bfs_link(struct dentry *old, struct inode *dir,
         mark_inode_dirty(inode);
         atomic_inc(&inode->i_count);
         d_instantiate(new, inode);
-        unlock_kernel();
+        mutex_unlock(&info->bfs_lock);
         return 0;
 }
 
 static int bfs_unlink(struct inode *dir, struct dentry *dentry)
 {
         int error = -ENOENT;
-        struct inode *inode;
+        struct inode *inode = dentry->d_inode;
         struct buffer_head *bh;
         struct bfs_dirent *de;
+        struct bfs_sb_info *info = BFS_SB(inode->i_sb);
 
-        inode = dentry->d_inode;
-        lock_kernel();
+        mutex_lock(&info->bfs_lock);
         bh = bfs_find_entry(dir, dentry->d_name.name, dentry->d_name.len, &de);
         if (!bh || (le16_to_cpu(de->ino) != inode->i_ino))
                 goto out_brelse;
@@ -210,7 +213,7 @@ static int bfs_unlink(struct inode *dir, struct dentry *dentry)
 
 out_brelse:
         brelse(bh);
-        unlock_kernel();
+        mutex_unlock(&info->bfs_lock);
         return error;
 }
 
@@ -220,6 +223,7 @@ static int bfs_rename(struct inode *old_dir, struct dentry *old_dentry,
         struct inode *old_inode, *new_inode;
         struct buffer_head *old_bh, *new_bh;
         struct bfs_dirent *old_de, *new_de;
+        struct bfs_sb_info *info;
         int error = -ENOENT;
 
         old_bh = new_bh = NULL;
@@ -227,7 +231,9 @@ static int bfs_rename(struct inode *old_dir, struct dentry *old_dentry,
         if (S_ISDIR(old_inode->i_mode))
                 return -EINVAL;
 
-        lock_kernel();
+        info = BFS_SB(old_inode->i_sb);
+
+        mutex_lock(&info->bfs_lock);
         old_bh = bfs_find_entry(old_dir, 
                                 old_dentry->d_name.name, 
                                 old_dentry->d_name.len, &old_de);
@@ -264,7 +270,7 @@ static int bfs_rename(struct inode *old_dir, struct dentry *old_dentry,
         error = 0;
 
 end_rename:
-        unlock_kernel();
+        mutex_unlock(&info->bfs_lock);
         brelse(old_bh);
         brelse(new_bh);
         return error;
diff --git a/fs/bfs/file.c b/fs/bfs/file.c
index b11e63e8fbcd..6a021265f018 100644
--- a/fs/bfs/file.c
+++ b/fs/bfs/file.c
@@ -99,7 +99,7 @@ static int bfs_get_block(struct inode *inode, sector_t block,
                 return -ENOSPC;
 
         /* The rest has to be protected against itself. */
-        lock_kernel();
+        mutex_lock(&info->bfs_lock);
 
         /*
          * If the last data block for this file is the last allocated
@@ -151,7 +151,7 @@ static int bfs_get_block(struct inode *inode, sector_t block,
         mark_buffer_dirty(sbh);
         map_bh(bh_result, sb, phys);
 out:
-        unlock_kernel();
+        mutex_unlock(&info->bfs_lock);
         return err;
 }
 
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index 8db623838b50..0ed57b5ee012 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -104,6 +104,7 @@ static int bfs_write_inode(struct inode *inode, int unused)
         struct bfs_inode *di;
         struct buffer_head *bh;
         int block, off;
+        struct bfs_sb_info *info = BFS_SB(inode->i_sb);
 
         dprintf("ino=%08x\n", ino);
 
@@ -112,13 +113,13 @@ static int bfs_write_inode(struct inode *inode, int unused)
                 return -EIO;
         }
 
-        lock_kernel();
+        mutex_lock(&info->bfs_lock);
         block = (ino - BFS_ROOT_INO) / BFS_INODES_PER_BLOCK + 1;
         bh = sb_bread(inode->i_sb, block);
         if (!bh) {
                 printf("Unable to read inode %s:%08x\n",
                                 inode->i_sb->s_id, ino);
-                unlock_kernel();
+                mutex_unlock(&info->bfs_lock);
                 return -EIO;
         }
 
@@ -145,7 +146,7 @@ static int bfs_write_inode(struct inode *inode, int unused)
 
         mark_buffer_dirty(bh);
         brelse(bh);
-        unlock_kernel();
+        mutex_unlock(&info->bfs_lock);
         return 0;
 }
 
@@ -170,7 +171,7 @@ static void bfs_delete_inode(struct inode *inode)
         
         inode->i_size = 0;
         inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC;
-        lock_kernel();
+        mutex_lock(&info->bfs_lock);
         mark_inode_dirty(inode);
 
         block = (ino - BFS_ROOT_INO) / BFS_INODES_PER_BLOCK + 1;
@@ -178,7 +179,7 @@ static void bfs_delete_inode(struct inode *inode)
         if (!bh) {
                 printf("Unable to read inode %s:%08lx\n",
                                         inode->i_sb->s_id, ino);
-                unlock_kernel();
+                mutex_unlock(&info->bfs_lock);
                 return;
         }
         off = (ino - BFS_ROOT_INO) % BFS_INODES_PER_BLOCK;
@@ -204,14 +205,16 @@ static void bfs_delete_inode(struct inode *inode)
                 info->si_lf_eblk = bi->i_sblock - 1;
                 mark_buffer_dirty(info->si_sbh);
         }
-        unlock_kernel();
+        mutex_unlock(&info->bfs_lock);
         clear_inode(inode);
 }
 
 static void bfs_put_super(struct super_block *s)
 {
         struct bfs_sb_info *info = BFS_SB(s);
+
         brelse(info->si_sbh);
+        mutex_destroy(&info->bfs_lock);
         kfree(info->si_imap);
         kfree(info);
         s->s_fs_info = NULL;
@@ -236,11 +239,13 @@ static int bfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 static void bfs_write_super(struct super_block *s)
 {
-        lock_kernel();
+        struct bfs_sb_info *info = BFS_SB(s);
+
+        mutex_lock(&info->bfs_lock);
         if (!(s->s_flags & MS_RDONLY))
-                mark_buffer_dirty(BFS_SB(s)->si_sbh);
+                mark_buffer_dirty(info->si_sbh);
         s->s_dirt = 0;
-        unlock_kernel();
+        mutex_unlock(&info->bfs_lock);
 }
 
 static struct kmem_cache *bfs_inode_cachep;
@@ -259,7 +264,7 @@ static void bfs_destroy_inode(struct inode *inode)
         kmem_cache_free(bfs_inode_cachep, BFS_I(inode));
 }
 
-static void init_once(struct kmem_cache *cachep, void *foo)
+static void init_once(void *foo)
 {
         struct bfs_inode_info *bi = foo;
 
@@ -380,7 +385,7 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent)
                 struct bfs_inode *di;
                 int block = (i - BFS_ROOT_INO) / BFS_INODES_PER_BLOCK + 1;
                 int off = (i - BFS_ROOT_INO) % BFS_INODES_PER_BLOCK;
-                unsigned long sblock, eblock;
+                unsigned long eblock;
 
                 if (!off) {
                         brelse(bh);
@@ -399,7 +404,6 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent)
                 set_bit(i, info->si_imap);
                 info->si_freeb -= BFS_FILEBLOCKS(di);
 
-                sblock =  le32_to_cpu(di->i_sblock);
                 eblock =  le32_to_cpu(di->i_eblock);
                 if (eblock > info->si_lf_eblk)
                         info->si_lf_eblk = eblock;
@@ -410,6 +414,7 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent)
                 s->s_dirt = 1;
         } 
         dump_imap("read_super", s);
+        mutex_init(&info->bfs_lock);
         return 0;
 
 out:
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index ba4cddb92f1d..204cfd1d7676 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -444,12 +444,6 @@ beyond_if:
         regs->gp = ex.a_gpvalue;
 #endif
         start_thread(regs, ex.a_entry, current->mm->start_stack);
-        if (unlikely(current->ptrace & PT_PTRACED)) {
-                if (current->ptrace & PT_TRACE_EXEC)
-                        ptrace_notify ((PTRACE_EVENT_EXEC << 8) | SIGTRAP);
-                else
-                        send_sig(SIGTRAP, current, 0);
-        }
         return 0;
 }
 
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index d48ff5f370f4..655ed8d30a86 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -131,6 +131,15 @@ static int padzero(unsigned long elf_bss)
 #define STACK_ALLOC(sp, len) ({ sp -= len ; sp; })
 #endif
 
+#ifndef ELF_BASE_PLATFORM
+/*
+ * AT_BASE_PLATFORM indicates the "real" hardware/microarchitecture.
+ * If the arch defines ELF_BASE_PLATFORM (in asm/elf.h), the value
+ * will be copied to the user stack in the same manner as AT_PLATFORM.
+ */
+#define ELF_BASE_PLATFORM NULL
+#endif
+
 static int
 create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
                 unsigned long load_addr, unsigned long interp_load_addr)
@@ -142,7 +151,9 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
         elf_addr_t __user *envp;
         elf_addr_t __user *sp;
         elf_addr_t __user *u_platform;
+        elf_addr_t __user *u_base_platform;
         const char *k_platform = ELF_PLATFORM;
+        const char *k_base_platform = ELF_BASE_PLATFORM;
         int items;
         elf_addr_t *elf_info;
         int ei_index = 0;
@@ -172,6 +183,19 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
                         return -EFAULT;
         }
 
+        /*
+         * If this architecture has a "base" platform capability
+         * string, copy it to userspace.
+         */
+        u_base_platform = NULL;
+        if (k_base_platform) {
+                size_t len = strlen(k_base_platform) + 1;
+
+                u_base_platform = (elf_addr_t __user *)STACK_ALLOC(p, len);
+                if (__copy_to_user(u_base_platform, k_base_platform, len))
+                        return -EFAULT;
+        }
+
         /* Create the ELF interpreter info */
         elf_info = (elf_addr_t *)current->mm->saved_auxv;
         /* update AT_VECTOR_SIZE_BASE if the number of NEW_AUX_ENT() changes */
@@ -204,10 +228,15 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
         NEW_AUX_ENT(AT_GID, tsk->gid);
         NEW_AUX_ENT(AT_EGID, tsk->egid);
         NEW_AUX_ENT(AT_SECURE, security_bprm_secureexec(bprm));
+        NEW_AUX_ENT(AT_EXECFN, bprm->exec);
         if (k_platform) {
                 NEW_AUX_ENT(AT_PLATFORM,
                             (elf_addr_t)(unsigned long)u_platform);
         }
+        if (k_base_platform) {
+                NEW_AUX_ENT(AT_BASE_PLATFORM,
+                            (elf_addr_t)(unsigned long)u_base_platform);
+        }
         if (bprm->interp_flags & BINPRM_FLAGS_EXECFD) {
                 NEW_AUX_ENT(AT_EXECFD, bprm->interp_data);
         }
@@ -974,12 +1003,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 #endif
 
         start_thread(regs, elf_entry, bprm->p);
-        if (unlikely(current->ptrace & PT_PTRACED)) {
-                if (current->ptrace & PT_TRACE_EXEC)
-                        ptrace_notify ((PTRACE_EVENT_EXEC << 8) | SIGTRAP);
-                else
-                        send_sig(SIGTRAP, current, 0);
-        }
         retval = 0;
 out:
         kfree(loc);
@@ -1477,7 +1500,7 @@ static int fill_note_info(struct elfhdr *elf, int phdrs,
         const struct user_regset_view *view = task_user_regset_view(dump_task);
         struct elf_thread_core_info *t;
         struct elf_prpsinfo *psinfo;
-        struct task_struct *g, *p;
+        struct core_thread *ct;
         unsigned int i;
 
         info->size = 0;
@@ -1516,31 +1539,26 @@ static int fill_note_info(struct elfhdr *elf, int phdrs,
         /*
          * Allocate a structure for each thread.
          */
-        rcu_read_lock();
-        do_each_thread(g, p)
-                if (p->mm == dump_task->mm) {
-                        t = kzalloc(offsetof(struct elf_thread_core_info,
-                                             notes[info->thread_notes]),
-                                    GFP_ATOMIC);
-                        if (unlikely(!t)) {
-                                rcu_read_unlock();
-                                return 0;
-                        }
-                        t->task = p;
-                        if (p == dump_task || !info->thread) {
-                                t->next = info->thread;
-                                info->thread = t;
-                        } else {
-                                /*
-                                 * Make sure to keep the original task at
-                                 * the head of the list.
-                                 */
-                                t->next = info->thread->next;
-                                info->thread->next = t;
-                        }
+        for (ct = &dump_task->mm->core_state->dumper; ct; ct = ct->next) {
+                t = kzalloc(offsetof(struct elf_thread_core_info,
+                                     notes[info->thread_notes]),
+                            GFP_KERNEL);
+                if (unlikely(!t))
+                        return 0;
+
+                t->task = ct->task;
+                if (ct->task == dump_task || !info->thread) {
+                        t->next = info->thread;
+                        info->thread = t;
+                } else {
+                        /*
+                         * Make sure to keep the original task at
+                         * the head of the list.
+                         */
+                        t->next = info->thread->next;
+                        info->thread->next = t;
                 }
-        while_each_thread(g, p);
-        rcu_read_unlock();
+        }
 
         /*
          * Now fill in each thread's information.
@@ -1687,7 +1705,6 @@ static int fill_note_info(struct elfhdr *elf, int phdrs,
 {
 #define NUM_NOTES       6
         struct list_head *t;
-        struct task_struct *g, *p;
 
         info->notes = NULL;
         info->prstatus = NULL;
@@ -1719,20 +1736,19 @@ static int fill_note_info(struct elfhdr *elf, int phdrs,
 
         info->thread_status_size = 0;
         if (signr) {
+                struct core_thread *ct;
                 struct elf_thread_status *ets;
-                rcu_read_lock();
-                do_each_thread(g, p)
-                        if (current->mm == p->mm && current != p) {
-                                ets = kzalloc(sizeof(*ets), GFP_ATOMIC);
-                                if (!ets) {
-                                        rcu_read_unlock();
-                                        return 0;
-                                }
-                                ets->thread = p;
-                                list_add(&ets->list, &info->thread_list);
-                        }
-                while_each_thread(g, p);
-                rcu_read_unlock();
+
+                for (ct = current->mm->core_state->dumper.next;
+                                                ct; ct = ct->next) {
+                        ets = kzalloc(sizeof(*ets), GFP_KERNEL);
+                        if (!ets)
+                                return 0;
+
+                        ets->thread = ct->task;
+                        list_add(&ets->list, &info->thread_list);
+                }
+
                 list_for_each(t, &info->thread_list) {
                         int sz;
 
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index d051a32e6270..80c1f952ef78 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -433,13 +433,6 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm,
         entryaddr = interp_params.entry_addr ?: exec_params.entry_addr;
         start_thread(regs, entryaddr, current->mm->start_stack);
 
-        if (unlikely(current->ptrace & PT_PTRACED)) {
-                if (current->ptrace & PT_TRACE_EXEC)
-                        ptrace_notify((PTRACE_EVENT_EXEC << 8) | SIGTRAP);
-                else
-                        send_sig(SIGTRAP, current, 0);
-        }
-
         retval = 0;
 
 error:
@@ -477,6 +470,7 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
         char __user *u_platform, *p;
         long hwcap;
         int loop;
+        int nr; /* reset for each csp adjustment */
 
         /* we're going to shovel a whole load of stuff onto the stack */
 #ifdef CONFIG_MMU
@@ -549,10 +543,7 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
         /* force 16 byte _final_ alignment here for generality */
 #define DLINFO_ITEMS 13
 
-        nitems = 1 + DLINFO_ITEMS + (k_platform ? 1 : 0);
-#ifdef DLINFO_ARCH_ITEMS
-        nitems += DLINFO_ARCH_ITEMS;
-#endif
+        nitems = 1 + DLINFO_ITEMS + (k_platform ? 1 : 0) + AT_VECTOR_SIZE_ARCH;
 
         csp = sp;
         sp -= nitems * 2 * sizeof(unsigned long);
@@ -564,39 +555,46 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
         sp -= sp & 15UL;
 
         /* put the ELF interpreter info on the stack */
-#define NEW_AUX_ENT(nr, id, val)                                        \
+#define NEW_AUX_ENT(id, val)                                            \
         do {                                                            \
                 struct { unsigned long _id, _val; } __user *ent;        \
                                                                         \
                 ent = (void __user *) csp;                              \
                 __put_user((id), &ent[nr]._id);                         \
                 __put_user((val), &ent[nr]._val);                       \
+                nr++;                                                   \
         } while (0)
 
+        nr = 0;
         csp -= 2 * sizeof(unsigned long);
-        NEW_AUX_ENT(0, AT_NULL, 0);
+        NEW_AUX_ENT(AT_NULL, 0);
         if (k_platform) {
+                nr = 0;
                 csp -= 2 * sizeof(unsigned long);
-                NEW_AUX_ENT(0, AT_PLATFORM,
+                NEW_AUX_ENT(AT_PLATFORM,
                             (elf_addr_t) (unsigned long) u_platform);
         }
 
+        nr = 0;
         csp -= DLINFO_ITEMS * 2 * sizeof(unsigned long);
-        NEW_AUX_ENT( 0, AT_HWCAP,       hwcap);
-        NEW_AUX_ENT( 1, AT_PAGESZ,      PAGE_SIZE);
-        NEW_AUX_ENT( 2, AT_CLKTCK,      CLOCKS_PER_SEC);
-        NEW_AUX_ENT( 3, AT_PHDR,        exec_params->ph_addr);
-        NEW_AUX_ENT( 4, AT_PHENT,       sizeof(struct elf_phdr));
-        NEW_AUX_ENT( 5, AT_PHNUM,       exec_params->hdr.e_phnum);
-        NEW_AUX_ENT( 6, AT_BASE,        interp_params->elfhdr_addr);
-        NEW_AUX_ENT( 7, AT_FLAGS,       0);
-        NEW_AUX_ENT( 8, AT_ENTRY,       exec_params->entry_addr);
-        NEW_AUX_ENT( 9, AT_UID,         (elf_addr_t) current->uid);
-        NEW_AUX_ENT(10, AT_EUID,        (elf_addr_t) current->euid);
-        NEW_AUX_ENT(11, AT_GID,         (elf_addr_t) current->gid);
-        NEW_AUX_ENT(12, AT_EGID,        (elf_addr_t) current->egid);
+        NEW_AUX_ENT(AT_HWCAP,   hwcap);
+        NEW_AUX_ENT(AT_PAGESZ,  PAGE_SIZE);
+        NEW_AUX_ENT(AT_CLKTCK,  CLOCKS_PER_SEC);
+        NEW_AUX_ENT(AT_PHDR,    exec_params->ph_addr);
+        NEW_AUX_ENT(AT_PHENT,   sizeof(struct elf_phdr));
+        NEW_AUX_ENT(AT_PHNUM,   exec_params->hdr.e_phnum);
+        NEW_AUX_ENT(AT_BASE,    interp_params->elfhdr_addr);
+        NEW_AUX_ENT(AT_FLAGS,   0);
+        NEW_AUX_ENT(AT_ENTRY,   exec_params->entry_addr);
+        NEW_AUX_ENT(AT_UID,     (elf_addr_t) current->uid);
+        NEW_AUX_ENT(AT_EUID,    (elf_addr_t) current->euid);
+        NEW_AUX_ENT(AT_GID,     (elf_addr_t) current->gid);
+        NEW_AUX_ENT(AT_EGID,    (elf_addr_t) current->egid);
 
 #ifdef ARCH_DLINFO
+        nr = 0;
+        csp -= AT_VECTOR_SIZE_ARCH * 2 * sizeof(unsigned long);
+
         /* ARCH_DLINFO must come last so platform specific code can enforce
          * special alignment requirements on the AUXV if necessary (eg. PPC).
          */
@@ -1573,7 +1571,6 @@ static int elf_fdpic_core_dump(long signr, struct pt_regs *regs,
         struct memelfnote *notes = NULL;
         struct elf_prstatus *prstatus = NULL;   /* NT_PRSTATUS */
         struct elf_prpsinfo *psinfo = NULL;     /* NT_PRPSINFO */
-        struct task_struct *g, *p;
         LIST_HEAD(thread_list);
         struct list_head *t;
         elf_fpregset_t *fpu = NULL;
@@ -1622,20 +1619,19 @@ static int elf_fdpic_core_dump(long signr, struct pt_regs *regs,
 #endif
 
         if (signr) {
+                struct core_thread *ct;
                 struct elf_thread_status *tmp;
-                rcu_read_lock();
-                do_each_thread(g,p)
-                        if (current->mm == p->mm && current != p) {
-                                tmp = kzalloc(sizeof(*tmp), GFP_ATOMIC);
-                                if (!tmp) {
-                                        rcu_read_unlock();
-                                        goto cleanup;
-                                }
-                                tmp->thread = p;
-                                list_add(&tmp->list, &thread_list);
-                        }
-                while_each_thread(g,p);
-                rcu_read_unlock();
+
+                for (ct = current->mm->core_state->dumper.next;
+                                                ct; ct = ct->next) {
+                        tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
+                        if (!tmp)
+                                goto cleanup;
+
+                        tmp->thread = ct->task;
+                        list_add(&tmp->list, &thread_list);
+                }
+
                 list_for_each(t, &thread_list) {
                         struct elf_thread_status *tmp;
                         int sz;
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index 2cb1acda3a82..56372ecf1690 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -920,9 +920,6 @@ static int load_flat_binary(struct linux_binprm * bprm, struct pt_regs * regs)
         
         start_thread(regs, start_addr, current->mm->start_stack);
 
-        if (current->ptrace & PT_PTRACED)
-                send_sig(SIGTRAP, current, 0);
-
         return 0;
 }
 
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 7191306367c5..756205314c24 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -27,6 +27,7 @@
 #include <linux/namei.h>
 #include <linux/mount.h>
 #include <linux/syscalls.h>
+#include <linux/fs.h>
 
 #include <asm/uaccess.h>
 
@@ -535,31 +536,16 @@ static ssize_t
 bm_entry_read(struct file * file, char __user * buf, size_t nbytes, loff_t *ppos)
 {
         Node *e = file->f_path.dentry->d_inode->i_private;
-        loff_t pos = *ppos;
         ssize_t res;
         char *page;
-        int len;
 
         if (!(page = (char*) __get_free_page(GFP_KERNEL)))
                 return -ENOMEM;
 
         entry_status(e, page);
-        len = strlen(page);
 
-        res = -EINVAL;
-        if (pos < 0)
-                goto out;
-        res = 0;
-        if (pos >= len)
-                goto out;
-        if (len < pos + nbytes)
-                nbytes = len - pos;
-        res = -EFAULT;
-        if (copy_to_user(buf, page + pos, nbytes))
-                goto out;
-        *ppos = pos + nbytes;
-        res = nbytes;
-out:
+        res = simple_read_from_buffer(buf, nbytes, ppos, page, strlen(page));
+
         free_page((unsigned long) page);
         return res;
 }
diff --git a/fs/binfmt_som.c b/fs/binfmt_som.c
index fdc36bfd6a7b..68be580ba289 100644
--- a/fs/binfmt_som.c
+++ b/fs/binfmt_som.c
@@ -274,8 +274,6 @@ load_som_binary(struct linux_binprm * bprm, struct pt_regs * regs)
         map_hpux_gateway_page(current,current->mm);
 
         start_thread_som(regs, som_entry, bprm->p);
-        if (current->ptrace & PT_PTRACED)
-                send_sig(SIGTRAP, current, 0);
         return 0;
 
         /* error cleanup */
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index 63e2ee63058d..c3e174b35fe6 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -705,7 +705,6 @@ void __init bio_integrity_init_slab(void)
         bio_integrity_slab = KMEM_CACHE(bio_integrity_payload,
                                         SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 }
-EXPORT_SYMBOL(bio_integrity_init_slab);
 
 static int __init integrity_init(void)
 {
diff --git a/fs/bio.c b/fs/bio.c
index 88322b066acb..8000e2fa16cb 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -77,11 +77,8 @@ struct bio_vec *bvec_alloc_bs(gfp_t gfp_mask, int nr, unsigned long *idx, struct
          */
 
         bvl = mempool_alloc(bs->bvec_pools[*idx], gfp_mask);
-        if (bvl) {
-                struct biovec_slab *bp = bvec_slabs + *idx;
-
-                memset(bvl, 0, bp->nr_vecs * sizeof(struct bio_vec));
-        }
+        if (bvl)
+                memset(bvl, 0, bvec_nr_vecs(*idx) * sizeof(struct bio_vec));
 
         return bvl;
 }
@@ -149,7 +146,7 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
                                 goto out;
                         }
                         bio->bi_flags |= idx << BIO_POOL_OFFSET;
-                        bio->bi_max_vecs = bvec_slabs[idx].nr_vecs;
+                        bio->bi_max_vecs = bvec_nr_vecs(idx);
                 }
                 bio->bi_io_vec = bvl;
         }
@@ -721,12 +718,8 @@ static struct bio *__bio_map_user_iov(struct request_queue *q,
                 const int local_nr_pages = end - start;
                 const int page_limit = cur_page + local_nr_pages;
                 
-                down_read(&current->mm->mmap_sem);
-                ret = get_user_pages(current, current->mm, uaddr,
-                                     local_nr_pages,
-                                     write_to_vm, 0, &pages[cur_page], NULL);
-                up_read(&current->mm->mmap_sem);
-
+                ret = get_user_pages_fast(uaddr, local_nr_pages,
+                                write_to_vm, &pages[cur_page]);
                 if (ret < local_nr_pages) {
                         ret = -EFAULT;
                         goto out_unmap;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 10d8a0aa871a..aff54219e049 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -271,7 +271,7 @@ static void bdev_destroy_inode(struct inode *inode)
         kmem_cache_free(bdev_cachep, bdi);
 }
 
-static void init_once(struct kmem_cache * cachep, void *foo)
+static void init_once(void *foo)
 {
         struct bdev_inode *ei = (struct bdev_inode *) foo;
         struct block_device *bdev = &ei->bdev;
@@ -941,8 +941,10 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
          * hooks: /n/, see "layering violations".
          */
         ret = devcgroup_inode_permission(bdev->bd_inode, perm);
-        if (ret != 0)
+        if (ret != 0) {
+                bdput(bdev);
                 return ret;
+        }
 
         ret = -ENXIO;
         file->f_mapping = bdev->bd_inode->i_mapping;
@@ -1234,6 +1236,7 @@ fail:
         bdev = ERR_PTR(error);
         goto out;
 }
+EXPORT_SYMBOL(lookup_bdev);
 
 /**
  * open_bdev_excl  -  open a block device by name and set it up for use
diff --git a/fs/buffer.c b/fs/buffer.c
index d48caee12e2a..38653e36e225 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -580,7 +580,7 @@ EXPORT_SYMBOL(mark_buffer_async_write);
 /*
  * The buffer's backing address_space's private_lock must be held
  */
-static inline void __remove_assoc_queue(struct buffer_head *bh)
+static void __remove_assoc_queue(struct buffer_head *bh)
 {
         list_del_init(&bh->b_assoc_buffers);
         WARN_ON(!bh->b_assoc_map);
@@ -706,7 +706,7 @@ static int __set_page_dirty(struct page *page,
         if (TestSetPageDirty(page))
                 return 0;
 
-        write_lock_irq(&mapping->tree_lock);
+        spin_lock_irq(&mapping->tree_lock);
         if (page->mapping) {    /* Race with truncate? */
                 WARN_ON_ONCE(warn && !PageUptodate(page));
 
@@ -719,7 +719,7 @@ static int __set_page_dirty(struct page *page,
                 radix_tree_tag_set(&mapping->page_tree,
                                 page_index(page), PAGECACHE_TAG_DIRTY);
         }
-        write_unlock_irq(&mapping->tree_lock);
+        spin_unlock_irq(&mapping->tree_lock);
         __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 
         return 1;
@@ -1214,8 +1214,7 @@ void __brelse(struct buffer_head * buf)
                 put_bh(buf);
                 return;
         }
-        printk(KERN_ERR "VFS: brelse: Trying to free free buffer\n");
-        WARN_ON(1);
+        WARN(1, KERN_ERR "VFS: brelse: Trying to free free buffer\n");
 }
 
 /*
@@ -1721,7 +1720,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
                  */
                 if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) {
                         lock_buffer(bh);
-                } else if (test_set_buffer_locked(bh)) {
+                } else if (!trylock_buffer(bh)) {
                         redirty_page_for_writepage(wbc, page);
                         continue;
                 }
@@ -2097,6 +2096,52 @@ int generic_write_end(struct file *file, struct address_space *mapping,
 EXPORT_SYMBOL(generic_write_end);
 
 /*
+ * block_is_partially_uptodate checks whether buffers within a page are
+ * uptodate or not.
+ *
+ * Returns true if all buffers which correspond to a file portion
+ * we want to read are uptodate.
+ */
+int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
+                                        unsigned long from)
+{
+        struct inode *inode = page->mapping->host;
+        unsigned block_start, block_end, blocksize;
+        unsigned to;
+        struct buffer_head *bh, *head;
+        int ret = 1;
+
+        if (!page_has_buffers(page))
+                return 0;
+
+        blocksize = 1 << inode->i_blkbits;
+        to = min_t(unsigned, PAGE_CACHE_SIZE - from, desc->count);
+        to = from + to;
+        if (from < blocksize && to > PAGE_CACHE_SIZE - blocksize)
+                return 0;
+
+        head = page_buffers(page);
+        bh = head;
+        block_start = 0;
+        do {
+                block_end = block_start + blocksize;
+                if (block_end > from && block_start < to) {
+                        if (!buffer_uptodate(bh)) {
+                                ret = 0;
+                                break;
+                        }
+                        if (block_end >= to)
+                                break;
+                }
+                block_start = block_end;
+                bh = bh->b_this_page;
+        } while (bh != head);
+
+        return ret;
+}
+EXPORT_SYMBOL(block_is_partially_uptodate);
+
+/*
  * Generic "read page" function for block devices that have the normal
  * get_block functionality. This is most of the block device filesystems.
  * Reads the page asynchronously --- the unlock_buffer() and
@@ -2955,7 +3000,7 @@ void ll_rw_block(int rw, int nr, struct buffer_head *bhs[])
 
                 if (rw == SWRITE || rw == SWRITE_SYNC)
                         lock_buffer(bh);
-                else if (test_set_buffer_locked(bh))
+                else if (!trylock_buffer(bh))
                         continue;
 
                 if (rw == WRITE || rw == SWRITE || rw == SWRITE_SYNC) {
@@ -3272,7 +3317,7 @@ int bh_submit_read(struct buffer_head *bh)
 EXPORT_SYMBOL(bh_submit_read);
 
 static void
-init_buffer_head(struct kmem_cache *cachep, void *data)
+init_buffer_head(void *data)
 {
         struct buffer_head *bh = data;
 
diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES
index 1f3465201fdf..f5d0083e09fa 100644
--- a/fs/cifs/CHANGES
+++ b/fs/cifs/CHANGES
@@ -1,3 +1,11 @@
+Version 1.54
+------------
+Fix premature write failure on congested networks (we would give up
+on EAGAIN from the socket too quickly on large writes).
+Cifs_mkdir and cifs_create now respect the setgid bit on parent dir.
+Fix endian problems in acl (mode from/to cifs acl) on bigendian
+architectures.
+
 Version 1.53
 ------------
 DFS support added (Microsoft Distributed File System client support needed
diff --git a/fs/cifs/asn1.c b/fs/cifs/asn1.c
index f58e41d3ba48..5fabd2caf93c 100644
--- a/fs/cifs/asn1.c
+++ b/fs/cifs/asn1.c
@@ -400,7 +400,7 @@ asn1_oid_decode(struct asn1_ctx *ctx,
         size = eoc - ctx->pointer + 1;
 
         /* first subid actually encodes first two subids */
-        if (size < 2 || size > ULONG_MAX/sizeof(unsigned long))
+        if (size < 2 || size > UINT_MAX/sizeof(unsigned long))
                 return 0;
 
         *oid = kmalloc(size * sizeof(unsigned long), GFP_ATOMIC);
@@ -483,6 +483,7 @@ decode_negTokenInit(unsigned char *security_blob, int length,
 
         asn1_open(&ctx, security_blob, length);
 
+        /* GSSAPI header */
         if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
                 cFYI(1, ("Error decoding negTokenInit header"));
                 return 0;
@@ -490,153 +491,142 @@ decode_negTokenInit(unsigned char *security_blob, int length,
                    || (tag != ASN1_EOC)) {
                 cFYI(1, ("cls = %d con = %d tag = %d", cls, con, tag));
                 return 0;
-        } else {
-                /*      remember to free obj->oid */
-                rc = asn1_header_decode(&ctx, &end, &cls, &con, &tag);
-                if (rc) {
-                        if ((tag == ASN1_OJI) && (cls == ASN1_PRI)) {
-                                rc = asn1_oid_decode(&ctx, end, &oid, &oidlen);
-                                if (rc) {
-                                        rc = compare_oid(oid, oidlen,
-                                                         SPNEGO_OID,
-                                                         SPNEGO_OID_LEN);
-                                        kfree(oid);
-                                }
-                        } else
-                                rc = 0;
-                }
+        }
 
-                if (!rc) {
-                        cFYI(1, ("Error decoding negTokenInit header"));
-                        return 0;
-                }
+        /* Check for SPNEGO OID -- remember to free obj->oid */
+        rc = asn1_header_decode(&ctx, &end, &cls, &con, &tag);
+        if (rc) {
+                if ((tag == ASN1_OJI) && (con == ASN1_PRI) &&
+                    (cls == ASN1_UNI)) {
+                        rc = asn1_oid_decode(&ctx, end, &oid, &oidlen);
+                        if (rc) {
+                                rc = compare_oid(oid, oidlen, SPNEGO_OID,
+                                                 SPNEGO_OID_LEN);
+                                kfree(oid);
+                        }
+                } else
+                        rc = 0;
+        }
 
-                if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-                        cFYI(1, ("Error decoding negTokenInit"));
-                        return 0;
-                } else if ((cls != ASN1_CTX) || (con != ASN1_CON)
-                           || (tag != ASN1_EOC)) {
-                        cFYI(1,
-                             ("cls = %d con = %d tag = %d end = %p (%d) exit 0",
-                              cls, con, tag, end, *end));
-                        return 0;
-                }
+        /* SPNEGO OID not present or garbled -- bail out */
+        if (!rc) {
+                cFYI(1, ("Error decoding negTokenInit header"));
+                return 0;
+        }
 
-                if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-                        cFYI(1, ("Error decoding negTokenInit"));
-                        return 0;
-                } else if ((cls != ASN1_UNI) || (con != ASN1_CON)
-                           || (tag != ASN1_SEQ)) {
-                        cFYI(1,
-                             ("cls = %d con = %d tag = %d end = %p (%d) exit 1",
-                              cls, con, tag, end, *end));
-                        return 0;
-                }
+        if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
+                cFYI(1, ("Error decoding negTokenInit"));
+                return 0;
+        } else if ((cls != ASN1_CTX) || (con != ASN1_CON)
+                   || (tag != ASN1_EOC)) {
+                cFYI(1,
+                     ("cls = %d con = %d tag = %d end = %p (%d) exit 0",
+                      cls, con, tag, end, *end));
+                return 0;
+        }
 
-                if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-                        cFYI(1, ("Error decoding 2nd part of negTokenInit"));
-                        return 0;
-                } else if ((cls != ASN1_CTX) || (con != ASN1_CON)
-                           || (tag != ASN1_EOC)) {
-                        cFYI(1,
-                             ("cls = %d con = %d tag = %d end = %p (%d) exit 0",
-                              cls, con, tag, end, *end));
-                        return 0;
-                }
+        if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
+                cFYI(1, ("Error decoding negTokenInit"));
+                return 0;
+        } else if ((cls != ASN1_UNI) || (con != ASN1_CON)
+                   || (tag != ASN1_SEQ)) {
+                cFYI(1,
+                     ("cls = %d con = %d tag = %d end = %p (%d) exit 1",
+                      cls, con, tag, end, *end));
+                return 0;
+        }
 
-                if (asn1_header_decode
-                    (&ctx, &sequence_end, &cls, &con, &tag) == 0) {
-                        cFYI(1, ("Error decoding 2nd part of negTokenInit"));
-                        return 0;
-                } else if ((cls != ASN1_UNI) || (con != ASN1_CON)
-                           || (tag != ASN1_SEQ)) {
-                        cFYI(1,
-                             ("cls = %d con = %d tag = %d end = %p (%d) exit 1",
-                              cls, con, tag, end, *end));
-                        return 0;
-                }
+        if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
+                cFYI(1, ("Error decoding 2nd part of negTokenInit"));
+                return 0;
+        } else if ((cls != ASN1_CTX) || (con != ASN1_CON)
+                   || (tag != ASN1_EOC)) {
+                cFYI(1,
+                     ("cls = %d con = %d tag = %d end = %p (%d) exit 0",
+                      cls, con, tag, end, *end));
+                return 0;
+        }
 
-                while (!asn1_eoc_decode(&ctx, sequence_end)) {
-                        rc = asn1_header_decode(&ctx, &end, &cls, &con, &tag);
-                        if (!rc) {
-                                cFYI(1,
-                                     ("Error decoding negTokenInit hdr exit2"));
-                                return 0;
-                        }
-                        if ((tag == ASN1_OJI) && (con == ASN1_PRI)) {
-                                if (asn1_oid_decode(&ctx, end, &oid, &oidlen)) {
-
-                                        cFYI(1,
-                                          ("OID len = %d oid = 0x%lx 0x%lx "
-                                           "0x%lx 0x%lx",
-                                           oidlen, *oid, *(oid + 1),
-                                           *(oid + 2), *(oid + 3)));
-
-                                        if (compare_oid(oid, oidlen,
-                                                        MSKRB5_OID,
-                                                        MSKRB5_OID_LEN))
-                                                use_kerberos = true;
-                                        else if (compare_oid(oid, oidlen,
-                                                             KRB5_OID,
-                                                             KRB5_OID_LEN))
-                                                use_kerberos = true;
-                                        else if (compare_oid(oid, oidlen,
-                                                             NTLMSSP_OID,
-                                                             NTLMSSP_OID_LEN))
-                                                use_ntlmssp = true;
-
-                                        kfree(oid);
-                                }
-                        } else {
-                                cFYI(1, ("Should be an oid what is going on?"));
-                        }
-                }
+        if (asn1_header_decode
+            (&ctx, &sequence_end, &cls, &con, &tag) == 0) {
+                cFYI(1, ("Error decoding 2nd part of negTokenInit"));
+                return 0;
+        } else if ((cls != ASN1_UNI) || (con != ASN1_CON)
+                   || (tag != ASN1_SEQ)) {
+                cFYI(1,
+                     ("cls = %d con = %d tag = %d end = %p (%d) exit 1",
+                      cls, con, tag, end, *end));
+                return 0;
+        }
 
-                if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-                        cFYI(1,
-                             ("Error decoding last part negTokenInit exit3"));
-                        return 0;
-                } else if ((cls != ASN1_CTX) || (con != ASN1_CON)) {
-                        /* tag = 3 indicating mechListMIC */
+        while (!asn1_eoc_decode(&ctx, sequence_end)) {
+                rc = asn1_header_decode(&ctx, &end, &cls, &con, &tag);
+                if (!rc) {
                         cFYI(1,
-                             ("Exit 4 cls = %d con = %d tag = %d end = %p (%d)",
-                              cls, con, tag, end, *end));
+                             ("Error decoding negTokenInit hdr exit2"));
                         return 0;
                 }
-                if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-                        cFYI(1,
-                             ("Error decoding last part negTokenInit exit5"));
-                        return 0;
-                } else if ((cls != ASN1_UNI) || (con != ASN1_CON)
-                           || (tag != ASN1_SEQ)) {
-                        cFYI(1, ("cls = %d con = %d tag = %d end = %p (%d)",
-                                cls, con, tag, end, *end));
+                if ((tag == ASN1_OJI) && (con == ASN1_PRI)) {
+                        if (asn1_oid_decode(&ctx, end, &oid, &oidlen)) {
+
+                                cFYI(1, ("OID len = %d oid = 0x%lx 0x%lx "
+                                         "0x%lx 0x%lx", oidlen, *oid,
+                                         *(oid + 1), *(oid + 2), *(oid + 3)));
+
+                                if (compare_oid(oid, oidlen, MSKRB5_OID,
+                                                MSKRB5_OID_LEN))
+                                        use_kerberos = true;
+                                else if (compare_oid(oid, oidlen, KRB5_OID,
+                                                     KRB5_OID_LEN))
+                                        use_kerberos = true;
+                                else if (compare_oid(oid, oidlen, NTLMSSP_OID,
+                                                     NTLMSSP_OID_LEN))
+                                        use_ntlmssp = true;
+
+                                kfree(oid);
+                        }
+                } else {
+                        cFYI(1, ("Should be an oid what is going on?"));
                 }
+        }
 
-                if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-                        cFYI(1,
-                             ("Error decoding last part negTokenInit exit 7"));
-                        return 0;
-                } else if ((cls != ASN1_CTX) || (con != ASN1_CON)) {
-                        cFYI(1,
-                             ("Exit 8 cls = %d con = %d tag = %d end = %p (%d)",
-                              cls, con, tag, end, *end));
-                        return 0;
-                }
-                if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-                        cFYI(1,
-                             ("Error decoding last part negTokenInit exit9"));
-                        return 0;
-                } else if ((cls != ASN1_UNI) || (con != ASN1_PRI)
-                           || (tag != ASN1_GENSTR)) {
-                        cFYI(1,
-                             ("Exit10 cls = %d con = %d tag = %d end = %p (%d)",
-                              cls, con, tag, end, *end));
-                        return 0;
-                }
-                cFYI(1, ("Need to call asn1_octets_decode() function for %s",
-                         ctx.pointer)); /* is this UTF-8 or ASCII? */
+        if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
+                cFYI(1, ("Error decoding last part negTokenInit exit3"));
+                return 0;
+        } else if ((cls != ASN1_CTX) || (con != ASN1_CON)) {
+                /* tag = 3 indicating mechListMIC */
+                cFYI(1, ("Exit 4 cls = %d con = %d tag = %d end = %p (%d)",
+                         cls, con, tag, end, *end));
+                return 0;
+        }
+        if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
+                cFYI(1, ("Error decoding last part negTokenInit exit5"));
+                return 0;
+        } else if ((cls != ASN1_UNI) || (con != ASN1_CON)
+                   || (tag != ASN1_SEQ)) {
+                cFYI(1, ("cls = %d con = %d tag = %d end = %p (%d)",
+                        cls, con, tag, end, *end));
+        }
+
+        if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
+                cFYI(1, ("Error decoding last part negTokenInit exit 7"));
+                return 0;
+        } else if ((cls != ASN1_CTX) || (con != ASN1_CON)) {
+                cFYI(1, ("Exit 8 cls = %d con = %d tag = %d end = %p (%d)",
+                         cls, con, tag, end, *end));
+                return 0;
+        }
+        if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
+                cFYI(1, ("Error decoding last part negTokenInit exit9"));
+                return 0;
+        } else if ((cls != ASN1_UNI) || (con != ASN1_PRI)
+                   || (tag != ASN1_GENSTR)) {
+                cFYI(1, ("Exit10 cls = %d con = %d tag = %d end = %p (%d)",
+                         cls, con, tag, end, *end));
+                return 0;
         }
+        cFYI(1, ("Need to call asn1_octets_decode() function for %s",
+                 ctx.pointer)); /* is this UTF-8 or ASCII? */
 
         if (use_kerberos)
                 *secType = Kerberos;
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index cc950f69e51e..69a12aae91d3 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -79,27 +79,25 @@ void cifs_dump_mids(struct TCP_Server_Info *server)
         spin_lock(&GlobalMid_Lock);
         list_for_each(tmp, &server->pending_mid_q) {
                 mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
-                if (mid_entry) {
-                        cERROR(1, ("State: %d Cmd: %d Pid: %d Tsk: %p Mid %d",
-                                mid_entry->midState,
-                                (int)mid_entry->command,
-                                mid_entry->pid,
-                                mid_entry->tsk,
-                                mid_entry->mid));
+                cERROR(1, ("State: %d Cmd: %d Pid: %d Tsk: %p Mid %d",
+                        mid_entry->midState,
+                        (int)mid_entry->command,
+                        mid_entry->pid,
+                        mid_entry->tsk,
+                        mid_entry->mid));
 #ifdef CONFIG_CIFS_STATS2
-                        cERROR(1, ("IsLarge: %d buf: %p time rcv: %ld now: %ld",
-                                mid_entry->largeBuf,
-                                mid_entry->resp_buf,
-                                mid_entry->when_received,
-                                jiffies));
+                cERROR(1, ("IsLarge: %d buf: %p time rcv: %ld now: %ld",
+                        mid_entry->largeBuf,
+                        mid_entry->resp_buf,
+                        mid_entry->when_received,
+                        jiffies));
 #endif /* STATS2 */
-                        cERROR(1, ("IsMult: %d IsEnd: %d", mid_entry->multiRsp,
-                                  mid_entry->multiEnd));
-                        if (mid_entry->resp_buf) {
-                                cifs_dump_detail(mid_entry->resp_buf);
-                                cifs_dump_mem("existing buf: ",
-                                        mid_entry->resp_buf, 62);
-                        }
+                cERROR(1, ("IsMult: %d IsEnd: %d", mid_entry->multiRsp,
+                          mid_entry->multiEnd));
+                if (mid_entry->resp_buf) {
+                        cifs_dump_detail(mid_entry->resp_buf);
+                        cifs_dump_mem("existing buf: ",
+                                mid_entry->resp_buf, 62);
                 }
         }
         spin_unlock(&GlobalMid_Lock);
@@ -107,9 +105,7 @@ void cifs_dump_mids(struct TCP_Server_Info *server)
 #endif /* CONFIG_CIFS_DEBUG2 */
 
 #ifdef CONFIG_PROC_FS
-static int
-cifs_debug_data_read(char *buf, char **beginBuffer, off_t offset,
-                     int count, int *eof, void *data)
+static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 {
         struct list_head *tmp;
         struct list_head *tmp1;
@@ -117,23 +113,13 @@ cifs_debug_data_read(char *buf, char **beginBuffer, off_t offset,
         struct cifsSesInfo *ses;
         struct cifsTconInfo *tcon;
         int i;
-        int length = 0;
-        char *original_buf = buf;
-
-        *beginBuffer = buf + offset;
 
-        length =
-            sprintf(buf,
+        seq_puts(m,
                     "Display Internal CIFS Data Structures for Debugging\n"
                     "---------------------------------------------------\n");
-        buf += length;
-        length = sprintf(buf, "CIFS Version %s\n", CIFS_VERSION);
-        buf += length;
-        length = sprintf(buf,
-                "Active VFS Requests: %d\n", GlobalTotalActiveXid);
-        buf += length;
-        length = sprintf(buf, "Servers:");
-        buf += length;
+        seq_printf(m, "CIFS Version %s\n", CIFS_VERSION);
+        seq_printf(m, "Active VFS Requests: %d\n", GlobalTotalActiveXid);
+        seq_printf(m, "Servers:");
 
         i = 0;
         read_lock(&GlobalSMBSeslock);
@@ -142,11 +128,10 @@ cifs_debug_data_read(char *buf, char **beginBuffer, off_t offset,
                 ses = list_entry(tmp, struct cifsSesInfo, cifsSessionList);
                 if ((ses->serverDomain == NULL) || (ses->serverOS == NULL) ||
                    (ses->serverNOS == NULL)) {
-                        buf += sprintf(buf, "\nentry for %s not fully "
+                        seq_printf(m, "\nentry for %s not fully "
                                         "displayed\n\t", ses->serverName);
                 } else {
-                        length =
-                            sprintf(buf,
+                        seq_printf(m,
                                     "\n%d) Name: %s  Domain: %s Mounts: %d OS:"
                                     " %s  \n\tNOS: %s\tCapability: 0x%x\n\tSMB"
                                     " session status: %d\t",
@@ -154,10 +139,9 @@ cifs_debug_data_read(char *buf, char **beginBuffer, off_t offset,
                                 atomic_read(&ses->inUse),
                                 ses->serverOS, ses->serverNOS,
                                 ses->capabilities, ses->status);
-                        buf += length;
                 }
                 if (ses->server) {
-                        buf += sprintf(buf, "TCP status: %d\n\tLocal Users To "
+                        seq_printf(m, "TCP status: %d\n\tLocal Users To "
                                     "Server: %d SecMode: 0x%x Req On Wire: %d",
                                 ses->server->tcpStatus,
                                 atomic_read(&ses->server->socketUseCount),
@@ -165,41 +149,34 @@ cifs_debug_data_read(char *buf, char **beginBuffer, off_t offset,
                                 atomic_read(&ses->server->inFlight));
 
 #ifdef CONFIG_CIFS_STATS2
-                        buf += sprintf(buf, " In Send: %d In MaxReq Wait: %d",
+                        seq_printf(m, " In Send: %d In MaxReq Wait: %d",
                                 atomic_read(&ses->server->inSend),
                                 atomic_read(&ses->server->num_waiters));
 #endif
 
-                        length = sprintf(buf, "\nMIDs:\n");
-                        buf += length;
+                        seq_puts(m, "\nMIDs:\n");
 
                         spin_lock(&GlobalMid_Lock);
                         list_for_each(tmp1, &ses->server->pending_mid_q) {
                                 mid_entry = list_entry(tmp1, struct
                                         mid_q_entry,
                                         qhead);
-                                if (mid_entry) {
-                                        length = sprintf(buf,
-                                                        "State: %d com: %d pid:"
-                                                        " %d tsk: %p mid %d\n",
-                                                        mid_entry->midState,
-                                                        (int)mid_entry->command,
-                                                        mid_entry->pid,
-                                                        mid_entry->tsk,
-                                                        mid_entry->mid);
-                                        buf += length;
-                                }
+                                seq_printf(m, "State: %d com: %d pid:"
+                                                " %d tsk: %p mid %d\n",
+                                                mid_entry->midState,
+                                                (int)mid_entry->command,
+                                                mid_entry->pid,
+                                                mid_entry->tsk,
+                                                mid_entry->mid);
                         }
                         spin_unlock(&GlobalMid_Lock);
                 }
 
         }
         read_unlock(&GlobalSMBSeslock);
-        sprintf(buf, "\n");
-        buf++;
+        seq_putc(m, '\n');
 
-        length = sprintf(buf, "Shares:");
-        buf += length;
+        seq_puts(m, "Shares:");
 
         i = 0;
         read_lock(&GlobalSMBSeslock);
@@ -208,62 +185,52 @@ cifs_debug_data_read(char *buf, char **beginBuffer, off_t offset,
                 i++;
                 tcon = list_entry(tmp, struct cifsTconInfo, cifsConnectionList);
                 dev_type = le32_to_cpu(tcon->fsDevInfo.DeviceType);
-                length = sprintf(buf, "\n%d) %s Uses: %d ", i,
+                seq_printf(m, "\n%d) %s Uses: %d ", i,
                                  tcon->treeName, atomic_read(&tcon->useCount));
-                buf += length;
                 if (tcon->nativeFileSystem) {
-                        length = sprintf(buf, "Type: %s ",
+                        seq_printf(m, "Type: %s ",
                                          tcon->nativeFileSystem);
-                        buf += length;
                 }
-                length = sprintf(buf, "DevInfo: 0x%x Attributes: 0x%x"
+                seq_printf(m, "DevInfo: 0x%x Attributes: 0x%x"
                                  "\nPathComponentMax: %d Status: %d",
                             le32_to_cpu(tcon->fsDevInfo.DeviceCharacteristics),
                             le32_to_cpu(tcon->fsAttrInfo.Attributes),
                             le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength),
                             tcon->tidStatus);
-                buf += length;
                 if (dev_type == FILE_DEVICE_DISK)
-                        length = sprintf(buf, " type: DISK ");
+                        seq_puts(m, " type: DISK ");
                 else if (dev_type == FILE_DEVICE_CD_ROM)
-                        length = sprintf(buf, " type: CDROM ");
+                        seq_puts(m, " type: CDROM ");
                 else
-                        length =
-                            sprintf(buf, " type: %d ", dev_type);
-                buf += length;
-                if (tcon->tidStatus == CifsNeedReconnect) {
-                        buf += sprintf(buf, "\tDISCONNECTED ");
-                        length += 14;
-                }
+                        seq_printf(m, " type: %d ", dev_type);
+
+                if (tcon->tidStatus == CifsNeedReconnect)
+                        seq_puts(m, "\tDISCONNECTED ");
         }
         read_unlock(&GlobalSMBSeslock);
 
-        length = sprintf(buf, "\n");
-        buf += length;
+        seq_putc(m, '\n');
 
         /* BB add code to dump additional info such as TCP session info now */
-        /* Now calculate total size of returned data */
-        length = buf - original_buf;
-
-        if (offset + count >= length)
-                *eof = 1;
-        if (length < offset) {
-                *eof = 1;
-                return 0;
-        } else {
-                length = length - offset;
-        }
-        if (length > count)
-                length = count;
+        return 0;
+}
 
-        return length;
+static int cifs_debug_data_proc_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, cifs_debug_data_proc_show, NULL);
 }
 
-#ifdef CONFIG_CIFS_STATS
+static const struct file_operations cifs_debug_data_proc_fops = {
+        .owner          = THIS_MODULE,
+        .open           = cifs_debug_data_proc_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+};
 
-static int
-cifs_stats_write(struct file *file, const char __user *buffer,
-                 unsigned long count, void *data)
+#ifdef CONFIG_CIFS_STATS
+static ssize_t cifs_stats_proc_write(struct file *file,
+                const char __user *buffer, size_t count, loff_t *ppos)
 {
         char c;
         int rc;
@@ -307,236 +274,132 @@ cifs_stats_write(struct file *file, const char __user *buffer,
         return count;
 }
 
-static int
-cifs_stats_read(char *buf, char **beginBuffer, off_t offset,
-                  int count, int *eof, void *data)
+static int cifs_stats_proc_show(struct seq_file *m, void *v)
 {
-        int item_length, i, length;
+        int i;
         struct list_head *tmp;
         struct cifsTconInfo *tcon;
 
-        *beginBuffer = buf + offset;
-
-        length = sprintf(buf,
+        seq_printf(m,
                         "Resources in use\nCIFS Session: %d\n",
                         sesInfoAllocCount.counter);
-        buf += length;
-        item_length =
-                sprintf(buf, "Share (unique mount targets): %d\n",
+        seq_printf(m, "Share (unique mount targets): %d\n",
                         tconInfoAllocCount.counter);
-        length += item_length;
-        buf += item_length;
-        item_length =
-                sprintf(buf, "SMB Request/Response Buffer: %d Pool size: %d\n",
+        seq_printf(m, "SMB Request/Response Buffer: %d Pool size: %d\n",
                         bufAllocCount.counter,
                         cifs_min_rcv + tcpSesAllocCount.counter);
-        length += item_length;
-        buf += item_length;
-        item_length =
-                sprintf(buf, "SMB Small Req/Resp Buffer: %d Pool size: %d\n",
+        seq_printf(m, "SMB Small Req/Resp Buffer: %d Pool size: %d\n",
                         smBufAllocCount.counter, cifs_min_small);
-        length += item_length;
-        buf += item_length;
 #ifdef CONFIG_CIFS_STATS2
-        item_length = sprintf(buf, "Total Large %d Small %d Allocations\n",
+        seq_printf(m, "Total Large %d Small %d Allocations\n",
                                 atomic_read(&totBufAllocCount),
                                 atomic_read(&totSmBufAllocCount));
-        length += item_length;
-        buf += item_length;
 #endif /* CONFIG_CIFS_STATS2 */
 
-        item_length =
-                sprintf(buf, "Operations (MIDs): %d\n",
-                        midCount.counter);
-        length += item_length;
-        buf += item_length;
-        item_length = sprintf(buf,
+        seq_printf(m, "Operations (MIDs): %d\n", midCount.counter);
+        seq_printf(m,
                 "\n%d session %d share reconnects\n",
                 tcpSesReconnectCount.counter, tconInfoReconnectCount.counter);
-        length += item_length;
-        buf += item_length;
 
-        item_length = sprintf(buf,
+        seq_printf(m,
                 "Total vfs operations: %d maximum at one time: %d\n",
                 GlobalCurrentXid, GlobalMaxActiveXid);
-        length += item_length;
-        buf += item_length;
 
         i = 0;
         read_lock(&GlobalSMBSeslock);
         list_for_each(tmp, &GlobalTreeConnectionList) {
                 i++;
                 tcon = list_entry(tmp, struct cifsTconInfo, cifsConnectionList);
-                item_length = sprintf(buf, "\n%d) %s", i, tcon->treeName);
-                buf += item_length;
-                length += item_length;
-                if (tcon->tidStatus == CifsNeedReconnect) {
-                        buf += sprintf(buf, "\tDISCONNECTED ");
-                        length += 14;
-                }
-                item_length = sprintf(buf, "\nSMBs: %d Oplock Breaks: %d",
+                seq_printf(m, "\n%d) %s", i, tcon->treeName);
+                if (tcon->tidStatus == CifsNeedReconnect)
+                        seq_puts(m, "\tDISCONNECTED ");
+                seq_printf(m, "\nSMBs: %d Oplock Breaks: %d",
                         atomic_read(&tcon->num_smbs_sent),
                         atomic_read(&tcon->num_oplock_brks));
-                buf += item_length;
-                length += item_length;
-                item_length = sprintf(buf, "\nReads:  %d Bytes: %lld",
+                seq_printf(m, "\nReads:  %d Bytes: %lld",
                         atomic_read(&tcon->num_reads),
                         (long long)(tcon->bytes_read));
-                buf += item_length;
-                length += item_length;
-                item_length = sprintf(buf, "\nWrites: %d Bytes: %lld",
+                seq_printf(m, "\nWrites: %d Bytes: %lld",
                         atomic_read(&tcon->num_writes),
                         (long long)(tcon->bytes_written));
-                buf += item_length;
-                length += item_length;
-                item_length = sprintf(buf,
+                seq_printf(m,
                         "\nLocks: %d HardLinks: %d Symlinks: %d",
                         atomic_read(&tcon->num_locks),
                         atomic_read(&tcon->num_hardlinks),
                         atomic_read(&tcon->num_symlinks));
-                buf += item_length;
-                length += item_length;
 
-                item_length = sprintf(buf, "\nOpens: %d Closes: %d Deletes: %d",
+                seq_printf(m, "\nOpens: %d Closes: %d Deletes: %d",
                         atomic_read(&tcon->num_opens),
                         atomic_read(&tcon->num_closes),
                         atomic_read(&tcon->num_deletes));
-                buf += item_length;
-                length += item_length;
-                item_length = sprintf(buf, "\nMkdirs: %d Rmdirs: %d",
+                seq_printf(m, "\nMkdirs: %d Rmdirs: %d",
                         atomic_read(&tcon->num_mkdirs),
                         atomic_read(&tcon->num_rmdirs));
-                buf += item_length;
-                length += item_length;
-                item_length = sprintf(buf, "\nRenames: %d T2 Renames %d",
+                seq_printf(m, "\nRenames: %d T2 Renames %d",
                         atomic_read(&tcon->num_renames),
                         atomic_read(&tcon->num_t2renames));
-                buf += item_length;
-                length += item_length;
-                item_length = sprintf(buf, "\nFindFirst: %d FNext %d FClose %d",
+                seq_printf(m, "\nFindFirst: %d FNext %d FClose %d",
                         atomic_read(&tcon->num_ffirst),
                         atomic_read(&tcon->num_fnext),
                         atomic_read(&tcon->num_fclose));
-                buf += item_length;
-                length += item_length;
         }
         read_unlock(&GlobalSMBSeslock);
 
-        buf += sprintf(buf, "\n");
-        length++;
-
-        if (offset + count >= length)
-                *eof = 1;
-        if (length < offset) {
-                *eof = 1;
-                return 0;
-        } else {
-                length = length - offset;
-        }
-        if (length > count)
-                length = count;
+        seq_putc(m, '\n');
+        return 0;
+}
 
-        return length;
+static int cifs_stats_proc_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, cifs_stats_proc_show, NULL);
 }
+
+static const struct file_operations cifs_stats_proc_fops = {
+        .owner          = THIS_MODULE,
+        .open           = cifs_stats_proc_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+        .write          = cifs_stats_proc_write,
+};
 #endif /* STATS */
 
 static struct proc_dir_entry *proc_fs_cifs;
-read_proc_t cifs_txanchor_read;
-static read_proc_t cifsFYI_read;
-static write_proc_t cifsFYI_write;
-static read_proc_t oplockEnabled_read;
-static write_proc_t oplockEnabled_write;
-static read_proc_t lookupFlag_read;
-static write_proc_t lookupFlag_write;
-static read_proc_t traceSMB_read;
-static write_proc_t traceSMB_write;
-static read_proc_t multiuser_mount_read;
-static write_proc_t multiuser_mount_write;
-static read_proc_t security_flags_read;
-static write_proc_t security_flags_write;
-/* static read_proc_t ntlmv2_enabled_read;
-static write_proc_t ntlmv2_enabled_write;
-static read_proc_t packet_signing_enabled_read;
-static write_proc_t packet_signing_enabled_write;*/
-static read_proc_t experimEnabled_read;
-static write_proc_t experimEnabled_write;
-static read_proc_t linuxExtensionsEnabled_read;
-static write_proc_t linuxExtensionsEnabled_write;
+static const struct file_operations cifsFYI_proc_fops;
+static const struct file_operations cifs_oplock_proc_fops;
+static const struct file_operations cifs_lookup_cache_proc_fops;
+static const struct file_operations traceSMB_proc_fops;
+static const struct file_operations cifs_multiuser_mount_proc_fops;
+static const struct file_operations cifs_security_flags_proc_fops;
+static const struct file_operations cifs_experimental_proc_fops;
+static const struct file_operations cifs_linux_ext_proc_fops;
 
 void
 cifs_proc_init(void)
 {
-        struct proc_dir_entry *pde;
-
         proc_fs_cifs = proc_mkdir("fs/cifs", NULL);
         if (proc_fs_cifs == NULL)
                 return;
 
         proc_fs_cifs->owner = THIS_MODULE;
-        create_proc_read_entry("DebugData", 0, proc_fs_cifs,
-                                cifs_debug_data_read, NULL);
+        proc_create("DebugData", 0, proc_fs_cifs, &cifs_debug_data_proc_fops);
 
 #ifdef CONFIG_CIFS_STATS
-        pde = create_proc_read_entry("Stats", 0, proc_fs_cifs,
-                                cifs_stats_read, NULL);
-        if (pde)
-                pde->write_proc = cifs_stats_write;
+        proc_create("Stats", 0, proc_fs_cifs, &cifs_stats_proc_fops);
 #endif /* STATS */
-        pde = create_proc_read_entry("cifsFYI", 0, proc_fs_cifs,
-                                cifsFYI_read, NULL);
-        if (pde)
-                pde->write_proc = cifsFYI_write;
-
-        pde =
-            create_proc_read_entry("traceSMB", 0, proc_fs_cifs,
-                                traceSMB_read, NULL);
-        if (pde)
-                pde->write_proc = traceSMB_write;
-
-        pde = create_proc_read_entry("OplockEnabled", 0, proc_fs_cifs,
-                                oplockEnabled_read, NULL);
-        if (pde)
-                pde->write_proc = oplockEnabled_write;
-
-        pde = create_proc_read_entry("Experimental", 0, proc_fs_cifs,
-                                experimEnabled_read, NULL);
-        if (pde)
-                pde->write_proc = experimEnabled_write;
-
-        pde = create_proc_read_entry("LinuxExtensionsEnabled", 0, proc_fs_cifs,
-                                linuxExtensionsEnabled_read, NULL);
-        if (pde)
-                pde->write_proc = linuxExtensionsEnabled_write;
-
-        pde =
-            create_proc_read_entry("MultiuserMount", 0, proc_fs_cifs,
-                                multiuser_mount_read, NULL);
-        if (pde)
-                pde->write_proc = multiuser_mount_write;
-
-        pde =
-            create_proc_read_entry("SecurityFlags", 0, proc_fs_cifs,
-                                security_flags_read, NULL);
-        if (pde)
-                pde->write_proc = security_flags_write;
-
-        pde =
-        create_proc_read_entry("LookupCacheEnabled", 0, proc_fs_cifs,
-                                lookupFlag_read, NULL);
-        if (pde)
-                pde->write_proc = lookupFlag_write;
-
-/*      pde =
-            create_proc_read_entry("NTLMV2Enabled", 0, proc_fs_cifs,
-                                ntlmv2_enabled_read, NULL);
-        if (pde)
-                pde->write_proc = ntlmv2_enabled_write;
-
-        pde =
-            create_proc_read_entry("PacketSigningEnabled", 0, proc_fs_cifs,
-                                packet_signing_enabled_read, NULL);
-        if (pde)
-                pde->write_proc = packet_signing_enabled_write;*/
+        proc_create("cifsFYI", 0, proc_fs_cifs, &cifsFYI_proc_fops);
+        proc_create("traceSMB", 0, proc_fs_cifs, &traceSMB_proc_fops);
+        proc_create("OplockEnabled", 0, proc_fs_cifs, &cifs_oplock_proc_fops);
+        proc_create("Experimental", 0, proc_fs_cifs,
+                    &cifs_experimental_proc_fops);
+        proc_create("LinuxExtensionsEnabled", 0, proc_fs_cifs,
+                    &cifs_linux_ext_proc_fops);
+        proc_create("MultiuserMount", 0, proc_fs_cifs,
+                    &cifs_multiuser_mount_proc_fops);
+        proc_create("SecurityFlags", 0, proc_fs_cifs,
+                    &cifs_security_flags_proc_fops);
+        proc_create("LookupCacheEnabled", 0, proc_fs_cifs,
+                    &cifs_lookup_cache_proc_fops);
 }
 
 void
@@ -553,39 +416,26 @@ cifs_proc_clean(void)
 #endif
         remove_proc_entry("MultiuserMount", proc_fs_cifs);
         remove_proc_entry("OplockEnabled", proc_fs_cifs);
-/*      remove_proc_entry("NTLMV2Enabled",proc_fs_cifs); */
         remove_proc_entry("SecurityFlags", proc_fs_cifs);
-/*      remove_proc_entry("PacketSigningEnabled", proc_fs_cifs); */
         remove_proc_entry("LinuxExtensionsEnabled", proc_fs_cifs);
         remove_proc_entry("Experimental", proc_fs_cifs);
         remove_proc_entry("LookupCacheEnabled", proc_fs_cifs);
         remove_proc_entry("fs/cifs", NULL);
 }
 
-static int
-cifsFYI_read(char *page, char **start, off_t off, int count,
-             int *eof, void *data)
+static int cifsFYI_proc_show(struct seq_file *m, void *v)
 {
-        int len;
-
-        len = sprintf(page, "%d\n", cifsFYI);
-
-        len -= off;
-        *start = page + off;
-
-        if (len > count)
-                len = count;
-        else
-                *eof = 1;
-
-        if (len < 0)
-                len = 0;
+        seq_printf(m, "%d\n", cifsFYI);
+        return 0;
+}
 
-        return len;
+static int cifsFYI_proc_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, cifsFYI_proc_show, NULL);
 }
-static int
-cifsFYI_write(struct file *file, const char __user *buffer,
-              unsigned long count, void *data)
+
+static ssize_t cifsFYI_proc_write(struct file *file, const char __user *buffer,
+                size_t count, loff_t *ppos)
 {
         char c;
         int rc;
@@ -603,30 +453,28 @@ cifsFYI_write(struct file *file, const char __user *buffer,
         return count;
 }
 
-static int
-oplockEnabled_read(char *page, char **start, off_t off,
-                   int count, int *eof, void *data)
-{
-        int len;
-
-        len = sprintf(page, "%d\n", oplockEnabled);
-
-        len -= off;
-        *start = page + off;
+static const struct file_operations cifsFYI_proc_fops = {
+        .owner          = THIS_MODULE,
+        .open           = cifsFYI_proc_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+        .write          = cifsFYI_proc_write,
+};
 
-        if (len > count)
-                len = count;
-        else
-                *eof = 1;
-
-        if (len < 0)
-                len = 0;
+static int cifs_oplock_proc_show(struct seq_file *m, void *v)
+{
+        seq_printf(m, "%d\n", oplockEnabled);
+        return 0;
+}
 
-        return len;
+static int cifs_oplock_proc_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, cifs_oplock_proc_show, NULL);
 }
-static int
-oplockEnabled_write(struct file *file, const char __user *buffer,
-                    unsigned long count, void *data)
+
+static ssize_t cifs_oplock_proc_write(struct file *file,
+                const char __user *buffer, size_t count, loff_t *ppos)
 {
         char c;
         int rc;
@@ -642,30 +490,28 @@ oplockEnabled_write(struct file *file, const char __user *buffer,
         return count;
 }
 
-static int
-experimEnabled_read(char *page, char **start, off_t off,
-                    int count, int *eof, void *data)
-{
-        int len;
-
-        len = sprintf(page, "%d\n", experimEnabled);
+static const struct file_operations cifs_oplock_proc_fops = {
+        .owner          = THIS_MODULE,
+        .open           = cifs_oplock_proc_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+        .write          = cifs_oplock_proc_write,
+};
 
-        len -= off;
-        *start = page + off;
-
-        if (len > count)
-                len = count;
-        else
-                *eof = 1;
-
-        if (len < 0)
-                len = 0;
+static int cifs_experimental_proc_show(struct seq_file *m, void *v)
+{
+        seq_printf(m, "%d\n", experimEnabled);
+        return 0;
+}
 
-        return len;
+static int cifs_experimental_proc_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, cifs_experimental_proc_show, NULL);
 }
-static int
-experimEnabled_write(struct file *file, const char __user *buffer,
-                     unsigned long count, void *data)
+
+static ssize_t cifs_experimental_proc_write(struct file *file,
+                const char __user *buffer, size_t count, loff_t *ppos)
 {
         char c;
         int rc;
@@ -683,29 +529,28 @@ experimEnabled_write(struct file *file, const char __user *buffer,
         return count;
 }
 
-static int
-linuxExtensionsEnabled_read(char *page, char **start, off_t off,
-                            int count, int *eof, void *data)
-{
-        int len;
-
-        len = sprintf(page, "%d\n", linuxExtEnabled);
-        len -= off;
-        *start = page + off;
+static const struct file_operations cifs_experimental_proc_fops = {
+        .owner          = THIS_MODULE,
+        .open           = cifs_experimental_proc_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+        .write          = cifs_experimental_proc_write,
+};
 
-        if (len > count)
-                len = count;
-        else
-                *eof = 1;
-
-        if (len < 0)
-                len = 0;
+static int cifs_linux_ext_proc_show(struct seq_file *m, void *v)
+{
+        seq_printf(m, "%d\n", linuxExtEnabled);
+        return 0;
+}
 
-        return len;
+static int cifs_linux_ext_proc_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, cifs_linux_ext_proc_show, NULL);
 }
-static int
-linuxExtensionsEnabled_write(struct file *file, const char __user *buffer,
-                             unsigned long count, void *data)
+
+static ssize_t cifs_linux_ext_proc_write(struct file *file,
+                const char __user *buffer, size_t count, loff_t *ppos)
 {
         char c;
         int rc;
@@ -721,31 +566,28 @@ linuxExtensionsEnabled_write(struct file *file, const char __user *buffer,
         return count;
 }
 
+static const struct file_operations cifs_linux_ext_proc_fops = {
+        .owner          = THIS_MODULE,
+        .open           = cifs_linux_ext_proc_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+        .write          = cifs_linux_ext_proc_write,
+};
 
-static int
-lookupFlag_read(char *page, char **start, off_t off,
-                int count, int *eof, void *data)
+static int cifs_lookup_cache_proc_show(struct seq_file *m, void *v)
 {
-        int len;
-
-        len = sprintf(page, "%d\n", lookupCacheEnabled);
-
-        len -= off;
-        *start = page + off;
-
-        if (len > count)
-                len = count;
-        else
-                *eof = 1;
-
-        if (len < 0)
-                len = 0;
+        seq_printf(m, "%d\n", lookupCacheEnabled);
+        return 0;
+}
 
-        return len;
+static int cifs_lookup_cache_proc_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, cifs_lookup_cache_proc_show, NULL);
 }
-static int
-lookupFlag_write(struct file *file, const char __user *buffer,
-                    unsigned long count, void *data)
+
+static ssize_t cifs_lookup_cache_proc_write(struct file *file,
+                const char __user *buffer, size_t count, loff_t *ppos)
 {
         char c;
         int rc;
@@ -760,30 +602,29 @@ lookupFlag_write(struct file *file, const char __user *buffer,
 
         return count;
 }
-static int
-traceSMB_read(char *page, char **start, off_t off, int count,
-              int *eof, void *data)
-{
-        int len;
-
-        len = sprintf(page, "%d\n", traceSMB);
-
-        len -= off;
-        *start = page + off;
 
-        if (len > count)
-                len = count;
-        else
-                *eof = 1;
+static const struct file_operations cifs_lookup_cache_proc_fops = {
+        .owner          = THIS_MODULE,
+        .open           = cifs_lookup_cache_proc_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+        .write          = cifs_lookup_cache_proc_write,
+};
 
-        if (len < 0)
-                len = 0;
+static int traceSMB_proc_show(struct seq_file *m, void *v)
+{
+        seq_printf(m, "%d\n", traceSMB);
+        return 0;
+}
 
-        return len;
+static int traceSMB_proc_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, traceSMB_proc_show, NULL);
 }
-static int
-traceSMB_write(struct file *file, const char __user *buffer,
-               unsigned long count, void *data)
+
+static ssize_t traceSMB_proc_write(struct file *file, const char __user *buffer,
+                size_t count, loff_t *ppos)
 {
         char c;
         int rc;
@@ -799,30 +640,28 @@ traceSMB_write(struct file *file, const char __user *buffer,
         return count;
 }
 
-static int
-multiuser_mount_read(char *page, char **start, off_t off,
-                     int count, int *eof, void *data)
-{
-        int len;
-
-        len = sprintf(page, "%d\n", multiuser_mount);
-
-        len -= off;
-        *start = page + off;
+static const struct file_operations traceSMB_proc_fops = {
+        .owner          = THIS_MODULE,
+        .open           = traceSMB_proc_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+        .write          = traceSMB_proc_write,
+};
 
-        if (len > count)
-                len = count;
-        else
-                *eof = 1;
-
-        if (len < 0)
-                len = 0;
+static int cifs_multiuser_mount_proc_show(struct seq_file *m, void *v)
+{
+        seq_printf(m, "%d\n", multiuser_mount);
+        return 0;
+}
 
-        return len;
+static int cifs_multiuser_mount_proc_open(struct inode *inode, struct file *fh)
+{
+        return single_open(fh, cifs_multiuser_mount_proc_show, NULL);
 }
-static int
-multiuser_mount_write(struct file *file, const char __user *buffer,
-                      unsigned long count, void *data)
+
+static ssize_t cifs_multiuser_mount_proc_write(struct file *file,
+                const char __user *buffer, size_t count, loff_t *ppos)
 {
         char c;
         int rc;
@@ -838,30 +677,28 @@ multiuser_mount_write(struct file *file, const char __user *buffer,
         return count;
 }
 
-static int
-security_flags_read(char *page, char **start, off_t off,
-                       int count, int *eof, void *data)
-{
-        int len;
-
-        len = sprintf(page, "0x%x\n", extended_security);
-
-        len -= off;
-        *start = page + off;
+static const struct file_operations cifs_multiuser_mount_proc_fops = {
+        .owner          = THIS_MODULE,
+        .open           = cifs_multiuser_mount_proc_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+        .write          = cifs_multiuser_mount_proc_write,
+};
 
-        if (len > count)
-                len = count;
-        else
-                *eof = 1;
-
-        if (len < 0)
-                len = 0;
+static int cifs_security_flags_proc_show(struct seq_file *m, void *v)
+{
+        seq_printf(m, "0x%x\n", extended_security);
+        return 0;
+}
 
-        return len;
+static int cifs_security_flags_proc_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, cifs_security_flags_proc_show, NULL);
 }
-static int
-security_flags_write(struct file *file, const char __user *buffer,
-                        unsigned long count, void *data)
+
+static ssize_t cifs_security_flags_proc_write(struct file *file,
+                const char __user *buffer, size_t count, loff_t *ppos)
 {
         unsigned int flags;
         char flags_string[12];
@@ -917,6 +754,15 @@ security_flags_write(struct file *file, const char __user *buffer,
         /* BB should we turn on MAY flags for other MUST options? */
         return count;
 }
+
+static const struct file_operations cifs_security_flags_proc_fops = {
+        .owner          = THIS_MODULE,
+        .open           = cifs_security_flags_proc_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+        .write          = cifs_security_flags_proc_write,
+};
 #else
 inline void cifs_proc_init(void)
 {
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index d82374c9e329..d2c8eef84f3c 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -226,7 +226,7 @@ static int add_mount_helper(struct vfsmount *newmnt, struct nameidata *nd,
         int err;
 
         mntget(newmnt);
-        err = do_add_mount(newmnt, nd, nd->path.mnt->mnt_flags, mntlist);
+        err = do_add_mount(newmnt, &nd->path, nd->path.mnt->mnt_flags, mntlist);
         switch (err) {
         case 0:
                 path_put(&nd->path);
diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c
index 7013aaff6aed..2434ab0e8791 100644
--- a/fs/cifs/cifs_spnego.c
+++ b/fs/cifs/cifs_spnego.c
@@ -66,8 +66,8 @@ struct key_type cifs_spnego_key_type = {
         .describe       = user_describe,
 };
 
-#define MAX_VER_STR_LEN   9 /* length of longest version string e.g.
-                                strlen(";ver=0xFF") */
+#define MAX_VER_STR_LEN   8 /* length of longest version string e.g.
+                                strlen("ver=0xFF") */
 #define MAX_MECH_STR_LEN 13 /* length of longest security mechanism name, eg
                                in future could have strlen(";sec=ntlmsspi") */
 #define MAX_IPV6_ADDR_LEN 42 /* eg FEDC:BA98:7654:3210:FEDC:BA98:7654:3210/60 */
@@ -81,11 +81,15 @@ cifs_get_spnego_key(struct cifsSesInfo *sesInfo)
         struct key *spnego_key;
         const char *hostname = server->hostname;
 
-        /* BB: come up with better scheme for determining length */
-        /* length of fields (with semicolons): ver=0xyz ipv4= ipaddress host=
-           hostname sec=mechanism uid=0x uid */
-        desc_len = MAX_VER_STR_LEN + 5 + MAX_IPV6_ADDR_LEN + 1 + 6 +
-                  strlen(hostname) + MAX_MECH_STR_LEN + 8 + (sizeof(uid_t) * 2);
+        /* length of fields (with semicolons): ver=0xyz ip4=ipaddress
+           host=hostname sec=mechanism uid=0xFF user=username */
+        desc_len = MAX_VER_STR_LEN +
+                   6 /* len of "host=" */ + strlen(hostname) +
+                   5 /* len of ";ipv4=" */ + MAX_IPV6_ADDR_LEN +
+                   MAX_MECH_STR_LEN +
+                   7 /* len of ";uid=0x" */ + (sizeof(uid_t) * 2) +
+                   6 /* len of ";user=" */ + strlen(sesInfo->userName) + 1;
+
         spnego_key = ERR_PTR(-ENOMEM);
         description = kzalloc(desc_len, GFP_KERNEL);
         if (description == NULL)
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 0e9fc2ba90ee..57ecdc83c26f 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -56,7 +56,7 @@ int match_sid(struct cifs_sid *ctsid)
         struct cifs_sid *cwsid;
 
         if (!ctsid)
-                return (-1);
+                return -1;
 
         for (i = 0; i < NUM_WK_SIDS; ++i) {
                 cwsid = &(wksidarr[i].cifssid);
@@ -87,11 +87,11 @@ int match_sid(struct cifs_sid *ctsid)
                 }
 
                 cFYI(1, ("matching sid: %s\n", wksidarr[i].sidname));
-                return (0); /* sids compare/match */
+                return 0; /* sids compare/match */
         }
 
         cFYI(1, ("No matching sid"));
-        return (-1);
+        return -1;
 }
 
 /* if the two SIDs (roughly equivalent to a UUID for a user or group) are
@@ -102,16 +102,16 @@ int compare_sids(const struct cifs_sid *ctsid, const struct cifs_sid *cwsid)
         int num_subauth, num_sat, num_saw;
 
         if ((!ctsid) || (!cwsid))
-                return (0);
+                return 0;
 
         /* compare the revision */
         if (ctsid->revision != cwsid->revision)
-                return (0);
+                return 0;
 
         /* compare all of the six auth values */
         for (i = 0; i < 6; ++i) {
                 if (ctsid->authority[i] != cwsid->authority[i])
-                        return (0);
+                        return 0;
         }
 
         /* compare all of the subauth values if any */
@@ -121,11 +121,11 @@ int compare_sids(const struct cifs_sid *ctsid, const struct cifs_sid *cwsid)
         if (num_subauth) {
                 for (i = 0; i < num_subauth; ++i) {
                         if (ctsid->sub_auth[i] != cwsid->sub_auth[i])
-                                return (0);
+                                return 0;
                 }
         }
 
-        return (1); /* sids compare/match */
+        return 1; /* sids compare/match */
 }
 
 
@@ -169,8 +169,7 @@ static void copy_sec_desc(const struct cifs_ntsd *pntsd,
         for (i = 0; i < 6; i++)
                 ngroup_sid_ptr->authority[i] = group_sid_ptr->authority[i];
         for (i = 0; i < 5; i++)
-                ngroup_sid_ptr->sub_auth[i] =
-                                cpu_to_le32(group_sid_ptr->sub_auth[i]);
+                ngroup_sid_ptr->sub_auth[i] = group_sid_ptr->sub_auth[i];
 
         return;
 }
@@ -285,7 +284,7 @@ static __u16 fill_ace_for_sid(struct cifs_ace *pntace,
         size = 1 + 1 + 2 + 4 + 1 + 1 + 6 + (psid->num_subauth * 4);
         pntace->size = cpu_to_le16(size);
 
-        return (size);
+        return size;
 }
 
 
@@ -426,7 +425,7 @@ static int set_chmod_dacl(struct cifs_acl *pndacl, struct cifs_sid *pownersid,
         pndacl->size = cpu_to_le16(size + sizeof(struct cifs_acl));
         pndacl->num_aces = cpu_to_le32(3);
 
-        return (0);
+        return 0;
 }
 
 
@@ -510,7 +509,7 @@ static int parse_sec_desc(struct cifs_ntsd *pntsd, int acl_len,
                         sizeof(struct cifs_sid)); */
 
 
-        return (0);
+        return 0;
 }
 
 
@@ -527,7 +526,7 @@ static int build_sec_desc(struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd,
         struct cifs_acl *ndacl_ptr = NULL; /* no need for SACL ptr */
 
         if ((inode == NULL) || (pntsd == NULL) || (pnntsd == NULL))
-                return (-EIO);
+                return -EIO;
 
         owner_sid_ptr = (struct cifs_sid *)((char *)pntsd +
                                 le32_to_cpu(pntsd->osidoffset));
@@ -550,7 +549,7 @@ static int build_sec_desc(struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd,
         /* copy security descriptor control portion and owner and group sid */
         copy_sec_desc(pntsd, pnntsd, sidsoffset);
 
-        return (rc);
+        return rc;
 }
 
 
@@ -629,11 +628,11 @@ static int set_cifs_acl(struct cifs_ntsd *pnntsd, __u32 acllen,
         cFYI(DBG2, ("set ACL for %s from mode 0x%x", path, inode->i_mode));
 
         if (!inode)
-                return (rc);
+                return rc;
 
         sb = inode->i_sb;
         if (sb == NULL)
-                return (rc);
+                return rc;
 
         cifs_sb = CIFS_SB(sb);
         xid = GetXid();
@@ -652,7 +651,7 @@ static int set_cifs_acl(struct cifs_ntsd *pnntsd, __u32 acllen,
                 if (rc != 0) {
                         cERROR(1, ("Unable to open file to set ACL"));
                         FreeXid(xid);
-                        return (rc);
+                        return rc;
                 }
         }
 
@@ -665,7 +664,7 @@ static int set_cifs_acl(struct cifs_ntsd *pnntsd, __u32 acllen,
 
         FreeXid(xid);
 
-        return (rc);
+        return rc;
 }
 
 /* Translate the CIFS ACL (simlar to NTFS ACL) for a file into mode bits */
@@ -715,7 +714,7 @@ int mode_to_acl(struct inode *inode, const char *path, __u64 nmode)
                 if (!pnntsd) {
                         cERROR(1, ("Unable to allocate security descriptor"));
                         kfree(pntsd);
-                        return (-ENOMEM);
+                        return -ENOMEM;
                 }
 
                 rc = build_sec_desc(pntsd, pnntsd, inode, nmode);
@@ -732,6 +731,6 @@ int mode_to_acl(struct inode *inode, const char *path, __u64 nmode)
                 kfree(pntsd);
         }
 
-        return (rc);
+        return rc;
 }
 #endif /* CONFIG_CIFS_EXPERIMENTAL */
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 4ff8939c6cc7..83fd40dc1ef0 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -310,9 +310,8 @@ void calc_lanman_hash(struct cifsSesInfo *ses, char *lnm_session_key)
         utf8 and other multibyte codepages each need their own strupper
         function since a byte at a time will ont work. */
 
-        for (i = 0; i < CIFS_ENCPWD_SIZE; i++) {
+        for (i = 0; i < CIFS_ENCPWD_SIZE; i++)
                 password_with_pad[i] = toupper(password_with_pad[i]);
-        }
 
         SMBencrypt(password_with_pad, ses->server->cryptKey, lnm_session_key);
         /* clear password before we return/free memory */
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 22857c639df5..e8da4ee761b5 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -267,7 +267,7 @@ cifs_statfs(struct dentry *dentry, struct kstatfs *buf)
         return 0;
 }
 
-static int cifs_permission(struct inode *inode, int mask, struct nameidata *nd)
+static int cifs_permission(struct inode *inode, int mask)
 {
         struct cifs_sb_info *cifs_sb;
 
@@ -766,7 +766,7 @@ const struct file_operations cifs_dir_ops = {
 };
 
 static void
-cifs_init_once(struct kmem_cache *cachep, void *inode)
+cifs_init_once(void *inode)
 {
         struct cifsInodeInfo *cifsi = inode;
 
@@ -930,36 +930,34 @@ static int cifs_oplock_thread(void *dummyarg)
                         schedule_timeout(39*HZ);
                 } else {
                         oplock_item = list_entry(GlobalOplock_Q.next,
-                                struct oplock_q_entry, qhead);
-                        if (oplock_item) {
-                                cFYI(1, ("found oplock item to write out"));
-                                pTcon = oplock_item->tcon;
-                                inode = oplock_item->pinode;
-                                netfid = oplock_item->netfid;
-                                spin_unlock(&GlobalMid_Lock);
-                                DeleteOplockQEntry(oplock_item);
-                                /* can not grab inode sem here since it would
+                                                struct oplock_q_entry, qhead);
+                        cFYI(1, ("found oplock item to write out"));
+                        pTcon = oplock_item->tcon;
+                        inode = oplock_item->pinode;
+                        netfid = oplock_item->netfid;
+                        spin_unlock(&GlobalMid_Lock);
+                        DeleteOplockQEntry(oplock_item);
+                        /* can not grab inode sem here since it would
                                 deadlock when oplock received on delete
                                 since vfs_unlink holds the i_mutex across
                                 the call */
-                                /* mutex_lock(&inode->i_mutex);*/
-                                if (S_ISREG(inode->i_mode)) {
-                                        rc =
-                                           filemap_fdatawrite(inode->i_mapping);
-                                        if (CIFS_I(inode)->clientCanCacheRead
-                                                                         == 0) {
-                                                waitrc = filemap_fdatawait(inode->i_mapping);
-                                                invalidate_remote_inode(inode);
-                                        }
-                                        if (rc == 0)
-                                                rc = waitrc;
-                                } else
-                                        rc = 0;
-                                /* mutex_unlock(&inode->i_mutex);*/
-                                if (rc)
-                                        CIFS_I(inode)->write_behind_rc = rc;
-                                cFYI(1, ("Oplock flush inode %p rc %d",
-                                        inode, rc));
+                        /* mutex_lock(&inode->i_mutex);*/
+                        if (S_ISREG(inode->i_mode)) {
+                                rc = filemap_fdatawrite(inode->i_mapping);
+                                if (CIFS_I(inode)->clientCanCacheRead == 0) {
+                                        waitrc = filemap_fdatawait(
+                                                              inode->i_mapping);
+                                        invalidate_remote_inode(inode);
+                                }
+                                if (rc == 0)
+                                        rc = waitrc;
+                        } else
+                                rc = 0;
+                        /* mutex_unlock(&inode->i_mutex);*/
+                        if (rc)
+                                CIFS_I(inode)->write_behind_rc = rc;
+                        cFYI(1, ("Oplock flush inode %p rc %d",
+                                inode, rc));
 
                                 /* releasing stale oplock after recent reconnect
                                 of smb session using a now incorrect file
@@ -967,15 +965,13 @@ static int cifs_oplock_thread(void *dummyarg)
                                 not bother sending an oplock release if session
                                 to server still is disconnected since oplock
                                 already released by the server in that case */
-                                if (pTcon->tidStatus != CifsNeedReconnect) {
-                                    rc = CIFSSMBLock(0, pTcon, netfid,
-                                            0 /* len */ , 0 /* offset */, 0,
-                                            0, LOCKING_ANDX_OPLOCK_RELEASE,
-                                            false /* wait flag */);
-                                        cFYI(1, ("Oplock release rc = %d", rc));
-                                }
-                        } else
-                                spin_unlock(&GlobalMid_Lock);
+                        if (pTcon->tidStatus != CifsNeedReconnect) {
+                                rc = CIFSSMBLock(0, pTcon, netfid,
+                                                0 /* len */ , 0 /* offset */, 0,
+                                                0, LOCKING_ANDX_OPLOCK_RELEASE,
+                                                false /* wait flag */);
+                                cFYI(1, ("Oplock release rc = %d", rc));
+                        }
                         set_current_state(TASK_INTERRUPTIBLE);
                         schedule_timeout(1);  /* yield in case q were corrupt */
                 }
@@ -1001,8 +997,7 @@ static int cifs_dnotify_thread(void *dummyarg)
                 list_for_each(tmp, &GlobalSMBSessionList) {
                         ses = list_entry(tmp, struct cifsSesInfo,
                                 cifsSessionList);
-                        if (ses && ses->server &&
-                             atomic_read(&ses->server->inFlight))
+                        if (ses->server && atomic_read(&ses->server->inFlight))
                                 wake_up_all(&ses->server->response_q);
                 }
                 read_unlock(&GlobalSMBSeslock);
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 25a6cbd15529..135c965c4137 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -101,5 +101,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
 extern const struct export_operations cifs_export_ops;
 #endif /* EXPERIMENTAL */
 
-#define CIFS_VERSION   "1.53"
+#define CIFS_VERSION   "1.54"
 #endif                          /* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 9cfcf326ead3..7e1cf262effe 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -27,7 +27,7 @@
 #define MAX_SES_INFO 2
 #define MAX_TCON_INFO 4
 
-#define MAX_TREE_SIZE 2 + MAX_SERVER_SIZE + 1 + MAX_SHARE_SIZE + 1
+#define MAX_TREE_SIZE (2 + MAX_SERVER_SIZE + 1 + MAX_SHARE_SIZE + 1)
 #define MAX_SERVER_SIZE 15
 #define MAX_SHARE_SIZE  64      /* used to be 20, this should still be enough */
 #define MAX_USERNAME_SIZE 32    /* 32 is to allow for 15 char names + null
@@ -537,8 +537,8 @@ require use of the stronger protocol */
 #endif /* WEAK_PW_HASH */
 #define   CIFSSEC_MUST_SEAL     0x40040 /* not supported yet */
 
-#define   CIFSSEC_DEF  CIFSSEC_MAY_SIGN | CIFSSEC_MAY_NTLM | CIFSSEC_MAY_NTLMV2
-#define   CIFSSEC_MAX  CIFSSEC_MUST_SIGN | CIFSSEC_MUST_NTLMV2
+#define   CIFSSEC_DEF (CIFSSEC_MAY_SIGN | CIFSSEC_MAY_NTLM | CIFSSEC_MAY_NTLMV2)
+#define   CIFSSEC_MAX (CIFSSEC_MUST_SIGN | CIFSSEC_MUST_NTLMV2)
 #define   CIFSSEC_AUTH_MASK (CIFSSEC_MAY_NTLM | CIFSSEC_MAY_NTLMV2 | CIFSSEC_MAY_LANMAN | CIFSSEC_MAY_PLNTXT | CIFSSEC_MAY_KRB5)
 /*
  *****************************************************************
diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h
index 0f327c224da3..d2a073edd1b8 100644
--- a/fs/cifs/cifspdu.h
+++ b/fs/cifs/cifspdu.h
@@ -31,7 +31,7 @@
 #else
 #define CIFS_PROT   0
 #endif
-#define POSIX_PROT  CIFS_PROT+1
+#define POSIX_PROT  (CIFS_PROT+1)
 #define BAD_PROT 0xFFFF
 
 /* SMB command codes */
@@ -262,7 +262,7 @@
  */
 #define CIFS_NO_HANDLE        0xFFFF
 
-#define NO_CHANGE_64          cpu_to_le64(0xFFFFFFFFFFFFFFFFULL)
+#define NO_CHANGE_64          0xFFFFFFFFFFFFFFFFULL
 #define NO_CHANGE_32          0xFFFFFFFFUL
 
 /* IPC$ in ASCII */
@@ -341,7 +341,7 @@
 #define CREATE_COMPLETE_IF_OPLK 0x00000100      /* should be zero */
 #define CREATE_NO_EA_KNOWLEDGE  0x00000200
 #define CREATE_EIGHT_DOT_THREE  0x00000400      /* doc says this is obsolete
-                                                 "open for recovery" flag - should
+                                                 "open for recovery" flag should
                                                  be zero in any case */
 #define CREATE_OPEN_FOR_RECOVERY 0x00000400
 #define CREATE_RANDOM_ACCESS    0x00000800
@@ -414,8 +414,8 @@ struct smb_hdr {
         __u8 WordCount;
 } __attribute__((packed));
 /* given a pointer to an smb_hdr retrieve the value of byte count */
-#define BCC(smb_var) ( *(__u16 *)((char *)smb_var + sizeof(struct smb_hdr) + (2 * smb_var->WordCount)))
-#define BCC_LE(smb_var) ( *(__le16 *)((char *)smb_var + sizeof(struct smb_hdr) + (2 * smb_var->WordCount)))
+#define BCC(smb_var) (*(__u16 *)((char *)smb_var + sizeof(struct smb_hdr) + (2 * smb_var->WordCount)))
+#define BCC_LE(smb_var) (*(__le16 *)((char *)smb_var + sizeof(struct smb_hdr) + (2 * smb_var->WordCount)))
 /* given a pointer to an smb_hdr retrieve the pointer to the byte area */
 #define pByteArea(smb_var) ((unsigned char *)smb_var + sizeof(struct smb_hdr) + (2 * smb_var->WordCount) + 2)
 
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index b9f5e935f821..a729d083e6f4 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -172,12 +172,13 @@ extern int CIFSSMBQFSUnixInfo(const int xid, struct cifsTconInfo *tcon);
 extern int CIFSSMBQFSPosixInfo(const int xid, struct cifsTconInfo *tcon,
                         struct kstatfs *FSData);
 
-extern int CIFSSMBSetTimes(const int xid, struct cifsTconInfo *tcon,
+extern int CIFSSMBSetPathInfo(const int xid, struct cifsTconInfo *tcon,
                         const char *fileName, const FILE_BASIC_INFO *data,
                         const struct nls_table *nls_codepage,
                         int remap_special_chars);
-extern int CIFSSMBSetFileTimes(const int xid, struct cifsTconInfo *tcon,
-                        const FILE_BASIC_INFO *data, __u16 fid);
+extern int CIFSSMBSetFileInfo(const int xid, struct cifsTconInfo *tcon,
+                        const FILE_BASIC_INFO *data, __u16 fid,
+                        __u32 pid_of_opener);
 #if 0
 extern int CIFSSMBSetAttrLegacy(int xid, struct cifsTconInfo *tcon,
                         char *fileName, __u16 dos_attributes,
@@ -191,9 +192,20 @@ extern int CIFSSMBSetEOF(const int xid, struct cifsTconInfo *tcon,
 extern int CIFSSMBSetFileSize(const int xid, struct cifsTconInfo *tcon,
                          __u64 size, __u16 fileHandle, __u32 opener_pid,
                         bool AllocSizeFlag);
-extern int CIFSSMBUnixSetPerms(const int xid, struct cifsTconInfo *pTcon,
-                        char *full_path, __u64 mode, __u64 uid,
-                        __u64 gid, dev_t dev,
+
+struct cifs_unix_set_info_args {
+        __u64   ctime;
+        __u64   atime;
+        __u64   mtime;
+        __u64   mode;
+        __u64   uid;
+        __u64   gid;
+        dev_t   device;
+};
+
+extern int CIFSSMBUnixSetInfo(const int xid, struct cifsTconInfo *pTcon,
+                        char *fileName,
+                        const struct cifs_unix_set_info_args *args,
                         const struct nls_table *nls_codepage,
                         int remap_special_chars);
 
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 4511b708f0f3..994de7c90474 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -128,8 +128,7 @@ static void mark_open_files_invalid(struct cifsTconInfo *pTcon)
         write_lock(&GlobalSMBSeslock);
         list_for_each_safe(tmp, tmp1, &pTcon->openFileList) {
                 open_file = list_entry(tmp, struct cifsFileInfo, tlist);
-                if (open_file)
-                        open_file->invalidHandle = true;
+                open_file->invalidHandle = true;
         }
         write_unlock(&GlobalSMBSeslock);
         /* BB Add call to invalidate_inodes(sb) for all superblocks mounted
@@ -686,11 +685,10 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses)
                                                  SecurityBlob,
                                                  count - 16,
                                                  &server->secType);
-                        if (rc == 1) {
+                        if (rc == 1)
                                 rc = 0;
-                        } else {
+                        else
                                 rc = -EINVAL;
-                        }
                 }
         } else
                 server->capabilities &= ~CAP_EXTENDED_SECURITY;
@@ -3914,7 +3912,10 @@ parse_DFS_referrals(TRANSACTION2_GET_DFS_REFER_RSP *pSMBr,
         bool is_unicode;
         struct dfs_referral_level_3 *ref;
 
-        is_unicode = pSMBr->hdr.Flags2 & SMBFLG2_UNICODE;
+        if (pSMBr->hdr.Flags2 & SMBFLG2_UNICODE)
+                is_unicode = true;
+        else
+                is_unicode = false;
         *num_of_nodes = le16_to_cpu(pSMBr->NumberOfReferrals);
 
         if (*num_of_nodes < 1) {
@@ -4814,8 +4815,8 @@ CIFSSMBSetFileSize(const int xid, struct cifsTconInfo *tcon, __u64 size,
    time and resort to the original setpathinfo level which takes the ancient
    DOS time format with 2 second granularity */
 int
-CIFSSMBSetFileTimes(const int xid, struct cifsTconInfo *tcon,
-                    const FILE_BASIC_INFO *data, __u16 fid)
+CIFSSMBSetFileInfo(const int xid, struct cifsTconInfo *tcon,
+                    const FILE_BASIC_INFO *data, __u16 fid, __u32 pid_of_opener)
 {
         struct smb_com_transaction2_sfi_req *pSMB  = NULL;
         char *data_offset;
@@ -4828,11 +4829,8 @@ CIFSSMBSetFileTimes(const int xid, struct cifsTconInfo *tcon,
         if (rc)
                 return rc;
 
-        /* At this point there is no need to override the current pid
-        with the pid of the opener, but that could change if we someday
-        use an existing handle (rather than opening one on the fly) */
-        /* pSMB->hdr.Pid = cpu_to_le16((__u16)pid_of_opener);
-        pSMB->hdr.PidHigh = cpu_to_le16((__u16)(pid_of_opener >> 16));*/
+        pSMB->hdr.Pid = cpu_to_le16((__u16)pid_of_opener);
+        pSMB->hdr.PidHigh = cpu_to_le16((__u16)(pid_of_opener >> 16));
 
         params = 6;
         pSMB->MaxSetupCount = 0;
@@ -4880,9 +4878,9 @@ CIFSSMBSetFileTimes(const int xid, struct cifsTconInfo *tcon,
 
 
 int
-CIFSSMBSetTimes(const int xid, struct cifsTconInfo *tcon, const char *fileName,
-                const FILE_BASIC_INFO *data,
-                const struct nls_table *nls_codepage, int remap)
+CIFSSMBSetPathInfo(const int xid, struct cifsTconInfo *tcon,
+                   const char *fileName, const FILE_BASIC_INFO *data,
+                   const struct nls_table *nls_codepage, int remap)
 {
         TRANSACTION2_SPI_REQ *pSMB = NULL;
         TRANSACTION2_SPI_RSP *pSMBr = NULL;
@@ -5011,10 +5009,9 @@ SetAttrLgcyRetry:
 #endif /* temporarily unneeded SetAttr legacy function */
 
 int
-CIFSSMBUnixSetPerms(const int xid, struct cifsTconInfo *tcon,
-                    char *fileName, __u64 mode, __u64 uid, __u64 gid,
-                    dev_t device, const struct nls_table *nls_codepage,
-                    int remap)
+CIFSSMBUnixSetInfo(const int xid, struct cifsTconInfo *tcon, char *fileName,
+                   const struct cifs_unix_set_info_args *args,
+                   const struct nls_table *nls_codepage, int remap)
 {
         TRANSACTION2_SPI_REQ *pSMB = NULL;
         TRANSACTION2_SPI_RSP *pSMBr = NULL;
@@ -5023,6 +5020,7 @@ CIFSSMBUnixSetPerms(const int xid, struct cifsTconInfo *tcon,
         int bytes_returned = 0;
         FILE_UNIX_BASIC_INFO *data_offset;
         __u16 params, param_offset, offset, count, byte_count;
+        __u64 mode = args->mode;
 
         cFYI(1, ("In SetUID/GID/Mode"));
 setPermsRetry:
@@ -5078,16 +5076,16 @@ setPermsRetry:
         set file size and do not want to truncate file size to zero
         accidently as happened on one Samba server beta by putting
         zero instead of -1 here */
-        data_offset->EndOfFile = NO_CHANGE_64;
-        data_offset->NumOfBytes = NO_CHANGE_64;
-        data_offset->LastStatusChange = NO_CHANGE_64;
-        data_offset->LastAccessTime = NO_CHANGE_64;
-        data_offset->LastModificationTime = NO_CHANGE_64;
-        data_offset->Uid = cpu_to_le64(uid);
-        data_offset->Gid = cpu_to_le64(gid);
+        data_offset->EndOfFile = cpu_to_le64(NO_CHANGE_64);
+        data_offset->NumOfBytes = cpu_to_le64(NO_CHANGE_64);
+        data_offset->LastStatusChange = cpu_to_le64(args->ctime);
+        data_offset->LastAccessTime = cpu_to_le64(args->atime);
+        data_offset->LastModificationTime = cpu_to_le64(args->mtime);
+        data_offset->Uid = cpu_to_le64(args->uid);
+        data_offset->Gid = cpu_to_le64(args->gid);
         /* better to leave device as zero when it is  */
-        data_offset->DevMajor = cpu_to_le64(MAJOR(device));
-        data_offset->DevMinor = cpu_to_le64(MINOR(device));
+        data_offset->DevMajor = cpu_to_le64(MAJOR(args->device));
+        data_offset->DevMinor = cpu_to_le64(MINOR(args->device));
         data_offset->Permissions = cpu_to_le64(mode);
 
         if (S_ISREG(mode))
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index e8fa46c7cff2..0711db65afe8 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -151,7 +151,7 @@ cifs_reconnect(struct TCP_Server_Info *server)
         }
         list_for_each(tmp, &GlobalTreeConnectionList) {
                 tcon = list_entry(tmp, struct cifsTconInfo, cifsConnectionList);
-                if ((tcon) && (tcon->ses) && (tcon->ses->server == server))
+                if ((tcon->ses) && (tcon->ses->server == server))
                         tcon->tidStatus = CifsNeedReconnect;
         }
         read_unlock(&GlobalSMBSeslock);
@@ -173,14 +173,12 @@ cifs_reconnect(struct TCP_Server_Info *server)
                 mid_entry = list_entry(tmp, struct
                                         mid_q_entry,
                                         qhead);
-                if (mid_entry) {
-                        if (mid_entry->midState == MID_REQUEST_SUBMITTED) {
+                if (mid_entry->midState == MID_REQUEST_SUBMITTED) {
                                 /* Mark other intransit requests as needing
                                    retry so we do not immediately mark the
                                    session bad again (ie after we reconnect
                                    below) as they timeout too */
-                                mid_entry->midState = MID_RETRY_NEEDED;
-                        }
+                        mid_entry->midState = MID_RETRY_NEEDED;
                 }
         }
         spin_unlock(&GlobalMid_Lock);
@@ -351,11 +349,9 @@ cifs_demultiplex_thread(struct TCP_Server_Info *server)
 
         current->flags |= PF_MEMALLOC;
         cFYI(1, ("Demultiplex PID: %d", task_pid_nr(current)));
-        write_lock(&GlobalSMBSeslock);
-        atomic_inc(&tcpSesAllocCount);
-        length = tcpSesAllocCount.counter;
-        write_unlock(&GlobalSMBSeslock);
-        if (length  > 1)
+
+        length = atomic_inc_return(&tcpSesAllocCount);
+        if (length > 1)
                 mempool_resize(cifs_req_poolp, length + cifs_min_rcv,
                                 GFP_KERNEL);
 
@@ -455,7 +451,7 @@ incomplete_rcv:
                 /* Note that FC 1001 length is big endian on the wire,
                 but we convert it here so it is always manipulated
                 as host byte order */
-                pdu_length = ntohl(smb_buffer->smb_buf_length);
+                pdu_length = be32_to_cpu((__force __be32)smb_buffer->smb_buf_length);
                 smb_buffer->smb_buf_length = pdu_length;
 
                 cFYI(1, ("rfc1002 length 0x%x", pdu_length+4));
@@ -745,14 +741,11 @@ multi_t2_fnd:
                 coming home not much else we can do but free the memory */
         }
 
-        write_lock(&GlobalSMBSeslock);
-        atomic_dec(&tcpSesAllocCount);
-        length = tcpSesAllocCount.counter;
-
         /* last chance to mark ses pointers invalid
         if there are any pointing to this (e.g
         if a crazy root user tried to kill cifsd
         kernel thread explicitly this might happen) */
+        write_lock(&GlobalSMBSeslock);
         list_for_each(tmp, &GlobalSMBSessionList) {
                 ses = list_entry(tmp, struct cifsSesInfo,
                                 cifsSessionList);
@@ -763,6 +756,8 @@ multi_t2_fnd:
 
         kfree(server->hostname);
         kfree(server);
+
+        length = atomic_dec_return(&tcpSesAllocCount);
         if (length  > 0)
                 mempool_resize(cifs_req_poolp, length + cifs_min_rcv,
                                 GFP_KERNEL);
@@ -1461,6 +1456,39 @@ get_dfs_path(int xid, struct cifsSesInfo *pSesInfo, const char *old_path,
         return rc;
 }
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static struct lock_class_key cifs_key[2];
+static struct lock_class_key cifs_slock_key[2];
+
+static inline void
+cifs_reclassify_socket4(struct socket *sock)
+{
+        struct sock *sk = sock->sk;
+        BUG_ON(sock_owned_by_user(sk));
+        sock_lock_init_class_and_name(sk, "slock-AF_INET-CIFS",
+                &cifs_slock_key[0], "sk_lock-AF_INET-CIFS", &cifs_key[0]);
+}
+
+static inline void
+cifs_reclassify_socket6(struct socket *sock)
+{
+        struct sock *sk = sock->sk;
+        BUG_ON(sock_owned_by_user(sk));
+        sock_lock_init_class_and_name(sk, "slock-AF_INET6-CIFS",
+                &cifs_slock_key[1], "sk_lock-AF_INET6-CIFS", &cifs_key[1]);
+}
+#else
+static inline void
+cifs_reclassify_socket4(struct socket *sock)
+{
+}
+
+static inline void
+cifs_reclassify_socket6(struct socket *sock)
+{
+}
+#endif
+
 /* See RFC1001 section 14 on representation of Netbios names */
 static void rfc1002mangle(char *target, char *source, unsigned int length)
 {
@@ -1495,6 +1523,7 @@ ipv4_connect(struct sockaddr_in *psin_server, struct socket **csocket,
                 /* BB other socket options to set KEEPALIVE, NODELAY? */
                         cFYI(1, ("Socket created"));
                         (*csocket)->sk->sk_allocation = GFP_NOFS;
+                        cifs_reclassify_socket4(*csocket);
                 }
         }
 
@@ -1627,6 +1656,7 @@ ipv6_connect(struct sockaddr_in6 *psin_server, struct socket **csocket)
                 /* BB other socket options to set KEEPALIVE, NODELAY? */
                          cFYI(1, ("ipv6 Socket created"));
                         (*csocket)->sk->sk_allocation = GFP_NOFS;
+                        cifs_reclassify_socket6(*csocket);
                 }
         }
 
@@ -3588,97 +3618,91 @@ int cifs_setup_session(unsigned int xid, struct cifsSesInfo *pSesInfo,
                 }
                 first_time = 1;
         }
-        if (!rc) {
-                pSesInfo->flags = 0;
-                pSesInfo->capabilities = pSesInfo->server->capabilities;
-                if (linuxExtEnabled == 0)
-                        pSesInfo->capabilities &= (~CAP_UNIX);
+
+        if (rc)
+                goto ss_err_exit;
+
+        pSesInfo->flags = 0;
+        pSesInfo->capabilities = pSesInfo->server->capabilities;
+        if (linuxExtEnabled == 0)
+                pSesInfo->capabilities &= (~CAP_UNIX);
         /*      pSesInfo->sequence_number = 0;*/
-                cFYI(1,
-                      ("Security Mode: 0x%x Capabilities: 0x%x TimeAdjust: %d",
-                        pSesInfo->server->secMode,
-                        pSesInfo->server->capabilities,
-                        pSesInfo->server->timeAdj));
-                if (experimEnabled < 2)
-                        rc = CIFS_SessSetup(xid, pSesInfo,
-                                            first_time, nls_info);
-                else if (extended_security
-                                && (pSesInfo->capabilities
-                                        & CAP_EXTENDED_SECURITY)
-                                && (pSesInfo->server->secType == NTLMSSP)) {
-                        rc = -EOPNOTSUPP;
-                } else if (extended_security
-                           && (pSesInfo->capabilities & CAP_EXTENDED_SECURITY)
-                           && (pSesInfo->server->secType == RawNTLMSSP)) {
-                        cFYI(1, ("NTLMSSP sesssetup"));
-                        rc = CIFSNTLMSSPNegotiateSessSetup(xid,
-                                                pSesInfo,
-                                                &ntlmv2_flag,
-                                                nls_info);
-                        if (!rc) {
-                                if (ntlmv2_flag) {
-                                        char *v2_response;
-                                        cFYI(1, ("more secure NTLM ver2 hash"));
-                                        if (CalcNTLMv2_partial_mac_key(pSesInfo,
-                                                nls_info)) {
-                                                rc = -ENOMEM;
-                                                goto ss_err_exit;
-                                        } else
-                                                v2_response = kmalloc(16 + 64 /* blob */, GFP_KERNEL);
-                                        if (v2_response) {
-                                                CalcNTLMv2_response(pSesInfo,
-                                                                   v2_response);
-                                /*              if (first_time)
-                                                  cifs_calculate_ntlmv2_mac_key(
-                                                   pSesInfo->server->mac_signing_key,
-                                                   response, ntlm_session_key,*/
-                                                kfree(v2_response);
+        cFYI(1, ("Security Mode: 0x%x Capabilities: 0x%x TimeAdjust: %d",
+                 pSesInfo->server->secMode,
+                 pSesInfo->server->capabilities,
+                 pSesInfo->server->timeAdj));
+        if (experimEnabled < 2)
+                rc = CIFS_SessSetup(xid, pSesInfo, first_time, nls_info);
+        else if (extended_security
+                        && (pSesInfo->capabilities & CAP_EXTENDED_SECURITY)
+                        && (pSesInfo->server->secType == NTLMSSP)) {
+                rc = -EOPNOTSUPP;
+        } else if (extended_security
+                        && (pSesInfo->capabilities & CAP_EXTENDED_SECURITY)
+                        && (pSesInfo->server->secType == RawNTLMSSP)) {
+                cFYI(1, ("NTLMSSP sesssetup"));
+                rc = CIFSNTLMSSPNegotiateSessSetup(xid, pSesInfo, &ntlmv2_flag,
+                                                   nls_info);
+                if (!rc) {
+                        if (ntlmv2_flag) {
+                                char *v2_response;
+                                cFYI(1, ("more secure NTLM ver2 hash"));
+                                if (CalcNTLMv2_partial_mac_key(pSesInfo,
+                                                                nls_info)) {
+                                        rc = -ENOMEM;
+                                        goto ss_err_exit;
+                                } else
+                                        v2_response = kmalloc(16 + 64 /* blob*/,
+                                                                GFP_KERNEL);
+                                if (v2_response) {
+                                        CalcNTLMv2_response(pSesInfo,
+                                                                v2_response);
+                                /*      if (first_time)
+                                                cifs_calculate_ntlmv2_mac_key */
+                                        kfree(v2_response);
                                         /* BB Put dummy sig in SessSetup PDU? */
-                                        } else {
-                                                rc = -ENOMEM;
-                                                goto ss_err_exit;
-                                        }
-
                                 } else {
-                                        SMBNTencrypt(pSesInfo->password,
-                                                pSesInfo->server->cryptKey,
-                                                ntlm_session_key);
-
-                                        if (first_time)
-                                                cifs_calculate_mac_key(
-                                                        &pSesInfo->server->mac_signing_key,
-                                                        ntlm_session_key,
-                                                        pSesInfo->password);
+                                        rc = -ENOMEM;
+                                        goto ss_err_exit;
                                 }
+
+                        } else {
+                                SMBNTencrypt(pSesInfo->password,
+                                             pSesInfo->server->cryptKey,
+                                             ntlm_session_key);
+
+                                if (first_time)
+                                        cifs_calculate_mac_key(
+                                             &pSesInfo->server->mac_signing_key,
+                                             ntlm_session_key,
+                                             pSesInfo->password);
+                        }
                         /* for better security the weaker lanman hash not sent
                            in AuthSessSetup so we no longer calculate it */
 
-                                rc = CIFSNTLMSSPAuthSessSetup(xid,
-                                        pSesInfo,
-                                        ntlm_session_key,
-                                        ntlmv2_flag,
-                                        nls_info);
-                        }
-                } else { /* old style NTLM 0.12 session setup */
-                        SMBNTencrypt(pSesInfo->password,
-                                pSesInfo->server->cryptKey,
-                                ntlm_session_key);
+                        rc = CIFSNTLMSSPAuthSessSetup(xid, pSesInfo,
+                                                      ntlm_session_key,
+                                                      ntlmv2_flag,
+                                                      nls_info);
+                }
+        } else { /* old style NTLM 0.12 session setup */
+                SMBNTencrypt(pSesInfo->password, pSesInfo->server->cryptKey,
+                             ntlm_session_key);
 
-                        if (first_time)
-                                cifs_calculate_mac_key(
+                if (first_time)
+                        cifs_calculate_mac_key(
                                         &pSesInfo->server->mac_signing_key,
                                         ntlm_session_key, pSesInfo->password);
 
-                        rc = CIFSSessSetup(xid, pSesInfo,
-                                ntlm_session_key, nls_info);
-                }
-                if (rc) {
-                        cERROR(1, ("Send error in SessSetup = %d", rc));
-                } else {
-                        cFYI(1, ("CIFS Session Established successfully"));
+                rc = CIFSSessSetup(xid, pSesInfo, ntlm_session_key, nls_info);
+        }
+        if (rc) {
+                cERROR(1, ("Send error in SessSetup = %d", rc));
+        } else {
+                cFYI(1, ("CIFS Session Established successfully"));
                         pSesInfo->status = CifsGood;
-                }
         }
+
 ss_err_exit:
         return rc;
 }
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index fb69c1fa85c9..e962e75e6f7b 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -226,23 +226,28 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode,
                 /* If Open reported that we actually created a file
                 then we now have to set the mode if possible */
                 if ((pTcon->unix_ext) && (oplock & CIFS_CREATE_ACTION)) {
+                        struct cifs_unix_set_info_args args = {
+                                .mode   = mode,
+                                .ctime  = NO_CHANGE_64,
+                                .atime  = NO_CHANGE_64,
+                                .mtime  = NO_CHANGE_64,
+                                .device = 0,
+                        };
+
                         if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
-                                CIFSSMBUnixSetPerms(xid, pTcon, full_path, mode,
-                                        (__u64)current->fsuid,
-                                        (__u64)current->fsgid,
-                                        0 /* dev */,
-                                        cifs_sb->local_nls,
-                                        cifs_sb->mnt_cifs_flags &
-                                                CIFS_MOUNT_MAP_SPECIAL_CHR);
+                                args.uid = (__u64) current->fsuid;
+                                if (inode->i_mode & S_ISGID)
+                                        args.gid = (__u64) inode->i_gid;
+                                else
+                                        args.gid = (__u64) current->fsgid;
                         } else {
-                                CIFSSMBUnixSetPerms(xid, pTcon, full_path, mode,
-                                        (__u64)-1,
-                                        (__u64)-1,
-                                        0 /* dev */,
-                                        cifs_sb->local_nls,
-                                        cifs_sb->mnt_cifs_flags &
-                                                CIFS_MOUNT_MAP_SPECIAL_CHR);
+                                args.uid = NO_CHANGE_64;
+                                args.gid = NO_CHANGE_64;
                         }
+                        CIFSSMBUnixSetInfo(xid, pTcon, full_path, &args,
+                                cifs_sb->local_nls,
+                                cifs_sb->mnt_cifs_flags &
+                                        CIFS_MOUNT_MAP_SPECIAL_CHR);
                 } else {
                         /* BB implement mode setting via Windows security
                            descriptors e.g. */
@@ -267,7 +272,12 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode,
                                     (cifs_sb->mnt_cifs_flags &
                                      CIFS_MOUNT_SET_UID)) {
                                         newinode->i_uid = current->fsuid;
-                                        newinode->i_gid = current->fsgid;
+                                        if (inode->i_mode & S_ISGID)
+                                                newinode->i_gid =
+                                                        inode->i_gid;
+                                        else
+                                                newinode->i_gid =
+                                                        current->fsgid;
                                 }
                         }
                 }
@@ -357,21 +367,24 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, int mode,
         if (full_path == NULL)
                 rc = -ENOMEM;
         else if (pTcon->unix_ext) {
-                mode &= ~current->fs->umask;
+                struct cifs_unix_set_info_args args = {
+                        .mode   = mode & ~current->fs->umask,
+                        .ctime  = NO_CHANGE_64,
+                        .atime  = NO_CHANGE_64,
+                        .mtime  = NO_CHANGE_64,
+                        .device = device_number,
+                };
                 if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
-                        rc = CIFSSMBUnixSetPerms(xid, pTcon, full_path,
-                                mode, (__u64)current->fsuid,
-                                (__u64)current->fsgid,
-                                device_number, cifs_sb->local_nls,
-                                cifs_sb->mnt_cifs_flags &
-                                        CIFS_MOUNT_MAP_SPECIAL_CHR);
+                        args.uid = (__u64) current->fsuid;
+                        args.gid = (__u64) current->fsgid;
                 } else {
-                        rc = CIFSSMBUnixSetPerms(xid, pTcon,
-                                full_path, mode, (__u64)-1, (__u64)-1,
-                                device_number, cifs_sb->local_nls,
-                                cifs_sb->mnt_cifs_flags &
-                                        CIFS_MOUNT_MAP_SPECIAL_CHR);
+                        args.uid = NO_CHANGE_64;
+                        args.gid = NO_CHANGE_64;
                 }
+                rc = CIFSSMBUnixSetInfo(xid, pTcon, full_path,
+                        &args, cifs_sb->local_nls,
+                        cifs_sb->mnt_cifs_flags &
+                                CIFS_MOUNT_MAP_SPECIAL_CHR);
 
                 if (!rc) {
                         rc = cifs_get_inode_info_unix(&newinode, full_path,
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 0aac824371a5..ff14d14903a0 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -310,18 +310,19 @@ int cifs_open(struct inode *inode, struct file *file)
                 /* time to set mode which we can not set earlier due to
                    problems creating new read-only files */
                 if (pTcon->unix_ext) {
-                        CIFSSMBUnixSetPerms(xid, pTcon, full_path,
-                                            inode->i_mode,
-                                            (__u64)-1, (__u64)-1, 0 /* dev */,
+                        struct cifs_unix_set_info_args args = {
+                                .mode   = inode->i_mode,
+                                .uid    = NO_CHANGE_64,
+                                .gid    = NO_CHANGE_64,
+                                .ctime  = NO_CHANGE_64,
+                                .atime  = NO_CHANGE_64,
+                                .mtime  = NO_CHANGE_64,
+                                .device = 0,
+                        };
+                        CIFSSMBUnixSetInfo(xid, pTcon, full_path, &args,
                                             cifs_sb->local_nls,
                                             cifs_sb->mnt_cifs_flags &
                                                 CIFS_MOUNT_MAP_SPECIAL_CHR);
-                } else {
-                        /* BB implement via Windows security descriptors eg
-                           CIFSSMBWinSetPerms(xid, pTcon, full_path, mode,
-                                              -1, -1, local_nls);
-                           in the meantime could set r/o dos attribute when
-                           perms are eg: mode & 0222 == 0 */
                 }
         }
 
@@ -1280,7 +1281,7 @@ retry:
 
                         if (first < 0)
                                 lock_page(page);
-                        else if (TestSetPageLocked(page))
+                        else if (!trylock_page(page))
                                 break;
 
                         if (unlikely(page->mapping != mapping)) {
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 2e904bd111c8..28a22092d450 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -737,7 +737,7 @@ psx_del_no_retry:
                         /* ATTRS set to normal clears r/o bit */
                         pinfo_buf->Attributes = cpu_to_le32(ATTR_NORMAL);
                         if (!(pTcon->ses->flags & CIFS_SES_NT4))
-                                rc = CIFSSMBSetTimes(xid, pTcon, full_path,
+                                rc = CIFSSMBSetPathInfo(xid, pTcon, full_path,
                                                      pinfo_buf,
                                                      cifs_sb->local_nls,
                                                      cifs_sb->mnt_cifs_flags &
@@ -767,9 +767,10 @@ psx_del_no_retry:
                                                  cifs_sb->mnt_cifs_flags &
                                                     CIFS_MOUNT_MAP_SPECIAL_CHR);
                                 if (rc == 0) {
-                                        rc = CIFSSMBSetFileTimes(xid, pTcon,
-                                                                 pinfo_buf,
-                                                                 netfid);
+                                        rc = CIFSSMBSetFileInfo(xid, pTcon,
+                                                                pinfo_buf,
+                                                                netfid,
+                                                                current->tgid);
                                         CIFSSMBClose(xid, pTcon, netfid);
                                 }
                         }
@@ -984,32 +985,41 @@ mkdir_get_info:
                   * failed to get it from the server or was set bogus */
                 if ((direntry->d_inode) && (direntry->d_inode->i_nlink < 2))
                                 direntry->d_inode->i_nlink = 2;
+
                 mode &= ~current->fs->umask;
+                /* must turn on setgid bit if parent dir has it */
+                if (inode->i_mode & S_ISGID)
+                        mode |= S_ISGID;
+
                 if (pTcon->unix_ext) {
+                        struct cifs_unix_set_info_args args = {
+                                .mode   = mode,
+                                .ctime  = NO_CHANGE_64,
+                                .atime  = NO_CHANGE_64,
+                                .mtime  = NO_CHANGE_64,
+                                .device = 0,
+                        };
                         if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
-                                CIFSSMBUnixSetPerms(xid, pTcon, full_path,
-                                                    mode,
-                                                    (__u64)current->fsuid,
-                                                    (__u64)current->fsgid,
-                                                    0 /* dev_t */,
-                                                    cifs_sb->local_nls,
-                                                    cifs_sb->mnt_cifs_flags &
-                                                    CIFS_MOUNT_MAP_SPECIAL_CHR);
+                                args.uid = (__u64)current->fsuid;
+                                if (inode->i_mode & S_ISGID)
+                                        args.gid = (__u64)inode->i_gid;
+                                else
+                                        args.gid = (__u64)current->fsgid;
                         } else {
-                                CIFSSMBUnixSetPerms(xid, pTcon, full_path,
-                                                    mode, (__u64)-1,
-                                                    (__u64)-1, 0 /* dev_t */,
-                                                    cifs_sb->local_nls,
-                                                    cifs_sb->mnt_cifs_flags &
-                                                    CIFS_MOUNT_MAP_SPECIAL_CHR);
+                                args.uid = NO_CHANGE_64;
+                                args.gid = NO_CHANGE_64;
                         }
+                        CIFSSMBUnixSetInfo(xid, pTcon, full_path, &args,
+                                            cifs_sb->local_nls,
+                                            cifs_sb->mnt_cifs_flags &
+                                            CIFS_MOUNT_MAP_SPECIAL_CHR);
                 } else {
                         if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) &&
                             (mode & S_IWUGO) == 0) {
                                 FILE_BASIC_INFO pInfo;
                                 memset(&pInfo, 0, sizeof(pInfo));
                                 pInfo.Attributes = cpu_to_le32(ATTR_READONLY);
-                                CIFSSMBSetTimes(xid, pTcon, full_path,
+                                CIFSSMBSetPathInfo(xid, pTcon, full_path,
                                                 &pInfo, cifs_sb->local_nls,
                                                 cifs_sb->mnt_cifs_flags &
                                                 CIFS_MOUNT_MAP_SPECIAL_CHR);
@@ -1024,8 +1034,12 @@ mkdir_get_info:
                                      CIFS_MOUNT_SET_UID) {
                                         direntry->d_inode->i_uid =
                                                 current->fsuid;
-                                        direntry->d_inode->i_gid =
-                                                current->fsgid;
+                                        if (inode->i_mode & S_ISGID)
+                                                direntry->d_inode->i_gid =
+                                                        inode->i_gid;
+                                        else
+                                                direntry->d_inode->i_gid =
+                                                        current->fsgid;
                                 }
                         }
                 }
@@ -1310,10 +1324,11 @@ int cifs_revalidate(struct dentry *direntry)
 /*              if (S_ISDIR(direntry->d_inode->i_mode))
                         shrink_dcache_parent(direntry); */
                 if (S_ISREG(direntry->d_inode->i_mode)) {
-                        if (direntry->d_inode->i_mapping)
+                        if (direntry->d_inode->i_mapping) {
                                 wbrc = filemap_fdatawait(direntry->d_inode->i_mapping);
                                 if (wbrc)
                                         CIFS_I(direntry->d_inode)->write_behind_rc = wbrc;
+                        }
                         /* may eventually have to do this for open files too */
                         if (list_empty(&(cifsInode->openFileList))) {
                                 /* changed on server - flush read ahead pages */
@@ -1413,31 +1428,304 @@ out_busy:
         return -ETXTBSY;
 }
 
-int cifs_setattr(struct dentry *direntry, struct iattr *attrs)
+static int
+cifs_set_file_size(struct inode *inode, struct iattr *attrs,
+                   int xid, char *full_path)
 {
+        int rc;
+        struct cifsFileInfo *open_file;
+        struct cifsInodeInfo *cifsInode = CIFS_I(inode);
+        struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+        struct cifsTconInfo *pTcon = cifs_sb->tcon;
+
+        /*
+         * To avoid spurious oplock breaks from server, in the case of
+         * inodes that we already have open, avoid doing path based
+         * setting of file size if we can do it by handle.
+         * This keeps our caching token (oplock) and avoids timeouts
+         * when the local oplock break takes longer to flush
+         * writebehind data than the SMB timeout for the SetPathInfo
+         * request would allow
+         */
+        open_file = find_writable_file(cifsInode);
+        if (open_file) {
+                __u16 nfid = open_file->netfid;
+                __u32 npid = open_file->pid;
+                rc = CIFSSMBSetFileSize(xid, pTcon, attrs->ia_size, nfid,
+                                        npid, false);
+                atomic_dec(&open_file->wrtPending);
+                cFYI(1, ("SetFSize for attrs rc = %d", rc));
+                if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) {
+                        unsigned int bytes_written;
+                        rc = CIFSSMBWrite(xid, pTcon, nfid, 0, attrs->ia_size,
+                                          &bytes_written, NULL, NULL, 1);
+                        cFYI(1, ("Wrt seteof rc %d", rc));
+                }
+        } else
+                rc = -EINVAL;
+
+        if (rc != 0) {
+                /* Set file size by pathname rather than by handle
+                   either because no valid, writeable file handle for
+                   it was found or because there was an error setting
+                   it by handle */
+                rc = CIFSSMBSetEOF(xid, pTcon, full_path, attrs->ia_size,
+                                   false, cifs_sb->local_nls,
+                                   cifs_sb->mnt_cifs_flags &
+                                        CIFS_MOUNT_MAP_SPECIAL_CHR);
+                cFYI(1, ("SetEOF by path (setattrs) rc = %d", rc));
+                if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) {
+                        __u16 netfid;
+                        int oplock = 0;
+
+                        rc = SMBLegacyOpen(xid, pTcon, full_path,
+                                FILE_OPEN, GENERIC_WRITE,
+                                CREATE_NOT_DIR, &netfid, &oplock, NULL,
+                                cifs_sb->local_nls,
+                                cifs_sb->mnt_cifs_flags &
+                                        CIFS_MOUNT_MAP_SPECIAL_CHR);
+                        if (rc == 0) {
+                                unsigned int bytes_written;
+                                rc = CIFSSMBWrite(xid, pTcon, netfid, 0,
+                                                  attrs->ia_size,
+                                                  &bytes_written, NULL,
+                                                  NULL, 1);
+                                cFYI(1, ("wrt seteof rc %d", rc));
+                                CIFSSMBClose(xid, pTcon, netfid);
+                        }
+                }
+        }
+
+        if (rc == 0) {
+                rc = cifs_vmtruncate(inode, attrs->ia_size);
+                cifs_truncate_page(inode->i_mapping, inode->i_size);
+        }
+
+        return rc;
+}
+
+static int
+cifs_set_file_info(struct inode *inode, struct iattr *attrs, int xid,
+                    char *full_path, __u32 dosattr)
+{
+        int rc;
+        int oplock = 0;
+        __u16 netfid;
+        __u32 netpid;
+        bool set_time = false;
+        struct cifsFileInfo *open_file;
+        struct cifsInodeInfo *cifsInode = CIFS_I(inode);
+        struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+        struct cifsTconInfo *pTcon = cifs_sb->tcon;
+        FILE_BASIC_INFO info_buf;
+
+        if (attrs->ia_valid & ATTR_ATIME) {
+                set_time = true;
+                info_buf.LastAccessTime =
+                        cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_atime));
+        } else
+                info_buf.LastAccessTime = 0;
+
+        if (attrs->ia_valid & ATTR_MTIME) {
+                set_time = true;
+                info_buf.LastWriteTime =
+                    cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_mtime));
+        } else
+                info_buf.LastWriteTime = 0;
+
+        /*
+         * Samba throws this field away, but windows may actually use it.
+         * Do not set ctime unless other time stamps are changed explicitly
+         * (i.e. by utimes()) since we would then have a mix of client and
+         * server times.
+         */
+        if (set_time && (attrs->ia_valid & ATTR_CTIME)) {
+                cFYI(1, ("CIFS - CTIME changed"));
+                info_buf.ChangeTime =
+                    cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_ctime));
+        } else
+                info_buf.ChangeTime = 0;
+
+        info_buf.CreationTime = 0;      /* don't change */
+        info_buf.Attributes = cpu_to_le32(dosattr);
+
+        /*
+         * If the file is already open for write, just use that fileid
+         */
+        open_file = find_writable_file(cifsInode);
+        if (open_file) {
+                netfid = open_file->netfid;
+                netpid = open_file->pid;
+                goto set_via_filehandle;
+        }
+
+        /*
+         * NT4 apparently returns success on this call, but it doesn't
+         * really work.
+         */
+        if (!(pTcon->ses->flags & CIFS_SES_NT4)) {
+                rc = CIFSSMBSetPathInfo(xid, pTcon, full_path,
+                                     &info_buf, cifs_sb->local_nls,
+                                     cifs_sb->mnt_cifs_flags &
+                                        CIFS_MOUNT_MAP_SPECIAL_CHR);
+                if (rc != -EOPNOTSUPP && rc != -EINVAL)
+                        goto out;
+        }
+
+        cFYI(1, ("calling SetFileInfo since SetPathInfo for "
+                 "times not supported by this server"));
+        rc = CIFSSMBOpen(xid, pTcon, full_path, FILE_OPEN,
+                         SYNCHRONIZE | FILE_WRITE_ATTRIBUTES,
+                         CREATE_NOT_DIR, &netfid, &oplock,
+                         NULL, cifs_sb->local_nls,
+                         cifs_sb->mnt_cifs_flags &
+                                CIFS_MOUNT_MAP_SPECIAL_CHR);
+
+        if (rc != 0) {
+                if (rc == -EIO)
+                        rc = -EINVAL;
+                goto out;
+        }
+
+        netpid = current->tgid;
+
+set_via_filehandle:
+        rc = CIFSSMBSetFileInfo(xid, pTcon, &info_buf, netfid, netpid);
+        if (open_file == NULL)
+                CIFSSMBClose(xid, pTcon, netfid);
+        else
+                atomic_dec(&open_file->wrtPending);
+out:
+        return rc;
+}
+
+static int
+cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
+{
+        int rc;
         int xid;
-        struct cifs_sb_info *cifs_sb;
-        struct cifsTconInfo *pTcon;
         char *full_path = NULL;
-        int rc = -EACCES;
-        struct cifsFileInfo *open_file = NULL;
-        FILE_BASIC_INFO time_buf;
-        bool set_time = false;
-        bool set_dosattr = false;
-        __u64 mode = 0xFFFFFFFFFFFFFFFFULL;
-        __u64 uid = 0xFFFFFFFFFFFFFFFFULL;
-        __u64 gid = 0xFFFFFFFFFFFFFFFFULL;
-        struct cifsInodeInfo *cifsInode;
         struct inode *inode = direntry->d_inode;
+        struct cifsInodeInfo *cifsInode = CIFS_I(inode);
+        struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+        struct cifsTconInfo *pTcon = cifs_sb->tcon;
+        struct cifs_unix_set_info_args *args = NULL;
+
+        cFYI(1, ("setattr_unix on file %s attrs->ia_valid=0x%x",
+                 direntry->d_name.name, attrs->ia_valid));
+
+        xid = GetXid();
+
+        if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) == 0) {
+                /* check if we have permission to change attrs */
+                rc = inode_change_ok(inode, attrs);
+                if (rc < 0)
+                        goto out;
+                else
+                        rc = 0;
+        }
+
+        full_path = build_path_from_dentry(direntry);
+        if (full_path == NULL) {
+                rc = -ENOMEM;
+                goto out;
+        }
+
+        if ((attrs->ia_valid & ATTR_MTIME) || (attrs->ia_valid & ATTR_SIZE)) {
+                /*
+                   Flush data before changing file size or changing the last
+                   write time of the file on the server. If the
+                   flush returns error, store it to report later and continue.
+                   BB: This should be smarter. Why bother flushing pages that
+                   will be truncated anyway? Also, should we error out here if
+                   the flush returns error?
+                 */
+                rc = filemap_write_and_wait(inode->i_mapping);
+                if (rc != 0) {
+                        cifsInode->write_behind_rc = rc;
+                        rc = 0;
+                }
+        }
+
+        if (attrs->ia_valid & ATTR_SIZE) {
+                rc = cifs_set_file_size(inode, attrs, xid, full_path);
+                if (rc != 0)
+                        goto out;
+        }
+
+        /* skip mode change if it's just for clearing setuid/setgid */
+        if (attrs->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID))
+                attrs->ia_valid &= ~ATTR_MODE;
+
+        args = kmalloc(sizeof(*args), GFP_KERNEL);
+        if (args == NULL) {
+                rc = -ENOMEM;
+                goto out;
+        }
+
+        /* set up the struct */
+        if (attrs->ia_valid & ATTR_MODE)
+                args->mode = attrs->ia_mode;
+        else
+                args->mode = NO_CHANGE_64;
+
+        if (attrs->ia_valid & ATTR_UID)
+                args->uid = attrs->ia_uid;
+        else
+                args->uid = NO_CHANGE_64;
+
+        if (attrs->ia_valid & ATTR_GID)
+                args->gid = attrs->ia_gid;
+        else
+                args->gid = NO_CHANGE_64;
+
+        if (attrs->ia_valid & ATTR_ATIME)
+                args->atime = cifs_UnixTimeToNT(attrs->ia_atime);
+        else
+                args->atime = NO_CHANGE_64;
+
+        if (attrs->ia_valid & ATTR_MTIME)
+                args->mtime = cifs_UnixTimeToNT(attrs->ia_mtime);
+        else
+                args->mtime = NO_CHANGE_64;
+
+        if (attrs->ia_valid & ATTR_CTIME)
+                args->ctime = cifs_UnixTimeToNT(attrs->ia_ctime);
+        else
+                args->ctime = NO_CHANGE_64;
+
+        args->device = 0;
+        rc = CIFSSMBUnixSetInfo(xid, pTcon, full_path, args,
+                                cifs_sb->local_nls,
+                                cifs_sb->mnt_cifs_flags &
+                                CIFS_MOUNT_MAP_SPECIAL_CHR);
+
+        if (!rc)
+                rc = inode_setattr(inode, attrs);
+out:
+        kfree(args);
+        kfree(full_path);
+        FreeXid(xid);
+        return rc;
+}
+
+static int
+cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
+{
+        int xid;
+        struct inode *inode = direntry->d_inode;
+        struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+        struct cifsInodeInfo *cifsInode = CIFS_I(inode);
+        char *full_path = NULL;
+        int rc = -EACCES;
+        __u32 dosattr = 0;
+        __u64 mode = NO_CHANGE_64;
 
         xid = GetXid();
 
         cFYI(1, ("setattr on file %s attrs->iavalid 0x%x",
                  direntry->d_name.name, attrs->ia_valid));
 
-        cifs_sb = CIFS_SB(inode->i_sb);
-        pTcon = cifs_sb->tcon;
-
         if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) == 0) {
                 /* check if we have permission to change attrs */
                 rc = inode_change_ok(inode, attrs);
@@ -1453,7 +1741,6 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs)
                 FreeXid(xid);
                 return -ENOMEM;
         }
-        cifsInode = CIFS_I(inode);
 
         if ((attrs->ia_valid & ATTR_MTIME) || (attrs->ia_valid & ATTR_SIZE)) {
                 /*
@@ -1472,78 +1759,8 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs)
         }
 
         if (attrs->ia_valid & ATTR_SIZE) {
-                /* To avoid spurious oplock breaks from server, in the case of
-                   inodes that we already have open, avoid doing path based
-                   setting of file size if we can do it by handle.
-                   This keeps our caching token (oplock) and avoids timeouts
-                   when the local oplock break takes longer to flush
-                   writebehind data than the SMB timeout for the SetPathInfo
-                   request would allow */
-
-                open_file = find_writable_file(cifsInode);
-                if (open_file) {
-                        __u16 nfid = open_file->netfid;
-                        __u32 npid = open_file->pid;
-                        rc = CIFSSMBSetFileSize(xid, pTcon, attrs->ia_size,
-                                                nfid, npid, false);
-                        atomic_dec(&open_file->wrtPending);
-                        cFYI(1, ("SetFSize for attrs rc = %d", rc));
-                        if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) {
-                                unsigned int bytes_written;
-                                rc = CIFSSMBWrite(xid, pTcon,
-                                                  nfid, 0, attrs->ia_size,
-                                                  &bytes_written, NULL, NULL,
-                                                  1 /* 45 seconds */);
-                                cFYI(1, ("Wrt seteof rc %d", rc));
-                        }
-                } else
-                        rc = -EINVAL;
-
-                if (rc != 0) {
-                        /* Set file size by pathname rather than by handle
-                           either because no valid, writeable file handle for
-                           it was found or because there was an error setting
-                           it by handle */
-                        rc = CIFSSMBSetEOF(xid, pTcon, full_path,
-                                           attrs->ia_size, false,
-                                           cifs_sb->local_nls,
-                                           cifs_sb->mnt_cifs_flags &
-                                                CIFS_MOUNT_MAP_SPECIAL_CHR);
-                        cFYI(1, ("SetEOF by path (setattrs) rc = %d", rc));
-                        if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) {
-                                __u16 netfid;
-                                int oplock = 0;
-
-                                rc = SMBLegacyOpen(xid, pTcon, full_path,
-                                        FILE_OPEN, GENERIC_WRITE,
-                                        CREATE_NOT_DIR, &netfid, &oplock,
-                                        NULL, cifs_sb->local_nls,
-                                        cifs_sb->mnt_cifs_flags &
-                                                CIFS_MOUNT_MAP_SPECIAL_CHR);
-                                if (rc == 0) {
-                                        unsigned int bytes_written;
-                                        rc = CIFSSMBWrite(xid, pTcon,
-                                                        netfid, 0,
-                                                        attrs->ia_size,
-                                                        &bytes_written, NULL,
-                                                        NULL, 1 /* 45 sec */);
-                                        cFYI(1, ("wrt seteof rc %d", rc));
-                                        CIFSSMBClose(xid, pTcon, netfid);
-                                }
-
-                        }
-                }
-
-                /* Server is ok setting allocation size implicitly - no need
-                   to call:
-                CIFSSMBSetEOF(xid, pTcon, full_path, attrs->ia_size, true,
-                         cifs_sb->local_nls);
-                   */
-
-                if (rc == 0) {
-                        rc = cifs_vmtruncate(inode, attrs->ia_size);
-                        cifs_truncate_page(inode->i_mapping, inode->i_size);
-                } else
+                rc = cifs_set_file_size(inode, attrs, xid, full_path);
+                if (rc != 0)
                         goto cifs_setattr_exit;
         }
 
@@ -1554,21 +1771,8 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs)
          * CIFSACL support + proper Windows to Unix idmapping, we may be
          * able to support this in the future.
          */
-        if (!pTcon->unix_ext &&
-            !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)) {
+        if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID))
                 attrs->ia_valid &= ~(ATTR_UID | ATTR_GID);
-        } else {
-                if (attrs->ia_valid & ATTR_UID) {
-                        cFYI(1, ("UID changed to %d", attrs->ia_uid));
-                        uid = attrs->ia_uid;
-                }
-                if (attrs->ia_valid & ATTR_GID) {
-                        cFYI(1, ("GID changed to %d", attrs->ia_gid));
-                        gid = attrs->ia_gid;
-                }
-        }
-
-        time_buf.Attributes = 0;
 
         /* skip mode change if it's just for clearing setuid/setgid */
         if (attrs->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID))
@@ -1579,13 +1783,7 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs)
                 mode = attrs->ia_mode;
         }
 
-        if ((pTcon->unix_ext)
-            && (attrs->ia_valid & (ATTR_MODE | ATTR_GID | ATTR_UID)))
-                rc = CIFSSMBUnixSetPerms(xid, pTcon, full_path, mode, uid, gid,
-                                         0 /* dev_t */, cifs_sb->local_nls,
-                                         cifs_sb->mnt_cifs_flags &
-                                                CIFS_MOUNT_MAP_SPECIAL_CHR);
-        else if (attrs->ia_valid & ATTR_MODE) {
+        if (attrs->ia_valid & ATTR_MODE) {
                 rc = 0;
 #ifdef CONFIG_CIFS_EXPERIMENTAL
                 if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL)
@@ -1594,24 +1792,19 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs)
 #endif
                 if (((mode & S_IWUGO) == 0) &&
                     (cifsInode->cifsAttrs & ATTR_READONLY) == 0) {
-                        set_dosattr = true;
-                        time_buf.Attributes = cpu_to_le32(cifsInode->cifsAttrs |
-                                                          ATTR_READONLY);
+
+                        dosattr = cifsInode->cifsAttrs | ATTR_READONLY;
+
                         /* fix up mode if we're not using dynperm */
                         if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM) == 0)
                                 attrs->ia_mode = inode->i_mode & ~S_IWUGO;
                 } else if ((mode & S_IWUGO) &&
                            (cifsInode->cifsAttrs & ATTR_READONLY)) {
-                        /* If file is readonly on server, we would
-                        not be able to write to it - so if any write
-                        bit is enabled for user or group or other we
-                        need to at least try to remove r/o dos attr */
-                        set_dosattr = true;
-                        time_buf.Attributes = cpu_to_le32(cifsInode->cifsAttrs &
-                                            (~ATTR_READONLY));
-                        /* Windows ignores set to zero */
-                        if (time_buf.Attributes == 0)
-                                time_buf.Attributes |= cpu_to_le32(ATTR_NORMAL);
+
+                        dosattr = cifsInode->cifsAttrs & ~ATTR_READONLY;
+                        /* Attributes of 0 are ignored */
+                        if (dosattr == 0)
+                                dosattr |= ATTR_NORMAL;
 
                         /* reset local inode permissions to normal */
                         if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)) {
@@ -1629,82 +1822,18 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs)
                 }
         }
 
-        if (attrs->ia_valid & ATTR_ATIME) {
-                set_time = true;
-                time_buf.LastAccessTime =
-                    cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_atime));
-        } else
-                time_buf.LastAccessTime = 0;
-
-        if (attrs->ia_valid & ATTR_MTIME) {
-                set_time = true;
-                time_buf.LastWriteTime =
-                    cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_mtime));
-        } else
-                time_buf.LastWriteTime = 0;
-        /* Do not set ctime explicitly unless other time
-           stamps are changed explicitly (i.e. by utime()
-           since we would then have a mix of client and
-           server times */
-
-        if (set_time && (attrs->ia_valid & ATTR_CTIME)) {
-                set_time = true;
-                /* Although Samba throws this field away
-                it may be useful to Windows - but we do
-                not want to set ctime unless some other
-                timestamp is changing */
-                cFYI(1, ("CIFS - CTIME changed"));
-                time_buf.ChangeTime =
-                    cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_ctime));
-        } else
-                time_buf.ChangeTime = 0;
-
-        if (set_time || set_dosattr) {
-                time_buf.CreationTime = 0;      /* do not change */
-                /* In the future we should experiment - try setting timestamps
-                   via Handle (SetFileInfo) instead of by path */
-                if (!(pTcon->ses->flags & CIFS_SES_NT4))
-                        rc = CIFSSMBSetTimes(xid, pTcon, full_path, &time_buf,
-                                             cifs_sb->local_nls,
-                                             cifs_sb->mnt_cifs_flags &
-                                                CIFS_MOUNT_MAP_SPECIAL_CHR);
-                else
-                        rc = -EOPNOTSUPP;
+        if (attrs->ia_valid & (ATTR_MTIME|ATTR_ATIME|ATTR_CTIME) ||
+            ((attrs->ia_valid & ATTR_MODE) && dosattr)) {
+                rc = cifs_set_file_info(inode, attrs, xid, full_path, dosattr);
+                /* BB: check for rc = -EOPNOTSUPP and switch to legacy mode */
 
-                if (rc == -EOPNOTSUPP) {
-                        int oplock = 0;
-                        __u16 netfid;
-
-                        cFYI(1, ("calling SetFileInfo since SetPathInfo for "
-                                 "times not supported by this server"));
-                        /* BB we could scan to see if we already have it open
-                           and pass in pid of opener to function */
-                        rc = CIFSSMBOpen(xid, pTcon, full_path, FILE_OPEN,
-                                         SYNCHRONIZE | FILE_WRITE_ATTRIBUTES,
-                                         CREATE_NOT_DIR, &netfid, &oplock,
-                                         NULL, cifs_sb->local_nls,
-                                         cifs_sb->mnt_cifs_flags &
-                                                CIFS_MOUNT_MAP_SPECIAL_CHR);
-                        if (rc == 0) {
-                                rc = CIFSSMBSetFileTimes(xid, pTcon, &time_buf,
-                                                         netfid);
-                                CIFSSMBClose(xid, pTcon, netfid);
-                        } else {
-                        /* BB For even older servers we could convert time_buf
-                           into old DOS style which uses two second
-                           granularity */
-
-                        /* rc = CIFSSMBSetTimesLegacy(xid, pTcon, full_path,
-                                        &time_buf, cifs_sb->local_nls); */
-                        }
-                }
                 /* Even if error on time set, no sense failing the call if
                 the server would set the time to a reasonable value anyway,
                 and this check ensures that we are not being called from
                 sys_utimes in which case we ought to fail the call back to
                 the user when the server rejects the call */
                 if ((rc) && (attrs->ia_valid &
-                         (ATTR_MODE | ATTR_GID | ATTR_UID | ATTR_SIZE)))
+                                (ATTR_MODE | ATTR_GID | ATTR_UID | ATTR_SIZE)))
                         rc = 0;
         }
 
@@ -1718,6 +1847,21 @@ cifs_setattr_exit:
         return rc;
 }
 
+int
+cifs_setattr(struct dentry *direntry, struct iattr *attrs)
+{
+        struct inode *inode = direntry->d_inode;
+        struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+        struct cifsTconInfo *pTcon = cifs_sb->tcon;
+
+        if (pTcon->unix_ext)
+                return cifs_setattr_unix(direntry, attrs);
+
+        return cifs_setattr_nounix(direntry, attrs);
+
+        /* BB: add cifs_setattr_legacy for really old servers */
+}
+
 #if 0
 void cifs_delete_inode(struct inode *inode)
 {
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 83f306954883..5f40ed3473f5 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -690,6 +690,7 @@ static int find_cifs_entry(const int xid, struct cifsTconInfo *pTcon,
                         else
                                 cifs_buf_release(cifsFile->srch_inf.
                                                 ntwrk_buf_start);
+                        cifsFile->srch_inf.ntwrk_buf_start = NULL;
                 }
                 rc = initiate_cifs_search(xid, file);
                 if (rc) {
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 000ac509c98a..e286db9f5ee2 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -265,6 +265,7 @@ smb_send2(struct socket *ssocket, struct kvec *iov, int n_vec,
         cFYI(1, ("Sending smb:  total_len %d", total_len));
         dump_smb(smb_buffer, len);
 
+        i = 0;
         while (total_len) {
                 rc = kernel_sendmsg(ssocket, &smb_msg, &iov[first_vec],
                                     n_vec - first_vec, total_len);
diff --git a/fs/coda/coda_linux.c b/fs/coda/coda_linux.c
index e1c854890f94..bf4a3fd3c8e3 100644
--- a/fs/coda/coda_linux.c
+++ b/fs/coda/coda_linux.c
@@ -28,11 +28,9 @@ int coda_fake_statfs;
 char * coda_f2s(struct CodaFid *f)
 {
         static char s[60];
-#ifdef CONFIG_CODA_FS_OLD_API
-        sprintf(s, "(%08x.%08x.%08x)", f->opaque[0], f->opaque[1], f->opaque[2]);
-#else
+
         sprintf(s, "(%08x.%08x.%08x.%08x)", f->opaque[0], f->opaque[1], f->opaque[2], f->opaque[3]);
-#endif
+
         return s;
 }
 
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index 3d2580e00a3e..c5916228243c 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -137,9 +137,11 @@ exit:
 }
 
 
-int coda_permission(struct inode *inode, int mask, struct nameidata *nd)
+int coda_permission(struct inode *inode, int mask)
 {
         int error = 0;
+
+        mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
  
         if (!mask)
                 return 0; 
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index 2f58dfc70083..830f51abb971 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -58,7 +58,7 @@ static void coda_destroy_inode(struct inode *inode)
         kmem_cache_free(coda_inode_cachep, ITOC(inode));
 }
 
-static void init_once(struct kmem_cache * cachep, void *foo)
+static void init_once(void *foo)
 {
         struct coda_inode_info *ei = (struct coda_inode_info *) foo;
 
diff --git a/fs/coda/pioctl.c b/fs/coda/pioctl.c
index c21a1f552a63..c51365422aa8 100644
--- a/fs/coda/pioctl.c
+++ b/fs/coda/pioctl.c
@@ -24,8 +24,7 @@
 #include <linux/coda_psdev.h>
 
 /* pioctl ops */
-static int coda_ioctl_permission(struct inode *inode, int mask,
-                                 struct nameidata *nd);
+static int coda_ioctl_permission(struct inode *inode, int mask);
 static int coda_pioctl(struct inode * inode, struct file * filp, 
                        unsigned int cmd, unsigned long user_data);
 
@@ -42,8 +41,7 @@ const struct file_operations coda_ioctl_operations = {
 };
 
 /* the coda pioctl inode ops */
-static int coda_ioctl_permission(struct inode *inode, int mask,
-                                 struct nameidata *nd)
+static int coda_ioctl_permission(struct inode *inode, int mask)
 {
         return 0;
 }
@@ -51,7 +49,7 @@ static int coda_ioctl_permission(struct inode *inode, int mask,
 static int coda_pioctl(struct inode * inode, struct file * filp, 
                        unsigned int cmd, unsigned long user_data)
 {
-        struct nameidata nd;
+        struct path path;
         int error;
         struct PioctlData data;
         struct inode *target_inode = NULL;
@@ -66,21 +64,21 @@ static int coda_pioctl(struct inode * inode, struct file * filp,
          * Look up the pathname. Note that the pathname is in 
          * user memory, and namei takes care of this
          */
-        if ( data.follow ) {
-                error = user_path_walk(data.path, &nd);
+        if (data.follow) {
+                error = user_path(data.path, &path);
         } else {
-                error = user_path_walk_link(data.path, &nd);
+                error = user_lpath(data.path, &path);
         }
                 
         if ( error ) {
                 return error;
         } else {
-                target_inode = nd.path.dentry->d_inode;
+                target_inode = path.dentry->d_inode;
         }
         
         /* return if it is not a Coda inode */
         if ( target_inode->i_sb != inode->i_sb ) {
-                path_put(&nd.path);
+                path_put(&path);
                 return  -EINVAL;
         }
 
@@ -89,7 +87,7 @@ static int coda_pioctl(struct inode * inode, struct file * filp,
 
         error = venus_pioctl(inode->i_sb, &(cnp->c_fid), cmd, &data);
 
-        path_put(&nd.path);
+        path_put(&path);
         return error;
 }
 
diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c
index e3eb3556622b..0d9b80ec689c 100644
--- a/fs/coda/psdev.c
+++ b/fs/coda/psdev.c
@@ -362,8 +362,9 @@ static int init_coda_psdev(void)
                 goto out_chrdev;
         }               
         for (i = 0; i < MAX_CODADEVS; i++)
-                device_create(coda_psdev_class, NULL,
-                              MKDEV(CODA_PSDEV_MAJOR,i), "cfs%d", i);
+                device_create_drvdata(coda_psdev_class, NULL,
+                                      MKDEV(CODA_PSDEV_MAJOR, i),
+                                      NULL, "cfs%d", i);
         coda_sysctl_init();
         goto out;
 
@@ -377,11 +378,7 @@ MODULE_AUTHOR("Jan Harkes, Peter J. Braam");
 MODULE_DESCRIPTION("Coda Distributed File System VFS interface");
 MODULE_ALIAS_CHARDEV_MAJOR(CODA_PSDEV_MAJOR);
 MODULE_LICENSE("GPL");
-#ifdef CONFIG_CODA_FS_OLD_API
-MODULE_VERSION("5.3.21");
-#else
 MODULE_VERSION("6.6");
-#endif
 
 static int __init init_coda(void)
 {
diff --git a/fs/coda/upcall.c b/fs/coda/upcall.c
index 359e531094dd..ce432bca95d1 100644
--- a/fs/coda/upcall.c
+++ b/fs/coda/upcall.c
@@ -52,12 +52,8 @@ static void *alloc_upcall(int opcode, int size)
         inp->ih.opcode = opcode;
         inp->ih.pid = current->pid;
         inp->ih.pgid = task_pgrp_nr(current);
-#ifdef CONFIG_CODA_FS_OLD_API
-        memset(&inp->ih.cred, 0, sizeof(struct coda_cred));
-        inp->ih.cred.cr_fsuid = current->fsuid;
-#else
         inp->ih.uid = current->fsuid;
-#endif
+
         return (void*)inp;
 }
 
@@ -166,20 +162,11 @@ int venus_close(struct super_block *sb, struct CodaFid *fid, int flags,
         union inputArgs *inp;
         union outputArgs *outp;
         int insize, outsize, error;
-#ifdef CONFIG_CODA_FS_OLD_API
-        struct coda_cred cred = { 0, };
-        cred.cr_fsuid = uid;
-#endif
         
         insize = SIZE(release);
         UPARG(CODA_CLOSE);
         
-#ifdef CONFIG_CODA_FS_OLD_API
-        memcpy(&(inp->ih.cred), &cred, sizeof(cred));
-#else
         inp->ih.uid = uid;
-#endif
-        
         inp->coda_close.VFid = *fid;
         inp->coda_close.flags = flags;
 
diff --git a/fs/compat.c b/fs/compat.c
index ed43e17a5dc6..c9d1472e65c5 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -197,8 +197,8 @@ static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs *
 {
         
         if (sizeof ubuf->f_blocks == 4) {
-                if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail) &
-                    0xffffffff00000000ULL)
+                if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail |
+                     kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL)
                         return -EOVERFLOW;
                 /* f_files and f_ffree may be -1; it's okay
                  * to stuff that into 32 bits */
@@ -234,18 +234,18 @@ static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs *
  * The following statfs calls are copies of code from fs/open.c and
  * should be checked against those from time to time
  */
-asmlinkage long compat_sys_statfs(const char __user *path, struct compat_statfs __user *buf)
+asmlinkage long compat_sys_statfs(const char __user *pathname, struct compat_statfs __user *buf)
 {
-        struct nameidata nd;
+        struct path path;
         int error;
 
-        error = user_path_walk(path, &nd);
+        error = user_path(pathname, &path);
         if (!error) {
                 struct kstatfs tmp;
-                error = vfs_statfs(nd.path.dentry, &tmp);
+                error = vfs_statfs(path.dentry, &tmp);
                 if (!error)
                         error = put_compat_statfs(buf, &tmp);
-                path_put(&nd.path);
+                path_put(&path);
         }
         return error;
 }
@@ -271,8 +271,8 @@ out:
 static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstatfs *kbuf)
 {
         if (sizeof ubuf->f_blocks == 4) {
-                if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail) &
-                    0xffffffff00000000ULL)
+                if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail |
+                     kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL)
                         return -EOVERFLOW;
                 /* f_files and f_ffree may be -1; it's okay
                  * to stuff that into 32 bits */
@@ -299,21 +299,21 @@ static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstat
         return 0;
 }
 
-asmlinkage long compat_sys_statfs64(const char __user *path, compat_size_t sz, struct compat_statfs64 __user *buf)
+asmlinkage long compat_sys_statfs64(const char __user *pathname, compat_size_t sz, struct compat_statfs64 __user *buf)
 {
-        struct nameidata nd;
+        struct path path;
         int error;
 
         if (sz != sizeof(*buf))
                 return -EINVAL;
 
-        error = user_path_walk(path, &nd);
+        error = user_path(pathname, &path);
         if (!error) {
                 struct kstatfs tmp;
-                error = vfs_statfs(nd.path.dentry, &tmp);
+                error = vfs_statfs(path.dentry, &tmp);
                 if (!error)
                         error = put_compat_statfs64(buf, &tmp);
-                path_put(&nd.path);
+                path_put(&path);
         }
         return error;
 }
@@ -2131,9 +2131,9 @@ asmlinkage long compat_sys_epoll_pwait(int epfd,
 
 #ifdef CONFIG_SIGNALFD
 
-asmlinkage long compat_sys_signalfd(int ufd,
-                                    const compat_sigset_t __user *sigmask,
-                                    compat_size_t sigsetsize)
+asmlinkage long compat_sys_signalfd4(int ufd,
+                                     const compat_sigset_t __user *sigmask,
+                                     compat_size_t sigsetsize, int flags)
 {
         compat_sigset_t ss32;
         sigset_t tmp;
@@ -2148,9 +2148,15 @@ asmlinkage long compat_sys_signalfd(int ufd,
         if (copy_to_user(ksigmask, &tmp, sizeof(sigset_t)))
                 return -EFAULT;
 
-        return sys_signalfd(ufd, ksigmask, sizeof(sigset_t));
+        return sys_signalfd4(ufd, ksigmask, sizeof(sigset_t), flags);
 }
 
+asmlinkage long compat_sys_signalfd(int ufd,
+                                    const compat_sigset_t __user *sigmask,
+                                    compat_size_t sigsetsize)
+{
+        return compat_sys_signalfd4(ufd, sigmask, sigsetsize, 0);
+}
 #endif /* CONFIG_SIGNALFD */
 
 #ifdef CONFIG_TIMERFD
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 7b3a03c7c6a9..5235c67e7594 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -25,7 +25,6 @@
 #include <linux/slab.h>
 #include <linux/raid/md.h>
 #include <linux/kd.h>
-#include <linux/dirent.h>
 #include <linux/route.h>
 #include <linux/in6.h>
 #include <linux/ipv6_route.h>
@@ -2297,8 +2296,6 @@ COMPATIBLE_IOCTL(AUTOFS_IOC_PROTOVER)
 COMPATIBLE_IOCTL(AUTOFS_IOC_EXPIRE)
 COMPATIBLE_IOCTL(AUTOFS_IOC_EXPIRE_MULTI)
 COMPATIBLE_IOCTL(AUTOFS_IOC_PROTOSUBVER)
-COMPATIBLE_IOCTL(AUTOFS_IOC_ASKREGHOST)
-COMPATIBLE_IOCTL(AUTOFS_IOC_TOGGLEREGHOST)
 COMPATIBLE_IOCTL(AUTOFS_IOC_ASKUMOUNT)
 /* Raw devices */
 COMPATIBLE_IOCTL(RAW_SETBIND)
diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h
index da015c12e3ea..762d287123ca 100644
--- a/fs/configfs/configfs_internal.h
+++ b/fs/configfs/configfs_internal.h
@@ -49,8 +49,10 @@ struct configfs_dirent {
 #define CONFIGFS_USET_DEFAULT   0x0080
 #define CONFIGFS_USET_DROPPING  0x0100
 #define CONFIGFS_USET_IN_MKDIR  0x0200
+#define CONFIGFS_USET_CREATING  0x0400
 #define CONFIGFS_NOT_PINNED     (CONFIGFS_ITEM_ATTR)
 
+extern struct mutex configfs_symlink_mutex;
 extern spinlock_t configfs_dirent_lock;
 
 extern struct vfsmount * configfs_mount;
@@ -66,6 +68,7 @@ extern void configfs_inode_exit(void);
 extern int configfs_create_file(struct config_item *, const struct configfs_attribute *);
 extern int configfs_make_dirent(struct configfs_dirent *,
                                 struct dentry *, void *, umode_t, int);
+extern int configfs_dirent_is_ready(struct configfs_dirent *);
 
 extern int configfs_add_file(struct dentry *, const struct configfs_attribute *, int);
 extern void configfs_hash_and_remove(struct dentry * dir, const char * name);
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 179589be063a..7a8db78a91d2 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -185,7 +185,7 @@ static int create_dir(struct config_item * k, struct dentry * p,
         error = configfs_dirent_exists(p->d_fsdata, d->d_name.name);
         if (!error)
                 error = configfs_make_dirent(p->d_fsdata, d, k, mode,
-                                             CONFIGFS_DIR);
+                                             CONFIGFS_DIR | CONFIGFS_USET_CREATING);
         if (!error) {
                 error = configfs_create(d, mode, init_dir);
                 if (!error) {
@@ -209,6 +209,9 @@ static int create_dir(struct config_item * k, struct dentry * p,
  *      configfs_create_dir - create a directory for an config_item.
  *      @item:          config_itemwe're creating directory for.
  *      @dentry:        config_item's dentry.
+ *
+ *      Note: user-created entries won't be allowed under this new directory
+ *      until it is validated by configfs_dir_set_ready()
  */
 
 static int configfs_create_dir(struct config_item * item, struct dentry *dentry)
@@ -231,6 +234,44 @@ static int configfs_create_dir(struct config_item * item, struct dentry *dentry)
         return error;
 }
 
+/*
+ * Allow userspace to create new entries under a new directory created with
+ * configfs_create_dir(), and under all of its chidlren directories recursively.
+ * @sd          configfs_dirent of the new directory to validate
+ *
+ * Caller must hold configfs_dirent_lock.
+ */
+static void configfs_dir_set_ready(struct configfs_dirent *sd)
+{
+        struct configfs_dirent *child_sd;
+
+        sd->s_type &= ~CONFIGFS_USET_CREATING;
+        list_for_each_entry(child_sd, &sd->s_children, s_sibling)
+                if (child_sd->s_type & CONFIGFS_USET_CREATING)
+                        configfs_dir_set_ready(child_sd);
+}
+
+/*
+ * Check that a directory does not belong to a directory hierarchy being
+ * attached and not validated yet.
+ * @sd          configfs_dirent of the directory to check
+ *
+ * @return      non-zero iff the directory was validated
+ *
+ * Note: takes configfs_dirent_lock, so the result may change from false to true
+ * in two consecutive calls, but never from true to false.
+ */
+int configfs_dirent_is_ready(struct configfs_dirent *sd)
+{
+        int ret;
+
+        spin_lock(&configfs_dirent_lock);
+        ret = !(sd->s_type & CONFIGFS_USET_CREATING);
+        spin_unlock(&configfs_dirent_lock);
+
+        return ret;
+}
+
 int configfs_create_link(struct configfs_symlink *sl,
                          struct dentry *parent,
                          struct dentry *dentry)
@@ -283,6 +324,8 @@ static void remove_dir(struct dentry * d)
  * The only thing special about this is that we remove any files in
  * the directory before we remove the directory, and we've inlined
  * what used to be configfs_rmdir() below, instead of calling separately.
+ *
+ * Caller holds the mutex of the item's inode
  */
 
 static void configfs_remove_dir(struct config_item * item)
@@ -330,7 +373,19 @@ static struct dentry * configfs_lookup(struct inode *dir,
         struct configfs_dirent * parent_sd = dentry->d_parent->d_fsdata;
         struct configfs_dirent * sd;
         int found = 0;
-        int err = 0;
+        int err;
+
+        /*
+         * Fake invisibility if dir belongs to a group/default groups hierarchy
+         * being attached
+         *
+         * This forbids userspace to read/write attributes of items which may
+         * not complete their initialization, since the dentries of the
+         * attributes won't be instantiated.
+         */
+        err = -ENOENT;
+        if (!configfs_dirent_is_ready(parent_sd))
+                goto out;
 
         list_for_each_entry(sd, &parent_sd->s_children, s_sibling) {
                 if (sd->s_type & CONFIGFS_NOT_PINNED) {
@@ -353,6 +408,7 @@ static struct dentry * configfs_lookup(struct inode *dir,
                 return simple_lookup(dir, dentry, nd);
         }
 
+out:
         return ERR_PTR(err);
 }
 
@@ -370,13 +426,17 @@ static int configfs_detach_prep(struct dentry *dentry, struct mutex **wait_mutex
         struct configfs_dirent *sd;
         int ret;
 
+        /* Mark that we're trying to drop the group */
+        parent_sd->s_type |= CONFIGFS_USET_DROPPING;
+
         ret = -EBUSY;
         if (!list_empty(&parent_sd->s_links))
                 goto out;
 
         ret = 0;
         list_for_each_entry(sd, &parent_sd->s_children, s_sibling) {
-                if (sd->s_type & CONFIGFS_NOT_PINNED)
+                if (!sd->s_element ||
+                    (sd->s_type & CONFIGFS_NOT_PINNED))
                         continue;
                 if (sd->s_type & CONFIGFS_USET_DEFAULT) {
                         /* Abort if racing with mkdir() */
@@ -385,8 +445,6 @@ static int configfs_detach_prep(struct dentry *dentry, struct mutex **wait_mutex
                                         *wait_mutex = &sd->s_dentry->d_inode->i_mutex;
                                 return -EAGAIN;
                         }
-                        /* Mark that we're trying to drop the group */
-                        sd->s_type |= CONFIGFS_USET_DROPPING;
 
                         /*
                          * Yup, recursive.  If there's a problem, blame
@@ -414,12 +472,11 @@ static void configfs_detach_rollback(struct dentry *dentry)
         struct configfs_dirent *parent_sd = dentry->d_fsdata;
         struct configfs_dirent *sd;
 
-        list_for_each_entry(sd, &parent_sd->s_children, s_sibling) {
-                if (sd->s_type & CONFIGFS_USET_DEFAULT) {
+        parent_sd->s_type &= ~CONFIGFS_USET_DROPPING;
+
+        list_for_each_entry(sd, &parent_sd->s_children, s_sibling)
+                if (sd->s_type & CONFIGFS_USET_DEFAULT)
                         configfs_detach_rollback(sd->s_dentry);
-                        sd->s_type &= ~CONFIGFS_USET_DROPPING;
-                }
-        }
 }
 
 static void detach_attrs(struct config_item * item)
@@ -558,36 +615,21 @@ static int create_default_group(struct config_group *parent_group,
 static int populate_groups(struct config_group *group)
 {
         struct config_group *new_group;
-        struct dentry *dentry = group->cg_item.ci_dentry;
         int ret = 0;
         int i;
 
         if (group->default_groups) {
-                /*
-                 * FYI, we're faking mkdir here
-                 * I'm not sure we need this semaphore, as we're called
-                 * from our parent's mkdir.  That holds our parent's
-                 * i_mutex, so afaik lookup cannot continue through our
-                 * parent to find us, let alone mess with our tree.
-                 * That said, taking our i_mutex is closer to mkdir
-                 * emulation, and shouldn't hurt.
-                 */
-                mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_CHILD);
-
                 for (i = 0; group->default_groups[i]; i++) {
                         new_group = group->default_groups[i];
 
                         ret = create_default_group(group, new_group);
-                        if (ret)
+                        if (ret) {
+                                detach_groups(group);
                                 break;
+                        }
                 }
-
-                mutex_unlock(&dentry->d_inode->i_mutex);
         }
 
-        if (ret)
-                detach_groups(group);
-
         return ret;
 }
 
@@ -702,7 +744,15 @@ static int configfs_attach_item(struct config_item *parent_item,
         if (!ret) {
                 ret = populate_attrs(item);
                 if (ret) {
+                        /*
+                         * We are going to remove an inode and its dentry but
+                         * the VFS may already have hit and used them. Thus,
+                         * we must lock them as rmdir() would.
+                         */
+                        mutex_lock(&dentry->d_inode->i_mutex);
                         configfs_remove_dir(item);
+                        dentry->d_inode->i_flags |= S_DEAD;
+                        mutex_unlock(&dentry->d_inode->i_mutex);
                         d_delete(dentry);
                 }
         }
@@ -710,6 +760,7 @@ static int configfs_attach_item(struct config_item *parent_item,
         return ret;
 }
 
+/* Caller holds the mutex of the item's inode */
 static void configfs_detach_item(struct config_item *item)
 {
         detach_attrs(item);
@@ -728,16 +779,30 @@ static int configfs_attach_group(struct config_item *parent_item,
                 sd = dentry->d_fsdata;
                 sd->s_type |= CONFIGFS_USET_DIR;
 
+                /*
+                 * FYI, we're faking mkdir in populate_groups()
+                 * We must lock the group's inode to avoid races with the VFS
+                 * which can already hit the inode and try to add/remove entries
+                 * under it.
+                 *
+                 * We must also lock the inode to remove it safely in case of
+                 * error, as rmdir() would.
+                 */
+                mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_CHILD);
                 ret = populate_groups(to_config_group(item));
                 if (ret) {
                         configfs_detach_item(item);
-                        d_delete(dentry);
+                        dentry->d_inode->i_flags |= S_DEAD;
                 }
+                mutex_unlock(&dentry->d_inode->i_mutex);
+                if (ret)
+                        d_delete(dentry);
         }
 
         return ret;
 }
 
+/* Caller holds the mutex of the group's inode */
 static void configfs_detach_group(struct config_item *item)
 {
         detach_groups(to_config_group(item));
@@ -1035,7 +1100,7 @@ static int configfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
         struct configfs_subsystem *subsys;
         struct configfs_dirent *sd;
         struct config_item_type *type;
-        struct module *owner = NULL;
+        struct module *subsys_owner = NULL, *new_item_owner = NULL;
         char *name;
 
         if (dentry->d_parent == configfs_sb->s_root) {
@@ -1044,6 +1109,16 @@ static int configfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
         }
 
         sd = dentry->d_parent->d_fsdata;
+
+        /*
+         * Fake invisibility if dir belongs to a group/default groups hierarchy
+         * being attached
+         */
+        if (!configfs_dirent_is_ready(sd)) {
+                ret = -ENOENT;
+                goto out;
+        }
+
         if (!(sd->s_type & CONFIGFS_USET_DIR)) {
                 ret = -EPERM;
                 goto out;
@@ -1062,10 +1137,25 @@ static int configfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
                 goto out_put;
         }
 
+        /*
+         * The subsystem may belong to a different module than the item
+         * being created.  We don't want to safely pin the new item but
+         * fail to pin the subsystem it sits under.
+         */
+        if (!subsys->su_group.cg_item.ci_type) {
+                ret = -EINVAL;
+                goto out_put;
+        }
+        subsys_owner = subsys->su_group.cg_item.ci_type->ct_owner;
+        if (!try_module_get(subsys_owner)) {
+                ret = -EINVAL;
+                goto out_put;
+        }
+
         name = kmalloc(dentry->d_name.len + 1, GFP_KERNEL);
         if (!name) {
                 ret = -ENOMEM;
-                goto out_put;
+                goto out_subsys_put;
         }
 
         snprintf(name, dentry->d_name.len + 1, "%s", dentry->d_name.name);
@@ -1094,10 +1184,10 @@ static int configfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
         kfree(name);
         if (ret) {
                 /*
-                 * If item == NULL, then link_obj() was never called.
+                 * If ret != 0, then link_obj() was never called.
                  * There are no extra references to clean up.
                  */
-                goto out_put;
+                goto out_subsys_put;
         }
 
         /*
@@ -1111,8 +1201,8 @@ static int configfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
                 goto out_unlink;
         }
 
-        owner = type->ct_owner;
-        if (!try_module_get(owner)) {
+        new_item_owner = type->ct_owner;
+        if (!try_module_get(new_item_owner)) {
                 ret = -EINVAL;
                 goto out_unlink;
         }
@@ -1142,6 +1232,8 @@ static int configfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 
         spin_lock(&configfs_dirent_lock);
         sd->s_type &= ~CONFIGFS_USET_IN_MKDIR;
+        if (!ret)
+                configfs_dir_set_ready(dentry->d_fsdata);
         spin_unlock(&configfs_dirent_lock);
 
 out_unlink:
@@ -1159,9 +1251,13 @@ out_unlink:
                 mutex_unlock(&subsys->su_mutex);
 
                 if (module_got)
-                        module_put(owner);
+                        module_put(new_item_owner);
         }
 
+out_subsys_put:
+        if (ret)
+                module_put(subsys_owner);
+
 out_put:
         /*
          * link_obj()/link_group() took a reference from child->parent,
@@ -1180,7 +1276,7 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry)
         struct config_item *item;
         struct configfs_subsystem *subsys;
         struct configfs_dirent *sd;
-        struct module *owner = NULL;
+        struct module *subsys_owner = NULL, *dead_item_owner = NULL;
         int ret;
 
         if (dentry->d_parent == configfs_sb->s_root)
@@ -1207,6 +1303,15 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry)
                 return -EINVAL;
         }
 
+        /* configfs_mkdir() shouldn't have allowed this */
+        BUG_ON(!subsys->su_group.cg_item.ci_type);
+        subsys_owner = subsys->su_group.cg_item.ci_type->ct_owner;
+
+        /*
+         * Ensure that no racing symlink() will make detach_prep() fail while
+         * the new link is temporarily attached
+         */
+        mutex_lock(&configfs_symlink_mutex);
         spin_lock(&configfs_dirent_lock);
         do {
                 struct mutex *wait_mutex;
@@ -1215,6 +1320,7 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry)
                 if (ret) {
                         configfs_detach_rollback(dentry);
                         spin_unlock(&configfs_dirent_lock);
+                        mutex_unlock(&configfs_symlink_mutex);
                         if (ret != -EAGAIN) {
                                 config_item_put(parent_item);
                                 return ret;
@@ -1224,10 +1330,12 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry)
                         mutex_lock(wait_mutex);
                         mutex_unlock(wait_mutex);
 
+                        mutex_lock(&configfs_symlink_mutex);
                         spin_lock(&configfs_dirent_lock);
                 }
         } while (ret == -EAGAIN);
         spin_unlock(&configfs_dirent_lock);
+        mutex_unlock(&configfs_symlink_mutex);
 
         /* Get a working ref for the duration of this function */
         item = configfs_get_config_item(dentry);
@@ -1236,7 +1344,7 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry)
         config_item_put(parent_item);
 
         if (item->ci_type)
-                owner = item->ci_type->ct_owner;
+                dead_item_owner = item->ci_type->ct_owner;
 
         if (sd->s_type & CONFIGFS_USET_DIR) {
                 configfs_detach_group(item);
@@ -1258,7 +1366,8 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry)
         /* Drop our reference from above */
         config_item_put(item);
 
-        module_put(owner);
+        module_put(dead_item_owner);
+        module_put(subsys_owner);
 
         return 0;
 }
@@ -1314,13 +1423,24 @@ static int configfs_dir_open(struct inode *inode, struct file *file)
 {
         struct dentry * dentry = file->f_path.dentry;
         struct configfs_dirent * parent_sd = dentry->d_fsdata;
+        int err;
 
         mutex_lock(&dentry->d_inode->i_mutex);
-        file->private_data = configfs_new_dirent(parent_sd, NULL);
+        /*
+         * Fake invisibility if dir belongs to a group/default groups hierarchy
+         * being attached
+         */
+        err = -ENOENT;
+        if (configfs_dirent_is_ready(parent_sd)) {
+                file->private_data = configfs_new_dirent(parent_sd, NULL);
+                if (IS_ERR(file->private_data))
+                        err = PTR_ERR(file->private_data);
+                else
+                        err = 0;
+        }
         mutex_unlock(&dentry->d_inode->i_mutex);
 
-        return IS_ERR(file->private_data) ? PTR_ERR(file->private_data) : 0;
-
+        return err;
 }
 
 static int configfs_dir_close(struct inode *inode, struct file *file)
@@ -1491,6 +1611,10 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys)
                 if (err) {
                         d_delete(dentry);
                         dput(dentry);
+                } else {
+                        spin_lock(&configfs_dirent_lock);
+                        configfs_dir_set_ready(dentry->d_fsdata);
+                        spin_unlock(&configfs_dirent_lock);
                 }
         }
 
@@ -1517,11 +1641,13 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys)
         mutex_lock_nested(&configfs_sb->s_root->d_inode->i_mutex,
                           I_MUTEX_PARENT);
         mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_CHILD);
+        mutex_lock(&configfs_symlink_mutex);
         spin_lock(&configfs_dirent_lock);
         if (configfs_detach_prep(dentry, NULL)) {
                 printk(KERN_ERR "configfs: Tried to unregister non-empty subsystem!\n");
         }
         spin_unlock(&configfs_dirent_lock);
+        mutex_unlock(&configfs_symlink_mutex);
         configfs_detach_group(&group->cg_item);
         dentry->d_inode->i_flags |= S_DEAD;
         mutex_unlock(&dentry->d_inode->i_mutex);
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index 0004d18c40ac..bf74973b0492 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -31,6 +31,9 @@
 #include <linux/configfs.h>
 #include "configfs_internal.h"
 
+/* Protects attachments of new symlinks */
+DEFINE_MUTEX(configfs_symlink_mutex);
+
 static int item_depth(struct config_item * item)
 {
         struct config_item * p = item;
@@ -73,11 +76,20 @@ static int create_link(struct config_item *parent_item,
         struct configfs_symlink *sl;
         int ret;
 
+        ret = -ENOENT;
+        if (!configfs_dirent_is_ready(target_sd))
+                goto out;
         ret = -ENOMEM;
         sl = kmalloc(sizeof(struct configfs_symlink), GFP_KERNEL);
         if (sl) {
                 sl->sl_target = config_item_get(item);
                 spin_lock(&configfs_dirent_lock);
+                if (target_sd->s_type & CONFIGFS_USET_DROPPING) {
+                        spin_unlock(&configfs_dirent_lock);
+                        config_item_put(item);
+                        kfree(sl);
+                        return -ENOENT;
+                }
                 list_add(&sl->sl_list, &target_sd->s_links);
                 spin_unlock(&configfs_dirent_lock);
                 ret = configfs_create_link(sl, parent_item->ci_dentry,
@@ -91,6 +103,7 @@ static int create_link(struct config_item *parent_item,
                 }
         }
 
+out:
         return ret;
 }
 
@@ -120,6 +133,7 @@ int configfs_symlink(struct inode *dir, struct dentry *dentry, const char *symna
 {
         int ret;
         struct nameidata nd;
+        struct configfs_dirent *sd;
         struct config_item *parent_item;
         struct config_item *target_item;
         struct config_item_type *type;
@@ -128,9 +142,19 @@ int configfs_symlink(struct inode *dir, struct dentry *dentry, const char *symna
         if (dentry->d_parent == configfs_sb->s_root)
                 goto out;
 
+        sd = dentry->d_parent->d_fsdata;
+        /*
+         * Fake invisibility if dir belongs to a group/default groups hierarchy
+         * being attached
+         */
+        ret = -ENOENT;
+        if (!configfs_dirent_is_ready(sd))
+                goto out;
+
         parent_item = configfs_get_config_item(dentry->d_parent);
         type = parent_item->ci_type;
 
+        ret = -EPERM;
         if (!type || !type->ct_item_ops ||
             !type->ct_item_ops->allow_link)
                 goto out_put;
@@ -141,7 +165,9 @@ int configfs_symlink(struct inode *dir, struct dentry *dentry, const char *symna
 
         ret = type->ct_item_ops->allow_link(parent_item, target_item);
         if (!ret) {
+                mutex_lock(&configfs_symlink_mutex);
                 ret = create_link(parent_item, target_item, dentry);
+                mutex_unlock(&configfs_symlink_mutex);
                 if (ret && type->ct_item_ops->drop_link)
                         type->ct_item_ops->drop_link(parent_item,
                                                      target_item);
diff --git a/fs/dcache.c b/fs/dcache.c
index 6068c25b393c..101663d15e9f 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -61,7 +61,6 @@ static struct kmem_cache *dentry_cache __read_mostly;
 static unsigned int d_hash_mask __read_mostly;
 static unsigned int d_hash_shift __read_mostly;
 static struct hlist_head *dentry_hashtable __read_mostly;
-static LIST_HEAD(dentry_unused);
 
 /* Statistics gathering. */
 struct dentry_stat_t dentry_stat = {
@@ -96,14 +95,6 @@ static void d_free(struct dentry *dentry)
                 call_rcu(&dentry->d_u.d_rcu, d_callback);
 }
 
-static void dentry_lru_remove(struct dentry *dentry)
-{
-        if (!list_empty(&dentry->d_lru)) {
-                list_del_init(&dentry->d_lru);
-                dentry_stat.nr_unused--;
-        }
-}
-
 /*
  * Release the dentry's inode, using the filesystem
  * d_iput() operation if defined.
@@ -130,6 +121,41 @@ static void dentry_iput(struct dentry * dentry)
         }
 }
 
+/*
+ * dentry_lru_(add|add_tail|del|del_init) must be called with dcache_lock held.
+ */
+static void dentry_lru_add(struct dentry *dentry)
+{
+        list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
+        dentry->d_sb->s_nr_dentry_unused++;
+        dentry_stat.nr_unused++;
+}
+
+static void dentry_lru_add_tail(struct dentry *dentry)
+{
+        list_add_tail(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
+        dentry->d_sb->s_nr_dentry_unused++;
+        dentry_stat.nr_unused++;
+}
+
+static void dentry_lru_del(struct dentry *dentry)
+{
+        if (!list_empty(&dentry->d_lru)) {
+                list_del(&dentry->d_lru);
+                dentry->d_sb->s_nr_dentry_unused--;
+                dentry_stat.nr_unused--;
+        }
+}
+
+static void dentry_lru_del_init(struct dentry *dentry)
+{
+        if (likely(!list_empty(&dentry->d_lru))) {
+                list_del_init(&dentry->d_lru);
+                dentry->d_sb->s_nr_dentry_unused--;
+                dentry_stat.nr_unused--;
+        }
+}
+
 /**
  * d_kill - kill dentry and return parent
  * @dentry: dentry to kill
@@ -212,8 +238,7 @@ repeat:
                 goto kill_it;
         if (list_empty(&dentry->d_lru)) {
                 dentry->d_flags |= DCACHE_REFERENCED;
-                list_add(&dentry->d_lru, &dentry_unused);
-                dentry_stat.nr_unused++;
+                dentry_lru_add(dentry);
         }
         spin_unlock(&dentry->d_lock);
         spin_unlock(&dcache_lock);
@@ -222,7 +247,8 @@ repeat:
 unhash_it:
         __d_drop(dentry);
 kill_it:
-        dentry_lru_remove(dentry);
+        /* if dentry was on the d_lru list delete it from there */
+        dentry_lru_del(dentry);
         dentry = d_kill(dentry);
         if (dentry)
                 goto repeat;
@@ -290,7 +316,7 @@ int d_invalidate(struct dentry * dentry)
 static inline struct dentry * __dget_locked(struct dentry *dentry)
 {
         atomic_inc(&dentry->d_count);
-        dentry_lru_remove(dentry);
+        dentry_lru_del_init(dentry);
         return dentry;
 }
 
@@ -406,133 +432,168 @@ static void prune_one_dentry(struct dentry * dentry)
 
                 if (dentry->d_op && dentry->d_op->d_delete)
                         dentry->d_op->d_delete(dentry);
-                dentry_lru_remove(dentry);
+                dentry_lru_del_init(dentry);
                 __d_drop(dentry);
                 dentry = d_kill(dentry);
                 spin_lock(&dcache_lock);
         }
 }
 
-/**
- * prune_dcache - shrink the dcache
- * @count: number of entries to try and free
- * @sb: if given, ignore dentries for other superblocks
- *         which are being unmounted.
- *
- * Shrink the dcache. This is done when we need
- * more memory, or simply when we need to unmount
- * something (at which point we need to unuse
- * all dentries).
- *
- * This function may fail to free any resources if
- * all the dentries are in use.
+/*
+ * Shrink the dentry LRU on a given superblock.
+ * @sb   : superblock to shrink dentry LRU.
+ * @count: If count is NULL, we prune all dentries on superblock.
+ * @flags: If flags is non-zero, we need to do special processing based on
+ * which flags are set. This means we don't need to maintain multiple
+ * similar copies of this loop.
  */
- 
-static void prune_dcache(int count, struct super_block *sb)
+static void __shrink_dcache_sb(struct super_block *sb, int *count, int flags)
 {
-        spin_lock(&dcache_lock);
-        for (; count ; count--) {
-                struct dentry *dentry;
-                struct list_head *tmp;
-                struct rw_semaphore *s_umount;
-
-                cond_resched_lock(&dcache_lock);
+        LIST_HEAD(referenced);
+        LIST_HEAD(tmp);
+        struct dentry *dentry;
+        int cnt = 0;
 
-                tmp = dentry_unused.prev;
-                if (sb) {
-                        /* Try to find a dentry for this sb, but don't try
-                         * too hard, if they aren't near the tail they will
-                         * be moved down again soon
+        BUG_ON(!sb);
+        BUG_ON((flags & DCACHE_REFERENCED) && count == NULL);
+        spin_lock(&dcache_lock);
+        if (count != NULL)
+                /* called from prune_dcache() and shrink_dcache_parent() */
+                cnt = *count;
+restart:
+        if (count == NULL)
+                list_splice_init(&sb->s_dentry_lru, &tmp);
+        else {
+                while (!list_empty(&sb->s_dentry_lru)) {
+                        dentry = list_entry(sb->s_dentry_lru.prev,
+                                        struct dentry, d_lru);
+                        BUG_ON(dentry->d_sb != sb);
+
+                        spin_lock(&dentry->d_lock);
+                        /*
+                         * If we are honouring the DCACHE_REFERENCED flag and
+                         * the dentry has this flag set, don't free it. Clear
+                         * the flag and put it back on the LRU.
                          */
-                        int skip = count;
-                        while (skip && tmp != &dentry_unused &&
-                            list_entry(tmp, struct dentry, d_lru)->d_sb != sb) {
-                                skip--;
-                                tmp = tmp->prev;
+                        if ((flags & DCACHE_REFERENCED)
+                                && (dentry->d_flags & DCACHE_REFERENCED)) {
+                                dentry->d_flags &= ~DCACHE_REFERENCED;
+                                list_move_tail(&dentry->d_lru, &referenced);
+                                spin_unlock(&dentry->d_lock);
+                        } else {
+                                list_move_tail(&dentry->d_lru, &tmp);
+                                spin_unlock(&dentry->d_lock);
+                                cnt--;
+                                if (!cnt)
+                                        break;
                         }
+                        cond_resched_lock(&dcache_lock);
                 }
-                if (tmp == &dentry_unused)
-                        break;
-                list_del_init(tmp);
-                prefetch(dentry_unused.prev);
-                dentry_stat.nr_unused--;
-                dentry = list_entry(tmp, struct dentry, d_lru);
-
-                spin_lock(&dentry->d_lock);
+        }
+        while (!list_empty(&tmp)) {
+                dentry = list_entry(tmp.prev, struct dentry, d_lru);
+                dentry_lru_del_init(dentry);
+                spin_lock(&dentry->d_lock);
                 /*
                  * We found an inuse dentry which was not removed from
-                 * dentry_unused because of laziness during lookup.  Do not free
-                 * it - just keep it off the dentry_unused list.
+                 * the LRU because of laziness during lookup.  Do not free
+                 * it - just keep it off the LRU list.
                  */
-                if (atomic_read(&dentry->d_count)) {
-                        spin_unlock(&dentry->d_lock);
+                if (atomic_read(&dentry->d_count)) {
+                        spin_unlock(&dentry->d_lock);
                         continue;
                 }
-                /* If the dentry was recently referenced, don't free it. */
-                if (dentry->d_flags & DCACHE_REFERENCED) {
-                        dentry->d_flags &= ~DCACHE_REFERENCED;
-                        list_add(&dentry->d_lru, &dentry_unused);
-                        dentry_stat.nr_unused++;
-                        spin_unlock(&dentry->d_lock);
+                prune_one_dentry(dentry);
+                /* dentry->d_lock was dropped in prune_one_dentry() */
+                cond_resched_lock(&dcache_lock);
+        }
+        if (count == NULL && !list_empty(&sb->s_dentry_lru))
+                goto restart;
+        if (count != NULL)
+                *count = cnt;
+        if (!list_empty(&referenced))
+                list_splice(&referenced, &sb->s_dentry_lru);
+        spin_unlock(&dcache_lock);
+}
+
+/**
+ * prune_dcache - shrink the dcache
+ * @count: number of entries to try to free
+ *
+ * Shrink the dcache. This is done when we need more memory, or simply when we
+ * need to unmount something (at which point we need to unuse all dentries).
+ *
+ * This function may fail to free any resources if all the dentries are in use.
+ */
+static void prune_dcache(int count)
+{
+        struct super_block *sb;
+        int w_count;
+        int unused = dentry_stat.nr_unused;
+        int prune_ratio;
+        int pruned;
+
+        if (unused == 0 || count == 0)
+                return;
+        spin_lock(&dcache_lock);
+restart:
+        if (count >= unused)
+                prune_ratio = 1;
+        else
+                prune_ratio = unused / count;
+        spin_lock(&sb_lock);
+        list_for_each_entry(sb, &super_blocks, s_list) {
+                if (sb->s_nr_dentry_unused == 0)
                         continue;
-                }
-                /*
-                 * If the dentry is not DCACHED_REFERENCED, it is time
-                 * to remove it from the dcache, provided the super block is
-                 * NULL (which means we are trying to reclaim memory)
-                 * or this dentry belongs to the same super block that
-                 * we want to shrink.
+                sb->s_count++;
+                /* Now, we reclaim unused dentrins with fairness.
+                 * We reclaim them same percentage from each superblock.
+                 * We calculate number of dentries to scan on this sb
+                 * as follows, but the implementation is arranged to avoid
+                 * overflows:
+                 * number of dentries to scan on this sb =
+                 * count * (number of dentries on this sb /
+                 * number of dentries in the machine)
                  */
+                spin_unlock(&sb_lock);
+                if (prune_ratio != 1)
+                        w_count = (sb->s_nr_dentry_unused / prune_ratio) + 1;
+                else
+                        w_count = sb->s_nr_dentry_unused;
+                pruned = w_count;
                 /*
-                 * If this dentry is for "my" filesystem, then I can prune it
-                 * without taking the s_umount lock (I already hold it).
-                 */
-                if (sb && dentry->d_sb == sb) {
-                        prune_one_dentry(dentry);
-                        continue;
-                }
-                /*
-                 * ...otherwise we need to be sure this filesystem isn't being
-                 * unmounted, otherwise we could race with
-                 * generic_shutdown_super(), and end up holding a reference to
-                 * an inode while the filesystem is unmounted.
-                 * So we try to get s_umount, and make sure s_root isn't NULL.
-                 * (Take a local copy of s_umount to avoid a use-after-free of
-                 * `dentry').
+                 * We need to be sure this filesystem isn't being unmounted,
+                 * otherwise we could race with generic_shutdown_super(), and
+                 * end up holding a reference to an inode while the filesystem
+                 * is unmounted.  So we try to get s_umount, and make sure
+                 * s_root isn't NULL.
                  */
-                s_umount = &dentry->d_sb->s_umount;
-                if (down_read_trylock(s_umount)) {
-                        if (dentry->d_sb->s_root != NULL) {
-                                prune_one_dentry(dentry);
-                                up_read(s_umount);
-                                continue;
+                if (down_read_trylock(&sb->s_umount)) {
+                        if ((sb->s_root != NULL) &&
+                            (!list_empty(&sb->s_dentry_lru))) {
+                                spin_unlock(&dcache_lock);
+                                __shrink_dcache_sb(sb, &w_count,
+                                                DCACHE_REFERENCED);
+                                pruned -= w_count;
+                                spin_lock(&dcache_lock);
                         }
-                        up_read(s_umount);
+                        up_read(&sb->s_umount);
                 }
-                spin_unlock(&dentry->d_lock);
+                spin_lock(&sb_lock);
+                count -= pruned;
                 /*
-                 * Insert dentry at the head of the list as inserting at the
-                 * tail leads to a cycle.
+                 * restart only when sb is no longer on the list and
+                 * we have more work to do.
                  */
-                list_add(&dentry->d_lru, &dentry_unused);
-                dentry_stat.nr_unused++;
+                if (__put_super_and_need_restart(sb) && count > 0) {
+                        spin_unlock(&sb_lock);
+                        goto restart;
+                }
         }
+        spin_unlock(&sb_lock);
         spin_unlock(&dcache_lock);
 }
 
-/*
- * Shrink the dcache for the specified super block.
- * This allows us to unmount a device without disturbing
- * the dcache for the other devices.
- *
- * This implementation makes just two traversals of the
- * unused list.  On the first pass we move the selected
- * dentries to the most recent end, and on the second
- * pass we free them.  The second pass must restart after
- * each dput(), but since the target dentries are all at
- * the end, it's really just a single traversal.
- */
-
 /**
  * shrink_dcache_sb - shrink dcache for a superblock
  * @sb: superblock
@@ -541,44 +602,9 @@ static void prune_dcache(int count, struct super_block *sb)
  * is used to free the dcache before unmounting a file
  * system
  */
-
 void shrink_dcache_sb(struct super_block * sb)
 {
-        struct list_head *tmp, *next;
-        struct dentry *dentry;
-
-        /*
-         * Pass one ... move the dentries for the specified
-         * superblock to the most recent end of the unused list.
-         */
-        spin_lock(&dcache_lock);
-        list_for_each_prev_safe(tmp, next, &dentry_unused) {
-                dentry = list_entry(tmp, struct dentry, d_lru);
-                if (dentry->d_sb != sb)
-                        continue;
-                list_move_tail(tmp, &dentry_unused);
-        }
-
-        /*
-         * Pass two ... free the dentries for this superblock.
-         */
-repeat:
-        list_for_each_prev_safe(tmp, next, &dentry_unused) {
-                dentry = list_entry(tmp, struct dentry, d_lru);
-                if (dentry->d_sb != sb)
-                        continue;
-                dentry_stat.nr_unused--;
-                list_del_init(tmp);
-                spin_lock(&dentry->d_lock);
-                if (atomic_read(&dentry->d_count)) {
-                        spin_unlock(&dentry->d_lock);
-                        continue;
-                }
-                prune_one_dentry(dentry);
-                cond_resched_lock(&dcache_lock);
-                goto repeat;
-        }
-        spin_unlock(&dcache_lock);
+        __shrink_dcache_sb(sb, NULL, 0);
 }
 
 /*
@@ -595,7 +621,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
 
         /* detach this root from the system */
         spin_lock(&dcache_lock);
-        dentry_lru_remove(dentry);
+        dentry_lru_del_init(dentry);
         __d_drop(dentry);
         spin_unlock(&dcache_lock);
 
@@ -609,7 +635,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
                         spin_lock(&dcache_lock);
                         list_for_each_entry(loop, &dentry->d_subdirs,
                                             d_u.d_child) {
-                                dentry_lru_remove(loop);
+                                dentry_lru_del_init(loop);
                                 __d_drop(loop);
                                 cond_resched_lock(&dcache_lock);
                         }
@@ -791,14 +817,13 @@ resume:
                 struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
                 next = tmp->next;
 
-                dentry_lru_remove(dentry);
+                dentry_lru_del_init(dentry);
                 /* 
                  * move only zero ref count dentries to the end 
                  * of the unused list for prune_dcache
                  */
                 if (!atomic_read(&dentry->d_count)) {
-                        list_add_tail(&dentry->d_lru, &dentry_unused);
-                        dentry_stat.nr_unused++;
+                        dentry_lru_add_tail(dentry);
                         found++;
                 }
 
@@ -840,10 +865,11 @@ out:
  
 void shrink_dcache_parent(struct dentry * parent)
 {
+        struct super_block *sb = parent->d_sb;
         int found;
 
         while ((found = select_parent(parent)) != 0)
-                prune_dcache(found, parent->d_sb);
+                __shrink_dcache_sb(sb, &found, 0);
 }
 
 /*
@@ -863,7 +889,7 @@ static int shrink_dcache_memory(int nr, gfp_t gfp_mask)
         if (nr) {
                 if (!(gfp_mask & __GFP_FS))
                         return -1;
-                prune_dcache(nr, NULL);
+                prune_dcache(nr);
         }
         return (dentry_stat.nr_unused / 100) * sysctl_vfs_cache_pressure;
 }
@@ -1194,6 +1220,107 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
         return new;
 }
 
+/**
+ * d_add_ci - lookup or allocate new dentry with case-exact name
+ * @inode:  the inode case-insensitive lookup has found
+ * @dentry: the negative dentry that was passed to the parent's lookup func
+ * @name:   the case-exact name to be associated with the returned dentry
+ *
+ * This is to avoid filling the dcache with case-insensitive names to the
+ * same inode, only the actual correct case is stored in the dcache for
+ * case-insensitive filesystems.
+ *
+ * For a case-insensitive lookup match and if the the case-exact dentry
+ * already exists in in the dcache, use it and return it.
+ *
+ * If no entry exists with the exact case name, allocate new dentry with
+ * the exact case, and return the spliced entry.
+ */
+struct dentry *d_add_ci(struct inode *inode, struct dentry *dentry,
+                        struct qstr *name)
+{
+        int error;
+        struct dentry *found;
+        struct dentry *new;
+
+        /* Does a dentry matching the name exist already? */
+        found = d_hash_and_lookup(dentry->d_parent, name);
+        /* If not, create it now and return */
+        if (!found) {
+                new = d_alloc(dentry->d_parent, name);
+                if (!new) {
+                        error = -ENOMEM;
+                        goto err_out;
+                }
+                found = d_splice_alias(inode, new);
+                if (found) {
+                        dput(new);
+                        return found;
+                }
+                return new;
+        }
+        /* Matching dentry exists, check if it is negative. */
+        if (found->d_inode) {
+                if (unlikely(found->d_inode != inode)) {
+                        /* This can't happen because bad inodes are unhashed. */
+                        BUG_ON(!is_bad_inode(inode));
+                        BUG_ON(!is_bad_inode(found->d_inode));
+                }
+                /*
+                 * Already have the inode and the dentry attached, decrement
+                 * the reference count to balance the iget() done
+                 * earlier on.  We found the dentry using d_lookup() so it
+                 * cannot be disconnected and thus we do not need to worry
+                 * about any NFS/disconnectedness issues here.
+                 */
+                iput(inode);
+                return found;
+        }
+        /*
+         * Negative dentry: instantiate it unless the inode is a directory and
+         * has a 'disconnected' dentry (i.e. IS_ROOT and DCACHE_DISCONNECTED),
+         * in which case d_move() that in place of the found dentry.
+         */
+        if (!S_ISDIR(inode->i_mode)) {
+                /* Not a directory; everything is easy. */
+                d_instantiate(found, inode);
+                return found;
+        }
+        spin_lock(&dcache_lock);
+        if (list_empty(&inode->i_dentry)) {
+                /*
+                 * Directory without a 'disconnected' dentry; we need to do
+                 * d_instantiate() by hand because it takes dcache_lock which
+                 * we already hold.
+                 */
+                list_add(&found->d_alias, &inode->i_dentry);
+                found->d_inode = inode;
+                spin_unlock(&dcache_lock);
+                security_d_instantiate(found, inode);
+                return found;
+        }
+        /*
+         * Directory with a 'disconnected' dentry; get a reference to the
+         * 'disconnected' dentry.
+         */
+        new = list_entry(inode->i_dentry.next, struct dentry, d_alias);
+        dget_locked(new);
+        spin_unlock(&dcache_lock);
+        /* Do security vodoo. */
+        security_d_instantiate(found, inode);
+        /* Move new in place of found. */
+        d_move(new, found);
+        /* Balance the iget() we did above. */
+        iput(inode);
+        /* Throw away found. */
+        dput(found);
+        /* Use new as the actual dentry. */
+        return new;
+
+err_out:
+        iput(inode);
+        return ERR_PTR(error);
+}
 
 /**
  * d_lookup - search for a dentry
@@ -1215,7 +1342,7 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
  * rcu_read_lock() and rcu_read_unlock() are used to disable preemption while
  * lookup is going on.
  *
- * dentry_unused list is not updated even if lookup finds the required dentry
+ * The dentry unused LRU is not updated even if lookup finds the required dentry
  * in there. It is updated in places such as prune_dcache, shrink_dcache_sb,
  * select_parent and __dget_locked. This laziness saves lookup from dcache_lock
  * acquisition.
@@ -2228,6 +2355,7 @@ EXPORT_SYMBOL(d_path);
 EXPORT_SYMBOL(d_prune_aliases);
 EXPORT_SYMBOL(d_rehash);
 EXPORT_SYMBOL(d_splice_alias);
+EXPORT_SYMBOL(d_add_ci);
 EXPORT_SYMBOL(d_validate);
 EXPORT_SYMBOL(dget_locked);
 EXPORT_SYMBOL(dput);
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index e9602d85c11d..08e28c9bb416 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -309,6 +309,31 @@ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent,
 }
 EXPORT_SYMBOL_GPL(debugfs_create_symlink);
 
+static void __debugfs_remove(struct dentry *dentry, struct dentry *parent)
+{
+        int ret = 0;
+
+        if (debugfs_positive(dentry)) {
+                if (dentry->d_inode) {
+                        dget(dentry);
+                        switch (dentry->d_inode->i_mode & S_IFMT) {
+                        case S_IFDIR:
+                                ret = simple_rmdir(parent->d_inode, dentry);
+                                break;
+                        case S_IFLNK:
+                                kfree(dentry->d_inode->i_private);
+                                /* fall through */
+                        default:
+                                simple_unlink(parent->d_inode, dentry);
+                                break;
+                        }
+                        if (!ret)
+                                d_delete(dentry);
+                        dput(dentry);
+                }
+        }
+}
+
 /**
  * debugfs_remove - removes a file or directory from the debugfs filesystem
  * @dentry: a pointer to a the dentry of the file or directory to be
@@ -325,7 +350,6 @@ EXPORT_SYMBOL_GPL(debugfs_create_symlink);
 void debugfs_remove(struct dentry *dentry)
 {
         struct dentry *parent;
-        int ret = 0;
         
         if (!dentry)
                 return;
@@ -335,29 +359,83 @@ void debugfs_remove(struct dentry *dentry)
                 return;
 
         mutex_lock(&parent->d_inode->i_mutex);
-        if (debugfs_positive(dentry)) {
-                if (dentry->d_inode) {
-                        dget(dentry);
-                        switch (dentry->d_inode->i_mode & S_IFMT) {
-                        case S_IFDIR:
-                                ret = simple_rmdir(parent->d_inode, dentry);
-                                break;
-                        case S_IFLNK:
-                                kfree(dentry->d_inode->i_private);
-                                /* fall through */
-                        default:
-                                simple_unlink(parent->d_inode, dentry);
+        __debugfs_remove(dentry, parent);
+        mutex_unlock(&parent->d_inode->i_mutex);
+        simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+}
+EXPORT_SYMBOL_GPL(debugfs_remove);
+
+/**
+ * debugfs_remove_recursive - recursively removes a directory
+ * @dentry: a pointer to a the dentry of the directory to be removed.
+ *
+ * This function recursively removes a directory tree in debugfs that
+ * was previously created with a call to another debugfs function
+ * (like debugfs_create_file() or variants thereof.)
+ *
+ * This function is required to be called in order for the file to be
+ * removed, no automatic cleanup of files will happen when a module is
+ * removed, you are responsible here.
+ */
+void debugfs_remove_recursive(struct dentry *dentry)
+{
+        struct dentry *child;
+        struct dentry *parent;
+
+        if (!dentry)
+                return;
+
+        parent = dentry->d_parent;
+        if (!parent || !parent->d_inode)
+                return;
+
+        parent = dentry;
+        mutex_lock(&parent->d_inode->i_mutex);
+
+        while (1) {
+                /*
+                 * When all dentries under "parent" has been removed,
+                 * walk up the tree until we reach our starting point.
+                 */
+                if (list_empty(&parent->d_subdirs)) {
+                        mutex_unlock(&parent->d_inode->i_mutex);
+                        if (parent == dentry)
                                 break;
-                        }
-                        if (!ret)
-                                d_delete(dentry);
-                        dput(dentry);
+                        parent = parent->d_parent;
+                        mutex_lock(&parent->d_inode->i_mutex);
+                }
+                child = list_entry(parent->d_subdirs.next, struct dentry,
+                                d_u.d_child);
+
+                /*
+                 * If "child" isn't empty, walk down the tree and
+                 * remove all its descendants first.
+                 */
+                if (!list_empty(&child->d_subdirs)) {
+                        mutex_unlock(&parent->d_inode->i_mutex);
+                        parent = child;
+                        mutex_lock(&parent->d_inode->i_mutex);
+                        continue;
                 }
+                __debugfs_remove(child, parent);
+                if (parent->d_subdirs.next == &child->d_u.d_child) {
+                        /*
+                         * Avoid infinite loop if we fail to remove
+                         * one dentry.
+                         */
+                        mutex_unlock(&parent->d_inode->i_mutex);
+                        break;
+                }
+                simple_release_fs(&debugfs_mount, &debugfs_mount_count);
         }
+
+        parent = dentry->d_parent;
+        mutex_lock(&parent->d_inode->i_mutex);
+        __debugfs_remove(dentry, parent);
         mutex_unlock(&parent->d_inode->i_mutex);
         simple_release_fs(&debugfs_mount, &debugfs_mount_count);
 }
-EXPORT_SYMBOL_GPL(debugfs_remove);
+EXPORT_SYMBOL_GPL(debugfs_remove_recursive);
 
 /**
  * debugfs_rename - rename a file/directory in the debugfs filesystem
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 285b64a8b06e..488eb424f662 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -29,7 +29,7 @@
 #define DEVPTS_DEFAULT_MODE 0600
 
 extern int pty_limit;                   /* Config limit on Unix98 ptys */
-static DEFINE_IDR(allocated_ptys);
+static DEFINE_IDA(allocated_ptys);
 static DEFINE_MUTEX(allocated_ptys_lock);
 
 static struct vfsmount *devpts_mnt;
@@ -180,24 +180,24 @@ static struct dentry *get_node(int num)
 int devpts_new_index(void)
 {
         int index;
-        int idr_ret;
+        int ida_ret;
 
 retry:
-        if (!idr_pre_get(&allocated_ptys, GFP_KERNEL)) {
+        if (!ida_pre_get(&allocated_ptys, GFP_KERNEL)) {
                 return -ENOMEM;
         }
 
         mutex_lock(&allocated_ptys_lock);
-        idr_ret = idr_get_new(&allocated_ptys, NULL, &index);
-        if (idr_ret < 0) {
+        ida_ret = ida_get_new(&allocated_ptys, &index);
+        if (ida_ret < 0) {
                 mutex_unlock(&allocated_ptys_lock);
-                if (idr_ret == -EAGAIN)
+                if (ida_ret == -EAGAIN)
                         goto retry;
                 return -EIO;
         }
 
         if (index >= pty_limit) {
-                idr_remove(&allocated_ptys, index);
+                ida_remove(&allocated_ptys, index);
                 mutex_unlock(&allocated_ptys_lock);
                 return -EIO;
         }
@@ -208,7 +208,7 @@ retry:
 void devpts_kill_index(int idx)
 {
         mutex_lock(&allocated_ptys_lock);
-        idr_remove(&allocated_ptys, idx);
+        ida_remove(&allocated_ptys, idx);
         mutex_unlock(&allocated_ptys_lock);
 }
 
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 9e81addbd6ea..9606ee848fd8 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -150,17 +150,11 @@ static int dio_refill_pages(struct dio *dio)
         int nr_pages;
 
         nr_pages = min(dio->total_pages - dio->curr_page, DIO_PAGES);
-        down_read(&current->mm->mmap_sem);
-        ret = get_user_pages(
-                current,                        /* Task for fault acounting */
-                current->mm,                    /* whose pages? */
+        ret = get_user_pages_fast(
                 dio->curr_user_address,         /* Where from? */
                 nr_pages,                       /* How many pages? */
                 dio->rw == READ,                /* Write to memory? */
-                0,                              /* force (?) */
-                &dio->pages[0],
-                NULL);                          /* vmas */
-        up_read(&current->mm->mmap_sem);
+                &dio->pages[0]);                /* Put results here */
 
         if (ret < 0 && dio->blocks_available && (dio->rw & WRITE)) {
                 struct page *page = ZERO_PAGE(0);
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index 2d3d1027ce2b..724ddac91538 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -363,6 +363,7 @@ static int search_rsb_list(struct list_head *head, char *name, int len,
                 if (len == r->res_length && !memcmp(name, r->res_name, len))
                         goto found;
         }
+        *r_ret = NULL;
         return -EBADR;
 
  found:
@@ -1782,7 +1783,8 @@ static void grant_pending_locks(struct dlm_rsb *r)
 
         list_for_each_entry_safe(lkb, s, &r->res_grantqueue, lkb_statequeue) {
                 if (lkb->lkb_bastfn && lock_requires_bast(lkb, high, cw)) {
-                        if (cw && high == DLM_LOCK_PR)
+                        if (cw && high == DLM_LOCK_PR &&
+                            lkb->lkb_grmode == DLM_LOCK_PR)
                                 queue_bast(r, lkb, DLM_LOCK_CW);
                         else
                                 queue_bast(r, lkb, high);
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 637018c891ef..3962262f991a 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -891,8 +891,10 @@ static void tcp_connect_to_sock(struct connection *con)
                 goto out_err;
 
         memset(&saddr, 0, sizeof(saddr));
-        if (dlm_nodeid_to_addr(con->nodeid, &saddr))
+        if (dlm_nodeid_to_addr(con->nodeid, &saddr)) {
+                sock_release(sock);
                 goto out_err;
+        }
 
         sock->sk->sk_user_data = con;
         con->rx_action = receive_from_sock;
diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c
index 78878c5781ca..eba87ff3177b 100644
--- a/fs/dlm/plock.c
+++ b/fs/dlm/plock.c
@@ -116,7 +116,7 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
         if (xop->callback == NULL)
                 wait_event(recv_wq, (op->done != 0));
         else {
-                rv = -EINPROGRESS;
+                rv = FILE_LOCK_DEFERRED;
                 goto out;
         }
 
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index f976f303c196..929e48ae7591 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -539,7 +539,7 @@ static ssize_t device_write(struct file *file, const char __user *buf,
 
         /* do we really need this? can a write happen after a close? */
         if ((kbuf->cmd == DLM_USER_LOCK || kbuf->cmd == DLM_USER_UNLOCK) &&
-            test_bit(DLM_PROC_FLAGS_CLOSING, &proc->flags))
+            (proc && test_bit(DLM_PROC_FLAGS_CLOSING, &proc->flags)))
                 return -EINVAL;
 
         sigfillset(&allsigs);
diff --git a/fs/dquot.c b/fs/dquot.c
index 5ac77da19959..8ec4d6cc7633 100644
--- a/fs/dquot.c
+++ b/fs/dquot.c
@@ -562,6 +562,8 @@ static struct shrinker dqcache_shrinker = {
  */
 static void dqput(struct dquot *dquot)
 {
+        int ret;
+
         if (!dquot)
                 return;
 #ifdef __DQUOT_PARANOIA
@@ -594,7 +596,19 @@ we_slept:
         if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags) && dquot_dirty(dquot)) {
                 spin_unlock(&dq_list_lock);
                 /* Commit dquot before releasing */
-                dquot->dq_sb->dq_op->write_dquot(dquot);
+                ret = dquot->dq_sb->dq_op->write_dquot(dquot);
+                if (ret < 0) {
+                        printk(KERN_ERR "VFS: cannot write quota structure on "
+                                "device %s (error %d). Quota may get out of "
+                                "sync!\n", dquot->dq_sb->s_id, ret);
+                        /*
+                         * We clear dirty bit anyway, so that we avoid
+                         * infinite loop here
+                         */
+                        spin_lock(&dq_list_lock);
+                        clear_dquot_dirty(dquot);
+                        spin_unlock(&dq_list_lock);
+                }
                 goto we_slept;
         }
         /* Clear flag in case dquot was inactive (something bad happened) */
@@ -875,7 +889,10 @@ static void print_warning(struct dquot *dquot, const int warntype)
         char *msg = NULL;
         struct tty_struct *tty;
 
-        if (!need_print_warning(dquot))
+        if (warntype == QUOTA_NL_IHARDBELOW ||
+            warntype == QUOTA_NL_ISOFTBELOW ||
+            warntype == QUOTA_NL_BHARDBELOW ||
+            warntype == QUOTA_NL_BSOFTBELOW || !need_print_warning(dquot))
                 return;
 
         mutex_lock(&tty_mutex);
@@ -1083,6 +1100,35 @@ static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc, char *war
         return QUOTA_OK;
 }
 
+static int info_idq_free(struct dquot *dquot, ulong inodes)
+{
+        if (test_bit(DQ_FAKE_B, &dquot->dq_flags) ||
+            dquot->dq_dqb.dqb_curinodes <= dquot->dq_dqb.dqb_isoftlimit)
+                return QUOTA_NL_NOWARN;
+
+        if (dquot->dq_dqb.dqb_curinodes - inodes <= dquot->dq_dqb.dqb_isoftlimit)
+                return QUOTA_NL_ISOFTBELOW;
+        if (dquot->dq_dqb.dqb_curinodes >= dquot->dq_dqb.dqb_ihardlimit &&
+            dquot->dq_dqb.dqb_curinodes - inodes < dquot->dq_dqb.dqb_ihardlimit)
+                return QUOTA_NL_IHARDBELOW;
+        return QUOTA_NL_NOWARN;
+}
+
+static int info_bdq_free(struct dquot *dquot, qsize_t space)
+{
+        if (test_bit(DQ_FAKE_B, &dquot->dq_flags) ||
+            toqb(dquot->dq_dqb.dqb_curspace) <= dquot->dq_dqb.dqb_bsoftlimit)
+                return QUOTA_NL_NOWARN;
+
+        if (toqb(dquot->dq_dqb.dqb_curspace - space) <=
+            dquot->dq_dqb.dqb_bsoftlimit)
+                return QUOTA_NL_BSOFTBELOW;
+        if (toqb(dquot->dq_dqb.dqb_curspace) >= dquot->dq_dqb.dqb_bhardlimit &&
+            toqb(dquot->dq_dqb.dqb_curspace - space) <
+                                                dquot->dq_dqb.dqb_bhardlimit)
+                return QUOTA_NL_BHARDBELOW;
+        return QUOTA_NL_NOWARN;
+}
 /*
  *      Initialize quota pointers in inode
  *      Transaction must be started at entry
@@ -1139,6 +1185,28 @@ int dquot_drop(struct inode *inode)
         return 0;
 }
 
+/* Wrapper to remove references to quota structures from inode */
+void vfs_dq_drop(struct inode *inode)
+{
+        /* Here we can get arbitrary inode from clear_inode() so we have
+         * to be careful. OTOH we don't need locking as quota operations
+         * are allowed to change only at mount time */
+        if (!IS_NOQUOTA(inode) && inode->i_sb && inode->i_sb->dq_op
+            && inode->i_sb->dq_op->drop) {
+                int cnt;
+                /* Test before calling to rule out calls from proc and such
+                 * where we are not allowed to block. Note that this is
+                 * actually reliable test even without the lock - the caller
+                 * must assure that nobody can come after the DQUOT_DROP and
+                 * add quota pointers back anyway */
+                for (cnt = 0; cnt < MAXQUOTAS; cnt++)
+                        if (inode->i_dquot[cnt] != NODQUOT)
+                                break;
+                if (cnt < MAXQUOTAS)
+                        inode->i_sb->dq_op->drop(inode);
+        }
+}
+
 /*
  * Following four functions update i_blocks+i_bytes fields and
  * quota information (together with appropriate checks)
@@ -1248,6 +1316,7 @@ warn_put_all:
 int dquot_free_space(struct inode *inode, qsize_t number)
 {
         unsigned int cnt;
+        char warntype[MAXQUOTAS];
 
         /* First test before acquiring mutex - solves deadlocks when we
          * re-enter the quota code and are already holding the mutex */
@@ -1256,6 +1325,7 @@ out_sub:
                 inode_sub_bytes(inode, number);
                 return QUOTA_OK;
         }
+
         down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
         /* Now recheck reliably when holding dqptr_sem */
         if (IS_NOQUOTA(inode)) {
@@ -1266,6 +1336,7 @@ out_sub:
         for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
                 if (inode->i_dquot[cnt] == NODQUOT)
                         continue;
+                warntype[cnt] = info_bdq_free(inode->i_dquot[cnt], number);
                 dquot_decr_space(inode->i_dquot[cnt], number);
         }
         inode_sub_bytes(inode, number);
@@ -1274,6 +1345,7 @@ out_sub:
         for (cnt = 0; cnt < MAXQUOTAS; cnt++)
                 if (inode->i_dquot[cnt])
                         mark_dquot_dirty(inode->i_dquot[cnt]);
+        flush_warnings(inode->i_dquot, warntype);
         up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
         return QUOTA_OK;
 }
@@ -1284,11 +1356,13 @@ out_sub:
 int dquot_free_inode(const struct inode *inode, unsigned long number)
 {
         unsigned int cnt;
+        char warntype[MAXQUOTAS];
 
         /* First test before acquiring mutex - solves deadlocks when we
          * re-enter the quota code and are already holding the mutex */
         if (IS_NOQUOTA(inode))
                 return QUOTA_OK;
+
         down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
         /* Now recheck reliably when holding dqptr_sem */
         if (IS_NOQUOTA(inode)) {
@@ -1299,6 +1373,7 @@ int dquot_free_inode(const struct inode *inode, unsigned long number)
         for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
                 if (inode->i_dquot[cnt] == NODQUOT)
                         continue;
+                warntype[cnt] = info_idq_free(inode->i_dquot[cnt], number);
                 dquot_decr_inodes(inode->i_dquot[cnt], number);
         }
         spin_unlock(&dq_data_lock);
@@ -1306,6 +1381,7 @@ int dquot_free_inode(const struct inode *inode, unsigned long number)
         for (cnt = 0; cnt < MAXQUOTAS; cnt++)
                 if (inode->i_dquot[cnt])
                         mark_dquot_dirty(inode->i_dquot[cnt]);
+        flush_warnings(inode->i_dquot, warntype);
         up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
         return QUOTA_OK;
 }
@@ -1323,7 +1399,8 @@ int dquot_transfer(struct inode *inode, struct iattr *iattr)
         struct dquot *transfer_to[MAXQUOTAS];
         int cnt, ret = NO_QUOTA, chuid = (iattr->ia_valid & ATTR_UID) && inode->i_uid != iattr->ia_uid,
             chgid = (iattr->ia_valid & ATTR_GID) && inode->i_gid != iattr->ia_gid;
-        char warntype[MAXQUOTAS];
+        char warntype_to[MAXQUOTAS];
+        char warntype_from_inodes[MAXQUOTAS], warntype_from_space[MAXQUOTAS];
 
         /* First test before acquiring mutex - solves deadlocks when we
          * re-enter the quota code and are already holding the mutex */
@@ -1332,7 +1409,7 @@ int dquot_transfer(struct inode *inode, struct iattr *iattr)
         /* Clear the arrays */
         for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
                 transfer_to[cnt] = transfer_from[cnt] = NODQUOT;
-                warntype[cnt] = QUOTA_NL_NOWARN;
+                warntype_to[cnt] = QUOTA_NL_NOWARN;
         }
         down_write(&sb_dqopt(inode->i_sb)->dqptr_sem);
         /* Now recheck reliably when holding dqptr_sem */
@@ -1364,8 +1441,9 @@ int dquot_transfer(struct inode *inode, struct iattr *iattr)
                 if (transfer_to[cnt] == NODQUOT)
                         continue;
                 transfer_from[cnt] = inode->i_dquot[cnt];
-                if (check_idq(transfer_to[cnt], 1, warntype+cnt) == NO_QUOTA ||
-                    check_bdq(transfer_to[cnt], space, 0, warntype+cnt) == NO_QUOTA)
+                if (check_idq(transfer_to[cnt], 1, warntype_to + cnt) ==
+                    NO_QUOTA || check_bdq(transfer_to[cnt], space, 0,
+                    warntype_to + cnt) == NO_QUOTA)
                         goto warn_put_all;
         }
 
@@ -1381,6 +1459,10 @@ int dquot_transfer(struct inode *inode, struct iattr *iattr)
 
                 /* Due to IO error we might not have transfer_from[] structure */
                 if (transfer_from[cnt]) {
+                        warntype_from_inodes[cnt] =
+                                info_idq_free(transfer_from[cnt], 1);
+                        warntype_from_space[cnt] =
+                                info_bdq_free(transfer_from[cnt], space);
                         dquot_decr_inodes(transfer_from[cnt], 1);
                         dquot_decr_space(transfer_from[cnt], space);
                 }
@@ -1400,7 +1482,9 @@ warn_put_all:
                 if (transfer_to[cnt])
                         mark_dquot_dirty(transfer_to[cnt]);
         }
-        flush_warnings(transfer_to, warntype);
+        flush_warnings(transfer_to, warntype_to);
+        flush_warnings(transfer_from, warntype_from_inodes);
+        flush_warnings(transfer_from, warntype_from_space);
         
         for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
                 if (ret == QUOTA_OK && transfer_from[cnt] != NODQUOT)
@@ -1412,6 +1496,18 @@ warn_put_all:
         return ret;
 }
 
+/* Wrapper for transferring ownership of an inode */
+int vfs_dq_transfer(struct inode *inode, struct iattr *iattr)
+{
+        if (sb_any_quota_enabled(inode->i_sb) && !IS_NOQUOTA(inode)) {
+                vfs_dq_init(inode);
+                if (inode->i_sb->dq_op->transfer(inode, iattr) == NO_QUOTA)
+                        return 1;
+        }
+        return 0;
+}
+
+
 /*
  * Write info of quota file to disk
  */
@@ -1697,6 +1793,21 @@ static int vfs_quota_on_remount(struct super_block *sb, int type)
         return ret;
 }
 
+int vfs_quota_on_path(struct super_block *sb, int type, int format_id,
+                      struct path *path)
+{
+        int error = security_quota_on(path->dentry);
+        if (error)
+                return error;
+        /* Quota file not on the same filesystem? */
+        if (path->mnt->mnt_sb != sb)
+                error = -EXDEV;
+        else
+                error = vfs_quota_on_inode(path->dentry->d_inode, type,
+                                           format_id);
+        return error;
+}
+
 /* Actual function called from quotactl() */
 int vfs_quota_on(struct super_block *sb, int type, int format_id, char *path,
                  int remount)
@@ -1708,19 +1819,10 @@ int vfs_quota_on(struct super_block *sb, int type, int format_id, char *path,
                 return vfs_quota_on_remount(sb, type);
 
         error = path_lookup(path, LOOKUP_FOLLOW, &nd);
-        if (error < 0)
-                return error;
-        error = security_quota_on(nd.path.dentry);
-        if (error)
-                goto out_path;
-        /* Quota file not on the same filesystem? */
-        if (nd.path.mnt->mnt_sb != sb)
-                error = -EXDEV;
-        else
-                error = vfs_quota_on_inode(nd.path.dentry->d_inode, type,
-                                           format_id);
-out_path:
-        path_put(&nd.path);
+        if (!error) {
+                error = vfs_quota_on_path(sb, type, format_id, &nd.path);
+                path_put(&nd.path);
+        }
         return error;
 }
 
@@ -1752,6 +1854,22 @@ out:
         return error;
 }
 
+/* Wrapper to turn on quotas when remounting rw */
+int vfs_dq_quota_on_remount(struct super_block *sb)
+{
+        int cnt;
+        int ret = 0, err;
+
+        if (!sb->s_qcop || !sb->s_qcop->quota_on)
+                return -ENOSYS;
+        for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
+                err = sb->s_qcop->quota_on(sb, cnt, 0, NULL, 1);
+                if (err < 0 && !ret)
+                        ret = err;
+        }
+        return ret;
+}
+
 /* Generic routine for getting common part of quota structure */
 static void do_get_dqblk(struct dquot *dquot, struct if_dqblk *di)
 {
@@ -2073,6 +2191,7 @@ EXPORT_SYMBOL(unregister_quota_format);
 EXPORT_SYMBOL(dqstats);
 EXPORT_SYMBOL(dq_data_lock);
 EXPORT_SYMBOL(vfs_quota_on);
+EXPORT_SYMBOL(vfs_quota_on_path);
 EXPORT_SYMBOL(vfs_quota_on_mount);
 EXPORT_SYMBOL(vfs_quota_off);
 EXPORT_SYMBOL(vfs_quota_sync);
@@ -2087,8 +2206,11 @@ EXPORT_SYMBOL(dquot_release);
 EXPORT_SYMBOL(dquot_mark_dquot_dirty);
 EXPORT_SYMBOL(dquot_initialize);
 EXPORT_SYMBOL(dquot_drop);
+EXPORT_SYMBOL(vfs_dq_drop);
 EXPORT_SYMBOL(dquot_alloc_space);
 EXPORT_SYMBOL(dquot_alloc_inode);
 EXPORT_SYMBOL(dquot_free_space);
 EXPORT_SYMBOL(dquot_free_inode);
 EXPORT_SYMBOL(dquot_transfer);
+EXPORT_SYMBOL(vfs_dq_transfer);
+EXPORT_SYMBOL(vfs_dq_quota_on_remount);
diff --git a/fs/ecryptfs/Makefile b/fs/ecryptfs/Makefile
index 1e34a7fd4884..b4755a85996e 100644
--- a/fs/ecryptfs/Makefile
+++ b/fs/ecryptfs/Makefile
@@ -4,4 +4,4 @@
 
 obj-$(CONFIG_ECRYPT_FS) += ecryptfs.o
 
-ecryptfs-objs := dentry.o file.o inode.o main.o super.o mmap.o read_write.o crypto.o keystore.o messaging.o netlink.o miscdev.o debug.o
+ecryptfs-objs := dentry.o file.o inode.o main.o super.o mmap.o read_write.o crypto.o keystore.o messaging.o netlink.o miscdev.o kthread.o debug.o
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index e2832bc7869a..06db79d05c12 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -33,6 +33,7 @@
 #include <linux/crypto.h>
 #include <linux/file.h>
 #include <linux/scatterlist.h>
+#include <asm/unaligned.h>
 #include "ecryptfs_kernel.h"
 
 static int
@@ -474,8 +475,8 @@ int ecryptfs_encrypt_page(struct page *page)
 {
         struct inode *ecryptfs_inode;
         struct ecryptfs_crypt_stat *crypt_stat;
-        char *enc_extent_virt = NULL;
-        struct page *enc_extent_page;
+        char *enc_extent_virt;
+        struct page *enc_extent_page = NULL;
         loff_t extent_offset;
         int rc = 0;
 
@@ -491,14 +492,14 @@ int ecryptfs_encrypt_page(struct page *page)
                                page->index);
                 goto out;
         }
-        enc_extent_virt = kmalloc(PAGE_CACHE_SIZE, GFP_USER);
-        if (!enc_extent_virt) {
+        enc_extent_page = alloc_page(GFP_USER);
+        if (!enc_extent_page) {
                 rc = -ENOMEM;
                 ecryptfs_printk(KERN_ERR, "Error allocating memory for "
                                 "encrypted extent\n");
                 goto out;
         }
-        enc_extent_page = virt_to_page(enc_extent_virt);
+        enc_extent_virt = kmap(enc_extent_page);
         for (extent_offset = 0;
              extent_offset < (PAGE_CACHE_SIZE / crypt_stat->extent_size);
              extent_offset++) {
@@ -526,7 +527,10 @@ int ecryptfs_encrypt_page(struct page *page)
                 }
         }
 out:
-        kfree(enc_extent_virt);
+        if (enc_extent_page) {
+                kunmap(enc_extent_page);
+                __free_page(enc_extent_page);
+        }
         return rc;
 }
 
@@ -608,8 +612,8 @@ int ecryptfs_decrypt_page(struct page *page)
 {
         struct inode *ecryptfs_inode;
         struct ecryptfs_crypt_stat *crypt_stat;
-        char *enc_extent_virt = NULL;
-        struct page *enc_extent_page;
+        char *enc_extent_virt;
+        struct page *enc_extent_page = NULL;
         unsigned long extent_offset;
         int rc = 0;
 
@@ -626,14 +630,14 @@ int ecryptfs_decrypt_page(struct page *page)
                                page->index);
                 goto out;
         }
-        enc_extent_virt = kmalloc(PAGE_CACHE_SIZE, GFP_USER);
-        if (!enc_extent_virt) {
+        enc_extent_page = alloc_page(GFP_USER);
+        if (!enc_extent_page) {
                 rc = -ENOMEM;
                 ecryptfs_printk(KERN_ERR, "Error allocating memory for "
                                 "encrypted extent\n");
                 goto out;
         }
-        enc_extent_page = virt_to_page(enc_extent_virt);
+        enc_extent_virt = kmap(enc_extent_page);
         for (extent_offset = 0;
              extent_offset < (PAGE_CACHE_SIZE / crypt_stat->extent_size);
              extent_offset++) {
@@ -661,7 +665,10 @@ int ecryptfs_decrypt_page(struct page *page)
                 }
         }
 out:
-        kfree(enc_extent_virt);
+        if (enc_extent_page) {
+                kunmap(enc_extent_page);
+                __free_page(enc_extent_page);
+        }
         return rc;
 }
 
@@ -1032,10 +1039,8 @@ static int contains_ecryptfs_marker(char *data)
 {
         u32 m_1, m_2;
 
-        memcpy(&m_1, data, 4);
-        m_1 = be32_to_cpu(m_1);
-        memcpy(&m_2, (data + 4), 4);
-        m_2 = be32_to_cpu(m_2);
+        m_1 = get_unaligned_be32(data);
+        m_2 = get_unaligned_be32(data + 4);
         if ((m_1 ^ MAGIC_ECRYPTFS_MARKER) == m_2)
                 return 1;
         ecryptfs_printk(KERN_DEBUG, "m_1 = [0x%.8x]; m_2 = [0x%.8x]; "
@@ -1073,8 +1078,7 @@ static int ecryptfs_process_flags(struct ecryptfs_crypt_stat *crypt_stat,
         int i;
         u32 flags;
 
-        memcpy(&flags, page_virt, 4);
-        flags = be32_to_cpu(flags);
+        flags = get_unaligned_be32(page_virt);
         for (i = 0; i < ((sizeof(ecryptfs_flag_map)
                           / sizeof(struct ecryptfs_flag_map_elem))); i++)
                 if (flags & ecryptfs_flag_map[i].file_flag) {
@@ -1100,11 +1104,9 @@ static void write_ecryptfs_marker(char *page_virt, size_t *written)
 
         get_random_bytes(&m_1, (MAGIC_ECRYPTFS_MARKER_SIZE_BYTES / 2));
         m_2 = (m_1 ^ MAGIC_ECRYPTFS_MARKER);
-        m_1 = cpu_to_be32(m_1);
-        memcpy(page_virt, &m_1, (MAGIC_ECRYPTFS_MARKER_SIZE_BYTES / 2));
-        m_2 = cpu_to_be32(m_2);
-        memcpy(page_virt + (MAGIC_ECRYPTFS_MARKER_SIZE_BYTES / 2), &m_2,
-               (MAGIC_ECRYPTFS_MARKER_SIZE_BYTES / 2));
+        put_unaligned_be32(m_1, page_virt);
+        page_virt += (MAGIC_ECRYPTFS_MARKER_SIZE_BYTES / 2);
+        put_unaligned_be32(m_2, page_virt);
         (*written) = MAGIC_ECRYPTFS_MARKER_SIZE_BYTES;
 }
 
@@ -1121,8 +1123,7 @@ write_ecryptfs_flags(char *page_virt, struct ecryptfs_crypt_stat *crypt_stat,
                         flags |= ecryptfs_flag_map[i].file_flag;
         /* Version is in top 8 bits of the 32-bit flag vector */
         flags |= ((((u8)crypt_stat->file_version) << 24) & 0xFF000000);
-        flags = cpu_to_be32(flags);
-        memcpy(page_virt, &flags, 4);
+        put_unaligned_be32(flags, page_virt);
         (*written) = 4;
 }
 
@@ -1238,11 +1239,9 @@ ecryptfs_write_header_metadata(char *virt,
         num_header_extents_at_front =
                 (u16)(crypt_stat->num_header_bytes_at_front
                       / crypt_stat->extent_size);
-        header_extent_size = cpu_to_be32(header_extent_size);
-        memcpy(virt, &header_extent_size, 4);
+        put_unaligned_be32(header_extent_size, virt);
         virt += 4;
-        num_header_extents_at_front = cpu_to_be16(num_header_extents_at_front);
-        memcpy(virt, &num_header_extents_at_front, 2);
+        put_unaligned_be16(num_header_extents_at_front, virt);
         (*written) = 6;
 }
 
@@ -1410,15 +1409,13 @@ static int parse_header_metadata(struct ecryptfs_crypt_stat *crypt_stat,
         u32 header_extent_size;
         u16 num_header_extents_at_front;
 
-        memcpy(&header_extent_size, virt, sizeof(u32));
-        header_extent_size = be32_to_cpu(header_extent_size);
-        virt += sizeof(u32);
-        memcpy(&num_header_extents_at_front, virt, sizeof(u16));
-        num_header_extents_at_front = be16_to_cpu(num_header_extents_at_front);
+        header_extent_size = get_unaligned_be32(virt);
+        virt += sizeof(__be32);
+        num_header_extents_at_front = get_unaligned_be16(virt);
         crypt_stat->num_header_bytes_at_front =
                 (((size_t)num_header_extents_at_front
                   * (size_t)header_extent_size));
-        (*bytes_read) = (sizeof(u32) + sizeof(u16));
+        (*bytes_read) = (sizeof(__be32) + sizeof(__be16));
         if ((validate_header_size == ECRYPTFS_VALIDATE_HEADER_SIZE)
             && (crypt_stat->num_header_bytes_at_front
                 < ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE)) {
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index c15c25745e05..b73fb752c5f8 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -559,10 +559,25 @@ extern struct kmem_cache *ecryptfs_key_record_cache;
 extern struct kmem_cache *ecryptfs_key_sig_cache;
 extern struct kmem_cache *ecryptfs_global_auth_tok_cache;
 extern struct kmem_cache *ecryptfs_key_tfm_cache;
+extern struct kmem_cache *ecryptfs_open_req_cache;
 
+struct ecryptfs_open_req {
+#define ECRYPTFS_REQ_PROCESSED 0x00000001
+#define ECRYPTFS_REQ_DROPPED   0x00000002
+#define ECRYPTFS_REQ_ZOMBIE    0x00000004
+        u32 flags;
+        struct file **lower_file;
+        struct dentry *lower_dentry;
+        struct vfsmount *lower_mnt;
+        wait_queue_head_t wait;
+        struct mutex mux;
+        struct list_head kthread_ctl_list;
+};
+
+#define ECRYPTFS_INTERPOSE_FLAG_D_ADD                 0x00000001
 int ecryptfs_interpose(struct dentry *hidden_dentry,
                        struct dentry *this_dentry, struct super_block *sb,
-                       int flag);
+                       u32 flags);
 int ecryptfs_fill_zeros(struct file *file, loff_t new_length);
 int ecryptfs_decode_filename(struct ecryptfs_crypt_stat *crypt_stat,
                              const char *name, int length,
@@ -690,5 +705,11 @@ void ecryptfs_msg_ctx_alloc_to_free(struct ecryptfs_msg_ctx *msg_ctx);
 int
 ecryptfs_spawn_daemon(struct ecryptfs_daemon **daemon, uid_t euid,
                       struct user_namespace *user_ns, struct pid *pid);
+int ecryptfs_init_kthread(void);
+void ecryptfs_destroy_kthread(void);
+int ecryptfs_privileged_open(struct file **lower_file,
+                             struct dentry *lower_dentry,
+                             struct vfsmount *lower_mnt);
+int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry);
 
 #endif /* #ifndef ECRYPTFS_KERNEL_H */
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 24749bf0668f..9244d653743e 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -192,6 +192,23 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
                                       | ECRYPTFS_ENCRYPTED);
         }
         mutex_unlock(&crypt_stat->cs_mutex);
+        if ((ecryptfs_inode_to_private(inode)->lower_file->f_flags & O_RDONLY)
+            && !(file->f_flags & O_RDONLY)) {
+                rc = -EPERM;
+                printk(KERN_WARNING "%s: Lower persistent file is RO; eCryptfs "
+                       "file must hence be opened RO\n", __func__);
+                goto out;
+        }
+        if (!ecryptfs_inode_to_private(inode)->lower_file) {
+                rc = ecryptfs_init_persistent_file(ecryptfs_dentry);
+                if (rc) {
+                        printk(KERN_ERR "%s: Error attempting to initialize "
+                               "the persistent file for the dentry with name "
+                               "[%s]; rc = [%d]\n", __func__,
+                               ecryptfs_dentry->d_name.name, rc);
+                        goto out;
+                }
+        }
         ecryptfs_set_file_lower(
                 file, ecryptfs_inode_to_private(inode)->lower_file);
         if (S_ISDIR(ecryptfs_dentry->d_inode->i_mode)) {
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index c92cc1c00aae..89209f00f9c7 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -31,6 +31,7 @@
 #include <linux/mount.h>
 #include <linux/crypto.h>
 #include <linux/fs_stack.h>
+#include <asm/unaligned.h>
 #include "ecryptfs_kernel.h"
 
 static struct dentry *lock_parent(struct dentry *dentry)
@@ -188,6 +189,16 @@ static int ecryptfs_initialize_file(struct dentry *ecryptfs_dentry)
                                 "context; rc = [%d]\n", rc);
                 goto out;
         }
+        if (!ecryptfs_inode_to_private(ecryptfs_dentry->d_inode)->lower_file) {
+                rc = ecryptfs_init_persistent_file(ecryptfs_dentry);
+                if (rc) {
+                        printk(KERN_ERR "%s: Error attempting to initialize "
+                               "the persistent file for the dentry with name "
+                               "[%s]; rc = [%d]\n", __func__,
+                               ecryptfs_dentry->d_name.name, rc);
+                        goto out;
+                }
+        }
         rc = ecryptfs_write_metadata(ecryptfs_dentry);
         if (rc) {
                 printk(KERN_ERR "Error writing headers; rc = [%d]\n", rc);
@@ -307,10 +318,11 @@ static struct dentry *ecryptfs_lookup(struct inode *dir, struct dentry *dentry,
                 d_add(dentry, NULL);
                 goto out;
         }
-        rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb, 1);
+        rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb,
+                                ECRYPTFS_INTERPOSE_FLAG_D_ADD);
         if (rc) {
                 ecryptfs_printk(KERN_ERR, "Error interposing\n");
-                goto out_dput;
+                goto out;
         }
         if (S_ISDIR(lower_inode->i_mode)) {
                 ecryptfs_printk(KERN_DEBUG, "Is a directory; returning\n");
@@ -336,11 +348,21 @@ static struct dentry *ecryptfs_lookup(struct inode *dir, struct dentry *dentry,
                 rc = -ENOMEM;
                 ecryptfs_printk(KERN_ERR,
                                 "Cannot ecryptfs_kmalloc a page\n");
-                goto out_dput;
+                goto out;
         }
         crypt_stat = &ecryptfs_inode_to_private(dentry->d_inode)->crypt_stat;
         if (!(crypt_stat->flags & ECRYPTFS_POLICY_APPLIED))
                 ecryptfs_set_default_sizes(crypt_stat);
+        if (!ecryptfs_inode_to_private(dentry->d_inode)->lower_file) {
+                rc = ecryptfs_init_persistent_file(dentry);
+                if (rc) {
+                        printk(KERN_ERR "%s: Error attempting to initialize "
+                               "the persistent file for the dentry with name "
+                               "[%s]; rc = [%d]\n", __func__,
+                               dentry->d_name.name, rc);
+                        goto out;
+                }
+        }
         rc = ecryptfs_read_and_validate_header_region(page_virt,
                                                       dentry->d_inode);
         if (rc) {
@@ -364,8 +386,7 @@ static struct dentry *ecryptfs_lookup(struct inode *dir, struct dentry *dentry,
                 else
                         file_size = i_size_read(lower_dentry->d_inode);
         } else {
-                memcpy(&file_size, page_virt, sizeof(file_size));
-                file_size = be64_to_cpu(file_size);
+                file_size = get_unaligned_be64(page_virt);
         }
         i_size_write(dentry->d_inode, (loff_t)file_size);
         kmem_cache_free(ecryptfs_header_cache_2, page_virt);
@@ -444,7 +465,6 @@ static int ecryptfs_symlink(struct inode *dir, struct dentry *dentry,
         int rc;
         struct dentry *lower_dentry;
         struct dentry *lower_dir_dentry;
-        umode_t mode;
         char *encoded_symname;
         int encoded_symlen;
         struct ecryptfs_crypt_stat *crypt_stat = NULL;
@@ -452,7 +472,6 @@ static int ecryptfs_symlink(struct inode *dir, struct dentry *dentry,
         lower_dentry = ecryptfs_dentry_to_lower(dentry);
         dget(lower_dentry);
         lower_dir_dentry = lock_parent(lower_dentry);
-        mode = S_IALLUGO;
         encoded_symlen = ecryptfs_encode_filename(crypt_stat, symname,
                                                   strlen(symname),
                                                   &encoded_symname);
@@ -461,7 +480,7 @@ static int ecryptfs_symlink(struct inode *dir, struct dentry *dentry,
                 goto out_lock;
         }
         rc = vfs_symlink(lower_dir_dentry->d_inode, lower_dentry,
-                         encoded_symname, mode);
+                         encoded_symname);
         kfree(encoded_symname);
         if (rc || !lower_dentry->d_inode)
                 goto out_lock;
@@ -809,22 +828,9 @@ out:
 }
 
 static int
-ecryptfs_permission(struct inode *inode, int mask, struct nameidata *nd)
+ecryptfs_permission(struct inode *inode, int mask)
 {
-        int rc;
-
-        if (nd) {
-                struct vfsmount *vfsmnt_save = nd->path.mnt;
-                struct dentry *dentry_save = nd->path.dentry;
-
-                nd->path.mnt = ecryptfs_dentry_to_lower_mnt(nd->path.dentry);
-                nd->path.dentry = ecryptfs_dentry_to_lower(nd->path.dentry);
-                rc = permission(ecryptfs_inode_to_lower(inode), mask, nd);
-                nd->path.mnt = vfsmnt_save;
-                nd->path.dentry = dentry_save;
-        } else
-                rc = permission(ecryptfs_inode_to_lower(inode), mask, NULL);
-        return rc;
+        return inode_permission(ecryptfs_inode_to_lower(inode), mask);
 }
 
 /**
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index e82b457180be..f5b76a331b9c 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -44,15 +44,15 @@ static int process_request_key_err(long err_code)
         int rc = 0;
 
         switch (err_code) {
-        case ENOKEY:
+        case -ENOKEY:
                 ecryptfs_printk(KERN_WARNING, "No key\n");
                 rc = -ENOENT;
                 break;
-        case EKEYEXPIRED:
+        case -EKEYEXPIRED:
                 ecryptfs_printk(KERN_WARNING, "Key expired\n");
                 rc = -ETIME;
                 break;
-        case EKEYREVOKED:
+        case -EKEYREVOKED:
                 ecryptfs_printk(KERN_WARNING, "Key revoked\n");
                 rc = -EINVAL;
                 break;
@@ -963,8 +963,7 @@ int ecryptfs_keyring_auth_tok_for_sig(struct key **auth_tok_key,
         if (!(*auth_tok_key) || IS_ERR(*auth_tok_key)) {
                 printk(KERN_ERR "Could not find key with description: [%s]\n",
                        sig);
-                process_request_key_err(PTR_ERR(*auth_tok_key));
-                rc = -EINVAL;
+                rc = process_request_key_err(PTR_ERR(*auth_tok_key));
                 goto out;
         }
         (*auth_tok) = ecryptfs_get_key_payload_data(*auth_tok_key);
diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c
new file mode 100644
index 000000000000..c440c6b58b2d
--- /dev/null
+++ b/fs/ecryptfs/kthread.c
@@ -0,0 +1,203 @@
+/**
+ * eCryptfs: Linux filesystem encryption layer
+ *
+ * Copyright (C) 2008 International Business Machines Corp.
+ *   Author(s): Michael A. Halcrow <mahalcro@us.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
+ * 02111-1307, USA.
+ */
+
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/wait.h>
+#include <linux/mount.h>
+#include "ecryptfs_kernel.h"
+
+struct kmem_cache *ecryptfs_open_req_cache;
+
+static struct ecryptfs_kthread_ctl {
+#define ECRYPTFS_KTHREAD_ZOMBIE 0x00000001
+        u32 flags;
+        struct mutex mux;
+        struct list_head req_list;
+        wait_queue_head_t wait;
+} ecryptfs_kthread_ctl;
+
+static struct task_struct *ecryptfs_kthread;
+
+/**
+ * ecryptfs_threadfn
+ * @ignored: ignored
+ *
+ * The eCryptfs kernel thread that has the responsibility of getting
+ * the lower persistent file with RW permissions.
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+static int ecryptfs_threadfn(void *ignored)
+{
+        set_freezable();
+        while (1)  {
+                struct ecryptfs_open_req *req;
+
+                wait_event_freezable(
+                        ecryptfs_kthread_ctl.wait,
+                        (!list_empty(&ecryptfs_kthread_ctl.req_list)
+                         || kthread_should_stop()));
+                mutex_lock(&ecryptfs_kthread_ctl.mux);
+                if (ecryptfs_kthread_ctl.flags & ECRYPTFS_KTHREAD_ZOMBIE) {
+                        mutex_unlock(&ecryptfs_kthread_ctl.mux);
+                        goto out;
+                }
+                while (!list_empty(&ecryptfs_kthread_ctl.req_list)) {
+                        req = list_first_entry(&ecryptfs_kthread_ctl.req_list,
+                                               struct ecryptfs_open_req,
+                                               kthread_ctl_list);
+                        mutex_lock(&req->mux);
+                        list_del(&req->kthread_ctl_list);
+                        if (!(req->flags & ECRYPTFS_REQ_ZOMBIE)) {
+                                dget(req->lower_dentry);
+                                mntget(req->lower_mnt);
+                                (*req->lower_file) = dentry_open(
+                                        req->lower_dentry, req->lower_mnt,
+                                        (O_RDWR | O_LARGEFILE));
+                                req->flags |= ECRYPTFS_REQ_PROCESSED;
+                        }
+                        wake_up(&req->wait);
+                        mutex_unlock(&req->mux);
+                }
+                mutex_unlock(&ecryptfs_kthread_ctl.mux);
+        }
+out:
+        return 0;
+}
+
+int ecryptfs_init_kthread(void)
+{
+        int rc = 0;
+
+        mutex_init(&ecryptfs_kthread_ctl.mux);
+        init_waitqueue_head(&ecryptfs_kthread_ctl.wait);
+        INIT_LIST_HEAD(&ecryptfs_kthread_ctl.req_list);
+        ecryptfs_kthread = kthread_run(&ecryptfs_threadfn, NULL,
+                                       "ecryptfs-kthread");
+        if (IS_ERR(ecryptfs_kthread)) {
+                rc = PTR_ERR(ecryptfs_kthread);
+                printk(KERN_ERR "%s: Failed to create kernel thread; rc = [%d]"
+                       "\n", __func__, rc);
+        }
+        return rc;
+}
+
+void ecryptfs_destroy_kthread(void)
+{
+        struct ecryptfs_open_req *req;
+
+        mutex_lock(&ecryptfs_kthread_ctl.mux);
+        ecryptfs_kthread_ctl.flags |= ECRYPTFS_KTHREAD_ZOMBIE;
+        list_for_each_entry(req, &ecryptfs_kthread_ctl.req_list,
+                            kthread_ctl_list) {
+                mutex_lock(&req->mux);
+                req->flags |= ECRYPTFS_REQ_ZOMBIE;
+                wake_up(&req->wait);
+                mutex_unlock(&req->mux);
+        }
+        mutex_unlock(&ecryptfs_kthread_ctl.mux);
+        kthread_stop(ecryptfs_kthread);
+        wake_up(&ecryptfs_kthread_ctl.wait);
+}
+
+/**
+ * ecryptfs_privileged_open
+ * @lower_file: Result of dentry_open by root on lower dentry
+ * @lower_dentry: Lower dentry for file to open
+ * @lower_mnt: Lower vfsmount for file to open
+ *
+ * This function gets a r/w file opened againt the lower dentry.
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+int ecryptfs_privileged_open(struct file **lower_file,
+                             struct dentry *lower_dentry,
+                             struct vfsmount *lower_mnt)
+{
+        struct ecryptfs_open_req *req;
+        int rc = 0;
+
+        /* Corresponding dput() and mntput() are done when the
+         * persistent file is fput() when the eCryptfs inode is
+         * destroyed. */
+        dget(lower_dentry);
+        mntget(lower_mnt);
+        (*lower_file) = dentry_open(lower_dentry, lower_mnt,
+                                    (O_RDWR | O_LARGEFILE));
+        if (!IS_ERR(*lower_file))
+                goto out;
+        req = kmem_cache_alloc(ecryptfs_open_req_cache, GFP_KERNEL);
+        if (!req) {
+                rc = -ENOMEM;
+                goto out;
+        }
+        mutex_init(&req->mux);
+        req->lower_file = lower_file;
+        req->lower_dentry = lower_dentry;
+        req->lower_mnt = lower_mnt;
+        init_waitqueue_head(&req->wait);
+        req->flags = 0;
+        mutex_lock(&ecryptfs_kthread_ctl.mux);
+        if (ecryptfs_kthread_ctl.flags & ECRYPTFS_KTHREAD_ZOMBIE) {
+                rc = -EIO;
+                mutex_unlock(&ecryptfs_kthread_ctl.mux);
+                printk(KERN_ERR "%s: We are in the middle of shutting down; "
+                       "aborting privileged request to open lower file\n",
+                        __func__);
+                goto out_free;
+        }
+        list_add_tail(&req->kthread_ctl_list, &ecryptfs_kthread_ctl.req_list);
+        mutex_unlock(&ecryptfs_kthread_ctl.mux);
+        wake_up(&ecryptfs_kthread_ctl.wait);
+        wait_event(req->wait, (req->flags != 0));
+        mutex_lock(&req->mux);
+        BUG_ON(req->flags == 0);
+        if (req->flags & ECRYPTFS_REQ_DROPPED
+            || req->flags & ECRYPTFS_REQ_ZOMBIE) {
+                rc = -EIO;
+                printk(KERN_WARNING "%s: Privileged open request dropped\n",
+                       __func__);
+                goto out_unlock;
+        }
+        if (IS_ERR(*req->lower_file)) {
+                rc = PTR_ERR(*req->lower_file);
+                dget(lower_dentry);
+                mntget(lower_mnt);
+                (*lower_file) = dentry_open(lower_dentry, lower_mnt,
+                                            (O_RDONLY | O_LARGEFILE));
+                if (IS_ERR(*lower_file)) {
+                        rc = PTR_ERR(*req->lower_file);
+                        (*lower_file) = NULL;
+                        printk(KERN_WARNING "%s: Error attempting privileged "
+                               "open of lower file with either RW or RO "
+                               "perms; rc = [%d]. Giving up.\n",
+                               __func__, rc);
+                }
+        }
+out_unlock:
+        mutex_unlock(&req->mux);
+out_free:
+        kmem_cache_free(ecryptfs_open_req_cache, req);
+out:
+        return rc;
+}
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index d603631601eb..448dfd597b5f 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -117,7 +117,7 @@ void __ecryptfs_printk(const char *fmt, ...)
  *
  * Returns zero on success; non-zero otherwise
  */
-static int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry)
+int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry)
 {
         struct ecryptfs_inode_info *inode_info =
                 ecryptfs_inode_to_private(ecryptfs_dentry->d_inode);
@@ -130,26 +130,12 @@ static int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry)
                         ecryptfs_dentry_to_lower_mnt(ecryptfs_dentry);
 
                 lower_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry);
-                /* Corresponding dput() and mntput() are done when the
-                 * persistent file is fput() when the eCryptfs inode
-                 * is destroyed. */
-                dget(lower_dentry);
-                mntget(lower_mnt);
-                inode_info->lower_file = dentry_open(lower_dentry,
-                                                     lower_mnt,
-                                                     (O_RDWR | O_LARGEFILE));
-                if (IS_ERR(inode_info->lower_file)) {
-                        dget(lower_dentry);
-                        mntget(lower_mnt);
-                        inode_info->lower_file = dentry_open(lower_dentry,
-                                                             lower_mnt,
-                                                             (O_RDONLY
-                                                              | O_LARGEFILE));
-                }
-                if (IS_ERR(inode_info->lower_file)) {
+                rc = ecryptfs_privileged_open(&inode_info->lower_file,
+                                                     lower_dentry, lower_mnt);
+                if (rc || IS_ERR(inode_info->lower_file)) {
                         printk(KERN_ERR "Error opening lower persistent file "
-                               "for lower_dentry [0x%p] and lower_mnt [0x%p]\n",
-                               lower_dentry, lower_mnt);
+                               "for lower_dentry [0x%p] and lower_mnt [0x%p]; "
+                               "rc = [%d]\n", lower_dentry, lower_mnt, rc);
                         rc = PTR_ERR(inode_info->lower_file);
                         inode_info->lower_file = NULL;
                 }
@@ -163,14 +149,14 @@ static int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry)
  * @lower_dentry: Existing dentry in the lower filesystem
  * @dentry: ecryptfs' dentry
  * @sb: ecryptfs's super_block
- * @flag: If set to true, then d_add is called, else d_instantiate is called
+ * @flags: flags to govern behavior of interpose procedure
  *
  * Interposes upper and lower dentries.
  *
  * Returns zero on success; non-zero otherwise
  */
 int ecryptfs_interpose(struct dentry *lower_dentry, struct dentry *dentry,
-                       struct super_block *sb, int flag)
+                       struct super_block *sb, u32 flags)
 {
         struct inode *lower_inode;
         struct inode *inode;
@@ -207,7 +193,7 @@ int ecryptfs_interpose(struct dentry *lower_dentry, struct dentry *dentry,
                 init_special_inode(inode, lower_inode->i_mode,
                                    lower_inode->i_rdev);
         dentry->d_op = &ecryptfs_dops;
-        if (flag)
+        if (flags & ECRYPTFS_INTERPOSE_FLAG_D_ADD)
                 d_add(dentry, inode);
         else
                 d_instantiate(dentry, inode);
@@ -215,13 +201,6 @@ int ecryptfs_interpose(struct dentry *lower_dentry, struct dentry *dentry,
         /* This size will be overwritten for real files w/ headers and
          * other metadata */
         fsstack_copy_inode_size(inode, lower_inode);
-        rc = ecryptfs_init_persistent_file(dentry);
-        if (rc) {
-                printk(KERN_ERR "%s: Error attempting to initialize the "
-                       "persistent file for the dentry with name [%s]; "
-                       "rc = [%d]\n", __func__, dentry->d_name.name, rc);
-                goto out;
-        }
 out:
         return rc;
 }
@@ -262,10 +241,11 @@ static int ecryptfs_init_global_auth_toks(
                                "session keyring for sig specified in mount "
                                "option: [%s]\n", global_auth_tok->sig);
                         global_auth_tok->flags |= ECRYPTFS_AUTH_TOK_INVALID;
-                        rc = 0;
+                        goto out;
                 } else
                         global_auth_tok->flags &= ~ECRYPTFS_AUTH_TOK_INVALID;
         }
+out:
         return rc;
 }
 
@@ -314,7 +294,6 @@ static int ecryptfs_parse_options(struct super_block *sb, char *options)
         char *cipher_name_dst;
         char *cipher_name_src;
         char *cipher_key_bytes_src;
-        int cipher_name_len;
 
         if (!options) {
                 rc = -EINVAL;
@@ -395,17 +374,12 @@ static int ecryptfs_parse_options(struct super_block *sb, char *options)
                 goto out;
         }
         if (!cipher_name_set) {
-                cipher_name_len = strlen(ECRYPTFS_DEFAULT_CIPHER);
-                if (unlikely(cipher_name_len
-                             >= ECRYPTFS_MAX_CIPHER_NAME_SIZE)) {
-                        rc = -EINVAL;
-                        BUG();
-                        goto out;
-                }
-                memcpy(mount_crypt_stat->global_default_cipher_name,
-                       ECRYPTFS_DEFAULT_CIPHER, cipher_name_len);
-                mount_crypt_stat->global_default_cipher_name[cipher_name_len]
-                    = '\0';
+                int cipher_name_len = strlen(ECRYPTFS_DEFAULT_CIPHER);
+
+                BUG_ON(cipher_name_len >= ECRYPTFS_MAX_CIPHER_NAME_SIZE);
+
+                strcpy(mount_crypt_stat->global_default_cipher_name,
+                       ECRYPTFS_DEFAULT_CIPHER);
         }
         if (!cipher_key_bytes_set) {
                 mount_crypt_stat->global_default_cipher_key_size = 0;
@@ -430,7 +404,6 @@ static int ecryptfs_parse_options(struct super_block *sb, char *options)
                 printk(KERN_WARNING "One or more global auth toks could not "
                        "properly register; rc = [%d]\n", rc);
         }
-        rc = 0;
 out:
         return rc;
 }
@@ -605,7 +578,7 @@ static struct file_system_type ecryptfs_fs_type = {
  * Initializes the ecryptfs_inode_info_cache when it is created
  */
 static void
-inode_info_init_once(struct kmem_cache *cachep, void *vptr)
+inode_info_init_once(void *vptr)
 {
         struct ecryptfs_inode_info *ei = (struct ecryptfs_inode_info *)vptr;
 
@@ -616,7 +589,7 @@ static struct ecryptfs_cache_info {
         struct kmem_cache **cache;
         const char *name;
         size_t size;
-        void (*ctor)(struct kmem_cache *cache, void *obj);
+        void (*ctor)(void *obj);
 } ecryptfs_cache_infos[] = {
         {
                 .cache = &ecryptfs_auth_tok_list_item_cache,
@@ -679,6 +652,11 @@ static struct ecryptfs_cache_info {
                 .name = "ecryptfs_key_tfm_cache",
                 .size = sizeof(struct ecryptfs_key_tfm),
         },
+        {
+                .cache = &ecryptfs_open_req_cache,
+                .name = "ecryptfs_open_req_cache",
+                .size = sizeof(struct ecryptfs_open_req),
+        },
 };
 
 static void ecryptfs_free_kmem_caches(void)
@@ -795,11 +773,17 @@ static int __init ecryptfs_init(void)
                 printk(KERN_ERR "sysfs registration failed\n");
                 goto out_unregister_filesystem;
         }
+        rc = ecryptfs_init_kthread();
+        if (rc) {
+                printk(KERN_ERR "%s: kthread initialization failed; "
+                       "rc = [%d]\n", __func__, rc);
+                goto out_do_sysfs_unregistration;
+        }
         rc = ecryptfs_init_messaging(ecryptfs_transport);
         if (rc) {
-                ecryptfs_printk(KERN_ERR, "Failure occured while attempting to "
+                printk(KERN_ERR "Failure occured while attempting to "
                                 "initialize the eCryptfs netlink socket\n");
-                goto out_do_sysfs_unregistration;
+                goto out_destroy_kthread;
         }
         rc = ecryptfs_init_crypto();
         if (rc) {
@@ -814,6 +798,8 @@ static int __init ecryptfs_init(void)
         goto out;
 out_release_messaging:
         ecryptfs_release_messaging(ecryptfs_transport);
+out_destroy_kthread:
+        ecryptfs_destroy_kthread();
 out_do_sysfs_unregistration:
         do_sysfs_unregistration();
 out_unregister_filesystem:
@@ -833,6 +819,7 @@ static void __exit ecryptfs_exit(void)
                 printk(KERN_ERR "Failure whilst attempting to destroy crypto; "
                        "rc = [%d]\n", rc);
         ecryptfs_release_messaging(ecryptfs_transport);
+        ecryptfs_destroy_kthread();
         do_sysfs_unregistration();
         unregister_filesystem(&ecryptfs_fs_type);
         ecryptfs_free_kmem_caches();
diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c
index 09a4522f65e6..b484792a0996 100644
--- a/fs/ecryptfs/miscdev.c
+++ b/fs/ecryptfs/miscdev.c
@@ -358,46 +358,6 @@ out_unlock_daemon:
 }
 
 /**
- * ecryptfs_miscdev_helo
- * @euid: effective user id of miscdevess sending helo packet
- * @user_ns: The namespace in which @euid applies
- * @pid: miscdevess id of miscdevess sending helo packet
- *
- * Returns zero on success; non-zero otherwise
- */
-static int ecryptfs_miscdev_helo(uid_t euid, struct user_namespace *user_ns,
-                                 struct pid *pid)
-{
-        int rc;
-
-        rc = ecryptfs_process_helo(ECRYPTFS_TRANSPORT_MISCDEV, euid, user_ns,
-                                   pid);
-        if (rc)
-                printk(KERN_WARNING "Error processing HELO; rc = [%d]\n", rc);
-        return rc;
-}
-
-/**
- * ecryptfs_miscdev_quit
- * @euid: effective user id of miscdevess sending quit packet
- * @user_ns: The namespace in which @euid applies
- * @pid: miscdevess id of miscdevess sending quit packet
- *
- * Returns zero on success; non-zero otherwise
- */
-static int ecryptfs_miscdev_quit(uid_t euid, struct user_namespace *user_ns,
-                                 struct pid *pid)
-{
-        int rc;
-
-        rc = ecryptfs_process_quit(euid, user_ns, pid);
-        if (rc)
-                printk(KERN_WARNING
-                       "Error processing QUIT message; rc = [%d]\n", rc);
-        return rc;
-}
-
-/**
  * ecryptfs_miscdev_response - miscdevess response to message previously sent to daemon
  * @data: Bytes comprising struct ecryptfs_message
  * @data_size: sizeof(struct ecryptfs_message) + data len
@@ -512,26 +472,7 @@ ecryptfs_miscdev_write(struct file *file, const char __user *buf,
                                __func__, rc);
                 break;
         case ECRYPTFS_MSG_HELO:
-                rc = ecryptfs_miscdev_helo(current->euid,
-                                           current->nsproxy->user_ns,
-                                           task_pid(current));
-                if (rc) {
-                        printk(KERN_ERR "%s: Error attempting to process "
-                               "helo from pid [0x%p]; rc = [%d]\n", __func__,
-                               task_pid(current), rc);
-                        goto out_free;
-                }
-                break;
         case ECRYPTFS_MSG_QUIT:
-                rc = ecryptfs_miscdev_quit(current->euid,
-                                           current->nsproxy->user_ns,
-                                           task_pid(current));
-                if (rc) {
-                        printk(KERN_ERR "%s: Error attempting to process "
-                               "quit from pid [0x%p]; rc = [%d]\n", __func__,
-                               task_pid(current), rc);
-                        goto out_free;
-                }
                 break;
         default:
                 ecryptfs_printk(KERN_WARNING, "Dropping miscdev "
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index 2b6fe1e6e8ba..245c2dc02d5c 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -32,6 +32,7 @@
 #include <linux/file.h>
 #include <linux/crypto.h>
 #include <linux/scatterlist.h>
+#include <asm/unaligned.h>
 #include "ecryptfs_kernel.h"
 
 /**
@@ -372,7 +373,6 @@ out:
  */
 static int ecryptfs_write_inode_size_to_header(struct inode *ecryptfs_inode)
 {
-        u64 file_size;
         char *file_size_virt;
         int rc;
 
@@ -381,9 +381,7 @@ static int ecryptfs_write_inode_size_to_header(struct inode *ecryptfs_inode)
                 rc = -ENOMEM;
                 goto out;
         }
-        file_size = (u64)i_size_read(ecryptfs_inode);
-        file_size = cpu_to_be64(file_size);
-        memcpy(file_size_virt, &file_size, sizeof(u64));
+        put_unaligned_be64(i_size_read(ecryptfs_inode), file_size_virt);
         rc = ecryptfs_write_lower(ecryptfs_inode, file_size_virt, 0,
                                   sizeof(u64));
         kfree(file_size_virt);
@@ -403,7 +401,6 @@ static int ecryptfs_write_inode_size_to_xattr(struct inode *ecryptfs_inode)
         struct dentry *lower_dentry =
                 ecryptfs_inode_to_private(ecryptfs_inode)->lower_file->f_dentry;
         struct inode *lower_inode = lower_dentry->d_inode;
-        u64 file_size;
         int rc;
 
         if (!lower_inode->i_op->getxattr || !lower_inode->i_op->setxattr) {
@@ -424,9 +421,7 @@ static int ecryptfs_write_inode_size_to_xattr(struct inode *ecryptfs_inode)
                                            xattr_virt, PAGE_CACHE_SIZE);
         if (size < 0)
                 size = 8;
-        file_size = (u64)i_size_read(ecryptfs_inode);
-        file_size = cpu_to_be64(file_size);
-        memcpy(xattr_virt, &file_size, sizeof(u64));
+        put_unaligned_be64(i_size_read(ecryptfs_inode), xattr_virt);
         rc = lower_inode->i_op->setxattr(lower_dentry, ECRYPTFS_XATTR_NAME,
                                          xattr_virt, size, 0);
         mutex_unlock(&lower_inode->i_mutex);
diff --git a/fs/efs/super.c b/fs/efs/super.c
index d733531b55e2..567b134fa1f1 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -70,7 +70,7 @@ static void efs_destroy_inode(struct inode *inode)
         kmem_cache_free(efs_inode_cachep, INODE_INFO(inode));
 }
 
-static void init_once(struct kmem_cache *cachep, void *foo)
+static void init_once(void *foo)
 {
         struct efs_inode_info *ei = (struct efs_inode_info *) foo;
 
diff --git a/fs/eventfd.c b/fs/eventfd.c
index 343942deeec1..08bf558d0408 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -198,11 +198,18 @@ struct file *eventfd_fget(int fd)
         return file;
 }
 
-asmlinkage long sys_eventfd(unsigned int count)
+asmlinkage long sys_eventfd2(unsigned int count, int flags)
 {
         int fd;
         struct eventfd_ctx *ctx;
 
+        /* Check the EFD_* constants for consistency.  */
+        BUILD_BUG_ON(EFD_CLOEXEC != O_CLOEXEC);
+        BUILD_BUG_ON(EFD_NONBLOCK != O_NONBLOCK);
+
+        if (flags & ~(EFD_CLOEXEC | EFD_NONBLOCK))
+                return -EINVAL;
+
         ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
         if (!ctx)
                 return -ENOMEM;
@@ -214,9 +221,15 @@ asmlinkage long sys_eventfd(unsigned int count)
          * When we call this, the initialization must be complete, since
          * anon_inode_getfd() will install the fd.
          */
-        fd = anon_inode_getfd("[eventfd]", &eventfd_fops, ctx);
+        fd = anon_inode_getfd("[eventfd]", &eventfd_fops, ctx,
+                              flags & (O_CLOEXEC | O_NONBLOCK));
         if (fd < 0)
                 kfree(ctx);
         return fd;
 }
 
+asmlinkage long sys_eventfd(unsigned int count)
+{
+        return sys_eventfd2(count, 0);
+}
+
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 990c01d2d66b..7cc0eb756b55 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1041,25 +1041,27 @@ retry:
 }
 
 /*
- * It opens an eventpoll file descriptor. The "size" parameter is there
- * for historical reasons, when epoll was using an hash instead of an
- * RB tree. With the current implementation, the "size" parameter is ignored
- * (besides sanity checks).
+ * Open an eventpoll file descriptor.
  */
-asmlinkage long sys_epoll_create(int size)
+asmlinkage long sys_epoll_create1(int flags)
 {
         int error, fd = -1;
         struct eventpoll *ep;
 
+        /* Check the EPOLL_* constant for consistency.  */
+        BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC);
+
+        if (flags & ~EPOLL_CLOEXEC)
+                return -EINVAL;
+
         DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d)\n",
-                     current, size));
+                     current, flags));
 
         /*
-         * Sanity check on the size parameter, and create the internal data
-         * structure ( "struct eventpoll" ).
+         * Create the internal data structure ( "struct eventpoll" ).
          */
-        error = -EINVAL;
-        if (size <= 0 || (error = ep_alloc(&ep)) < 0) {
+        error = ep_alloc(&ep);
+        if (error < 0) {
                 fd = error;
                 goto error_return;
         }
@@ -1068,17 +1070,26 @@ asmlinkage long sys_epoll_create(int size)
          * Creates all the items needed to setup an eventpoll file. That is,
          * a file structure and a free file descriptor.
          */
-        fd = anon_inode_getfd("[eventpoll]", &eventpoll_fops, ep);
+        fd = anon_inode_getfd("[eventpoll]", &eventpoll_fops, ep,
+                              flags & O_CLOEXEC);
         if (fd < 0)
                 ep_free(ep);
 
 error_return:
         DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n",
-                     current, size, fd));
+                     current, flags, fd));
 
         return fd;
 }
 
+asmlinkage long sys_epoll_create(int size)
+{
+        if (size < 0)
+                return -EINVAL;
+
+        return sys_epoll_create1(0);
+}
+
 /*
  * The following function implements the controller interface for
  * the eventpoll file that enables the insertion/removal/change of
diff --git a/fs/exec.c b/fs/exec.c
index fd9234379e8d..32993beecbe9 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -25,10 +25,11 @@
 #include <linux/slab.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
-#include <linux/mman.h>
+#include <linux/mm.h>
 #include <linux/stat.h>
 #include <linux/fcntl.h>
 #include <linux/smp_lock.h>
+#include <linux/swap.h>
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/pagemap.h>
@@ -37,20 +38,18 @@
 #include <linux/key.h>
 #include <linux/personality.h>
 #include <linux/binfmts.h>
-#include <linux/swap.h>
 #include <linux/utsname.h>
 #include <linux/pid_namespace.h>
 #include <linux/module.h>
 #include <linux/namei.h>
 #include <linux/proc_fs.h>
-#include <linux/ptrace.h>
 #include <linux/mount.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
-#include <linux/rmap.h>
 #include <linux/tsacct_kern.h>
 #include <linux/cn_proc.h>
 #include <linux/audit.h>
+#include <linux/tracehook.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
@@ -108,11 +107,17 @@ static inline void put_binfmt(struct linux_binfmt * fmt)
  */
 asmlinkage long sys_uselib(const char __user * library)
 {
-        struct file * file;
+        struct file *file;
         struct nameidata nd;
-        int error;
-
-        error = __user_path_lookup_open(library, LOOKUP_FOLLOW, &nd, FMODE_READ|FMODE_EXEC);
+        char *tmp = getname(library);
+        int error = PTR_ERR(tmp);
+
+        if (!IS_ERR(tmp)) {
+                error = path_lookup_open(AT_FDCWD, tmp,
+                                         LOOKUP_FOLLOW, &nd,
+                                         FMODE_READ|FMODE_EXEC);
+                putname(tmp);
+        }
         if (error)
                 goto out;
 
@@ -120,7 +125,11 @@ asmlinkage long sys_uselib(const char __user * library)
         if (!S_ISREG(nd.path.dentry->d_inode->i_mode))
                 goto exit;
 
-        error = vfs_permission(&nd, MAY_READ | MAY_EXEC);
+        error = -EACCES;
+        if (nd.path.mnt->mnt_flags & MNT_NOEXEC)
+                goto exit;
+
+        error = vfs_permission(&nd, MAY_READ | MAY_EXEC | MAY_OPEN);
         if (error)
                 goto exit;
 
@@ -541,7 +550,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
                 /*
                  * when the old and new regions overlap clear from new_end.
                  */
-                free_pgd_range(&tlb, new_end, old_end, new_end,
+                free_pgd_range(tlb, new_end, old_end, new_end,
                         vma->vm_next ? vma->vm_next->vm_start : 0);
         } else {
                 /*
@@ -550,7 +559,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
                  * have constraints on va-space that make this illegal (IA64) -
                  * for the others its just a little faster.
                  */
-                free_pgd_range(&tlb, old_start, old_end, new_end,
+                free_pgd_range(tlb, old_start, old_end, new_end,
                         vma->vm_next ? vma->vm_next->vm_start : 0);
         }
         tlb_finish_mmu(tlb, new_end, old_end);
@@ -658,38 +667,43 @@ EXPORT_SYMBOL(setup_arg_pages);
 struct file *open_exec(const char *name)
 {
         struct nameidata nd;
-        int err;
         struct file *file;
+        int err;
 
-        err = path_lookup_open(AT_FDCWD, name, LOOKUP_FOLLOW, &nd, FMODE_READ|FMODE_EXEC);
-        file = ERR_PTR(err);
-
-        if (!err) {
-                struct inode *inode = nd.path.dentry->d_inode;
-                file = ERR_PTR(-EACCES);
-                if (S_ISREG(inode->i_mode)) {
-                        int err = vfs_permission(&nd, MAY_EXEC);
-                        file = ERR_PTR(err);
-                        if (!err) {
-                                file = nameidata_to_filp(&nd,
-                                                        O_RDONLY|O_LARGEFILE);
-                                if (!IS_ERR(file)) {
-                                        err = deny_write_access(file);
-                                        if (err) {
-                                                fput(file);
-                                                file = ERR_PTR(err);
-                                        }
-                                }
-out:
-                                return file;
-                        }
-                }
-                release_open_intent(&nd);
-                path_put(&nd.path);
+        err = path_lookup_open(AT_FDCWD, name, LOOKUP_FOLLOW, &nd,
+                                FMODE_READ|FMODE_EXEC);
+        if (err)
+                goto out;
+
+        err = -EACCES;
+        if (!S_ISREG(nd.path.dentry->d_inode->i_mode))
+                goto out_path_put;
+
+        if (nd.path.mnt->mnt_flags & MNT_NOEXEC)
+                goto out_path_put;
+
+        err = vfs_permission(&nd, MAY_EXEC | MAY_OPEN);
+        if (err)
+                goto out_path_put;
+
+        file = nameidata_to_filp(&nd, O_RDONLY|O_LARGEFILE);
+        if (IS_ERR(file))
+                return file;
+
+        err = deny_write_access(file);
+        if (err) {
+                fput(file);
+                goto out;
         }
-        goto out;
-}
 
+        return file;
+
+ out_path_put:
+        release_open_intent(&nd);
+        path_put(&nd.path);
+ out:
+        return ERR_PTR(err);
+}
 EXPORT_SYMBOL(open_exec);
 
 int kernel_read(struct file *file, unsigned long offset,
@@ -724,12 +738,10 @@ static int exec_mmap(struct mm_struct *mm)
                  * Make sure that if there is a core dump in progress
                  * for the old mm, we get out and die instead of going
                  * through with the exec.  We must hold mmap_sem around
-                 * checking core_waiters and changing tsk->mm.  The
-                 * core-inducing thread will increment core_waiters for
-                 * each thread whose ->mm == old_mm.
+                 * checking core_state and changing tsk->mm.
                  */
                 down_read(&old_mm->mmap_sem);
-                if (unlikely(old_mm->core_waiters)) {
+                if (unlikely(old_mm->core_state)) {
                         up_read(&old_mm->mmap_sem);
                         return -EINTR;
                 }
@@ -1075,13 +1087,8 @@ EXPORT_SYMBOL(prepare_binprm);
 
 static int unsafe_exec(struct task_struct *p)
 {
-        int unsafe = 0;
-        if (p->ptrace & PT_PTRACED) {
-                if (p->ptrace & PT_PTRACE_CAP)
-                        unsafe |= LSM_UNSAFE_PTRACE_CAP;
-                else
-                        unsafe |= LSM_UNSAFE_PTRACE;
-        }
+        int unsafe = tracehook_unsafe_exec(p);
+
         if (atomic_read(&p->fs->count) > 1 ||
             atomic_read(&p->files->count) > 1 ||
             atomic_read(&p->sighand->count) > 1)
@@ -1218,6 +1225,7 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
                         read_unlock(&binfmt_lock);
                         retval = fn(bprm, regs);
                         if (retval >= 0) {
+                                tracehook_report_exec(fmt, bprm, regs);
                                 put_binfmt(fmt);
                                 allow_write_access(bprm->file);
                                 if (bprm->file)
@@ -1328,6 +1336,7 @@ int do_execve(char * filename,
         if (retval < 0)
                 goto out;
 
+        current->flags &= ~PF_KTHREAD;
         retval = search_binary_handler(bprm,regs);
         if (retval >= 0) {
                 /* execve success */
@@ -1382,17 +1391,14 @@ EXPORT_SYMBOL(set_binfmt);
  * name into corename, which must have space for at least
  * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator.
  */
-static int format_corename(char *corename, const char *pattern, long signr)
+static int format_corename(char *corename, int nr_threads, long signr)
 {
-        const char *pat_ptr = pattern;
+        const char *pat_ptr = core_pattern;
+        int ispipe = (*pat_ptr == '|');
         char *out_ptr = corename;
         char *const out_end = corename + CORENAME_MAX_SIZE;
         int rc;
         int pid_in_pattern = 0;
-        int ispipe = 0;
-
-        if (*pattern == '|')
-                ispipe = 1;
 
         /* Repeat as long as we have more pattern to process and more output
            space */
@@ -1493,7 +1499,7 @@ static int format_corename(char *corename, const char *pattern, long signr)
          * and core_uses_pid is set, then .%pid will be appended to
          * the filename. Do not do this for piped commands. */
         if (!ispipe && !pid_in_pattern
-            && (core_uses_pid || atomic_read(&current->mm->mm_users) != 1)) {
+            && (core_uses_pid || nr_threads)) {
                 rc = snprintf(out_ptr, out_end - out_ptr,
                               ".%d", task_tgid_vnr(current));
                 if (rc > out_end - out_ptr)
@@ -1505,9 +1511,10 @@ out:
         return ispipe;
 }
 
-static void zap_process(struct task_struct *start)
+static int zap_process(struct task_struct *start)
 {
         struct task_struct *t;
+        int nr = 0;
 
         start->signal->flags = SIGNAL_GROUP_EXIT;
         start->signal->group_stop_count = 0;
@@ -1515,72 +1522,99 @@ static void zap_process(struct task_struct *start)
         t = start;
         do {
                 if (t != current && t->mm) {
-                        t->mm->core_waiters++;
                         sigaddset(&t->pending.signal, SIGKILL);
                         signal_wake_up(t, 1);
+                        nr++;
                 }
-        } while ((t = next_thread(t)) != start);
+        } while_each_thread(start, t);
+
+        return nr;
 }
 
 static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
-                                int exit_code)
+                                struct core_state *core_state, int exit_code)
 {
         struct task_struct *g, *p;
         unsigned long flags;
-        int err = -EAGAIN;
+        int nr = -EAGAIN;
 
         spin_lock_irq(&tsk->sighand->siglock);
         if (!signal_group_exit(tsk->signal)) {
+                mm->core_state = core_state;
                 tsk->signal->group_exit_code = exit_code;
-                zap_process(tsk);
-                err = 0;
+                nr = zap_process(tsk);
         }
         spin_unlock_irq(&tsk->sighand->siglock);
-        if (err)
-                return err;
+        if (unlikely(nr < 0))
+                return nr;
 
-        if (atomic_read(&mm->mm_users) == mm->core_waiters + 1)
+        if (atomic_read(&mm->mm_users) == nr + 1)
                 goto done;
-
+        /*
+         * We should find and kill all tasks which use this mm, and we should
+         * count them correctly into ->nr_threads. We don't take tasklist
+         * lock, but this is safe wrt:
+         *
+         * fork:
+         *      None of sub-threads can fork after zap_process(leader). All
+         *      processes which were created before this point should be
+         *      visible to zap_threads() because copy_process() adds the new
+         *      process to the tail of init_task.tasks list, and lock/unlock
+         *      of ->siglock provides a memory barrier.
+         *
+         * do_exit:
+         *      The caller holds mm->mmap_sem. This means that the task which
+         *      uses this mm can't pass exit_mm(), so it can't exit or clear
+         *      its ->mm.
+         *
+         * de_thread:
+         *      It does list_replace_rcu(&leader->tasks, &current->tasks),
+         *      we must see either old or new leader, this does not matter.
+         *      However, it can change p->sighand, so lock_task_sighand(p)
+         *      must be used. Since p->mm != NULL and we hold ->mmap_sem
+         *      it can't fail.
+         *
+         *      Note also that "g" can be the old leader with ->mm == NULL
+         *      and already unhashed and thus removed from ->thread_group.
+         *      This is OK, __unhash_process()->list_del_rcu() does not
+         *      clear the ->next pointer, we will find the new leader via
+         *      next_thread().
+         */
         rcu_read_lock();
         for_each_process(g) {
                 if (g == tsk->group_leader)
                         continue;
-
+                if (g->flags & PF_KTHREAD)
+                        continue;
                 p = g;
                 do {
                         if (p->mm) {
-                                if (p->mm == mm) {
-                                        /*
-                                         * p->sighand can't disappear, but
-                                         * may be changed by de_thread()
-                                         */
+                                if (unlikely(p->mm == mm)) {
                                         lock_task_sighand(p, &flags);
-                                        zap_process(p);
+                                        nr += zap_process(p);
                                         unlock_task_sighand(p, &flags);
                                 }
                                 break;
                         }
-                } while ((p = next_thread(p)) != g);
+                } while_each_thread(g, p);
         }
         rcu_read_unlock();
 done:
-        return mm->core_waiters;
+        atomic_set(&core_state->nr_threads, nr);
+        return nr;
 }
 
-static int coredump_wait(int exit_code)
+static int coredump_wait(int exit_code, struct core_state *core_state)
 {
         struct task_struct *tsk = current;
         struct mm_struct *mm = tsk->mm;
-        struct completion startup_done;
         struct completion *vfork_done;
         int core_waiters;
 
-        init_completion(&mm->core_done);
-        init_completion(&startup_done);
-        mm->core_startup_done = &startup_done;
-
-        core_waiters = zap_threads(tsk, mm, exit_code);
+        init_completion(&core_state->startup);
+        core_state->dumper.task = tsk;
+        core_state->dumper.next = NULL;
+        core_waiters = zap_threads(tsk, mm, core_state, exit_code);
         up_write(&mm->mmap_sem);
 
         if (unlikely(core_waiters < 0))
@@ -1597,12 +1631,32 @@ static int coredump_wait(int exit_code)
         }
 
         if (core_waiters)
-                wait_for_completion(&startup_done);
+                wait_for_completion(&core_state->startup);
 fail:
-        BUG_ON(mm->core_waiters);
         return core_waiters;
 }
 
+static void coredump_finish(struct mm_struct *mm)
+{
+        struct core_thread *curr, *next;
+        struct task_struct *task;
+
+        next = mm->core_state->dumper.next;
+        while ((curr = next) != NULL) {
+                next = curr->next;
+                task = curr->task;
+                /*
+                 * see exit_mm(), curr->task must not see
+                 * ->task == NULL before we read ->next.
+                 */
+                smp_mb();
+                curr->task = NULL;
+                wake_up_process(task);
+        }
+
+        mm->core_state = NULL;
+}
+
 /*
  * set_dumpable converts traditional three-value dumpable to two flags and
  * stores them into mm->flags.  It modifies lower two bits of mm->flags, but
@@ -1654,6 +1708,7 @@ int get_dumpable(struct mm_struct *mm)
 
 int do_coredump(long signr, int exit_code, struct pt_regs * regs)
 {
+        struct core_state core_state;
         char corename[CORENAME_MAX_SIZE + 1];
         struct mm_struct *mm = current->mm;
         struct linux_binfmt * binfmt;
@@ -1677,7 +1732,7 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs)
         /*
          * If another thread got here first, or we are not dumpable, bail out.
          */
-        if (mm->core_waiters || !get_dumpable(mm)) {
+        if (mm->core_state || !get_dumpable(mm)) {
                 up_write(&mm->mmap_sem);
                 goto fail;
         }
@@ -1692,7 +1747,7 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs)
                 current->fsuid = 0;     /* Dump root private */
         }
 
-        retval = coredump_wait(exit_code);
+        retval = coredump_wait(exit_code, &core_state);
         if (retval < 0)
                 goto fail;
 
@@ -1707,7 +1762,7 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs)
          * uses lock_kernel()
          */
         lock_kernel();
-        ispipe = format_corename(corename, core_pattern, signr);
+        ispipe = format_corename(corename, retval, signr);
         unlock_kernel();
         /*
          * Don't bother to check the RLIMIT_CORE value if core_pattern points
@@ -1786,7 +1841,7 @@ fail_unlock:
                 argv_free(helper_argv);
 
         current->fsuid = fsuid;
-        complete_all(&mm->core_done);
+        coredump_finish(mm);
 fail:
         return retval;
 }
diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c
index e58669e1b87c..ae8c4f850b27 100644
--- a/fs/ext2/acl.c
+++ b/fs/ext2/acl.c
@@ -294,7 +294,7 @@ ext2_check_acl(struct inode *inode, int mask)
 }
 
 int
-ext2_permission(struct inode *inode, int mask, struct nameidata *nd)
+ext2_permission(struct inode *inode, int mask)
 {
         return generic_permission(inode, mask, ext2_check_acl);
 }
diff --git a/fs/ext2/acl.h b/fs/ext2/acl.h
index 0bde85bafe38..b42cf578554b 100644
--- a/fs/ext2/acl.h
+++ b/fs/ext2/acl.h
@@ -58,7 +58,7 @@ static inline int ext2_acl_count(size_t size)
 #define EXT2_ACL_NOT_CACHED ((void *)-1)
 
 /* acl.c */
-extern int ext2_permission (struct inode *, int, struct nameidata *);
+extern int ext2_permission (struct inode *, int);
 extern int ext2_acl_chmod (struct inode *);
 extern int ext2_init_acl (struct inode *, struct inode *);
 
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 384fc0d1dd74..991d6dfeb51f 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -791,6 +791,7 @@ const struct address_space_operations ext2_aops = {
         .direct_IO              = ext2_direct_IO,
         .writepages             = ext2_writepages,
         .migratepage            = buffer_migrate_page,
+        .is_partially_uptodate  = block_is_partially_uptodate,
 };
 
 const struct address_space_operations ext2_aops_xip = {
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index ef50cbc792db..fd88c7b43e66 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -31,6 +31,7 @@
 #include <linux/seq_file.h>
 #include <linux/mount.h>
 #include <linux/log2.h>
+#include <linux/quotaops.h>
 #include <asm/uaccess.h>
 #include "ext2.h"
 #include "xattr.h"
@@ -158,7 +159,7 @@ static void ext2_destroy_inode(struct inode *inode)
         kmem_cache_free(ext2_inode_cachep, EXT2_I(inode));
 }
 
-static void init_once(struct kmem_cache * cachep, void *foo)
+static void init_once(void *foo)
 {
         struct ext2_inode_info *ei = (struct ext2_inode_info *) foo;
 
diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c
index eaa23d2d5213..70c0dbdcdcb7 100644
--- a/fs/ext2/xattr_security.c
+++ b/fs/ext2/xattr_security.c
@@ -14,7 +14,7 @@ static size_t
 ext2_xattr_security_list(struct inode *inode, char *list, size_t list_size,
                          const char *name, size_t name_len)
 {
-        const int prefix_len = sizeof(XATTR_SECURITY_PREFIX)-1;
+        const int prefix_len = XATTR_SECURITY_PREFIX_LEN;
         const size_t total_len = prefix_len + name_len + 1;
 
         if (list && total_len <= list_size) {
diff --git a/fs/ext2/xattr_trusted.c b/fs/ext2/xattr_trusted.c
index 83ee149f353d..e8219f8eae9f 100644
--- a/fs/ext2/xattr_trusted.c
+++ b/fs/ext2/xattr_trusted.c
@@ -12,13 +12,11 @@
 #include <linux/ext2_fs.h>
 #include "xattr.h"
 
-#define XATTR_TRUSTED_PREFIX "trusted."
-
 static size_t
 ext2_xattr_trusted_list(struct inode *inode, char *list, size_t list_size,
                         const char *name, size_t name_len)
 {
-        const int prefix_len = sizeof(XATTR_TRUSTED_PREFIX)-1;
+        const int prefix_len = XATTR_TRUSTED_PREFIX_LEN;
         const size_t total_len = prefix_len + name_len + 1;
 
         if (!capable(CAP_SYS_ADMIN))
diff --git a/fs/ext2/xattr_user.c b/fs/ext2/xattr_user.c
index f383e7c3a7b5..92495d28c62f 100644
--- a/fs/ext2/xattr_user.c
+++ b/fs/ext2/xattr_user.c
@@ -11,13 +11,11 @@
 #include "ext2.h"
 #include "xattr.h"
 
-#define XATTR_USER_PREFIX "user."
-
 static size_t
 ext2_xattr_user_list(struct inode *inode, char *list, size_t list_size,
                      const char *name, size_t name_len)
 {
-        const size_t prefix_len = sizeof(XATTR_USER_PREFIX)-1;
+        const size_t prefix_len = XATTR_USER_PREFIX_LEN;
         const size_t total_len = prefix_len + name_len + 1;
 
         if (!test_opt(inode->i_sb, XATTR_USER))
diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c
index a754d1848173..b60bb241880c 100644
--- a/fs/ext3/acl.c
+++ b/fs/ext3/acl.c
@@ -299,7 +299,7 @@ ext3_check_acl(struct inode *inode, int mask)
 }
 
 int
-ext3_permission(struct inode *inode, int mask, struct nameidata *nd)
+ext3_permission(struct inode *inode, int mask)
 {
         return generic_permission(inode, mask, ext3_check_acl);
 }
diff --git a/fs/ext3/acl.h b/fs/ext3/acl.h
index 0d1e6279cbfd..42da16b8cac0 100644
--- a/fs/ext3/acl.h
+++ b/fs/ext3/acl.h
@@ -58,7 +58,7 @@ static inline int ext3_acl_count(size_t size)
 #define EXT3_ACL_NOT_CACHED ((void *)-1)
 
 /* acl.c */
-extern int ext3_permission (struct inode *, int, struct nameidata *);
+extern int ext3_permission (struct inode *, int);
 extern int ext3_acl_chmod (struct inode *);
 extern int ext3_init_acl (handle_t *, struct inode *, struct inode *);
 
diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c
index 8ca3bfd72427..2eea96ec78ed 100644
--- a/fs/ext3/dir.c
+++ b/fs/ext3/dir.c
@@ -272,7 +272,7 @@ static void free_rb_tree_fname(struct rb_root *root)
 
         while (n) {
                 /* Do the node's children first */
-                if ((n)->rb_left) {
+                if (n->rb_left) {
                         n = n->rb_left;
                         continue;
                 }
@@ -301,24 +301,18 @@ static void free_rb_tree_fname(struct rb_root *root)
                         parent->rb_right = NULL;
                 n = parent;
         }
-        root->rb_node = NULL;
 }
 
 
-static struct dir_private_info *create_dir_info(loff_t pos)
+static struct dir_private_info *ext3_htree_create_dir_info(loff_t pos)
 {
         struct dir_private_info *p;
 
-        p = kmalloc(sizeof(struct dir_private_info), GFP_KERNEL);
+        p = kzalloc(sizeof(struct dir_private_info), GFP_KERNEL);
         if (!p)
                 return NULL;
-        p->root.rb_node = NULL;
-        p->curr_node = NULL;
-        p->extra_fname = NULL;
-        p->last_pos = 0;
         p->curr_hash = pos2maj_hash(pos);
         p->curr_minor_hash = pos2min_hash(pos);
-        p->next_hash = 0;
         return p;
 }
 
@@ -433,7 +427,7 @@ static int ext3_dx_readdir(struct file * filp,
         int     ret;
 
         if (!info) {
-                info = create_dir_info(filp->f_pos);
+                info = ext3_htree_create_dir_info(filp->f_pos);
                 if (!info)
                         return -ENOMEM;
                 filp->private_data = info;
diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c
index 77126821b2e9..47b678d73e7a 100644
--- a/fs/ext3/ialloc.c
+++ b/fs/ext3/ialloc.c
@@ -669,6 +669,14 @@ struct inode *ext3_orphan_get(struct super_block *sb, unsigned long ino)
         if (IS_ERR(inode))
                 goto iget_failed;
 
+        /*
+         * If the orphans has i_nlinks > 0 then it should be able to be
+         * truncated, otherwise it won't be removed from the orphan list
+         * during processing and an infinite loop will result.
+         */
+        if (inode->i_nlink && !ext3_can_truncate(inode))
+                goto bad_orphan;
+
         if (NEXT_ORPHAN(inode) > max_ino)
                 goto bad_orphan;
         brelse(bitmap_bh);
@@ -690,6 +698,7 @@ bad_orphan:
                 printk(KERN_NOTICE "NEXT_ORPHAN(inode)=%u\n",
                        NEXT_ORPHAN(inode));
                 printk(KERN_NOTICE "max_ino=%lu\n", max_ino);
+                printk(KERN_NOTICE "i_nlink=%u\n", inode->i_nlink);
                 /* Avoid freeing blocks if we got a bad deleted inode */
                 if (inode->i_nlink == 0)
                         inode->i_blocks = 0;
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 6ae4ecf3ce40..507d8689b111 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -1767,44 +1767,47 @@ static int ext3_journalled_set_page_dirty(struct page *page)
 }
 
 static const struct address_space_operations ext3_ordered_aops = {
-        .readpage       = ext3_readpage,
-        .readpages      = ext3_readpages,
-        .writepage      = ext3_ordered_writepage,
-        .sync_page      = block_sync_page,
-        .write_begin    = ext3_write_begin,
-        .write_end      = ext3_ordered_write_end,
-        .bmap           = ext3_bmap,
-        .invalidatepage = ext3_invalidatepage,
-        .releasepage    = ext3_releasepage,
-        .direct_IO      = ext3_direct_IO,
-        .migratepage    = buffer_migrate_page,
+        .readpage               = ext3_readpage,
+        .readpages              = ext3_readpages,
+        .writepage              = ext3_ordered_writepage,
+        .sync_page              = block_sync_page,
+        .write_begin            = ext3_write_begin,
+        .write_end              = ext3_ordered_write_end,
+        .bmap                   = ext3_bmap,
+        .invalidatepage         = ext3_invalidatepage,
+        .releasepage            = ext3_releasepage,
+        .direct_IO              = ext3_direct_IO,
+        .migratepage            = buffer_migrate_page,
+        .is_partially_uptodate  = block_is_partially_uptodate,
 };
 
 static const struct address_space_operations ext3_writeback_aops = {
-        .readpage       = ext3_readpage,
-        .readpages      = ext3_readpages,
-        .writepage      = ext3_writeback_writepage,
-        .sync_page      = block_sync_page,
-        .write_begin    = ext3_write_begin,
-        .write_end      = ext3_writeback_write_end,
-        .bmap           = ext3_bmap,
-        .invalidatepage = ext3_invalidatepage,
-        .releasepage    = ext3_releasepage,
-        .direct_IO      = ext3_direct_IO,
-        .migratepage    = buffer_migrate_page,
+        .readpage               = ext3_readpage,
+        .readpages              = ext3_readpages,
+        .writepage              = ext3_writeback_writepage,
+        .sync_page              = block_sync_page,
+        .write_begin            = ext3_write_begin,
+        .write_end              = ext3_writeback_write_end,
+        .bmap                   = ext3_bmap,
+        .invalidatepage         = ext3_invalidatepage,
+        .releasepage            = ext3_releasepage,
+        .direct_IO              = ext3_direct_IO,
+        .migratepage            = buffer_migrate_page,
+        .is_partially_uptodate  = block_is_partially_uptodate,
 };
 
 static const struct address_space_operations ext3_journalled_aops = {
-        .readpage       = ext3_readpage,
-        .readpages      = ext3_readpages,
-        .writepage      = ext3_journalled_writepage,
-        .sync_page      = block_sync_page,
-        .write_begin    = ext3_write_begin,
-        .write_end      = ext3_journalled_write_end,
-        .set_page_dirty = ext3_journalled_set_page_dirty,
-        .bmap           = ext3_bmap,
-        .invalidatepage = ext3_invalidatepage,
-        .releasepage    = ext3_releasepage,
+        .readpage               = ext3_readpage,
+        .readpages              = ext3_readpages,
+        .writepage              = ext3_journalled_writepage,
+        .sync_page              = block_sync_page,
+        .write_begin            = ext3_write_begin,
+        .write_end              = ext3_journalled_write_end,
+        .set_page_dirty         = ext3_journalled_set_page_dirty,
+        .bmap                   = ext3_bmap,
+        .invalidatepage         = ext3_invalidatepage,
+        .releasepage            = ext3_releasepage,
+        .is_partially_uptodate  = block_is_partially_uptodate,
 };
 
 void ext3_set_aops(struct inode *inode)
@@ -2127,7 +2130,21 @@ static void ext3_free_data(handle_t *handle, struct inode *inode,
 
         if (this_bh) {
                 BUFFER_TRACE(this_bh, "call ext3_journal_dirty_metadata");
-                ext3_journal_dirty_metadata(handle, this_bh);
+
+                /*
+                 * The buffer head should have an attached journal head at this
+                 * point. However, if the data is corrupted and an indirect
+                 * block pointed to itself, it would have been detached when
+                 * the block was cleared. Check for this instead of OOPSing.
+                 */
+                if (bh2jh(this_bh))
+                        ext3_journal_dirty_metadata(handle, this_bh);
+                else
+                        ext3_error(inode->i_sb, "ext3_free_data",
+                                   "circular indirect block detected, "
+                                   "inode=%lu, block=%llu",
+                                   inode->i_ino,
+                                   (unsigned long long)this_bh->b_blocknr);
         }
 }
 
@@ -2253,6 +2270,19 @@ static void ext3_free_branches(handle_t *handle, struct inode *inode,
         }
 }
 
+int ext3_can_truncate(struct inode *inode)
+{
+        if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
+                return 0;
+        if (S_ISREG(inode->i_mode))
+                return 1;
+        if (S_ISDIR(inode->i_mode))
+                return 1;
+        if (S_ISLNK(inode->i_mode))
+                return !ext3_inode_is_fast_symlink(inode);
+        return 0;
+}
+
 /*
  * ext3_truncate()
  *
@@ -2297,12 +2327,7 @@ void ext3_truncate(struct inode *inode)
         unsigned blocksize = inode->i_sb->s_blocksize;
         struct page *page;
 
-        if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-            S_ISLNK(inode->i_mode)))
-                return;
-        if (ext3_inode_is_fast_symlink(inode))
-                return;
-        if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
+        if (!ext3_can_truncate(inode))
                 return;
 
         /*
@@ -2513,6 +2538,16 @@ static int __ext3_get_inode_loc(struct inode *inode,
         }
         if (!buffer_uptodate(bh)) {
                 lock_buffer(bh);
+
+                /*
+                 * If the buffer has the write error flag, we have failed
+                 * to write out another inode in the same block.  In this
+                 * case, we don't have to read the block because we may
+                 * read the old inode data successfully.
+                 */
+                if (buffer_write_io_error(bh) && !buffer_uptodate(bh))
+                        set_buffer_uptodate(bh);
+
                 if (buffer_uptodate(bh)) {
                         /* someone brought it uptodate while we waited */
                         unlock_buffer(bh);
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 0b8cf80154f1..de13e919cd81 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -240,13 +240,13 @@ static inline unsigned dx_root_limit (struct inode *dir, unsigned infosize)
 {
         unsigned entry_space = dir->i_sb->s_blocksize - EXT3_DIR_REC_LEN(1) -
                 EXT3_DIR_REC_LEN(2) - infosize;
-        return 0? 20: entry_space / sizeof(struct dx_entry);
+        return entry_space / sizeof(struct dx_entry);
 }
 
 static inline unsigned dx_node_limit (struct inode *dir)
 {
         unsigned entry_space = dir->i_sb->s_blocksize - EXT3_DIR_REC_LEN(0);
-        return 0? 22: entry_space / sizeof(struct dx_entry);
+        return entry_space / sizeof(struct dx_entry);
 }
 
 /*
@@ -991,19 +991,21 @@ static struct buffer_head * ext3_dx_find_entry(struct dentry *dentry,
                 de = (struct ext3_dir_entry_2 *) bh->b_data;
                 top = (struct ext3_dir_entry_2 *) ((char *) de + sb->s_blocksize -
                                        EXT3_DIR_REC_LEN(0));
-                for (; de < top; de = ext3_next_entry(de))
-                if (ext3_match (namelen, name, de)) {
-                        if (!ext3_check_dir_entry("ext3_find_entry",
-                                                  dir, de, bh,
-                                  (block<<EXT3_BLOCK_SIZE_BITS(sb))
-                                          +((char *)de - bh->b_data))) {
-                                brelse (bh);
+                for (; de < top; de = ext3_next_entry(de)) {
+                        int off = (block << EXT3_BLOCK_SIZE_BITS(sb))
+                                  + ((char *) de - bh->b_data);
+
+                        if (!ext3_check_dir_entry(__func__, dir, de, bh, off)) {
+                                brelse(bh);
                                 *err = ERR_BAD_DX_DIR;
                                 goto errout;
                         }
-                        *res_dir = de;
-                        dx_release (frames);
-                        return bh;
+
+                        if (ext3_match(namelen, name, de)) {
+                                *res_dir = de;
+                                dx_release(frames);
+                                return bh;
+                        }
                 }
                 brelse (bh);
                 /* Check to see if we should continue to search */
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 2845425077e8..f38a5afc39a1 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -472,7 +472,7 @@ static void ext3_destroy_inode(struct inode *inode)
         kmem_cache_free(ext3_inode_cachep, EXT3_I(inode));
 }
 
-static void init_once(struct kmem_cache * cachep, void *foo)
+static void init_once(void *foo)
 {
         struct ext3_inode_info *ei = (struct ext3_inode_info *) foo;
 
@@ -842,7 +842,7 @@ static int parse_options (char *options, struct super_block *sb,
         int data_opt = 0;
         int option;
 #ifdef CONFIG_QUOTA
-        int qtype;
+        int qtype, qfmt;
         char *qname;
 #endif
 
@@ -1018,9 +1018,11 @@ static int parse_options (char *options, struct super_block *sb,
                 case Opt_grpjquota:
                         qtype = GRPQUOTA;
 set_qf_name:
-                        if (sb_any_quota_enabled(sb)) {
+                        if ((sb_any_quota_enabled(sb) ||
+                             sb_any_quota_suspended(sb)) &&
+                            !sbi->s_qf_names[qtype]) {
                                 printk(KERN_ERR
-                                        "EXT3-fs: Cannot change journalled "
+                                        "EXT3-fs: Cannot change journaled "
                                         "quota options when quota turned on.\n");
                                 return 0;
                         }
@@ -1056,9 +1058,11 @@ set_qf_name:
                 case Opt_offgrpjquota:
                         qtype = GRPQUOTA;
 clear_qf_name:
-                        if (sb_any_quota_enabled(sb)) {
+                        if ((sb_any_quota_enabled(sb) ||
+                             sb_any_quota_suspended(sb)) &&
+                            sbi->s_qf_names[qtype]) {
                                 printk(KERN_ERR "EXT3-fs: Cannot change "
-                                        "journalled quota options when "
+                                        "journaled quota options when "
                                         "quota turned on.\n");
                                 return 0;
                         }
@@ -1069,10 +1073,20 @@ clear_qf_name:
                         sbi->s_qf_names[qtype] = NULL;
                         break;
                 case Opt_jqfmt_vfsold:
-                        sbi->s_jquota_fmt = QFMT_VFS_OLD;
-                        break;
+                        qfmt = QFMT_VFS_OLD;
+                        goto set_qf_format;
                 case Opt_jqfmt_vfsv0:
-                        sbi->s_jquota_fmt = QFMT_VFS_V0;
+                        qfmt = QFMT_VFS_V0;
+set_qf_format:
+                        if ((sb_any_quota_enabled(sb) ||
+                             sb_any_quota_suspended(sb)) &&
+                            sbi->s_jquota_fmt != qfmt) {
+                                printk(KERN_ERR "EXT3-fs: Cannot change "
+                                        "journaled quota options when "
+                                        "quota turned on.\n");
+                                return 0;
+                        }
+                        sbi->s_jquota_fmt = qfmt;
                         break;
                 case Opt_quota:
                 case Opt_usrquota:
@@ -1084,7 +1098,8 @@ clear_qf_name:
                         set_opt(sbi->s_mount_opt, GRPQUOTA);
                         break;
                 case Opt_noquota:
-                        if (sb_any_quota_enabled(sb)) {
+                        if (sb_any_quota_enabled(sb) ||
+                            sb_any_quota_suspended(sb)) {
                                 printk(KERN_ERR "EXT3-fs: Cannot change quota "
                                         "options when quota turned on.\n");
                                 return 0;
@@ -1169,14 +1184,14 @@ clear_qf_name:
                 }
 
                 if (!sbi->s_jquota_fmt) {
-                        printk(KERN_ERR "EXT3-fs: journalled quota format "
+                        printk(KERN_ERR "EXT3-fs: journaled quota format "
                                         "not specified.\n");
                         return 0;
                 }
         } else {
                 if (sbi->s_jquota_fmt) {
-                        printk(KERN_ERR "EXT3-fs: journalled quota format "
-                                        "specified with no journalling "
+                        printk(KERN_ERR "EXT3-fs: journaled quota format "
+                                        "specified with no journaling "
                                         "enabled.\n");
                         return 0;
                 }
@@ -1370,7 +1385,7 @@ static void ext3_orphan_cleanup (struct super_block * sb,
                         int ret = ext3_quota_on_mount(sb, i);
                         if (ret < 0)
                                 printk(KERN_ERR
-                                        "EXT3-fs: Cannot turn on journalled "
+                                        "EXT3-fs: Cannot turn on journaled "
                                         "quota: error %d\n", ret);
                 }
         }
@@ -2712,7 +2727,7 @@ static int ext3_release_dquot(struct dquot *dquot)
 
 static int ext3_mark_dquot_dirty(struct dquot *dquot)
 {
-        /* Are we journalling quotas? */
+        /* Are we journaling quotas? */
         if (EXT3_SB(dquot->dq_sb)->s_qf_names[USRQUOTA] ||
             EXT3_SB(dquot->dq_sb)->s_qf_names[GRPQUOTA]) {
                 dquot_mark_dquot_dirty(dquot);
@@ -2759,25 +2774,45 @@ static int ext3_quota_on(struct super_block *sb, int type, int format_id,
 
         if (!test_opt(sb, QUOTA))
                 return -EINVAL;
-        /* Not journalling quota or remount? */
-        if ((!EXT3_SB(sb)->s_qf_names[USRQUOTA] &&
-            !EXT3_SB(sb)->s_qf_names[GRPQUOTA]) || remount)
+        /* When remounting, no checks are needed and in fact, path is NULL */
+        if (remount)
                 return vfs_quota_on(sb, type, format_id, path, remount);
+
         err = path_lookup(path, LOOKUP_FOLLOW, &nd);
         if (err)
                 return err;
+
         /* Quotafile not on the same filesystem? */
         if (nd.path.mnt->mnt_sb != sb) {
                 path_put(&nd.path);
                 return -EXDEV;
         }
-        /* Quotafile not in fs root? */
-        if (nd.path.dentry->d_parent->d_inode != sb->s_root->d_inode)
-                printk(KERN_WARNING
-                        "EXT3-fs: Quota file not on filesystem root. "
-                        "Journalled quota will not work.\n");
+        /* Journaling quota? */
+        if (EXT3_SB(sb)->s_qf_names[type]) {
+                /* Quotafile not of fs root? */
+                if (nd.path.dentry->d_parent->d_inode != sb->s_root->d_inode)
+                        printk(KERN_WARNING
+                                "EXT3-fs: Quota file not on filesystem root. "
+                                "Journaled quota will not work.\n");
+        }
+
+        /*
+         * When we journal data on quota file, we have to flush journal to see
+         * all updates to the file when we bypass pagecache...
+         */
+        if (ext3_should_journal_data(nd.path.dentry->d_inode)) {
+                /*
+                 * We don't need to lock updates but journal_flush() could
+                 * otherwise be livelocked...
+                 */
+                journal_lock_updates(EXT3_SB(sb)->s_journal);
+                journal_flush(EXT3_SB(sb)->s_journal);
+                journal_unlock_updates(EXT3_SB(sb)->s_journal);
+        }
+
+        err = vfs_quota_on_path(sb, type, format_id, &nd.path);
         path_put(&nd.path);
-        return vfs_quota_on(sb, type, format_id, path, remount);
+        return err;
 }
 
 /* Read data from quotafile - avoid pagecache and such because we cannot afford
diff --git a/fs/ext3/xattr_security.c b/fs/ext3/xattr_security.c
index 821efaf2b94e..37b81097bdf2 100644
--- a/fs/ext3/xattr_security.c
+++ b/fs/ext3/xattr_security.c
@@ -15,7 +15,7 @@ static size_t
 ext3_xattr_security_list(struct inode *inode, char *list, size_t list_size,
                          const char *name, size_t name_len)
 {
-        const size_t prefix_len = sizeof(XATTR_SECURITY_PREFIX)-1;
+        const size_t prefix_len = XATTR_SECURITY_PREFIX_LEN;
         const size_t total_len = prefix_len + name_len + 1;
 
 
diff --git a/fs/ext3/xattr_trusted.c b/fs/ext3/xattr_trusted.c
index 0327497a55ce..c7c41a410c4b 100644
--- a/fs/ext3/xattr_trusted.c
+++ b/fs/ext3/xattr_trusted.c
@@ -13,13 +13,11 @@
 #include <linux/ext3_fs.h>
 #include "xattr.h"
 
-#define XATTR_TRUSTED_PREFIX "trusted."
-
 static size_t
 ext3_xattr_trusted_list(struct inode *inode, char *list, size_t list_size,
                         const char *name, size_t name_len)
 {
-        const size_t prefix_len = sizeof(XATTR_TRUSTED_PREFIX)-1;
+        const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN;
         const size_t total_len = prefix_len + name_len + 1;
 
         if (!capable(CAP_SYS_ADMIN))
diff --git a/fs/ext3/xattr_user.c b/fs/ext3/xattr_user.c
index 1abd8f92c440..430fe63b31b3 100644
--- a/fs/ext3/xattr_user.c
+++ b/fs/ext3/xattr_user.c
@@ -12,13 +12,11 @@
 #include <linux/ext3_fs.h>
 #include "xattr.h"
 
-#define XATTR_USER_PREFIX "user."
-
 static size_t
 ext3_xattr_user_list(struct inode *inode, char *list, size_t list_size,
                      const char *name, size_t name_len)
 {
-        const size_t prefix_len = sizeof(XATTR_USER_PREFIX)-1;
+        const size_t prefix_len = XATTR_USER_PREFIX_LEN;
         const size_t total_len = prefix_len + name_len + 1;
 
         if (!test_opt(inode->i_sb, XATTR_USER))
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index 3c8dab880d91..694ed6fadcc8 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -40,34 +40,35 @@ ext4_acl_from_disk(const void *value, size_t size)
         acl = posix_acl_alloc(count, GFP_NOFS);
         if (!acl)
                 return ERR_PTR(-ENOMEM);
-        for (n=0; n < count; n++) {
+        for (n = 0; n < count; n++) {
                 ext4_acl_entry *entry =
                         (ext4_acl_entry *)value;
                 if ((char *)value + sizeof(ext4_acl_entry_short) > end)
                         goto fail;
                 acl->a_entries[n].e_tag  = le16_to_cpu(entry->e_tag);
                 acl->a_entries[n].e_perm = le16_to_cpu(entry->e_perm);
-                switch(acl->a_entries[n].e_tag) {
-                        case ACL_USER_OBJ:
-                        case ACL_GROUP_OBJ:
-                        case ACL_MASK:
-                        case ACL_OTHER:
-                                value = (char *)value +
-                                        sizeof(ext4_acl_entry_short);
-                                acl->a_entries[n].e_id = ACL_UNDEFINED_ID;
-                                break;
-
-                        case ACL_USER:
-                        case ACL_GROUP:
-                                value = (char *)value + sizeof(ext4_acl_entry);
-                                if ((char *)value > end)
-                                        goto fail;
-                                acl->a_entries[n].e_id =
-                                        le32_to_cpu(entry->e_id);
-                                break;
-
-                        default:
+
+                switch (acl->a_entries[n].e_tag) {
+                case ACL_USER_OBJ:
+                case ACL_GROUP_OBJ:
+                case ACL_MASK:
+                case ACL_OTHER:
+                        value = (char *)value +
+                                sizeof(ext4_acl_entry_short);
+                        acl->a_entries[n].e_id = ACL_UNDEFINED_ID;
+                        break;
+
+                case ACL_USER:
+                case ACL_GROUP:
+                        value = (char *)value + sizeof(ext4_acl_entry);
+                        if ((char *)value > end)
                                 goto fail;
+                        acl->a_entries[n].e_id =
+                                le32_to_cpu(entry->e_id);
+                        break;
+
+                default:
+                        goto fail;
                 }
         }
         if (value != end)
@@ -96,27 +97,26 @@ ext4_acl_to_disk(const struct posix_acl *acl, size_t *size)
                 return ERR_PTR(-ENOMEM);
         ext_acl->a_version = cpu_to_le32(EXT4_ACL_VERSION);
         e = (char *)ext_acl + sizeof(ext4_acl_header);
-        for (n=0; n < acl->a_count; n++) {
+        for (n = 0; n < acl->a_count; n++) {
                 ext4_acl_entry *entry = (ext4_acl_entry *)e;
                 entry->e_tag  = cpu_to_le16(acl->a_entries[n].e_tag);
                 entry->e_perm = cpu_to_le16(acl->a_entries[n].e_perm);
-                switch(acl->a_entries[n].e_tag) {
-                        case ACL_USER:
-                        case ACL_GROUP:
-                                entry->e_id =
-                                        cpu_to_le32(acl->a_entries[n].e_id);
-                                e += sizeof(ext4_acl_entry);
-                                break;
-
-                        case ACL_USER_OBJ:
-                        case ACL_GROUP_OBJ:
-                        case ACL_MASK:
-                        case ACL_OTHER:
-                                e += sizeof(ext4_acl_entry_short);
-                                break;
-
-                        default:
-                                goto fail;
+                switch (acl->a_entries[n].e_tag) {
+                case ACL_USER:
+                case ACL_GROUP:
+                        entry->e_id = cpu_to_le32(acl->a_entries[n].e_id);
+                        e += sizeof(ext4_acl_entry);
+                        break;
+
+                case ACL_USER_OBJ:
+                case ACL_GROUP_OBJ:
+                case ACL_MASK:
+                case ACL_OTHER:
+                        e += sizeof(ext4_acl_entry_short);
+                        break;
+
+                default:
+                        goto fail;
                 }
         }
         return (char *)ext_acl;
@@ -167,23 +167,23 @@ ext4_get_acl(struct inode *inode, int type)
         if (!test_opt(inode->i_sb, POSIX_ACL))
                 return NULL;
 
-        switch(type) {
-                case ACL_TYPE_ACCESS:
-                        acl = ext4_iget_acl(inode, &ei->i_acl);
-                        if (acl != EXT4_ACL_NOT_CACHED)
-                                return acl;
-                        name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS;
-                        break;
-
-                case ACL_TYPE_DEFAULT:
-                        acl = ext4_iget_acl(inode, &ei->i_default_acl);
-                        if (acl != EXT4_ACL_NOT_CACHED)
-                                return acl;
-                        name_index = EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT;
-                        break;
-
-                default:
-                        return ERR_PTR(-EINVAL);
+        switch (type) {
+        case ACL_TYPE_ACCESS:
+                acl = ext4_iget_acl(inode, &ei->i_acl);
+                if (acl != EXT4_ACL_NOT_CACHED)
+                        return acl;
+                name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS;
+                break;
+
+        case ACL_TYPE_DEFAULT:
+                acl = ext4_iget_acl(inode, &ei->i_default_acl);
+                if (acl != EXT4_ACL_NOT_CACHED)
+                        return acl;
+                name_index = EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT;
+                break;
+
+        default:
+                return ERR_PTR(-EINVAL);
         }
         retval = ext4_xattr_get(inode, name_index, "", NULL, 0);
         if (retval > 0) {
@@ -201,14 +201,14 @@ ext4_get_acl(struct inode *inode, int type)
         kfree(value);
 
         if (!IS_ERR(acl)) {
-                switch(type) {
-                        case ACL_TYPE_ACCESS:
-                                ext4_iset_acl(inode, &ei->i_acl, acl);
-                                break;
-
-                        case ACL_TYPE_DEFAULT:
-                                ext4_iset_acl(inode, &ei->i_default_acl, acl);
-                                break;
+                switch (type) {
+                case ACL_TYPE_ACCESS:
+                        ext4_iset_acl(inode, &ei->i_acl, acl);
+                        break;
+
+                case ACL_TYPE_DEFAULT:
+                        ext4_iset_acl(inode, &ei->i_default_acl, acl);
+                        break;
                 }
         }
         return acl;
@@ -232,31 +232,31 @@ ext4_set_acl(handle_t *handle, struct inode *inode, int type,
         if (S_ISLNK(inode->i_mode))
                 return -EOPNOTSUPP;
 
-        switch(type) {
-                case ACL_TYPE_ACCESS:
-                        name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS;
-                        if (acl) {
-                                mode_t mode = inode->i_mode;
-                                error = posix_acl_equiv_mode(acl, &mode);
-                                if (error < 0)
-                                        return error;
-                                else {
-                                        inode->i_mode = mode;
-                                        ext4_mark_inode_dirty(handle, inode);
-                                        if (error == 0)
-                                                acl = NULL;
-                                }
+        switch (type) {
+        case ACL_TYPE_ACCESS:
+                name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS;
+                if (acl) {
+                        mode_t mode = inode->i_mode;
+                        error = posix_acl_equiv_mode(acl, &mode);
+                        if (error < 0)
+                                return error;
+                        else {
+                                inode->i_mode = mode;
+                                ext4_mark_inode_dirty(handle, inode);
+                                if (error == 0)
+                                        acl = NULL;
                         }
-                        break;
+                }
+                break;
 
-                case ACL_TYPE_DEFAULT:
-                        name_index = EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT;
-                        if (!S_ISDIR(inode->i_mode))
-                                return acl ? -EACCES : 0;
-                        break;
+        case ACL_TYPE_DEFAULT:
+                name_index = EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT;
+                if (!S_ISDIR(inode->i_mode))
+                        return acl ? -EACCES : 0;
+                break;
 
-                default:
-                        return -EINVAL;
+        default:
+                return -EINVAL;
         }
         if (acl) {
                 value = ext4_acl_to_disk(acl, &size);
@@ -269,14 +269,14 @@ ext4_set_acl(handle_t *handle, struct inode *inode, int type,
 
         kfree(value);
         if (!error) {
-                switch(type) {
-                        case ACL_TYPE_ACCESS:
-                                ext4_iset_acl(inode, &ei->i_acl, acl);
-                                break;
-
-                        case ACL_TYPE_DEFAULT:
-                                ext4_iset_acl(inode, &ei->i_default_acl, acl);
-                                break;
+                switch (type) {
+                case ACL_TYPE_ACCESS:
+                        ext4_iset_acl(inode, &ei->i_acl, acl);
+                        break;
+
+                case ACL_TYPE_DEFAULT:
+                        ext4_iset_acl(inode, &ei->i_default_acl, acl);
+                        break;
                 }
         }
         return error;
@@ -299,7 +299,7 @@ ext4_check_acl(struct inode *inode, int mask)
 }
 
 int
-ext4_permission(struct inode *inode, int mask, struct nameidata *nd)
+ext4_permission(struct inode *inode, int mask)
 {
         return generic_permission(inode, mask, ext4_check_acl);
 }
diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h
index 26a5c1abf147..cd2b855a07d6 100644
--- a/fs/ext4/acl.h
+++ b/fs/ext4/acl.h
@@ -58,7 +58,7 @@ static inline int ext4_acl_count(size_t size)
 #define EXT4_ACL_NOT_CACHED ((void *)-1)
 
 /* acl.c */
-extern int ext4_permission (struct inode *, int, struct nameidata *);
+extern int ext4_permission (struct inode *, int);
 extern int ext4_acl_chmod (struct inode *);
 extern int ext4_init_acl (handle_t *, struct inode *, struct inode *);
 
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 495ab21b9832..1ae5004e93fc 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -314,25 +314,28 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
         if (unlikely(!bh)) {
                 ext4_error(sb, __func__,
                             "Cannot read block bitmap - "
-                            "block_group = %d, block_bitmap = %llu",
-                            (int)block_group, (unsigned long long)bitmap_blk);
+                            "block_group = %lu, block_bitmap = %llu",
+                            block_group, bitmap_blk);
                 return NULL;
         }
         if (bh_uptodate_or_lock(bh))
                 return bh;
 
+        spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group));
         if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
                 ext4_init_block_bitmap(sb, bh, block_group, desc);
                 set_buffer_uptodate(bh);
                 unlock_buffer(bh);
+                spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
                 return bh;
         }
+        spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
         if (bh_submit_read(bh) < 0) {
                 put_bh(bh);
                 ext4_error(sb, __func__,
                             "Cannot read block bitmap - "
-                            "block_group = %d, block_bitmap = %llu",
-                            (int)block_group, (unsigned long long)bitmap_blk);
+                            "block_group = %lu, block_bitmap = %llu",
+                            block_group, bitmap_blk);
                 return NULL;
         }
         ext4_valid_block_bitmap(sb, desc, block_group, bh);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 303e41cf7b14..6c7924d9e358 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1044,7 +1044,6 @@ extern void ext4_mb_update_group_info(struct ext4_group_info *grp,
 
 
 /* inode.c */
-void ext4_da_release_space(struct inode *inode, int used, int to_free);
 int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
                 struct buffer_head *bh, ext4_fsblk_t blocknr);
 struct buffer_head *ext4_getblk(handle_t *, struct inode *,
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 42c4c0c892ed..612c3d2c3824 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -99,7 +99,7 @@ static int ext4_ext_journal_restart(handle_t *handle, int needed)
         if (handle->h_buffer_credits > needed)
                 return 0;
         err = ext4_journal_extend(handle, needed);
-        if (err)
+        if (err <= 0)
                 return err;
         return ext4_journal_restart(handle, needed);
 }
@@ -1441,7 +1441,7 @@ unsigned int ext4_ext_check_overlap(struct inode *inode,
 
         /*
          * get the next allocated block if the extent in the path
-         * is before the requested block(s) 
+         * is before the requested block(s)
          */
         if (b2 < b1) {
                 b2 = ext4_ext_next_allocated_block(path);
@@ -1910,9 +1910,13 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
                         BUG_ON(b != ex_ee_block + ex_ee_len - 1);
                 }
 
-                /* at present, extent can't cross block group: */
-                /* leaf + bitmap + group desc + sb + inode */
-                credits = 5;
+                /*
+                 * 3 for leaf, sb, and inode plus 2 (bmap and group
+                 * descriptor) for each block group; assume two block
+                 * groups plus ex_ee_len/blocks_per_block_group for
+                 * the worst case
+                 */
+                credits = 7 + 2*(ex_ee_len/EXT4_BLOCKS_PER_GROUP(inode->i_sb));
                 if (ex == EXT_FIRST_EXTENT(eh)) {
                         correct_index = 1;
                         credits += (ext_depth(inode)) + 1;
@@ -2323,7 +2327,10 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
                 unsigned int newdepth;
                 /* If extent has less than EXT4_EXT_ZERO_LEN zerout directly */
                 if (allocated <= EXT4_EXT_ZERO_LEN) {
-                        /* Mark first half uninitialized.
+                        /*
+                         * iblock == ee_block is handled by the zerouout
+                         * at the beginning.
+                         * Mark first half uninitialized.
                          * Mark second half initialized and zero out the
                          * initialized extent
                          */
@@ -2346,7 +2353,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
                                 ex->ee_len   = orig_ex.ee_len;
                                 ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
                                 ext4_ext_dirty(handle, inode, path + depth);
-                                /* zeroed the full extent */
+                                /* blocks available from iblock */
                                 return allocated;
 
                         } else if (err)
@@ -2374,6 +2381,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
                                         err = PTR_ERR(path);
                                         return err;
                                 }
+                                /* get the second half extent details */
                                 ex = path[depth].p_ext;
                                 err = ext4_ext_get_access(handle, inode,
                                                                 path + depth);
@@ -2403,6 +2411,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
                         ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
                         ext4_ext_dirty(handle, inode, path + depth);
                         /* zeroed the full extent */
+                        /* blocks available from iblock */
                         return allocated;
 
                 } else if (err)
@@ -2418,23 +2427,22 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
                  */
                 orig_ex.ee_len = cpu_to_le16(ee_len -
                                                 ext4_ext_get_actual_len(ex3));
-                if (newdepth != depth) {
-                        depth = newdepth;
-                        ext4_ext_drop_refs(path);
-                        path = ext4_ext_find_extent(inode, iblock, path);
-                        if (IS_ERR(path)) {
-                                err = PTR_ERR(path);
-                                goto out;
-                        }
-                        eh = path[depth].p_hdr;
-                        ex = path[depth].p_ext;
-                        if (ex2 != &newex)
-                                ex2 = ex;
-
-                        err = ext4_ext_get_access(handle, inode, path + depth);
-                        if (err)
-                                goto out;
+                depth = newdepth;
+                ext4_ext_drop_refs(path);
+                path = ext4_ext_find_extent(inode, iblock, path);
+                if (IS_ERR(path)) {
+                        err = PTR_ERR(path);
+                        goto out;
                 }
+                eh = path[depth].p_hdr;
+                ex = path[depth].p_ext;
+                if (ex2 != &newex)
+                        ex2 = ex;
+
+                err = ext4_ext_get_access(handle, inode, path + depth);
+                if (err)
+                        goto out;
+
                 allocated = max_blocks;
 
                 /* If extent has less than EXT4_EXT_ZERO_LEN and we are trying
@@ -2452,6 +2460,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
                         ext4_ext_store_pblock(ex, ext_pblock(&orig_ex));
                         ext4_ext_dirty(handle, inode, path + depth);
                         /* zero out the first half */
+                        /* blocks available from iblock */
                         return allocated;
                 }
         }
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index a92eb305344f..655e760212b8 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -97,34 +97,44 @@ unsigned ext4_init_inode_bitmap(struct super_block *sb, struct buffer_head *bh,
  * Return buffer_head of bitmap on success or NULL.
  */
 static struct buffer_head *
-read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
+ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 {
         struct ext4_group_desc *desc;
         struct buffer_head *bh = NULL;
+        ext4_fsblk_t bitmap_blk;
 
         desc = ext4_get_group_desc(sb, block_group, NULL);
         if (!desc)
-                goto error_out;
-        if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
-                bh = sb_getblk(sb, ext4_inode_bitmap(sb, desc));
-                if (!buffer_uptodate(bh)) {
-                        lock_buffer(bh);
-                        if (!buffer_uptodate(bh)) {
-                                ext4_init_inode_bitmap(sb, bh, block_group,
-                                                       desc);
-                                set_buffer_uptodate(bh);
-                        }
-                        unlock_buffer(bh);
-                }
-        } else {
-                bh = sb_bread(sb, ext4_inode_bitmap(sb, desc));
+                return NULL;
+        bitmap_blk = ext4_inode_bitmap(sb, desc);
+        bh = sb_getblk(sb, bitmap_blk);
+        if (unlikely(!bh)) {
+                ext4_error(sb, __func__,
+                            "Cannot read inode bitmap - "
+                            "block_group = %lu, inode_bitmap = %llu",
+                            block_group, bitmap_blk);
+                return NULL;
         }
-        if (!bh)
-                ext4_error(sb, "read_inode_bitmap",
+        if (bh_uptodate_or_lock(bh))
+                return bh;
+
+        spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group));
+        if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
+                ext4_init_inode_bitmap(sb, bh, block_group, desc);
+                set_buffer_uptodate(bh);
+                unlock_buffer(bh);
+                spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+                return bh;
+        }
+        spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+        if (bh_submit_read(bh) < 0) {
+                put_bh(bh);
+                ext4_error(sb, __func__,
                             "Cannot read inode bitmap - "
                             "block_group = %lu, inode_bitmap = %llu",
-                            block_group, ext4_inode_bitmap(sb, desc));
-error_out:
+                            block_group, bitmap_blk);
+                return NULL;
+        }
         return bh;
 }
 
@@ -200,7 +210,7 @@ void ext4_free_inode (handle_t *handle, struct inode * inode)
         }
         block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
         bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
-        bitmap_bh = read_inode_bitmap(sb, block_group);
+        bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
         if (!bitmap_bh)
                 goto error_return;
 
@@ -623,7 +633,7 @@ got_group:
                         goto fail;
 
                 brelse(bitmap_bh);
-                bitmap_bh = read_inode_bitmap(sb, group);
+                bitmap_bh = ext4_read_inode_bitmap(sb, group);
                 if (!bitmap_bh)
                         goto fail;
 
@@ -728,7 +738,7 @@ got:
 
                         /* When marking the block group with
                          * ~EXT4_BG_INODE_UNINIT we don't want to depend
-                         * on the value of bg_itable_unsed even though
+                         * on the value of bg_itable_unused even though
                          * mke2fs could have initialized the same for us.
                          * Instead we calculated the value below
                          */
@@ -891,7 +901,7 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
 
         block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
         bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
-        bitmap_bh = read_inode_bitmap(sb, block_group);
+        bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
         if (!bitmap_bh) {
                 ext4_warning(sb, __func__,
                              "inode bitmap error for orphan %lu", ino);
@@ -969,7 +979,7 @@ unsigned long ext4_count_free_inodes (struct super_block * sb)
                         continue;
                 desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
                 brelse(bitmap_bh);
-                bitmap_bh = read_inode_bitmap(sb, i);
+                bitmap_bh = ext4_read_inode_bitmap(sb, i);
                 if (!bitmap_bh)
                         continue;
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 8ca2763df091..59fbbe899acc 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -191,6 +191,7 @@ static int ext4_journal_test_restart(handle_t *handle, struct inode *inode)
 void ext4_delete_inode (struct inode * inode)
 {
         handle_t *handle;
+        int err;
 
         if (ext4_should_order_data(inode))
                 ext4_begin_ordered_truncate(inode, 0);
@@ -199,8 +200,9 @@ void ext4_delete_inode (struct inode * inode)
         if (is_bad_inode(inode))
                 goto no_delete;
 
-        handle = start_transaction(inode);
+        handle = ext4_journal_start(inode, blocks_for_truncate(inode)+3);
         if (IS_ERR(handle)) {
+                ext4_std_error(inode->i_sb, PTR_ERR(handle));
                 /*
                  * If we're going to skip the normal cleanup, we still need to
                  * make sure that the in-core orphan linked list is properly
@@ -213,8 +215,34 @@ void ext4_delete_inode (struct inode * inode)
         if (IS_SYNC(inode))
                 handle->h_sync = 1;
         inode->i_size = 0;
+        err = ext4_mark_inode_dirty(handle, inode);
+        if (err) {
+                ext4_warning(inode->i_sb, __func__,
+                             "couldn't mark inode dirty (err %d)", err);
+                goto stop_handle;
+        }
         if (inode->i_blocks)
                 ext4_truncate(inode);
+
+        /*
+         * ext4_ext_truncate() doesn't reserve any slop when it
+         * restarts journal transactions; therefore there may not be
+         * enough credits left in the handle to remove the inode from
+         * the orphan list and set the dtime field.
+         */
+        if (handle->h_buffer_credits < 3) {
+                err = ext4_journal_extend(handle, 3);
+                if (err > 0)
+                        err = ext4_journal_restart(handle, 3);
+                if (err != 0) {
+                        ext4_warning(inode->i_sb, __func__,
+                                     "couldn't extend journal (err %d)", err);
+                stop_handle:
+                        ext4_journal_stop(handle);
+                        goto no_delete;
+                }
+        }
+
         /*
          * Kill off the orphan record which ext4_truncate created.
          * AKPM: I think this can be inside the above `if'.
@@ -952,6 +980,67 @@ out:
         return err;
 }
 
+/*
+ * Calculate the number of metadata blocks need to reserve
+ * to allocate @blocks for non extent file based file
+ */
+static int ext4_indirect_calc_metadata_amount(struct inode *inode, int blocks)
+{
+        int icap = EXT4_ADDR_PER_BLOCK(inode->i_sb);
+        int ind_blks, dind_blks, tind_blks;
+
+        /* number of new indirect blocks needed */
+        ind_blks = (blocks + icap - 1) / icap;
+
+        dind_blks = (ind_blks + icap - 1) / icap;
+
+        tind_blks = 1;
+
+        return ind_blks + dind_blks + tind_blks;
+}
+
+/*
+ * Calculate the number of metadata blocks need to reserve
+ * to allocate given number of blocks
+ */
+static int ext4_calc_metadata_amount(struct inode *inode, int blocks)
+{
+        if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
+                return ext4_ext_calc_metadata_amount(inode, blocks);
+
+        return ext4_indirect_calc_metadata_amount(inode, blocks);
+}
+
+static void ext4_da_update_reserve_space(struct inode *inode, int used)
+{
+        struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+        int total, mdb, mdb_free;
+
+        spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
+        /* recalculate the number of metablocks still need to be reserved */
+        total = EXT4_I(inode)->i_reserved_data_blocks - used;
+        mdb = ext4_calc_metadata_amount(inode, total);
+
+        /* figure out how many metablocks to release */
+        BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
+        mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb;
+
+        /* Account for allocated meta_blocks */
+        mdb_free -= EXT4_I(inode)->i_allocated_meta_blocks;
+
+        /* update fs free blocks counter for truncate case */
+        percpu_counter_add(&sbi->s_freeblocks_counter, mdb_free);
+
+        /* update per-inode reservations */
+        BUG_ON(used  > EXT4_I(inode)->i_reserved_data_blocks);
+        EXT4_I(inode)->i_reserved_data_blocks -= used;
+
+        BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
+        EXT4_I(inode)->i_reserved_meta_blocks = mdb;
+        EXT4_I(inode)->i_allocated_meta_blocks = 0;
+        spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+}
+
 /* Maximum number of blocks we map for direct IO at once. */
 #define DIO_MAX_BLOCKS 4096
 /*
@@ -965,10 +1054,9 @@ out:
 
 
 /*
+ * The ext4_get_blocks_wrap() function try to look up the requested blocks,
+ * and returns if the blocks are already mapped.
  *
- *
- * ext4_ext4 get_block() wrapper function
- * It will do a look up first, and returns if the blocks already mapped.
  * Otherwise it takes the write lock of the i_data_sem and allocate blocks
  * and store the allocated blocks in the result buffer head and mark it
  * mapped.
@@ -1069,7 +1157,7 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
                  * which were deferred till now
                  */
                 if ((retval > 0) && buffer_delay(bh))
-                        ext4_da_release_space(inode, retval, 0);
+                        ext4_da_update_reserve_space(inode, retval);
         }
 
         up_write((&EXT4_I(inode)->i_data_sem));
@@ -1336,12 +1424,8 @@ static int ext4_ordered_write_end(struct file *file,
 {
         handle_t *handle = ext4_journal_current_handle();
         struct inode *inode = mapping->host;
-        unsigned from, to;
         int ret = 0, ret2;
 
-        from = pos & (PAGE_CACHE_SIZE - 1);
-        to = from + len;
-
         ret = ext4_jbd2_file_inode(handle, inode);
 
         if (ret == 0) {
@@ -1437,36 +1521,6 @@ static int ext4_journalled_write_end(struct file *file,
 
         return ret ? ret : copied;
 }
-/*
- * Calculate the number of metadata blocks need to reserve
- * to allocate @blocks for non extent file based file
- */
-static int ext4_indirect_calc_metadata_amount(struct inode *inode, int blocks)
-{
-        int icap = EXT4_ADDR_PER_BLOCK(inode->i_sb);
-        int ind_blks, dind_blks, tind_blks;
-
-        /* number of new indirect blocks needed */
-        ind_blks = (blocks + icap - 1) / icap;
-
-        dind_blks = (ind_blks + icap - 1) / icap;
-
-        tind_blks = 1;
-
-        return ind_blks + dind_blks + tind_blks;
-}
-
-/*
- * Calculate the number of metadata blocks need to reserve
- * to allocate given number of blocks
- */
-static int ext4_calc_metadata_amount(struct inode *inode, int blocks)
-{
-        if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
-                return ext4_ext_calc_metadata_amount(inode, blocks);
-
-        return ext4_indirect_calc_metadata_amount(inode, blocks);
-}
 
 static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
 {
@@ -1490,7 +1544,6 @@ static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
                 spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
                 return -ENOSPC;
         }
-
         /* reduce fs free blocks counter */
         percpu_counter_sub(&sbi->s_freeblocks_counter, total);
 
@@ -1501,35 +1554,31 @@ static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
         return 0;       /* success */
 }
 
-void ext4_da_release_space(struct inode *inode, int used, int to_free)
+static void ext4_da_release_space(struct inode *inode, int to_free)
 {
         struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
         int total, mdb, mdb_free, release;
 
         spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
         /* recalculate the number of metablocks still need to be reserved */
-        total = EXT4_I(inode)->i_reserved_data_blocks - used - to_free;
+        total = EXT4_I(inode)->i_reserved_data_blocks - to_free;
         mdb = ext4_calc_metadata_amount(inode, total);
 
         /* figure out how many metablocks to release */
         BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
         mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb;
 
-        /* Account for allocated meta_blocks */
-        mdb_free -= EXT4_I(inode)->i_allocated_meta_blocks;
-
         release = to_free + mdb_free;
 
         /* update fs free blocks counter for truncate case */
         percpu_counter_add(&sbi->s_freeblocks_counter, release);
 
         /* update per-inode reservations */
-        BUG_ON(used + to_free > EXT4_I(inode)->i_reserved_data_blocks);
-        EXT4_I(inode)->i_reserved_data_blocks -= (used + to_free);
+        BUG_ON(to_free > EXT4_I(inode)->i_reserved_data_blocks);
+        EXT4_I(inode)->i_reserved_data_blocks -= to_free;
 
         BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
         EXT4_I(inode)->i_reserved_meta_blocks = mdb;
-        EXT4_I(inode)->i_allocated_meta_blocks = 0;
         spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
 }
 
@@ -1551,7 +1600,7 @@ static void ext4_da_page_release_reservation(struct page *page,
                 }
                 curr_off = next_off;
         } while ((bh = bh->b_this_page) != head);
-        ext4_da_release_space(page->mapping->host, 0, to_release);
+        ext4_da_release_space(page->mapping->host, to_release);
 }
 
 /*
@@ -2280,8 +2329,11 @@ retry:
         }
 
         page = __grab_cache_page(mapping, index);
-        if (!page)
-                return -ENOMEM;
+        if (!page) {
+                ext4_journal_stop(handle);
+                ret = -ENOMEM;
+                goto out;
+        }
         *pagep = page;
 
         ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
@@ -2806,59 +2858,63 @@ static int ext4_journalled_set_page_dirty(struct page *page)
 }
 
 static const struct address_space_operations ext4_ordered_aops = {
-        .readpage       = ext4_readpage,
-        .readpages      = ext4_readpages,
-        .writepage      = ext4_normal_writepage,
-        .sync_page      = block_sync_page,
-        .write_begin    = ext4_write_begin,
-        .write_end      = ext4_ordered_write_end,
-        .bmap           = ext4_bmap,
-        .invalidatepage = ext4_invalidatepage,
-        .releasepage    = ext4_releasepage,
-        .direct_IO      = ext4_direct_IO,
-        .migratepage    = buffer_migrate_page,
+        .readpage               = ext4_readpage,
+        .readpages              = ext4_readpages,
+        .writepage              = ext4_normal_writepage,
+        .sync_page              = block_sync_page,
+        .write_begin            = ext4_write_begin,
+        .write_end              = ext4_ordered_write_end,
+        .bmap                   = ext4_bmap,
+        .invalidatepage         = ext4_invalidatepage,
+        .releasepage            = ext4_releasepage,
+        .direct_IO              = ext4_direct_IO,
+        .migratepage            = buffer_migrate_page,
+        .is_partially_uptodate  = block_is_partially_uptodate,
 };
 
 static const struct address_space_operations ext4_writeback_aops = {
-        .readpage       = ext4_readpage,
-        .readpages      = ext4_readpages,
-        .writepage      = ext4_normal_writepage,
-        .sync_page      = block_sync_page,
-        .write_begin    = ext4_write_begin,
-        .write_end      = ext4_writeback_write_end,
-        .bmap           = ext4_bmap,
-        .invalidatepage = ext4_invalidatepage,
-        .releasepage    = ext4_releasepage,
-        .direct_IO      = ext4_direct_IO,
-        .migratepage    = buffer_migrate_page,
+        .readpage               = ext4_readpage,
+        .readpages              = ext4_readpages,
+        .writepage              = ext4_normal_writepage,
+        .sync_page              = block_sync_page,
+        .write_begin            = ext4_write_begin,
+        .write_end              = ext4_writeback_write_end,
+        .bmap                   = ext4_bmap,
+        .invalidatepage         = ext4_invalidatepage,
+        .releasepage            = ext4_releasepage,
+        .direct_IO              = ext4_direct_IO,
+        .migratepage            = buffer_migrate_page,
+        .is_partially_uptodate  = block_is_partially_uptodate,
 };
 
 static const struct address_space_operations ext4_journalled_aops = {
-        .readpage       = ext4_readpage,
-        .readpages      = ext4_readpages,
-        .writepage      = ext4_journalled_writepage,
-        .sync_page      = block_sync_page,
-        .write_begin    = ext4_write_begin,
-        .write_end      = ext4_journalled_write_end,
-        .set_page_dirty = ext4_journalled_set_page_dirty,
-        .bmap           = ext4_bmap,
-        .invalidatepage = ext4_invalidatepage,
-        .releasepage    = ext4_releasepage,
+        .readpage               = ext4_readpage,
+        .readpages              = ext4_readpages,
+        .writepage              = ext4_journalled_writepage,
+        .sync_page              = block_sync_page,
+        .write_begin            = ext4_write_begin,
+        .write_end              = ext4_journalled_write_end,
+        .set_page_dirty         = ext4_journalled_set_page_dirty,
+        .bmap                   = ext4_bmap,
+        .invalidatepage         = ext4_invalidatepage,
+        .releasepage            = ext4_releasepage,
+        .is_partially_uptodate  = block_is_partially_uptodate,
 };
 
 static const struct address_space_operations ext4_da_aops = {
-        .readpage       = ext4_readpage,
-        .readpages      = ext4_readpages,
-        .writepage      = ext4_da_writepage,
-        .writepages     = ext4_da_writepages,
-        .sync_page      = block_sync_page,
-        .write_begin    = ext4_da_write_begin,
-        .write_end      = ext4_da_write_end,
-        .bmap           = ext4_bmap,
-        .invalidatepage = ext4_da_invalidatepage,
-        .releasepage    = ext4_releasepage,
-        .direct_IO      = ext4_direct_IO,
-        .migratepage    = buffer_migrate_page,
+        .readpage               = ext4_readpage,
+        .readpages              = ext4_readpages,
+        .writepage              = ext4_da_writepage,
+        .writepages             = ext4_da_writepages,
+        .sync_page              = block_sync_page,
+        .write_begin            = ext4_da_write_begin,
+        .write_end              = ext4_da_write_end,
+        .bmap                   = ext4_bmap,
+        .invalidatepage         = ext4_da_invalidatepage,
+        .releasepage            = ext4_releasepage,
+        .direct_IO              = ext4_direct_IO,
+        .migratepage            = buffer_migrate_page,
+        .is_partially_uptodate  = block_is_partially_uptodate,
 };
 
 void ext4_set_aops(struct inode *inode)
@@ -3586,6 +3642,16 @@ static int __ext4_get_inode_loc(struct inode *inode,
         }
         if (!buffer_uptodate(bh)) {
                 lock_buffer(bh);
+
+                /*
+                 * If the buffer has the write error flag, we have failed
+                 * to write out another inode in the same block.  In this
+                 * case, we don't have to read the block because we may
+                 * read the old inode data successfully.
+                 */
+                if (buffer_write_io_error(bh) && !buffer_uptodate(bh))
+                        set_buffer_uptodate(bh);
+
                 if (buffer_uptodate(bh)) {
                         /* someone brought it uptodate while we waited */
                         unlock_buffer(bh);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 8d141a25bbee..865e9ddb44d4 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -787,13 +787,16 @@ static int ext4_mb_init_cache(struct page *page, char *incore)
                 if (bh_uptodate_or_lock(bh[i]))
                         continue;
 
+                spin_lock(sb_bgl_lock(EXT4_SB(sb), first_group + i));
                 if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
                         ext4_init_block_bitmap(sb, bh[i],
                                                 first_group + i, desc);
                         set_buffer_uptodate(bh[i]);
                         unlock_buffer(bh[i]);
+                        spin_unlock(sb_bgl_lock(EXT4_SB(sb), first_group + i));
                         continue;
                 }
+                spin_unlock(sb_bgl_lock(EXT4_SB(sb), first_group + i));
                 get_bh(bh[i]);
                 bh[i]->b_end_io = end_buffer_read_sync;
                 submit_bh(READ, bh[i]);
@@ -2477,7 +2480,7 @@ err_freesgi:
 int ext4_mb_init(struct super_block *sb, int needs_recovery)
 {
         struct ext4_sb_info *sbi = EXT4_SB(sb);
-        unsigned i;
+        unsigned i, j;
         unsigned offset;
         unsigned max;
         int ret;
@@ -2537,7 +2540,7 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
         sbi->s_mb_history_filter = EXT4_MB_HISTORY_DEFAULT;
         sbi->s_mb_group_prealloc = MB_DEFAULT_GROUP_PREALLOC;
 
-        i = sizeof(struct ext4_locality_group) * NR_CPUS;
+        i = sizeof(struct ext4_locality_group) * nr_cpu_ids;
         sbi->s_locality_groups = kmalloc(i, GFP_KERNEL);
         if (sbi->s_locality_groups == NULL) {
                 clear_opt(sbi->s_mount_opt, MBALLOC);
@@ -2545,11 +2548,12 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
                 kfree(sbi->s_mb_maxs);
                 return -ENOMEM;
         }
-        for (i = 0; i < NR_CPUS; i++) {
+        for (i = 0; i < nr_cpu_ids; i++) {
                 struct ext4_locality_group *lg;
                 lg = &sbi->s_locality_groups[i];
                 mutex_init(&lg->lg_mutex);
-                INIT_LIST_HEAD(&lg->lg_prealloc_list);
+                for (j = 0; j < PREALLOC_TB_SIZE; j++)
+                        INIT_LIST_HEAD(&lg->lg_prealloc_list[j]);
                 spin_lock_init(&lg->lg_prealloc_lock);
         }
 
@@ -3260,6 +3264,7 @@ static void ext4_mb_use_group_pa(struct ext4_allocation_context *ac,
                                 struct ext4_prealloc_space *pa)
 {
         unsigned int len = ac->ac_o_ex.fe_len;
+
         ext4_get_group_no_and_offset(ac->ac_sb, pa->pa_pstart,
                                         &ac->ac_b_ex.fe_group,
                                         &ac->ac_b_ex.fe_start);
@@ -3282,6 +3287,7 @@ static void ext4_mb_use_group_pa(struct ext4_allocation_context *ac,
 static noinline_for_stack int
 ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
 {
+        int order, i;
         struct ext4_inode_info *ei = EXT4_I(ac->ac_inode);
         struct ext4_locality_group *lg;
         struct ext4_prealloc_space *pa;
@@ -3322,22 +3328,29 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
         lg = ac->ac_lg;
         if (lg == NULL)
                 return 0;
-
-        rcu_read_lock();
-        list_for_each_entry_rcu(pa, &lg->lg_prealloc_list, pa_inode_list) {
-                spin_lock(&pa->pa_lock);
-                if (pa->pa_deleted == 0 && pa->pa_free >= ac->ac_o_ex.fe_len) {
-                        atomic_inc(&pa->pa_count);
-                        ext4_mb_use_group_pa(ac, pa);
+        order  = fls(ac->ac_o_ex.fe_len) - 1;
+        if (order > PREALLOC_TB_SIZE - 1)
+                /* The max size of hash table is PREALLOC_TB_SIZE */
+                order = PREALLOC_TB_SIZE - 1;
+
+        for (i = order; i < PREALLOC_TB_SIZE; i++) {
+                rcu_read_lock();
+                list_for_each_entry_rcu(pa, &lg->lg_prealloc_list[i],
+                                        pa_inode_list) {
+                        spin_lock(&pa->pa_lock);
+                        if (pa->pa_deleted == 0 &&
+                                        pa->pa_free >= ac->ac_o_ex.fe_len) {
+                                atomic_inc(&pa->pa_count);
+                                ext4_mb_use_group_pa(ac, pa);
+                                spin_unlock(&pa->pa_lock);
+                                ac->ac_criteria = 20;
+                                rcu_read_unlock();
+                                return 1;
+                        }
                         spin_unlock(&pa->pa_lock);
-                        ac->ac_criteria = 20;
-                        rcu_read_unlock();
-                        return 1;
                 }
-                spin_unlock(&pa->pa_lock);
+                rcu_read_unlock();
         }
-        rcu_read_unlock();
-
         return 0;
 }
 
@@ -3560,6 +3573,7 @@ ext4_mb_new_group_pa(struct ext4_allocation_context *ac)
         pa->pa_free = pa->pa_len;
         atomic_set(&pa->pa_count, 1);
         spin_lock_init(&pa->pa_lock);
+        INIT_LIST_HEAD(&pa->pa_inode_list);
         pa->pa_deleted = 0;
         pa->pa_linear = 1;
 
@@ -3580,10 +3594,10 @@ ext4_mb_new_group_pa(struct ext4_allocation_context *ac)
         list_add(&pa->pa_group_list, &grp->bb_prealloc_list);
         ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
 
-        spin_lock(pa->pa_obj_lock);
-        list_add_tail_rcu(&pa->pa_inode_list, &lg->lg_prealloc_list);
-        spin_unlock(pa->pa_obj_lock);
-
+        /*
+         * We will later add the new pa to the right bucket
+         * after updating the pa_free in ext4_mb_release_context
+         */
         return 0;
 }
 
@@ -3733,20 +3747,23 @@ ext4_mb_discard_group_preallocations(struct super_block *sb,
 
         bitmap_bh = ext4_read_block_bitmap(sb, group);
         if (bitmap_bh == NULL) {
-                /* error handling here */
-                ext4_mb_release_desc(&e4b);
-                BUG_ON(bitmap_bh == NULL);
+                ext4_error(sb, __func__, "Error in reading block "
+                                "bitmap for %lu\n", group);
+                return 0;
         }
 
         err = ext4_mb_load_buddy(sb, group, &e4b);
-        BUG_ON(err != 0); /* error handling here */
+        if (err) {
+                ext4_error(sb, __func__, "Error in loading buddy "
+                                "information for %lu\n", group);
+                put_bh(bitmap_bh);
+                return 0;
+        }
 
         if (needed == 0)
                 needed = EXT4_BLOCKS_PER_GROUP(sb) + 1;
 
-        grp = ext4_get_group_info(sb, group);
         INIT_LIST_HEAD(&list);
-
         ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
 repeat:
         ext4_lock_group(sb, group);
@@ -3903,13 +3920,18 @@ repeat:
                 ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, NULL);
 
                 err = ext4_mb_load_buddy(sb, group, &e4b);
-                BUG_ON(err != 0); /* error handling here */
+                if (err) {
+                        ext4_error(sb, __func__, "Error in loading buddy "
+                                        "information for %lu\n", group);
+                        continue;
+                }
 
                 bitmap_bh = ext4_read_block_bitmap(sb, group);
                 if (bitmap_bh == NULL) {
-                        /* error handling here */
+                        ext4_error(sb, __func__, "Error in reading block "
+                                        "bitmap for %lu\n", group);
                         ext4_mb_release_desc(&e4b);
-                        BUG_ON(bitmap_bh == NULL);
+                        continue;
                 }
 
                 ext4_lock_group(sb, group);
@@ -4112,22 +4134,168 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac,
 
 }
 
+static noinline_for_stack void
+ext4_mb_discard_lg_preallocations(struct super_block *sb,
+                                        struct ext4_locality_group *lg,
+                                        int order, int total_entries)
+{
+        ext4_group_t group = 0;
+        struct ext4_buddy e4b;
+        struct list_head discard_list;
+        struct ext4_prealloc_space *pa, *tmp;
+        struct ext4_allocation_context *ac;
+
+        mb_debug("discard locality group preallocation\n");
+
+        INIT_LIST_HEAD(&discard_list);
+        ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
+
+        spin_lock(&lg->lg_prealloc_lock);
+        list_for_each_entry_rcu(pa, &lg->lg_prealloc_list[order],
+                                                pa_inode_list) {
+                spin_lock(&pa->pa_lock);
+                if (atomic_read(&pa->pa_count)) {
+                        /*
+                         * This is the pa that we just used
+                         * for block allocation. So don't
+                         * free that
+                         */
+                        spin_unlock(&pa->pa_lock);
+                        continue;
+                }
+                if (pa->pa_deleted) {
+                        spin_unlock(&pa->pa_lock);
+                        continue;
+                }
+                /* only lg prealloc space */
+                BUG_ON(!pa->pa_linear);
+
+                /* seems this one can be freed ... */
+                pa->pa_deleted = 1;
+                spin_unlock(&pa->pa_lock);
+
+                list_del_rcu(&pa->pa_inode_list);
+                list_add(&pa->u.pa_tmp_list, &discard_list);
+
+                total_entries--;
+                if (total_entries <= 5) {
+                        /*
+                         * we want to keep only 5 entries
+                         * allowing it to grow to 8. This
+                         * mak sure we don't call discard
+                         * soon for this list.
+                         */
+                        break;
+                }
+        }
+        spin_unlock(&lg->lg_prealloc_lock);
+
+        list_for_each_entry_safe(pa, tmp, &discard_list, u.pa_tmp_list) {
+
+                ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, NULL);
+                if (ext4_mb_load_buddy(sb, group, &e4b)) {
+                        ext4_error(sb, __func__, "Error in loading buddy "
+                                        "information for %lu\n", group);
+                        continue;
+                }
+                ext4_lock_group(sb, group);
+                list_del(&pa->pa_group_list);
+                ext4_mb_release_group_pa(&e4b, pa, ac);
+                ext4_unlock_group(sb, group);
+
+                ext4_mb_release_desc(&e4b);
+                list_del(&pa->u.pa_tmp_list);
+                call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback);
+        }
+        if (ac)
+                kmem_cache_free(ext4_ac_cachep, ac);
+}
+
+/*
+ * We have incremented pa_count. So it cannot be freed at this
+ * point. Also we hold lg_mutex. So no parallel allocation is
+ * possible from this lg. That means pa_free cannot be updated.
+ *
+ * A parallel ext4_mb_discard_group_preallocations is possible.
+ * which can cause the lg_prealloc_list to be updated.
+ */
+
+static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac)
+{
+        int order, added = 0, lg_prealloc_count = 1;
+        struct super_block *sb = ac->ac_sb;
+        struct ext4_locality_group *lg = ac->ac_lg;
+        struct ext4_prealloc_space *tmp_pa, *pa = ac->ac_pa;
+
+        order = fls(pa->pa_free) - 1;
+        if (order > PREALLOC_TB_SIZE - 1)
+                /* The max size of hash table is PREALLOC_TB_SIZE */
+                order = PREALLOC_TB_SIZE - 1;
+        /* Add the prealloc space to lg */
+        rcu_read_lock();
+        list_for_each_entry_rcu(tmp_pa, &lg->lg_prealloc_list[order],
+                                                pa_inode_list) {
+                spin_lock(&tmp_pa->pa_lock);
+                if (tmp_pa->pa_deleted) {
+                        spin_unlock(&pa->pa_lock);
+                        continue;
+                }
+                if (!added && pa->pa_free < tmp_pa->pa_free) {
+                        /* Add to the tail of the previous entry */
+                        list_add_tail_rcu(&pa->pa_inode_list,
+                                                &tmp_pa->pa_inode_list);
+                        added = 1;
+                        /*
+                         * we want to count the total
+                         * number of entries in the list
+                         */
+                }
+                spin_unlock(&tmp_pa->pa_lock);
+                lg_prealloc_count++;
+        }
+        if (!added)
+                list_add_tail_rcu(&pa->pa_inode_list,
+                                        &lg->lg_prealloc_list[order]);
+        rcu_read_unlock();
+
+        /* Now trim the list to be not more than 8 elements */
+        if (lg_prealloc_count > 8) {
+                ext4_mb_discard_lg_preallocations(sb, lg,
+                                                order, lg_prealloc_count);
+                return;
+        }
+        return ;
+}
+
 /*
  * release all resource we used in allocation
  */
 static int ext4_mb_release_context(struct ext4_allocation_context *ac)
 {
-        if (ac->ac_pa) {
-                if (ac->ac_pa->pa_linear) {
+        struct ext4_prealloc_space *pa = ac->ac_pa;
+        if (pa) {
+                if (pa->pa_linear) {
                         /* see comment in ext4_mb_use_group_pa() */
-                        spin_lock(&ac->ac_pa->pa_lock);
-                        ac->ac_pa->pa_pstart += ac->ac_b_ex.fe_len;
-                        ac->ac_pa->pa_lstart += ac->ac_b_ex.fe_len;
-                        ac->ac_pa->pa_free -= ac->ac_b_ex.fe_len;
-                        ac->ac_pa->pa_len -= ac->ac_b_ex.fe_len;
-                        spin_unlock(&ac->ac_pa->pa_lock);
+                        spin_lock(&pa->pa_lock);
+                        pa->pa_pstart += ac->ac_b_ex.fe_len;
+                        pa->pa_lstart += ac->ac_b_ex.fe_len;
+                        pa->pa_free -= ac->ac_b_ex.fe_len;
+                        pa->pa_len -= ac->ac_b_ex.fe_len;
+                        spin_unlock(&pa->pa_lock);
+                        /*
+                         * We want to add the pa to the right bucket.
+                         * Remove it from the list and while adding
+                         * make sure the list to which we are adding
+                         * doesn't grow big.
+                         */
+                        if (likely(pa->pa_free)) {
+                                spin_lock(pa->pa_obj_lock);
+                                list_del_rcu(&pa->pa_inode_list);
+                                spin_unlock(pa->pa_obj_lock);
+                                ext4_mb_add_n_trim(ac);
+                        }
                 }
-                ext4_mb_put_pa(ac, ac->ac_sb, ac->ac_pa);
+                ext4_mb_put_pa(ac, ac->ac_sb, pa);
         }
         if (ac->ac_bitmap_page)
                 page_cache_release(ac->ac_bitmap_page);
@@ -4420,11 +4588,15 @@ do_more:
                 count -= overflow;
         }
         bitmap_bh = ext4_read_block_bitmap(sb, block_group);
-        if (!bitmap_bh)
+        if (!bitmap_bh) {
+                err = -EIO;
                 goto error_return;
+        }
         gdp = ext4_get_group_desc(sb, block_group, &gd_bh);
-        if (!gdp)
+        if (!gdp) {
+                err = -EIO;
                 goto error_return;
+        }
 
         if (in_range(ext4_block_bitmap(sb, gdp), block, count) ||
             in_range(ext4_inode_bitmap(sb, gdp), block, count) ||
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index bfe6add46bcf..c7c9906c2a75 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -164,11 +164,17 @@ struct ext4_free_extent {
  * Locality group:
  *   we try to group all related changes together
  *   so that writeback can flush/allocate them together as well
+ *   Size of lg_prealloc_list hash is determined by MB_DEFAULT_GROUP_PREALLOC
+ *   (512). We store prealloc space into the hash based on the pa_free blocks
+ *   order value.ie, fls(pa_free)-1;
  */
+#define PREALLOC_TB_SIZE 10
 struct ext4_locality_group {
         /* for allocator */
-        struct mutex            lg_mutex;       /* to serialize allocates */
-        struct list_head        lg_prealloc_list;/* list of preallocations */
+        /* to serialize allocates */
+        struct mutex            lg_mutex;
+        /* list of preallocations */
+        struct list_head        lg_prealloc_list[PREALLOC_TB_SIZE];
         spinlock_t              lg_prealloc_lock;
 };
 
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index f000fbe2cd93..0a9265164265 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -73,7 +73,7 @@ static int verify_group_input(struct super_block *sb,
                              "Inode bitmap not in group (block %llu)",
                              (unsigned long long)input->inode_bitmap);
         else if (outside(input->inode_table, start, end) ||
-                 outside(itend - 1, start, end))
+                 outside(itend - 1, start, end))
                 ext4_warning(sb, __func__,
                              "Inode table not in group (blocks %llu-%llu)",
                              (unsigned long long)input->inode_table, itend - 1);
@@ -104,7 +104,7 @@ static int verify_group_input(struct super_block *sb,
                              (unsigned long long)input->inode_bitmap,
                              start, metaend - 1);
         else if (inside(input->inode_table, start, metaend) ||
-                 inside(itend - 1, start, metaend))
+                 inside(itend - 1, start, metaend))
                 ext4_warning(sb, __func__,
                              "Inode table (%llu-%llu) overlaps"
                              "GDT table (%llu-%llu)",
@@ -158,9 +158,9 @@ static int extend_or_restart_transaction(handle_t *handle, int thresh,
         if (err) {
                 if ((err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA)))
                         return err;
-                if ((err = ext4_journal_get_write_access(handle, bh)))
+                if ((err = ext4_journal_get_write_access(handle, bh)))
                         return err;
-        }
+        }
 
         return 0;
 }
@@ -416,11 +416,11 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
                        "EXT4-fs: ext4_add_new_gdb: adding group block %lu\n",
                        gdb_num);
 
-        /*
-         * If we are not using the primary superblock/GDT copy don't resize,
-         * because the user tools have no way of handling this.  Probably a
-         * bad time to do it anyways.
-         */
+        /*
+         * If we are not using the primary superblock/GDT copy don't resize,
+         * because the user tools have no way of handling this.  Probably a
+         * bad time to do it anyways.
+         */
         if (EXT4_SB(sb)->s_sbh->b_blocknr !=
             le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) {
                 ext4_warning(sb, __func__,
@@ -507,14 +507,14 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
         return 0;
 
 exit_inode:
-        //ext4_journal_release_buffer(handle, iloc.bh);
+        /* ext4_journal_release_buffer(handle, iloc.bh); */
         brelse(iloc.bh);
 exit_dindj:
-        //ext4_journal_release_buffer(handle, dind);
+        /* ext4_journal_release_buffer(handle, dind); */
 exit_primary:
-        //ext4_journal_release_buffer(handle, *primary);
+        /* ext4_journal_release_buffer(handle, *primary); */
 exit_sbh:
-        //ext4_journal_release_buffer(handle, *primary);
+        /* ext4_journal_release_buffer(handle, *primary); */
 exit_dind:
         brelse(dind);
 exit_bh:
@@ -818,12 +818,12 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
         if ((err = ext4_journal_get_write_access(handle, sbi->s_sbh)))
                 goto exit_journal;
 
-        /*
-         * We will only either add reserved group blocks to a backup group
-         * or remove reserved blocks for the first group in a new group block.
-         * Doing both would be mean more complex code, and sane people don't
-         * use non-sparse filesystems anymore.  This is already checked above.
-         */
+        /*
+         * We will only either add reserved group blocks to a backup group
+         * or remove reserved blocks for the first group in a new group block.
+         * Doing both would be mean more complex code, and sane people don't
+         * use non-sparse filesystems anymore.  This is already checked above.
+         */
         if (gdb_off) {
                 primary = sbi->s_group_desc[gdb_num];
                 if ((err = ext4_journal_get_write_access(handle, primary)))
@@ -835,24 +835,24 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
         } else if ((err = add_new_gdb(handle, inode, input, &primary)))
                 goto exit_journal;
 
-        /*
-         * OK, now we've set up the new group.  Time to make it active.
-         *
-         * Current kernels don't lock all allocations via lock_super(),
-         * so we have to be safe wrt. concurrent accesses the group
-         * data.  So we need to be careful to set all of the relevant
-         * group descriptor data etc. *before* we enable the group.
-         *
-         * The key field here is sbi->s_groups_count: as long as
-         * that retains its old value, nobody is going to access the new
-         * group.
-         *
-         * So first we update all the descriptor metadata for the new
-         * group; then we update the total disk blocks count; then we
-         * update the groups count to enable the group; then finally we
-         * update the free space counts so that the system can start
-         * using the new disk blocks.
-         */
+        /*
+         * OK, now we've set up the new group.  Time to make it active.
+         *
+         * Current kernels don't lock all allocations via lock_super(),
+         * so we have to be safe wrt. concurrent accesses the group
+         * data.  So we need to be careful to set all of the relevant
+         * group descriptor data etc. *before* we enable the group.
+         *
+         * The key field here is sbi->s_groups_count: as long as
+         * that retains its old value, nobody is going to access the new
+         * group.
+         *
+         * So first we update all the descriptor metadata for the new
+         * group; then we update the total disk blocks count; then we
+         * update the groups count to enable the group; then finally we
+         * update the free space counts so that the system can start
+         * using the new disk blocks.
+         */
 
         /* Update group descriptor block for new group */
         gdp = (struct ext4_group_desc *)((char *)primary->b_data +
@@ -946,7 +946,8 @@ exit_put:
         return err;
 } /* ext4_group_add */
 
-/* Extend the filesystem to the new number of blocks specified.  This entry
+/*
+ * Extend the filesystem to the new number of blocks specified.  This entry
  * point is only used to extend the current filesystem to the end of the last
  * existing group.  It can be accessed via ioctl, or by "remount,resize=<size>"
  * for emergencies (because it has no dependencies on reserved blocks).
@@ -1024,7 +1025,7 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
                              o_blocks_count + add, add);
 
         /* See if the device is actually as big as what was requested */
-        bh = sb_bread(sb, o_blocks_count + add -1);
+        bh = sb_bread(sb, o_blocks_count + add - 1);
         if (!bh) {
                 ext4_warning(sb, __func__,
                              "can't read last block, resize aborted");
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 1cb371dcd609..d5d77958b861 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -49,20 +49,19 @@ static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
                              unsigned long journal_devnum);
 static int ext4_create_journal(struct super_block *, struct ext4_super_block *,
                                unsigned int);
-static void ext4_commit_super (struct super_block * sb,
-                               struct ext4_super_block * es,
-                               int sync);
-static void ext4_mark_recovery_complete(struct super_block * sb,
-                                        struct ext4_super_block * es);
-static void ext4_clear_journal_err(struct super_block * sb,
-                                   struct ext4_super_block * es);
+static void ext4_commit_super(struct super_block *sb,
+                              struct ext4_super_block *es, int sync);
+static void ext4_mark_recovery_complete(struct super_block *sb,
+                                        struct ext4_super_block *es);
+static void ext4_clear_journal_err(struct super_block *sb,
+                                   struct ext4_super_block *es);
 static int ext4_sync_fs(struct super_block *sb, int wait);
-static const char *ext4_decode_error(struct super_block * sb, int errno,
+static const char *ext4_decode_error(struct super_block *sb, int errno,
                                      char nbuf[16]);
-static int ext4_remount (struct super_block * sb, int * flags, char * data);
-static int ext4_statfs (struct dentry * dentry, struct kstatfs * buf);
+static int ext4_remount(struct super_block *sb, int *flags, char *data);
+static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf);
 static void ext4_unlockfs(struct super_block *sb);
-static void ext4_write_super (struct super_block * sb);
+static void ext4_write_super(struct super_block *sb);
 static void ext4_write_super_lockfs(struct super_block *sb);
 
 
@@ -211,15 +210,15 @@ static void ext4_handle_error(struct super_block *sb)
         if (sb->s_flags & MS_RDONLY)
                 return;
 
-        if (!test_opt (sb, ERRORS_CONT)) {
+        if (!test_opt(sb, ERRORS_CONT)) {
                 journal_t *journal = EXT4_SB(sb)->s_journal;
 
                 EXT4_SB(sb)->s_mount_opt |= EXT4_MOUNT_ABORT;
                 if (journal)
                         jbd2_journal_abort(journal, -EIO);
         }
-        if (test_opt (sb, ERRORS_RO)) {
-                printk (KERN_CRIT "Remounting filesystem read-only\n");
+        if (test_opt(sb, ERRORS_RO)) {
+                printk(KERN_CRIT "Remounting filesystem read-only\n");
                 sb->s_flags |= MS_RDONLY;
         }
         ext4_commit_super(sb, es, 1);
@@ -228,13 +227,13 @@ static void ext4_handle_error(struct super_block *sb)
                         sb->s_id);
 }
 
-void ext4_error (struct super_block * sb, const char * function,
-                 const char * fmt, ...)
+void ext4_error(struct super_block *sb, const char *function,
+                const char *fmt, ...)
 {
         va_list args;
 
         va_start(args, fmt);
-        printk(KERN_CRIT "EXT4-fs error (device %s): %s: ",sb->s_id, function);
+        printk(KERN_CRIT "EXT4-fs error (device %s): %s: ", sb->s_id, function);
         vprintk(fmt, args);
         printk("\n");
         va_end(args);
@@ -242,7 +241,7 @@ void ext4_error (struct super_block * sb, const char * function,
         ext4_handle_error(sb);
 }
 
-static const char *ext4_decode_error(struct super_block * sb, int errno,
+static const char *ext4_decode_error(struct super_block *sb, int errno,
                                      char nbuf[16])
 {
         char *errstr = NULL;
@@ -278,8 +277,7 @@ static const char *ext4_decode_error(struct super_block * sb, int errno,
 /* __ext4_std_error decodes expected errors from journaling functions
  * automatically and invokes the appropriate error response.  */
 
-void __ext4_std_error (struct super_block * sb, const char * function,
-                       int errno)
+void __ext4_std_error(struct super_block *sb, const char *function, int errno)
 {
         char nbuf[16];
         const char *errstr;
@@ -292,8 +290,8 @@ void __ext4_std_error (struct super_block * sb, const char * function,
                 return;
 
         errstr = ext4_decode_error(sb, errno, nbuf);
-        printk (KERN_CRIT "EXT4-fs error (device %s) in %s: %s\n",
-                sb->s_id, function, errstr);
+        printk(KERN_CRIT "EXT4-fs error (device %s) in %s: %s\n",
+               sb->s_id, function, errstr);
 
         ext4_handle_error(sb);
 }
@@ -308,15 +306,15 @@ void __ext4_std_error (struct super_block * sb, const char * function,
  * case we take the easy way out and panic immediately.
  */
 
-void ext4_abort (struct super_block * sb, const char * function,
-                 const char * fmt, ...)
+void ext4_abort(struct super_block *sb, const char *function,
+                const char *fmt, ...)
 {
         va_list args;
 
-        printk (KERN_CRIT "ext4_abort called.\n");
+        printk(KERN_CRIT "ext4_abort called.\n");
 
         va_start(args, fmt);
-        printk(KERN_CRIT "EXT4-fs error (device %s): %s: ",sb->s_id, function);
+        printk(KERN_CRIT "EXT4-fs error (device %s): %s: ", sb->s_id, function);
         vprintk(fmt, args);
         printk("\n");
         va_end(args);
@@ -334,8 +332,8 @@ void ext4_abort (struct super_block * sb, const char * function,
         jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
 }
 
-void ext4_warning (struct super_block * sb, const char * function,
-                   const char * fmt, ...)
+void ext4_warning(struct super_block *sb, const char *function,
+                  const char *fmt, ...)
 {
         va_list args;
 
@@ -496,7 +494,7 @@ static void dump_orphan_list(struct super_block *sb, struct ext4_sb_info *sbi)
         }
 }
 
-static void ext4_put_super (struct super_block * sb)
+static void ext4_put_super(struct super_block *sb)
 {
         struct ext4_sb_info *sbi = EXT4_SB(sb);
         struct ext4_super_block *es = sbi->s_es;
@@ -595,7 +593,7 @@ static void ext4_destroy_inode(struct inode *inode)
         kmem_cache_free(ext4_inode_cachep, EXT4_I(inode));
 }
 
-static void init_once(struct kmem_cache *cachep, void *foo)
+static void init_once(void *foo)
 {
         struct ext4_inode_info *ei = (struct ext4_inode_info *) foo;
 
@@ -647,7 +645,8 @@ static void ext4_clear_inode(struct inode *inode)
                                        &EXT4_I(inode)->jinode);
 }
 
-static inline void ext4_show_quota_options(struct seq_file *seq, struct super_block *sb)
+static inline void ext4_show_quota_options(struct seq_file *seq,
+                                           struct super_block *sb)
 {
 #if defined(CONFIG_QUOTA)
         struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -822,8 +821,8 @@ static struct dentry *ext4_fh_to_parent(struct super_block *sb, struct fid *fid,
 }
 
 #ifdef CONFIG_QUOTA
-#define QTYPE2NAME(t) ((t)==USRQUOTA?"user":"group")
-#define QTYPE2MOPT(on, t) ((t)==USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA))
+#define QTYPE2NAME(t) ((t) == USRQUOTA?"user":"group")
+#define QTYPE2MOPT(on, t) ((t) == USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA))
 
 static int ext4_dquot_initialize(struct inode *inode, int type);
 static int ext4_dquot_drop(struct inode *inode);
@@ -991,12 +990,12 @@ static ext4_fsblk_t get_sb_block(void **data)
         return sb_block;
 }
 
-static int parse_options (char *options, struct super_block *sb,
-                          unsigned int *inum, unsigned long *journal_devnum,
-                          ext4_fsblk_t *n_blocks_count, int is_remount)
+static int parse_options(char *options, struct super_block *sb,
+                         unsigned int *inum, unsigned long *journal_devnum,
+                         ext4_fsblk_t *n_blocks_count, int is_remount)
 {
         struct ext4_sb_info *sbi = EXT4_SB(sb);
-        char * p;
+        char *p;
         substring_t args[MAX_OPT_ARGS];
         int data_opt = 0;
         int option;
@@ -1009,7 +1008,7 @@ static int parse_options (char *options, struct super_block *sb,
         if (!options)
                 return 1;
 
-        while ((p = strsep (&options, ",")) != NULL) {
+        while ((p = strsep(&options, ",")) != NULL) {
                 int token;
                 if (!*p)
                         continue;
@@ -1017,16 +1016,16 @@ static int parse_options (char *options, struct super_block *sb,
                 token = match_token(p, tokens, args);
                 switch (token) {
                 case Opt_bsd_df:
-                        clear_opt (sbi->s_mount_opt, MINIX_DF);
+                        clear_opt(sbi->s_mount_opt, MINIX_DF);
                         break;
                 case Opt_minix_df:
-                        set_opt (sbi->s_mount_opt, MINIX_DF);
+                        set_opt(sbi->s_mount_opt, MINIX_DF);
                         break;
                 case Opt_grpid:
-                        set_opt (sbi->s_mount_opt, GRPID);
+                        set_opt(sbi->s_mount_opt, GRPID);
                         break;
                 case Opt_nogrpid:
-                        clear_opt (sbi->s_mount_opt, GRPID);
+                        clear_opt(sbi->s_mount_opt, GRPID);
                         break;
                 case Opt_resuid:
                         if (match_int(&args[0], &option))
@@ -1043,41 +1042,41 @@ static int parse_options (char *options, struct super_block *sb,
                         /* *sb_block = match_int(&args[0]); */
                         break;
                 case Opt_err_panic:
-                        clear_opt (sbi->s_mount_opt, ERRORS_CONT);
-                        clear_opt (sbi->s_mount_opt, ERRORS_RO);
-                        set_opt (sbi->s_mount_opt, ERRORS_PANIC);
+                        clear_opt(sbi->s_mount_opt, ERRORS_CONT);
+                        clear_opt(sbi->s_mount_opt, ERRORS_RO);
+                        set_opt(sbi->s_mount_opt, ERRORS_PANIC);
                         break;
                 case Opt_err_ro:
-                        clear_opt (sbi->s_mount_opt, ERRORS_CONT);
-                        clear_opt (sbi->s_mount_opt, ERRORS_PANIC);
-                        set_opt (sbi->s_mount_opt, ERRORS_RO);
+                        clear_opt(sbi->s_mount_opt, ERRORS_CONT);
+                        clear_opt(sbi->s_mount_opt, ERRORS_PANIC);
+                        set_opt(sbi->s_mount_opt, ERRORS_RO);
                         break;
                 case Opt_err_cont:
-                        clear_opt (sbi->s_mount_opt, ERRORS_RO);
-                        clear_opt (sbi->s_mount_opt, ERRORS_PANIC);
-                        set_opt (sbi->s_mount_opt, ERRORS_CONT);
+                        clear_opt(sbi->s_mount_opt, ERRORS_RO);
+                        clear_opt(sbi->s_mount_opt, ERRORS_PANIC);
+                        set_opt(sbi->s_mount_opt, ERRORS_CONT);
                         break;
                 case Opt_nouid32:
-                        set_opt (sbi->s_mount_opt, NO_UID32);
+                        set_opt(sbi->s_mount_opt, NO_UID32);
                         break;
                 case Opt_nocheck:
-                        clear_opt (sbi->s_mount_opt, CHECK);
+                        clear_opt(sbi->s_mount_opt, CHECK);
                         break;
                 case Opt_debug:
-                        set_opt (sbi->s_mount_opt, DEBUG);
+                        set_opt(sbi->s_mount_opt, DEBUG);
                         break;
                 case Opt_oldalloc:
-                        set_opt (sbi->s_mount_opt, OLDALLOC);
+                        set_opt(sbi->s_mount_opt, OLDALLOC);
                         break;
                 case Opt_orlov:
-                        clear_opt (sbi->s_mount_opt, OLDALLOC);
+                        clear_opt(sbi->s_mount_opt, OLDALLOC);
                         break;
 #ifdef CONFIG_EXT4DEV_FS_XATTR
                 case Opt_user_xattr:
-                        set_opt (sbi->s_mount_opt, XATTR_USER);
+                        set_opt(sbi->s_mount_opt, XATTR_USER);
                         break;
                 case Opt_nouser_xattr:
-                        clear_opt (sbi->s_mount_opt, XATTR_USER);
+                        clear_opt(sbi->s_mount_opt, XATTR_USER);
                         break;
 #else
                 case Opt_user_xattr:
@@ -1115,7 +1114,7 @@ static int parse_options (char *options, struct super_block *sb,
                                        "journal on remount\n");
                                 return 0;
                         }
-                        set_opt (sbi->s_mount_opt, UPDATE_JOURNAL);
+                        set_opt(sbi->s_mount_opt, UPDATE_JOURNAL);
                         break;
                 case Opt_journal_inum:
                         if (is_remount) {
@@ -1145,7 +1144,7 @@ static int parse_options (char *options, struct super_block *sb,
                         set_opt(sbi->s_mount_opt, JOURNAL_CHECKSUM);
                         break;
                 case Opt_noload:
-                        set_opt (sbi->s_mount_opt, NOLOAD);
+                        set_opt(sbi->s_mount_opt, NOLOAD);
                         break;
                 case Opt_commit:
                         if (match_int(&args[0], &option))
@@ -1331,7 +1330,7 @@ set_qf_format:
                                         "on this filesystem, use tune2fs\n");
                                 return 0;
                         }
-                        set_opt (sbi->s_mount_opt, EXTENTS);
+                        set_opt(sbi->s_mount_opt, EXTENTS);
                         break;
                 case Opt_noextents:
                         /*
@@ -1348,7 +1347,7 @@ set_qf_format:
                                                 "-o noextents options\n");
                                 return 0;
                         }
-                        clear_opt (sbi->s_mount_opt, EXTENTS);
+                        clear_opt(sbi->s_mount_opt, EXTENTS);
                         break;
                 case Opt_i_version:
                         set_opt(sbi->s_mount_opt, I_VERSION);
@@ -1374,9 +1373,9 @@ set_qf_format:
                         set_opt(sbi->s_mount_opt, DELALLOC);
                         break;
                 default:
-                        printk (KERN_ERR
-                                "EXT4-fs: Unrecognized mount option \"%s\" "
-                                "or missing value\n", p);
+                        printk(KERN_ERR
+                               "EXT4-fs: Unrecognized mount option \"%s\" "
+                               "or missing value\n", p);
                         return 0;
                 }
         }
@@ -1423,31 +1422,31 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
         int res = 0;
 
         if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) {
-                printk (KERN_ERR "EXT4-fs warning: revision level too high, "
-                        "forcing read-only mode\n");
+                printk(KERN_ERR "EXT4-fs warning: revision level too high, "
+                       "forcing read-only mode\n");
                 res = MS_RDONLY;
         }
         if (read_only)
                 return res;
         if (!(sbi->s_mount_state & EXT4_VALID_FS))
-                printk (KERN_WARNING "EXT4-fs warning: mounting unchecked fs, "
-                        "running e2fsck is recommended\n");
+                printk(KERN_WARNING "EXT4-fs warning: mounting unchecked fs, "
+                       "running e2fsck is recommended\n");
         else if ((sbi->s_mount_state & EXT4_ERROR_FS))
-                printk (KERN_WARNING
-                        "EXT4-fs warning: mounting fs with errors, "
-                        "running e2fsck is recommended\n");
+                printk(KERN_WARNING
+                       "EXT4-fs warning: mounting fs with errors, "
+                       "running e2fsck is recommended\n");
         else if ((__s16) le16_to_cpu(es->s_max_mnt_count) >= 0 &&
                  le16_to_cpu(es->s_mnt_count) >=
                  (unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count))
-                printk (KERN_WARNING
-                        "EXT4-fs warning: maximal mount count reached, "
-                        "running e2fsck is recommended\n");
+                printk(KERN_WARNING
+                       "EXT4-fs warning: maximal mount count reached, "
+                       "running e2fsck is recommended\n");
         else if (le32_to_cpu(es->s_checkinterval) &&
                 (le32_to_cpu(es->s_lastcheck) +
                         le32_to_cpu(es->s_checkinterval) <= get_seconds()))
-                printk (KERN_WARNING
-                        "EXT4-fs warning: checktime reached, "
-                        "running e2fsck is recommended\n");
+                printk(KERN_WARNING
+                       "EXT4-fs warning: checktime reached, "
+                       "running e2fsck is recommended\n");
 #if 0
                 /* @@@ We _will_ want to clear the valid bit if we find
                  * inconsistencies, to force a fsck at reboot.  But for
@@ -1506,14 +1505,13 @@ static int ext4_fill_flex_info(struct super_block *sb)
 
         flex_group_count = (sbi->s_groups_count + groups_per_flex - 1) /
                 groups_per_flex;
-        sbi->s_flex_groups = kmalloc(flex_group_count *
+        sbi->s_flex_groups = kzalloc(flex_group_count *
                                      sizeof(struct flex_groups), GFP_KERNEL);
         if (sbi->s_flex_groups == NULL) {
-                printk(KERN_ERR "EXT4-fs: not enough memory\n");
+                printk(KERN_ERR "EXT4-fs: not enough memory for "
+                                "%lu flex groups\n", flex_group_count);
                 goto failed;
         }
-        memset(sbi->s_flex_groups, 0, flex_group_count *
-               sizeof(struct flex_groups));
 
         gdp = ext4_get_group_desc(sb, 1, &bh);
         block_bitmap = ext4_block_bitmap(sb, gdp) - 1;
@@ -1597,16 +1595,14 @@ static int ext4_check_descriptors(struct super_block *sb)
                                 (EXT4_BLOCKS_PER_GROUP(sb) - 1);
 
                 block_bitmap = ext4_block_bitmap(sb, gdp);
-                if (block_bitmap < first_block || block_bitmap > last_block)
-                {
+                if (block_bitmap < first_block || block_bitmap > last_block) {
                         printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
                                "Block bitmap for group %lu not in group "
                                "(block %llu)!", i, block_bitmap);
                         return 0;
                 }
                 inode_bitmap = ext4_inode_bitmap(sb, gdp);
-                if (inode_bitmap < first_block || inode_bitmap > last_block)
-                {
+                if (inode_bitmap < first_block || inode_bitmap > last_block) {
                         printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
                                "Inode bitmap for group %lu not in group "
                                "(block %llu)!", i, inode_bitmap);
@@ -1614,26 +1610,28 @@ static int ext4_check_descriptors(struct super_block *sb)
                 }
                 inode_table = ext4_inode_table(sb, gdp);
                 if (inode_table < first_block ||
-                    inode_table + sbi->s_itb_per_group - 1 > last_block)
-                {
+                    inode_table + sbi->s_itb_per_group - 1 > last_block) {
                         printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
                                "Inode table for group %lu not in group "
                                "(block %llu)!", i, inode_table);
                         return 0;
                 }
+                spin_lock(sb_bgl_lock(sbi, i));
                 if (!ext4_group_desc_csum_verify(sbi, i, gdp)) {
                         printk(KERN_ERR "EXT4-fs: ext4_check_descriptors: "
                                "Checksum for group %lu failed (%u!=%u)\n",
                                i, le16_to_cpu(ext4_group_desc_csum(sbi, i,
                                gdp)), le16_to_cpu(gdp->bg_checksum));
-                        return 0;
+                        if (!(sb->s_flags & MS_RDONLY))
+                                return 0;
                 }
+                spin_unlock(sb_bgl_lock(sbi, i));
                 if (!flexbg_flag)
                         first_block += EXT4_BLOCKS_PER_GROUP(sb);
         }
 
         ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb));
-        sbi->s_es->s_free_inodes_count=cpu_to_le32(ext4_count_free_inodes(sb));
+        sbi->s_es->s_free_inodes_count = cpu_to_le32(ext4_count_free_inodes(sb));
         return 1;
 }
 
@@ -1654,8 +1652,8 @@ static int ext4_check_descriptors(struct super_block *sb)
  * e2fsck was run on this filesystem, and it must have already done the orphan
  * inode cleanup for us, so we can safely abort without any further action.
  */
-static void ext4_orphan_cleanup (struct super_block * sb,
-                                 struct ext4_super_block * es)
+static void ext4_orphan_cleanup(struct super_block *sb,
+                                struct ext4_super_block *es)
 {
         unsigned int s_flags = sb->s_flags;
         int nr_orphans = 0, nr_truncates = 0;
@@ -1732,7 +1730,7 @@ static void ext4_orphan_cleanup (struct super_block * sb,
                 iput(inode);  /* The delete magic happens here! */
         }
 
-#define PLURAL(x) (x), ((x)==1) ? "" : "s"
+#define PLURAL(x) (x), ((x) == 1) ? "" : "s"
 
         if (nr_orphans)
                 printk(KERN_INFO "EXT4-fs: %s: %d orphan inode%s deleted\n",
@@ -1899,12 +1897,12 @@ static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi)
         return 0;
 }
 
-static int ext4_fill_super (struct super_block *sb, void *data, int silent)
+static int ext4_fill_super(struct super_block *sb, void *data, int silent)
                                 __releases(kernel_lock)
                                 __acquires(kernel_lock)
 
 {
-        struct buffer_head * bh;
+        struct buffer_head *bh;
         struct ext4_super_block *es = NULL;
         struct ext4_sb_info *sbi;
         ext4_fsblk_t block;
@@ -1953,7 +1951,7 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
         }
 
         if (!(bh = sb_bread(sb, logical_sb_block))) {
-                printk (KERN_ERR "EXT4-fs: unable to read superblock\n");
+                printk(KERN_ERR "EXT4-fs: unable to read superblock\n");
                 goto out_fail;
         }
         /*
@@ -2026,8 +2024,8 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
         set_opt(sbi->s_mount_opt, DELALLOC);
 
 
-        if (!parse_options ((char *) data, sb, &journal_inum, &journal_devnum,
-                            NULL, 0))
+        if (!parse_options((char *) data, sb, &journal_inum, &journal_devnum,
+                           NULL, 0))
                 goto failed_mount;
 
         sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
@@ -2102,7 +2100,7 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
                         goto failed_mount;
                 }
 
-                brelse (bh);
+                brelse(bh);
                 logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE;
                 offset = do_div(logical_sb_block, blocksize);
                 bh = sb_bread(sb, logical_sb_block);
@@ -2114,8 +2112,8 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
                 es = (struct ext4_super_block *)(((char *)bh->b_data) + offset);
                 sbi->s_es = es;
                 if (es->s_magic != cpu_to_le16(EXT4_SUPER_MAGIC)) {
-                        printk (KERN_ERR
-                                "EXT4-fs: Magic mismatch, very weird !\n");
+                        printk(KERN_ERR
+                               "EXT4-fs: Magic mismatch, very weird !\n");
                         goto failed_mount;
                 }
         }
@@ -2132,9 +2130,9 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
                 if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) ||
                     (!is_power_of_2(sbi->s_inode_size)) ||
                     (sbi->s_inode_size > blocksize)) {
-                        printk (KERN_ERR
-                                "EXT4-fs: unsupported inode size: %d\n",
-                                sbi->s_inode_size);
+                        printk(KERN_ERR
+                               "EXT4-fs: unsupported inode size: %d\n",
+                               sbi->s_inode_size);
                         goto failed_mount;
                 }
                 if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE)
@@ -2166,20 +2164,20 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
         sbi->s_mount_state = le16_to_cpu(es->s_state);
         sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb));
         sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb));
-        for (i=0; i < 4; i++)
+        for (i = 0; i < 4; i++)
                 sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
         sbi->s_def_hash_version = es->s_def_hash_version;
 
         if (sbi->s_blocks_per_group > blocksize * 8) {
-                printk (KERN_ERR
-                        "EXT4-fs: #blocks per group too big: %lu\n",
-                        sbi->s_blocks_per_group);
+                printk(KERN_ERR
+                       "EXT4-fs: #blocks per group too big: %lu\n",
+                       sbi->s_blocks_per_group);
                 goto failed_mount;
         }
         if (sbi->s_inodes_per_group > blocksize * 8) {
-                printk (KERN_ERR
-                        "EXT4-fs: #inodes per group too big: %lu\n",
-                        sbi->s_inodes_per_group);
+                printk(KERN_ERR
+                       "EXT4-fs: #inodes per group too big: %lu\n",
+                       sbi->s_inodes_per_group);
                 goto failed_mount;
         }
 
@@ -2213,10 +2211,10 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
         sbi->s_groups_count = blocks_count;
         db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
                    EXT4_DESC_PER_BLOCK(sb);
-        sbi->s_group_desc = kmalloc(db_count * sizeof (struct buffer_head *),
+        sbi->s_group_desc = kmalloc(db_count * sizeof(struct buffer_head *),
                                     GFP_KERNEL);
         if (sbi->s_group_desc == NULL) {
-                printk (KERN_ERR "EXT4-fs: not enough memory\n");
+                printk(KERN_ERR "EXT4-fs: not enough memory\n");
                 goto failed_mount;
         }
 
@@ -2226,13 +2224,13 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
                 block = descriptor_loc(sb, logical_sb_block, i);
                 sbi->s_group_desc[i] = sb_bread(sb, block);
                 if (!sbi->s_group_desc[i]) {
-                        printk (KERN_ERR "EXT4-fs: "
-                                "can't read group descriptor %d\n", i);
+                        printk(KERN_ERR "EXT4-fs: "
+                               "can't read group descriptor %d\n", i);
                         db_count = i;
                         goto failed_mount2;
                 }
         }
-        if (!ext4_check_descriptors (sb)) {
+        if (!ext4_check_descriptors(sb)) {
                 printk(KERN_ERR "EXT4-fs: group descriptors corrupted!\n");
                 goto failed_mount2;
         }
@@ -2308,11 +2306,11 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
                     EXT4_SB(sb)->s_journal->j_failed_commit) {
                         printk(KERN_CRIT "EXT4-fs error (device %s): "
                                "ext4_fill_super: Journal transaction "
-                               "%u is corrupt\n", sb->s_id, 
+                               "%u is corrupt\n", sb->s_id,
                                EXT4_SB(sb)->s_journal->j_failed_commit);
-                        if (test_opt (sb, ERRORS_RO)) {
-                                printk (KERN_CRIT
-                                        "Mounting filesystem read-only\n");
+                        if (test_opt(sb, ERRORS_RO)) {
+                                printk(KERN_CRIT
+                                       "Mounting filesystem read-only\n");
                                 sb->s_flags |= MS_RDONLY;
                                 EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
                                 es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
@@ -2332,9 +2330,9 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
                         goto failed_mount3;
         } else {
                 if (!silent)
-                        printk (KERN_ERR
-                                "ext4: No journal on filesystem on %s\n",
-                                sb->s_id);
+                        printk(KERN_ERR
+                               "ext4: No journal on filesystem on %s\n",
+                               sb->s_id);
                 goto failed_mount3;
         }
 
@@ -2418,7 +2416,7 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
                 goto failed_mount4;
         }
 
-        ext4_setup_super (sb, es, sb->s_flags & MS_RDONLY);
+        ext4_setup_super(sb, es, sb->s_flags & MS_RDONLY);
 
         /* determine the minimum size of new large inodes, if present */
         if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) {
@@ -2457,12 +2455,12 @@ static int ext4_fill_super (struct super_block *sb, void *data, int silent)
         ext4_orphan_cleanup(sb, es);
         EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS;
         if (needs_recovery)
-                printk (KERN_INFO "EXT4-fs: recovery complete.\n");
+                printk(KERN_INFO "EXT4-fs: recovery complete.\n");
         ext4_mark_recovery_complete(sb, es);
-        printk (KERN_INFO "EXT4-fs: mounted filesystem with %s data mode.\n",
-                test_opt(sb,DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ? "journal":
-                test_opt(sb,DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA ? "ordered":
-                "writeback");
+        printk(KERN_INFO "EXT4-fs: mounted filesystem with %s data mode.\n",
+               test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ? "journal":
+               test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA ? "ordered":
+               "writeback");
 
         if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
                 printk(KERN_WARNING "EXT4-fs: Ignoring delalloc option - "
@@ -2575,14 +2573,14 @@ static journal_t *ext4_get_journal(struct super_block *sb,
 static journal_t *ext4_get_dev_journal(struct super_block *sb,
                                        dev_t j_dev)
 {
-        struct buffer_head * bh;
+        struct buffer_head *bh;
         journal_t *journal;
         ext4_fsblk_t start;
         ext4_fsblk_t len;
         int hblock, blocksize;
         ext4_fsblk_t sb_block;
         unsigned long offset;
-        struct ext4_super_block * es;
+        struct ext4_super_block *es;
         struct block_device *bdev;
 
         bdev = ext4_blkdev_get(j_dev);
@@ -2697,8 +2695,8 @@ static int ext4_load_journal(struct super_block *sb,
                                         "unavailable, cannot proceed.\n");
                                 return -EROFS;
                         }
-                        printk (KERN_INFO "EXT4-fs: write access will "
-                                        "be enabled during recovery.\n");
+                        printk(KERN_INFO "EXT4-fs: write access will "
+                               "be enabled during recovery.\n");
                 }
         }
 
@@ -2751,8 +2749,8 @@ static int ext4_load_journal(struct super_block *sb,
         return 0;
 }
 
-static int ext4_create_journal(struct super_block * sb,
-                               struct ext4_super_block * es,
+static int ext4_create_journal(struct super_block *sb,
+                               struct ext4_super_block *es,
                                unsigned int journal_inum)
 {
         journal_t *journal;
@@ -2793,9 +2791,8 @@ static int ext4_create_journal(struct super_block * sb,
         return 0;
 }
 
-static void ext4_commit_super (struct super_block * sb,
-                               struct ext4_super_block * es,
-                               int sync)
+static void ext4_commit_super(struct super_block *sb,
+                              struct ext4_super_block *es, int sync)
 {
         struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
 
@@ -2816,8 +2813,8 @@ static void ext4_commit_super (struct super_block * sb,
  * remounting) the filesystem readonly, then we will end up with a
  * consistent fs on disk.  Record that fact.
  */
-static void ext4_mark_recovery_complete(struct super_block * sb,
-                                        struct ext4_super_block * es)
+static void ext4_mark_recovery_complete(struct super_block *sb,
+                                        struct ext4_super_block *es)
 {
         journal_t *journal = EXT4_SB(sb)->s_journal;
 
@@ -2839,8 +2836,8 @@ static void ext4_mark_recovery_complete(struct super_block * sb,
  * has recorded an error from a previous lifetime, move that error to the
  * main filesystem now.
  */
-static void ext4_clear_journal_err(struct super_block * sb,
-                                   struct ext4_super_block * es)
+static void ext4_clear_journal_err(struct super_block *sb,
+                                   struct ext4_super_block *es)
 {
         journal_t *journal;
         int j_errno;
@@ -2865,7 +2862,7 @@ static void ext4_clear_journal_err(struct super_block * sb,
 
                 EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
                 es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
-                ext4_commit_super (sb, es, 1);
+                ext4_commit_super(sb, es, 1);
 
                 jbd2_journal_clear_err(journal);
         }
@@ -2898,7 +2895,7 @@ int ext4_force_commit(struct super_block *sb)
  * This implicitly triggers the writebehind on sync().
  */
 
-static void ext4_write_super (struct super_block * sb)
+static void ext4_write_super(struct super_block *sb)
 {
         if (mutex_trylock(&sb->s_lock) != 0)
                 BUG();
@@ -2954,13 +2951,14 @@ static void ext4_unlockfs(struct super_block *sb)
         }
 }
 
-static int ext4_remount (struct super_block * sb, int * flags, char * data)
+static int ext4_remount(struct super_block *sb, int *flags, char *data)
 {
-        struct ext4_super_block * es;
+        struct ext4_super_block *es;
         struct ext4_sb_info *sbi = EXT4_SB(sb);
         ext4_fsblk_t n_blocks_count = 0;
         unsigned long old_sb_flags;
         struct ext4_mount_options old_opts;
+        ext4_group_t g;
         int err;
 #ifdef CONFIG_QUOTA
         int i;
@@ -3039,6 +3037,26 @@ static int ext4_remount (struct super_block * sb, int * flags, char * data)
                         }
 
                         /*
+                         * Make sure the group descriptor checksums
+                         * are sane.  If they aren't, refuse to
+                         * remount r/w.
+                         */
+                        for (g = 0; g < sbi->s_groups_count; g++) {
+                                struct ext4_group_desc *gdp =
+                                        ext4_get_group_desc(sb, g, NULL);
+
+                                if (!ext4_group_desc_csum_verify(sbi, g, gdp)) {
+                                        printk(KERN_ERR
+               "EXT4-fs: ext4_remount: "
+                "Checksum for group %lu failed (%u!=%u)\n",
+                g, le16_to_cpu(ext4_group_desc_csum(sbi, g, gdp)),
+                                               le16_to_cpu(gdp->bg_checksum));
+                                        err = -EINVAL;
+                                        goto restore_opts;
+                                }
+                        }
+
+                        /*
                          * If we have an unprocessed orphan list hanging
                          * around from a previously readonly bdev mount,
                          * require a full umount/remount for now.
@@ -3063,7 +3081,7 @@ static int ext4_remount (struct super_block * sb, int * flags, char * data)
                         sbi->s_mount_state = le16_to_cpu(es->s_state);
                         if ((err = ext4_group_extend(sb, es, n_blocks_count)))
                                 goto restore_opts;
-                        if (!ext4_setup_super (sb, es, 0))
+                        if (!ext4_setup_super(sb, es, 0))
                                 sb->s_flags &= ~MS_RDONLY;
                 }
         }
@@ -3093,7 +3111,7 @@ restore_opts:
         return err;
 }
 
-static int ext4_statfs (struct dentry * dentry, struct kstatfs * buf)
+static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
         struct super_block *sb = dentry->d_sb;
         struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -3331,12 +3349,12 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
         }
         /* Journaling quota? */
         if (EXT4_SB(sb)->s_qf_names[type]) {
-                /* Quotafile not of fs root? */
+                /* Quotafile not in fs root? */
                 if (nd.path.dentry->d_parent->d_inode != sb->s_root->d_inode)
                         printk(KERN_WARNING
                                 "EXT4-fs: Quota file not on filesystem root. "
                                 "Journaled quota will not work.\n");
-        }
+        }
 
         /*
          * When we journal data on quota file, we have to flush journal to see
@@ -3352,8 +3370,9 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
                 jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
         }
 
+        err = vfs_quota_on_path(sb, type, format_id, &nd.path);
         path_put(&nd.path);
-        return vfs_quota_on(sb, type, format_id, path, remount);
+        return err;
 }
 
 /* Read data from quotafile - avoid pagecache and such because we cannot afford
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 93c5fdcdad2e..8954208b4893 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1512,7 +1512,7 @@ static inline void ext4_xattr_hash_entry(struct ext4_xattr_header *header,
         char *name = entry->e_name;
         int n;
 
-        for (n=0; n < entry->e_name_len; n++) {
+        for (n = 0; n < entry->e_name_len; n++) {
                 hash = (hash << NAME_HASH_SHIFT) ^
                        (hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^
                        *name++;
diff --git a/fs/fat/cache.c b/fs/fat/cache.c
index 3a9ecac8d61f..3222f51c41cf 100644
--- a/fs/fat/cache.c
+++ b/fs/fat/cache.c
@@ -36,7 +36,7 @@ static inline int fat_max_cache(struct inode *inode)
 
 static struct kmem_cache *fat_cache_cachep;
 
-static void init_once(struct kmem_cache *cachep, void *foo)
+static void init_once(void *foo)
 {
         struct fat_cache *cache = (struct fat_cache *)foo;
 
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 34541d06e626..cd4a0162e10d 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -17,7 +17,6 @@
 #include <linux/slab.h>
 #include <linux/time.h>
 #include <linux/msdos_fs.h>
-#include <linux/dirent.h>
 #include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
 #include <linux/compat.h>
@@ -124,10 +123,11 @@ static inline int fat_get_entry(struct inode *dir, loff_t *pos,
  * but ignore that right now.
  * Ahem... Stack smashing in ring 0 isn't fun. Fixed.
  */
-static int uni16_to_x8(unsigned char *ascii, wchar_t *uni, int len,
+static int uni16_to_x8(unsigned char *ascii, const wchar_t *uni, int len,
                        int uni_xlate, struct nls_table *nls)
 {
-        wchar_t *ip, ec;
+        const wchar_t *ip;
+        wchar_t ec;
         unsigned char *op, nc;
         int charlen;
         int k;
@@ -167,6 +167,16 @@ static int uni16_to_x8(unsigned char *ascii, wchar_t *uni, int len,
         return (op - ascii);
 }
 
+static inline int fat_uni_to_x8(struct msdos_sb_info *sbi, const wchar_t *uni,
+                                unsigned char *buf, int size)
+{
+        if (sbi->options.utf8)
+                return utf8_wcstombs(buf, uni, size);
+        else
+                return uni16_to_x8(buf, uni, size, sbi->options.unicode_xlate,
+                                   sbi->nls_io);
+}
+
 static inline int
 fat_short2uni(struct nls_table *t, unsigned char *c, int clen, wchar_t *uni)
 {
@@ -227,6 +237,19 @@ fat_shortname2uni(struct nls_table *nls, unsigned char *buf, int buf_size,
         return len;
 }
 
+static inline int fat_name_match(struct msdos_sb_info *sbi,
+                                 const unsigned char *a, int a_len,
+                                 const unsigned char *b, int b_len)
+{
+        if (a_len != b_len)
+                return 0;
+
+        if (sbi->options.name_check != 's')
+                return !nls_strnicmp(sbi->nls_io, a, b, a_len);
+        else
+                return !memcmp(a, b, a_len);
+}
+
 enum { PARSE_INVALID = 1, PARSE_NOT_LONGNAME, PARSE_EOF, };
 
 /**
@@ -302,6 +325,19 @@ parse_long:
 }
 
 /*
+ * Maximum buffer size of short name.
+ * [(MSDOS_NAME + '.') * max one char + nul]
+ * For msdos style, ['.' (hidden) + MSDOS_NAME + '.' + nul]
+ */
+#define FAT_MAX_SHORT_SIZE      ((MSDOS_NAME + 1) * NLS_MAX_CHARSET_SIZE + 1)
+/*
+ * Maximum buffer size of unicode chars from slots.
+ * [(max longname slots * 13 (size in a slot) + nul) * sizeof(wchar_t)]
+ */
+#define FAT_MAX_UNI_CHARS       ((MSDOS_SLOTS - 1) * 13 + 1)
+#define FAT_MAX_UNI_SIZE        (FAT_MAX_UNI_CHARS * sizeof(wchar_t))
+
+/*
  * Return values: negative -> error, 0 -> not found, positive -> found,
  * value is the total amount of slots, including the shortname entry.
  */
@@ -312,29 +348,20 @@ int fat_search_long(struct inode *inode, const unsigned char *name,
         struct msdos_sb_info *sbi = MSDOS_SB(sb);
         struct buffer_head *bh = NULL;
         struct msdos_dir_entry *de;
-        struct nls_table *nls_io = sbi->nls_io;
         struct nls_table *nls_disk = sbi->nls_disk;
-        wchar_t bufuname[14];
         unsigned char nr_slots;
-        int xlate_len;
+        wchar_t bufuname[14];
         wchar_t *unicode = NULL;
         unsigned char work[MSDOS_NAME];
-        unsigned char *bufname = NULL;
-        int uni_xlate = sbi->options.unicode_xlate;
-        int utf8 = sbi->options.utf8;
-        int anycase = (sbi->options.name_check != 's');
+        unsigned char bufname[FAT_MAX_SHORT_SIZE];
         unsigned short opt_shortname = sbi->options.shortname;
         loff_t cpos = 0;
-        int chl, i, j, last_u, err;
-
-        bufname = __getname();
-        if (!bufname)
-                return -ENOMEM;
+        int chl, i, j, last_u, err, len;
 
         err = -ENOENT;
-        while(1) {
+        while (1) {
                 if (fat_get_entry(inode, &cpos, &bh, &de) == -1)
-                        goto EODir;
+                        goto end_of_dir;
 parse_record:
                 nr_slots = 0;
                 if (de->name[0] == DELETED_FLAG)
@@ -353,7 +380,7 @@ parse_record:
                         else if (status == PARSE_NOT_LONGNAME)
                                 goto parse_record;
                         else if (status == PARSE_EOF)
-                                goto EODir;
+                                goto end_of_dir;
                 }
 
                 memcpy(work, de->name, sizeof(de->name));
@@ -394,30 +421,24 @@ parse_record:
                 if (!last_u)
                         continue;
 
+                /* Compare shortname */
                 bufuname[last_u] = 0x0000;
-                xlate_len = utf8
-                        ?utf8_wcstombs(bufname, bufuname, PATH_MAX)
-                        :uni16_to_x8(bufname, bufuname, PATH_MAX, uni_xlate, nls_io);
-                if (xlate_len == name_len)
-                        if ((!anycase && !memcmp(name, bufname, xlate_len)) ||
-                            (anycase && !nls_strnicmp(nls_io, name, bufname,
-                                                                xlate_len)))
-                                goto Found;
+                len = fat_uni_to_x8(sbi, bufuname, bufname, sizeof(bufname));
+                if (fat_name_match(sbi, name, name_len, bufname, len))
+                        goto found;
 
                 if (nr_slots) {
-                        xlate_len = utf8
-                                ?utf8_wcstombs(bufname, unicode, PATH_MAX)
-                                :uni16_to_x8(bufname, unicode, PATH_MAX, uni_xlate, nls_io);
-                        if (xlate_len != name_len)
-                                continue;
-                        if ((!anycase && !memcmp(name, bufname, xlate_len)) ||
-                            (anycase && !nls_strnicmp(nls_io, name, bufname,
-                                                                xlate_len)))
-                                goto Found;
+                        void *longname = unicode + FAT_MAX_UNI_CHARS;
+                        int size = PATH_MAX - FAT_MAX_UNI_SIZE;
+
+                        /* Compare longname */
+                        len = fat_uni_to_x8(sbi, unicode, longname, size);
+                        if (fat_name_match(sbi, name, name_len, longname, len))
+                                goto found;
                 }
         }
 
-Found:
+found:
         nr_slots++;     /* include the de */
         sinfo->slot_off = cpos - nr_slots * sizeof(*de);
         sinfo->nr_slots = nr_slots;
@@ -425,9 +446,7 @@ Found:
         sinfo->bh = bh;
         sinfo->i_pos = fat_make_i_pos(sb, sinfo->bh, sinfo->de);
         err = 0;
-EODir:
-        if (bufname)
-                __putname(bufname);
+end_of_dir:
         if (unicode)
                 __putname(unicode);
 
@@ -453,23 +472,20 @@ static int __fat_readdir(struct inode *inode, struct file *filp, void *dirent,
         struct msdos_sb_info *sbi = MSDOS_SB(sb);
         struct buffer_head *bh;
         struct msdos_dir_entry *de;
-        struct nls_table *nls_io = sbi->nls_io;
         struct nls_table *nls_disk = sbi->nls_disk;
-        unsigned char long_slots;
-        const char *fill_name;
-        int fill_len;
+        unsigned char nr_slots;
         wchar_t bufuname[14];
         wchar_t *unicode = NULL;
-        unsigned char c, work[MSDOS_NAME], bufname[56], *ptname = bufname;
-        unsigned long lpos, dummy, *furrfu = &lpos;
-        int uni_xlate = sbi->options.unicode_xlate;
+        unsigned char c, work[MSDOS_NAME];
+        unsigned char bufname[FAT_MAX_SHORT_SIZE], *ptname = bufname;
+        unsigned short opt_shortname = sbi->options.shortname;
         int isvfat = sbi->options.isvfat;
-        int utf8 = sbi->options.utf8;
         int nocase = sbi->options.nocase;
-        unsigned short opt_shortname = sbi->options.shortname;
+        const char *fill_name = NULL;
         unsigned long inum;
-        int chi, chl, i, i2, j, last, last_u, dotoffset = 0;
+        unsigned long lpos, dummy, *furrfu = &lpos;
         loff_t cpos;
+        int chi, chl, i, i2, j, last, last_u, dotoffset = 0, fill_len = 0;
         int ret = 0;
 
         lock_super(sb);
@@ -489,43 +505,58 @@ static int __fat_readdir(struct inode *inode, struct file *filp, void *dirent,
                         cpos = 0;
                 }
         }
-        if (cpos & (sizeof(struct msdos_dir_entry)-1)) {
+        if (cpos & (sizeof(struct msdos_dir_entry) - 1)) {
                 ret = -ENOENT;
                 goto out;
         }
 
         bh = NULL;
-GetNew:
+get_new:
         if (fat_get_entry(inode, &cpos, &bh, &de) == -1)
-                goto EODir;
+                goto end_of_dir;
 parse_record:
-        long_slots = 0;
-        /* Check for long filename entry */
-        if (isvfat) {
+        nr_slots = 0;
+        /*
+         * Check for long filename entry, but if short_only, we don't
+         * need to parse long filename.
+         */
+        if (isvfat && !short_only) {
                 if (de->name[0] == DELETED_FLAG)
-                        goto RecEnd;
+                        goto record_end;
                 if (de->attr != ATTR_EXT && (de->attr & ATTR_VOLUME))
-                        goto RecEnd;
+                        goto record_end;
                 if (de->attr != ATTR_EXT && IS_FREE(de->name))
-                        goto RecEnd;
+                        goto record_end;
         } else {
                 if ((de->attr & ATTR_VOLUME) || IS_FREE(de->name))
-                        goto RecEnd;
+                        goto record_end;
         }
 
         if (isvfat && de->attr == ATTR_EXT) {
                 int status = fat_parse_long(inode, &cpos, &bh, &de,
-                                            &unicode, &long_slots);
+                                            &unicode, &nr_slots);
                 if (status < 0) {
                         filp->f_pos = cpos;
                         ret = status;
                         goto out;
                 } else if (status == PARSE_INVALID)
-                        goto RecEnd;
+                        goto record_end;
                 else if (status == PARSE_NOT_LONGNAME)
                         goto parse_record;
                 else if (status == PARSE_EOF)
-                        goto EODir;
+                        goto end_of_dir;
+
+                if (nr_slots) {
+                        void *longname = unicode + FAT_MAX_UNI_CHARS;
+                        int size = PATH_MAX - FAT_MAX_UNI_SIZE;
+                        int len = fat_uni_to_x8(sbi, unicode, longname, size);
+
+                        fill_name = longname;
+                        fill_len = len;
+                        /* !both && !short_only, so we don't need shortname. */
+                        if (!both)
+                                goto start_filldir;
+                }
         }
 
         if (sbi->options.dotsOK) {
@@ -587,12 +618,32 @@ parse_record:
                 }
         }
         if (!last)
-                goto RecEnd;
+                goto record_end;
 
         i = last + dotoffset;
         j = last_u;
 
-        lpos = cpos - (long_slots+1)*sizeof(struct msdos_dir_entry);
+        if (isvfat) {
+                bufuname[j] = 0x0000;
+                i = fat_uni_to_x8(sbi, bufuname, bufname, sizeof(bufname));
+        }
+        if (nr_slots) {
+                /* hack for fat_ioctl_filldir() */
+                struct fat_ioctl_filldir_callback *p = dirent;
+
+                p->longname = fill_name;
+                p->long_len = fill_len;
+                p->shortname = bufname;
+                p->short_len = i;
+                fill_name = NULL;
+                fill_len = 0;
+        } else {
+                fill_name = bufname;
+                fill_len = i;
+        }
+
+start_filldir:
+        lpos = cpos - (nr_slots + 1) * sizeof(struct msdos_dir_entry);
         if (!memcmp(de->name, MSDOS_DOT, MSDOS_NAME))
                 inum = inode->i_ino;
         else if (!memcmp(de->name, MSDOS_DOTDOT, MSDOS_NAME)) {
@@ -607,49 +658,17 @@ parse_record:
                         inum = iunique(sb, MSDOS_ROOT_INO);
         }
 
-        if (isvfat) {
-                bufuname[j] = 0x0000;
-                i = utf8 ? utf8_wcstombs(bufname, bufuname, sizeof(bufname))
-                         : uni16_to_x8(bufname, bufuname, sizeof(bufname), uni_xlate, nls_io);
-        }
-
-        fill_name = bufname;
-        fill_len = i;
-        if (!short_only && long_slots) {
-                /* convert the unicode long name. 261 is maximum size
-                 * of unicode buffer. (13 * slots + nul) */
-                void *longname = unicode + 261;
-                int buf_size = PATH_MAX - (261 * sizeof(unicode[0]));
-                int long_len = utf8
-                        ? utf8_wcstombs(longname, unicode, buf_size)
-                        : uni16_to_x8(longname, unicode, buf_size, uni_xlate, nls_io);
-
-                if (!both) {
-                        fill_name = longname;
-                        fill_len = long_len;
-                } else {
-                        /* hack for fat_ioctl_filldir() */
-                        struct fat_ioctl_filldir_callback *p = dirent;
-
-                        p->longname = longname;
-                        p->long_len = long_len;
-                        p->shortname = bufname;
-                        p->short_len = i;
-                        fill_name = NULL;
-                        fill_len = 0;
-                }
-        }
         if (filldir(dirent, fill_name, fill_len, *furrfu, inum,
                     (de->attr & ATTR_DIR) ? DT_DIR : DT_REG) < 0)
-                goto FillFailed;
+                goto fill_failed;
 
-RecEnd:
+record_end:
         furrfu = &lpos;
         filp->f_pos = cpos;
-        goto GetNew;
-EODir:
+        goto get_new;
+end_of_dir:
         filp->f_pos = cpos;
-FillFailed:
+fill_failed:
         brelse(bh);
         if (unicode)
                 __putname(unicode);
@@ -715,7 +734,7 @@ efault:									   \
         return -EFAULT;                                                    \
 }
 
-FAT_IOCTL_FILLDIR_FUNC(fat_ioctl_filldir, dirent)
+FAT_IOCTL_FILLDIR_FUNC(fat_ioctl_filldir, __fat_dirent)
 
 static int fat_ioctl_readdir(struct inode *inode, struct file *filp,
                              void __user *dirent, filldir_t filldir,
@@ -741,7 +760,7 @@ static int fat_ioctl_readdir(struct inode *inode, struct file *filp,
 static int fat_dir_ioctl(struct inode *inode, struct file *filp,
                          unsigned int cmd, unsigned long arg)
 {
-        struct dirent __user *d1 = (struct dirent __user *)arg;
+        struct __fat_dirent __user *d1 = (struct __fat_dirent __user *)arg;
         int short_only, both;
 
         switch (cmd) {
@@ -757,7 +776,7 @@ static int fat_dir_ioctl(struct inode *inode, struct file *filp,
                 return fat_generic_ioctl(inode, filp, cmd, arg);
         }
 
-        if (!access_ok(VERIFY_WRITE, d1, sizeof(struct dirent[2])))
+        if (!access_ok(VERIFY_WRITE, d1, sizeof(struct __fat_dirent[2])))
                 return -EFAULT;
         /*
          * Yes, we don't need this put_user() absolutely. However old
@@ -1082,7 +1101,7 @@ int fat_alloc_new_dir(struct inode *dir, struct timespec *ts)
                 goto error_free;
         }
 
-        fat_date_unix2dos(ts->tv_sec, &time, &date);
+        fat_date_unix2dos(ts->tv_sec, &time, &date, sbi->options.tz_utc);
 
         de = (struct msdos_dir_entry *)bhs[0]->b_data;
         /* filling the new directory slots ("." and ".." entries) */
diff --git a/fs/fat/file.c b/fs/fat/file.c
index c672df4036e9..ddde37025ca6 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -15,6 +15,8 @@
 #include <linux/writeback.h>
 #include <linux/backing-dev.h>
 #include <linux/blkdev.h>
+#include <linux/fsnotify.h>
+#include <linux/security.h>
 
 int fat_generic_ioctl(struct inode *inode, struct file *filp,
                       unsigned int cmd, unsigned long arg)
@@ -64,6 +66,7 @@ int fat_generic_ioctl(struct inode *inode, struct file *filp,
 
                 /* Equivalent to a chmod() */
                 ia.ia_valid = ATTR_MODE | ATTR_CTIME;
+                ia.ia_ctime = current_fs_time(inode->i_sb);
                 if (is_dir) {
                         ia.ia_mode = MSDOS_MKMODE(attr,
                                 S_IRWXUGO & ~sbi->options.fs_dmask)
@@ -90,11 +93,21 @@ int fat_generic_ioctl(struct inode *inode, struct file *filp,
                         }
                 }
 
+                /*
+                 * The security check is questionable...  We single
+                 * out the RO attribute for checking by the security
+                 * module, just because it maps to a file mode.
+                 */
+                err = security_inode_setattr(filp->f_path.dentry, &ia);
+                if (err)
+                        goto up;
+
                 /* This MUST be done before doing anything irreversible... */
-                err = notify_change(filp->f_path.dentry, &ia);
+                err = fat_setattr(filp->f_path.dentry, &ia);
                 if (err)
                         goto up;
 
+                fsnotify_change(filp->f_path.dentry, ia.ia_valid);
                 if (sbi->options.sys_immutable) {
                         if (attr & ATTR_SYS)
                                 inode->i_flags |= S_IMMUTABLE;
@@ -300,6 +313,8 @@ static int fat_allow_set_time(struct msdos_sb_info *sbi, struct inode *inode)
         return 0;
 }
 
+#define TIMES_SET_FLAGS (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)
+
 int fat_setattr(struct dentry *dentry, struct iattr *attr)
 {
         struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb);
@@ -323,9 +338,9 @@ int fat_setattr(struct dentry *dentry, struct iattr *attr)
 
         /* Check for setting the inode time. */
         ia_valid = attr->ia_valid;
-        if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET)) {
+        if (ia_valid & TIMES_SET_FLAGS) {
                 if (fat_allow_set_time(sbi, inode))
-                        attr->ia_valid &= ~(ATTR_MTIME_SET | ATTR_ATIME_SET);
+                        attr->ia_valid &= ~TIMES_SET_FLAGS;
         }
 
         error = inode_change_ok(inode, attr);
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 46a4508ffd2e..6d266d793e2c 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -382,17 +382,20 @@ static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
         inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1))
                            & ~((loff_t)sbi->cluster_size - 1)) >> 9;
         inode->i_mtime.tv_sec =
-                date_dos2unix(le16_to_cpu(de->time), le16_to_cpu(de->date));
+                date_dos2unix(le16_to_cpu(de->time), le16_to_cpu(de->date),
+                              sbi->options.tz_utc);
         inode->i_mtime.tv_nsec = 0;
         if (sbi->options.isvfat) {
                 int secs = de->ctime_cs / 100;
                 int csecs = de->ctime_cs % 100;
                 inode->i_ctime.tv_sec  =
                         date_dos2unix(le16_to_cpu(de->ctime),
-                                      le16_to_cpu(de->cdate)) + secs;
+                                      le16_to_cpu(de->cdate),
+                                      sbi->options.tz_utc) + secs;
                 inode->i_ctime.tv_nsec = csecs * 10000000;
                 inode->i_atime.tv_sec =
-                        date_dos2unix(0, le16_to_cpu(de->adate));
+                        date_dos2unix(0, le16_to_cpu(de->adate),
+                                      sbi->options.tz_utc);
                 inode->i_atime.tv_nsec = 0;
         } else
                 inode->i_ctime = inode->i_atime = inode->i_mtime;
@@ -495,7 +498,7 @@ static void fat_destroy_inode(struct inode *inode)
         kmem_cache_free(fat_inode_cachep, MSDOS_I(inode));
 }
 
-static void init_once(struct kmem_cache *cachep, void *foo)
+static void init_once(void *foo)
 {
         struct msdos_inode_info *ei = (struct msdos_inode_info *)foo;
 
@@ -591,11 +594,14 @@ retry:
         raw_entry->attr = fat_attr(inode);
         raw_entry->start = cpu_to_le16(MSDOS_I(inode)->i_logstart);
         raw_entry->starthi = cpu_to_le16(MSDOS_I(inode)->i_logstart >> 16);
-        fat_date_unix2dos(inode->i_mtime.tv_sec, &raw_entry->time, &raw_entry->date);
+        fat_date_unix2dos(inode->i_mtime.tv_sec, &raw_entry->time,
+                          &raw_entry->date, sbi->options.tz_utc);
         if (sbi->options.isvfat) {
                 __le16 atime;
-                fat_date_unix2dos(inode->i_ctime.tv_sec,&raw_entry->ctime,&raw_entry->cdate);
-                fat_date_unix2dos(inode->i_atime.tv_sec,&atime,&raw_entry->adate);
+                fat_date_unix2dos(inode->i_ctime.tv_sec, &raw_entry->ctime,
+                                  &raw_entry->cdate, sbi->options.tz_utc);
+                fat_date_unix2dos(inode->i_atime.tv_sec, &atime,
+                                  &raw_entry->adate, sbi->options.tz_utc);
                 raw_entry->ctime_cs = (inode->i_ctime.tv_sec & 1) * 100 +
                         inode->i_ctime.tv_nsec / 10000000;
         }
@@ -836,6 +842,8 @@ static int fat_show_options(struct seq_file *m, struct vfsmount *mnt)
         }
         if (sbi->options.flush)
                 seq_puts(m, ",flush");
+        if (opts->tz_utc)
+                seq_puts(m, ",tz=UTC");
 
         return 0;
 }
@@ -848,7 +856,7 @@ enum {
         Opt_charset, Opt_shortname_lower, Opt_shortname_win95,
         Opt_shortname_winnt, Opt_shortname_mixed, Opt_utf8_no, Opt_utf8_yes,
         Opt_uni_xl_no, Opt_uni_xl_yes, Opt_nonumtail_no, Opt_nonumtail_yes,
-        Opt_obsolate, Opt_flush, Opt_err,
+        Opt_obsolate, Opt_flush, Opt_tz_utc, Opt_err,
 };
 
 static match_table_t fat_tokens = {
@@ -883,6 +891,7 @@ static match_table_t fat_tokens = {
         {Opt_obsolate, "cvf_options=%100s"},
         {Opt_obsolate, "posix"},
         {Opt_flush, "flush"},
+        {Opt_tz_utc, "tz=UTC"},
         {Opt_err, NULL},
 };
 static match_table_t msdos_tokens = {
@@ -947,10 +956,11 @@ static int parse_options(char *options, int is_vfat, int silent, int *debug,
         opts->utf8 = opts->unicode_xlate = 0;
         opts->numtail = 1;
         opts->usefree = opts->nocase = 0;
+        opts->tz_utc = 0;
         *debug = 0;
 
         if (!options)
-                return 0;
+                goto out;
 
         while ((p = strsep(&options, ",")) != NULL) {
                 int token;
@@ -1036,6 +1046,9 @@ static int parse_options(char *options, int is_vfat, int silent, int *debug,
                 case Opt_flush:
                         opts->flush = 1;
                         break;
+                case Opt_tz_utc:
+                        opts->tz_utc = 1;
+                        break;
 
                 /* msdos specific */
                 case Opt_dots:
@@ -1104,10 +1117,13 @@ static int parse_options(char *options, int is_vfat, int silent, int *debug,
                         return -EINVAL;
                 }
         }
+
+out:
         /* UTF-8 doesn't provide FAT semantics */
         if (!strcmp(opts->iocharset, "utf8")) {
                 printk(KERN_ERR "FAT: utf8 is not a recommended IO charset"
-                       " for FAT filesystems, filesystem will be case sensitive!\n");
+                       " for FAT filesystems, filesystem will be "
+                       "case sensitive!\n");
         }
 
         /* If user doesn't specify allow_utime, it's initialized from dmask. */
diff --git a/fs/fat/misc.c b/fs/fat/misc.c
index 61f23511eacf..79fb98ad36d4 100644
--- a/fs/fat/misc.c
+++ b/fs/fat/misc.c
@@ -142,7 +142,7 @@ static int day_n[] = {
 };
 
 /* Convert a MS-DOS time/date pair to a UNIX date (seconds since 1 1 70). */
-int date_dos2unix(unsigned short time, unsigned short date)
+int date_dos2unix(unsigned short time, unsigned short date, int tz_utc)
 {
         int month, year, secs;
 
@@ -156,16 +156,18 @@ int date_dos2unix(unsigned short time, unsigned short date)
             ((date & 31)-1+day_n[month]+(year/4)+year*365-((year & 3) == 0 &&
             month < 2 ? 1 : 0)+3653);
                         /* days since 1.1.70 plus 80's leap day */
-        secs += sys_tz.tz_minuteswest*60;
+        if (!tz_utc)
+                secs += sys_tz.tz_minuteswest*60;
         return secs;
 }
 
 /* Convert linear UNIX date to a MS-DOS time/date pair. */
-void fat_date_unix2dos(int unix_date, __le16 *time, __le16 *date)
+void fat_date_unix2dos(int unix_date, __le16 *time, __le16 *date, int tz_utc)
 {
         int day, year, nl_day, month;
 
-        unix_date -= sys_tz.tz_minuteswest*60;
+        if (!tz_utc)
+                unix_date -= sys_tz.tz_minuteswest*60;
 
         /* Jan 1 GMT 00:00:00 1980. But what about another time zone? */
         if (unix_date < 315532800)
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 330a7d782591..ac4f7db9f134 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -49,145 +49,94 @@ static int get_close_on_exec(unsigned int fd)
         return res;
 }
 
-/*
- * locate_fd finds a free file descriptor in the open_fds fdset,
- * expanding the fd arrays if necessary.  Must be called with the
- * file_lock held for write.
- */
-
-static int locate_fd(unsigned int orig_start, int cloexec)
-{
-        struct files_struct *files = current->files;
-        unsigned int newfd;
-        unsigned int start;
-        int error;
-        struct fdtable *fdt;
-
-        spin_lock(&files->file_lock);
-
-        error = -EINVAL;
-        if (orig_start >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur)
-                goto out;
-
-repeat:
-        fdt = files_fdtable(files);
-        /*
-         * Someone might have closed fd's in the range
-         * orig_start..fdt->next_fd
-         */
-        start = orig_start;
-        if (start < files->next_fd)
-                start = files->next_fd;
-
-        newfd = start;
-        if (start < fdt->max_fds)
-                newfd = find_next_zero_bit(fdt->open_fds->fds_bits,
-                                           fdt->max_fds, start);
-        
-        error = -EMFILE;
-        if (newfd >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur)
-                goto out;
-
-        error = expand_files(files, newfd);
-        if (error < 0)
-                goto out;
-
-        /*
-         * If we needed to expand the fs array we
-         * might have blocked - try again.
-         */
-        if (error)
-                goto repeat;
-
-        if (start <= files->next_fd)
-                files->next_fd = newfd + 1;
-
-        FD_SET(newfd, fdt->open_fds);
-        if (cloexec)
-                FD_SET(newfd, fdt->close_on_exec);
-        else
-                FD_CLR(newfd, fdt->close_on_exec);
-        error = newfd;
-
-out:
-        spin_unlock(&files->file_lock);
-        return error;
-}
-
-static int dupfd(struct file *file, unsigned int start, int cloexec)
-{
-        int fd = locate_fd(start, cloexec);
-        if (fd >= 0)
-                fd_install(fd, file);
-        else
-                fput(file);
-
-        return fd;
-}
-
-asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd)
+asmlinkage long sys_dup3(unsigned int oldfd, unsigned int newfd, int flags)
 {
         int err = -EBADF;
         struct file * file, *tofree;
         struct files_struct * files = current->files;
         struct fdtable *fdt;
 
-        spin_lock(&files->file_lock);
-        if (!(file = fcheck(oldfd)))
-                goto out_unlock;
-        err = newfd;
-        if (newfd == oldfd)
-                goto out_unlock;
-        err = -EBADF;
-        if (newfd >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur)
-                goto out_unlock;
-        get_file(file);                 /* We are now finished with oldfd */
-
-        err = expand_files(files, newfd);
-        if (err < 0)
-                goto out_fput;
+        if ((flags & ~O_CLOEXEC) != 0)
+                return -EINVAL;
 
-        /* To avoid races with open() and dup(), we will mark the fd as
-         * in-use in the open-file bitmap throughout the entire dup2()
-         * process.  This is quite safe: do_close() uses the fd array
-         * entry, not the bitmap, to decide what work needs to be
-         * done.  --sct */
-        /* Doesn't work. open() might be there first. --AV */
+        if (unlikely(oldfd == newfd))
+                return -EINVAL;
 
-        /* Yes. It's a race. In user space. Nothing sane to do */
+        spin_lock(&files->file_lock);
+        err = expand_files(files, newfd);
+        file = fcheck(oldfd);
+        if (unlikely(!file))
+                goto Ebadf;
+        if (unlikely(err < 0)) {
+                if (err == -EMFILE)
+                        goto Ebadf;
+                goto out_unlock;
+        }
+        /*
+         * We need to detect attempts to do dup2() over allocated but still
+         * not finished descriptor.  NB: OpenBSD avoids that at the price of
+         * extra work in their equivalent of fget() - they insert struct
+         * file immediately after grabbing descriptor, mark it larval if
+         * more work (e.g. actual opening) is needed and make sure that
+         * fget() treats larval files as absent.  Potentially interesting,
+         * but while extra work in fget() is trivial, locking implications
+         * and amount of surgery on open()-related paths in VFS are not.
+         * FreeBSD fails with -EBADF in the same situation, NetBSD "solution"
+         * deadlocks in rather amusing ways, AFAICS.  All of that is out of
+         * scope of POSIX or SUS, since neither considers shared descriptor
+         * tables and this condition does not arise without those.
+         */
         err = -EBUSY;
         fdt = files_fdtable(files);
         tofree = fdt->fd[newfd];
         if (!tofree && FD_ISSET(newfd, fdt->open_fds))
-                goto out_fput;
-
+                goto out_unlock;
+        get_file(file);
         rcu_assign_pointer(fdt->fd[newfd], file);
         FD_SET(newfd, fdt->open_fds);
-        FD_CLR(newfd, fdt->close_on_exec);
+        if (flags & O_CLOEXEC)
+                FD_SET(newfd, fdt->close_on_exec);
+        else
+                FD_CLR(newfd, fdt->close_on_exec);
         spin_unlock(&files->file_lock);
 
         if (tofree)
                 filp_close(tofree, files);
-        err = newfd;
-out:
-        return err;
+
+        return newfd;
+
+Ebadf:
+        err = -EBADF;
 out_unlock:
         spin_unlock(&files->file_lock);
-        goto out;
+        return err;
+}
 
-out_fput:
-        spin_unlock(&files->file_lock);
-        fput(file);
-        goto out;
+asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd)
+{
+        if (unlikely(newfd == oldfd)) { /* corner case */
+                struct files_struct *files = current->files;
+                rcu_read_lock();
+                if (!fcheck_files(files, oldfd))
+                        oldfd = -EBADF;
+                rcu_read_unlock();
+                return oldfd;
+        }
+        return sys_dup3(oldfd, newfd, 0);
 }
 
 asmlinkage long sys_dup(unsigned int fildes)
 {
         int ret = -EBADF;
-        struct file * file = fget(fildes);
-
-        if (file)
-                ret = dupfd(file, 0, 0);
+        struct file *file = fget(fildes);
+
+        if (file) {
+                ret = get_unused_fd();
+                if (ret >= 0)
+                        fd_install(ret, file);
+                else
+                        fput(file);
+        }
         return ret;
 }
 
@@ -310,8 +259,13 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
         switch (cmd) {
         case F_DUPFD:
         case F_DUPFD_CLOEXEC:
-                get_file(filp);
-                err = dupfd(filp, arg, cmd == F_DUPFD_CLOEXEC);
+                if (arg >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur)
+                        break;
+                err = alloc_fd(arg, cmd == F_DUPFD_CLOEXEC ? O_CLOEXEC : 0);
+                if (err >= 0) {
+                        get_file(filp);
+                        fd_install(err, filp);
+                }
                 break;
         case F_GETFD:
                 err = get_close_on_exec(fd) ? FD_CLOEXEC : 0;
diff --git a/fs/fifo.c b/fs/fifo.c
index 9785e36f81e7..987bf9411495 100644
--- a/fs/fifo.c
+++ b/fs/fifo.c
@@ -57,7 +57,7 @@ static int fifo_open(struct inode *inode, struct file *filp)
          *  POSIX.1 says that O_NONBLOCK means return with the FIFO
          *  opened, even when there is no process writing the FIFO.
          */
-                filp->f_op = &read_fifo_fops;
+                filp->f_op = &read_pipefifo_fops;
                 pipe->r_counter++;
                 if (pipe->readers++ == 0)
                         wake_up_partner(inode);
@@ -86,7 +86,7 @@ static int fifo_open(struct inode *inode, struct file *filp)
                 if ((filp->f_flags & O_NONBLOCK) && !pipe->readers)
                         goto err;
 
-                filp->f_op = &write_fifo_fops;
+                filp->f_op = &write_pipefifo_fops;
                 pipe->w_counter++;
                 if (!pipe->writers++)
                         wake_up_partner(inode);
@@ -105,7 +105,7 @@ static int fifo_open(struct inode *inode, struct file *filp)
          *  This implementation will NEVER block on a O_RDWR open, since
          *  the process can at least talk to itself.
          */
-                filp->f_op = &rdwr_fifo_fops;
+                filp->f_op = &rdwr_pipefifo_fops;
 
                 pipe->readers++;
                 pipe->writers++;
@@ -151,5 +151,5 @@ err_nocleanup:
  * depending on the access mode of the file...
  */
 const struct file_operations def_fifo_fops = {
-        .open           = fifo_open,    /* will set read or write pipe_fops */
+        .open           = fifo_open,    /* will set read_ or write_pipefifo_fops */
 };
diff --git a/fs/file.c b/fs/file.c
index 7b3887e054d0..f313314f996f 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -6,6 +6,7 @@
  *  Manage the dynamic fd arrays in the process files_struct.
  */
 
+#include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/time.h>
@@ -250,9 +251,18 @@ int expand_files(struct files_struct *files, int nr)
         struct fdtable *fdt;
 
         fdt = files_fdtable(files);
+
+        /*
+         * N.B. For clone tasks sharing a files structure, this test
+         * will limit the total number of files that can be opened.
+         */
+        if (nr >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur)
+                return -EMFILE;
+
         /* Do we need to expand? */
         if (nr < fdt->max_fds)
                 return 0;
+
         /* Can we expand? */
         if (nr >= sysctl_nr_open)
                 return -EMFILE;
@@ -423,3 +433,63 @@ struct files_struct init_files = {
         },
         .file_lock      = __SPIN_LOCK_UNLOCKED(init_task.file_lock),
 };
+
+/*
+ * allocate a file descriptor, mark it busy.
+ */
+int alloc_fd(unsigned start, unsigned flags)
+{
+        struct files_struct *files = current->files;
+        unsigned int fd;
+        int error;
+        struct fdtable *fdt;
+
+        spin_lock(&files->file_lock);
+repeat:
+        fdt = files_fdtable(files);
+        fd = start;
+        if (fd < files->next_fd)
+                fd = files->next_fd;
+
+        if (fd < fdt->max_fds)
+                fd = find_next_zero_bit(fdt->open_fds->fds_bits,
+                                           fdt->max_fds, fd);
+
+        error = expand_files(files, fd);
+        if (error < 0)
+                goto out;
+
+        /*
+         * If we needed to expand the fs array we
+         * might have blocked - try again.
+         */
+        if (error)
+                goto repeat;
+
+        if (start <= files->next_fd)
+                files->next_fd = fd + 1;
+
+        FD_SET(fd, fdt->open_fds);
+        if (flags & O_CLOEXEC)
+                FD_SET(fd, fdt->close_on_exec);
+        else
+                FD_CLR(fd, fdt->close_on_exec);
+        error = fd;
+#if 1
+        /* Sanity check */
+        if (rcu_dereference(fdt->fd[fd]) != NULL) {
+                printk(KERN_WARNING "alloc_fd: slot %d not NULL!\n", fd);
+                rcu_assign_pointer(fdt->fd[fd], NULL);
+        }
+#endif
+
+out:
+        spin_unlock(&files->file_lock);
+        return error;
+}
+
+int get_unused_fd(void)
+{
+        return alloc_fd(0, 0);
+}
+EXPORT_SYMBOL(get_unused_fd);
diff --git a/fs/file_table.c b/fs/file_table.c
index 83084225b4c3..f45a4493f9e7 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -120,7 +120,7 @@ struct file *get_empty_filp(void)
 
         tsk = current;
         INIT_LIST_HEAD(&f->f_u.fu_list);
-        atomic_set(&f->f_count, 1);
+        atomic_long_set(&f->f_count, 1);
         rwlock_init(&f->f_owner.lock);
         f->f_uid = tsk->fsuid;
         f->f_gid = tsk->fsgid;
@@ -219,7 +219,7 @@ EXPORT_SYMBOL(init_file);
 
 void fput(struct file *file)
 {
-        if (atomic_dec_and_test(&file->f_count))
+        if (atomic_long_dec_and_test(&file->f_count))
                 __fput(file);
 }
 
@@ -294,7 +294,7 @@ struct file *fget(unsigned int fd)
         rcu_read_lock();
         file = fcheck_files(files, fd);
         if (file) {
-                if (!atomic_inc_not_zero(&file->f_count)) {
+                if (!atomic_long_inc_not_zero(&file->f_count)) {
                         /* File object ref couldn't be taken */
                         rcu_read_unlock();
                         return NULL;
@@ -326,7 +326,7 @@ struct file *fget_light(unsigned int fd, int *fput_needed)
                 rcu_read_lock();
                 file = fcheck_files(files, fd);
                 if (file) {
-                        if (atomic_inc_not_zero(&file->f_count))
+                        if (atomic_long_inc_not_zero(&file->f_count))
                                 *fput_needed = 1;
                         else
                                 /* Didn't get the reference, someone's freed */
@@ -341,7 +341,7 @@ struct file *fget_light(unsigned int fd, int *fput_needed)
 
 void put_filp(struct file *file)
 {
-        if (atomic_dec_and_test(&file->f_count)) {
+        if (atomic_long_dec_and_test(&file->f_count)) {
                 security_file_free(file);
                 file_kill(file);
                 file_free(file);
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 2060bf06b906..fd03330cadeb 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -97,7 +97,7 @@ void fuse_invalidate_attr(struct inode *inode)
  * timeout is unknown (unlink, rmdir, rename and in some cases
  * lookup)
  */
-static void fuse_invalidate_entry_cache(struct dentry *entry)
+void fuse_invalidate_entry_cache(struct dentry *entry)
 {
         fuse_dentry_settime(entry, 0);
 }
@@ -112,18 +112,16 @@ static void fuse_invalidate_entry(struct dentry *entry)
         fuse_invalidate_entry_cache(entry);
 }
 
-static void fuse_lookup_init(struct fuse_req *req, struct inode *dir,
-                             struct dentry *entry,
+static void fuse_lookup_init(struct fuse_conn *fc, struct fuse_req *req,
+                             u64 nodeid, struct qstr *name,
                              struct fuse_entry_out *outarg)
 {
-        struct fuse_conn *fc = get_fuse_conn(dir);
-
         memset(outarg, 0, sizeof(struct fuse_entry_out));
         req->in.h.opcode = FUSE_LOOKUP;
-        req->in.h.nodeid = get_node_id(dir);
+        req->in.h.nodeid = nodeid;
         req->in.numargs = 1;
-        req->in.args[0].size = entry->d_name.len + 1;
-        req->in.args[0].value = entry->d_name.name;
+        req->in.args[0].size = name->len + 1;
+        req->in.args[0].value = name->name;
         req->out.numargs = 1;
         if (fc->minor < 9)
                 req->out.args[0].size = FUSE_COMPAT_ENTRY_OUT_SIZE;
@@ -189,7 +187,8 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
                 attr_version = fuse_get_attr_version(fc);
 
                 parent = dget_parent(entry);
-                fuse_lookup_init(req, parent->d_inode, entry, &outarg);
+                fuse_lookup_init(fc, req, get_node_id(parent->d_inode),
+                                 &entry->d_name, &outarg);
                 request_send(fc, req);
                 dput(parent);
                 err = req->out.h.error;
@@ -225,7 +224,7 @@ static int invalid_nodeid(u64 nodeid)
         return !nodeid || nodeid == FUSE_ROOT_ID;
 }
 
-static struct dentry_operations fuse_dentry_operations = {
+struct dentry_operations fuse_dentry_operations = {
         .d_revalidate   = fuse_dentry_revalidate,
 };
 
@@ -239,85 +238,127 @@ int fuse_valid_type(int m)
  * Add a directory inode to a dentry, ensuring that no other dentry
  * refers to this inode.  Called with fc->inst_mutex.
  */
-static int fuse_d_add_directory(struct dentry *entry, struct inode *inode)
+static struct dentry *fuse_d_add_directory(struct dentry *entry,
+                                           struct inode *inode)
 {
         struct dentry *alias = d_find_alias(inode);
-        if (alias) {
+        if (alias && !(alias->d_flags & DCACHE_DISCONNECTED)) {
                 /* This tries to shrink the subtree below alias */
                 fuse_invalidate_entry(alias);
                 dput(alias);
                 if (!list_empty(&inode->i_dentry))
-                        return -EBUSY;
+                        return ERR_PTR(-EBUSY);
+        } else {
+                dput(alias);
         }
-        d_add(entry, inode);
-        return 0;
+        return d_splice_alias(inode, entry);
 }
 
-static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
-                                  struct nameidata *nd)
+int fuse_lookup_name(struct super_block *sb, u64 nodeid, struct qstr *name,
+                     struct fuse_entry_out *outarg, struct inode **inode)
 {
-        int err;
-        struct fuse_entry_out outarg;
-        struct inode *inode = NULL;
-        struct fuse_conn *fc = get_fuse_conn(dir);
+        struct fuse_conn *fc = get_fuse_conn_super(sb);
         struct fuse_req *req;
         struct fuse_req *forget_req;
         u64 attr_version;
+        int err;
 
-        if (entry->d_name.len > FUSE_NAME_MAX)
-                return ERR_PTR(-ENAMETOOLONG);
+        *inode = NULL;
+        err = -ENAMETOOLONG;
+        if (name->len > FUSE_NAME_MAX)
+                goto out;
 
         req = fuse_get_req(fc);
+        err = PTR_ERR(req);
         if (IS_ERR(req))
-                return ERR_CAST(req);
+                goto out;
 
         forget_req = fuse_get_req(fc);
+        err = PTR_ERR(forget_req);
         if (IS_ERR(forget_req)) {
                 fuse_put_request(fc, req);
-                return ERR_CAST(forget_req);
+                goto out;
         }
 
         attr_version = fuse_get_attr_version(fc);
 
-        fuse_lookup_init(req, dir, entry, &outarg);
+        fuse_lookup_init(fc, req, nodeid, name, outarg);
         request_send(fc, req);
         err = req->out.h.error;
         fuse_put_request(fc, req);
         /* Zero nodeid is same as -ENOENT, but with valid timeout */
-        if (!err && outarg.nodeid &&
-            (invalid_nodeid(outarg.nodeid) ||
-             !fuse_valid_type(outarg.attr.mode)))
-                err = -EIO;
-        if (!err && outarg.nodeid) {
-                inode = fuse_iget(dir->i_sb, outarg.nodeid, outarg.generation,
-                                  &outarg.attr, entry_attr_timeout(&outarg),
-                                  attr_version);
-                if (!inode) {
-                        fuse_send_forget(fc, forget_req, outarg.nodeid, 1);
-                        return ERR_PTR(-ENOMEM);
-                }
+        if (err || !outarg->nodeid)
+                goto out_put_forget;
+
+        err = -EIO;
+        if (!outarg->nodeid)
+                goto out_put_forget;
+        if (!fuse_valid_type(outarg->attr.mode))
+                goto out_put_forget;
+
+        *inode = fuse_iget(sb, outarg->nodeid, outarg->generation,
+                           &outarg->attr, entry_attr_timeout(outarg),
+                           attr_version);
+        err = -ENOMEM;
+        if (!*inode) {
+                fuse_send_forget(fc, forget_req, outarg->nodeid, 1);
+                goto out;
         }
+        err = 0;
+
+ out_put_forget:
         fuse_put_request(fc, forget_req);
-        if (err && err != -ENOENT)
-                return ERR_PTR(err);
+ out:
+        return err;
+}
+
+static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
+                                  struct nameidata *nd)
+{
+        int err;
+        struct fuse_entry_out outarg;
+        struct inode *inode;
+        struct dentry *newent;
+        struct fuse_conn *fc = get_fuse_conn(dir);
+        bool outarg_valid = true;
+
+        err = fuse_lookup_name(dir->i_sb, get_node_id(dir), &entry->d_name,
+                               &outarg, &inode);
+        if (err == -ENOENT) {
+                outarg_valid = false;
+                err = 0;
+        }
+        if (err)
+                goto out_err;
+
+        err = -EIO;
+        if (inode && get_node_id(inode) == FUSE_ROOT_ID)
+                goto out_iput;
 
         if (inode && S_ISDIR(inode->i_mode)) {
                 mutex_lock(&fc->inst_mutex);
-                err = fuse_d_add_directory(entry, inode);
+                newent = fuse_d_add_directory(entry, inode);
                 mutex_unlock(&fc->inst_mutex);
-                if (err) {
-                        iput(inode);
-                        return ERR_PTR(err);
-                }
-        } else
-                d_add(entry, inode);
+                err = PTR_ERR(newent);
+                if (IS_ERR(newent))
+                        goto out_iput;
+        } else {
+                newent = d_splice_alias(inode, entry);
+        }
 
+        entry = newent ? newent : entry;
         entry->d_op = &fuse_dentry_operations;
-        if (!err)
+        if (outarg_valid)
                 fuse_change_entry_timeout(entry, &outarg);
         else
                 fuse_invalidate_entry_cache(entry);
-        return NULL;
+
+        return newent;
+
+ out_iput:
+        iput(inode);
+ out_err:
+        return ERR_PTR(err);
 }
 
 /*
@@ -857,7 +898,7 @@ static int fuse_access(struct inode *inode, int mask)
                 return PTR_ERR(req);
 
         memset(&inarg, 0, sizeof(inarg));
-        inarg.mask = mask;
+        inarg.mask = mask & (MAY_READ | MAY_WRITE | MAY_EXEC);
         req->in.h.opcode = FUSE_ACCESS;
         req->in.h.nodeid = get_node_id(inode);
         req->in.numargs = 1;
@@ -886,7 +927,7 @@ static int fuse_access(struct inode *inode, int mask)
  * access request is sent.  Execute permission is still checked
  * locally based on file mode.
  */
-static int fuse_permission(struct inode *inode, int mask, struct nameidata *nd)
+static int fuse_permission(struct inode *inode, int mask)
 {
         struct fuse_conn *fc = get_fuse_conn(inode);
         bool refreshed = false;
@@ -921,7 +962,7 @@ static int fuse_permission(struct inode *inode, int mask, struct nameidata *nd)
                    exist.  So if permissions are revoked this won't be
                    noticed immediately, only after the attribute
                    timeout has expired */
-        } else if (nd && (nd->flags & (LOOKUP_ACCESS | LOOKUP_CHDIR))) {
+        } else if (mask & MAY_ACCESS) {
                 err = fuse_access(inode, mask);
         } else if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode)) {
                 if (!(inode->i_mode & S_IXUGO)) {
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 8092f0d9fd1f..2bada6bbc317 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -893,7 +893,7 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
         if (count == 0)
                 goto out;
 
-        err = remove_suid(file->f_path.dentry);
+        err = file_remove_suid(file);
         if (err)
                 goto out;
 
@@ -1341,6 +1341,11 @@ static int fuse_setlk(struct file *file, struct file_lock *fl, int flock)
         pid_t pid = fl->fl_type != F_UNLCK ? current->tgid : 0;
         int err;
 
+        if (fl->fl_lmops && fl->fl_lmops->fl_grant) {
+                /* NLM needs asynchronous locks, which we don't support yet */
+                return -ENOLCK;
+        }
+
         /* Unlock on close is handled by the flush method */
         if (fl->fl_flags & FL_CLOSE)
                 return 0;
@@ -1365,7 +1370,9 @@ static int fuse_file_lock(struct file *file, int cmd, struct file_lock *fl)
         struct fuse_conn *fc = get_fuse_conn(inode);
         int err;
 
-        if (cmd == F_GETLK) {
+        if (cmd == F_CANCELLK) {
+                err = 0;
+        } else if (cmd == F_GETLK) {
                 if (fc->no_lock) {
                         posix_test_lock(file, fl);
                         err = 0;
@@ -1373,7 +1380,7 @@ static int fuse_file_lock(struct file *file, int cmd, struct file_lock *fl)
                         err = fuse_getlk(file, fl);
         } else {
                 if (fc->no_lock)
-                        err = posix_lock_file_wait(file, fl);
+                        err = posix_lock_file(file, fl, NULL);
                 else
                         err = fuse_setlk(file, fl, 0);
         }
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index bae948657c4f..3a876076bdd1 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -363,6 +363,9 @@ struct fuse_conn {
         /** Do not send separate SETATTR request before open(O_TRUNC)  */
         unsigned atomic_o_trunc : 1;
 
+        /** Filesystem supports NFS exporting.  Only set in INIT */
+        unsigned export_support : 1;
+
         /*
          * The following bitfields are only for optimization purposes
          * and hence races in setting them will not cause malfunction
@@ -464,6 +467,8 @@ static inline u64 get_node_id(struct inode *inode)
 /** Device operations */
 extern const struct file_operations fuse_dev_operations;
 
+extern struct dentry_operations fuse_dentry_operations;
+
 /**
  * Get a filled in inode
  */
@@ -471,6 +476,9 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
                         int generation, struct fuse_attr *attr,
                         u64 attr_valid, u64 attr_version);
 
+int fuse_lookup_name(struct super_block *sb, u64 nodeid, struct qstr *name,
+                     struct fuse_entry_out *outarg, struct inode **inode);
+
 /**
  * Send FORGET command
  */
@@ -604,6 +612,8 @@ void fuse_abort_conn(struct fuse_conn *fc);
  */
 void fuse_invalidate_attr(struct inode *inode);
 
+void fuse_invalidate_entry_cache(struct dentry *entry);
+
 /**
  * Acquire reference to fuse_conn
  */
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 3141690558c8..d2249f174e20 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -18,6 +18,7 @@
 #include <linux/statfs.h>
 #include <linux/random.h>
 #include <linux/sched.h>
+#include <linux/exportfs.h>
 
 MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
 MODULE_DESCRIPTION("Filesystem in Userspace");
@@ -552,6 +553,174 @@ static struct inode *get_root_inode(struct super_block *sb, unsigned mode)
         return fuse_iget(sb, 1, 0, &attr, 0, 0);
 }
 
+struct fuse_inode_handle
+{
+        u64 nodeid;
+        u32 generation;
+};
+
+static struct dentry *fuse_get_dentry(struct super_block *sb,
+                                      struct fuse_inode_handle *handle)
+{
+        struct fuse_conn *fc = get_fuse_conn_super(sb);
+        struct inode *inode;
+        struct dentry *entry;
+        int err = -ESTALE;
+
+        if (handle->nodeid == 0)
+                goto out_err;
+
+        inode = ilookup5(sb, handle->nodeid, fuse_inode_eq, &handle->nodeid);
+        if (!inode) {
+                struct fuse_entry_out outarg;
+                struct qstr name;
+
+                if (!fc->export_support)
+                        goto out_err;
+
+                name.len = 1;
+                name.name = ".";
+                err = fuse_lookup_name(sb, handle->nodeid, &name, &outarg,
+                                       &inode);
+                if (err && err != -ENOENT)
+                        goto out_err;
+                if (err || !inode) {
+                        err = -ESTALE;
+                        goto out_err;
+                }
+                err = -EIO;
+                if (get_node_id(inode) != handle->nodeid)
+                        goto out_iput;
+        }
+        err = -ESTALE;
+        if (inode->i_generation != handle->generation)
+                goto out_iput;
+
+        entry = d_alloc_anon(inode);
+        err = -ENOMEM;
+        if (!entry)
+                goto out_iput;
+
+        if (get_node_id(inode) != FUSE_ROOT_ID) {
+                entry->d_op = &fuse_dentry_operations;
+                fuse_invalidate_entry_cache(entry);
+        }
+
+        return entry;
+
+ out_iput:
+        iput(inode);
+ out_err:
+        return ERR_PTR(err);
+}
+
+static int fuse_encode_fh(struct dentry *dentry, u32 *fh, int *max_len,
+                           int connectable)
+{
+        struct inode *inode = dentry->d_inode;
+        bool encode_parent = connectable && !S_ISDIR(inode->i_mode);
+        int len = encode_parent ? 6 : 3;
+        u64 nodeid;
+        u32 generation;
+
+        if (*max_len < len)
+                return  255;
+
+        nodeid = get_fuse_inode(inode)->nodeid;
+        generation = inode->i_generation;
+
+        fh[0] = (u32)(nodeid >> 32);
+        fh[1] = (u32)(nodeid & 0xffffffff);
+        fh[2] = generation;
+
+        if (encode_parent) {
+                struct inode *parent;
+
+                spin_lock(&dentry->d_lock);
+                parent = dentry->d_parent->d_inode;
+                nodeid = get_fuse_inode(parent)->nodeid;
+                generation = parent->i_generation;
+                spin_unlock(&dentry->d_lock);
+
+                fh[3] = (u32)(nodeid >> 32);
+                fh[4] = (u32)(nodeid & 0xffffffff);
+                fh[5] = generation;
+        }
+
+        *max_len = len;
+        return encode_parent ? 0x82 : 0x81;
+}
+
+static struct dentry *fuse_fh_to_dentry(struct super_block *sb,
+                struct fid *fid, int fh_len, int fh_type)
+{
+        struct fuse_inode_handle handle;
+
+        if ((fh_type != 0x81 && fh_type != 0x82) || fh_len < 3)
+                return NULL;
+
+        handle.nodeid = (u64) fid->raw[0] << 32;
+        handle.nodeid |= (u64) fid->raw[1];
+        handle.generation = fid->raw[2];
+        return fuse_get_dentry(sb, &handle);
+}
+
+static struct dentry *fuse_fh_to_parent(struct super_block *sb,
+                struct fid *fid, int fh_len, int fh_type)
+{
+        struct fuse_inode_handle parent;
+
+        if (fh_type != 0x82 || fh_len < 6)
+                return NULL;
+
+        parent.nodeid = (u64) fid->raw[3] << 32;
+        parent.nodeid |= (u64) fid->raw[4];
+        parent.generation = fid->raw[5];
+        return fuse_get_dentry(sb, &parent);
+}
+
+static struct dentry *fuse_get_parent(struct dentry *child)
+{
+        struct inode *child_inode = child->d_inode;
+        struct fuse_conn *fc = get_fuse_conn(child_inode);
+        struct inode *inode;
+        struct dentry *parent;
+        struct fuse_entry_out outarg;
+        struct qstr name;
+        int err;
+
+        if (!fc->export_support)
+                return ERR_PTR(-ESTALE);
+
+        name.len = 2;
+        name.name = "..";
+        err = fuse_lookup_name(child_inode->i_sb, get_node_id(child_inode),
+                               &name, &outarg, &inode);
+        if (err && err != -ENOENT)
+                return ERR_PTR(err);
+        if (err || !inode)
+                return ERR_PTR(-ESTALE);
+
+        parent = d_alloc_anon(inode);
+        if (!parent) {
+                iput(inode);
+                return ERR_PTR(-ENOMEM);
+        }
+        if (get_node_id(inode) != FUSE_ROOT_ID) {
+                parent->d_op = &fuse_dentry_operations;
+                fuse_invalidate_entry_cache(parent);
+        }
+
+        return parent;
+}
+
+static const struct export_operations fuse_export_operations = {
+        .fh_to_dentry   = fuse_fh_to_dentry,
+        .fh_to_parent   = fuse_fh_to_parent,
+        .encode_fh      = fuse_encode_fh,
+        .get_parent     = fuse_get_parent,
+};
+
 static const struct super_operations fuse_super_operations = {
         .alloc_inode    = fuse_alloc_inode,
         .destroy_inode  = fuse_destroy_inode,
@@ -581,6 +750,11 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
                                 fc->no_lock = 1;
                         if (arg->flags & FUSE_ATOMIC_O_TRUNC)
                                 fc->atomic_o_trunc = 1;
+                        if (arg->minor >= 9) {
+                                /* LOOKUP has dependency on proto version */
+                                if (arg->flags & FUSE_EXPORT_SUPPORT)
+                                        fc->export_support = 1;
+                        }
                         if (arg->flags & FUSE_BIG_WRITES)
                                 fc->big_writes = 1;
                 } else {
@@ -607,7 +781,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
         arg->minor = FUSE_KERNEL_MINOR_VERSION;
         arg->max_readahead = fc->bdi.ra_pages * PAGE_CACHE_SIZE;
         arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC |
-                FUSE_BIG_WRITES;
+                FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES;
         req->in.h.opcode = FUSE_INIT;
         req->in.numargs = 1;
         req->in.args[0].size = sizeof(*arg);
@@ -652,6 +826,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
         sb->s_magic = FUSE_SUPER_MAGIC;
         sb->s_op = &fuse_super_operations;
         sb->s_maxbytes = MAX_LFS_FILESIZE;
+        sb->s_export_op = &fuse_export_operations;
 
         file = fget(d.fd);
         if (!file)
@@ -781,7 +956,7 @@ static inline void unregister_fuseblk(void)
 }
 #endif
 
-static void fuse_inode_init_once(struct kmem_cache *cachep, void *foo)
+static void fuse_inode_init_once(void *foo)
 {
         struct inode * inode = foo;
 
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 6da0ab355b8a..8b0806a32948 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -448,7 +448,7 @@ struct inode *gfs2_lookup_simple(struct inode *dip, const char *name)
         struct qstr qstr;
         struct inode *inode;
         gfs2_str2qstr(&qstr, name);
-        inode = gfs2_lookupi(dip, &qstr, 1, NULL);
+        inode = gfs2_lookupi(dip, &qstr, 1);
         /* gfs2_lookupi has inconsistent callers: vfs
          * related routines expect NULL for no entry found,
          * gfs2_lookup_simple callers expect ENOENT
@@ -477,7 +477,7 @@ struct inode *gfs2_lookup_simple(struct inode *dip, const char *name)
  */
 
 struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
-                           int is_root, struct nameidata *nd)
+                           int is_root)
 {
         struct super_block *sb = dir->i_sb;
         struct gfs2_inode *dip = GFS2_I(dir);
@@ -1173,7 +1173,7 @@ int gfs2_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to)
                         break;
                 }
 
-                tmp = gfs2_lookupi(dir, &dotdot, 1, NULL);
+                tmp = gfs2_lookupi(dir, &dotdot, 1);
                 if (IS_ERR(tmp)) {
                         error = PTR_ERR(tmp);
                         break;
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index 6074c2506f75..58f9607d6a86 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -83,7 +83,7 @@ int gfs2_inode_refresh(struct gfs2_inode *ip);
 int gfs2_dinode_dealloc(struct gfs2_inode *inode);
 int gfs2_change_nlink(struct gfs2_inode *ip, int diff);
 struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
-                           int is_root, struct nameidata *nd);
+                           int is_root);
 struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
                            unsigned int mode, dev_t dev);
 int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name,
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index bcc668d0fadd..bb2cc303ac29 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -24,7 +24,7 @@
 #include "util.h"
 #include "glock.h"
 
-static void gfs2_init_inode_once(struct kmem_cache *cachep, void *foo)
+static void gfs2_init_inode_once(void *foo)
 {
         struct gfs2_inode *ip = foo;
 
@@ -33,7 +33,7 @@ static void gfs2_init_inode_once(struct kmem_cache *cachep, void *foo)
         ip->i_alloc = NULL;
 }
 
-static void gfs2_init_glock_once(struct kmem_cache *cachep, void *foo)
+static void gfs2_init_glock_once(void *foo)
 {
         struct gfs2_glock *gl = foo;
 
diff --git a/fs/gfs2/ops_export.c b/fs/gfs2/ops_export.c
index 990d9f4bc463..9cda8536530c 100644
--- a/fs/gfs2/ops_export.c
+++ b/fs/gfs2/ops_export.c
@@ -134,7 +134,7 @@ static struct dentry *gfs2_get_parent(struct dentry *child)
         struct dentry *dentry;
 
         gfs2_str2qstr(&dotdot, "..");
-        inode = gfs2_lookupi(child->d_inode, &dotdot, 1, NULL);
+        inode = gfs2_lookupi(child->d_inode, &dotdot, 1);
 
         if (!inode)
                 return ERR_PTR(-ENOENT);
diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index 1e252dfc5294..e2c62f73a778 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -74,7 +74,7 @@ static int gfs2_create(struct inode *dir, struct dentry *dentry,
                         return PTR_ERR(inode);
                 }
 
-                inode = gfs2_lookupi(dir, &dentry->d_name, 0, nd);
+                inode = gfs2_lookupi(dir, &dentry->d_name, 0);
                 if (inode) {
                         if (!IS_ERR(inode)) {
                                 gfs2_holder_uninit(ghs);
@@ -109,7 +109,7 @@ static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry,
 
         dentry->d_op = &gfs2_dops;
 
-        inode = gfs2_lookupi(dir, &dentry->d_name, 0, nd);
+        inode = gfs2_lookupi(dir, &dentry->d_name, 0);
         if (inode && IS_ERR(inode))
                 return ERR_CAST(inode);
 
@@ -915,12 +915,6 @@ int gfs2_permission(struct inode *inode, int mask)
         return error;
 }
 
-static int gfs2_iop_permission(struct inode *inode, int mask,
-                               struct nameidata *nd)
-{
-        return gfs2_permission(inode, mask);
-}
-
 static int setattr_size(struct inode *inode, struct iattr *attr)
 {
         struct gfs2_inode *ip = GFS2_I(inode);
@@ -1150,7 +1144,7 @@ static int gfs2_removexattr(struct dentry *dentry, const char *name)
 }
 
 const struct inode_operations gfs2_file_iops = {
-        .permission = gfs2_iop_permission,
+        .permission = gfs2_permission,
         .setattr = gfs2_setattr,
         .getattr = gfs2_getattr,
         .setxattr = gfs2_setxattr,
@@ -1169,7 +1163,7 @@ const struct inode_operations gfs2_dir_iops = {
         .rmdir = gfs2_rmdir,
         .mknod = gfs2_mknod,
         .rename = gfs2_rename,
-        .permission = gfs2_iop_permission,
+        .permission = gfs2_permission,
         .setattr = gfs2_setattr,
         .getattr = gfs2_getattr,
         .setxattr = gfs2_setxattr,
@@ -1181,7 +1175,7 @@ const struct inode_operations gfs2_dir_iops = {
 const struct inode_operations gfs2_symlink_iops = {
         .readlink = gfs2_readlink,
         .follow_link = gfs2_follow_link,
-        .permission = gfs2_iop_permission,
+        .permission = gfs2_permission,
         .setattr = gfs2_setattr,
         .getattr = gfs2_getattr,
         .setxattr = gfs2_setxattr,
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 63a8a902d9db..ca831991cbc2 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -389,7 +389,7 @@ int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh)
                         break;
 
                 INIT_LIST_HEAD(&jd->extent_list);
-                jd->jd_inode = gfs2_lookupi(sdp->sd_jindex, &name, 1, NULL);
+                jd->jd_inode = gfs2_lookupi(sdp->sd_jindex, &name, 1);
                 if (!jd->jd_inode || IS_ERR(jd->jd_inode)) {
                         if (!jd->jd_inode)
                                 error = -ENOENT;
diff --git a/fs/hfs/bitmap.c b/fs/hfs/bitmap.c
index 24e75798ddf0..c6e97366e8ac 100644
--- a/fs/hfs/bitmap.c
+++ b/fs/hfs/bitmap.c
@@ -145,7 +145,7 @@ u32 hfs_vbm_search_free(struct super_block *sb, u32 goal, u32 *num_bits)
         if (!*num_bits)
                 return 0;
 
-        down(&HFS_SB(sb)->bitmap_lock);
+        mutex_lock(&HFS_SB(sb)->bitmap_lock);
         bitmap = HFS_SB(sb)->bitmap;
 
         pos = hfs_find_set_zero_bits(bitmap, HFS_SB(sb)->fs_ablocks, goal, num_bits);
@@ -162,7 +162,7 @@ u32 hfs_vbm_search_free(struct super_block *sb, u32 goal, u32 *num_bits)
         HFS_SB(sb)->free_ablocks -= *num_bits;
         hfs_bitmap_dirty(sb);
 out:
-        up(&HFS_SB(sb)->bitmap_lock);
+        mutex_unlock(&HFS_SB(sb)->bitmap_lock);
         return pos;
 }
 
@@ -205,7 +205,7 @@ int hfs_clear_vbm_bits(struct super_block *sb, u16 start, u16 count)
         if ((start + count) > HFS_SB(sb)->fs_ablocks)
                 return -2;
 
-        down(&HFS_SB(sb)->bitmap_lock);
+        mutex_lock(&HFS_SB(sb)->bitmap_lock);
         /* bitmap is always on a 32-bit boundary */
         curr = HFS_SB(sb)->bitmap + (start / 32);
         len = count;
@@ -236,7 +236,7 @@ int hfs_clear_vbm_bits(struct super_block *sb, u16 start, u16 count)
         }
 out:
         HFS_SB(sb)->free_ablocks += len;
-        up(&HFS_SB(sb)->bitmap_lock);
+        mutex_unlock(&HFS_SB(sb)->bitmap_lock);
         hfs_bitmap_dirty(sb);
 
         return 0;
diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c
index f6621a785202..9b9d6395bad3 100644
--- a/fs/hfs/btree.c
+++ b/fs/hfs/btree.c
@@ -40,7 +40,7 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke
         {
         struct hfs_mdb *mdb = HFS_SB(sb)->mdb;
         HFS_I(tree->inode)->flags = 0;
-        init_MUTEX(&HFS_I(tree->inode)->extents_lock);
+        mutex_init(&HFS_I(tree->inode)->extents_lock);
         switch (id) {
         case HFS_EXT_CNID:
                 hfs_inode_read_fork(tree->inode, mdb->drXTExtRec, mdb->drXTFlSize,
diff --git a/fs/hfs/extent.c b/fs/hfs/extent.c
index c176f67ba0a5..2c16316d2917 100644
--- a/fs/hfs/extent.c
+++ b/fs/hfs/extent.c
@@ -343,16 +343,16 @@ int hfs_get_block(struct inode *inode, sector_t block,
                 goto done;
         }
 
-        down(&HFS_I(inode)->extents_lock);
+        mutex_lock(&HFS_I(inode)->extents_lock);
         res = hfs_ext_read_extent(inode, ablock);
         if (!res)
                 dblock = hfs_ext_find_block(HFS_I(inode)->cached_extents,
                                             ablock - HFS_I(inode)->cached_start);
         else {
-                up(&HFS_I(inode)->extents_lock);
+                mutex_unlock(&HFS_I(inode)->extents_lock);
                 return -EIO;
         }
-        up(&HFS_I(inode)->extents_lock);
+        mutex_unlock(&HFS_I(inode)->extents_lock);
 
 done:
         map_bh(bh_result, sb, HFS_SB(sb)->fs_start +
@@ -375,7 +375,7 @@ int hfs_extend_file(struct inode *inode)
         u32 start, len, goal;
         int res;
 
-        down(&HFS_I(inode)->extents_lock);
+        mutex_lock(&HFS_I(inode)->extents_lock);
         if (HFS_I(inode)->alloc_blocks == HFS_I(inode)->first_blocks)
                 goal = hfs_ext_lastblock(HFS_I(inode)->first_extents);
         else {
@@ -425,7 +425,7 @@ int hfs_extend_file(struct inode *inode)
                         goto insert_extent;
         }
 out:
-        up(&HFS_I(inode)->extents_lock);
+        mutex_unlock(&HFS_I(inode)->extents_lock);
         if (!res) {
                 HFS_I(inode)->alloc_blocks += len;
                 mark_inode_dirty(inode);
@@ -487,7 +487,7 @@ void hfs_file_truncate(struct inode *inode)
         if (blk_cnt == alloc_cnt)
                 goto out;
 
-        down(&HFS_I(inode)->extents_lock);
+        mutex_lock(&HFS_I(inode)->extents_lock);
         hfs_find_init(HFS_SB(sb)->ext_tree, &fd);
         while (1) {
                 if (alloc_cnt == HFS_I(inode)->first_blocks) {
@@ -514,7 +514,7 @@ void hfs_file_truncate(struct inode *inode)
                 hfs_brec_remove(&fd);
         }
         hfs_find_exit(&fd);
-        up(&HFS_I(inode)->extents_lock);
+        mutex_unlock(&HFS_I(inode)->extents_lock);
 
         HFS_I(inode)->alloc_blocks = blk_cnt;
 out:
diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h
index 147374b6f675..9955232fdf8c 100644
--- a/fs/hfs/hfs_fs.h
+++ b/fs/hfs/hfs_fs.h
@@ -11,6 +11,7 @@
 
 #include <linux/slab.h>
 #include <linux/types.h>
+#include <linux/mutex.h>
 #include <linux/buffer_head.h>
 #include <linux/fs.h>
 
@@ -53,7 +54,7 @@ struct hfs_inode_info {
         struct list_head open_dir_list;
         struct inode *rsrc_inode;
 
-        struct semaphore extents_lock;
+        struct mutex extents_lock;
 
         u16 alloc_blocks, clump_blocks;
         sector_t fs_blocks;
@@ -139,7 +140,7 @@ struct hfs_sb_info {
 
         struct nls_table *nls_io, *nls_disk;
 
-        struct semaphore bitmap_lock;
+        struct mutex bitmap_lock;
 
         unsigned long flags;
 
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 97f8446c4ff4..7e19835efa2e 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -150,7 +150,7 @@ struct inode *hfs_new_inode(struct inode *dir, struct qstr *name, int mode)
         if (!inode)
                 return NULL;
 
-        init_MUTEX(&HFS_I(inode)->extents_lock);
+        mutex_init(&HFS_I(inode)->extents_lock);
         INIT_LIST_HEAD(&HFS_I(inode)->open_dir_list);
         hfs_cat_build_key(sb, (btree_key *)&HFS_I(inode)->cat_key, dir->i_ino, name);
         inode->i_ino = HFS_SB(sb)->next_id++;
@@ -281,7 +281,7 @@ static int hfs_read_inode(struct inode *inode, void *data)
 
         HFS_I(inode)->flags = 0;
         HFS_I(inode)->rsrc_inode = NULL;
-        init_MUTEX(&HFS_I(inode)->extents_lock);
+        mutex_init(&HFS_I(inode)->extents_lock);
         INIT_LIST_HEAD(&HFS_I(inode)->open_dir_list);
 
         /* Initialize the inode */
@@ -511,8 +511,7 @@ void hfs_clear_inode(struct inode *inode)
         }
 }
 
-static int hfs_permission(struct inode *inode, int mask,
-                          struct nameidata *nd)
+static int hfs_permission(struct inode *inode, int mask)
 {
         if (S_ISREG(inode->i_mode) && mask & MAY_EXEC)
                 return 0;
@@ -523,8 +522,6 @@ static int hfs_file_open(struct inode *inode, struct file *file)
 {
         if (HFS_IS_RSRC(inode))
                 inode = HFS_I(inode)->rsrc_inode;
-        if (atomic_read(&file->f_count) != 1)
-                return 0;
         atomic_inc(&HFS_I(inode)->opencnt);
         return 0;
 }
@@ -535,8 +532,6 @@ static int hfs_file_release(struct inode *inode, struct file *file)
 
         if (HFS_IS_RSRC(inode))
                 inode = HFS_I(inode)->rsrc_inode;
-        if (atomic_read(&file->f_count) != 0)
-                return 0;
         if (atomic_dec_and_test(&HFS_I(inode)->opencnt)) {
                 mutex_lock(&inode->i_mutex);
                 hfs_file_truncate(inode);
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index 8cf67974adf6..4abb1047c689 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -372,7 +372,7 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent)
 
         sb->s_op = &hfs_super_operations;
         sb->s_flags |= MS_NODIRATIME;
-        init_MUTEX(&sbi->bitmap_lock);
+        mutex_init(&sbi->bitmap_lock);
 
         res = hfs_mdb_get(sb);
         if (res) {
@@ -432,7 +432,7 @@ static struct file_system_type hfs_fs_type = {
         .fs_flags       = FS_REQUIRES_DEV,
 };
 
-static void hfs_init_once(struct kmem_cache *cachep, void *p)
+static void hfs_init_once(void *p)
 {
         struct hfs_inode_info *i = p;
 
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index 12e899cd7886..fec8f61227ff 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -199,16 +199,16 @@ int hfsplus_get_block(struct inode *inode, sector_t iblock,
                 goto done;
         }
 
-        down(&HFSPLUS_I(inode).extents_lock);
+        mutex_lock(&HFSPLUS_I(inode).extents_lock);
         res = hfsplus_ext_read_extent(inode, ablock);
         if (!res) {
                 dblock = hfsplus_ext_find_block(HFSPLUS_I(inode).cached_extents, ablock -
                                              HFSPLUS_I(inode).cached_start);
         } else {
-                up(&HFSPLUS_I(inode).extents_lock);
+                mutex_unlock(&HFSPLUS_I(inode).extents_lock);
                 return -EIO;
         }
-        up(&HFSPLUS_I(inode).extents_lock);
+        mutex_unlock(&HFSPLUS_I(inode).extents_lock);
 
 done:
         dprint(DBG_EXTENT, "get_block(%lu): %llu - %u\n", inode->i_ino, (long long)iblock, dblock);
@@ -355,7 +355,7 @@ int hfsplus_file_extend(struct inode *inode)
                 return -ENOSPC;
         }
 
-        down(&HFSPLUS_I(inode).extents_lock);
+        mutex_lock(&HFSPLUS_I(inode).extents_lock);
         if (HFSPLUS_I(inode).alloc_blocks == HFSPLUS_I(inode).first_blocks)
                 goal = hfsplus_ext_lastblock(HFSPLUS_I(inode).first_extents);
         else {
@@ -408,7 +408,7 @@ int hfsplus_file_extend(struct inode *inode)
                         goto insert_extent;
         }
 out:
-        up(&HFSPLUS_I(inode).extents_lock);
+        mutex_unlock(&HFSPLUS_I(inode).extents_lock);
         if (!res) {
                 HFSPLUS_I(inode).alloc_blocks += len;
                 mark_inode_dirty(inode);
@@ -465,7 +465,7 @@ void hfsplus_file_truncate(struct inode *inode)
         if (blk_cnt == alloc_cnt)
                 goto out;
 
-        down(&HFSPLUS_I(inode).extents_lock);
+        mutex_lock(&HFSPLUS_I(inode).extents_lock);
         hfs_find_init(HFSPLUS_SB(sb).ext_tree, &fd);
         while (1) {
                 if (alloc_cnt == HFSPLUS_I(inode).first_blocks) {
@@ -492,7 +492,7 @@ void hfsplus_file_truncate(struct inode *inode)
                 hfs_brec_remove(&fd);
         }
         hfs_find_exit(&fd);
-        up(&HFSPLUS_I(inode).extents_lock);
+        mutex_unlock(&HFSPLUS_I(inode).extents_lock);
 
         HFSPLUS_I(inode).alloc_blocks = blk_cnt;
 out:
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 9e59537b43d5..f027a905225f 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -11,6 +11,7 @@
 #define _LINUX_HFSPLUS_FS_H
 
 #include <linux/fs.h>
+#include <linux/mutex.h>
 #include <linux/buffer_head.h>
 #include "hfsplus_raw.h"
 
@@ -154,7 +155,7 @@ struct hfsplus_sb_info {
 
 
 struct hfsplus_inode_info {
-        struct semaphore extents_lock;
+        struct mutex extents_lock;
         u32 clump_blocks, alloc_blocks;
         sector_t fs_blocks;
         /* Allocation extents from catalog record or volume header */
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 67e1c8b467c4..b085d64a2b67 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -163,7 +163,7 @@ static struct dentry *hfsplus_file_lookup(struct inode *dir, struct dentry *dent
 
         inode->i_ino = dir->i_ino;
         INIT_LIST_HEAD(&HFSPLUS_I(inode).open_dir_list);
-        init_MUTEX(&HFSPLUS_I(inode).extents_lock);
+        mutex_init(&HFSPLUS_I(inode).extents_lock);
         HFSPLUS_I(inode).flags = HFSPLUS_FLG_RSRC;
 
         hfs_find_init(HFSPLUS_SB(sb).cat_tree, &fd);
@@ -238,7 +238,7 @@ static void hfsplus_set_perms(struct inode *inode, struct hfsplus_perm *perms)
         perms->dev = cpu_to_be32(HFSPLUS_I(inode).dev);
 }
 
-static int hfsplus_permission(struct inode *inode, int mask, struct nameidata *nd)
+static int hfsplus_permission(struct inode *inode, int mask)
 {
         /* MAY_EXEC is also used for lookup, if no x bit is set allow lookup,
          * open_exec has the same test, so it's still not executable, if a x bit
@@ -254,8 +254,6 @@ static int hfsplus_file_open(struct inode *inode, struct file *file)
 {
         if (HFSPLUS_IS_RSRC(inode))
                 inode = HFSPLUS_I(inode).rsrc_inode;
-        if (atomic_read(&file->f_count) != 1)
-                return 0;
         atomic_inc(&HFSPLUS_I(inode).opencnt);
         return 0;
 }
@@ -266,8 +264,6 @@ static int hfsplus_file_release(struct inode *inode, struct file *file)
 
         if (HFSPLUS_IS_RSRC(inode))
                 inode = HFSPLUS_I(inode).rsrc_inode;
-        if (atomic_read(&file->f_count) != 0)
-                return 0;
         if (atomic_dec_and_test(&HFSPLUS_I(inode).opencnt)) {
                 mutex_lock(&inode->i_mutex);
                 hfsplus_file_truncate(inode);
@@ -316,7 +312,7 @@ struct inode *hfsplus_new_inode(struct super_block *sb, int mode)
         inode->i_nlink = 1;
         inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
         INIT_LIST_HEAD(&HFSPLUS_I(inode).open_dir_list);
-        init_MUTEX(&HFSPLUS_I(inode).extents_lock);
+        mutex_init(&HFSPLUS_I(inode).extents_lock);
         atomic_set(&HFSPLUS_I(inode).opencnt, 0);
         HFSPLUS_I(inode).flags = 0;
         memset(HFSPLUS_I(inode).first_extents, 0, sizeof(hfsplus_extent_rec));
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index ce97a54518d8..e834e578c93f 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -34,7 +34,7 @@ struct inode *hfsplus_iget(struct super_block *sb, unsigned long ino)
                 return inode;
 
         INIT_LIST_HEAD(&HFSPLUS_I(inode).open_dir_list);
-        init_MUTEX(&HFSPLUS_I(inode).extents_lock);
+        mutex_init(&HFSPLUS_I(inode).extents_lock);
         HFSPLUS_I(inode).flags = 0;
         HFSPLUS_I(inode).rsrc_inode = NULL;
         atomic_set(&HFSPLUS_I(inode).opencnt, 0);
@@ -485,7 +485,7 @@ static struct file_system_type hfsplus_fs_type = {
         .fs_flags       = FS_REQUIRES_DEV,
 };
 
-static void hfsplus_init_once(struct kmem_cache *cachep, void *p)
+static void hfsplus_init_once(void *p)
 {
         struct hfsplus_inode_info *i = p;
 
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 5222345ddccf..d6ecabf4d231 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -822,7 +822,7 @@ int hostfs_rename(struct inode *from_ino, struct dentry *from,
         return err;
 }
 
-int hostfs_permission(struct inode *ino, int desired, struct nameidata *nd)
+int hostfs_permission(struct inode *ino, int desired)
 {
         char *name;
         int r = 0, w = 0, x = 0, err;
diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c
index d256559b4104..d9c59a775449 100644
--- a/fs/hpfs/namei.c
+++ b/fs/hpfs/namei.c
@@ -415,7 +415,7 @@ again:
                 d_drop(dentry);
                 spin_lock(&dentry->d_lock);
                 if (atomic_read(&dentry->d_count) > 1 ||
-                    permission(inode, MAY_WRITE, NULL) ||
+                    generic_permission(inode, MAY_WRITE, NULL) ||
                     !S_ISREG(inode->i_mode) ||
                     get_write_access(inode)) {
                         spin_unlock(&dentry->d_lock);
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index f63a699ec659..b8ae9c90ada0 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -173,7 +173,7 @@ static void hpfs_destroy_inode(struct inode *inode)
         kmem_cache_free(hpfs_inode_cachep, hpfs_i(inode));
 }
 
-static void init_once(struct kmem_cache *cachep, void *foo)
+static void init_once(void *foo)
 {
         struct hpfs_inode_info *ei = (struct hpfs_inode_info *) foo;
 
diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c
index 65077aa90f0a..2b3d1828db99 100644
--- a/fs/hppfs/hppfs.c
+++ b/fs/hppfs/hppfs.c
@@ -655,20 +655,13 @@ static void *hppfs_follow_link(struct dentry *dentry, struct nameidata *nd)
         return proc_dentry->d_inode->i_op->follow_link(proc_dentry, nd);
 }
 
-int hppfs_permission(struct inode *inode, int mask, struct nameidata *nd)
-{
-        return generic_permission(inode, mask, NULL);
-}
-
 static const struct inode_operations hppfs_dir_iops = {
         .lookup         = hppfs_lookup,
-        .permission     = hppfs_permission,
 };
 
 static const struct inode_operations hppfs_link_iops = {
         .readlink       = hppfs_readlink,
         .follow_link    = hppfs_follow_link,
-        .permission     = hppfs_permission,
 };
 
 static struct inode *get_inode(struct super_block *sb, struct dentry *dentry)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index aeabf80f81a5..3f58923fb39b 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -53,6 +53,7 @@ int sysctl_hugetlb_shm_group;
 enum {
         Opt_size, Opt_nr_inodes,
         Opt_mode, Opt_uid, Opt_gid,
+        Opt_pagesize,
         Opt_err,
 };
 
@@ -62,6 +63,7 @@ static match_table_t tokens = {
         {Opt_mode,      "mode=%o"},
         {Opt_uid,       "uid=%u"},
         {Opt_gid,       "gid=%u"},
+        {Opt_pagesize,  "pagesize=%s"},
         {Opt_err,       NULL},
 };
 
@@ -80,6 +82,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
         struct inode *inode = file->f_path.dentry->d_inode;
         loff_t len, vma_len;
         int ret;
+        struct hstate *h = hstate_file(file);
 
         /*
          * vma address alignment (but not the pgoff alignment) has
@@ -92,7 +95,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
         vma->vm_flags |= VM_HUGETLB | VM_RESERVED;
         vma->vm_ops = &hugetlb_vm_ops;
 
-        if (vma->vm_pgoff & ~(HPAGE_MASK >> PAGE_SHIFT))
+        if (vma->vm_pgoff & ~(huge_page_mask(h) >> PAGE_SHIFT))
                 return -EINVAL;
 
         vma_len = (loff_t)(vma->vm_end - vma->vm_start);
@@ -103,9 +106,9 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
         ret = -ENOMEM;
         len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
 
-        if (vma->vm_flags & VM_MAYSHARE &&
-            hugetlb_reserve_pages(inode, vma->vm_pgoff >> (HPAGE_SHIFT-PAGE_SHIFT),
-                                  len >> HPAGE_SHIFT))
+        if (hugetlb_reserve_pages(inode,
+                                vma->vm_pgoff >> huge_page_order(h),
+                                len >> huge_page_shift(h), vma))
                 goto out;
 
         ret = 0;
@@ -130,20 +133,21 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
         struct mm_struct *mm = current->mm;
         struct vm_area_struct *vma;
         unsigned long start_addr;
+        struct hstate *h = hstate_file(file);
 
-        if (len & ~HPAGE_MASK)
+        if (len & ~huge_page_mask(h))
                 return -EINVAL;
         if (len > TASK_SIZE)
                 return -ENOMEM;
 
         if (flags & MAP_FIXED) {
-                if (prepare_hugepage_range(addr, len))
+                if (prepare_hugepage_range(file, addr, len))
                         return -EINVAL;
                 return addr;
         }
 
         if (addr) {
-                addr = ALIGN(addr, HPAGE_SIZE);
+                addr = ALIGN(addr, huge_page_size(h));
                 vma = find_vma(mm, addr);
                 if (TASK_SIZE - len >= addr &&
                     (!vma || addr + len <= vma->vm_start))
@@ -156,7 +160,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
                 start_addr = TASK_UNMAPPED_BASE;
 
 full_search:
-        addr = ALIGN(start_addr, HPAGE_SIZE);
+        addr = ALIGN(start_addr, huge_page_size(h));
 
         for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
                 /* At this point:  (!vma || addr < vma->vm_end). */
@@ -174,7 +178,7 @@ full_search:
 
                 if (!vma || addr + len <= vma->vm_start)
                         return addr;
-                addr = ALIGN(vma->vm_end, HPAGE_SIZE);
+                addr = ALIGN(vma->vm_end, huge_page_size(h));
         }
 }
 #endif
@@ -225,10 +229,11 @@ hugetlbfs_read_actor(struct page *page, unsigned long offset,
 static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
                               size_t len, loff_t *ppos)
 {
+        struct hstate *h = hstate_file(filp);
         struct address_space *mapping = filp->f_mapping;
         struct inode *inode = mapping->host;
-        unsigned long index = *ppos >> HPAGE_SHIFT;
-        unsigned long offset = *ppos & ~HPAGE_MASK;
+        unsigned long index = *ppos >> huge_page_shift(h);
+        unsigned long offset = *ppos & ~huge_page_mask(h);
         unsigned long end_index;
         loff_t isize;
         ssize_t retval = 0;
@@ -243,17 +248,17 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
         if (!isize)
                 goto out;
 
-        end_index = (isize - 1) >> HPAGE_SHIFT;
+        end_index = (isize - 1) >> huge_page_shift(h);
         for (;;) {
                 struct page *page;
-                int nr, ret;
+                unsigned long nr, ret;
 
                 /* nr is the maximum number of bytes to copy from this page */
-                nr = HPAGE_SIZE;
+                nr = huge_page_size(h);
                 if (index >= end_index) {
                         if (index > end_index)
                                 goto out;
-                        nr = ((isize - 1) & ~HPAGE_MASK) + 1;
+                        nr = ((isize - 1) & ~huge_page_mask(h)) + 1;
                         if (nr <= offset) {
                                 goto out;
                         }
@@ -287,8 +292,8 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
                 offset += ret;
                 retval += ret;
                 len -= ret;
-                index += offset >> HPAGE_SHIFT;
-                offset &= ~HPAGE_MASK;
+                index += offset >> huge_page_shift(h);
+                offset &= ~huge_page_mask(h);
 
                 if (page)
                         page_cache_release(page);
@@ -298,7 +303,7 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
                         break;
         }
 out:
-        *ppos = ((loff_t)index << HPAGE_SHIFT) + offset;
+        *ppos = ((loff_t)index << huge_page_shift(h)) + offset;
         mutex_unlock(&inode->i_mutex);
         return retval;
 }
@@ -339,8 +344,9 @@ static void truncate_huge_page(struct page *page)
 
 static void truncate_hugepages(struct inode *inode, loff_t lstart)
 {
+        struct hstate *h = hstate_inode(inode);
         struct address_space *mapping = &inode->i_data;
-        const pgoff_t start = lstart >> HPAGE_SHIFT;
+        const pgoff_t start = lstart >> huge_page_shift(h);
         struct pagevec pvec;
         pgoff_t next;
         int i, freed = 0;
@@ -441,7 +447,7 @@ hugetlb_vmtruncate_list(struct prio_tree_root *root, pgoff_t pgoff)
                         v_offset = 0;
 
                 __unmap_hugepage_range(vma,
-                                vma->vm_start + v_offset, vma->vm_end);
+                                vma->vm_start + v_offset, vma->vm_end, NULL);
         }
 }
 
@@ -449,8 +455,9 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
 {
         pgoff_t pgoff;
         struct address_space *mapping = inode->i_mapping;
+        struct hstate *h = hstate_inode(inode);
 
-        BUG_ON(offset & ~HPAGE_MASK);
+        BUG_ON(offset & ~huge_page_mask(h));
         pgoff = offset >> PAGE_SHIFT;
 
         i_size_write(inode, offset);
@@ -465,6 +472,7 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
 static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr)
 {
         struct inode *inode = dentry->d_inode;
+        struct hstate *h = hstate_inode(inode);
         int error;
         unsigned int ia_valid = attr->ia_valid;
 
@@ -476,7 +484,7 @@ static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr)
 
         if (ia_valid & ATTR_SIZE) {
                 error = -EINVAL;
-                if (!(attr->ia_size & ~HPAGE_MASK))
+                if (!(attr->ia_size & ~huge_page_mask(h)))
                         error = hugetlb_vmtruncate(inode, attr->ia_size);
                 if (error)
                         goto out;
@@ -610,9 +618,10 @@ static int hugetlbfs_set_page_dirty(struct page *page)
 static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
         struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb);
+        struct hstate *h = hstate_inode(dentry->d_inode);
 
         buf->f_type = HUGETLBFS_MAGIC;
-        buf->f_bsize = HPAGE_SIZE;
+        buf->f_bsize = huge_page_size(h);
         if (sbinfo) {
                 spin_lock(&sbinfo->stat_lock);
                 /* If no limits set, just report 0 for max/free/used
@@ -696,7 +705,7 @@ static const struct address_space_operations hugetlbfs_aops = {
 };
 
 
-static void init_once(struct kmem_cache *cachep, void *foo)
+static void init_once(void *foo)
 {
         struct hugetlbfs_inode_info *ei = (struct hugetlbfs_inode_info *)foo;
 
@@ -743,6 +752,8 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
         char *p, *rest;
         substring_t args[MAX_OPT_ARGS];
         int option;
+        unsigned long long size = 0;
+        enum { NO_SIZE, SIZE_STD, SIZE_PERCENT } setsize = NO_SIZE;
 
         if (!options)
                 return 0;
@@ -773,17 +784,13 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
                         break;
 
                 case Opt_size: {
-                        unsigned long long size;
                         /* memparse() will accept a K/M/G without a digit */
                         if (!isdigit(*args[0].from))
                                 goto bad_val;
                         size = memparse(args[0].from, &rest);
-                        if (*rest == '%') {
-                                size <<= HPAGE_SHIFT;
-                                size *= max_huge_pages;
-                                do_div(size, 100);
-                        }
-                        pconfig->nr_blocks = (size >> HPAGE_SHIFT);
+                        setsize = SIZE_STD;
+                        if (*rest == '%')
+                                setsize = SIZE_PERCENT;
                         break;
                 }
 
@@ -794,6 +801,19 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
                         pconfig->nr_inodes = memparse(args[0].from, &rest);
                         break;
 
+                case Opt_pagesize: {
+                        unsigned long ps;
+                        ps = memparse(args[0].from, &rest);
+                        pconfig->hstate = size_to_hstate(ps);
+                        if (!pconfig->hstate) {
+                                printk(KERN_ERR
+                                "hugetlbfs: Unsupported page size %lu MB\n",
+                                        ps >> 20);
+                                return -EINVAL;
+                        }
+                        break;
+                }
+
                 default:
                         printk(KERN_ERR "hugetlbfs: Bad mount option: \"%s\"\n",
                                  p);
@@ -801,6 +821,18 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
                         break;
                 }
         }
+
+        /* Do size after hstate is set up */
+        if (setsize > NO_SIZE) {
+                struct hstate *h = pconfig->hstate;
+                if (setsize == SIZE_PERCENT) {
+                        size <<= huge_page_shift(h);
+                        size *= h->max_huge_pages;
+                        do_div(size, 100);
+                }
+                pconfig->nr_blocks = (size >> huge_page_shift(h));
+        }
+
         return 0;
 
 bad_val:
@@ -825,6 +857,7 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
         config.uid = current->fsuid;
         config.gid = current->fsgid;
         config.mode = 0755;
+        config.hstate = &default_hstate;
         ret = hugetlbfs_parse_options(data, &config);
         if (ret)
                 return ret;
@@ -833,14 +866,15 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
         if (!sbinfo)
                 return -ENOMEM;
         sb->s_fs_info = sbinfo;
+        sbinfo->hstate = config.hstate;
         spin_lock_init(&sbinfo->stat_lock);
         sbinfo->max_blocks = config.nr_blocks;
         sbinfo->free_blocks = config.nr_blocks;
         sbinfo->max_inodes = config.nr_inodes;
         sbinfo->free_inodes = config.nr_inodes;
         sb->s_maxbytes = MAX_LFS_FILESIZE;
-        sb->s_blocksize = HPAGE_SIZE;
-        sb->s_blocksize_bits = HPAGE_SHIFT;
+        sb->s_blocksize = huge_page_size(config.hstate);
+        sb->s_blocksize_bits = huge_page_shift(config.hstate);
         sb->s_magic = HUGETLBFS_MAGIC;
         sb->s_op = &hugetlbfs_ops;
         sb->s_time_gran = 1;
@@ -942,7 +976,8 @@ struct file *hugetlb_file_setup(const char *name, size_t size)
                 goto out_dentry;
 
         error = -ENOMEM;
-        if (hugetlb_reserve_pages(inode, 0, size >> HPAGE_SHIFT))
+        if (hugetlb_reserve_pages(inode, 0,
+                        size >> huge_page_shift(hstate_inode(inode)), NULL))
                 goto out_inode;
 
         d_instantiate(dentry, inode);
diff --git a/fs/inode.c b/fs/inode.c
index c36d9480335c..b6726f644530 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -209,7 +209,7 @@ void inode_init_once(struct inode *inode)
         INIT_LIST_HEAD(&inode->i_dentry);
         INIT_LIST_HEAD(&inode->i_devices);
         INIT_RADIX_TREE(&inode->i_data.page_tree, GFP_ATOMIC);
-        rwlock_init(&inode->i_data.tree_lock);
+        spin_lock_init(&inode->i_data.tree_lock);
         spin_lock_init(&inode->i_data.i_mmap_lock);
         INIT_LIST_HEAD(&inode->i_data.private_list);
         spin_lock_init(&inode->i_data.private_lock);
@@ -224,7 +224,7 @@ void inode_init_once(struct inode *inode)
 
 EXPORT_SYMBOL(inode_init_once);
 
-static void init_once(struct kmem_cache * cachep, void *foo)
+static void init_once(void *foo)
 {
         struct inode * inode = (struct inode *) foo;
 
diff --git a/fs/inotify_user.c b/fs/inotify_user.c
index 6676c06bb7c1..60249429a253 100644
--- a/fs/inotify_user.c
+++ b/fs/inotify_user.c
@@ -354,20 +354,20 @@ static void inotify_dev_event_dequeue(struct inotify_device *dev)
 }
 
 /*
- * find_inode - resolve a user-given path to a specific inode and return a nd
+ * find_inode - resolve a user-given path to a specific inode
  */
-static int find_inode(const char __user *dirname, struct nameidata *nd,
+static int find_inode(const char __user *dirname, struct path *path,
                       unsigned flags)
 {
         int error;
 
-        error = __user_walk(dirname, flags, nd);
+        error = user_path_at(AT_FDCWD, dirname, flags, path);
         if (error)
                 return error;
         /* you can only watch an inode if you have read permissions on it */
-        error = vfs_permission(nd, MAY_READ);
+        error = inode_permission(path->dentry->d_inode, MAY_READ);
         if (error)
-                path_put(&nd->path);
+                path_put(path);
         return error;
 }
 
@@ -566,7 +566,7 @@ static const struct inotify_operations inotify_user_ops = {
         .destroy_watch  = free_inotify_user_watch,
 };
 
-asmlinkage long sys_inotify_init(void)
+asmlinkage long sys_inotify_init1(int flags)
 {
         struct inotify_device *dev;
         struct inotify_handle *ih;
@@ -574,7 +574,14 @@ asmlinkage long sys_inotify_init(void)
         struct file *filp;
         int fd, ret;
 
-        fd = get_unused_fd();
+        /* Check the IN_* constants for consistency.  */
+        BUILD_BUG_ON(IN_CLOEXEC != O_CLOEXEC);
+        BUILD_BUG_ON(IN_NONBLOCK != O_NONBLOCK);
+
+        if (flags & ~(IN_CLOEXEC | IN_NONBLOCK))
+                return -EINVAL;
+
+        fd = get_unused_fd_flags(flags & O_CLOEXEC);
         if (fd < 0)
                 return fd;
 
@@ -610,7 +617,7 @@ asmlinkage long sys_inotify_init(void)
         filp->f_path.dentry = dget(inotify_mnt->mnt_root);
         filp->f_mapping = filp->f_path.dentry->d_inode->i_mapping;
         filp->f_mode = FMODE_READ;
-        filp->f_flags = O_RDONLY;
+        filp->f_flags = O_RDONLY | (flags & O_NONBLOCK);
         filp->private_data = dev;
 
         INIT_LIST_HEAD(&dev->events);
@@ -638,11 +645,16 @@ out_put_fd:
         return ret;
 }
 
-asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, u32 mask)
+asmlinkage long sys_inotify_init(void)
+{
+        return sys_inotify_init1(0);
+}
+
+asmlinkage long sys_inotify_add_watch(int fd, const char __user *pathname, u32 mask)
 {
         struct inode *inode;
         struct inotify_device *dev;
-        struct nameidata nd;
+        struct path path;
         struct file *filp;
         int ret, fput_needed;
         unsigned flags = 0;
@@ -662,12 +674,12 @@ asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, u32 mask)
         if (mask & IN_ONLYDIR)
                 flags |= LOOKUP_DIRECTORY;
 
-        ret = find_inode(path, &nd, flags);
+        ret = find_inode(pathname, &path, flags);
         if (unlikely(ret))
                 goto fput_and_out;
 
-        /* inode held in place by reference to nd; dev by fget on fd */
-        inode = nd.path.dentry->d_inode;
+        /* inode held in place by reference to path; dev by fget on fd */
+        inode = path.dentry->d_inode;
         dev = filp->private_data;
 
         mutex_lock(&dev->up_mutex);
@@ -676,7 +688,7 @@ asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, u32 mask)
                 ret = create_watch(dev, inode, mask);
         mutex_unlock(&dev->up_mutex);
 
-        path_put(&nd.path);
+        path_put(&path);
 fput_and_out:
         fput_light(filp, fput_needed);
         return ret;
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 044a254d526b..26948a6033b6 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -73,7 +73,7 @@ static void isofs_destroy_inode(struct inode *inode)
         kmem_cache_free(isofs_inode_cachep, ISOFS_I(inode));
 }
 
-static void init_once(struct kmem_cache *cachep, void *foo)
+static void init_once(void *foo)
 {
         struct iso_inode_info *ei = foo;
 
diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c
index 6bd48f0a7047..c2fb2dd0131f 100644
--- a/fs/isofs/rock.c
+++ b/fs/isofs/rock.c
@@ -209,6 +209,11 @@ repeat:
 
         while (rs.len > 2) { /* There may be one byte for padding somewhere */
                 rr = (struct rock_ridge *)rs.chr;
+                /*
+                 * Ignore rock ridge info if rr->len is out of range, but
+                 * don't return -EIO because that would make the file
+                 * invisible.
+                 */
                 if (rr->len < 3)
                         goto out;       /* Something got screwed up here */
                 sig = isonum_721(rs.chr);
@@ -216,8 +221,12 @@ repeat:
                         goto eio;
                 rs.chr += rr->len;
                 rs.len -= rr->len;
+                /*
+                 * As above, just ignore the rock ridge info if rr->len
+                 * is bogus.
+                 */
                 if (rs.len < 0)
-                        goto eio;       /* corrupted isofs */
+                        goto out;       /* Something got screwed up here */
 
                 switch (sig) {
                 case SIG('R', 'R'):
@@ -307,6 +316,11 @@ parse_rock_ridge_inode_internal(struct iso_directory_record *de,
 repeat:
         while (rs.len > 2) { /* There may be one byte for padding somewhere */
                 rr = (struct rock_ridge *)rs.chr;
+                /*
+                 * Ignore rock ridge info if rr->len is out of range, but
+                 * don't return -EIO because that would make the file
+                 * invisible.
+                 */
                 if (rr->len < 3)
                         goto out;       /* Something got screwed up here */
                 sig = isonum_721(rs.chr);
@@ -314,8 +328,12 @@ repeat:
                         goto eio;
                 rs.chr += rr->len;
                 rs.len -= rr->len;
+                /*
+                 * As above, just ignore the rock ridge info if rr->len
+                 * is bogus.
+                 */
                 if (rs.len < 0)
-                        goto eio;       /* corrupted isofs */
+                        goto out;       /* Something got screwed up here */
 
                 switch (sig) {
 #ifndef CONFIG_ZISOFS           /* No flag for SF or ZF */
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index 5a8ca61498ca..ae08c057e751 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -36,7 +36,7 @@ static void journal_end_buffer_io_sync(struct buffer_head *bh, int uptodate)
 
 /*
  * When an ext3-ordered file is truncated, it is possible that many pages are
- * not sucessfully freed, because they are attached to a committing transaction.
+ * not successfully freed, because they are attached to a committing transaction.
  * After the transaction commits, these pages are left on the LRU, with no
  * ->mapping, and with attached buffers.  These pages are trivially reclaimable
  * by the VM, but their apparent absence upsets the VM accounting, and it makes
@@ -45,8 +45,8 @@ static void journal_end_buffer_io_sync(struct buffer_head *bh, int uptodate)
  * So here, we have a buffer which has just come off the forget list.  Look to
  * see if we can strip all buffers from the backing page.
  *
- * Called under lock_journal(), and possibly under journal_datalist_lock.  The
- * caller provided us with a ref against the buffer, and we drop that here.
+ * Called under journal->j_list_lock.  The caller provided us with a ref
+ * against the buffer, and we drop that here.
  */
 static void release_buffer_page(struct buffer_head *bh)
 {
@@ -63,7 +63,7 @@ static void release_buffer_page(struct buffer_head *bh)
                 goto nope;
 
         /* OK, it's a truncated page */
-        if (TestSetPageLocked(page))
+        if (!trylock_page(page))
                 goto nope;
 
         page_cache_get(page);
@@ -78,6 +78,19 @@ nope:
 }
 
 /*
+ * Decrement reference counter for data buffer. If it has been marked
+ * 'BH_Freed', release it and the page to which it belongs if possible.
+ */
+static void release_data_buffer(struct buffer_head *bh)
+{
+        if (buffer_freed(bh)) {
+                clear_buffer_freed(bh);
+                release_buffer_page(bh);
+        } else
+                put_bh(bh);
+}
+
+/*
  * Try to acquire jbd_lock_bh_state() against the buffer, when j_list_lock is
  * held.  For ranking reasons we must trylock.  If we lose, schedule away and
  * return 0.  j_list_lock is dropped in this case.
@@ -172,7 +185,7 @@ static void journal_do_submit_data(struct buffer_head **wbuf, int bufs)
 /*
  *  Submit all the data buffers to disk
  */
-static void journal_submit_data_buffers(journal_t *journal,
+static int journal_submit_data_buffers(journal_t *journal,
                                 transaction_t *commit_transaction)
 {
         struct journal_head *jh;
@@ -180,6 +193,7 @@ static void journal_submit_data_buffers(journal_t *journal,
         int locked;
         int bufs = 0;
         struct buffer_head **wbuf = journal->j_wbuf;
+        int err = 0;
 
         /*
          * Whenever we unlock the journal and sleep, things can get added
@@ -207,7 +221,7 @@ write_out_data:
                  * blocking lock_buffer().
                  */
                 if (buffer_dirty(bh)) {
-                        if (test_set_buffer_locked(bh)) {
+                        if (!trylock_buffer(bh)) {
                                 BUFFER_TRACE(bh, "needs blocking lock");
                                 spin_unlock(&journal->j_list_lock);
                                 /* Write out all data to prevent deadlocks */
@@ -231,7 +245,7 @@ write_out_data:
                         if (locked)
                                 unlock_buffer(bh);
                         BUFFER_TRACE(bh, "already cleaned up");
-                        put_bh(bh);
+                        release_data_buffer(bh);
                         continue;
                 }
                 if (locked && test_clear_buffer_dirty(bh)) {
@@ -253,15 +267,17 @@ write_out_data:
                         put_bh(bh);
                 } else {
                         BUFFER_TRACE(bh, "writeout complete: unfile");
+                        if (unlikely(!buffer_uptodate(bh)))
+                                err = -EIO;
                         __journal_unfile_buffer(jh);
                         jbd_unlock_bh_state(bh);
                         if (locked)
                                 unlock_buffer(bh);
                         journal_remove_journal_head(bh);
-                        /* Once for our safety reference, once for
+                        /* One for our safety reference, other for
                          * journal_remove_journal_head() */
                         put_bh(bh);
-                        put_bh(bh);
+                        release_data_buffer(bh);
                 }
 
                 if (need_resched() || spin_needbreak(&journal->j_list_lock)) {
@@ -271,6 +287,8 @@ write_out_data:
         }
         spin_unlock(&journal->j_list_lock);
         journal_do_submit_data(wbuf, bufs);
+
+        return err;
 }
 
 /*
@@ -410,8 +428,7 @@ void journal_commit_transaction(journal_t *journal)
          * Now start flushing things to disk, in the order they appear
          * on the transaction lists.  Data blocks go first.
          */
-        err = 0;
-        journal_submit_data_buffers(journal, commit_transaction);
+        err = journal_submit_data_buffers(journal, commit_transaction);
 
         /*
          * Wait for all previously submitted IO to complete.
@@ -426,10 +443,21 @@ void journal_commit_transaction(journal_t *journal)
                 if (buffer_locked(bh)) {
                         spin_unlock(&journal->j_list_lock);
                         wait_on_buffer(bh);
-                        if (unlikely(!buffer_uptodate(bh)))
-                                err = -EIO;
                         spin_lock(&journal->j_list_lock);
                 }
+                if (unlikely(!buffer_uptodate(bh))) {
+                        if (!trylock_page(bh->b_page)) {
+                                spin_unlock(&journal->j_list_lock);
+                                lock_page(bh->b_page);
+                                spin_lock(&journal->j_list_lock);
+                        }
+                        if (bh->b_page->mapping)
+                                set_bit(AS_EIO, &bh->b_page->mapping->flags);
+
+                        unlock_page(bh->b_page);
+                        SetPageError(bh->b_page);
+                        err = -EIO;
+                }
                 if (!inverted_lock(journal, bh)) {
                         put_bh(bh);
                         spin_lock(&journal->j_list_lock);
@@ -443,17 +471,21 @@ void journal_commit_transaction(journal_t *journal)
                 } else {
                         jbd_unlock_bh_state(bh);
                 }
-                put_bh(bh);
+                release_data_buffer(bh);
                 cond_resched_lock(&journal->j_list_lock);
         }
         spin_unlock(&journal->j_list_lock);
 
-        if (err)
-                journal_abort(journal, err);
+        if (err) {
+                char b[BDEVNAME_SIZE];
 
-        journal_write_revoke_records(journal, commit_transaction);
+                printk(KERN_WARNING
+                        "JBD: Detected IO errors while flushing file data "
+                        "on %s\n", bdevname(journal->j_fs_dev, b));
+                err = 0;
+        }
 
-        jbd_debug(3, "JBD: commit phase 2\n");
+        journal_write_revoke_records(journal, commit_transaction);
 
         /*
          * If we found any dirty or locked buffers, then we should have
diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c
index b99c3b3654c4..aa7143a8349b 100644
--- a/fs/jbd/journal.c
+++ b/fs/jbd/journal.c
@@ -68,7 +68,6 @@ EXPORT_SYMBOL(journal_set_features);
 EXPORT_SYMBOL(journal_create);
 EXPORT_SYMBOL(journal_load);
 EXPORT_SYMBOL(journal_destroy);
-EXPORT_SYMBOL(journal_update_superblock);
 EXPORT_SYMBOL(journal_abort);
 EXPORT_SYMBOL(journal_errno);
 EXPORT_SYMBOL(journal_ack_err);
@@ -1636,9 +1635,10 @@ static int journal_init_journal_head_cache(void)
 
 static void journal_destroy_journal_head_cache(void)
 {
-        J_ASSERT(journal_head_cache != NULL);
-        kmem_cache_destroy(journal_head_cache);
-        journal_head_cache = NULL;
+        if (journal_head_cache) {
+                kmem_cache_destroy(journal_head_cache);
+                journal_head_cache = NULL;
+        }
 }
 
 /*
diff --git a/fs/jbd/revoke.c b/fs/jbd/revoke.c
index 1bb43e987f4b..c7bd649bbbdc 100644
--- a/fs/jbd/revoke.c
+++ b/fs/jbd/revoke.c
@@ -166,138 +166,123 @@ static struct jbd_revoke_record_s *find_revoke_record(journal_t *journal,
         return NULL;
 }
 
+void journal_destroy_revoke_caches(void)
+{
+        if (revoke_record_cache) {
+                kmem_cache_destroy(revoke_record_cache);
+                revoke_record_cache = NULL;
+        }
+        if (revoke_table_cache) {
+                kmem_cache_destroy(revoke_table_cache);
+                revoke_table_cache = NULL;
+        }
+}
+
 int __init journal_init_revoke_caches(void)
 {
+        J_ASSERT(!revoke_record_cache);
+        J_ASSERT(!revoke_table_cache);
+
         revoke_record_cache = kmem_cache_create("revoke_record",
                                            sizeof(struct jbd_revoke_record_s),
                                            0,
                                            SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY,
                                            NULL);
         if (!revoke_record_cache)
-                return -ENOMEM;
+                goto record_cache_failure;
 
         revoke_table_cache = kmem_cache_create("revoke_table",
                                            sizeof(struct jbd_revoke_table_s),
                                            0, SLAB_TEMPORARY, NULL);
-        if (!revoke_table_cache) {
-                kmem_cache_destroy(revoke_record_cache);
-                revoke_record_cache = NULL;
-                return -ENOMEM;
-        }
+        if (!revoke_table_cache)
+                goto table_cache_failure;
+
         return 0;
-}
 
-void journal_destroy_revoke_caches(void)
-{
-        kmem_cache_destroy(revoke_record_cache);
-        revoke_record_cache = NULL;
-        kmem_cache_destroy(revoke_table_cache);
-        revoke_table_cache = NULL;
+table_cache_failure:
+        journal_destroy_revoke_caches();
+record_cache_failure:
+        return -ENOMEM;
 }
 
-/* Initialise the revoke table for a given journal to a given size. */
-
-int journal_init_revoke(journal_t *journal, int hash_size)
+static struct jbd_revoke_table_s *journal_init_revoke_table(int hash_size)
 {
-        int shift, tmp;
+        int shift = 0;
+        int tmp = hash_size;
+        struct jbd_revoke_table_s *table;
 
-        J_ASSERT (journal->j_revoke_table[0] == NULL);
+        table = kmem_cache_alloc(revoke_table_cache, GFP_KERNEL);
+        if (!table)
+                goto out;
 
-        shift = 0;
-        tmp = hash_size;
         while((tmp >>= 1UL) != 0UL)
                 shift++;
 
-        journal->j_revoke_table[0] = kmem_cache_alloc(revoke_table_cache, GFP_KERNEL);
-        if (!journal->j_revoke_table[0])
-                return -ENOMEM;
-        journal->j_revoke = journal->j_revoke_table[0];
-
-        /* Check that the hash_size is a power of two */
-        J_ASSERT(is_power_of_2(hash_size));
-
-        journal->j_revoke->hash_size = hash_size;
-
-        journal->j_revoke->hash_shift = shift;
-
-        journal->j_revoke->hash_table =
+        table->hash_size = hash_size;
+        table->hash_shift = shift;
+        table->hash_table =
                 kmalloc(hash_size * sizeof(struct list_head), GFP_KERNEL);
-        if (!journal->j_revoke->hash_table) {
-                kmem_cache_free(revoke_table_cache, journal->j_revoke_table[0]);
-                journal->j_revoke = NULL;
-                return -ENOMEM;
+        if (!table->hash_table) {
+                kmem_cache_free(revoke_table_cache, table);
+                table = NULL;
+                goto out;
         }
 
         for (tmp = 0; tmp < hash_size; tmp++)
-                INIT_LIST_HEAD(&journal->j_revoke->hash_table[tmp]);
+                INIT_LIST_HEAD(&table->hash_table[tmp]);
 
-        journal->j_revoke_table[1] = kmem_cache_alloc(revoke_table_cache, GFP_KERNEL);
-        if (!journal->j_revoke_table[1]) {
-                kfree(journal->j_revoke_table[0]->hash_table);
-                kmem_cache_free(revoke_table_cache, journal->j_revoke_table[0]);
-                return -ENOMEM;
+out:
+        return table;
+}
+
+static void journal_destroy_revoke_table(struct jbd_revoke_table_s *table)
+{
+        int i;
+        struct list_head *hash_list;
+
+        for (i = 0; i < table->hash_size; i++) {
+                hash_list = &table->hash_table[i];
+                J_ASSERT(list_empty(hash_list));
         }
 
-        journal->j_revoke = journal->j_revoke_table[1];
+        kfree(table->hash_table);
+        kmem_cache_free(revoke_table_cache, table);
+}
 
-        /* Check that the hash_size is a power of two */
+/* Initialise the revoke table for a given journal to a given size. */
+int journal_init_revoke(journal_t *journal, int hash_size)
+{
+        J_ASSERT(journal->j_revoke_table[0] == NULL);
         J_ASSERT(is_power_of_2(hash_size));
 
-        journal->j_revoke->hash_size = hash_size;
+        journal->j_revoke_table[0] = journal_init_revoke_table(hash_size);
+        if (!journal->j_revoke_table[0])
+                goto fail0;
 
-        journal->j_revoke->hash_shift = shift;
+        journal->j_revoke_table[1] = journal_init_revoke_table(hash_size);
+        if (!journal->j_revoke_table[1])
+                goto fail1;
 
-        journal->j_revoke->hash_table =
-                kmalloc(hash_size * sizeof(struct list_head), GFP_KERNEL);
-        if (!journal->j_revoke->hash_table) {
-                kfree(journal->j_revoke_table[0]->hash_table);
-                kmem_cache_free(revoke_table_cache, journal->j_revoke_table[0]);
-                kmem_cache_free(revoke_table_cache, journal->j_revoke_table[1]);
-                journal->j_revoke = NULL;
-                return -ENOMEM;
-        }
-
-        for (tmp = 0; tmp < hash_size; tmp++)
-                INIT_LIST_HEAD(&journal->j_revoke->hash_table[tmp]);
+        journal->j_revoke = journal->j_revoke_table[1];
 
         spin_lock_init(&journal->j_revoke_lock);
 
         return 0;
-}
 
-/* Destoy a journal's revoke table.  The table must already be empty! */
+fail1:
+        journal_destroy_revoke_table(journal->j_revoke_table[0]);
+fail0:
+        return -ENOMEM;
+}
 
+/* Destroy a journal's revoke table.  The table must already be empty! */
 void journal_destroy_revoke(journal_t *journal)
 {
-        struct jbd_revoke_table_s *table;
-        struct list_head *hash_list;
-        int i;
-
-        table = journal->j_revoke_table[0];
-        if (!table)
-                return;
-
-        for (i=0; i<table->hash_size; i++) {
-                hash_list = &table->hash_table[i];
-                J_ASSERT (list_empty(hash_list));
-        }
-
-        kfree(table->hash_table);
-        kmem_cache_free(revoke_table_cache, table);
-        journal->j_revoke = NULL;
-
-        table = journal->j_revoke_table[1];
-        if (!table)
-                return;
-
-        for (i=0; i<table->hash_size; i++) {
-                hash_list = &table->hash_table[i];
-                J_ASSERT (list_empty(hash_list));
-        }
-
-        kfree(table->hash_table);
-        kmem_cache_free(revoke_table_cache, table);
         journal->j_revoke = NULL;
+        if (journal->j_revoke_table[0])
+                journal_destroy_revoke_table(journal->j_revoke_table[0]);
+        if (journal->j_revoke_table[1])
+                journal_destroy_revoke_table(journal->j_revoke_table[1]);
 }
 
 
diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c
index 67ff2024c23c..0540ca27a446 100644
--- a/fs/jbd/transaction.c
+++ b/fs/jbd/transaction.c
@@ -291,7 +291,7 @@ handle_t *journal_start(journal_t *journal, int nblocks)
                 goto out;
         }
 
-        lock_acquire(&handle->h_lockdep_map, 0, 0, 0, 2, _THIS_IP_);
+        lock_map_acquire(&handle->h_lockdep_map);
 
 out:
         return handle;
@@ -1448,7 +1448,7 @@ int journal_stop(handle_t *handle)
                 spin_unlock(&journal->j_state_lock);
         }
 
-        lock_release(&handle->h_lockdep_map, 1, _THIS_IP_);
+        lock_map_release(&handle->h_lockdep_map);
 
         jbd_free_handle(handle);
         return err;
@@ -1648,12 +1648,42 @@ out:
         return;
 }
 
+/*
+ * journal_try_to_free_buffers() could race with journal_commit_transaction()
+ * The latter might still hold the a count on buffers when inspecting
+ * them on t_syncdata_list or t_locked_list.
+ *
+ * journal_try_to_free_buffers() will call this function to
+ * wait for the current transaction to finish syncing data buffers, before
+ * tryinf to free that buffer.
+ *
+ * Called with journal->j_state_lock held.
+ */
+static void journal_wait_for_transaction_sync_data(journal_t *journal)
+{
+        transaction_t *transaction = NULL;
+        tid_t tid;
+
+        spin_lock(&journal->j_state_lock);
+        transaction = journal->j_committing_transaction;
+
+        if (!transaction) {
+                spin_unlock(&journal->j_state_lock);
+                return;
+        }
+
+        tid = transaction->t_tid;
+        spin_unlock(&journal->j_state_lock);
+        log_wait_commit(journal, tid);
+}
 
 /**
  * int journal_try_to_free_buffers() - try to free page buffers.
  * @journal: journal for operation
  * @page: to try and free
- * @unused_gfp_mask: unused
+ * @gfp_mask: we use the mask to detect how hard should we try to release
+ * buffers. If __GFP_WAIT and __GFP_FS is set, we wait for commit code to
+ * release the buffers.
  *
  *
  * For all the buffers on this page,
@@ -1682,9 +1712,11 @@ out:
  * journal_try_to_free_buffer() is changing its state.  But that
  * cannot happen because we never reallocate freed data as metadata
  * while the data is part of a transaction.  Yes?
+ *
+ * Return 0 on failure, 1 on success
  */
 int journal_try_to_free_buffers(journal_t *journal,
-                                struct page *page, gfp_t unused_gfp_mask)
+                                struct page *page, gfp_t gfp_mask)
 {
         struct buffer_head *head;
         struct buffer_head *bh;
@@ -1713,7 +1745,28 @@ int journal_try_to_free_buffers(journal_t *journal,
                 if (buffer_jbd(bh))
                         goto busy;
         } while ((bh = bh->b_this_page) != head);
+
         ret = try_to_free_buffers(page);
+
+        /*
+         * There are a number of places where journal_try_to_free_buffers()
+         * could race with journal_commit_transaction(), the later still
+         * holds the reference to the buffers to free while processing them.
+         * try_to_free_buffers() failed to free those buffers. Some of the
+         * caller of releasepage() request page buffers to be dropped, otherwise
+         * treat the fail-to-free as errors (such as generic_file_direct_IO())
+         *
+         * So, if the caller of try_to_release_page() wants the synchronous
+         * behaviour(i.e make sure buffers are dropped upon return),
+         * let's wait for the current transaction to finish flush of
+         * dirty data buffers, then try to free those buffers again,
+         * with the journal locked.
+         */
+        if (ret == 0 && (gfp_mask & __GFP_WAIT) && (gfp_mask & __GFP_FS)) {
+                journal_wait_for_transaction_sync_data(journal);
+                ret = try_to_free_buffers(page);
+        }
+
 busy:
         return ret;
 }
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index f8b3be873226..f2ad061e95ec 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -67,7 +67,7 @@ static void release_buffer_page(struct buffer_head *bh)
                 goto nope;
 
         /* OK, it's a truncated page */
-        if (TestSetPageLocked(page))
+        if (!trylock_page(page))
                 goto nope;
 
         page_cache_get(page);
@@ -262,8 +262,18 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
                 jinode->i_flags |= JI_COMMIT_RUNNING;
                 spin_unlock(&journal->j_list_lock);
                 err = filemap_fdatawait(jinode->i_vfs_inode->i_mapping);
-                if (!ret)
-                        ret = err;
+                if (err) {
+                        /*
+                         * Because AS_EIO is cleared by
+                         * wait_on_page_writeback_range(), set it again so
+                         * that user process can get -EIO from fsync().
+                         */
+                        set_bit(AS_EIO,
+                                &jinode->i_vfs_inode->i_mapping->flags);
+
+                        if (!ret)
+                                ret = err;
+                }
                 spin_lock(&journal->j_list_lock);
                 jinode->i_flags &= ~JI_COMMIT_RUNNING;
                 wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
@@ -670,8 +680,14 @@ start_journal_io:
          * commit block, which happens below in such setting.
          */
         err = journal_finish_inode_data_buffers(journal, commit_transaction);
-        if (err)
-                jbd2_journal_abort(journal, err);
+        if (err) {
+                char b[BDEVNAME_SIZE];
+
+                printk(KERN_WARNING
+                        "JBD2: Detected IO errors while flushing file data "
+                        "on %s\n", bdevname(journal->j_fs_dev, b));
+                err = 0;
+        }
 
         /* Lo and behold: we have just managed to send a transaction to
            the log.  Before we can commit it, wait for the IO so far to
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index b26c6d9fe6ae..8207a01c4edb 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -68,7 +68,6 @@ EXPORT_SYMBOL(jbd2_journal_set_features);
 EXPORT_SYMBOL(jbd2_journal_create);
 EXPORT_SYMBOL(jbd2_journal_load);
 EXPORT_SYMBOL(jbd2_journal_destroy);
-EXPORT_SYMBOL(jbd2_journal_update_superblock);
 EXPORT_SYMBOL(jbd2_journal_abort);
 EXPORT_SYMBOL(jbd2_journal_errno);
 EXPORT_SYMBOL(jbd2_journal_ack_err);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 4f7cadbb19fa..e5d540588fa9 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -301,7 +301,7 @@ handle_t *jbd2_journal_start(journal_t *journal, int nblocks)
                 goto out;
         }
 
-        lock_acquire(&handle->h_lockdep_map, 0, 0, 0, 2, _THIS_IP_);
+        lock_map_acquire(&handle->h_lockdep_map);
 out:
         return handle;
 }
@@ -1279,7 +1279,7 @@ int jbd2_journal_stop(handle_t *handle)
                 spin_unlock(&journal->j_state_lock);
         }
 
-        lock_release(&handle->h_lockdep_map, 1, _THIS_IP_);
+        lock_map_release(&handle->h_lockdep_map);
 
         jbd2_free_handle(handle);
         return err;
diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c
index 4c80404a9aba..d98713777a1b 100644
--- a/fs/jffs2/acl.c
+++ b/fs/jffs2/acl.c
@@ -314,7 +314,7 @@ static int jffs2_check_acl(struct inode *inode, int mask)
         return -EAGAIN;
 }
 
-int jffs2_permission(struct inode *inode, int mask, struct nameidata *nd)
+int jffs2_permission(struct inode *inode, int mask)
 {
         return generic_permission(inode, mask, jffs2_check_acl);
 }
diff --git a/fs/jffs2/acl.h b/fs/jffs2/acl.h
index 0bb7f003fd80..8ca058aed384 100644
--- a/fs/jffs2/acl.h
+++ b/fs/jffs2/acl.h
@@ -28,7 +28,7 @@ struct jffs2_acl_header {
 
 #define JFFS2_ACL_NOT_CACHED ((void *)-1)
 
-extern int jffs2_permission(struct inode *, int, struct nameidata *);
+extern int jffs2_permission(struct inode *, int);
 extern int jffs2_acl_chmod(struct inode *);
 extern int jffs2_init_acl_pre(struct inode *, struct inode *, int *);
 extern int jffs2_init_acl_post(struct inode *);
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index c0c141f6fde1..cd219ef55254 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -38,7 +38,7 @@ const struct file_operations jffs2_dir_operations =
 {
         .read =         generic_read_dir,
         .readdir =      jffs2_readdir,
-        .ioctl =        jffs2_ioctl,
+        .unlocked_ioctl=jffs2_ioctl,
         .fsync =        jffs2_fsync
 };
 
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index 5e920343b2c5..5a98aa87c853 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -46,7 +46,7 @@ const struct file_operations jffs2_file_operations =
         .aio_read =     generic_file_aio_read,
         .write =        do_sync_write,
         .aio_write =    generic_file_aio_write,
-        .ioctl =        jffs2_ioctl,
+        .unlocked_ioctl=jffs2_ioctl,
         .mmap =         generic_file_readonly_mmap,
         .fsync =        jffs2_fsync,
         .splice_read =  generic_file_splice_read,
diff --git a/fs/jffs2/ioctl.c b/fs/jffs2/ioctl.c
index e2177210f621..9d41f43e47bb 100644
--- a/fs/jffs2/ioctl.c
+++ b/fs/jffs2/ioctl.c
@@ -12,8 +12,7 @@
 #include <linux/fs.h>
 #include "nodelist.h"
 
-int jffs2_ioctl(struct inode *inode, struct file *filp, unsigned int cmd,
-                unsigned long arg)
+long jffs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
         /* Later, this will provide for lsattr.jffs2 and chattr.jffs2, which
            will include compression support etc. */
diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h
index 2cc866cf134f..5e194a5c8e29 100644
--- a/fs/jffs2/os-linux.h
+++ b/fs/jffs2/os-linux.h
@@ -167,7 +167,7 @@ int jffs2_fsync(struct file *, struct dentry *, int);
 int jffs2_do_readpage_unlock (struct inode *inode, struct page *pg);
 
 /* ioctl.c */
-int jffs2_ioctl(struct inode *, struct file *, unsigned int, unsigned long);
+long jffs2_ioctl(struct file *, unsigned int, unsigned long);
 
 /* symlink.c */
 extern const struct inode_operations jffs2_symlink_inode_operations;
diff --git a/fs/jffs2/summary.c b/fs/jffs2/summary.c
index 629af01e5ade..6caf1e1ee26d 100644
--- a/fs/jffs2/summary.c
+++ b/fs/jffs2/summary.c
@@ -23,6 +23,8 @@
 
 int jffs2_sum_init(struct jffs2_sb_info *c)
 {
+        uint32_t sum_size = max_t(uint32_t, c->sector_size, MAX_SUMMARY_SIZE);
+
         c->summary = kzalloc(sizeof(struct jffs2_summary), GFP_KERNEL);
 
         if (!c->summary) {
@@ -30,7 +32,7 @@ int jffs2_sum_init(struct jffs2_sb_info *c)
                 return -ENOMEM;
         }
 
-        c->summary->sum_buf = vmalloc(c->sector_size);
+        c->summary->sum_buf = kmalloc(sum_size, GFP_KERNEL);
 
         if (!c->summary->sum_buf) {
                 JFFS2_WARNING("Can't allocate buffer for writing out summary information!\n");
@@ -49,7 +51,7 @@ void jffs2_sum_exit(struct jffs2_sb_info *c)
 
         jffs2_sum_disable_collecting(c->summary);
 
-        vfree(c->summary->sum_buf);
+        kfree(c->summary->sum_buf);
         c->summary->sum_buf = NULL;
 
         kfree(c->summary);
@@ -665,7 +667,7 @@ crc_err:
 /* Write summary data to flash - helper function for jffs2_sum_write_sumnode() */
 
 static int jffs2_sum_write_data(struct jffs2_sb_info *c, struct jffs2_eraseblock *jeb,
-                                        uint32_t infosize, uint32_t datasize, int padsize)
+                                uint32_t infosize, uint32_t datasize, int padsize)
 {
         struct jffs2_raw_summary isum;
         union jffs2_sum_mem *temp;
@@ -676,6 +678,26 @@ static int jffs2_sum_write_data(struct jffs2_sb_info *c, struct jffs2_eraseblock
         int ret;
         size_t retlen;
 
+        if (padsize + datasize > MAX_SUMMARY_SIZE) {
+                /* It won't fit in the buffer. Abort summary for this jeb */
+                jffs2_sum_disable_collecting(c->summary);
+
+                JFFS2_WARNING("Summary too big (%d data, %d pad) in eraseblock at %08x\n",
+                              datasize, padsize, jeb->offset);
+                /* Non-fatal */
+                return 0;
+        }
+        /* Is there enough space for summary? */
+        if (padsize < 0) {
+                /* don't try to write out summary for this jeb */
+                jffs2_sum_disable_collecting(c->summary);
+
+                JFFS2_WARNING("Not enough space for summary, padsize = %d\n",
+                              padsize);
+                /* Non-fatal */
+                return 0;
+        }
+
         memset(c->summary->sum_buf, 0xff, datasize);
         memset(&isum, 0, sizeof(isum));
 
@@ -821,7 +843,7 @@ int jffs2_sum_write_sumnode(struct jffs2_sb_info *c)
 {
         int datasize, infosize, padsize;
         struct jffs2_eraseblock *jeb;
-        int ret;
+        int ret = 0;
 
         dbg_summary("called\n");
 
@@ -841,16 +863,6 @@ int jffs2_sum_write_sumnode(struct jffs2_sb_info *c)
         infosize += padsize;
         datasize += padsize;
 
-        /* Is there enough space for summary? */
-        if (padsize < 0) {
-                /* don't try to write out summary for this jeb */
-                jffs2_sum_disable_collecting(c->summary);
-
-                JFFS2_WARNING("Not enough space for summary, padsize = %d\n", padsize);
-                spin_lock(&c->erase_completion_lock);
-                return 0;
-        }
-
         ret = jffs2_sum_write_data(c, jeb, infosize, datasize, padsize);
         spin_lock(&c->erase_completion_lock);
         return ret;
diff --git a/fs/jffs2/summary.h b/fs/jffs2/summary.h
index 8bf34f2fa5ce..60207a2ae952 100644
--- a/fs/jffs2/summary.h
+++ b/fs/jffs2/summary.h
@@ -13,6 +13,12 @@
 #ifndef JFFS2_SUMMARY_H
 #define JFFS2_SUMMARY_H
 
+/* Limit summary size to 64KiB so that we can kmalloc it. If the summary
+   is larger than that, we have to just ditch it and avoid using summary
+   for the eraseblock in question... and it probably doesn't hurt us much
+   anyway. */
+#define MAX_SUMMARY_SIZE 65536
+
 #include <linux/uio.h>
 #include <linux/jffs2.h>
 
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index 7da69eae49e4..efd401257ed9 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -44,7 +44,7 @@ static void jffs2_destroy_inode(struct inode *inode)
         kmem_cache_free(jffs2_inode_cachep, JFFS2_INODE_INFO(inode));
 }
 
-static void jffs2_i_init_once(struct kmem_cache *cachep, void *foo)
+static void jffs2_i_init_once(void *foo)
 {
         struct jffs2_inode_info *f = foo;
 
diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c
index 4d84bdc88299..d3e5c33665de 100644
--- a/fs/jfs/acl.c
+++ b/fs/jfs/acl.c
@@ -140,7 +140,7 @@ static int jfs_check_acl(struct inode *inode, int mask)
         return -EAGAIN;
 }
 
-int jfs_permission(struct inode *inode, int mask, struct nameidata *nd)
+int jfs_permission(struct inode *inode, int mask)
 {
         return generic_permission(inode, mask, jfs_check_acl);
 }
diff --git a/fs/jfs/jfs_acl.h b/fs/jfs/jfs_acl.h
index 455fa4292045..88475f10a389 100644
--- a/fs/jfs/jfs_acl.h
+++ b/fs/jfs/jfs_acl.h
@@ -20,7 +20,7 @@
 
 #ifdef CONFIG_JFS_POSIX_ACL
 
-int jfs_permission(struct inode *, int, struct nameidata *);
+int jfs_permission(struct inode *, int);
 int jfs_init_acl(tid_t, struct inode *, struct inode *);
 int jfs_setattr(struct dentry *, struct iattr *);
 
diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c
index 854ff0ec574f..c350057087dd 100644
--- a/fs/jfs/jfs_metapage.c
+++ b/fs/jfs/jfs_metapage.c
@@ -182,7 +182,7 @@ static inline void remove_metapage(struct page *page, struct metapage *mp)
 
 #endif
 
-static void init_once(struct kmem_cache *cachep, void *foo)
+static void init_once(void *foo)
 {
         struct metapage *mp = (struct metapage *)foo;
 
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 0288e6d7936a..3630718be395 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -22,6 +22,7 @@
 #include <linux/parser.h>
 #include <linux/completion.h>
 #include <linux/vfs.h>
+#include <linux/quotaops.h>
 #include <linux/mount.h>
 #include <linux/moduleparam.h>
 #include <linux/kthread.h>
@@ -759,7 +760,7 @@ static struct file_system_type jfs_fs_type = {
         .fs_flags       = FS_REQUIRES_DEV,
 };
 
-static void init_once(struct kmem_cache *cachep, void *foo)
+static void init_once(void *foo)
 {
         struct jfs_inode_info *jfs_ip = (struct jfs_inode_info *) foo;
 
diff --git a/fs/libfs.c b/fs/libfs.c
index baeb71ee1cde..1add676a19df 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -216,8 +216,8 @@ int get_sb_pseudo(struct file_system_type *fs_type, char *name,
 
         s->s_flags = MS_NOUSER;
         s->s_maxbytes = ~0ULL;
-        s->s_blocksize = 1024;
-        s->s_blocksize_bits = 10;
+        s->s_blocksize = PAGE_SIZE;
+        s->s_blocksize_bits = PAGE_SHIFT;
         s->s_magic = magic;
         s->s_op = ops ? ops : &simple_super_operations;
         s->s_time_gran = 1;
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index 1f6dc518505c..31668b690e03 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -582,7 +582,15 @@ again:
         }
         if (status < 0)
                 goto out_unlock;
-        status = nlm_stat_to_errno(resp->status);
+        /*
+         * EAGAIN doesn't make sense for sleeping locks, and in some
+         * cases NLM_LCK_DENIED is returned for a permanent error.  So
+         * turn it into an ENOLCK.
+         */
+        if (resp->status == nlm_lck_denied && (fl_flags & FL_SLEEP))
+                status = -ENOLCK;
+        else
+                status = nlm_stat_to_errno(resp->status);
 out_unblock:
         nlmclnt_finish_block(block);
 out:
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index 399444639337..4a714f64515b 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -83,7 +83,7 @@ nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp,
 {
         struct nlm_host *host;
         struct nlm_file *file;
-        int rc = rpc_success;
+        __be32 rc = rpc_success;
 
         dprintk("lockd: TEST4        called\n");
         resp->cookie = argp->cookie;
@@ -116,7 +116,7 @@ nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
 {
         struct nlm_host *host;
         struct nlm_file *file;
-        int rc = rpc_success;
+        __be32 rc = rpc_success;
 
         dprintk("lockd: LOCK          called\n");
 
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index 821b9acdfb66..cf0d5c2c318d 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -418,8 +418,8 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
                         goto out;
                 case -EAGAIN:
                         ret = nlm_lck_denied;
-                        break;
-                case -EINPROGRESS:
+                        goto out;
+                case FILE_LOCK_DEFERRED:
                         if (wait)
                                 break;
                         /* Filesystem lock operation is in progress
@@ -434,10 +434,6 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
                         goto out;
         }
 
-        ret = nlm_lck_denied;
-        if (!wait)
-                goto out;
-
         ret = nlm_lck_blocked;
 
         /* Append to list of blocked */
@@ -507,7 +503,7 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
         }
 
         error = vfs_test_lock(file->f_file, &lock->fl);
-        if (error == -EINPROGRESS) {
+        if (error == FILE_LOCK_DEFERRED) {
                 ret = nlmsvc_defer_lock_rqst(rqstp, block);
                 goto out;
         }
@@ -731,8 +727,7 @@ nlmsvc_grant_blocked(struct nlm_block *block)
         switch (error) {
         case 0:
                 break;
-        case -EAGAIN:
-        case -EINPROGRESS:
+        case FILE_LOCK_DEFERRED:
                 dprintk("lockd: lock still blocked error %d\n", error);
                 nlmsvc_insert_block(block, NLM_NEVER);
                 nlmsvc_release_block(block);
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index 76019d2ff72d..76262c1986f2 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -112,7 +112,7 @@ nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp,
 {
         struct nlm_host *host;
         struct nlm_file *file;
-        int rc = rpc_success;
+        __be32 rc = rpc_success;
 
         dprintk("lockd: TEST          called\n");
         resp->cookie = argp->cookie;
@@ -146,7 +146,7 @@ nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
 {
         struct nlm_host *host;
         struct nlm_file *file;
-        int rc = rpc_success;
+        __be32 rc = rpc_success;
 
         dprintk("lockd: LOCK          called\n");
 
diff --git a/fs/locks.c b/fs/locks.c
index dce8c747371c..5eb259e3cd38 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -201,7 +201,7 @@ EXPORT_SYMBOL(locks_init_lock);
  * Initialises the fields of the file lock which are invariant for
  * free file_locks.
  */
-static void init_once(struct kmem_cache *cache, void *foo)
+static void init_once(void *foo)
 {
         struct file_lock *lock = (struct file_lock *) foo;
 
@@ -779,8 +779,10 @@ find_conflict:
                 if (!flock_locks_conflict(request, fl))
                         continue;
                 error = -EAGAIN;
-                if (request->fl_flags & FL_SLEEP)
-                        locks_insert_block(fl, request);
+                if (!(request->fl_flags & FL_SLEEP))
+                        goto out;
+                error = FILE_LOCK_DEFERRED;
+                locks_insert_block(fl, request);
                 goto out;
         }
         if (request->fl_flags & FL_ACCESS)
@@ -836,7 +838,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
                         error = -EDEADLK;
                         if (posix_locks_deadlock(request, fl))
                                 goto out;
-                        error = -EAGAIN;
+                        error = FILE_LOCK_DEFERRED;
                         locks_insert_block(fl, request);
                         goto out;
                 }
@@ -1035,7 +1037,7 @@ int posix_lock_file_wait(struct file *filp, struct file_lock *fl)
         might_sleep ();
         for (;;) {
                 error = posix_lock_file(filp, fl, NULL);
-                if ((error != -EAGAIN) || !(fl->fl_flags & FL_SLEEP))
+                if (error != FILE_LOCK_DEFERRED)
                         break;
                 error = wait_event_interruptible(fl->fl_wait, !fl->fl_next);
                 if (!error)
@@ -1107,9 +1109,7 @@ int locks_mandatory_area(int read_write, struct inode *inode,
 
         for (;;) {
                 error = __posix_lock_file(inode, &fl, NULL);
-                if (error != -EAGAIN)
-                        break;
-                if (!(fl.fl_flags & FL_SLEEP))
+                if (error != FILE_LOCK_DEFERRED)
                         break;
                 error = wait_event_interruptible(fl.fl_wait, !fl.fl_next);
                 if (!error) {
@@ -1531,7 +1531,7 @@ int flock_lock_file_wait(struct file *filp, struct file_lock *fl)
         might_sleep();
         for (;;) {
                 error = flock_lock_file(filp, fl);
-                if ((error != -EAGAIN) || !(fl->fl_flags & FL_SLEEP))
+                if (error != FILE_LOCK_DEFERRED)
                         break;
                 error = wait_event_interruptible(fl->fl_wait, !fl->fl_next);
                 if (!error)
@@ -1716,17 +1716,17 @@ out:
  * fl_grant is set. Callers expecting ->lock() to return asynchronously
  * will only use F_SETLK, not F_SETLKW; they will set FL_SLEEP if (and only if)
  * the request is for a blocking lock. When ->lock() does return asynchronously,
- * it must return -EINPROGRESS, and call ->fl_grant() when the lock
+ * it must return FILE_LOCK_DEFERRED, and call ->fl_grant() when the lock
  * request completes.
  * If the request is for non-blocking lock the file system should return
- * -EINPROGRESS then try to get the lock and call the callback routine with
- * the result. If the request timed out the callback routine will return a
+ * FILE_LOCK_DEFERRED then try to get the lock and call the callback routine
+ * with the result. If the request timed out the callback routine will return a
  * nonzero return code and the file system should release the lock. The file
  * system is also responsible to keep a corresponding posix lock when it
  * grants a lock so the VFS can find out which locks are locally held and do
  * the correct lock cleanup when required.
  * The underlying filesystem must not drop the kernel lock or call
- * ->fl_grant() before returning to the caller with a -EINPROGRESS
+ * ->fl_grant() before returning to the caller with a FILE_LOCK_DEFERRED
  * return code.
  */
 int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf)
@@ -1738,6 +1738,30 @@ int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, str
 }
 EXPORT_SYMBOL_GPL(vfs_lock_file);
 
+static int do_lock_file_wait(struct file *filp, unsigned int cmd,
+                             struct file_lock *fl)
+{
+        int error;
+
+        error = security_file_lock(filp, fl->fl_type);
+        if (error)
+                return error;
+
+        for (;;) {
+                error = vfs_lock_file(filp, cmd, fl, NULL);
+                if (error != FILE_LOCK_DEFERRED)
+                        break;
+                error = wait_event_interruptible(fl->fl_wait, !fl->fl_next);
+                if (!error)
+                        continue;
+
+                locks_delete_block(fl);
+                break;
+        }
+
+        return error;
+}
+
 /* Apply the lock described by l to an open file descriptor.
  * This implements both the F_SETLK and F_SETLKW commands of fcntl().
  */
@@ -1795,26 +1819,7 @@ again:
                 goto out;
         }
 
-        error = security_file_lock(filp, file_lock->fl_type);
-        if (error)
-                goto out;
-
-        if (filp->f_op && filp->f_op->lock != NULL)
-                error = filp->f_op->lock(filp, cmd, file_lock);
-        else {
-                for (;;) {
-                        error = posix_lock_file(filp, file_lock, NULL);
-                        if (error != -EAGAIN || cmd == F_SETLK)
-                                break;
-                        error = wait_event_interruptible(file_lock->fl_wait,
-                                        !file_lock->fl_next);
-                        if (!error)
-                                continue;
-
-                        locks_delete_block(file_lock);
-                        break;
-                }
-        }
+        error = do_lock_file_wait(filp, cmd, file_lock);
 
         /*
          * Attempt to detect a close/fcntl race and recover by
@@ -1932,26 +1937,7 @@ again:
                 goto out;
         }
 
-        error = security_file_lock(filp, file_lock->fl_type);
-        if (error)
-                goto out;
-
-        if (filp->f_op && filp->f_op->lock != NULL)
-                error = filp->f_op->lock(filp, cmd, file_lock);
-        else {
-                for (;;) {
-                        error = posix_lock_file(filp, file_lock, NULL);
-                        if (error != -EAGAIN || cmd == F_SETLK64)
-                                break;
-                        error = wait_event_interruptible(file_lock->fl_wait,
-                                        !file_lock->fl_next);
-                        if (!error)
-                                continue;
-
-                        locks_delete_block(file_lock);
-                        break;
-                }
-        }
+        error = do_lock_file_wait(filp, cmd, file_lock);
 
         /*
          * Attempt to detect a close/fcntl race and recover by
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index 84f6242ba6fc..d1d1eb84679d 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -68,7 +68,7 @@ static void minix_destroy_inode(struct inode *inode)
         kmem_cache_free(minix_inode_cachep, minix_i(inode));
 }
 
-static void init_once(struct kmem_cache * cachep, void *foo)
+static void init_once(void *foo)
 {
         struct minix_inode_info *ei = (struct minix_inode_info *) foo;
 
@@ -256,9 +256,6 @@ static int minix_fill_super(struct super_block *s, void *data, int silent)
         if (!s->s_root)
                 goto out_iput;
 
-        if (!NO_TRUNCATE)
-                s->s_root->d_op = &minix_dentry_operations;
-
         if (!(s->s_flags & MS_RDONLY)) {
                 if (sbi->s_version != MINIX_V3) /* s_state is now out from V3 sb */
                         ms->s_state &= ~MINIX_VALID_FS;
diff --git a/fs/minix/minix.h b/fs/minix/minix.h
index 326edfe96108..e6a0b193bea4 100644
--- a/fs/minix/minix.h
+++ b/fs/minix/minix.h
@@ -2,11 +2,6 @@
 #include <linux/pagemap.h>
 #include <linux/minix_fs.h>
 
-/*
- * change the define below to 0 if you want names > info->s_namelen chars to be
- * truncated. Else they will be disallowed (ENAMETOOLONG).
- */
-#define NO_TRUNCATE 1
 #define INODE_VERSION(inode)    minix_sb(inode->i_sb)->s_version
 #define MINIX_V1                0x0001          /* original minix fs */
 #define MINIX_V2                0x0002          /* minix V2 fs */
@@ -83,7 +78,6 @@ extern const struct inode_operations minix_file_inode_operations;
 extern const struct inode_operations minix_dir_inode_operations;
 extern const struct file_operations minix_file_operations;
 extern const struct file_operations minix_dir_operations;
-extern struct dentry_operations minix_dentry_operations;
 
 static inline struct minix_sb_info *minix_sb(struct super_block *sb)
 {
diff --git a/fs/minix/namei.c b/fs/minix/namei.c
index 102241bc9c79..32b131cd6121 100644
--- a/fs/minix/namei.c
+++ b/fs/minix/namei.c
@@ -18,30 +18,6 @@ static int add_nondir(struct dentry *dentry, struct inode *inode)
         return err;
 }
 
-static int minix_hash(struct dentry *dentry, struct qstr *qstr)
-{
-        unsigned long hash;
-        int i;
-        const unsigned char *name;
-
-        i = minix_sb(dentry->d_inode->i_sb)->s_namelen;
-        if (i >= qstr->len)
-                return 0;
-        /* Truncate the name in place, avoids having to define a compare
-           function. */
-        qstr->len = i;
-        name = qstr->name;
-        hash = init_name_hash();
-        while (i--)
-                hash = partial_name_hash(*name++, hash);
-        qstr->hash = end_name_hash(hash);
-        return 0;
-}
-
-struct dentry_operations minix_dentry_operations = {
-        .d_hash         = minix_hash,
-};
-
 static struct dentry *minix_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
 {
         struct inode * inode = NULL;
diff --git a/fs/msdos/namei.c b/fs/msdos/namei.c
index 1f7f2956412a..e844b9809d27 100644
--- a/fs/msdos/namei.c
+++ b/fs/msdos/namei.c
@@ -14,12 +14,7 @@
 
 /* Characters that are undesirable in an MS-DOS file name */
 static unsigned char bad_chars[] = "*?<>|\"";
-static unsigned char bad_if_strict_pc[] = "+=,; ";
-/* GEMDOS is less restrictive */
-static unsigned char bad_if_strict_atari[] = " ";
-
-#define bad_if_strict(opts) \
-        ((opts)->atari ? bad_if_strict_atari : bad_if_strict_pc)
+static unsigned char bad_if_strict[] = "+=,; ";
 
 /***** Formats an MS-DOS file name. Rejects invalid names. */
 static int msdos_format_name(const unsigned char *name, int len,
@@ -40,21 +35,20 @@ static int msdos_format_name(const unsigned char *name, int len,
                         /* Get rid of dot - test for it elsewhere */
                         name++;
                         len--;
-                } else if (!opts->atari)
+                } else
                         return -EINVAL;
         }
         /*
-         * disallow names that _really_ start with a dot for MS-DOS,
-         * GEMDOS does not care
+         * disallow names that _really_ start with a dot
          */
-        space = !opts->atari;
+        space = 1;
         c = 0;
         for (walk = res; len && walk - res < 8; walk++) {
                 c = *name++;
                 len--;
                 if (opts->name_check != 'r' && strchr(bad_chars, c))
                         return -EINVAL;
-                if (opts->name_check == 's' && strchr(bad_if_strict(opts), c))
+                if (opts->name_check == 's' && strchr(bad_if_strict, c))
                         return -EINVAL;
                 if (c >= 'A' && c <= 'Z' && opts->name_check == 's')
                         return -EINVAL;
@@ -94,7 +88,7 @@ static int msdos_format_name(const unsigned char *name, int len,
                         if (opts->name_check != 'r' && strchr(bad_chars, c))
                                 return -EINVAL;
                         if (opts->name_check == 's' &&
-                            strchr(bad_if_strict(opts), c))
+                            strchr(bad_if_strict, c))
                                 return -EINVAL;
                         if (c < ' ' || c == ':' || c == '\\')
                                 return -EINVAL;
@@ -243,6 +237,7 @@ static int msdos_add_entry(struct inode *dir, const unsigned char *name,
                            int is_dir, int is_hid, int cluster,
                            struct timespec *ts, struct fat_slot_info *sinfo)
 {
+        struct msdos_sb_info *sbi = MSDOS_SB(dir->i_sb);
         struct msdos_dir_entry de;
         __le16 time, date;
         int err;
@@ -252,7 +247,7 @@ static int msdos_add_entry(struct inode *dir, const unsigned char *name,
         if (is_hid)
                 de.attr |= ATTR_HIDDEN;
         de.lcase = 0;
-        fat_date_unix2dos(ts->tv_sec, &time, &date);
+        fat_date_unix2dos(ts->tv_sec, &time, &date, sbi->options.tz_utc);
         de.cdate = de.adate = 0;
         de.ctime = 0;
         de.ctime_cs = 0;
diff --git a/fs/namei.c b/fs/namei.c
index 01e67dddcc3d..4ea63ed5e791 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -31,7 +31,6 @@
 #include <linux/file.h>
 #include <linux/fcntl.h>
 #include <linux/device_cgroup.h>
-#include <asm/namei.h>
 #include <asm/uaccess.h>
 
 #define ACC_MODE(x) ("\000\004\002\006"[(x)&O_ACCMODE])
@@ -185,6 +184,8 @@ int generic_permission(struct inode *inode, int mask,
 {
         umode_t                 mode = inode->i_mode;
 
+        mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
+
         if (current->fsuid == inode->i_uid)
                 mode >>= 6;
         else {
@@ -203,7 +204,7 @@ int generic_permission(struct inode *inode, int mask,
         /*
          * If the DACs are ok we don't need any capability check.
          */
-        if (((mode & mask & (MAY_READ|MAY_WRITE|MAY_EXEC)) == mask))
+        if ((mask & ~mode) == 0)
                 return 0;
 
  check_capabilities:
@@ -226,13 +227,9 @@ int generic_permission(struct inode *inode, int mask,
         return -EACCES;
 }
 
-int permission(struct inode *inode, int mask, struct nameidata *nd)
+int inode_permission(struct inode *inode, int mask)
 {
-        int retval, submask;
-        struct vfsmount *mnt = NULL;
-
-        if (nd)
-                mnt = nd->path.mnt;
+        int retval;
 
         if (mask & MAY_WRITE) {
                 umode_t mode = inode->i_mode;
@@ -251,19 +248,9 @@ int permission(struct inode *inode, int mask, struct nameidata *nd)
                         return -EACCES;
         }
 
-        if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode)) {
-                /*
-                 * MAY_EXEC on regular files is denied if the fs is mounted
-                 * with the "noexec" flag.
-                 */
-                if (mnt && (mnt->mnt_flags & MNT_NOEXEC))
-                        return -EACCES;
-        }
-
         /* Ordinary permission routines do not understand MAY_APPEND. */
-        submask = mask & ~MAY_APPEND;
         if (inode->i_op && inode->i_op->permission) {
-                retval = inode->i_op->permission(inode, submask, nd);
+                retval = inode->i_op->permission(inode, mask);
                 if (!retval) {
                         /*
                          * Exec permission on a regular file is denied if none
@@ -277,7 +264,7 @@ int permission(struct inode *inode, int mask, struct nameidata *nd)
                                 return -EACCES;
                 }
         } else {
-                retval = generic_permission(inode, submask, NULL);
+                retval = generic_permission(inode, mask, NULL);
         }
         if (retval)
                 return retval;
@@ -286,7 +273,8 @@ int permission(struct inode *inode, int mask, struct nameidata *nd)
         if (retval)
                 return retval;
 
-        return security_inode_permission(inode, mask, nd);
+        return security_inode_permission(inode,
+                        mask & (MAY_READ|MAY_WRITE|MAY_EXEC|MAY_APPEND));
 }
 
 /**
@@ -301,7 +289,7 @@ int permission(struct inode *inode, int mask, struct nameidata *nd)
  */
 int vfs_permission(struct nameidata *nd, int mask)
 {
-        return permission(nd->path.dentry->d_inode, mask, nd);
+        return inode_permission(nd->path.dentry->d_inode, mask);
 }
 
 /**
@@ -318,7 +306,7 @@ int vfs_permission(struct nameidata *nd, int mask)
  */
 int file_permission(struct file *file, int mask)
 {
-        return permission(file->f_path.dentry->d_inode, mask, NULL);
+        return inode_permission(file->f_path.dentry->d_inode, mask);
 }
 
 /*
@@ -459,8 +447,7 @@ static struct dentry * cached_lookup(struct dentry * parent, struct qstr * name,
  * short-cut DAC fails, then call permission() to do more
  * complete permission check.
  */
-static int exec_permission_lite(struct inode *inode,
-                                       struct nameidata *nd)
+static int exec_permission_lite(struct inode *inode)
 {
         umode_t mode = inode->i_mode;
 
@@ -486,7 +473,7 @@ static int exec_permission_lite(struct inode *inode,
 
         return -EACCES;
 ok:
-        return security_inode_permission(inode, MAY_EXEC, nd);
+        return security_inode_permission(inode, MAY_EXEC);
 }
 
 /*
@@ -519,7 +506,14 @@ static struct dentry * real_lookup(struct dentry * parent, struct qstr * name, s
          */
         result = d_lookup(parent, name);
         if (!result) {
-                struct dentry * dentry = d_alloc(parent, name);
+                struct dentry *dentry;
+
+                /* Don't create child dentry for a dead directory. */
+                result = ERR_PTR(-ENOENT);
+                if (IS_DEADDIR(dir))
+                        goto out_unlock;
+
+                dentry = d_alloc(parent, name);
                 result = ERR_PTR(-ENOMEM);
                 if (dentry) {
                         result = dir->i_op->lookup(dir, dentry, nd);
@@ -528,6 +522,7 @@ static struct dentry * real_lookup(struct dentry * parent, struct qstr * name, s
                         else
                                 result = dentry;
                 }
+out_unlock:
                 mutex_unlock(&dir->i_mutex);
                 return result;
         }
@@ -545,27 +540,16 @@ static struct dentry * real_lookup(struct dentry * parent, struct qstr * name, s
         return result;
 }
 
-static int __emul_lookup_dentry(const char *, struct nameidata *);
-
 /* SMP-safe */
-static __always_inline int
+static __always_inline void
 walk_init_root(const char *name, struct nameidata *nd)
 {
         struct fs_struct *fs = current->fs;
 
         read_lock(&fs->lock);
-        if (fs->altroot.dentry && !(nd->flags & LOOKUP_NOALT)) {
-                nd->path = fs->altroot;
-                path_get(&fs->altroot);
-                read_unlock(&fs->lock);
-                if (__emul_lookup_dentry(name,nd))
-                        return 0;
-                read_lock(&fs->lock);
-        }
         nd->path = fs->root;
         path_get(&fs->root);
         read_unlock(&fs->lock);
-        return 1;
 }
 
 /*
@@ -606,12 +590,9 @@ static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *l
 
         if (*link == '/') {
                 path_put(&nd->path);
-                if (!walk_init_root(link, nd))
-                        /* weird __emul_prefix() stuff did it */
-                        goto out;
+                walk_init_root(link, nd);
         }
         res = link_path_walk(link, nd);
-out:
         if (nd->depth || res || nd->last_type!=LAST_NORM)
                 return res;
         /*
@@ -889,7 +870,7 @@ static int __link_path_walk(const char *name, struct nameidata *nd)
                 unsigned int c;
 
                 nd->flags |= LOOKUP_CONTINUE;
-                err = exec_permission_lite(inode, nd);
+                err = exec_permission_lite(inode);
                 if (err == -EAGAIN)
                         err = vfs_permission(nd, MAY_EXEC);
                 if (err)
@@ -1060,67 +1041,6 @@ static int path_walk(const char *name, struct nameidata *nd)
         return link_path_walk(name, nd);
 }
 
-/* 
- * SMP-safe: Returns 1 and nd will have valid dentry and mnt, if
- * everything is done. Returns 0 and drops input nd, if lookup failed;
- */
-static int __emul_lookup_dentry(const char *name, struct nameidata *nd)
-{
-        if (path_walk(name, nd))
-                return 0;               /* something went wrong... */
-
-        if (!nd->path.dentry->d_inode ||
-            S_ISDIR(nd->path.dentry->d_inode->i_mode)) {
-                struct path old_path = nd->path;
-                struct qstr last = nd->last;
-                int last_type = nd->last_type;
-                struct fs_struct *fs = current->fs;
-
-                /*
-                 * NAME was not found in alternate root or it's a directory.
-                 * Try to find it in the normal root:
-                 */
-                nd->last_type = LAST_ROOT;
-                read_lock(&fs->lock);
-                nd->path = fs->root;
-                path_get(&fs->root);
-                read_unlock(&fs->lock);
-                if (path_walk(name, nd) == 0) {
-                        if (nd->path.dentry->d_inode) {
-                                path_put(&old_path);
-                                return 1;
-                        }
-                        path_put(&nd->path);
-                }
-                nd->path = old_path;
-                nd->last = last;
-                nd->last_type = last_type;
-        }
-        return 1;
-}
-
-void set_fs_altroot(void)
-{
-        char *emul = __emul_prefix();
-        struct nameidata nd;
-        struct path path = {}, old_path;
-        int err;
-        struct fs_struct *fs = current->fs;
-
-        if (!emul)
-                goto set_it;
-        err = path_lookup(emul, LOOKUP_FOLLOW|LOOKUP_DIRECTORY|LOOKUP_NOALT, &nd);
-        if (!err)
-                path = nd.path;
-set_it:
-        write_lock(&fs->lock);
-        old_path = fs->altroot;
-        fs->altroot = path;
-        write_unlock(&fs->lock);
-        if (old_path.dentry)
-                path_put(&old_path);
-}
-
 /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
 static int do_path_lookup(int dfd, const char *name,
                                 unsigned int flags, struct nameidata *nd)
@@ -1136,14 +1056,6 @@ static int do_path_lookup(int dfd, const char *name,
 
         if (*name=='/') {
                 read_lock(&fs->lock);
-                if (fs->altroot.dentry && !(nd->flags & LOOKUP_NOALT)) {
-                        nd->path = fs->altroot;
-                        path_get(&fs->altroot);
-                        read_unlock(&fs->lock);
-                        if (__emul_lookup_dentry(name,nd))
-                                goto out; /* found in altroot */
-                        read_lock(&fs->lock);
-                }
                 nd->path = fs->root;
                 path_get(&fs->root);
                 read_unlock(&fs->lock);
@@ -1177,7 +1089,6 @@ static int do_path_lookup(int dfd, const char *name,
         }
 
         retval = path_walk(name, nd);
-out:
         if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry &&
                                 nd->path.dentry->d_inode))
                 audit_inode(name, nd->path.dentry);
@@ -1282,19 +1193,6 @@ static int path_lookup_create(int dfd, const char *name,
                         nd, open_flags, create_mode);
 }
 
-int __user_path_lookup_open(const char __user *name, unsigned int lookup_flags,
-                struct nameidata *nd, int open_flags)
-{
-        char *tmp = getname(name);
-        int err = PTR_ERR(tmp);
-
-        if (!IS_ERR(tmp)) {
-                err = __path_lookup_intent_open(AT_FDCWD, tmp, lookup_flags, nd, open_flags, 0);
-                putname(tmp);
-        }
-        return err;
-}
-
 static struct dentry *__lookup_hash(struct qstr *name,
                 struct dentry *base, struct nameidata *nd)
 {
@@ -1317,7 +1215,14 @@ static struct dentry *__lookup_hash(struct qstr *name,
 
         dentry = cached_lookup(base, name, nd);
         if (!dentry) {
-                struct dentry *new = d_alloc(base, name);
+                struct dentry *new;
+
+                /* Don't create child dentry for a dead directory. */
+                dentry = ERR_PTR(-ENOENT);
+                if (IS_DEADDIR(inode))
+                        goto out;
+
+                new = d_alloc(base, name);
                 dentry = ERR_PTR(-ENOMEM);
                 if (!new)
                         goto out;
@@ -1340,7 +1245,7 @@ static struct dentry *lookup_hash(struct nameidata *nd)
 {
         int err;
 
-        err = permission(nd->path.dentry->d_inode, MAY_EXEC, nd);
+        err = inode_permission(nd->path.dentry->d_inode, MAY_EXEC);
         if (err)
                 return ERR_PTR(err);
         return __lookup_hash(&nd->last, nd->path.dentry, nd);
@@ -1388,7 +1293,7 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
         if (err)
                 return ERR_PTR(err);
 
-        err = permission(base->d_inode, MAY_EXEC, NULL);
+        err = inode_permission(base->d_inode, MAY_EXEC);
         if (err)
                 return ERR_PTR(err);
         return __lookup_hash(&this, base, NULL);
@@ -1416,22 +1321,40 @@ struct dentry *lookup_one_noperm(const char *name, struct dentry *base)
         return __lookup_hash(&this, base, NULL);
 }
 
-int __user_walk_fd(int dfd, const char __user *name, unsigned flags,
-                            struct nameidata *nd)
+int user_path_at(int dfd, const char __user *name, unsigned flags,
+                 struct path *path)
 {
+        struct nameidata nd;
         char *tmp = getname(name);
         int err = PTR_ERR(tmp);
-
         if (!IS_ERR(tmp)) {
-                err = do_path_lookup(dfd, tmp, flags, nd);
+
+                BUG_ON(flags & LOOKUP_PARENT);
+
+                err = do_path_lookup(dfd, tmp, flags, &nd);
                 putname(tmp);
+                if (!err)
+                        *path = nd.path;
         }
         return err;
 }
 
-int __user_walk(const char __user *name, unsigned flags, struct nameidata *nd)
+static int user_path_parent(int dfd, const char __user *path,
+                        struct nameidata *nd, char **name)
 {
-        return __user_walk_fd(AT_FDCWD, name, flags, nd);
+        char *s = getname(path);
+        int error;
+
+        if (IS_ERR(s))
+                return PTR_ERR(s);
+
+        error = do_path_lookup(dfd, s, LOOKUP_PARENT, nd);
+        if (error)
+                putname(s);
+        else
+                *name = s;
+
+        return error;
 }
 
 /*
@@ -1478,7 +1401,7 @@ static int may_delete(struct inode *dir,struct dentry *victim,int isdir)
         BUG_ON(victim->d_parent->d_inode != dir);
         audit_inode_child(victim->d_name.name, victim, dir);
 
-        error = permission(dir,MAY_WRITE | MAY_EXEC, NULL);
+        error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
         if (error)
                 return error;
         if (IS_APPEND(dir))
@@ -1508,14 +1431,13 @@ static int may_delete(struct inode *dir,struct dentry *victim,int isdir)
  *  3. We should have write and exec permissions on dir
  *  4. We can't do it if dir is immutable (done in permission())
  */
-static inline int may_create(struct inode *dir, struct dentry *child,
-                             struct nameidata *nd)
+static inline int may_create(struct inode *dir, struct dentry *child)
 {
         if (child->d_inode)
                 return -EEXIST;
         if (IS_DEADDIR(dir))
                 return -ENOENT;
-        return permission(dir,MAY_WRITE | MAY_EXEC, nd);
+        return inode_permission(dir, MAY_WRITE | MAY_EXEC);
 }
 
 /* 
@@ -1581,7 +1503,7 @@ void unlock_rename(struct dentry *p1, struct dentry *p2)
 int vfs_create(struct inode *dir, struct dentry *dentry, int mode,
                 struct nameidata *nd)
 {
-        int error = may_create(dir, dentry, nd);
+        int error = may_create(dir, dentry);
 
         if (error)
                 return error;
@@ -1755,7 +1677,7 @@ struct file *do_filp_open(int dfd, const char *pathname,
         int will_write;
         int flag = open_to_namei_flags(open_flag);
 
-        acc_mode = ACC_MODE(flag);
+        acc_mode = MAY_OPEN | ACC_MODE(flag);
 
         /* O_TRUNC implies we need access checks for write permissions */
         if (flag & O_TRUNC)
@@ -2025,7 +1947,7 @@ EXPORT_SYMBOL_GPL(lookup_create);
 
 int vfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
 {
-        int error = may_create(dir, dentry, NULL);
+        int error = may_create(dir, dentry);
 
         if (error)
                 return error;
@@ -2071,20 +1993,18 @@ static int may_mknod(mode_t mode)
 asmlinkage long sys_mknodat(int dfd, const char __user *filename, int mode,
                                 unsigned dev)
 {
-        int error = 0;
-        char * tmp;
-        struct dentry * dentry;
+        int error;
+        char *tmp;
+        struct dentry *dentry;
         struct nameidata nd;
 
         if (S_ISDIR(mode))
                 return -EPERM;
-        tmp = getname(filename);
-        if (IS_ERR(tmp))
-                return PTR_ERR(tmp);
 
-        error = do_path_lookup(dfd, tmp, LOOKUP_PARENT, &nd);
+        error = user_path_parent(dfd, filename, &nd, &tmp);
         if (error)
-                goto out;
+                return error;
+
         dentry = lookup_create(&nd, 0);
         if (IS_ERR(dentry)) {
                 error = PTR_ERR(dentry);
@@ -2116,7 +2036,6 @@ out_dput:
 out_unlock:
         mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
         path_put(&nd.path);
-out:
         putname(tmp);
 
         return error;
@@ -2129,7 +2048,7 @@ asmlinkage long sys_mknod(const char __user *filename, int mode, unsigned dev)
 
 int vfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 {
-        int error = may_create(dir, dentry, NULL);
+        int error = may_create(dir, dentry);
 
         if (error)
                 return error;
@@ -2156,14 +2075,10 @@ asmlinkage long sys_mkdirat(int dfd, const char __user *pathname, int mode)
         struct dentry *dentry;
         struct nameidata nd;
 
-        tmp = getname(pathname);
-        error = PTR_ERR(tmp);
-        if (IS_ERR(tmp))
+        error = user_path_parent(dfd, pathname, &nd, &tmp);
+        if (error)
                 goto out_err;
 
-        error = do_path_lookup(dfd, tmp, LOOKUP_PARENT, &nd);
-        if (error)
-                goto out;
         dentry = lookup_create(&nd, 1);
         error = PTR_ERR(dentry);
         if (IS_ERR(dentry))
@@ -2181,7 +2096,6 @@ out_dput:
 out_unlock:
         mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
         path_put(&nd.path);
-out:
         putname(tmp);
 out_err:
         return error;
@@ -2259,13 +2173,9 @@ static long do_rmdir(int dfd, const char __user *pathname)
         struct dentry *dentry;
         struct nameidata nd;
 
-        name = getname(pathname);
-        if(IS_ERR(name))
-                return PTR_ERR(name);
-
-        error = do_path_lookup(dfd, name, LOOKUP_PARENT, &nd);
+        error = user_path_parent(dfd, pathname, &nd, &name);
         if (error)
-                goto exit;
+                return error;
 
         switch(nd.last_type) {
                 case LAST_DOTDOT:
@@ -2294,7 +2204,6 @@ exit2:
         mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
 exit1:
         path_put(&nd.path);
-exit:
         putname(name);
         return error;
 }
@@ -2343,19 +2252,16 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry)
  */
 static long do_unlinkat(int dfd, const char __user *pathname)
 {
-        int error = 0;
-        char * name;
+        int error;
+        char *name;
         struct dentry *dentry;
         struct nameidata nd;
         struct inode *inode = NULL;
 
-        name = getname(pathname);
-        if(IS_ERR(name))
-                return PTR_ERR(name);
-
-        error = do_path_lookup(dfd, name, LOOKUP_PARENT, &nd);
+        error = user_path_parent(dfd, pathname, &nd, &name);
         if (error)
-                goto exit;
+                return error;
+
         error = -EISDIR;
         if (nd.last_type != LAST_NORM)
                 goto exit1;
@@ -2382,7 +2288,6 @@ static long do_unlinkat(int dfd, const char __user *pathname)
                 iput(inode);    /* truncate the inode here */
 exit1:
         path_put(&nd.path);
-exit:
         putname(name);
         return error;
 
@@ -2408,9 +2313,9 @@ asmlinkage long sys_unlink(const char __user *pathname)
         return do_unlinkat(AT_FDCWD, pathname);
 }
 
-int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname, int mode)
+int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname)
 {
-        int error = may_create(dir, dentry, NULL);
+        int error = may_create(dir, dentry);
 
         if (error)
                 return error;
@@ -2432,23 +2337,20 @@ int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname, i
 asmlinkage long sys_symlinkat(const char __user *oldname,
                               int newdfd, const char __user *newname)
 {
-        int error = 0;
-        char * from;
-        char * to;
+        int error;
+        char *from;
+        char *to;
         struct dentry *dentry;
         struct nameidata nd;
 
         from = getname(oldname);
-        if(IS_ERR(from))
+        if (IS_ERR(from))
                 return PTR_ERR(from);
-        to = getname(newname);
-        error = PTR_ERR(to);
-        if (IS_ERR(to))
-                goto out_putname;
 
-        error = do_path_lookup(newdfd, to, LOOKUP_PARENT, &nd);
+        error = user_path_parent(newdfd, newname, &nd, &to);
         if (error)
-                goto out;
+                goto out_putname;
+
         dentry = lookup_create(&nd, 0);
         error = PTR_ERR(dentry);
         if (IS_ERR(dentry))
@@ -2457,14 +2359,13 @@ asmlinkage long sys_symlinkat(const char __user *oldname,
         error = mnt_want_write(nd.path.mnt);
         if (error)
                 goto out_dput;
-        error = vfs_symlink(nd.path.dentry->d_inode, dentry, from, S_IALLUGO);
+        error = vfs_symlink(nd.path.dentry->d_inode, dentry, from);
         mnt_drop_write(nd.path.mnt);
 out_dput:
         dput(dentry);
 out_unlock:
         mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
         path_put(&nd.path);
-out:
         putname(to);
 out_putname:
         putname(from);
@@ -2484,7 +2385,7 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de
         if (!inode)
                 return -ENOENT;
 
-        error = may_create(dir, new_dentry, NULL);
+        error = may_create(dir, new_dentry);
         if (error)
                 return error;
 
@@ -2498,19 +2399,19 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de
                 return -EPERM;
         if (!dir->i_op || !dir->i_op->link)
                 return -EPERM;
-        if (S_ISDIR(old_dentry->d_inode->i_mode))
+        if (S_ISDIR(inode->i_mode))
                 return -EPERM;
 
         error = security_inode_link(old_dentry, dir, new_dentry);
         if (error)
                 return error;
 
-        mutex_lock(&old_dentry->d_inode->i_mutex);
+        mutex_lock(&inode->i_mutex);
         DQUOT_INIT(dir);
         error = dir->i_op->link(old_dentry, dir, new_dentry);
-        mutex_unlock(&old_dentry->d_inode->i_mutex);
+        mutex_unlock(&inode->i_mutex);
         if (!error)
-                fsnotify_link(dir, old_dentry->d_inode, new_dentry);
+                fsnotify_link(dir, inode, new_dentry);
         return error;
 }
 
@@ -2528,27 +2429,25 @@ asmlinkage long sys_linkat(int olddfd, const char __user *oldname,
                            int flags)
 {
         struct dentry *new_dentry;
-        struct nameidata nd, old_nd;
+        struct nameidata nd;
+        struct path old_path;
         int error;
-        char * to;
+        char *to;
 
         if ((flags & ~AT_SYMLINK_FOLLOW) != 0)
                 return -EINVAL;
 
-        to = getname(newname);
-        if (IS_ERR(to))
-                return PTR_ERR(to);
-
-        error = __user_walk_fd(olddfd, oldname,
-                               flags & AT_SYMLINK_FOLLOW ? LOOKUP_FOLLOW : 0,
-                               &old_nd);
+        error = user_path_at(olddfd, oldname,
+                             flags & AT_SYMLINK_FOLLOW ? LOOKUP_FOLLOW : 0,
+                             &old_path);
         if (error)
-                goto exit;
-        error = do_path_lookup(newdfd, to, LOOKUP_PARENT, &nd);
+                return error;
+
+        error = user_path_parent(newdfd, newname, &nd, &to);
         if (error)
                 goto out;
         error = -EXDEV;
-        if (old_nd.path.mnt != nd.path.mnt)
+        if (old_path.mnt != nd.path.mnt)
                 goto out_release;
         new_dentry = lookup_create(&nd, 0);
         error = PTR_ERR(new_dentry);
@@ -2557,7 +2456,7 @@ asmlinkage long sys_linkat(int olddfd, const char __user *oldname,
         error = mnt_want_write(nd.path.mnt);
         if (error)
                 goto out_dput;
-        error = vfs_link(old_nd.path.dentry, nd.path.dentry->d_inode, new_dentry);
+        error = vfs_link(old_path.dentry, nd.path.dentry->d_inode, new_dentry);
         mnt_drop_write(nd.path.mnt);
 out_dput:
         dput(new_dentry);
@@ -2565,10 +2464,9 @@ out_unlock:
         mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
 out_release:
         path_put(&nd.path);
-out:
-        path_put(&old_nd.path);
-exit:
         putname(to);
+out:
+        path_put(&old_path);
 
         return error;
 }
@@ -2621,7 +2519,7 @@ static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry,
          * we'll need to flip '..'.
          */
         if (new_dir != old_dir) {
-                error = permission(old_dentry->d_inode, MAY_WRITE, NULL);
+                error = inode_permission(old_dentry->d_inode, MAY_WRITE);
                 if (error)
                         return error;
         }
@@ -2696,7 +2594,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
                 return error;
 
         if (!new_dentry->d_inode)
-                error = may_create(new_dir, new_dentry, NULL);
+                error = may_create(new_dir, new_dentry);
         else
                 error = may_delete(new_dir, new_dentry, is_dir);
         if (error)
@@ -2724,20 +2622,22 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
         return error;
 }
 
-static int do_rename(int olddfd, const char *oldname,
-                        int newdfd, const char *newname)
+asmlinkage long sys_renameat(int olddfd, const char __user *oldname,
+                             int newdfd, const char __user *newname)
 {
-        int error = 0;
-        struct dentry * old_dir, * new_dir;
-        struct dentry * old_dentry, *new_dentry;
-        struct dentry * trap;
+        struct dentry *old_dir, *new_dir;
+        struct dentry *old_dentry, *new_dentry;
+        struct dentry *trap;
         struct nameidata oldnd, newnd;
+        char *from;
+        char *to;
+        int error;
 
-        error = do_path_lookup(olddfd, oldname, LOOKUP_PARENT, &oldnd);
+        error = user_path_parent(olddfd, oldname, &oldnd, &from);
         if (error)
                 goto exit;
 
-        error = do_path_lookup(newdfd, newname, LOOKUP_PARENT, &newnd);
+        error = user_path_parent(newdfd, newname, &newnd, &to);
         if (error)
                 goto exit1;
 
@@ -2799,29 +2699,11 @@ exit3:
         unlock_rename(new_dir, old_dir);
 exit2:
         path_put(&newnd.path);
+        putname(to);
 exit1:
         path_put(&oldnd.path);
-exit:
-        return error;
-}
-
-asmlinkage long sys_renameat(int olddfd, const char __user *oldname,
-                             int newdfd, const char __user *newname)
-{
-        int error;
-        char * from;
-        char * to;
-
-        from = getname(oldname);
-        if(IS_ERR(from))
-                return PTR_ERR(from);
-        to = getname(newname);
-        error = PTR_ERR(to);
-        if (!IS_ERR(to)) {
-                error = do_rename(olddfd, from, newdfd, to);
-                putname(to);
-        }
         putname(from);
+exit:
         return error;
 }
 
@@ -2959,8 +2841,7 @@ const struct inode_operations page_symlink_inode_operations = {
         .put_link       = page_put_link,
 };
 
-EXPORT_SYMBOL(__user_walk);
-EXPORT_SYMBOL(__user_walk_fd);
+EXPORT_SYMBOL(user_path_at);
 EXPORT_SYMBOL(follow_down);
 EXPORT_SYMBOL(follow_up);
 EXPORT_SYMBOL(get_write_access); /* binfmt_aout */
@@ -2975,7 +2856,7 @@ EXPORT_SYMBOL(page_symlink);
 EXPORT_SYMBOL(page_symlink_inode_operations);
 EXPORT_SYMBOL(path_lookup);
 EXPORT_SYMBOL(vfs_path_lookup);
-EXPORT_SYMBOL(permission);
+EXPORT_SYMBOL(inode_permission);
 EXPORT_SYMBOL(vfs_permission);
 EXPORT_SYMBOL(file_permission);
 EXPORT_SYMBOL(unlock_rename);
diff --git a/fs/namespace.c b/fs/namespace.c
index 4f6f7635b59c..6e283c93b50d 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -112,9 +112,13 @@ struct vfsmount *alloc_vfsmnt(const char *name)
                 int err;
 
                 err = mnt_alloc_id(mnt);
-                if (err) {
-                        kmem_cache_free(mnt_cache, mnt);
-                        return NULL;
+                if (err)
+                        goto out_free_cache;
+
+                if (name) {
+                        mnt->mnt_devname = kstrdup(name, GFP_KERNEL);
+                        if (!mnt->mnt_devname)
+                                goto out_free_id;
                 }
 
                 atomic_set(&mnt->mnt_count, 1);
@@ -127,16 +131,14 @@ struct vfsmount *alloc_vfsmnt(const char *name)
                 INIT_LIST_HEAD(&mnt->mnt_slave_list);
                 INIT_LIST_HEAD(&mnt->mnt_slave);
                 atomic_set(&mnt->__mnt_writers, 0);
-                if (name) {
-                        int size = strlen(name) + 1;
-                        char *newname = kmalloc(size, GFP_KERNEL);
-                        if (newname) {
-                                memcpy(newname, name, size);
-                                mnt->mnt_devname = newname;
-                        }
-                }
         }
         return mnt;
+
+out_free_id:
+        mnt_free_id(mnt);
+out_free_cache:
+        kmem_cache_free(mnt_cache, mnt);
+        return NULL;
 }
 
 /*
@@ -309,10 +311,9 @@ static void handle_write_count_underflow(struct vfsmount *mnt)
          */
         if ((atomic_read(&mnt->__mnt_writers) < 0) &&
             !(mnt->mnt_flags & MNT_IMBALANCED_WRITE_COUNT)) {
-                printk(KERN_DEBUG "leak detected on mount(%p) writers "
+                WARN(1, KERN_DEBUG "leak detected on mount(%p) writers "
                                 "count: %d\n",
                         mnt, atomic_read(&mnt->__mnt_writers));
-                WARN_ON(1);
                 /* use the flag to keep the dmesg spam down */
                 mnt->mnt_flags |= MNT_IMBALANCED_WRITE_COUNT;
         }
@@ -1129,27 +1130,27 @@ static int do_umount(struct vfsmount *mnt, int flags)
 
 asmlinkage long sys_umount(char __user * name, int flags)
 {
-        struct nameidata nd;
+        struct path path;
         int retval;
 
-        retval = __user_walk(name, LOOKUP_FOLLOW, &nd);
+        retval = user_path(name, &path);
         if (retval)
                 goto out;
         retval = -EINVAL;
-        if (nd.path.dentry != nd.path.mnt->mnt_root)
+        if (path.dentry != path.mnt->mnt_root)
                 goto dput_and_out;
-        if (!check_mnt(nd.path.mnt))
+        if (!check_mnt(path.mnt))
                 goto dput_and_out;
 
         retval = -EPERM;
         if (!capable(CAP_SYS_ADMIN))
                 goto dput_and_out;
 
-        retval = do_umount(nd.path.mnt, flags);
+        retval = do_umount(path.mnt, flags);
 dput_and_out:
         /* we mustn't call path_put() as that would clear mnt_expiry_mark */
-        dput(nd.path.dentry);
-        mntput_no_expire(nd.path.mnt);
+        dput(path.dentry);
+        mntput_no_expire(path.mnt);
 out:
         return retval;
 }
@@ -1666,31 +1667,31 @@ static noinline int do_new_mount(struct nameidata *nd, char *type, int flags,
         if (IS_ERR(mnt))
                 return PTR_ERR(mnt);
 
-        return do_add_mount(mnt, nd, mnt_flags, NULL);
+        return do_add_mount(mnt, &nd->path, mnt_flags, NULL);
 }
 
 /*
  * add a mount into a namespace's mount tree
  * - provide the option of adding the new mount to an expiration list
  */
-int do_add_mount(struct vfsmount *newmnt, struct nameidata *nd,
+int do_add_mount(struct vfsmount *newmnt, struct path *path,
                  int mnt_flags, struct list_head *fslist)
 {
         int err;
 
         down_write(&namespace_sem);
         /* Something was mounted here while we slept */
-        while (d_mountpoint(nd->path.dentry) &&
-               follow_down(&nd->path.mnt, &nd->path.dentry))
+        while (d_mountpoint(path->dentry) &&
+               follow_down(&path->mnt, &path->dentry))
                 ;
         err = -EINVAL;
-        if (!check_mnt(nd->path.mnt))
+        if (!check_mnt(path->mnt))
                 goto unlock;
 
         /* Refuse the same filesystem on the same mount point */
         err = -EBUSY;
-        if (nd->path.mnt->mnt_sb == newmnt->mnt_sb &&
-            nd->path.mnt->mnt_root == nd->path.dentry)
+        if (path->mnt->mnt_sb == newmnt->mnt_sb &&
+            path->mnt->mnt_root == path->dentry)
                 goto unlock;
 
         err = -EINVAL;
@@ -1698,7 +1699,7 @@ int do_add_mount(struct vfsmount *newmnt, struct nameidata *nd,
                 goto unlock;
 
         newmnt->mnt_flags = mnt_flags;
-        if ((err = graft_tree(newmnt, &nd->path)))
+        if ((err = graft_tree(newmnt, path)))
                 goto unlock;
 
         if (fslist) /* add to the specified expiration list */
@@ -1973,7 +1974,7 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
                 struct fs_struct *fs)
 {
         struct mnt_namespace *new_ns;
-        struct vfsmount *rootmnt = NULL, *pwdmnt = NULL, *altrootmnt = NULL;
+        struct vfsmount *rootmnt = NULL, *pwdmnt = NULL;
         struct vfsmount *p, *q;
 
         new_ns = kmalloc(sizeof(struct mnt_namespace), GFP_KERNEL);
@@ -2016,10 +2017,6 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
                                 pwdmnt = p;
                                 fs->pwd.mnt = mntget(q);
                         }
-                        if (p == fs->altroot.mnt) {
-                                altrootmnt = p;
-                                fs->altroot.mnt = mntget(q);
-                        }
                 }
                 p = next_mnt(p, mnt_ns->root);
                 q = next_mnt(q, new_ns->root);
@@ -2030,8 +2027,6 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
                 mntput(rootmnt);
         if (pwdmnt)
                 mntput(pwdmnt);
-        if (altrootmnt)
-                mntput(altrootmnt);
 
         return new_ns;
 }
@@ -2184,28 +2179,26 @@ asmlinkage long sys_pivot_root(const char __user * new_root,
                                const char __user * put_old)
 {
         struct vfsmount *tmp;
-        struct nameidata new_nd, old_nd;
-        struct path parent_path, root_parent, root;
+        struct path new, old, parent_path, root_parent, root;
         int error;
 
         if (!capable(CAP_SYS_ADMIN))
                 return -EPERM;
 
-        error = __user_walk(new_root, LOOKUP_FOLLOW | LOOKUP_DIRECTORY,
-                            &new_nd);
+        error = user_path_dir(new_root, &new);
         if (error)
                 goto out0;
         error = -EINVAL;
-        if (!check_mnt(new_nd.path.mnt))
+        if (!check_mnt(new.mnt))
                 goto out1;
 
-        error = __user_walk(put_old, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &old_nd);
+        error = user_path_dir(put_old, &old);
         if (error)
                 goto out1;
 
-        error = security_sb_pivotroot(&old_nd.path, &new_nd.path);
+        error = security_sb_pivotroot(&old, &new);
         if (error) {
-                path_put(&old_nd.path);
+                path_put(&old);
                 goto out1;
         }
 
@@ -2214,69 +2207,69 @@ asmlinkage long sys_pivot_root(const char __user * new_root,
         path_get(&current->fs->root);
         read_unlock(&current->fs->lock);
         down_write(&namespace_sem);
-        mutex_lock(&old_nd.path.dentry->d_inode->i_mutex);
+        mutex_lock(&old.dentry->d_inode->i_mutex);
         error = -EINVAL;
-        if (IS_MNT_SHARED(old_nd.path.mnt) ||
-                IS_MNT_SHARED(new_nd.path.mnt->mnt_parent) ||
+        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;
         error = -ENOENT;
-        if (IS_DEADDIR(new_nd.path.dentry->d_inode))
+        if (IS_DEADDIR(new.dentry->d_inode))
                 goto out2;
-        if (d_unhashed(new_nd.path.dentry) && !IS_ROOT(new_nd.path.dentry))
+        if (d_unhashed(new.dentry) && !IS_ROOT(new.dentry))
                 goto out2;
-        if (d_unhashed(old_nd.path.dentry) && !IS_ROOT(old_nd.path.dentry))
+        if (d_unhashed(old.dentry) && !IS_ROOT(old.dentry))
                 goto out2;
         error = -EBUSY;
-        if (new_nd.path.mnt == root.mnt ||
-            old_nd.path.mnt == root.mnt)
+        if (new.mnt == root.mnt ||
+            old.mnt == root.mnt)
                 goto out2; /* loop, on the same file system  */
         error = -EINVAL;
         if (root.mnt->mnt_root != root.dentry)
                 goto out2; /* not a mountpoint */
         if (root.mnt->mnt_parent == root.mnt)
                 goto out2; /* not attached */
-        if (new_nd.path.mnt->mnt_root != new_nd.path.dentry)
+        if (new.mnt->mnt_root != new.dentry)
                 goto out2; /* not a mountpoint */
-        if (new_nd.path.mnt->mnt_parent == new_nd.path.mnt)
+        if (new.mnt->mnt_parent == new.mnt)
                 goto out2; /* not attached */
         /* make sure we can reach put_old from new_root */
-        tmp = old_nd.path.mnt;
+        tmp = old.mnt;
         spin_lock(&vfsmount_lock);
-        if (tmp != new_nd.path.mnt) {
+        if (tmp != new.mnt) {
                 for (;;) {
                         if (tmp->mnt_parent == tmp)
                                 goto out3; /* already mounted on put_old */
-                        if (tmp->mnt_parent == new_nd.path.mnt)
+                        if (tmp->mnt_parent == new.mnt)
                                 break;
                         tmp = tmp->mnt_parent;
                 }
-                if (!is_subdir(tmp->mnt_mountpoint, new_nd.path.dentry))
+                if (!is_subdir(tmp->mnt_mountpoint, new.dentry))
                         goto out3;
-        } else if (!is_subdir(old_nd.path.dentry, new_nd.path.dentry))
+        } else if (!is_subdir(old.dentry, new.dentry))
                 goto out3;
-        detach_mnt(new_nd.path.mnt, &parent_path);
+        detach_mnt(new.mnt, &parent_path);
         detach_mnt(root.mnt, &root_parent);
         /* mount old root on put_old */
-        attach_mnt(root.mnt, &old_nd.path);
+        attach_mnt(root.mnt, &old);
         /* mount new_root on / */
-        attach_mnt(new_nd.path.mnt, &root_parent);
+        attach_mnt(new.mnt, &root_parent);
         touch_mnt_namespace(current->nsproxy->mnt_ns);
         spin_unlock(&vfsmount_lock);
-        chroot_fs_refs(&root, &new_nd.path);
-        security_sb_post_pivotroot(&root, &new_nd.path);
+        chroot_fs_refs(&root, &new);
+        security_sb_post_pivotroot(&root, &new);
         error = 0;
         path_put(&root_parent);
         path_put(&parent_path);
 out2:
-        mutex_unlock(&old_nd.path.dentry->d_inode->i_mutex);
+        mutex_unlock(&old.dentry->d_inode->i_mutex);
         up_write(&namespace_sem);
         path_put(&root);
-        path_put(&old_nd.path);
+        path_put(&old);
 out1:
-        path_put(&new_nd.path);
+        path_put(&new);
 out0:
         return error;
 out3:
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index 011ef0b6d2d4..07e9715b8658 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -266,7 +266,7 @@ leave_me:;
 
 
 static int
-__ncp_lookup_validate(struct dentry * dentry, struct nameidata *nd)
+__ncp_lookup_validate(struct dentry *dentry)
 {
         struct ncp_server *server;
         struct dentry *parent;
@@ -340,7 +340,7 @@ ncp_lookup_validate(struct dentry * dentry, struct nameidata *nd)
 {
         int res;
         lock_kernel();
-        res = __ncp_lookup_validate(dentry, nd);
+        res = __ncp_lookup_validate(dentry);
         unlock_kernel();
         return res;
 }
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index 2e5ab1204dec..d642f0e5b365 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -64,7 +64,7 @@ static void ncp_destroy_inode(struct inode *inode)
         kmem_cache_free(ncp_inode_cachep, NCP_FINFO(inode));
 }
 
-static void init_once(struct kmem_cache *cachep, void *foo)
+static void init_once(void *foo)
 {
         struct ncp_inode_info *ei = (struct ncp_inode_info *) foo;
 
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 28a238dab23a..74f92b717f78 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1884,7 +1884,7 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
                 return status;
         nfs_access_add_cache(inode, &cache);
 out:
-        if ((cache.mask & mask) == mask)
+        if ((mask & ~cache.mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0)
                 return 0;
         return -EACCES;
 }
@@ -1907,17 +1907,17 @@ int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags)
         return nfs_do_access(inode, cred, nfs_open_permission_mask(openflags));
 }
 
-int nfs_permission(struct inode *inode, int mask, struct nameidata *nd)
+int nfs_permission(struct inode *inode, int mask)
 {
         struct rpc_cred *cred;
         int res = 0;
 
         nfs_inc_stats(inode, NFSIOS_VFSACCESS);
 
-        if (mask == 0)
+        if ((mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0)
                 goto out;
         /* Is this sys_access() ? */
-        if (nd != NULL && (nd->flags & LOOKUP_ACCESS))
+        if (mask & MAY_ACCESS)
                 goto force_lookup;
 
         switch (inode->i_mode & S_IFMT) {
@@ -1926,8 +1926,7 @@ int nfs_permission(struct inode *inode, int mask, struct nameidata *nd)
                 case S_IFREG:
                         /* NFSv4 has atomic_open... */
                         if (nfs_server_capable(inode, NFS_CAP_ATOMIC_OPEN)
-                                        && nd != NULL
-                                        && (nd->flags & LOOKUP_OPEN))
+                                        && (mask & MAY_OPEN))
                                 goto out;
                         break;
                 case S_IFDIR:
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index df23f987da6b..52daefa2f521 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1242,7 +1242,7 @@ static inline void nfs4_init_once(struct nfs_inode *nfsi)
 #endif
 }
 
-static void init_once(struct kmem_cache * cachep, void *foo)
+static void init_once(void *foo)
 {
         struct nfs_inode *nfsi = (struct nfs_inode *) foo;
 
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 2f285ef76399..66df08dd1caf 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -129,7 +129,7 @@ static void * nfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
                 goto out_err;
 
         mntget(mnt);
-        err = do_add_mount(mnt, nd, nd->path.mnt->mnt_flags|MNT_SHRINKABLE,
+        err = do_add_mount(mnt, &nd->path, nd->path.mnt->mnt_flags|MNT_SHRINKABLE,
                            &nfs_automount_list);
         if (err < 0) {
                 mntput(mnt);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 1b94e3650f5c..9abcd2b329f7 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1718,9 +1718,9 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data)
          * ones were explicitly specified. Fall back to legacy behavior and
          * just return success.
          */
-        if ((nfsvers == 4 && options4->version == 1) ||
-            (nfsvers <= 3 && options->version >= 1 &&
-             options->version <= 6))
+        if ((nfsvers == 4 && (!options4 || options4->version == 1)) ||
+            (nfsvers <= 3 && (!options || (options->version >= 1 &&
+                                           options->version <= 6))))
                 return 0;
 
         data = kzalloc(sizeof(*data), GFP_KERNEL);
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 3adf8b266461..f089e5839d7d 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -95,10 +95,11 @@ static void nfs_async_unlink_done(struct rpc_task *task, void *calldata)
 static void nfs_async_unlink_release(void *calldata)
 {
         struct nfs_unlinkdata   *data = calldata;
+        struct super_block *sb = data->dir->i_sb;
 
         nfs_dec_sillycount(data->dir);
-        nfs_sb_deactive(NFS_SERVER(data->dir));
         nfs_free_unlinkdata(data);
+        nfs_sb_deactive(NFS_SB(sb));
 }
 
 static const struct rpc_call_ops nfs_unlink_ops = {
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 33bfcf09db46..9dc036f18356 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -1023,7 +1023,7 @@ exp_export(struct nfsctl_export *nxp)
         /* Look up the dentry */
         err = path_lookup(nxp->ex_path, 0, &nd);
         if (err)
-                goto out_unlock;
+                goto out_put_clp;
         err = -EINVAL;
 
         exp = exp_get_by_name(clp, nd.path.mnt, nd.path.dentry, NULL);
@@ -1090,9 +1090,9 @@ finish:
                 exp_put(exp);
         if (fsid_key && !IS_ERR(fsid_key))
                 cache_put(&fsid_key->h, &svc_expkey_cache);
-        if (clp)
-                auth_domain_put(clp);
         path_put(&nd.path);
+out_put_clp:
+        auth_domain_put(clp);
 out_unlock:
         exp_writeunlock();
 out:
diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c
index 6b6225ac4926..15c6faeec77c 100644
--- a/fs/nfsd/lockd.c
+++ b/fs/nfsd/lockd.c
@@ -19,6 +19,13 @@
 
 #define NFSDDBG_FACILITY                NFSDDBG_LOCKD
 
+#ifdef CONFIG_LOCKD_V4
+#define nlm_stale_fh    nlm4_stale_fh
+#define nlm_failed      nlm4_failed
+#else
+#define nlm_stale_fh    nlm_lck_denied_nolocks
+#define nlm_failed      nlm_lck_denied_nolocks
+#endif
 /*
  * Note: we hold the dentry use count while the file is open.
  */
@@ -47,12 +54,10 @@ nlm_fopen(struct svc_rqst *rqstp, struct nfs_fh *f, struct file **filp)
                 return 0;
         case nfserr_dropit:
                 return nlm_drop_reply;
-#ifdef CONFIG_LOCKD_V4
         case nfserr_stale:
-                return nlm4_stale_fh;
-#endif
+                return nlm_stale_fh;
         default:
-                return nlm_lck_denied;
+                return nlm_failed;
         }
 }
 
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index eef1629806f5..2e51adac65de 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -851,7 +851,7 @@ struct nfsd4_operation {
 
 static struct nfsd4_operation nfsd4_ops[];
 
-static inline char *nfsd4_op_name(unsigned opnum);
+static const char *nfsd4_op_name(unsigned opnum);
 
 /*
  * COMPOUND call.
@@ -1116,8 +1116,7 @@ static struct nfsd4_operation nfsd4_ops[OP_RELEASE_LOCKOWNER+1] = {
         },
 };
 
-static inline char *
-nfsd4_op_name(unsigned opnum)
+static const char *nfsd4_op_name(unsigned opnum)
 {
         if (opnum < ARRAY_SIZE(nfsd4_ops))
                 return nfsd4_ops[opnum].op_name;
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 1955a2702e60..c53e65f8f3a2 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -12,6 +12,7 @@
 #include <linux/time.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
+#include <linux/namei.h>
 #include <linux/fcntl.h>
 #include <linux/net.h>
 #include <linux/in.h>
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index f45451eb1e38..ea37c96f0445 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -51,7 +51,7 @@ static int nfsd_acceptable(void *expv, struct dentry *dentry)
                 /* make sure parents give x permission to user */
                 int err;
                 parent = dget_parent(tdentry);
-                err = permission(parent->d_inode, MAY_EXEC, NULL);
+                err = inode_permission(parent->d_inode, MAY_EXEC);
                 if (err < 0) {
                         dput(parent);
                         break;
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 0f4481e0502d..18060bed5267 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1516,7 +1516,6 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
         struct dentry   *dentry, *dnew;
         __be32          err, cerr;
         int             host_err;
-        umode_t         mode;
 
         err = nfserr_noent;
         if (!flen || !plen)
@@ -1535,11 +1534,6 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
         if (IS_ERR(dnew))
                 goto out_nfserr;
 
-        mode = S_IALLUGO;
-        /* Only the MODE ATTRibute is even vaguely meaningful */
-        if (iap && (iap->ia_valid & ATTR_MODE))
-                mode = iap->ia_mode & S_IALLUGO;
-
         host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
         if (host_err)
                 goto out_nfserr;
@@ -1551,11 +1545,11 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
                 else {
                         strncpy(path_alloced, path, plen);
                         path_alloced[plen] = 0;
-                        host_err = vfs_symlink(dentry->d_inode, dnew, path_alloced, mode);
+                        host_err = vfs_symlink(dentry->d_inode, dnew, path_alloced);
                         kfree(path_alloced);
                 }
         } else
-                host_err = vfs_symlink(dentry->d_inode, dnew, path, mode);
+                host_err = vfs_symlink(dentry->d_inode, dnew, path);
 
         if (!host_err) {
                 if (EX_ISSYNC(fhp->fh_export))
@@ -1959,12 +1953,12 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
                 return 0;
 
         /* This assumes  NFSD_MAY_{READ,WRITE,EXEC} == MAY_{READ,WRITE,EXEC} */
-        err = permission(inode, acc & (MAY_READ|MAY_WRITE|MAY_EXEC), NULL);
+        err = inode_permission(inode, acc & (MAY_READ|MAY_WRITE|MAY_EXEC));
 
         /* Allow read access to binaries even when mode 111 */
         if (err == -EACCES && S_ISREG(inode->i_mode) &&
             acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE))
-                err = permission(inode, MAY_EXEC, NULL);
+                err = inode_permission(inode, MAY_EXEC);
 
         return err? nfserrno(err) : 0;
 }
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 00e9ccde8e42..b38f944f0667 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -1194,7 +1194,7 @@ lock_retry_remap:
                 tbh = bhs[i];
                 if (!tbh)
                         continue;
-                if (unlikely(test_set_buffer_locked(tbh)))
+                if (!trylock_buffer(tbh))
                         BUG();
                 /* The buffer dirty state is now irrelevant, just clean it. */
                 clear_buffer_dirty(tbh);
diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c
index 33ff314cc507..9669541d0119 100644
--- a/fs/ntfs/compress.c
+++ b/fs/ntfs/compress.c
@@ -665,7 +665,7 @@ lock_retry_remap:
         for (i = 0; i < nr_bhs; i++) {
                 struct buffer_head *tbh = bhs[i];
 
-                if (unlikely(test_set_buffer_locked(tbh)))
+                if (!trylock_buffer(tbh))
                         continue;
                 if (unlikely(buffer_uptodate(tbh))) {
                         unlock_buffer(tbh);
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index 3c5550cd11d6..d020866d4232 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -2118,7 +2118,7 @@ static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb,
                 goto out;
         if (!count)
                 goto out;
-        err = remove_suid(file->f_path.dentry);
+        err = file_remove_suid(file);
         if (err)
                 goto out;
         file_update_time(file);
diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c
index 790defb847e7..17d32ca6bc35 100644
--- a/fs/ntfs/mft.c
+++ b/fs/ntfs/mft.c
@@ -586,7 +586,7 @@ int ntfs_sync_mft_mirror(ntfs_volume *vol, const unsigned long mft_no,
                 for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++) {
                         struct buffer_head *tbh = bhs[i_bhs];
 
-                        if (unlikely(test_set_buffer_locked(tbh)))
+                        if (!trylock_buffer(tbh))
                                 BUG();
                         BUG_ON(!buffer_uptodate(tbh));
                         clear_buffer_dirty(tbh);
@@ -779,7 +779,7 @@ int write_mft_record_nolock(ntfs_inode *ni, MFT_RECORD *m, int sync)
         for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++) {
                 struct buffer_head *tbh = bhs[i_bhs];
 
-                if (unlikely(test_set_buffer_locked(tbh)))
+                if (!trylock_buffer(tbh))
                         BUG();
                 BUG_ON(!buffer_uptodate(tbh));
                 clear_buffer_dirty(tbh);
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index 3e76f3b216bc..4a46743b5077 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -3080,7 +3080,7 @@ struct kmem_cache *ntfs_inode_cache;
 struct kmem_cache *ntfs_big_inode_cache;
 
 /* Init once constructor for the inode slab cache. */
-static void ntfs_big_inode_init_once(struct kmem_cache *cachep, void *foo)
+static void ntfs_big_inode_init_once(void *foo)
 {
         ntfs_inode *ni = (ntfs_inode *)foo;
 
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 1db080135c6d..506c24fb5078 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -1073,12 +1073,15 @@ static void ocfs2_write_failure(struct inode *inode,
         for(i = 0; i < wc->w_num_pages; i++) {
                 tmppage = wc->w_pages[i];
 
-                if (ocfs2_should_order_data(inode))
-                        walk_page_buffers(wc->w_handle, page_buffers(tmppage),
-                                          from, to, NULL,
-                                          ocfs2_journal_dirty_data);
-
-                block_commit_write(tmppage, from, to);
+                if (page_has_buffers(tmppage)) {
+                        if (ocfs2_should_order_data(inode))
+                                walk_page_buffers(wc->w_handle,
+                                                  page_buffers(tmppage),
+                                                  from, to, NULL,
+                                                  ocfs2_journal_dirty_data);
+
+                        block_commit_write(tmppage, from, to);
+                }
         }
 }
 
@@ -1901,12 +1904,14 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
                         to = PAGE_CACHE_SIZE;
                 }
 
-                if (ocfs2_should_order_data(inode))
-                        walk_page_buffers(wc->w_handle, page_buffers(tmppage),
-                                          from, to, NULL,
-                                          ocfs2_journal_dirty_data);
-
-                block_commit_write(tmppage, from, to);
+                if (page_has_buffers(tmppage)) {
+                        if (ocfs2_should_order_data(inode))
+                                walk_page_buffers(wc->w_handle,
+                                                  page_buffers(tmppage),
+                                                  from, to, NULL,
+                                                  ocfs2_journal_dirty_data);
+                        block_commit_write(tmppage, from, to);
+                }
         }
 
 out_write_size:
diff --git a/fs/ocfs2/dlm/dlmfs.c b/fs/ocfs2/dlm/dlmfs.c
index e48aba698b77..533a789c3ef8 100644
--- a/fs/ocfs2/dlm/dlmfs.c
+++ b/fs/ocfs2/dlm/dlmfs.c
@@ -267,8 +267,7 @@ static ssize_t dlmfs_file_write(struct file *filp,
         return writelen;
 }
 
-static void dlmfs_init_once(struct kmem_cache *cachep,
-                            void *foo)
+static void dlmfs_init_once(void *foo)
 {
         struct dlmfs_inode_private *ip =
                 (struct dlmfs_inode_private *) foo;
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index e8514e8b6ce8..ec2ed15c3daa 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1176,7 +1176,7 @@ bail:
         return err;
 }
 
-int ocfs2_permission(struct inode *inode, int mask, struct nameidata *nd)
+int ocfs2_permission(struct inode *inode, int mask)
 {
         int ret;
 
@@ -1766,8 +1766,8 @@ out_inode_unlock:
 out_rw_unlock:
         ocfs2_rw_unlock(inode, 1);
 
-        mutex_unlock(&inode->i_mutex);
 out:
+        mutex_unlock(&inode->i_mutex);
         return ret;
 }
 
diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h
index 048ddcaf5c80..1e27b4d017ea 100644
--- a/fs/ocfs2/file.h
+++ b/fs/ocfs2/file.h
@@ -62,8 +62,7 @@ int ocfs2_lock_allocators(struct inode *inode, struct ocfs2_dinode *di,
 int ocfs2_setattr(struct dentry *dentry, struct iattr *attr);
 int ocfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
                   struct kstat *stat);
-int ocfs2_permission(struct inode *inode, int mask,
-                     struct nameidata *nd);
+int ocfs2_permission(struct inode *inode, int mask);
 
 int ocfs2_should_update_atime(struct inode *inode,
                               struct vfsmount *vfsmnt);
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index a8c19cb3cfdd..7a37240f7a31 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -57,7 +57,7 @@ static int __ocfs2_recovery_thread(void *arg);
 static int ocfs2_commit_cache(struct ocfs2_super *osb);
 static int ocfs2_wait_on_mount(struct ocfs2_super *osb);
 static int ocfs2_journal_toggle_dirty(struct ocfs2_super *osb,
-                                      int dirty);
+                                      int dirty, int replayed);
 static int ocfs2_trylock_journal(struct ocfs2_super *osb,
                                  int slot_num);
 static int ocfs2_recover_orphans(struct ocfs2_super *osb,
@@ -562,8 +562,18 @@ done:
         return status;
 }
 
+static void ocfs2_bump_recovery_generation(struct ocfs2_dinode *di)
+{
+        le32_add_cpu(&(di->id1.journal1.ij_recovery_generation), 1);
+}
+
+static u32 ocfs2_get_recovery_generation(struct ocfs2_dinode *di)
+{
+        return le32_to_cpu(di->id1.journal1.ij_recovery_generation);
+}
+
 static int ocfs2_journal_toggle_dirty(struct ocfs2_super *osb,
-                                      int dirty)
+                                      int dirty, int replayed)
 {
         int status;
         unsigned int flags;
@@ -593,6 +603,9 @@ static int ocfs2_journal_toggle_dirty(struct ocfs2_super *osb,
                 flags &= ~OCFS2_JOURNAL_DIRTY_FL;
         fe->id1.journal1.ij_flags = cpu_to_le32(flags);
 
+        if (replayed)
+                ocfs2_bump_recovery_generation(fe);
+
         status = ocfs2_write_block(osb, bh, journal->j_inode);
         if (status < 0)
                 mlog_errno(status);
@@ -667,7 +680,7 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb)
                  * Do not toggle if flush was unsuccessful otherwise
                  * will leave dirty metadata in a "clean" journal
                  */
-                status = ocfs2_journal_toggle_dirty(osb, 0);
+                status = ocfs2_journal_toggle_dirty(osb, 0, 0);
                 if (status < 0)
                         mlog_errno(status);
         }
@@ -710,7 +723,7 @@ static void ocfs2_clear_journal_error(struct super_block *sb,
         }
 }
 
-int ocfs2_journal_load(struct ocfs2_journal *journal, int local)
+int ocfs2_journal_load(struct ocfs2_journal *journal, int local, int replayed)
 {
         int status = 0;
         struct ocfs2_super *osb;
@@ -729,7 +742,7 @@ int ocfs2_journal_load(struct ocfs2_journal *journal, int local)
 
         ocfs2_clear_journal_error(osb->sb, journal->j_journal, osb->slot_num);
 
-        status = ocfs2_journal_toggle_dirty(osb, 1);
+        status = ocfs2_journal_toggle_dirty(osb, 1, replayed);
         if (status < 0) {
                 mlog_errno(status);
                 goto done;
@@ -771,7 +784,7 @@ int ocfs2_journal_wipe(struct ocfs2_journal *journal, int full)
                 goto bail;
         }
 
-        status = ocfs2_journal_toggle_dirty(journal->j_osb, 0);
+        status = ocfs2_journal_toggle_dirty(journal->j_osb, 0, 0);
         if (status < 0)
                 mlog_errno(status);
 
@@ -1034,6 +1047,12 @@ restart:
         spin_unlock(&osb->osb_lock);
         mlog(0, "All nodes recovered\n");
 
+        /* Refresh all journal recovery generations from disk */
+        status = ocfs2_check_journals_nolocks(osb);
+        status = (status == -EROFS) ? 0 : status;
+        if (status < 0)
+                mlog_errno(status);
+
         ocfs2_super_unlock(osb, 1);
 
         /* We always run recovery on our own orphan dir - the dead
@@ -1096,6 +1115,42 @@ out:
         mlog_exit_void();
 }
 
+static int ocfs2_read_journal_inode(struct ocfs2_super *osb,
+                                    int slot_num,
+                                    struct buffer_head **bh,
+                                    struct inode **ret_inode)
+{
+        int status = -EACCES;
+        struct inode *inode = NULL;
+
+        BUG_ON(slot_num >= osb->max_slots);
+
+        inode = ocfs2_get_system_file_inode(osb, JOURNAL_SYSTEM_INODE,
+                                            slot_num);
+        if (!inode || is_bad_inode(inode)) {
+                mlog_errno(status);
+                goto bail;
+        }
+        SET_INODE_JOURNAL(inode);
+
+        status = ocfs2_read_block(osb, OCFS2_I(inode)->ip_blkno, bh, 0, inode);
+        if (status < 0) {
+                mlog_errno(status);
+                goto bail;
+        }
+
+        status = 0;
+
+bail:
+        if (inode) {
+                if (status || !ret_inode)
+                        iput(inode);
+                else
+                        *ret_inode = inode;
+        }
+        return status;
+}
+
 /* Does the actual journal replay and marks the journal inode as
  * clean. Will only replay if the journal inode is marked dirty. */
 static int ocfs2_replay_journal(struct ocfs2_super *osb,
@@ -1109,22 +1164,36 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb,
         struct ocfs2_dinode *fe;
         journal_t *journal = NULL;
         struct buffer_head *bh = NULL;
+        u32 slot_reco_gen;
 
-        inode = ocfs2_get_system_file_inode(osb, JOURNAL_SYSTEM_INODE,
-                                            slot_num);
-        if (inode == NULL) {
-                status = -EACCES;
+        status = ocfs2_read_journal_inode(osb, slot_num, &bh, &inode);
+        if (status) {
                 mlog_errno(status);
                 goto done;
         }
-        if (is_bad_inode(inode)) {
-                status = -EACCES;
-                iput(inode);
-                inode = NULL;
-                mlog_errno(status);
+
+        fe = (struct ocfs2_dinode *)bh->b_data;
+        slot_reco_gen = ocfs2_get_recovery_generation(fe);
+        brelse(bh);
+        bh = NULL;
+
+        /*
+         * As the fs recovery is asynchronous, there is a small chance that
+         * another node mounted (and recovered) the slot before the recovery
+         * thread could get the lock. To handle that, we dirty read the journal
+         * inode for that slot to get the recovery generation. If it is
+         * different than what we expected, the slot has been recovered.
+         * If not, it needs recovery.
+         */
+        if (osb->slot_recovery_generations[slot_num] != slot_reco_gen) {
+                mlog(0, "Slot %u already recovered (old/new=%u/%u)\n", slot_num,
+                     osb->slot_recovery_generations[slot_num], slot_reco_gen);
+                osb->slot_recovery_generations[slot_num] = slot_reco_gen;
+                status = -EBUSY;
                 goto done;
         }
-        SET_INODE_JOURNAL(inode);
+
+        /* Continue with recovery as the journal has not yet been recovered */
 
         status = ocfs2_inode_lock_full(inode, &bh, 1, OCFS2_META_LOCK_RECOVERY);
         if (status < 0) {
@@ -1138,9 +1207,12 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb,
         fe = (struct ocfs2_dinode *) bh->b_data;
 
         flags = le32_to_cpu(fe->id1.journal1.ij_flags);
+        slot_reco_gen = ocfs2_get_recovery_generation(fe);
 
         if (!(flags & OCFS2_JOURNAL_DIRTY_FL)) {
                 mlog(0, "No recovery required for node %d\n", node_num);
+                /* Refresh recovery generation for the slot */
+                osb->slot_recovery_generations[slot_num] = slot_reco_gen;
                 goto done;
         }
 
@@ -1188,6 +1260,11 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb,
         flags &= ~OCFS2_JOURNAL_DIRTY_FL;
         fe->id1.journal1.ij_flags = cpu_to_le32(flags);
 
+        /* Increment recovery generation to indicate successful recovery */
+        ocfs2_bump_recovery_generation(fe);
+        osb->slot_recovery_generations[slot_num] =
+                                        ocfs2_get_recovery_generation(fe);
+
         status = ocfs2_write_block(osb, bh, inode);
         if (status < 0)
                 mlog_errno(status);
@@ -1252,6 +1329,13 @@ static int ocfs2_recover_node(struct ocfs2_super *osb,
 
         status = ocfs2_replay_journal(osb, node_num, slot_num);
         if (status < 0) {
+                if (status == -EBUSY) {
+                        mlog(0, "Skipping recovery for slot %u (node %u) "
+                             "as another node has recovered it\n", slot_num,
+                             node_num);
+                        status = 0;
+                        goto done;
+                }
                 mlog_errno(status);
                 goto done;
         }
@@ -1334,12 +1418,29 @@ int ocfs2_mark_dead_nodes(struct ocfs2_super *osb)
 {
         unsigned int node_num;
         int status, i;
+        struct buffer_head *bh = NULL;
+        struct ocfs2_dinode *di;
 
         /* This is called with the super block cluster lock, so we
          * know that the slot map can't change underneath us. */
 
         spin_lock(&osb->osb_lock);
         for (i = 0; i < osb->max_slots; i++) {
+                /* Read journal inode to get the recovery generation */
+                status = ocfs2_read_journal_inode(osb, i, &bh, NULL);
+                if (status) {
+                        mlog_errno(status);
+                        goto bail;
+                }
+                di = (struct ocfs2_dinode *)bh->b_data;
+                osb->slot_recovery_generations[i] =
+                                        ocfs2_get_recovery_generation(di);
+                brelse(bh);
+                bh = NULL;
+
+                mlog(0, "Slot %u recovery generation is %u\n", i,
+                     osb->slot_recovery_generations[i]);
+
                 if (i == osb->slot_num)
                         continue;
 
@@ -1603,49 +1704,41 @@ static int ocfs2_commit_thread(void *arg)
         return 0;
 }
 
-/* Look for a dirty journal without taking any cluster locks. Used for
- * hard readonly access to determine whether the file system journals
- * require recovery. */
+/* Reads all the journal inodes without taking any cluster locks. Used
+ * for hard readonly access to determine whether any journal requires
+ * recovery. Also used to refresh the recovery generation numbers after
+ * a journal has been recovered by another node.
+ */
 int ocfs2_check_journals_nolocks(struct ocfs2_super *osb)
 {
         int ret = 0;
         unsigned int slot;
-        struct buffer_head *di_bh;
+        struct buffer_head *di_bh = NULL;
         struct ocfs2_dinode *di;
-        struct inode *journal = NULL;
+        int journal_dirty = 0;
 
         for(slot = 0; slot < osb->max_slots; slot++) {
-                journal = ocfs2_get_system_file_inode(osb,
-                                                      JOURNAL_SYSTEM_INODE,
-                                                      slot);
-                if (!journal || is_bad_inode(journal)) {
-                        ret = -EACCES;
-                        mlog_errno(ret);
-                        goto out;
-                }
-
-                di_bh = NULL;
-                ret = ocfs2_read_block(osb, OCFS2_I(journal)->ip_blkno, &di_bh,
-                                       0, journal);
-                if (ret < 0) {
+                ret = ocfs2_read_journal_inode(osb, slot, &di_bh, NULL);
+                if (ret) {
                         mlog_errno(ret);
                         goto out;
                 }
 
                 di = (struct ocfs2_dinode *) di_bh->b_data;
 
+                osb->slot_recovery_generations[slot] =
+                                        ocfs2_get_recovery_generation(di);
+
                 if (le32_to_cpu(di->id1.journal1.ij_flags) &
                     OCFS2_JOURNAL_DIRTY_FL)
-                        ret = -EROFS;
+                        journal_dirty = 1;
 
                 brelse(di_bh);
-                if (ret)
-                        break;
+                di_bh = NULL;
         }
 
 out:
-        if (journal)
-                iput(journal);
-
+        if (journal_dirty)
+                ret = -EROFS;
         return ret;
 }
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index db82be2532ed..2178ebffa05f 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -161,7 +161,8 @@ int    ocfs2_journal_init(struct ocfs2_journal *journal,
 void   ocfs2_journal_shutdown(struct ocfs2_super *osb);
 int    ocfs2_journal_wipe(struct ocfs2_journal *journal,
                           int full);
-int    ocfs2_journal_load(struct ocfs2_journal *journal, int local);
+int    ocfs2_journal_load(struct ocfs2_journal *journal, int local,
+                          int replayed);
 int    ocfs2_check_journals_nolocks(struct ocfs2_super *osb);
 void   ocfs2_recovery_thread(struct ocfs2_super *osb,
                              int node_num);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 1cb814be8ef1..7f625f2b1117 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -204,6 +204,8 @@ struct ocfs2_super
 
         struct ocfs2_slot_info *slot_info;
 
+        u32 *slot_recovery_generations;
+
         spinlock_t node_map_lock;
 
         u64 root_blkno;
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 3f1945177629..4f619850ccf7 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -660,7 +660,10 @@ struct ocfs2_dinode {
                 struct {                /* Info for journal system
                                            inodes */
                         __le32 ij_flags;        /* Mounted, version, etc. */
-                        __le32 ij_pad;
+                        __le32 ij_recovery_generation; /* Incremented when the
+                                                          journal is recovered
+                                                          after an unclean
+                                                          shutdown */
                 } journal1;
         } id1;                          /* Inode type dependant 1 */
 /*C0*/  union {
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index ccecfe5094fa..88255d3f52b4 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1118,7 +1118,7 @@ bail:
         return status;
 }
 
-static void ocfs2_inode_init_once(struct kmem_cache *cachep, void *data)
+static void ocfs2_inode_init_once(void *data)
 {
         struct ocfs2_inode_info *oi = data;
 
@@ -1442,6 +1442,15 @@ static int ocfs2_initialize_super(struct super_block *sb,
         }
         mlog(0, "max_slots for this device: %u\n", osb->max_slots);
 
+        osb->slot_recovery_generations =
+                kcalloc(osb->max_slots, sizeof(*osb->slot_recovery_generations),
+                        GFP_KERNEL);
+        if (!osb->slot_recovery_generations) {
+                status = -ENOMEM;
+                mlog_errno(status);
+                goto bail;
+        }
+
         init_waitqueue_head(&osb->osb_wipe_event);
         osb->osb_orphan_wipes = kcalloc(osb->max_slots,
                                         sizeof(*osb->osb_orphan_wipes),
@@ -1703,7 +1712,7 @@ static int ocfs2_check_volume(struct ocfs2_super *osb)
         local = ocfs2_mount_local(osb);
 
         /* will play back anything left in the journal. */
-        status = ocfs2_journal_load(osb->journal, local);
+        status = ocfs2_journal_load(osb->journal, local, dirty);
         if (status < 0) {
                 mlog(ML_ERROR, "ocfs2 journal load failed! %d\n", status);
                 goto finally;
@@ -1768,6 +1777,7 @@ static void ocfs2_delete_osb(struct ocfs2_super *osb)
         ocfs2_free_slot_info(osb);
 
         kfree(osb->osb_orphan_wipes);
+        kfree(osb->slot_recovery_generations);
         /* FIXME
          * This belongs in journal shutdown, but because we have to
          * allocate osb->journal at the start of ocfs2_initalize_osb(),
diff --git a/fs/omfs/Makefile b/fs/omfs/Makefile
new file mode 100644
index 000000000000..8b82b63f1129
--- /dev/null
+++ b/fs/omfs/Makefile
@@ -0,0 +1,4 @@
+
+obj-$(CONFIG_OMFS_FS) += omfs.o
+
+omfs-y := bitmap.o dir.o file.o inode.o
diff --git a/fs/omfs/bitmap.c b/fs/omfs/bitmap.c
new file mode 100644
index 000000000000..697663b01bae
--- /dev/null
+++ b/fs/omfs/bitmap.c
@@ -0,0 +1,192 @@
+#include <linux/kernel.h>
+#include <linux/fs.h>
+#include <linux/buffer_head.h>
+#include <asm/div64.h>
+#include "omfs.h"
+
+unsigned long omfs_count_free(struct super_block *sb)
+{
+        unsigned int i;
+        unsigned long sum = 0;
+        struct omfs_sb_info *sbi = OMFS_SB(sb);
+        int nbits = sb->s_blocksize * 8;
+
+        for (i = 0; i < sbi->s_imap_size; i++)
+                sum += nbits - bitmap_weight(sbi->s_imap[i], nbits);
+
+        return sum;
+}
+
+/*
+ *  Counts the run of zero bits starting at bit up to max.
+ *  It handles the case where a run might spill over a buffer.
+ *  Called with bitmap lock.
+ */
+static int count_run(unsigned long **addr, int nbits,
+                int addrlen, int bit, int max)
+{
+        int count = 0;
+        int x;
+
+        for (; addrlen > 0; addrlen--, addr++) {
+                x = find_next_bit(*addr, nbits, bit);
+                count += x - bit;
+
+                if (x < nbits || count > max)
+                        return min(count, max);
+
+                bit = 0;
+        }
+        return min(count, max);
+}
+
+/*
+ * Sets or clears the run of count bits starting with bit.
+ * Called with bitmap lock.
+ */
+static int set_run(struct super_block *sb, int map,
+                int nbits, int bit, int count, int set)
+{
+        int i;
+        int err;
+        struct buffer_head *bh;
+        struct omfs_sb_info *sbi = OMFS_SB(sb);
+
+        err = -ENOMEM;
+        bh = sb_bread(sb, clus_to_blk(sbi, sbi->s_bitmap_ino) + map);
+        if (!bh)
+                goto out;
+
+        for (i = 0; i < count; i++, bit++) {
+                if (bit >= nbits) {
+                        bit = 0;
+                        map++;
+
+                        mark_buffer_dirty(bh);
+                        brelse(bh);
+                        bh = sb_bread(sb,
+                                clus_to_blk(sbi, sbi->s_bitmap_ino) + map);
+                        if (!bh)
+                                goto out;
+                }
+                if (set) {
+                        set_bit(bit, sbi->s_imap[map]);
+                        set_bit(bit, (unsigned long *)bh->b_data);
+                } else {
+                        clear_bit(bit, sbi->s_imap[map]);
+                        clear_bit(bit, (unsigned long *)bh->b_data);
+                }
+        }
+        mark_buffer_dirty(bh);
+        brelse(bh);
+        err = 0;
+out:
+        return err;
+}
+
+/*
+ * Tries to allocate exactly one block.  Returns true if sucessful.
+ */
+int omfs_allocate_block(struct super_block *sb, u64 block)
+{
+        struct buffer_head *bh;
+        struct omfs_sb_info *sbi = OMFS_SB(sb);
+        int bits_per_entry = 8 * sb->s_blocksize;
+        int map, bit;
+        int ret = 0;
+        u64 tmp;
+
+        tmp = block;
+        bit = do_div(tmp, bits_per_entry);
+        map = tmp;
+
+        mutex_lock(&sbi->s_bitmap_lock);
+        if (map >= sbi->s_imap_size || test_and_set_bit(bit, sbi->s_imap[map]))
+                goto out;
+
+        if (sbi->s_bitmap_ino > 0) {
+                bh = sb_bread(sb, clus_to_blk(sbi, sbi->s_bitmap_ino) + map);
+                if (!bh)
+                        goto out;
+
+                set_bit(bit, (unsigned long *)bh->b_data);
+                mark_buffer_dirty(bh);
+                brelse(bh);
+        }
+        ret = 1;
+out:
+        mutex_unlock(&sbi->s_bitmap_lock);
+        return ret;
+}
+
+
+/*
+ *  Tries to allocate a set of blocks.  The request size depends on the
+ *  type: for inodes, we must allocate sbi->s_mirrors blocks, and for file
+ *  blocks, we try to allocate sbi->s_clustersize, but can always get away
+ *  with just one block.
+ */
+int omfs_allocate_range(struct super_block *sb,
+                        int min_request,
+                        int max_request,
+                        u64 *return_block,
+                        int *return_size)
+{
+        struct omfs_sb_info *sbi = OMFS_SB(sb);
+        int bits_per_entry = 8 * sb->s_blocksize;
+        int ret = 0;
+        int i, run, bit;
+
+        mutex_lock(&sbi->s_bitmap_lock);
+        for (i = 0; i < sbi->s_imap_size; i++) {
+                bit = 0;
+                while (bit < bits_per_entry) {
+                        bit = find_next_zero_bit(sbi->s_imap[i], bits_per_entry,
+                                bit);
+
+                        if (bit == bits_per_entry)
+                                break;
+
+                        run = count_run(&sbi->s_imap[i], bits_per_entry,
+                                sbi->s_imap_size-i, bit, max_request);
+
+                        if (run >= min_request)
+                                goto found;
+                        bit += run;
+                }
+        }
+        ret = -ENOSPC;
+        goto out;
+
+found:
+        *return_block = i * bits_per_entry + bit;
+        *return_size = run;
+        ret = set_run(sb, i, bits_per_entry, bit, run, 1);
+
+out:
+        mutex_unlock(&sbi->s_bitmap_lock);
+        return ret;
+}
+
+/*
+ * Clears count bits starting at a given block.
+ */
+int omfs_clear_range(struct super_block *sb, u64 block, int count)
+{
+        struct omfs_sb_info *sbi = OMFS_SB(sb);
+        int bits_per_entry = 8 * sb->s_blocksize;
+        u64 tmp;
+        int map, bit, ret;
+
+        tmp = block;
+        bit = do_div(tmp, bits_per_entry);
+        map = tmp;
+
+        if (map >= sbi->s_imap_size)
+                return 0;
+
+        mutex_lock(&sbi->s_bitmap_lock);
+        ret = set_run(sb, map, bits_per_entry, bit, count, 0);
+        mutex_unlock(&sbi->s_bitmap_lock);
+        return ret;
+}
diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c
new file mode 100644
index 000000000000..c0757e998876
--- /dev/null
+++ b/fs/omfs/dir.c
@@ -0,0 +1,504 @@
+/*
+ * OMFS (as used by RIO Karma) directory operations.
+ * Copyright (C) 2005 Bob Copeland <me@bobcopeland.com>
+ * Released under GPL v2.
+ */
+
+#include <linux/fs.h>
+#include <linux/ctype.h>
+#include <linux/buffer_head.h>
+#include "omfs.h"
+
+static int omfs_hash(const char *name, int namelen, int mod)
+{
+        int i, hash = 0;
+        for (i = 0; i < namelen; i++)
+                hash ^= tolower(name[i]) << (i % 24);
+        return hash % mod;
+}
+
+/*
+ * Finds the bucket for a given name and reads the containing block;
+ * *ofs is set to the offset of the first list entry.
+ */
+static struct buffer_head *omfs_get_bucket(struct inode *dir,
+                const char *name, int namelen, int *ofs)
+{
+        int nbuckets = (dir->i_size - OMFS_DIR_START)/8;
+        int block = clus_to_blk(OMFS_SB(dir->i_sb), dir->i_ino);
+        int bucket = omfs_hash(name, namelen, nbuckets);
+
+        *ofs = OMFS_DIR_START + bucket * 8;
+        return sb_bread(dir->i_sb, block);
+}
+
+static struct buffer_head *omfs_scan_list(struct inode *dir, u64 block,
+                                const char *name, int namelen,
+                                u64 *prev_block)
+{
+        struct buffer_head *bh;
+        struct omfs_inode *oi;
+        int err = -ENOENT;
+        *prev_block = ~0;
+
+        while (block != ~0) {
+                bh = sb_bread(dir->i_sb,
+                        clus_to_blk(OMFS_SB(dir->i_sb), block));
+                if (!bh) {
+                        err = -EIO;
+                        goto err;
+                }
+
+                oi = (struct omfs_inode *) bh->b_data;
+                if (omfs_is_bad(OMFS_SB(dir->i_sb), &oi->i_head, block)) {
+                        brelse(bh);
+                        goto err;
+                }
+
+                if (strncmp(oi->i_name, name, namelen) == 0)
+                        return bh;
+
+                *prev_block = block;
+                block = be64_to_cpu(oi->i_sibling);
+                brelse(bh);
+        }
+err:
+        return ERR_PTR(err);
+}
+
+static struct buffer_head *omfs_find_entry(struct inode *dir,
+                                           const char *name, int namelen)
+{
+        struct buffer_head *bh;
+        int ofs;
+        u64 block, dummy;
+
+        bh = omfs_get_bucket(dir, name, namelen, &ofs);
+        if (!bh)
+                return ERR_PTR(-EIO);
+
+        block = be64_to_cpu(*((__be64 *) &bh->b_data[ofs]));
+        brelse(bh);
+
+        return omfs_scan_list(dir, block, name, namelen, &dummy);
+}
+
+int omfs_make_empty(struct inode *inode, struct super_block *sb)
+{
+        struct omfs_sb_info *sbi = OMFS_SB(sb);
+        int block = clus_to_blk(sbi, inode->i_ino);
+        struct buffer_head *bh;
+        struct omfs_inode *oi;
+
+        bh = sb_bread(sb, block);
+        if (!bh)
+                return -ENOMEM;
+
+        memset(bh->b_data, 0, sizeof(struct omfs_inode));
+
+        if (inode->i_mode & S_IFDIR) {
+                memset(&bh->b_data[OMFS_DIR_START], 0xff,
+                        sbi->s_sys_blocksize - OMFS_DIR_START);
+        } else
+                omfs_make_empty_table(bh, OMFS_EXTENT_START);
+
+        oi = (struct omfs_inode *) bh->b_data;
+        oi->i_head.h_self = cpu_to_be64(inode->i_ino);
+        oi->i_sibling = ~cpu_to_be64(0ULL);
+
+        mark_buffer_dirty(bh);
+        brelse(bh);
+        return 0;
+}
+
+static int omfs_add_link(struct dentry *dentry, struct inode *inode)
+{
+        struct inode *dir = dentry->d_parent->d_inode;
+        const char *name = dentry->d_name.name;
+        int namelen = dentry->d_name.len;
+        struct omfs_inode *oi;
+        struct buffer_head *bh;
+        u64 block;
+        __be64 *entry;
+        int ofs;
+
+        /* just prepend to head of queue in proper bucket */
+        bh = omfs_get_bucket(dir, name, namelen, &ofs);
+        if (!bh)
+                goto out;
+
+        entry = (__be64 *) &bh->b_data[ofs];
+        block = be64_to_cpu(*entry);
+        *entry = cpu_to_be64(inode->i_ino);
+        mark_buffer_dirty(bh);
+        brelse(bh);
+
+        /* now set the sibling and parent pointers on the new inode */
+        bh = sb_bread(dir->i_sb, clus_to_blk(OMFS_SB(dir->i_sb), inode->i_ino));
+        if (!bh)
+                goto out;
+
+        oi = (struct omfs_inode *) bh->b_data;
+        memcpy(oi->i_name, name, namelen);
+        memset(oi->i_name + namelen, 0, OMFS_NAMELEN - namelen);
+        oi->i_sibling = cpu_to_be64(block);
+        oi->i_parent = cpu_to_be64(dir->i_ino);
+        mark_buffer_dirty(bh);
+        brelse(bh);
+
+        dir->i_ctime = CURRENT_TIME_SEC;
+
+        /* mark affected inodes dirty to rebuild checksums */
+        mark_inode_dirty(dir);
+        mark_inode_dirty(inode);
+        return 0;
+out:
+        return -ENOMEM;
+}
+
+static int omfs_delete_entry(struct dentry *dentry)
+{
+        struct inode *dir = dentry->d_parent->d_inode;
+        struct inode *dirty;
+        const char *name = dentry->d_name.name;
+        int namelen = dentry->d_name.len;
+        struct omfs_inode *oi;
+        struct buffer_head *bh, *bh2;
+        __be64 *entry, next;
+        u64 block, prev;
+        int ofs;
+        int err = -ENOMEM;
+
+        /* delete the proper node in the bucket's linked list */
+        bh = omfs_get_bucket(dir, name, namelen, &ofs);
+        if (!bh)
+                goto out;
+
+        entry = (__be64 *) &bh->b_data[ofs];
+        block = be64_to_cpu(*entry);
+
+        bh2 = omfs_scan_list(dir, block, name, namelen, &prev);
+        if (IS_ERR(bh2)) {
+                err = PTR_ERR(bh2);
+                goto out_free_bh;
+        }
+
+        oi = (struct omfs_inode *) bh2->b_data;
+        next = oi->i_sibling;
+        brelse(bh2);
+
+        if (prev != ~0) {
+                /* found in middle of list, get list ptr */
+                brelse(bh);
+                bh = sb_bread(dir->i_sb,
+                        clus_to_blk(OMFS_SB(dir->i_sb), prev));
+                if (!bh)
+                        goto out;
+
+                oi = (struct omfs_inode *) bh->b_data;
+                entry = &oi->i_sibling;
+        }
+
+        *entry = next;
+        mark_buffer_dirty(bh);
+
+        if (prev != ~0) {
+                dirty = omfs_iget(dir->i_sb, prev);
+                if (!IS_ERR(dirty)) {
+                        mark_inode_dirty(dirty);
+                        iput(dirty);
+                }
+        }
+
+        err = 0;
+out_free_bh:
+        brelse(bh);
+out:
+        return err;
+}
+
+static int omfs_dir_is_empty(struct inode *inode)
+{
+        int nbuckets = (inode->i_size - OMFS_DIR_START) / 8;
+        struct buffer_head *bh;
+        u64 *ptr;
+        int i;
+
+        bh = sb_bread(inode->i_sb, clus_to_blk(OMFS_SB(inode->i_sb),
+                        inode->i_ino));
+
+        if (!bh)
+                return 0;
+
+        ptr = (u64 *) &bh->b_data[OMFS_DIR_START];
+
+        for (i = 0; i < nbuckets; i++, ptr++)
+                if (*ptr != ~0)
+                        break;
+
+        brelse(bh);
+        return *ptr != ~0;
+}
+
+static int omfs_unlink(struct inode *dir, struct dentry *dentry)
+{
+        int ret;
+        struct inode *inode = dentry->d_inode;
+
+        ret = omfs_delete_entry(dentry);
+        if (ret)
+                goto end_unlink;
+
+        inode_dec_link_count(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;
+}
+
+static int omfs_add_node(struct inode *dir, struct dentry *dentry, int mode)
+{
+        int err;
+        struct inode *inode = omfs_new_inode(dir, mode);
+
+        if (IS_ERR(inode))
+                return PTR_ERR(inode);
+
+        err = omfs_make_empty(inode, dir->i_sb);
+        if (err)
+                goto out_free_inode;
+
+        err = omfs_add_link(dentry, inode);
+        if (err)
+                goto out_free_inode;
+
+        d_instantiate(dentry, inode);
+        return 0;
+
+out_free_inode:
+        iput(inode);
+        return err;
+}
+
+static int omfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
+{
+        return omfs_add_node(dir, dentry, mode | S_IFDIR);
+}
+
+static int omfs_create(struct inode *dir, struct dentry *dentry, int mode,
+                struct nameidata *nd)
+{
+        return omfs_add_node(dir, dentry, mode | S_IFREG);
+}
+
+static struct dentry *omfs_lookup(struct inode *dir, struct dentry *dentry,
+                                  struct nameidata *nd)
+{
+        struct buffer_head *bh;
+        struct inode *inode = NULL;
+
+        if (dentry->d_name.len > OMFS_NAMELEN)
+                return ERR_PTR(-ENAMETOOLONG);
+
+        bh = omfs_find_entry(dir, dentry->d_name.name, dentry->d_name.len);
+        if (!IS_ERR(bh)) {
+                struct omfs_inode *oi = (struct omfs_inode *)bh->b_data;
+                ino_t ino = be64_to_cpu(oi->i_head.h_self);
+                brelse(bh);
+                inode = omfs_iget(dir->i_sb, ino);
+                if (IS_ERR(inode))
+                        return ERR_CAST(inode);
+        }
+        d_add(dentry, inode);
+        return NULL;
+}
+
+/* sanity check block's self pointer */
+int omfs_is_bad(struct omfs_sb_info *sbi, struct omfs_header *header,
+        u64 fsblock)
+{
+        int is_bad;
+        u64 ino = be64_to_cpu(header->h_self);
+        is_bad = ((ino != fsblock) || (ino < sbi->s_root_ino) ||
+                (ino > sbi->s_num_blocks));
+
+        if (is_bad)
+                printk(KERN_WARNING "omfs: bad hash chain detected\n");
+
+        return is_bad;
+}
+
+static int omfs_fill_chain(struct file *filp, void *dirent, filldir_t filldir,
+                u64 fsblock, int hindex)
+{
+        struct inode *dir = filp->f_dentry->d_inode;
+        struct buffer_head *bh;
+        struct omfs_inode *oi;
+        u64 self;
+        int res = 0;
+        unsigned char d_type;
+
+        /* follow chain in this bucket */
+        while (fsblock != ~0) {
+                bh = sb_bread(dir->i_sb, clus_to_blk(OMFS_SB(dir->i_sb),
+                                fsblock));
+                if (!bh)
+                        goto out;
+
+                oi = (struct omfs_inode *) bh->b_data;
+                if (omfs_is_bad(OMFS_SB(dir->i_sb), &oi->i_head, fsblock)) {
+                        brelse(bh);
+                        goto out;
+                }
+
+                self = fsblock;
+                fsblock = be64_to_cpu(oi->i_sibling);
+
+                /* skip visited nodes */
+                if (hindex) {
+                        hindex--;
+                        brelse(bh);
+                        continue;
+                }
+
+                d_type = (oi->i_type == OMFS_DIR) ? DT_DIR : DT_REG;
+
+                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);
+        }
+out:
+        return res;
+}
+
+static int omfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+                struct inode *new_dir, struct dentry *new_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);
+                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);
+                goto out;
+        }
+
+        err = omfs_add_link(new_dentry, old_inode);
+        if (err)
+                goto out;
+
+        old_inode->i_ctime = CURRENT_TIME_SEC;
+out:
+        return err;
+}
+
+static int omfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
+{
+        struct inode *dir = filp->f_dentry->d_inode;
+        struct buffer_head *bh;
+        loff_t offset, res;
+        unsigned int hchain, hindex;
+        int nbuckets;
+        u64 fsblock;
+        int ret = -EINVAL;
+
+        if (filp->f_pos >> 32)
+                goto success;
+
+        switch ((unsigned long) filp->f_pos) {
+        case 0:
+                if (filldir(dirent, ".", 1, 0, dir->i_ino, DT_DIR) < 0)
+                        goto success;
+                filp->f_pos++;
+                /* fall through */
+        case 1:
+                if (filldir(dirent, "..", 2, 1,
+                    parent_ino(filp->f_dentry), DT_DIR) < 0)
+                        goto success;
+                filp->f_pos = 1 << 20;
+                /* fall through */
+        }
+
+        nbuckets = (dir->i_size - OMFS_DIR_START) / 8;
+
+        /* high 12 bits store bucket + 1 and low 20 bits store hash index */
+        hchain = (filp->f_pos >> 20) - 1;
+        hindex = filp->f_pos & 0xfffff;
+
+        bh = sb_bread(dir->i_sb, clus_to_blk(OMFS_SB(dir->i_sb), dir->i_ino));
+        if (!bh)
+                goto out;
+
+        offset = OMFS_DIR_START + hchain * 8;
+
+        for (; hchain < nbuckets; hchain++, offset += 8) {
+                fsblock = be64_to_cpu(*((__be64 *) &bh->b_data[offset]));
+
+                res = omfs_fill_chain(filp, dirent, filldir, fsblock, hindex);
+                hindex = 0;
+                if (res < 0)
+                        break;
+
+                filp->f_pos = (hchain+2) << 20;
+        }
+        brelse(bh);
+success:
+        ret = 0;
+out:
+        return ret;
+}
+
+struct inode_operations omfs_dir_inops = {
+        .lookup = omfs_lookup,
+        .mkdir = omfs_mkdir,
+        .rename = omfs_rename,
+        .create = omfs_create,
+        .unlink = omfs_unlink,
+        .rmdir = omfs_rmdir,
+};
+
+struct file_operations omfs_dir_operations = {
+        .read = generic_read_dir,
+        .readdir = omfs_readdir,
+};
diff --git a/fs/omfs/file.c b/fs/omfs/file.c
new file mode 100644
index 000000000000..7e2499053e4d
--- /dev/null
+++ b/fs/omfs/file.c
@@ -0,0 +1,346 @@
+/*
+ * OMFS (as used by RIO Karma) file operations.
+ * Copyright (C) 2005 Bob Copeland <me@bobcopeland.com>
+ * Released under GPL v2.
+ */
+
+#include <linux/version.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/buffer_head.h>
+#include <linux/mpage.h>
+#include "omfs.h"
+
+static int omfs_sync_file(struct file *file, struct dentry *dentry,
+                int datasync)
+{
+        struct inode *inode = dentry->d_inode;
+        int err;
+
+        err = sync_mapping_buffers(inode->i_mapping);
+        if (!(inode->i_state & I_DIRTY))
+                return err;
+        if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
+                return err;
+        err |= omfs_sync_inode(inode);
+        return err ? -EIO : 0;
+}
+
+void omfs_make_empty_table(struct buffer_head *bh, int offset)
+{
+        struct omfs_extent *oe = (struct omfs_extent *) &bh->b_data[offset];
+
+        oe->e_next = ~cpu_to_be64(0ULL);
+        oe->e_extent_count = cpu_to_be32(1),
+        oe->e_fill = cpu_to_be32(0x22),
+        oe->e_entry.e_cluster = ~cpu_to_be64(0ULL);
+        oe->e_entry.e_blocks = ~cpu_to_be64(0ULL);
+}
+
+int omfs_shrink_inode(struct inode *inode)
+{
+        struct omfs_sb_info *sbi = OMFS_SB(inode->i_sb);
+        struct omfs_extent *oe;
+        struct omfs_extent_entry *entry;
+        struct buffer_head *bh;
+        u64 next, last;
+        u32 extent_count;
+        int ret;
+
+        /* traverse extent table, freeing each entry that is greater
+         * than inode->i_size;
+         */
+        next = inode->i_ino;
+
+        /* only support truncate -> 0 for now */
+        ret = -EIO;
+        if (inode->i_size != 0)
+                goto out;
+
+        bh = sb_bread(inode->i_sb, clus_to_blk(sbi, next));
+        if (!bh)
+                goto out;
+
+        oe = (struct omfs_extent *)(&bh->b_data[OMFS_EXTENT_START]);
+
+        for (;;) {
+
+                if (omfs_is_bad(sbi, (struct omfs_header *) bh->b_data, next)) {
+                        brelse(bh);
+                        goto out;
+                }
+
+                extent_count = be32_to_cpu(oe->e_extent_count);
+                last = next;
+                next = be64_to_cpu(oe->e_next);
+                entry = &oe->e_entry;
+
+                /* ignore last entry as it is the terminator */
+                for (; extent_count > 1; extent_count--) {
+                        u64 start, count;
+                        start = be64_to_cpu(entry->e_cluster);
+                        count = be64_to_cpu(entry->e_blocks);
+
+                        omfs_clear_range(inode->i_sb, start, (int) count);
+                        entry++;
+                }
+                omfs_make_empty_table(bh, (char *) oe - bh->b_data);
+                mark_buffer_dirty(bh);
+                brelse(bh);
+
+                if (last != inode->i_ino)
+                        omfs_clear_range(inode->i_sb, last, sbi->s_mirrors);
+
+                if (next == ~0)
+                        break;
+
+                bh = sb_bread(inode->i_sb, clus_to_blk(sbi, next));
+                if (!bh)
+                        goto out;
+                oe = (struct omfs_extent *) (&bh->b_data[OMFS_EXTENT_CONT]);
+        }
+        ret = 0;
+out:
+        return ret;
+}
+
+static void omfs_truncate(struct inode *inode)
+{
+        omfs_shrink_inode(inode);
+        mark_inode_dirty(inode);
+}
+
+/*
+ * Add new blocks to the current extent, or create new entries/continuations
+ * as necessary.
+ */
+static int omfs_grow_extent(struct inode *inode, struct omfs_extent *oe,
+                        u64 *ret_block)
+{
+        struct omfs_extent_entry *terminator;
+        struct omfs_extent_entry *entry = &oe->e_entry;
+        struct omfs_sb_info *sbi = OMFS_SB(inode->i_sb);
+        u32 extent_count = be32_to_cpu(oe->e_extent_count);
+        u64 new_block = 0;
+        u32 max_count;
+        int new_count;
+        int ret = 0;
+
+        /* reached the end of the extent table with no blocks mapped.
+         * there are three possibilities for adding: grow last extent,
+         * add a new extent to the current extent table, and add a
+         * continuation inode.  in last two cases need an allocator for
+         * sbi->s_cluster_size
+         */
+
+        /* TODO: handle holes */
+
+        /* should always have a terminator */
+        if (extent_count < 1)
+                return -EIO;
+
+        /* trivially grow current extent, if next block is not taken */
+        terminator = entry + extent_count - 1;
+        if (extent_count > 1) {
+                entry = terminator-1;
+                new_block = be64_to_cpu(entry->e_cluster) +
+                        be64_to_cpu(entry->e_blocks);
+
+                if (omfs_allocate_block(inode->i_sb, new_block)) {
+                        entry->e_blocks =
+                                cpu_to_be64(be64_to_cpu(entry->e_blocks) + 1);
+                        terminator->e_blocks = ~(cpu_to_be64(
+                                be64_to_cpu(~terminator->e_blocks) + 1));
+                        goto out;
+                }
+        }
+        max_count = (sbi->s_sys_blocksize - OMFS_EXTENT_START -
+                sizeof(struct omfs_extent)) /
+                sizeof(struct omfs_extent_entry) + 1;
+
+        /* TODO: add a continuation block here */
+        if (be32_to_cpu(oe->e_extent_count) > max_count-1)
+                return -EIO;
+
+        /* try to allocate a new cluster */
+        ret = omfs_allocate_range(inode->i_sb, 1, sbi->s_clustersize,
+                &new_block, &new_count);
+        if (ret)
+                goto out_fail;
+
+        /* copy terminator down an entry */
+        entry = terminator;
+        terminator++;
+        memcpy(terminator, entry, sizeof(struct omfs_extent_entry));
+
+        entry->e_cluster = cpu_to_be64(new_block);
+        entry->e_blocks = cpu_to_be64((u64) new_count);
+
+        terminator->e_blocks = ~(cpu_to_be64(
+                be64_to_cpu(~terminator->e_blocks) + (u64) new_count));
+
+        /* write in new entry */
+        oe->e_extent_count = cpu_to_be32(1 + be32_to_cpu(oe->e_extent_count));
+
+out:
+        *ret_block = new_block;
+out_fail:
+        return ret;
+}
+
+/*
+ * Scans across the directory table for a given file block number.
+ * If block not found, return 0.
+ */
+static sector_t find_block(struct inode *inode, struct omfs_extent_entry *ent,
+                        sector_t block, int count, int *left)
+{
+        /* count > 1 because of terminator */
+        sector_t searched = 0;
+        for (; count > 1; count--) {
+                int numblocks = clus_to_blk(OMFS_SB(inode->i_sb),
+                        be64_to_cpu(ent->e_blocks));
+
+                if (block >= searched  &&
+                    block < searched + numblocks) {
+                        /*
+                         * found it at cluster + (block - searched)
+                         * numblocks - (block - searched) is remainder
+                         */
+                        *left = numblocks - (block - searched);
+                        return clus_to_blk(OMFS_SB(inode->i_sb),
+                                be64_to_cpu(ent->e_cluster)) +
+                                block - searched;
+                }
+                searched += numblocks;
+                ent++;
+        }
+        return 0;
+}
+
+static int omfs_get_block(struct inode *inode, sector_t block,
+                          struct buffer_head *bh_result, int create)
+{
+        struct buffer_head *bh;
+        sector_t next, offset;
+        int ret;
+        u64 new_block;
+        int extent_count;
+        struct omfs_extent *oe;
+        struct omfs_extent_entry *entry;
+        struct omfs_sb_info *sbi = OMFS_SB(inode->i_sb);
+        int max_blocks = bh_result->b_size >> inode->i_blkbits;
+        int remain;
+
+        ret = -EIO;
+        bh = sb_bread(inode->i_sb, clus_to_blk(sbi, inode->i_ino));
+        if (!bh)
+                goto out;
+
+        oe = (struct omfs_extent *)(&bh->b_data[OMFS_EXTENT_START]);
+        next = inode->i_ino;
+
+        for (;;) {
+
+                if (omfs_is_bad(sbi, (struct omfs_header *) bh->b_data, next))
+                        goto out_brelse;
+
+                extent_count = be32_to_cpu(oe->e_extent_count);
+                next = be64_to_cpu(oe->e_next);
+                entry = &oe->e_entry;
+
+                offset = find_block(inode, entry, block, extent_count, &remain);
+                if (offset > 0) {
+                        ret = 0;
+                        map_bh(bh_result, inode->i_sb, offset);
+                        if (remain > max_blocks)
+                                remain = max_blocks;
+                        bh_result->b_size = (remain << inode->i_blkbits);
+                        goto out_brelse;
+                }
+                if (next == ~0)
+                        break;
+
+                brelse(bh);
+                bh = sb_bread(inode->i_sb, clus_to_blk(sbi, next));
+                if (!bh)
+                        goto out;
+                oe = (struct omfs_extent *) (&bh->b_data[OMFS_EXTENT_CONT]);
+        }
+        if (create) {
+                ret = omfs_grow_extent(inode, oe, &new_block);
+                if (ret == 0) {
+                        mark_buffer_dirty(bh);
+                        mark_inode_dirty(inode);
+                        map_bh(bh_result, inode->i_sb,
+                                        clus_to_blk(sbi, new_block));
+                }
+        }
+out_brelse:
+        brelse(bh);
+out:
+        return ret;
+}
+
+static int omfs_readpage(struct file *file, struct page *page)
+{
+        return block_read_full_page(page, omfs_get_block);
+}
+
+static int omfs_readpages(struct file *file, struct address_space *mapping,
+                struct list_head *pages, unsigned nr_pages)
+{
+        return mpage_readpages(mapping, pages, nr_pages, omfs_get_block);
+}
+
+static int omfs_writepage(struct page *page, struct writeback_control *wbc)
+{
+        return block_write_full_page(page, omfs_get_block, wbc);
+}
+
+static int
+omfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
+{
+        return mpage_writepages(mapping, wbc, omfs_get_block);
+}
+
+static int omfs_write_begin(struct file *file, struct address_space *mapping,
+                        loff_t pos, unsigned len, unsigned flags,
+                        struct page **pagep, void **fsdata)
+{
+        *pagep = NULL;
+        return block_write_begin(file, mapping, pos, len, flags,
+                                pagep, fsdata, omfs_get_block);
+}
+
+static sector_t omfs_bmap(struct address_space *mapping, sector_t block)
+{
+        return generic_block_bmap(mapping, block, omfs_get_block);
+}
+
+struct file_operations omfs_file_operations = {
+        .llseek = generic_file_llseek,
+        .read = do_sync_read,
+        .write = do_sync_write,
+        .aio_read = generic_file_aio_read,
+        .aio_write = generic_file_aio_write,
+        .mmap = generic_file_mmap,
+        .fsync = omfs_sync_file,
+        .splice_read = generic_file_splice_read,
+};
+
+struct inode_operations omfs_file_inops = {
+        .truncate = omfs_truncate
+};
+
+struct address_space_operations omfs_aops = {
+        .readpage = omfs_readpage,
+        .readpages = omfs_readpages,
+        .writepage = omfs_writepage,
+        .writepages = omfs_writepages,
+        .sync_page = block_sync_page,
+        .write_begin = omfs_write_begin,
+        .write_end = generic_write_end,
+        .bmap = omfs_bmap,
+};
+
diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c
new file mode 100644
index 000000000000..a95fe5984f4b
--- /dev/null
+++ b/fs/omfs/inode.c
@@ -0,0 +1,554 @@
+/*
+ * Optimized MPEG FS - inode and super operations.
+ * Copyright (C) 2006 Bob Copeland <me@bobcopeland.com>
+ * Released under GPL v2.
+ */
+#include <linux/version.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+#include <linux/vfs.h>
+#include <linux/parser.h>
+#include <linux/buffer_head.h>
+#include <linux/vmalloc.h>
+#include <linux/crc-itu-t.h>
+#include "omfs.h"
+
+MODULE_AUTHOR("Bob Copeland <me@bobcopeland.com>");
+MODULE_DESCRIPTION("OMFS (ReplayTV/Karma) Filesystem for Linux");
+MODULE_LICENSE("GPL");
+
+struct inode *omfs_new_inode(struct inode *dir, int mode)
+{
+        struct inode *inode;
+        u64 new_block;
+        int err;
+        int len;
+        struct omfs_sb_info *sbi = OMFS_SB(dir->i_sb);
+
+        inode = new_inode(dir->i_sb);
+        if (!inode)
+                return ERR_PTR(-ENOMEM);
+
+        err = omfs_allocate_range(dir->i_sb, sbi->s_mirrors, sbi->s_mirrors,
+                        &new_block, &len);
+        if (err)
+                goto fail;
+
+        inode->i_ino = new_block;
+        inode->i_mode = mode;
+        inode->i_uid = current->fsuid;
+        inode->i_gid = current->fsgid;
+        inode->i_blocks = 0;
+        inode->i_mapping->a_ops = &omfs_aops;
+
+        inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+        switch (mode & S_IFMT) {
+        case S_IFDIR:
+                inode->i_op = &omfs_dir_inops;
+                inode->i_fop = &omfs_dir_operations;
+                inode->i_size = sbi->s_sys_blocksize;
+                inc_nlink(inode);
+                break;
+        case S_IFREG:
+                inode->i_op = &omfs_file_inops;
+                inode->i_fop = &omfs_file_operations;
+                inode->i_size = 0;
+                break;
+        }
+
+        insert_inode_hash(inode);
+        mark_inode_dirty(inode);
+        return inode;
+fail:
+        make_bad_inode(inode);
+        iput(inode);
+        return ERR_PTR(err);
+}
+
+/*
+ * Update the header checksums for a dirty inode based on its contents.
+ * Caller is expected to hold the buffer head underlying oi and mark it
+ * dirty.
+ */
+static void omfs_update_checksums(struct omfs_inode *oi)
+{
+        int xor, i, ofs = 0, count;
+        u16 crc = 0;
+        unsigned char *ptr = (unsigned char *) oi;
+
+        count = be32_to_cpu(oi->i_head.h_body_size);
+        ofs = sizeof(struct omfs_header);
+
+        crc = crc_itu_t(crc, ptr + ofs, count);
+        oi->i_head.h_crc = cpu_to_be16(crc);
+
+        xor = ptr[0];
+        for (i = 1; i < OMFS_XOR_COUNT; i++)
+                xor ^= ptr[i];
+
+        oi->i_head.h_check_xor = xor;
+}
+
+static int omfs_write_inode(struct inode *inode, int wait)
+{
+        struct omfs_inode *oi;
+        struct omfs_sb_info *sbi = OMFS_SB(inode->i_sb);
+        struct buffer_head *bh, *bh2;
+        unsigned int block;
+        u64 ctime;
+        int i;
+        int ret = -EIO;
+        int sync_failed = 0;
+
+        /* get current inode since we may have written sibling ptrs etc. */
+        block = clus_to_blk(sbi, inode->i_ino);
+        bh = sb_bread(inode->i_sb, block);
+        if (!bh)
+                goto out;
+
+        oi = (struct omfs_inode *) bh->b_data;
+
+        oi->i_head.h_self = cpu_to_be64(inode->i_ino);
+        if (S_ISDIR(inode->i_mode))
+                oi->i_type = OMFS_DIR;
+        else if (S_ISREG(inode->i_mode))
+                oi->i_type = OMFS_FILE;
+        else {
+                printk(KERN_WARNING "omfs: unknown file type: %d\n",
+                        inode->i_mode);
+                goto out_brelse;
+        }
+
+        oi->i_head.h_body_size = cpu_to_be32(sbi->s_sys_blocksize -
+                sizeof(struct omfs_header));
+        oi->i_head.h_version = 1;
+        oi->i_head.h_type = OMFS_INODE_NORMAL;
+        oi->i_head.h_magic = OMFS_IMAGIC;
+        oi->i_size = cpu_to_be64(inode->i_size);
+
+        ctime = inode->i_ctime.tv_sec * 1000LL +
+                ((inode->i_ctime.tv_nsec + 999)/1000);
+        oi->i_ctime = cpu_to_be64(ctime);
+
+        omfs_update_checksums(oi);
+
+        mark_buffer_dirty(bh);
+        if (wait) {
+                sync_dirty_buffer(bh);
+                if (buffer_req(bh) && !buffer_uptodate(bh))
+                        sync_failed = 1;
+        }
+
+        /* if mirroring writes, copy to next fsblock */
+        for (i = 1; i < sbi->s_mirrors; i++) {
+                bh2 = sb_bread(inode->i_sb, block + i *
+                        (sbi->s_blocksize / sbi->s_sys_blocksize));
+                if (!bh2)
+                        goto out_brelse;
+
+                memcpy(bh2->b_data, bh->b_data, bh->b_size);
+                mark_buffer_dirty(bh2);
+                if (wait) {
+                        sync_dirty_buffer(bh2);
+                        if (buffer_req(bh2) && !buffer_uptodate(bh2))
+                                sync_failed = 1;
+                }
+                brelse(bh2);
+        }
+        ret = (sync_failed) ? -EIO : 0;
+out_brelse:
+        brelse(bh);
+out:
+        return ret;
+}
+
+int omfs_sync_inode(struct inode *inode)
+{
+        return omfs_write_inode(inode, 1);
+}
+
+/*
+ * called when an entry is deleted, need to clear the bits in the
+ * bitmaps.
+ */
+static void omfs_delete_inode(struct inode *inode)
+{
+        truncate_inode_pages(&inode->i_data, 0);
+
+        if (S_ISREG(inode->i_mode)) {
+                inode->i_size = 0;
+                omfs_shrink_inode(inode);
+        }
+
+        omfs_clear_range(inode->i_sb, inode->i_ino, 2);
+        clear_inode(inode);
+}
+
+struct inode *omfs_iget(struct super_block *sb, ino_t ino)
+{
+        struct omfs_sb_info *sbi = OMFS_SB(sb);
+        struct omfs_inode *oi;
+        struct buffer_head *bh;
+        unsigned int block;
+        u64 ctime;
+        unsigned long nsecs;
+        struct inode *inode;
+
+        inode = iget_locked(sb, ino);
+        if (!inode)
+                return ERR_PTR(-ENOMEM);
+        if (!(inode->i_state & I_NEW))
+                return inode;
+
+        block = clus_to_blk(sbi, ino);
+        bh = sb_bread(inode->i_sb, block);
+        if (!bh)
+                goto iget_failed;
+
+        oi = (struct omfs_inode *)bh->b_data;
+
+        /* check self */
+        if (ino != be64_to_cpu(oi->i_head.h_self))
+                goto fail_bh;
+
+        inode->i_uid = sbi->s_uid;
+        inode->i_gid = sbi->s_gid;
+
+        ctime = be64_to_cpu(oi->i_ctime);
+        nsecs = do_div(ctime, 1000) * 1000L;
+
+        inode->i_atime.tv_sec = ctime;
+        inode->i_mtime.tv_sec = ctime;
+        inode->i_ctime.tv_sec = ctime;
+        inode->i_atime.tv_nsec = nsecs;
+        inode->i_mtime.tv_nsec = nsecs;
+        inode->i_ctime.tv_nsec = nsecs;
+
+        inode->i_mapping->a_ops = &omfs_aops;
+
+        switch (oi->i_type) {
+        case OMFS_DIR:
+                inode->i_mode = S_IFDIR | (S_IRWXUGO & ~sbi->s_dmask);
+                inode->i_op = &omfs_dir_inops;
+                inode->i_fop = &omfs_dir_operations;
+                inode->i_size = be32_to_cpu(oi->i_head.h_body_size) +
+                        sizeof(struct omfs_header);
+                inc_nlink(inode);
+                break;
+        case OMFS_FILE:
+                inode->i_mode = S_IFREG | (S_IRWXUGO & ~sbi->s_fmask);
+                inode->i_fop = &omfs_file_operations;
+                inode->i_size = be64_to_cpu(oi->i_size);
+                break;
+        }
+        brelse(bh);
+        unlock_new_inode(inode);
+        return inode;
+fail_bh:
+        brelse(bh);
+iget_failed:
+        iget_failed(inode);
+        return ERR_PTR(-EIO);
+}
+
+static void omfs_put_super(struct super_block *sb)
+{
+        struct omfs_sb_info *sbi = OMFS_SB(sb);
+        kfree(sbi->s_imap);
+        kfree(sbi);
+        sb->s_fs_info = NULL;
+}
+
+static int omfs_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+        struct super_block *s = dentry->d_sb;
+        struct omfs_sb_info *sbi = OMFS_SB(s);
+        buf->f_type = OMFS_MAGIC;
+        buf->f_bsize = sbi->s_blocksize;
+        buf->f_blocks = sbi->s_num_blocks;
+        buf->f_files = sbi->s_num_blocks;
+        buf->f_namelen = OMFS_NAMELEN;
+
+        buf->f_bfree = buf->f_bavail = buf->f_ffree =
+                omfs_count_free(s);
+        return 0;
+}
+
+static struct super_operations omfs_sops = {
+        .write_inode    = omfs_write_inode,
+        .delete_inode   = omfs_delete_inode,
+        .put_super      = omfs_put_super,
+        .statfs         = omfs_statfs,
+        .show_options   = generic_show_options,
+};
+
+/*
+ * For Rio Karma, there is an on-disk free bitmap whose location is
+ * stored in the root block.  For ReplayTV, there is no such free bitmap
+ * so we have to walk the tree.  Both inodes and file data are allocated
+ * from the same map.  This array can be big (300k) so we allocate
+ * in units of the blocksize.
+ */
+static int omfs_get_imap(struct super_block *sb)
+{
+        int bitmap_size;
+        int array_size;
+        int count;
+        struct omfs_sb_info *sbi = OMFS_SB(sb);
+        struct buffer_head *bh;
+        unsigned long **ptr;
+        sector_t block;
+
+        bitmap_size = DIV_ROUND_UP(sbi->s_num_blocks, 8);
+        array_size = DIV_ROUND_UP(bitmap_size, sb->s_blocksize);
+
+        if (sbi->s_bitmap_ino == ~0ULL)
+                goto out;
+
+        sbi->s_imap_size = array_size;
+        sbi->s_imap = kzalloc(array_size * sizeof(unsigned long *), GFP_KERNEL);
+        if (!sbi->s_imap)
+                goto nomem;
+
+        block = clus_to_blk(sbi, sbi->s_bitmap_ino);
+        ptr = sbi->s_imap;
+        for (count = bitmap_size; count > 0; count -= sb->s_blocksize) {
+                bh = sb_bread(sb, block++);
+                if (!bh)
+                        goto nomem_free;
+                *ptr = kmalloc(sb->s_blocksize, GFP_KERNEL);
+                if (!*ptr) {
+                        brelse(bh);
+                        goto nomem_free;
+                }
+                memcpy(*ptr, bh->b_data, sb->s_blocksize);
+                if (count < sb->s_blocksize)
+                        memset((void *)*ptr + count, 0xff,
+                                sb->s_blocksize - count);
+                brelse(bh);
+                ptr++;
+        }
+out:
+        return 0;
+
+nomem_free:
+        for (count = 0; count < array_size; count++)
+                kfree(sbi->s_imap[count]);
+
+        kfree(sbi->s_imap);
+nomem:
+        sbi->s_imap = NULL;
+        sbi->s_imap_size = 0;
+        return -ENOMEM;
+}
+
+enum {
+        Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask
+};
+
+static match_table_t tokens = {
+        {Opt_uid, "uid=%u"},
+        {Opt_gid, "gid=%u"},
+        {Opt_umask, "umask=%o"},
+        {Opt_dmask, "dmask=%o"},
+        {Opt_fmask, "fmask=%o"},
+};
+
+static int parse_options(char *options, struct omfs_sb_info *sbi)
+{
+        char *p;
+        substring_t args[MAX_OPT_ARGS];
+        int option;
+
+        if (!options)
+                return 1;
+
+        while ((p = strsep(&options, ",")) != NULL) {
+                int token;
+                if (!*p)
+                        continue;
+
+                token = match_token(p, tokens, args);
+                switch (token) {
+                case Opt_uid:
+                        if (match_int(&args[0], &option))
+                                return 0;
+                        sbi->s_uid = option;
+                        break;
+                case Opt_gid:
+                        if (match_int(&args[0], &option))
+                                return 0;
+                        sbi->s_gid = option;
+                        break;
+                case Opt_umask:
+                        if (match_octal(&args[0], &option))
+                                return 0;
+                        sbi->s_fmask = sbi->s_dmask = option;
+                        break;
+                case Opt_dmask:
+                        if (match_octal(&args[0], &option))
+                                return 0;
+                        sbi->s_dmask = option;
+                        break;
+                case Opt_fmask:
+                        if (match_octal(&args[0], &option))
+                                return 0;
+                        sbi->s_fmask = option;
+                        break;
+                default:
+                        return 0;
+                }
+        }
+        return 1;
+}
+
+static int omfs_fill_super(struct super_block *sb, void *data, int silent)
+{
+        struct buffer_head *bh, *bh2;
+        struct omfs_super_block *omfs_sb;
+        struct omfs_root_block *omfs_rb;
+        struct omfs_sb_info *sbi;
+        struct inode *root;
+        sector_t start;
+        int ret = -EINVAL;
+
+        save_mount_options(sb, (char *) data);
+
+        sbi = kzalloc(sizeof(struct omfs_sb_info), GFP_KERNEL);
+        if (!sbi)
+                return -ENOMEM;
+
+        sb->s_fs_info = sbi;
+
+        sbi->s_uid = current->uid;
+        sbi->s_gid = current->gid;
+        sbi->s_dmask = sbi->s_fmask = current->fs->umask;
+
+        if (!parse_options((char *) data, sbi))
+                goto end;
+
+        sb->s_maxbytes = 0xffffffff;
+
+        sb_set_blocksize(sb, 0x200);
+
+        bh = sb_bread(sb, 0);
+        if (!bh)
+                goto end;
+
+        omfs_sb = (struct omfs_super_block *)bh->b_data;
+
+        if (omfs_sb->s_magic != cpu_to_be32(OMFS_MAGIC)) {
+                if (!silent)
+                        printk(KERN_ERR "omfs: Invalid superblock (%x)\n",
+                                   omfs_sb->s_magic);
+                goto out_brelse_bh;
+        }
+        sb->s_magic = OMFS_MAGIC;
+
+        sbi->s_num_blocks = be64_to_cpu(omfs_sb->s_num_blocks);
+        sbi->s_blocksize = be32_to_cpu(omfs_sb->s_blocksize);
+        sbi->s_mirrors = be32_to_cpu(omfs_sb->s_mirrors);
+        sbi->s_root_ino = be64_to_cpu(omfs_sb->s_root_block);
+        sbi->s_sys_blocksize = be32_to_cpu(omfs_sb->s_sys_blocksize);
+        mutex_init(&sbi->s_bitmap_lock);
+
+        if (sbi->s_sys_blocksize > PAGE_SIZE) {
+                printk(KERN_ERR "omfs: sysblock size (%d) is out of range\n",
+                        sbi->s_sys_blocksize);
+                goto out_brelse_bh;
+        }
+
+        if (sbi->s_blocksize < sbi->s_sys_blocksize ||
+            sbi->s_blocksize > OMFS_MAX_BLOCK_SIZE) {
+                printk(KERN_ERR "omfs: block size (%d) is out of range\n",
+                        sbi->s_blocksize);
+                goto out_brelse_bh;
+        }
+
+        /*
+         * Use sys_blocksize as the fs block since it is smaller than a
+         * page while the fs blocksize can be larger.
+         */
+        sb_set_blocksize(sb, sbi->s_sys_blocksize);
+
+        /*
+         * ...and the difference goes into a shift.  sys_blocksize is always
+         * a power of two factor of blocksize.
+         */
+        sbi->s_block_shift = get_bitmask_order(sbi->s_blocksize) -
+                get_bitmask_order(sbi->s_sys_blocksize);
+
+        start = clus_to_blk(sbi, be64_to_cpu(omfs_sb->s_root_block));
+        bh2 = sb_bread(sb, start);
+        if (!bh2)
+                goto out_brelse_bh;
+
+        omfs_rb = (struct omfs_root_block *)bh2->b_data;
+
+        sbi->s_bitmap_ino = be64_to_cpu(omfs_rb->r_bitmap);
+        sbi->s_clustersize = be32_to_cpu(omfs_rb->r_clustersize);
+
+        if (sbi->s_num_blocks != be64_to_cpu(omfs_rb->r_num_blocks)) {
+                printk(KERN_ERR "omfs: block count discrepancy between "
+                        "super and root blocks (%llx, %llx)\n",
+                        (unsigned long long)sbi->s_num_blocks,
+                        (unsigned long long)be64_to_cpu(omfs_rb->r_num_blocks));
+                goto out_brelse_bh2;
+        }
+
+        ret = omfs_get_imap(sb);
+        if (ret)
+                goto out_brelse_bh2;
+
+        sb->s_op = &omfs_sops;
+
+        root = omfs_iget(sb, be64_to_cpu(omfs_rb->r_root_dir));
+        if (IS_ERR(root)) {
+                ret = PTR_ERR(root);
+                goto out_brelse_bh2;
+        }
+
+        sb->s_root = d_alloc_root(root);
+        if (!sb->s_root) {
+                iput(root);
+                goto out_brelse_bh2;
+        }
+        printk(KERN_DEBUG "omfs: Mounted volume %s\n", omfs_rb->r_name);
+
+        ret = 0;
+out_brelse_bh2:
+        brelse(bh2);
+out_brelse_bh:
+        brelse(bh);
+end:
+        return ret;
+}
+
+static int omfs_get_sb(struct file_system_type *fs_type,
+                        int flags, const char *dev_name,
+                        void *data, struct vfsmount *m)
+{
+        return get_sb_bdev(fs_type, flags, dev_name, data, omfs_fill_super, m);
+}
+
+static struct file_system_type omfs_fs_type = {
+        .owner = THIS_MODULE,
+        .name = "omfs",
+        .get_sb = omfs_get_sb,
+        .kill_sb = kill_block_super,
+        .fs_flags = FS_REQUIRES_DEV,
+};
+
+static int __init init_omfs_fs(void)
+{
+        return register_filesystem(&omfs_fs_type);
+}
+
+static void __exit exit_omfs_fs(void)
+{
+        unregister_filesystem(&omfs_fs_type);
+}
+
+module_init(init_omfs_fs);
+module_exit(exit_omfs_fs);
diff --git a/fs/omfs/omfs.h b/fs/omfs/omfs.h
new file mode 100644
index 000000000000..2bc0f0670406
--- /dev/null
+++ b/fs/omfs/omfs.h
@@ -0,0 +1,67 @@
+#ifndef _OMFS_H
+#define _OMFS_H
+
+#include <linux/module.h>
+#include <linux/fs.h>
+
+#include "omfs_fs.h"
+
+/* In-memory structures */
+struct omfs_sb_info {
+        u64 s_num_blocks;
+        u64 s_bitmap_ino;
+        u64 s_root_ino;
+        u32 s_blocksize;
+        u32 s_mirrors;
+        u32 s_sys_blocksize;
+        u32 s_clustersize;
+        int s_block_shift;
+        unsigned long **s_imap;
+        int s_imap_size;
+        struct mutex s_bitmap_lock;
+        int s_uid;
+        int s_gid;
+        int s_dmask;
+        int s_fmask;
+};
+
+/* convert a cluster number to a scaled block number */
+static inline sector_t clus_to_blk(struct omfs_sb_info *sbi, sector_t block)
+{
+        return block << sbi->s_block_shift;
+}
+
+static inline struct omfs_sb_info *OMFS_SB(struct super_block *sb)
+{
+        return sb->s_fs_info;
+}
+
+/* bitmap.c */
+extern unsigned long omfs_count_free(struct super_block *sb);
+extern int omfs_allocate_block(struct super_block *sb, u64 block);
+extern int omfs_allocate_range(struct super_block *sb, int min_request,
+                        int max_request, u64 *return_block, int *return_size);
+extern int omfs_clear_range(struct super_block *sb, u64 block, int count);
+
+/* dir.c */
+extern struct file_operations omfs_dir_operations;
+extern struct inode_operations omfs_dir_inops;
+extern int omfs_make_empty(struct inode *inode, struct super_block *sb);
+extern int omfs_is_bad(struct omfs_sb_info *sbi, struct omfs_header *header,
+                        u64 fsblock);
+
+/* file.c */
+extern struct file_operations omfs_file_operations;
+extern struct inode_operations omfs_file_inops;
+extern struct address_space_operations omfs_aops;
+extern void omfs_make_empty_table(struct buffer_head *bh, int offset);
+extern int omfs_shrink_inode(struct inode *inode);
+
+/* inode.c */
+extern struct inode *omfs_iget(struct super_block *sb, ino_t inode);
+extern struct inode *omfs_new_inode(struct inode *dir, int mode);
+extern int omfs_reserve_block(struct super_block *sb, sector_t block);
+extern int omfs_find_empty_block(struct super_block *sb, int mode, ino_t *ino);
+extern int omfs_sync_inode(struct inode *inode);
+
+#endif
diff --git a/fs/omfs/omfs_fs.h b/fs/omfs/omfs_fs.h
new file mode 100644
index 000000000000..12cca245d6e8
--- /dev/null
+++ b/fs/omfs/omfs_fs.h
@@ -0,0 +1,80 @@
+#ifndef _OMFS_FS_H
+#define _OMFS_FS_H
+
+/* OMFS On-disk structures */
+
+#define OMFS_MAGIC 0xC2993D87
+#define OMFS_IMAGIC 0xD2
+
+#define OMFS_DIR 'D'
+#define OMFS_FILE 'F'
+#define OMFS_INODE_NORMAL 'e'
+#define OMFS_INODE_CONTINUATION 'c'
+#define OMFS_INODE_SYSTEM 's'
+#define OMFS_NAMELEN 256
+#define OMFS_DIR_START 0x1b8
+#define OMFS_EXTENT_START 0x1d0
+#define OMFS_EXTENT_CONT 0x40
+#define OMFS_XOR_COUNT 19
+#define OMFS_MAX_BLOCK_SIZE 8192
+
+struct omfs_super_block {
+        char s_fill1[256];
+        __be64 s_root_block;            /* block number of omfs_root_block */
+        __be64 s_num_blocks;            /* total number of FS blocks */
+        __be32 s_magic;                 /* OMFS_MAGIC */
+        __be32 s_blocksize;             /* size of a block */
+        __be32 s_mirrors;               /* # of mirrors of system blocks */
+        __be32 s_sys_blocksize;         /* size of non-data blocks */
+};
+
+struct omfs_header {
+        __be64 h_self;                  /* FS block where this is located */
+        __be32 h_body_size;             /* size of useful data after header */
+        __be16 h_crc;                   /* crc-ccitt of body_size bytes */
+        char h_fill1[2];
+        u8 h_version;                   /* version, always 1 */
+        char h_type;                    /* OMFS_INODE_X */
+        u8 h_magic;                     /* OMFS_IMAGIC */
+        u8 h_check_xor;                 /* XOR of header bytes before this */
+        __be32 h_fill2;
+};
+
+struct omfs_root_block {
+        struct omfs_header r_head;      /* header */
+        __be64 r_fill1;
+        __be64 r_num_blocks;            /* total number of FS blocks */
+        __be64 r_root_dir;              /* block # of root directory */
+        __be64 r_bitmap;                /* block # of free space bitmap */
+        __be32 r_blocksize;             /* size of a block */
+        __be32 r_clustersize;           /* size allocated for data blocks */
+        __be64 r_mirrors;               /* # of mirrors of system blocks */
+        char r_name[OMFS_NAMELEN];      /* partition label */
+};
+
+struct omfs_inode {
+        struct omfs_header i_head;      /* header */
+        __be64 i_parent;                /* parent containing this inode */
+        __be64 i_sibling;               /* next inode in hash bucket */
+        __be64 i_ctime;                 /* ctime, in milliseconds */
+        char i_fill1[35];
+        char i_type;                    /* OMFS_[DIR,FILE] */
+        __be32 i_fill2;
+        char i_fill3[64];
+        char i_name[OMFS_NAMELEN];      /* filename */
+        __be64 i_size;                  /* size of file, in bytes */
+};
+
+struct omfs_extent_entry {
+        __be64 e_cluster;               /* start location of a set of blocks */
+        __be64 e_blocks;                /* number of blocks after e_cluster */
+};
+
+struct omfs_extent {
+        __be64 e_next;                  /* next extent table location */
+        __be32 e_extent_count;          /* total # extents in this table */
+        __be32 e_fill;
+        struct omfs_extent_entry e_entry;       /* start of extent entries */
+};
+
+#endif
diff --git a/fs/open.c b/fs/open.c
index a99ad09c3197..07da9359481c 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -64,7 +64,8 @@ static int vfs_statfs_native(struct dentry *dentry, struct statfs *buf)
                 memcpy(buf, &st, sizeof(st));
         else {
                 if (sizeof buf->f_blocks == 4) {
-                        if ((st.f_blocks | st.f_bfree | st.f_bavail) &
+                        if ((st.f_blocks | st.f_bfree | st.f_bavail |
+                             st.f_bsize | st.f_frsize) &
                             0xffffffff00000000ULL)
                                 return -EOVERFLOW;
                         /*
@@ -121,37 +122,37 @@ static int vfs_statfs64(struct dentry *dentry, struct statfs64 *buf)
         return 0;
 }
 
-asmlinkage long sys_statfs(const char __user * path, struct statfs __user * buf)
+asmlinkage long sys_statfs(const char __user *pathname, struct statfs __user * buf)
 {
-        struct nameidata nd;
+        struct path path;
         int error;
 
-        error = user_path_walk(path, &nd);
+        error = user_path(pathname, &path);
         if (!error) {
                 struct statfs tmp;
-                error = vfs_statfs_native(nd.path.dentry, &tmp);
+                error = vfs_statfs_native(path.dentry, &tmp);
                 if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
                         error = -EFAULT;
-                path_put(&nd.path);
+                path_put(&path);
         }
         return error;
 }
 
 
-asmlinkage long sys_statfs64(const char __user *path, size_t sz, struct statfs64 __user *buf)
+asmlinkage long sys_statfs64(const char __user *pathname, size_t sz, struct statfs64 __user *buf)
 {
-        struct nameidata nd;
+        struct path path;
         long error;
 
         if (sz != sizeof(*buf))
                 return -EINVAL;
-        error = user_path_walk(path, &nd);
+        error = user_path(pathname, &path);
         if (!error) {
                 struct statfs64 tmp;
-                error = vfs_statfs64(nd.path.dentry, &tmp);
+                error = vfs_statfs64(path.dentry, &tmp);
                 if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
                         error = -EFAULT;
-                path_put(&nd.path);
+                path_put(&path);
         }
         return error;
 }
@@ -222,20 +223,20 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
         return err;
 }
 
-static long do_sys_truncate(const char __user * path, loff_t length)
+static long do_sys_truncate(const char __user *pathname, loff_t length)
 {
-        struct nameidata nd;
-        struct inode * inode;
+        struct path path;
+        struct inode *inode;
         int error;
 
         error = -EINVAL;
         if (length < 0) /* sorry, but loff_t says... */
                 goto out;
 
-        error = user_path_walk(path, &nd);
+        error = user_path(pathname, &path);
         if (error)
                 goto out;
-        inode = nd.path.dentry->d_inode;
+        inode = path.dentry->d_inode;
 
         /* For directories it's -EISDIR, for other non-regulars - -EINVAL */
         error = -EISDIR;
@@ -246,16 +247,16 @@ static long do_sys_truncate(const char __user * path, loff_t length)
         if (!S_ISREG(inode->i_mode))
                 goto dput_and_out;
 
-        error = mnt_want_write(nd.path.mnt);
+        error = mnt_want_write(path.mnt);
         if (error)
                 goto dput_and_out;
 
-        error = vfs_permission(&nd, MAY_WRITE);
+        error = inode_permission(inode, MAY_WRITE);
         if (error)
                 goto mnt_drop_write_and_out;
 
         error = -EPERM;
-        if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
+        if (IS_APPEND(inode))
                 goto mnt_drop_write_and_out;
 
         error = get_write_access(inode);
@@ -273,15 +274,15 @@ static long do_sys_truncate(const char __user * path, loff_t length)
         error = locks_verify_truncate(inode, NULL, length);
         if (!error) {
                 DQUOT_INIT(inode);
-                error = do_truncate(nd.path.dentry, length, 0, NULL);
+                error = do_truncate(path.dentry, length, 0, NULL);
         }
 
 put_write_and_out:
         put_write_access(inode);
 mnt_drop_write_and_out:
-        mnt_drop_write(nd.path.mnt);
+        mnt_drop_write(path.mnt);
 dput_and_out:
-        path_put(&nd.path);
+        path_put(&path);
 out:
         return error;
 }
@@ -424,7 +425,8 @@ out:
  */
 asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode)
 {
-        struct nameidata nd;
+        struct path path;
+        struct inode *inode;
         int old_fsuid, old_fsgid;
         kernel_cap_t uninitialized_var(old_cap);  /* !SECURE_NO_SETUID_FIXUP */
         int res;
@@ -447,7 +449,7 @@ asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode)
                  * FIXME: There is a race here against sys_capset.  The
                  * capabilities can change yet we will restore the old
                  * value below.  We should hold task_capabilities_lock,
-                 * but we cannot because user_path_walk can sleep.
+                 * but we cannot because user_path_at can sleep.
                  */
 #endif /* ndef CONFIG_SECURITY_FILE_CAPABILITIES */
                 if (current->uid)
@@ -456,14 +458,25 @@ asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode)
                         old_cap = cap_set_effective(current->cap_permitted);
         }
 
-        res = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW|LOOKUP_ACCESS, &nd);
+        res = user_path_at(dfd, filename, LOOKUP_FOLLOW, &path);
         if (res)
                 goto out;
 
-        res = vfs_permission(&nd, mode);
+        inode = path.dentry->d_inode;
+
+        if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) {
+                /*
+                 * MAY_EXEC on regular files is denied if the fs is mounted
+                 * with the "noexec" flag.
+                 */
+                res = -EACCES;
+                if (path.mnt->mnt_flags & MNT_NOEXEC)
+                        goto out_path_release;
+        }
+
+        res = inode_permission(inode, mode | MAY_ACCESS);
         /* SuS v2 requires we report a read only fs too */
-        if(res || !(mode & S_IWOTH) ||
-           special_file(nd.path.dentry->d_inode->i_mode))
+        if (res || !(mode & S_IWOTH) || special_file(inode->i_mode))
                 goto out_path_release;
         /*
          * This is a rare case where using __mnt_is_readonly()
@@ -475,11 +488,11 @@ asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode)
          * inherently racy and know that the fs may change
          * state before we even see this result.
          */
-        if (__mnt_is_readonly(nd.path.mnt))
+        if (__mnt_is_readonly(path.mnt))
                 res = -EROFS;
 
 out_path_release:
-        path_put(&nd.path);
+        path_put(&path);
 out:
         current->fsuid = old_fsuid;
         current->fsgid = old_fsgid;
@@ -497,22 +510,21 @@ asmlinkage long sys_access(const char __user *filename, int mode)
 
 asmlinkage long sys_chdir(const char __user * filename)
 {
-        struct nameidata nd;
+        struct path path;
         int error;
 
-        error = __user_walk(filename,
-                            LOOKUP_FOLLOW|LOOKUP_DIRECTORY|LOOKUP_CHDIR, &nd);
+        error = user_path_dir(filename, &path);
         if (error)
                 goto out;
 
-        error = vfs_permission(&nd, MAY_EXEC);
+        error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_ACCESS);
         if (error)
                 goto dput_and_out;
 
-        set_fs_pwd(current->fs, &nd.path);
+        set_fs_pwd(current->fs, &path);
 
 dput_and_out:
-        path_put(&nd.path);
+        path_put(&path);
 out:
         return error;
 }
@@ -534,7 +546,7 @@ asmlinkage long sys_fchdir(unsigned int fd)
         if (!S_ISDIR(inode->i_mode))
                 goto out_putf;
 
-        error = file_permission(file, MAY_EXEC);
+        error = inode_permission(inode, MAY_EXEC | MAY_ACCESS);
         if (!error)
                 set_fs_pwd(current->fs, &file->f_path);
 out_putf:
@@ -545,14 +557,14 @@ out:
 
 asmlinkage long sys_chroot(const char __user * filename)
 {
-        struct nameidata nd;
+        struct path path;
         int error;
 
-        error = __user_walk(filename, LOOKUP_FOLLOW | LOOKUP_DIRECTORY | LOOKUP_NOALT, &nd);
+        error = user_path_dir(filename, &path);
         if (error)
                 goto out;
 
-        error = vfs_permission(&nd, MAY_EXEC);
+        error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_ACCESS);
         if (error)
                 goto dput_and_out;
 
@@ -560,11 +572,10 @@ asmlinkage long sys_chroot(const char __user * filename)
         if (!capable(CAP_SYS_CHROOT))
                 goto dput_and_out;
 
-        set_fs_root(current->fs, &nd.path);
-        set_fs_altroot();
+        set_fs_root(current->fs, &path);
         error = 0;
 dput_and_out:
-        path_put(&nd.path);
+        path_put(&path);
 out:
         return error;
 }
@@ -589,9 +600,6 @@ asmlinkage long sys_fchmod(unsigned int fd, mode_t mode)
         err = mnt_want_write(file->f_path.mnt);
         if (err)
                 goto out_putf;
-        err = -EPERM;
-        if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
-                goto out_drop_write;
         mutex_lock(&inode->i_mutex);
         if (mode == (mode_t) -1)
                 mode = inode->i_mode;
@@ -599,8 +607,6 @@ asmlinkage long sys_fchmod(unsigned int fd, mode_t mode)
         newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
         err = notify_change(dentry, &newattrs);
         mutex_unlock(&inode->i_mutex);
-
-out_drop_write:
         mnt_drop_write(file->f_path.mnt);
 out_putf:
         fput(file);
@@ -611,36 +617,29 @@ out:
 asmlinkage long sys_fchmodat(int dfd, const char __user *filename,
                              mode_t mode)
 {
-        struct nameidata nd;
-        struct inode * inode;
+        struct path path;
+        struct inode *inode;
         int error;
         struct iattr newattrs;
 
-        error = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW, &nd);
+        error = user_path_at(dfd, filename, LOOKUP_FOLLOW, &path);
         if (error)
                 goto out;
-        inode = nd.path.dentry->d_inode;
+        inode = path.dentry->d_inode;
 
-        error = mnt_want_write(nd.path.mnt);
+        error = mnt_want_write(path.mnt);
         if (error)
                 goto dput_and_out;
-
-        error = -EPERM;
-        if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
-                goto out_drop_write;
-
         mutex_lock(&inode->i_mutex);
         if (mode == (mode_t) -1)
                 mode = inode->i_mode;
         newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
         newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
-        error = notify_change(nd.path.dentry, &newattrs);
+        error = notify_change(path.dentry, &newattrs);
         mutex_unlock(&inode->i_mutex);
-
-out_drop_write:
-        mnt_drop_write(nd.path.mnt);
+        mnt_drop_write(path.mnt);
 dput_and_out:
-        path_put(&nd.path);
+        path_put(&path);
 out:
         return error;
 }
@@ -652,18 +651,10 @@ asmlinkage long sys_chmod(const char __user *filename, mode_t mode)
 
 static int chown_common(struct dentry * dentry, uid_t user, gid_t group)
 {
-        struct inode * inode;
+        struct inode *inode = dentry->d_inode;
         int error;
         struct iattr newattrs;
 
-        error = -ENOENT;
-        if (!(inode = dentry->d_inode)) {
-                printk(KERN_ERR "chown_common: NULL inode\n");
-                goto out;
-        }
-        error = -EPERM;
-        if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
-                goto out;
         newattrs.ia_valid =  ATTR_CTIME;
         if (user != (uid_t) -1) {
                 newattrs.ia_valid |= ATTR_UID;
@@ -679,25 +670,25 @@ static int chown_common(struct dentry * dentry, uid_t user, gid_t group)
         mutex_lock(&inode->i_mutex);
         error = notify_change(dentry, &newattrs);
         mutex_unlock(&inode->i_mutex);
-out:
+
         return error;
 }
 
 asmlinkage long sys_chown(const char __user * filename, uid_t user, gid_t group)
 {
-        struct nameidata nd;
+        struct path path;
         int error;
 
-        error = user_path_walk(filename, &nd);
+        error = user_path(filename, &path);
         if (error)
                 goto out;
-        error = mnt_want_write(nd.path.mnt);
+        error = mnt_want_write(path.mnt);
         if (error)
                 goto out_release;
-        error = chown_common(nd.path.dentry, user, group);
-        mnt_drop_write(nd.path.mnt);
+        error = chown_common(path.dentry, user, group);
+        mnt_drop_write(path.mnt);
 out_release:
-        path_put(&nd.path);
+        path_put(&path);
 out:
         return error;
 }
@@ -705,7 +696,7 @@ out:
 asmlinkage long sys_fchownat(int dfd, const char __user *filename, uid_t user,
                              gid_t group, int flag)
 {
-        struct nameidata nd;
+        struct path path;
         int error = -EINVAL;
         int follow;
 
@@ -713,35 +704,35 @@ asmlinkage long sys_fchownat(int dfd, const char __user *filename, uid_t user,
                 goto out;
 
         follow = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
-        error = __user_walk_fd(dfd, filename, follow, &nd);
+        error = user_path_at(dfd, filename, follow, &path);
         if (error)
                 goto out;
-        error = mnt_want_write(nd.path.mnt);
+        error = mnt_want_write(path.mnt);
         if (error)
                 goto out_release;
-        error = chown_common(nd.path.dentry, user, group);
-        mnt_drop_write(nd.path.mnt);
+        error = chown_common(path.dentry, user, group);
+        mnt_drop_write(path.mnt);
 out_release:
-        path_put(&nd.path);
+        path_put(&path);
 out:
         return error;
 }
 
 asmlinkage long sys_lchown(const char __user * filename, uid_t user, gid_t group)
 {
-        struct nameidata nd;
+        struct path path;
         int error;
 
-        error = user_path_walk_link(filename, &nd);
+        error = user_lpath(filename, &path);
         if (error)
                 goto out;
-        error = mnt_want_write(nd.path.mnt);
+        error = mnt_want_write(path.mnt);
         if (error)
                 goto out_release;
-        error = chown_common(nd.path.dentry, user, group);
-        mnt_drop_write(nd.path.mnt);
+        error = chown_common(path.dentry, user, group);
+        mnt_drop_write(path.mnt);
 out_release:
-        path_put(&nd.path);
+        path_put(&path);
 out:
         return error;
 }
@@ -972,71 +963,6 @@ struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags)
 }
 EXPORT_SYMBOL(dentry_open);
 
-/*
- * Find an empty file descriptor entry, and mark it busy.
- */
-int get_unused_fd_flags(int flags)
-{
-        struct files_struct * files = current->files;
-        int fd, error;
-        struct fdtable *fdt;
-
-        error = -EMFILE;
-        spin_lock(&files->file_lock);
-
-repeat:
-        fdt = files_fdtable(files);
-        fd = find_next_zero_bit(fdt->open_fds->fds_bits, fdt->max_fds,
-                                files->next_fd);
-
-        /*
-         * N.B. For clone tasks sharing a files structure, this test
-         * will limit the total number of files that can be opened.
-         */
-        if (fd >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur)
-                goto out;
-
-        /* Do we need to expand the fd array or fd set?  */
-        error = expand_files(files, fd);
-        if (error < 0)
-                goto out;
-
-        if (error) {
-                /*
-                 * If we needed to expand the fs array we
-                 * might have blocked - try again.
-                 */
-                error = -EMFILE;
-                goto repeat;
-        }
-
-        FD_SET(fd, fdt->open_fds);
-        if (flags & O_CLOEXEC)
-                FD_SET(fd, fdt->close_on_exec);
-        else
-                FD_CLR(fd, fdt->close_on_exec);
-        files->next_fd = fd + 1;
-#if 1
-        /* Sanity check */
-        if (fdt->fd[fd] != NULL) {
-                printk(KERN_WARNING "get_unused_fd: slot %d not NULL!\n", fd);
-                fdt->fd[fd] = NULL;
-        }
-#endif
-        error = fd;
-
-out:
-        spin_unlock(&files->file_lock);
-        return error;
-}
-
-int get_unused_fd(void)
-{
-        return get_unused_fd_flags(0);
-}
-
-EXPORT_SYMBOL(get_unused_fd);
-
 static void __put_unused_fd(struct files_struct *files, unsigned int fd)
 {
         struct fdtable *fdt = files_fdtable(files);
diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c
index d17b4fd204e1..9f5b054f06b9 100644
--- a/fs/openpromfs/inode.c
+++ b/fs/openpromfs/inode.c
@@ -430,7 +430,7 @@ static struct file_system_type openprom_fs_type = {
         .kill_sb        = kill_anon_super,
 };
 
-static void op_inode_init_once(struct kmem_cache * cachep, void *data)
+static void op_inode_init_once(void *data)
 {
         struct op_inode_info *oi = (struct op_inode_info *) data;
 
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index 6149e4b58c88..7d6b34e201db 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -344,18 +344,18 @@ static ssize_t whole_disk_show(struct device *dev,
 static DEVICE_ATTR(whole_disk, S_IRUSR | S_IRGRP | S_IROTH,
                    whole_disk_show, NULL);
 
-void add_partition(struct gendisk *disk, int part, sector_t start, sector_t len, int flags)
+int add_partition(struct gendisk *disk, int part, sector_t start, sector_t len, int flags)
 {
         struct hd_struct *p;
         int err;
 
         p = kzalloc(sizeof(*p), GFP_KERNEL);
         if (!p)
-                return;
+                return -ENOMEM;
 
         if (!init_part_stats(p)) {
-                kfree(p);
-                return;
+                err = -ENOMEM;
+                goto out0;
         }
         p->start_sect = start;
         p->nr_sects = len;
@@ -378,15 +378,31 @@ void add_partition(struct gendisk *disk, int part, sector_t start, sector_t len,
 
         /* delay uevent until 'holders' subdir is created */
         p->dev.uevent_suppress = 1;
-        device_add(&p->dev);
+        err = device_add(&p->dev);
+        if (err)
+                goto out1;
         partition_sysfs_add_subdir(p);
         p->dev.uevent_suppress = 0;
-        if (flags & ADDPART_FLAG_WHOLEDISK)
+        if (flags & ADDPART_FLAG_WHOLEDISK) {
                 err = device_create_file(&p->dev, &dev_attr_whole_disk);
+                if (err)
+                        goto out2;
+        }
 
         /* suppress uevent if the disk supresses it */
         if (!disk->dev.uevent_suppress)
                 kobject_uevent(&p->dev.kobj, KOBJ_ADD);
+
+        return 0;
+
+out2:
+        device_del(&p->dev);
+out1:
+        put_device(&p->dev);
+        free_part_stats(p);
+out0:
+        kfree(p);
+        return err;
 }
 
 /* Not exported, helper to add_disk(). */
@@ -401,7 +417,7 @@ void register_disk(struct gendisk *disk)
         disk->dev.parent = disk->driverfs_dev;
         disk->dev.devt = MKDEV(disk->major, disk->first_minor);
 
-        strlcpy(disk->dev.bus_id, disk->disk_name, KOBJ_NAME_LEN);
+        strlcpy(disk->dev.bus_id, disk->disk_name, BUS_ID_SIZE);
         /* ewww... some of these buggers have / in the name... */
         s = strchr(disk->dev.bus_id, '/');
         if (s)
@@ -483,10 +499,16 @@ int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
                 if (!size)
                         continue;
                 if (from + size > get_capacity(disk)) {
-                        printk(" %s: p%d exceeds device capacity\n",
+                        printk(KERN_ERR " %s: p%d exceeds device capacity\n",
                                 disk->disk_name, p);
+                        continue;
+                }
+                res = add_partition(disk, p, from, size, state->parts[p].flags);
+                if (res) {
+                        printk(KERN_ERR " %s: p%d could not be added: %d\n",
+                                disk->disk_name, p, -res);
+                        continue;
                 }
-                add_partition(disk, p, from, size, state->parts[p].flags);
 #ifdef CONFIG_BLK_DEV_MD
                 if (state->parts[p].flags & ADDPART_FLAG_RAID)
                         md_autodetect_dev(bdev->bd_dev+p);
diff --git a/fs/partitions/efi.c b/fs/partitions/efi.c
index e7b07006bc41..038a6022152f 100644
--- a/fs/partitions/efi.c
+++ b/fs/partitions/efi.c
@@ -95,13 +95,6 @@
 #include "check.h"
 #include "efi.h"
 
-#undef EFI_DEBUG
-#ifdef EFI_DEBUG
-#define Dprintk(x...) printk(KERN_DEBUG x)
-#else
-#define Dprintk(x...)
-#endif
-
 /* This allows a kernel command line option 'gpt' to override
  * the test for invalid PMBR.  Not __initdata because reloading
  * the partition tables happens after init too.
@@ -305,10 +298,10 @@ is_gpt_valid(struct block_device *bdev, u64 lba,
 
         /* Check the GUID Partition Table signature */
         if (le64_to_cpu((*gpt)->signature) != GPT_HEADER_SIGNATURE) {
-                Dprintk("GUID Partition Table Header signature is wrong:"
-                        "%lld != %lld\n",
-                        (unsigned long long)le64_to_cpu((*gpt)->signature),
-                        (unsigned long long)GPT_HEADER_SIGNATURE);
+                pr_debug("GUID Partition Table Header signature is wrong:"
+                         "%lld != %lld\n",
+                         (unsigned long long)le64_to_cpu((*gpt)->signature),
+                         (unsigned long long)GPT_HEADER_SIGNATURE);
                 goto fail;
         }
 
@@ -318,9 +311,8 @@ is_gpt_valid(struct block_device *bdev, u64 lba,
         crc = efi_crc32((const unsigned char *) (*gpt), le32_to_cpu((*gpt)->header_size));
 
         if (crc != origcrc) {
-                Dprintk
-                    ("GUID Partition Table Header CRC is wrong: %x != %x\n",
-                     crc, origcrc);
+                pr_debug("GUID Partition Table Header CRC is wrong: %x != %x\n",
+                         crc, origcrc);
                 goto fail;
         }
         (*gpt)->header_crc32 = cpu_to_le32(origcrc);
@@ -328,9 +320,9 @@ is_gpt_valid(struct block_device *bdev, u64 lba,
         /* Check that the my_lba entry points to the LBA that contains
          * the GUID Partition Table */
         if (le64_to_cpu((*gpt)->my_lba) != lba) {
-                Dprintk("GPT my_lba incorrect: %lld != %lld\n",
-                        (unsigned long long)le64_to_cpu((*gpt)->my_lba),
-                        (unsigned long long)lba);
+                pr_debug("GPT my_lba incorrect: %lld != %lld\n",
+                         (unsigned long long)le64_to_cpu((*gpt)->my_lba),
+                         (unsigned long long)lba);
                 goto fail;
         }
 
@@ -339,15 +331,15 @@ is_gpt_valid(struct block_device *bdev, u64 lba,
          */
         lastlba = last_lba(bdev);
         if (le64_to_cpu((*gpt)->first_usable_lba) > lastlba) {
-                Dprintk("GPT: first_usable_lba incorrect: %lld > %lld\n",
-                        (unsigned long long)le64_to_cpu((*gpt)->first_usable_lba),
-                        (unsigned long long)lastlba);
+                pr_debug("GPT: first_usable_lba incorrect: %lld > %lld\n",
+                         (unsigned long long)le64_to_cpu((*gpt)->first_usable_lba),
+                         (unsigned long long)lastlba);
                 goto fail;
         }
         if (le64_to_cpu((*gpt)->last_usable_lba) > lastlba) {
-                Dprintk("GPT: last_usable_lba incorrect: %lld > %lld\n",
-                        (unsigned long long)le64_to_cpu((*gpt)->last_usable_lba),
-                        (unsigned long long)lastlba);
+                pr_debug("GPT: last_usable_lba incorrect: %lld > %lld\n",
+                         (unsigned long long)le64_to_cpu((*gpt)->last_usable_lba),
+                         (unsigned long long)lastlba);
                 goto fail;
         }
 
@@ -360,7 +352,7 @@ is_gpt_valid(struct block_device *bdev, u64 lba,
                         le32_to_cpu((*gpt)->sizeof_partition_entry));
 
         if (crc != le32_to_cpu((*gpt)->partition_entry_array_crc32)) {
-                Dprintk("GUID Partitition Entry Array CRC check failed.\n");
+                pr_debug("GUID Partitition Entry Array CRC check failed.\n");
                 goto fail_ptes;
         }
 
@@ -616,7 +608,7 @@ efi_partition(struct parsed_partitions *state, struct block_device *bdev)
                 return 0;
         }
 
-        Dprintk("GUID Partition Table is valid!  Yea!\n");
+        pr_debug("GUID Partition Table is valid!  Yea!\n");
 
         for (i = 0; i < le32_to_cpu(gpt->num_partition_entries) && i < state->limit-1; i++) {
                 if (!is_pte_valid(&ptes[i], last_lba(bdev)))
diff --git a/fs/partitions/ldm.c b/fs/partitions/ldm.c
index 0fdda2e8a4cc..8652fb99e962 100644
--- a/fs/partitions/ldm.c
+++ b/fs/partitions/ldm.c
@@ -133,17 +133,17 @@ static bool ldm_parse_privhead(const u8 *data, struct privhead *ph)
         bool is_vista = false;
 
         BUG_ON(!data || !ph);
-        if (MAGIC_PRIVHEAD != BE64(data)) {
+        if (MAGIC_PRIVHEAD != get_unaligned_be64(data)) {
                 ldm_error("Cannot find PRIVHEAD structure. LDM database is"
                         " corrupt. Aborting.");
                 return false;
         }
-        ph->ver_major = BE16(data + 0x000C);
-        ph->ver_minor = BE16(data + 0x000E);
-        ph->logical_disk_start = BE64(data + 0x011B);
-        ph->logical_disk_size = BE64(data + 0x0123);
-        ph->config_start = BE64(data + 0x012B);
-        ph->config_size = BE64(data + 0x0133);
+        ph->ver_major = get_unaligned_be16(data + 0x000C);
+        ph->ver_minor = get_unaligned_be16(data + 0x000E);
+        ph->logical_disk_start = get_unaligned_be64(data + 0x011B);
+        ph->logical_disk_size = get_unaligned_be64(data + 0x0123);
+        ph->config_start = get_unaligned_be64(data + 0x012B);
+        ph->config_size = get_unaligned_be64(data + 0x0133);
         /* Version 2.11 is Win2k/XP and version 2.12 is Vista. */
         if (ph->ver_major == 2 && ph->ver_minor == 12)
                 is_vista = true;
@@ -191,14 +191,14 @@ static bool ldm_parse_tocblock (const u8 *data, struct tocblock *toc)
 {
         BUG_ON (!data || !toc);
 
-        if (MAGIC_TOCBLOCK != BE64 (data)) {
+        if (MAGIC_TOCBLOCK != get_unaligned_be64(data)) {
                 ldm_crit ("Cannot find TOCBLOCK, database may be corrupt.");
                 return false;
         }
         strncpy (toc->bitmap1_name, data + 0x24, sizeof (toc->bitmap1_name));
         toc->bitmap1_name[sizeof (toc->bitmap1_name) - 1] = 0;
-        toc->bitmap1_start = BE64 (data + 0x2E);
-        toc->bitmap1_size  = BE64 (data + 0x36);
+        toc->bitmap1_start = get_unaligned_be64(data + 0x2E);
+        toc->bitmap1_size  = get_unaligned_be64(data + 0x36);
 
         if (strncmp (toc->bitmap1_name, TOC_BITMAP1,
                         sizeof (toc->bitmap1_name)) != 0) {
@@ -208,8 +208,8 @@ static bool ldm_parse_tocblock (const u8 *data, struct tocblock *toc)
         }
         strncpy (toc->bitmap2_name, data + 0x46, sizeof (toc->bitmap2_name));
         toc->bitmap2_name[sizeof (toc->bitmap2_name) - 1] = 0;
-        toc->bitmap2_start = BE64 (data + 0x50);
-        toc->bitmap2_size  = BE64 (data + 0x58);
+        toc->bitmap2_start = get_unaligned_be64(data + 0x50);
+        toc->bitmap2_size  = get_unaligned_be64(data + 0x58);
         if (strncmp (toc->bitmap2_name, TOC_BITMAP2,
                         sizeof (toc->bitmap2_name)) != 0) {
                 ldm_crit ("TOCBLOCK's second bitmap is '%s', should be '%s'.",
@@ -237,22 +237,22 @@ static bool ldm_parse_vmdb (const u8 *data, struct vmdb *vm)
 {
         BUG_ON (!data || !vm);
 
-        if (MAGIC_VMDB != BE32 (data)) {
+        if (MAGIC_VMDB != get_unaligned_be32(data)) {
                 ldm_crit ("Cannot find the VMDB, database may be corrupt.");
                 return false;
         }
 
-        vm->ver_major = BE16 (data + 0x12);
-        vm->ver_minor = BE16 (data + 0x14);
+        vm->ver_major = get_unaligned_be16(data + 0x12);
+        vm->ver_minor = get_unaligned_be16(data + 0x14);
         if ((vm->ver_major != 4) || (vm->ver_minor != 10)) {
                 ldm_error ("Expected VMDB version %d.%d, got %d.%d. "
                         "Aborting.", 4, 10, vm->ver_major, vm->ver_minor);
                 return false;
         }
 
-        vm->vblk_size     = BE32 (data + 0x08);
-        vm->vblk_offset   = BE32 (data + 0x0C);
-        vm->last_vblk_seq = BE32 (data + 0x04);
+        vm->vblk_size     = get_unaligned_be32(data + 0x08);
+        vm->vblk_offset   = get_unaligned_be32(data + 0x0C);
+        vm->last_vblk_seq = get_unaligned_be32(data + 0x04);
 
         ldm_debug ("Parsed VMDB successfully.");
         return true;
@@ -507,7 +507,7 @@ static bool ldm_validate_vmdb (struct block_device *bdev, unsigned long base,
                 goto out;                               /* Already logged */
 
         /* Are there uncommitted transactions? */
-        if (BE16(data + 0x10) != 0x01) {
+        if (get_unaligned_be16(data + 0x10) != 0x01) {
                 ldm_crit ("Database is not in a consistent state.  Aborting.");
                 goto out;
         }
@@ -802,7 +802,7 @@ static bool ldm_parse_cmp3 (const u8 *buffer, int buflen, struct vblk *vb)
                 return false;
 
         len += VBLK_SIZE_CMP3;
-        if (len != BE32 (buffer + 0x14))
+        if (len != get_unaligned_be32(buffer + 0x14))
                 return false;
 
         comp = &vb->vblk.comp;
@@ -851,7 +851,7 @@ static int ldm_parse_dgr3 (const u8 *buffer, int buflen, struct vblk *vb)
                 return false;
 
         len += VBLK_SIZE_DGR3;
-        if (len != BE32 (buffer + 0x14))
+        if (len != get_unaligned_be32(buffer + 0x14))
                 return false;
 
         dgrp = &vb->vblk.dgrp;
@@ -895,7 +895,7 @@ static bool ldm_parse_dgr4 (const u8 *buffer, int buflen, struct vblk *vb)
                 return false;
 
         len += VBLK_SIZE_DGR4;
-        if (len != BE32 (buffer + 0x14))
+        if (len != get_unaligned_be32(buffer + 0x14))
                 return false;
 
         dgrp = &vb->vblk.dgrp;
@@ -931,7 +931,7 @@ static bool ldm_parse_dsk3 (const u8 *buffer, int buflen, struct vblk *vb)
                 return false;
 
         len += VBLK_SIZE_DSK3;
-        if (len != BE32 (buffer + 0x14))
+        if (len != get_unaligned_be32(buffer + 0x14))
                 return false;
 
         disk = &vb->vblk.disk;
@@ -968,7 +968,7 @@ static bool ldm_parse_dsk4 (const u8 *buffer, int buflen, struct vblk *vb)
                 return false;
 
         len += VBLK_SIZE_DSK4;
-        if (len != BE32 (buffer + 0x14))
+        if (len != get_unaligned_be32(buffer + 0x14))
                 return false;
 
         disk = &vb->vblk.disk;
@@ -1034,14 +1034,14 @@ static bool ldm_parse_prt3(const u8 *buffer, int buflen, struct vblk *vb)
                 return false;
         }
         len += VBLK_SIZE_PRT3;
-        if (len > BE32(buffer + 0x14)) {
+        if (len > get_unaligned_be32(buffer + 0x14)) {
                 ldm_error("len %d > BE32(buffer + 0x14) %d", len,
-                                BE32(buffer + 0x14));
+                                get_unaligned_be32(buffer + 0x14));
                 return false;
         }
         part = &vb->vblk.part;
-        part->start = BE64(buffer + 0x24 + r_name);
-        part->volume_offset = BE64(buffer + 0x2C + r_name);
+        part->start = get_unaligned_be64(buffer + 0x24 + r_name);
+        part->volume_offset = get_unaligned_be64(buffer + 0x2C + r_name);
         part->size = ldm_get_vnum(buffer + 0x34 + r_name);
         part->parent_id = ldm_get_vnum(buffer + 0x34 + r_size);
         part->disk_id = ldm_get_vnum(buffer + 0x34 + r_parent);
@@ -1139,9 +1139,9 @@ static bool ldm_parse_vol5(const u8 *buffer, int buflen, struct vblk *vb)
                 return false;
         }
         len += VBLK_SIZE_VOL5;
-        if (len > BE32(buffer + 0x14)) {
+        if (len > get_unaligned_be32(buffer + 0x14)) {
                 ldm_error("len %d > BE32(buffer + 0x14) %d", len,
-                                BE32(buffer + 0x14));
+                                get_unaligned_be32(buffer + 0x14));
                 return false;
         }
         volu = &vb->vblk.volu;
@@ -1294,9 +1294,9 @@ static bool ldm_frag_add (const u8 *data, int size, struct list_head *frags)
 
         BUG_ON (!data || !frags);
 
-        group = BE32 (data + 0x08);
-        rec   = BE16 (data + 0x0C);
-        num   = BE16 (data + 0x0E);
+        group = get_unaligned_be32(data + 0x08);
+        rec   = get_unaligned_be16(data + 0x0C);
+        num   = get_unaligned_be16(data + 0x0E);
         if ((num < 1) || (num > 4)) {
                 ldm_error ("A VBLK claims to have %d parts.", num);
                 return false;
@@ -1425,12 +1425,12 @@ static bool ldm_get_vblks (struct block_device *bdev, unsigned long base,
                 }
 
                 for (v = 0; v < perbuf; v++, data+=size) {  /* For each vblk */
-                        if (MAGIC_VBLK != BE32 (data)) {
+                        if (MAGIC_VBLK != get_unaligned_be32(data)) {
                                 ldm_error ("Expected to find a VBLK.");
                                 goto out;
                         }
 
-                        recs = BE16 (data + 0x0E);      /* Number of records */
+                        recs = get_unaligned_be16(data + 0x0E); /* Number of records */
                         if (recs == 1) {
                                 if (!ldm_ldmdb_add (data, size, ldb))
                                         goto out;       /* Already logged */
diff --git a/fs/partitions/ldm.h b/fs/partitions/ldm.h
index 80f63b5fdd9f..30e08e809c1d 100644
--- a/fs/partitions/ldm.h
+++ b/fs/partitions/ldm.h
@@ -98,11 +98,6 @@ struct parsed_partitions;
 #define TOC_BITMAP1             "config"        /* Names of the two defined */
 #define TOC_BITMAP2             "log"           /* bitmaps in the TOCBLOCK. */
 
-/* Most numbers we deal with are big-endian and won't be aligned. */
-#define BE16(x)                 ((u16)be16_to_cpu(get_unaligned((__be16*)(x))))
-#define BE32(x)                 ((u32)be32_to_cpu(get_unaligned((__be32*)(x))))
-#define BE64(x)                 ((u64)be64_to_cpu(get_unaligned((__be64*)(x))))
-
 /* Borrowed from msdos.c */
 #define SYS_IND(p)              (get_unaligned(&(p)->sys_ind))
 
diff --git a/fs/pipe.c b/fs/pipe.c
index 700f4e0d9572..fcba6542b8d0 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -777,45 +777,10 @@ pipe_rdwr_open(struct inode *inode, struct file *filp)
 /*
  * The file_operations structs are not static because they
  * are also used in linux/fs/fifo.c to do operations on FIFOs.
+ *
+ * Pipes reuse fifos' file_operations structs.
  */
-const struct file_operations read_fifo_fops = {
-        .llseek         = no_llseek,
-        .read           = do_sync_read,
-        .aio_read       = pipe_read,
-        .write          = bad_pipe_w,
-        .poll           = pipe_poll,
-        .unlocked_ioctl = pipe_ioctl,
-        .open           = pipe_read_open,
-        .release        = pipe_read_release,
-        .fasync         = pipe_read_fasync,
-};
-
-const struct file_operations write_fifo_fops = {
-        .llseek         = no_llseek,
-        .read           = bad_pipe_r,
-        .write          = do_sync_write,
-        .aio_write      = pipe_write,
-        .poll           = pipe_poll,
-        .unlocked_ioctl = pipe_ioctl,
-        .open           = pipe_write_open,
-        .release        = pipe_write_release,
-        .fasync         = pipe_write_fasync,
-};
-
-const struct file_operations rdwr_fifo_fops = {
-        .llseek         = no_llseek,
-        .read           = do_sync_read,
-        .aio_read       = pipe_read,
-        .write          = do_sync_write,
-        .aio_write      = pipe_write,
-        .poll           = pipe_poll,
-        .unlocked_ioctl = pipe_ioctl,
-        .open           = pipe_rdwr_open,
-        .release        = pipe_rdwr_release,
-        .fasync         = pipe_rdwr_fasync,
-};
-
-static const struct file_operations read_pipe_fops = {
+const struct file_operations read_pipefifo_fops = {
         .llseek         = no_llseek,
         .read           = do_sync_read,
         .aio_read       = pipe_read,
@@ -827,7 +792,7 @@ static const struct file_operations read_pipe_fops = {
         .fasync         = pipe_read_fasync,
 };
 
-static const struct file_operations write_pipe_fops = {
+const struct file_operations write_pipefifo_fops = {
         .llseek         = no_llseek,
         .read           = bad_pipe_r,
         .write          = do_sync_write,
@@ -839,7 +804,7 @@ static const struct file_operations write_pipe_fops = {
         .fasync         = pipe_write_fasync,
 };
 
-static const struct file_operations rdwr_pipe_fops = {
+const struct file_operations rdwr_pipefifo_fops = {
         .llseek         = no_llseek,
         .read           = do_sync_read,
         .aio_read       = pipe_read,
@@ -927,7 +892,7 @@ static struct inode * get_pipe_inode(void)
         inode->i_pipe = pipe;
 
         pipe->readers = pipe->writers = 1;
-        inode->i_fop = &rdwr_pipe_fops;
+        inode->i_fop = &rdwr_pipefifo_fops;
 
         /*
          * Mark the inode dirty from the very beginning,
@@ -950,7 +915,7 @@ fail_inode:
         return NULL;
 }
 
-struct file *create_write_pipe(void)
+struct file *create_write_pipe(int flags)
 {
         int err;
         struct inode *inode;
@@ -978,12 +943,12 @@ struct file *create_write_pipe(void)
         d_instantiate(dentry, inode);
 
         err = -ENFILE;
-        f = alloc_file(pipe_mnt, dentry, FMODE_WRITE, &write_pipe_fops);
+        f = alloc_file(pipe_mnt, dentry, FMODE_WRITE, &write_pipefifo_fops);
         if (!f)
                 goto err_dentry;
         f->f_mapping = inode->i_mapping;
 
-        f->f_flags = O_WRONLY;
+        f->f_flags = O_WRONLY | (flags & O_NONBLOCK);
         f->f_version = 0;
 
         return f;
@@ -1007,7 +972,7 @@ void free_write_pipe(struct file *f)
         put_filp(f);
 }
 
-struct file *create_read_pipe(struct file *wrf)
+struct file *create_read_pipe(struct file *wrf, int flags)
 {
         struct file *f = get_empty_filp();
         if (!f)
@@ -1019,34 +984,37 @@ struct file *create_read_pipe(struct file *wrf)
         f->f_mapping = wrf->f_path.dentry->d_inode->i_mapping;
 
         f->f_pos = 0;
-        f->f_flags = O_RDONLY;
-        f->f_op = &read_pipe_fops;
+        f->f_flags = O_RDONLY | (flags & O_NONBLOCK);
+        f->f_op = &read_pipefifo_fops;
         f->f_mode = FMODE_READ;
         f->f_version = 0;
 
         return f;
 }
 
-int do_pipe(int *fd)
+int do_pipe_flags(int *fd, int flags)
 {
         struct file *fw, *fr;
         int error;
         int fdw, fdr;
 
-        fw = create_write_pipe();
+        if (flags & ~(O_CLOEXEC | O_NONBLOCK))
+                return -EINVAL;
+
+        fw = create_write_pipe(flags);
         if (IS_ERR(fw))
                 return PTR_ERR(fw);
-        fr = create_read_pipe(fw);
+        fr = create_read_pipe(fw, flags);
         error = PTR_ERR(fr);
         if (IS_ERR(fr))
                 goto err_write_pipe;
 
-        error = get_unused_fd();
+        error = get_unused_fd_flags(flags);
         if (error < 0)
                 goto err_read_pipe;
         fdr = error;
 
-        error = get_unused_fd();
+        error = get_unused_fd_flags(flags);
         if (error < 0)
                 goto err_fdr;
         fdw = error;
@@ -1074,16 +1042,21 @@ int do_pipe(int *fd)
         return error;
 }
 
+int do_pipe(int *fd)
+{
+        return do_pipe_flags(fd, 0);
+}
+
 /*
  * sys_pipe() is the normal C calling standard for creating
  * a pipe. It's not the way Unix traditionally does this, though.
  */
-asmlinkage long __weak sys_pipe(int __user *fildes)
+asmlinkage long __weak sys_pipe2(int __user *fildes, int flags)
 {
         int fd[2];
         int error;
 
-        error = do_pipe(fd);
+        error = do_pipe_flags(fd, flags);
         if (!error) {
                 if (copy_to_user(fildes, fd, sizeof(fd))) {
                         sys_close(fd[0]);
@@ -1094,6 +1067,11 @@ asmlinkage long __weak sys_pipe(int __user *fildes)
         return error;
 }
 
+asmlinkage long __weak sys_pipe(int __user *fildes)
+{
+        return sys_pipe2(fildes, 0);
+}
+
 /*
  * pipefs should _never_ be mounted by userland - too much of security hassle,
  * no real gain from having the whole whorehouse mounted. So we don't need
diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig
new file mode 100644
index 000000000000..73cd7a418f06
--- /dev/null
+++ b/fs/proc/Kconfig
@@ -0,0 +1,59 @@
+config PROC_FS
+        bool "/proc file system support" if EMBEDDED
+        default y
+        help
+          This is a virtual file system providing information about the status
+          of the system. "Virtual" means that it doesn't take up any space on
+          your hard disk: the files are created on the fly by the kernel when
+          you try to access them. Also, you cannot read the files with older
+          version of the program less: you need to use more or cat.
+
+          It's totally cool; for example, "cat /proc/interrupts" gives
+          information about what the different IRQs are used for at the moment
+          (there is a small number of Interrupt ReQuest lines in your computer
+          that are used by the attached devices to gain the CPU's attention --
+          often a source of trouble if two devices are mistakenly configured
+          to use the same IRQ). The program procinfo to display some
+          information about your system gathered from the /proc file system.
+
+          Before you can use the /proc file system, it has to be mounted,
+          meaning it has to be given a location in the directory hierarchy.
+          That location should be /proc. A command such as "mount -t proc proc
+          /proc" or the equivalent line in /etc/fstab does the job.
+
+          The /proc file system is explained in the file
+          <file:Documentation/filesystems/proc.txt> and on the proc(5) manpage
+          ("man 5 proc").
+
+          This option will enlarge your kernel by about 67 KB. Several
+          programs depend on this, so everyone should say Y here.
+
+config PROC_KCORE
+        bool "/proc/kcore support" if !ARM
+        depends on PROC_FS && MMU
+
+config PROC_VMCORE
+        bool "/proc/vmcore support (EXPERIMENTAL)"
+        depends on PROC_FS && CRASH_DUMP
+        default y
+        help
+        Exports the dump image of crashed kernel in ELF format.
+
+config PROC_SYSCTL
+        bool "Sysctl support (/proc/sys)" if EMBEDDED
+        depends on PROC_FS
+        select SYSCTL
+        default y
+        ---help---
+          The sysctl interface provides a means of dynamically changing
+          certain kernel parameters and variables on the fly without requiring
+          a recompile of the kernel or reboot of the system.  The primary
+          interface is through /proc/sys.  If you say Y here a tree of
+          modifiable sysctl entries will be generated beneath the
+          /proc/sys directory. They are explained in the files
+          in <file:Documentation/sysctl/>.  Note that enabling this
+          option will enlarge the kernel by at least 8 KB.
+
+          As it is generally a good thing, you should say Y here unless
+          building a kernel for install/rescue disks or your system is very
+          limited in memory.
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 797d775e0354..0d6eb33597c6 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -80,6 +80,7 @@
 #include <linux/delayacct.h>
 #include <linux/seq_file.h>
 #include <linux/pid_namespace.h>
+#include <linux/tracehook.h>
 
 #include <asm/pgtable.h>
 #include <asm/processor.h>
@@ -168,8 +169,12 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
         rcu_read_lock();
         ppid = pid_alive(p) ?
                 task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0;
-        tpid = pid_alive(p) && p->ptrace ?
-                task_pid_nr_ns(rcu_dereference(p->parent), ns) : 0;
+        tpid = 0;
+        if (pid_alive(p)) {
+                struct task_struct *tracer = tracehook_tracer_task(p);
+                if (tracer)
+                        tpid = task_pid_nr_ns(tracer, ns);
+        }
         seq_printf(m,
                 "State:\t%s\n"
                 "Tgid:\t%d\n"
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 58c3e6a8e15e..a28840b11b89 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -53,6 +53,7 @@
 #include <linux/time.h>
 #include <linux/proc_fs.h>
 #include <linux/stat.h>
+#include <linux/task_io_accounting_ops.h>
 #include <linux/init.h>
 #include <linux/capability.h>
 #include <linux/file.h>
@@ -69,6 +70,7 @@
 #include <linux/mount.h>
 #include <linux/security.h>
 #include <linux/ptrace.h>
+#include <linux/tracehook.h>
 #include <linux/cgroup.h>
 #include <linux/cpuset.h>
 #include <linux/audit.h>
@@ -231,10 +233,14 @@ static int check_mem_permission(struct task_struct *task)
          * If current is actively ptrace'ing, and would also be
          * permitted to freshly attach with ptrace now, permit it.
          */
-        if (task->parent == current && (task->ptrace & PT_PTRACED) &&
-            task_is_stopped_or_traced(task) &&
-            ptrace_may_access(task, PTRACE_MODE_ATTACH))
-                return 0;
+        if (task_is_stopped_or_traced(task)) {
+                int match;
+                rcu_read_lock();
+                match = (tracehook_tracer_task(task) == current);
+                rcu_read_unlock();
+                if (match && ptrace_may_access(task, PTRACE_MODE_ATTACH))
+                        return 0;
+        }
 
         /*
          * Noone else is allowed.
@@ -504,6 +510,26 @@ static int proc_pid_limits(struct task_struct *task, char *buffer)
         return count;
 }
 
+#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
+static int proc_pid_syscall(struct task_struct *task, char *buffer)
+{
+        long nr;
+        unsigned long args[6], sp, pc;
+
+        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,
+                       "%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);
+}
+#endif /* CONFIG_HAVE_ARCH_TRACEHOOK */
+
 /************************************************************************/
 /*                       Here the fs part begins                        */
 /************************************************************************/
@@ -1834,8 +1860,7 @@ static const struct file_operations proc_fd_operations = {
  * /proc/pid/fd needs a special permission handler so that a process can still
  * access /proc/self/fd after it has executed a setuid().
  */
-static int proc_fd_permission(struct inode *inode, int mask,
-                                struct nameidata *nd)
+static int proc_fd_permission(struct inode *inode, int mask)
 {
         int rv;
 
@@ -2376,29 +2401,47 @@ static int proc_base_fill_cache(struct file *filp, void *dirent,
 }
 
 #ifdef CONFIG_TASK_IO_ACCOUNTING
-static int proc_pid_io_accounting(struct task_struct *task, char *buffer)
+static int do_io_accounting(struct task_struct *task, char *buffer, int whole)
 {
+        struct task_io_accounting acct = task->ioac;
+        unsigned long flags;
+
+        if (whole && lock_task_sighand(task, &flags)) {
+                struct task_struct *t = task;
+
+                task_io_accounting_add(&acct, &task->signal->ioac);
+                while_each_thread(task, t)
+                        task_io_accounting_add(&acct, &t->ioac);
+
+                unlock_task_sighand(task, &flags);
+        }
         return sprintf(buffer,
-#ifdef CONFIG_TASK_XACCT
                         "rchar: %llu\n"
                         "wchar: %llu\n"
                         "syscr: %llu\n"
                         "syscw: %llu\n"
-#endif
                         "read_bytes: %llu\n"
                         "write_bytes: %llu\n"
                         "cancelled_write_bytes: %llu\n",
-#ifdef CONFIG_TASK_XACCT
-                        (unsigned long long)task->rchar,
-                        (unsigned long long)task->wchar,
-                        (unsigned long long)task->syscr,
-                        (unsigned long long)task->syscw,
-#endif
-                        (unsigned long long)task->ioac.read_bytes,
-                        (unsigned long long)task->ioac.write_bytes,
-                        (unsigned long long)task->ioac.cancelled_write_bytes);
+                        (unsigned long long)acct.rchar,
+                        (unsigned long long)acct.wchar,
+                        (unsigned long long)acct.syscr,
+                        (unsigned long long)acct.syscw,
+                        (unsigned long long)acct.read_bytes,
+                        (unsigned long long)acct.write_bytes,
+                        (unsigned long long)acct.cancelled_write_bytes);
+}
+
+static int proc_tid_io_accounting(struct task_struct *task, char *buffer)
+{
+        return do_io_accounting(task, buffer, 0);
 }
-#endif
+
+static int proc_tgid_io_accounting(struct task_struct *task, char *buffer)
+{
+        return do_io_accounting(task, buffer, 1);
+}
+#endif /* CONFIG_TASK_IO_ACCOUNTING */
 
 /*
  * Thread groups
@@ -2420,6 +2463,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_SCHED_DEBUG
         REG("sched",      S_IRUGO|S_IWUSR, pid_sched),
 #endif
+#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
+        INF("syscall",    S_IRUSR, pid_syscall),
+#endif
         INF("cmdline",    S_IRUGO, pid_cmdline),
         ONE("stat",       S_IRUGO, tgid_stat),
         ONE("statm",      S_IRUGO, pid_statm),
@@ -2470,7 +2516,7 @@ static const struct pid_entry tgid_base_stuff[] = {
         REG("coredump_filter", S_IRUGO|S_IWUSR, coredump_filter),
 #endif
 #ifdef CONFIG_TASK_IO_ACCOUNTING
-        INF("io",       S_IRUGO, pid_io_accounting),
+        INF("io",       S_IRUGO, tgid_io_accounting),
 #endif
 };
 
@@ -2752,6 +2798,9 @@ static const struct pid_entry tid_base_stuff[] = {
 #ifdef CONFIG_SCHED_DEBUG
         REG("sched",     S_IRUGO|S_IWUSR, pid_sched),
 #endif
+#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
+        INF("syscall",   S_IRUSR, pid_syscall),
+#endif
         INF("cmdline",   S_IRUGO, pid_cmdline),
         ONE("stat",      S_IRUGO, tid_stat),
         ONE("statm",     S_IRUGO, pid_statm),
@@ -2797,6 +2846,9 @@ static const struct pid_entry tid_base_stuff[] = {
 #ifdef CONFIG_FAULT_INJECTION
         REG("make-it-fail", S_IRUGO|S_IWUSR, fault_inject),
 #endif
+#ifdef CONFIG_TASK_IO_ACCOUNTING
+        INF("io",       S_IRUGO, tid_io_accounting),
+#endif
 };
 
 static int proc_tid_base_readdir(struct file * filp,
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 43e54e86cefd..4fb81e9c94e3 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -300,10 +300,10 @@ out:
         return rtn;
 }
 
-static DEFINE_IDR(proc_inum_idr);
+static DEFINE_IDA(proc_inum_ida);
 static DEFINE_SPINLOCK(proc_inum_lock); /* protects the above */
 
-#define PROC_DYNAMIC_FIRST 0xF0000000UL
+#define PROC_DYNAMIC_FIRST 0xF0000000U
 
 /*
  * Return an inode number between PROC_DYNAMIC_FIRST and
@@ -311,36 +311,33 @@ static DEFINE_SPINLOCK(proc_inum_lock); /* protects the above */
  */
 static unsigned int get_inode_number(void)
 {
-        int i, inum = 0;
+        unsigned int i;
         int error;
 
 retry:
-        if (idr_pre_get(&proc_inum_idr, GFP_KERNEL) == 0)
+        if (ida_pre_get(&proc_inum_ida, GFP_KERNEL) == 0)
                 return 0;
 
         spin_lock(&proc_inum_lock);
-        error = idr_get_new(&proc_inum_idr, NULL, &i);
+        error = ida_get_new(&proc_inum_ida, &i);
         spin_unlock(&proc_inum_lock);
         if (error == -EAGAIN)
                 goto retry;
         else if (error)
                 return 0;
 
-        inum = (i & MAX_ID_MASK) + PROC_DYNAMIC_FIRST;
-
-        /* inum will never be more than 0xf0ffffff, so no check
-         * for overflow.
-         */
-
-        return inum;
+        if (i > UINT_MAX - PROC_DYNAMIC_FIRST) {
+                spin_lock(&proc_inum_lock);
+                ida_remove(&proc_inum_ida, i);
+                spin_unlock(&proc_inum_lock);
+        }
+        return PROC_DYNAMIC_FIRST + i;
 }
 
 static void release_inode_number(unsigned int inum)
 {
-        int id = (inum - PROC_DYNAMIC_FIRST) | ~MAX_ID_MASK;
-
         spin_lock(&proc_inum_lock);
-        idr_remove(&proc_inum_idr, id);
+        ida_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
         spin_unlock(&proc_inum_lock);
 }
 
@@ -597,6 +594,7 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
         ent->pde_users = 0;
         spin_lock_init(&ent->pde_unload_lock);
         ent->pde_unload_completion = NULL;
+        INIT_LIST_HEAD(&ent->pde_openers);
  out:
         return ent;
 }
@@ -789,15 +787,25 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
         spin_unlock(&de->pde_unload_lock);
 
 continue_removing:
+        spin_lock(&de->pde_unload_lock);
+        while (!list_empty(&de->pde_openers)) {
+                struct pde_opener *pdeo;
+
+                pdeo = list_first_entry(&de->pde_openers, struct pde_opener, lh);
+                list_del(&pdeo->lh);
+                spin_unlock(&de->pde_unload_lock);
+                pdeo->release(pdeo->inode, pdeo->file);
+                kfree(pdeo);
+                spin_lock(&de->pde_unload_lock);
+        }
+        spin_unlock(&de->pde_unload_lock);
+
         if (S_ISDIR(de->mode))
                 parent->nlink--;
         de->nlink = 0;
-        if (de->subdir) {
-                printk(KERN_WARNING "%s: removing non-empty directory "
+        WARN(de->subdir, KERN_WARNING "%s: removing non-empty directory "
                         "'%s/%s', leaking at least '%s'\n", __func__,
                         de->parent->name, de->name, de->subdir->name);
-                WARN_ON(1);
-        }
         if (atomic_dec_and_test(&de->count))
                 free_proc_entry(de);
 }
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index b08d10017911..8bb03f056c28 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -17,6 +17,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/smp_lock.h>
+#include <linux/sysctl.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -65,6 +66,8 @@ static void proc_delete_inode(struct inode *inode)
                         module_put(de->owner);
                 de_put(de);
         }
+        if (PROC_I(inode)->sysctl)
+                sysctl_head_put(PROC_I(inode)->sysctl);
         clear_inode(inode);
 }
 
@@ -84,6 +87,8 @@ static struct inode *proc_alloc_inode(struct super_block *sb)
         ei->fd = 0;
         ei->op.proc_get_link = NULL;
         ei->pde = NULL;
+        ei->sysctl = NULL;
+        ei->sysctl_entry = NULL;
         inode = &ei->vfs_inode;
         inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
         return inode;
@@ -94,7 +99,7 @@ static void proc_destroy_inode(struct inode *inode)
         kmem_cache_free(proc_inode_cachep, PROC_I(inode));
 }
 
-static void init_once(struct kmem_cache * cachep, void *foo)
+static void init_once(void *foo)
 {
         struct proc_inode *ei = (struct proc_inode *) foo;
 
@@ -111,27 +116,25 @@ int __init proc_init_inodecache(void)
         return 0;
 }
 
-static int proc_remount(struct super_block *sb, int *flags, char *data)
-{
-        *flags |= MS_NODIRATIME;
-        return 0;
-}
-
 static const struct super_operations proc_sops = {
         .alloc_inode    = proc_alloc_inode,
         .destroy_inode  = proc_destroy_inode,
         .drop_inode     = generic_delete_inode,
         .delete_inode   = proc_delete_inode,
         .statfs         = simple_statfs,
-        .remount_fs     = proc_remount,
 };
 
-static void pde_users_dec(struct proc_dir_entry *pde)
+static void __pde_users_dec(struct proc_dir_entry *pde)
 {
-        spin_lock(&pde->pde_unload_lock);
         pde->pde_users--;
         if (pde->pde_unload_completion && pde->pde_users == 0)
                 complete(pde->pde_unload_completion);
+}
+
+static void pde_users_dec(struct proc_dir_entry *pde)
+{
+        spin_lock(&pde->pde_unload_lock);
+        __pde_users_dec(pde);
         spin_unlock(&pde->pde_unload_lock);
 }
 
@@ -318,36 +321,97 @@ static int proc_reg_open(struct inode *inode, struct file *file)
         struct proc_dir_entry *pde = PDE(inode);
         int rv = 0;
         int (*open)(struct inode *, struct file *);
+        int (*release)(struct inode *, struct file *);
+        struct pde_opener *pdeo;
+
+        /*
+         * What for, you ask? Well, we can have open, rmmod, remove_proc_entry
+         * sequence. ->release won't be called because ->proc_fops will be
+         * cleared. Depending on complexity of ->release, consequences vary.
+         *
+         * We can't wait for mercy when close will be done for real, it's
+         * deadlockable: rmmod foo </proc/foo . So, we're going to do ->release
+         * by hand in remove_proc_entry(). For this, save opener's credentials
+         * for later.
+         */
+        pdeo = kmalloc(sizeof(struct pde_opener), GFP_KERNEL);
+        if (!pdeo)
+                return -ENOMEM;
 
         spin_lock(&pde->pde_unload_lock);
         if (!pde->proc_fops) {
                 spin_unlock(&pde->pde_unload_lock);
+                kfree(pdeo);
                 return rv;
         }
         pde->pde_users++;
         open = pde->proc_fops->open;
+        release = pde->proc_fops->release;
         spin_unlock(&pde->pde_unload_lock);
 
         if (open)
                 rv = open(inode, file);
 
-        pde_users_dec(pde);
+        spin_lock(&pde->pde_unload_lock);
+        if (rv == 0 && release) {
+                /* To know what to release. */
+                pdeo->inode = inode;
+                pdeo->file = file;
+                /* Strictly for "too late" ->release in proc_reg_release(). */
+                pdeo->release = release;
+                list_add(&pdeo->lh, &pde->pde_openers);
+        } else
+                kfree(pdeo);
+        __pde_users_dec(pde);
+        spin_unlock(&pde->pde_unload_lock);
         return rv;
 }
 
+static struct pde_opener *find_pde_opener(struct proc_dir_entry *pde,
+                                        struct inode *inode, struct file *file)
+{
+        struct pde_opener *pdeo;
+
+        list_for_each_entry(pdeo, &pde->pde_openers, lh) {
+                if (pdeo->inode == inode && pdeo->file == file)
+                        return pdeo;
+        }
+        return NULL;
+}
+
 static int proc_reg_release(struct inode *inode, struct file *file)
 {
         struct proc_dir_entry *pde = PDE(inode);
         int rv = 0;
         int (*release)(struct inode *, struct file *);
+        struct pde_opener *pdeo;
 
         spin_lock(&pde->pde_unload_lock);
+        pdeo = find_pde_opener(pde, inode, file);
         if (!pde->proc_fops) {
-                spin_unlock(&pde->pde_unload_lock);
+                /*
+                 * Can't simply exit, __fput() will think that everything is OK,
+                 * and move on to freeing struct file. remove_proc_entry() will
+                 * find slacker in opener's list and will try to do non-trivial
+                 * things with struct file. Therefore, remove opener from list.
+                 *
+                 * But if opener is removed from list, who will ->release it?
+                 */
+                if (pdeo) {
+                        list_del(&pdeo->lh);
+                        spin_unlock(&pde->pde_unload_lock);
+                        rv = pdeo->release(inode, file);
+                        kfree(pdeo);
+                } else
+                        spin_unlock(&pde->pde_unload_lock);
                 return rv;
         }
         pde->pde_users++;
         release = pde->proc_fops->release;
+        if (pdeo) {
+                list_del(&pdeo->lh);
+                kfree(pdeo);
+        }
         spin_unlock(&pde->pde_unload_lock);
 
         if (release)
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 28cbca805905..442202314d53 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -63,6 +63,7 @@ extern const struct file_operations proc_smaps_operations;
 extern const struct file_operations proc_clear_refs_operations;
 extern const struct file_operations proc_pagemap_operations;
 extern const struct file_operations proc_net_operations;
+extern const struct file_operations proc_kmsg_operations;
 extern const struct inode_operations proc_net_inode_operations;
 
 void free_proc_entry(struct proc_dir_entry *de);
@@ -88,3 +89,10 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *ino,
                 struct dentry *dentry);
 int proc_readdir_de(struct proc_dir_entry *de, struct file *filp, void *dirent,
                 filldir_t filldir);
+
+struct pde_opener {
+        struct inode *inode;
+        struct file *file;
+        int (*release)(struct inode *, struct file *);
+        struct list_head lh;
+};
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index e78c81fcf547..c2370c76fb71 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -23,6 +23,10 @@
 
 #define CORE_STR "CORE"
 
+#ifndef ELF_CORE_EFLAGS
+#define ELF_CORE_EFLAGS 0
+#endif
+
 static int open_kcore(struct inode * inode, struct file * filp)
 {
         return capable(CAP_SYS_RAWIO) ? 0 : -EPERM;
@@ -164,11 +168,7 @@ static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff)
         elf->e_entry    = 0;
         elf->e_phoff    = sizeof(struct elfhdr);
         elf->e_shoff    = 0;
-#if defined(CONFIG_H8300)
-        elf->e_flags    = ELF_FLAGS;
-#else
-        elf->e_flags    = 0;
-#endif
+        elf->e_flags    = ELF_CORE_EFLAGS;
         elf->e_ehsize   = sizeof(struct elfhdr);
         elf->e_phentsize= sizeof(struct elf_phdr);
         elf->e_phnum    = nphdr;
diff --git a/fs/proc/kmsg.c b/fs/proc/kmsg.c
index ff3b90b56e9d..9fd5df3f40ce 100644
--- a/fs/proc/kmsg.c
+++ b/fs/proc/kmsg.c
@@ -15,6 +15,8 @@
 #include <asm/uaccess.h>
 #include <asm/io.h>
 
+#include "internal.h"
+
 extern wait_queue_head_t log_wait;
 
 extern int do_syslog(int type, char __user *bug, int count);
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index c652d469dc08..ded969862960 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -232,7 +232,6 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
 #undef K
 }
 
-extern const struct seq_operations fragmentation_op;
 static int fragmentation_open(struct inode *inode, struct file *file)
 {
         (void)inode;
@@ -246,7 +245,6 @@ static const struct file_operations fragmentation_file_operations = {
         .release        = seq_release,
 };
 
-extern const struct seq_operations pagetypeinfo_op;
 static int pagetypeinfo_open(struct inode *inode, struct file *file)
 {
         return seq_open(file, &pagetypeinfo_op);
@@ -259,7 +257,6 @@ static const struct file_operations pagetypeinfo_file_ops = {
         .release        = seq_release,
 };
 
-extern const struct seq_operations zoneinfo_op;
 static int zoneinfo_open(struct inode *inode, struct file *file)
 {
         return seq_open(file, &zoneinfo_op);
@@ -356,7 +353,6 @@ static const struct file_operations proc_devinfo_operations = {
         .release        = seq_release,
 };
 
-extern const struct seq_operations vmstat_op;
 static int vmstat_open(struct inode *inode, struct file *file)
 {
         return seq_open(file, &vmstat_op);
@@ -468,14 +464,25 @@ static const struct file_operations proc_slabstats_operations = {
 #ifdef CONFIG_MMU
 static int vmalloc_open(struct inode *inode, struct file *file)
 {
-        return seq_open(file, &vmalloc_op);
+        unsigned int *ptr = NULL;
+        int ret;
+
+        if (NUMA_BUILD)
+                ptr = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL);
+        ret = seq_open(file, &vmalloc_op);
+        if (!ret) {
+                struct seq_file *m = file->private_data;
+                m->private = ptr;
+        } else
+                kfree(ptr);
+        return ret;
 }
 
 static const struct file_operations proc_vmalloc_operations = {
         .open           = vmalloc_open,
         .read           = seq_read,
         .llseek         = seq_lseek,
-        .release        = seq_release,
+        .release        = seq_release_private,
 };
 #endif
 
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index b224a28e0c15..7bc296f424ae 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -27,6 +27,11 @@
 #include "internal.h"
 
 
+static struct net *get_proc_net(const struct inode *inode)
+{
+        return maybe_get_net(PDE_NET(PDE(inode)));
+}
+
 int seq_open_net(struct inode *ino, struct file *f,
                  const struct seq_operations *ops, int size)
 {
@@ -185,12 +190,6 @@ void proc_net_remove(struct net *net, const char *name)
 }
 EXPORT_SYMBOL_GPL(proc_net_remove);
 
-struct net *get_proc_net(const struct inode *inode)
-{
-        return maybe_get_net(PDE_NET(PDE(inode)));
-}
-EXPORT_SYMBOL_GPL(get_proc_net);
-
 static __net_init int proc_net_ns_init(struct net *net)
 {
         struct proc_dir_entry *netd, *net_statd;
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 5acc001d49f6..f9a8b892718f 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -10,149 +10,110 @@
 static struct dentry_operations proc_sys_dentry_operations;
 static const struct file_operations proc_sys_file_operations;
 static const struct inode_operations proc_sys_inode_operations;
+static const struct file_operations proc_sys_dir_file_operations;
+static const struct inode_operations proc_sys_dir_operations;
 
-static void proc_sys_refresh_inode(struct inode *inode, struct ctl_table *table)
-{
-        /* Refresh the cached information bits in the inode */
-        if (table) {
-                inode->i_uid = 0;
-                inode->i_gid = 0;
-                inode->i_mode = table->mode;
-                if (table->proc_handler) {
-                        inode->i_mode |= S_IFREG;
-                        inode->i_nlink = 1;
-                } else {
-                        inode->i_mode |= S_IFDIR;
-                        inode->i_nlink = 0;     /* It is too hard to figure out */
-                }
-        }
-}
-
-static struct inode *proc_sys_make_inode(struct inode *dir, struct ctl_table *table)
+static struct inode *proc_sys_make_inode(struct super_block *sb,
+                struct ctl_table_header *head, struct ctl_table *table)
 {
         struct inode *inode;
-        struct proc_inode *dir_ei, *ei;
-        int depth;
+        struct proc_inode *ei;
 
-        inode = new_inode(dir->i_sb);
+        inode = new_inode(sb);
         if (!inode)
                 goto out;
 
-        /* A directory is always one deeper than it's parent */
-        dir_ei = PROC_I(dir);
-        depth = dir_ei->fd + 1;
-
+        sysctl_head_get(head);
         ei = PROC_I(inode);
-        ei->fd = depth;
+        ei->sysctl = head;
+        ei->sysctl_entry = table;
+
         inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
-        inode->i_op = &proc_sys_inode_operations;
-        inode->i_fop = &proc_sys_file_operations;
         inode->i_flags |= S_PRIVATE; /* tell selinux to ignore this inode */
-        proc_sys_refresh_inode(inode, table);
+        inode->i_mode = table->mode;
+        if (!table->child) {
+                inode->i_mode |= S_IFREG;
+                inode->i_op = &proc_sys_inode_operations;
+                inode->i_fop = &proc_sys_file_operations;
+        } else {
+                inode->i_mode |= S_IFDIR;
+                inode->i_nlink = 0;
+                inode->i_op = &proc_sys_dir_operations;
+                inode->i_fop = &proc_sys_dir_file_operations;
+        }
 out:
         return inode;
 }
 
-static struct dentry *proc_sys_ancestor(struct dentry *dentry, int depth)
-{
-        for (;;) {
-                struct proc_inode *ei;
-
-                ei = PROC_I(dentry->d_inode);
-                if (ei->fd == depth)
-                        break; /* found */
-
-                dentry = dentry->d_parent;
-        }
-        return dentry;
-}
-
-static struct ctl_table *proc_sys_lookup_table_one(struct ctl_table *table,
-                                                        struct qstr *name)
+static struct ctl_table *find_in_table(struct ctl_table *p, struct qstr *name)
 {
         int len;
-        for ( ; table->ctl_name || table->procname; table++) {
+        for ( ; p->ctl_name || p->procname; p++) {
 
-                if (!table->procname)
+                if (!p->procname)
                         continue;
 
-                len = strlen(table->procname);
+                len = strlen(p->procname);
                 if (len != name->len)
                         continue;
 
-                if (memcmp(table->procname, name->name, len) != 0)
+                if (memcmp(p->procname, name->name, len) != 0)
                         continue;
 
                 /* I have a match */
-                return table;
+                return p;
         }
         return NULL;
 }
 
-static struct ctl_table *proc_sys_lookup_table(struct dentry *dentry,
-                                                struct ctl_table *table)
+struct ctl_table_header *grab_header(struct inode *inode)
 {
-        struct dentry *ancestor;
-        struct proc_inode *ei;
-        int depth, i;
+        if (PROC_I(inode)->sysctl)
+                return sysctl_head_grab(PROC_I(inode)->sysctl);
+        else
+                return sysctl_head_next(NULL);
+}
 
-        ei = PROC_I(dentry->d_inode);
-        depth = ei->fd;
+static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
+                                        struct nameidata *nd)
+{
+        struct ctl_table_header *head = grab_header(dir);
+        struct ctl_table *table = PROC_I(dir)->sysctl_entry;
+        struct ctl_table_header *h = NULL;
+        struct qstr *name = &dentry->d_name;
+        struct ctl_table *p;
+        struct inode *inode;
+        struct dentry *err = ERR_PTR(-ENOENT);
 
-        if (depth == 0)
-                return table;
+        if (IS_ERR(head))
+                return ERR_CAST(head);
 
-        for (i = 1; table && (i <= depth); i++) {
-                ancestor = proc_sys_ancestor(dentry, i);
-                table = proc_sys_lookup_table_one(table, &ancestor->d_name);
-                if (table)
-                        table = table->child;
+        if (table && !table->child) {
+                WARN_ON(1);
+                goto out;
         }
-        return table;
-
-}
-static struct ctl_table *proc_sys_lookup_entry(struct dentry *dparent,
-                                                struct qstr *name,
-                                                struct ctl_table *table)
-{
-        table = proc_sys_lookup_table(dparent, table);
-        if (table)
-                table = proc_sys_lookup_table_one(table, name);
-        return table;
-}
 
-static struct ctl_table *do_proc_sys_lookup(struct dentry *parent,
-                                                struct qstr *name,
-                                                struct ctl_table_header **ptr)
-{
-        struct ctl_table_header *head;
-        struct ctl_table *table = NULL;
+        table = table ? table->child : head->ctl_table;
 
-        for (head = sysctl_head_next(NULL); head;
-                        head = sysctl_head_next(head)) {
-                table = proc_sys_lookup_entry(parent, name, head->ctl_table);
-                if (table)
-                        break;
+        p = find_in_table(table, name);
+        if (!p) {
+                for (h = sysctl_head_next(NULL); h; h = sysctl_head_next(h)) {
+                        if (h->attached_to != table)
+                                continue;
+                        p = find_in_table(h->attached_by, name);
+                        if (p)
+                                break;
+                }
         }
-        *ptr = head;
-        return table;
-}
-
-static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
-                                        struct nameidata *nd)
-{
-        struct ctl_table_header *head;
-        struct inode *inode;
-        struct dentry *err;
-        struct ctl_table *table;
 
-        err = ERR_PTR(-ENOENT);
-        table = do_proc_sys_lookup(dentry->d_parent, &dentry->d_name, &head);
-        if (!table)
+        if (!p)
                 goto out;
 
         err = ERR_PTR(-ENOMEM);
-        inode = proc_sys_make_inode(dir, table);
+        inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p);
+        if (h)
+                sysctl_head_finish(h);
+
         if (!inode)
                 goto out;
 
@@ -168,22 +129,14 @@ out:
 static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
                 size_t count, loff_t *ppos, int write)
 {
-        struct dentry *dentry = filp->f_dentry;
-        struct ctl_table_header *head;
-        struct ctl_table *table;
+        struct inode *inode = filp->f_path.dentry->d_inode;
+        struct ctl_table_header *head = grab_header(inode);
+        struct ctl_table *table = PROC_I(inode)->sysctl_entry;
         ssize_t error;
         size_t res;
 
-        table = do_proc_sys_lookup(dentry->d_parent, &dentry->d_name, &head);
-        /* Has the sysctl entry disappeared on us? */
-        error = -ENOENT;
-        if (!table)
-                goto out;
-
-        /* Has the sysctl entry been replaced by a directory? */
-        error = -EISDIR;
-        if (!table->proc_handler)
-                goto out;
+        if (IS_ERR(head))
+                return PTR_ERR(head);
 
         /*
          * At this point we know that the sysctl was not unregistered
@@ -193,6 +146,11 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
         if (sysctl_perm(head->root, table, write ? MAY_WRITE : MAY_READ))
                 goto out;
 
+        /* if that can happen at all, it should be -EINVAL, not -EISDIR */
+        error = -EINVAL;
+        if (!table->proc_handler)
+                goto out;
+
         /* careful: calling conventions are nasty here */
         res = count;
         error = table->proc_handler(table, write, filp, buf, &res, ppos);
@@ -218,82 +176,86 @@ static ssize_t proc_sys_write(struct file *filp, const char __user *buf,
 
 
 static int proc_sys_fill_cache(struct file *filp, void *dirent,
-                                filldir_t filldir, struct ctl_table *table)
+                                filldir_t filldir,
+                                struct ctl_table_header *head,
+                                struct ctl_table *table)
 {
-        struct ctl_table_header *head;
-        struct ctl_table *child_table = NULL;
         struct dentry *child, *dir = filp->f_path.dentry;
         struct inode *inode;
         struct qstr qname;
         ino_t ino = 0;
         unsigned type = DT_UNKNOWN;
-        int ret;
 
         qname.name = table->procname;
         qname.len  = strlen(table->procname);
         qname.hash = full_name_hash(qname.name, qname.len);
 
-        /* Suppress duplicates.
-         * Only fill a directory entry if it is the value that
-         * an ordinary lookup of that name returns.  Hide all
-         * others.
-         *
-         * If we ever cache this translation in the dcache
-         * I should do a dcache lookup first.  But for now
-         * it is just simpler not to.
-         */
-        ret = 0;
-        child_table = do_proc_sys_lookup(dir, &qname, &head);
-        sysctl_head_finish(head);
-        if (child_table != table)
-                return 0;
-
         child = d_lookup(dir, &qname);
         if (!child) {
-                struct dentry *new;
-                new = d_alloc(dir, &qname);
-                if (new) {
-                        inode = proc_sys_make_inode(dir->d_inode, table);
-                        if (!inode)
-                                child = ERR_PTR(-ENOMEM);
-                        else {
-                                new->d_op = &proc_sys_dentry_operations;
-                                d_add(new, inode);
+                child = d_alloc(dir, &qname);
+                if (child) {
+                        inode = proc_sys_make_inode(dir->d_sb, head, table);
+                        if (!inode) {
+                                dput(child);
+                                return -ENOMEM;
+                        } else {
+                                child->d_op = &proc_sys_dentry_operations;
+                                d_add(child, inode);
                         }
-                        if (child)
-                                dput(new);
-                        else
-                                child = new;
+                } else {
+                        return -ENOMEM;
                 }
         }
-        if (!child || IS_ERR(child) || !child->d_inode)
-                goto end_instantiate;
         inode = child->d_inode;
-        if (inode) {
-                ino  = inode->i_ino;
-                type = inode->i_mode >> 12;
-        }
+        ino  = inode->i_ino;
+        type = inode->i_mode >> 12;
         dput(child);
-end_instantiate:
-        if (!ino)
-                ino= find_inode_number(dir, &qname);
-        if (!ino)
-                ino = 1;
-        return filldir(dirent, qname.name, qname.len, filp->f_pos, ino, type);
+        return !!filldir(dirent, qname.name, qname.len, filp->f_pos, ino, type);
+}
+
+static int scan(struct ctl_table_header *head, ctl_table *table,
+                unsigned long *pos, struct file *file,
+                void *dirent, filldir_t filldir)
+{
+
+        for (; table->ctl_name || table->procname; table++, (*pos)++) {
+                int res;
+
+                /* Can't do anything without a proc name */
+                if (!table->procname)
+                        continue;
+
+                if (*pos < file->f_pos)
+                        continue;
+
+                res = proc_sys_fill_cache(file, dirent, filldir, head, table);
+                if (res)
+                        return res;
+
+                file->f_pos = *pos + 1;
+        }
+        return 0;
 }
 
 static int proc_sys_readdir(struct file *filp, void *dirent, filldir_t filldir)
 {
-        struct dentry *dentry = filp->f_dentry;
+        struct dentry *dentry = filp->f_path.dentry;
         struct inode *inode = dentry->d_inode;
-        struct ctl_table_header *head = NULL;
-        struct ctl_table *table;
+        struct ctl_table_header *head = grab_header(inode);
+        struct ctl_table *table = PROC_I(inode)->sysctl_entry;
+        struct ctl_table_header *h = NULL;
         unsigned long pos;
-        int ret;
+        int ret = -EINVAL;
+
+        if (IS_ERR(head))
+                return PTR_ERR(head);
 
-        ret = -ENOTDIR;
-        if (!S_ISDIR(inode->i_mode))
+        if (table && !table->child) {
+                WARN_ON(1);
                 goto out;
+        }
+
+        table = table ? table->child : head->ctl_table;
 
         ret = 0;
         /* Avoid a switch here: arm builds fail with missing __cmpdi2 */
@@ -311,30 +273,17 @@ static int proc_sys_readdir(struct file *filp, void *dirent, filldir_t filldir)
         }
         pos = 2;
 
-        /* - Find each instance of the directory
-         * - Read all entries in each instance
-         * - Before returning an entry to user space lookup the entry
-         *   by name and if I find a different entry don't return
-         *   this one because it means it is a buried dup.
-         * For sysctl this should only happen for directory entries.
-         */
-        for (head = sysctl_head_next(NULL); head; head = sysctl_head_next(head)) {
-                table = proc_sys_lookup_table(dentry, head->ctl_table);
+        ret = scan(head, table, &pos, filp, dirent, filldir);
+        if (ret)
+                goto out;
 
-                if (!table)
+        for (h = sysctl_head_next(NULL); h; h = sysctl_head_next(h)) {
+                if (h->attached_to != table)
                         continue;
-
-                for (; table->ctl_name || table->procname; table++, pos++) {
-                        /* Can't do anything without a proc name */
-                        if (!table->procname)
-                                continue;
-
-                        if (pos < filp->f_pos)
-                                continue;
-
-                        if (proc_sys_fill_cache(filp, dirent, filldir, table) < 0)
-                                goto out;
-                        filp->f_pos = pos + 1;
+                ret = scan(h, h->attached_by, &pos, filp, dirent, filldir);
+                if (ret) {
+                        sysctl_head_finish(h);
+                        break;
                 }
         }
         ret = 1;
@@ -343,53 +292,24 @@ out:
         return ret;
 }
 
-static int proc_sys_permission(struct inode *inode, int mask, struct nameidata *nd)
+static int proc_sys_permission(struct inode *inode, int mask)
 {
         /*
          * sysctl entries that are not writeable,
          * are _NOT_ writeable, capabilities or not.
          */
-        struct ctl_table_header *head;
-        struct ctl_table *table;
-        struct dentry *dentry;
-        int mode;
-        int depth;
+        struct ctl_table_header *head = grab_header(inode);
+        struct ctl_table *table = PROC_I(inode)->sysctl_entry;
         int error;
 
-        head = NULL;
-        depth = PROC_I(inode)->fd;
-
-        /* First check the cached permissions, in case we don't have
-         * enough information to lookup the sysctl table entry.
-         */
-        error = -EACCES;
-        mode = inode->i_mode;
-
-        if (current->euid == 0)
-                mode >>= 6;
-        else if (in_group_p(0))
-                mode >>= 3;
-
-        if ((mode & mask & (MAY_READ|MAY_WRITE|MAY_EXEC)) == mask)
-                error = 0;
-
-        /* If we can't get a sysctl table entry the permission
-         * checks on the cached mode will have to be enough.
-         */
-        if (!nd || !depth)
-                goto out;
+        if (IS_ERR(head))
+                return PTR_ERR(head);
 
-        dentry = nd->path.dentry;
-        table = do_proc_sys_lookup(dentry->d_parent, &dentry->d_name, &head);
+        if (!table) /* global root - r-xr-xr-x */
+                error = mask & MAY_WRITE ? -EACCES : 0;
+        else /* Use the permissions on the sysctl table entry */
+                error = sysctl_perm(head->root, table, mask);
 
-        /* If the entry does not exist deny permission */
-        error = -EACCES;
-        if (!table)
-                goto out;
-
-        /* Use the permissions on the sysctl table entry */
-        error = sysctl_perm(head->root, table, mask);
-out:
         sysctl_head_finish(head);
         return error;
 }
@@ -409,33 +329,70 @@ static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
         return error;
 }
 
-/* I'm lazy and don't distinguish between files and directories,
- * until access time.
- */
+static int proc_sys_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+{
+        struct inode *inode = dentry->d_inode;
+        struct ctl_table_header *head = grab_header(inode);
+        struct ctl_table *table = PROC_I(inode)->sysctl_entry;
+
+        if (IS_ERR(head))
+                return PTR_ERR(head);
+
+        generic_fillattr(inode, stat);
+        if (table)
+                stat->mode = (stat->mode & S_IFMT) | table->mode;
+
+        sysctl_head_finish(head);
+        return 0;
+}
+
 static const struct file_operations proc_sys_file_operations = {
         .read           = proc_sys_read,
         .write          = proc_sys_write,
+};
+
+static const struct file_operations proc_sys_dir_file_operations = {
         .readdir        = proc_sys_readdir,
 };
 
 static const struct inode_operations proc_sys_inode_operations = {
+        .permission     = proc_sys_permission,
+        .setattr        = proc_sys_setattr,
+        .getattr        = proc_sys_getattr,
+};
+
+static const struct inode_operations proc_sys_dir_operations = {
         .lookup         = proc_sys_lookup,
         .permission     = proc_sys_permission,
         .setattr        = proc_sys_setattr,
+        .getattr        = proc_sys_getattr,
 };
 
 static int proc_sys_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
-        struct ctl_table_header *head;
-        struct ctl_table *table;
-        table = do_proc_sys_lookup(dentry->d_parent, &dentry->d_name, &head);
-        proc_sys_refresh_inode(dentry->d_inode, table);
-        sysctl_head_finish(head);
-        return !!table;
+        return !PROC_I(dentry->d_inode)->sysctl->unregistering;
+}
+
+static int proc_sys_delete(struct dentry *dentry)
+{
+        return !!PROC_I(dentry->d_inode)->sysctl->unregistering;
+}
+
+static int proc_sys_compare(struct dentry *dir, struct qstr *qstr,
+                            struct qstr *name)
+{
+        struct dentry *dentry = container_of(qstr, struct dentry, d_name);
+        if (qstr->len != name->len)
+                return 1;
+        if (memcmp(qstr->name, name->name, name->len))
+                return 1;
+        return !sysctl_is_seen(PROC_I(dentry->d_inode)->sysctl);
 }
 
 static struct dentry_operations proc_sys_dentry_operations = {
         .d_revalidate   = proc_sys_revalidate,
+        .d_delete       = proc_sys_delete,
+        .d_compare      = proc_sys_compare,
 };
 
 static struct proc_dir_entry *proc_sys_root;
@@ -443,8 +400,8 @@ static struct proc_dir_entry *proc_sys_root;
 int proc_sys_init(void)
 {
         proc_sys_root = proc_mkdir("sys", NULL);
-        proc_sys_root->proc_iops = &proc_sys_inode_operations;
-        proc_sys_root->proc_fops = &proc_sys_file_operations;
+        proc_sys_root->proc_iops = &proc_sys_dir_operations;
+        proc_sys_root->proc_fops = &proc_sys_dir_file_operations;
         proc_sys_root->nlink = 0;
         return 0;
 }
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 164bd9f9ede3..7546a918f790 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -636,7 +636,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
         struct pagemapread pm;
         int pagecount;
         int ret = -ESRCH;
-        struct mm_walk pagemap_walk;
+        struct mm_walk pagemap_walk = {};
         unsigned long src;
         unsigned long svpfn;
         unsigned long start_vaddr;
diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c
index b31ab78052b3..2aad1044b84c 100644
--- a/fs/qnx4/inode.c
+++ b/fs/qnx4/inode.c
@@ -553,7 +553,7 @@ static void qnx4_destroy_inode(struct inode *inode)
         kmem_cache_free(qnx4_inode_cachep, qnx4_i(inode));
 }
 
-static void init_once(struct kmem_cache *cachep, void *foo)
+static void init_once(void *foo)
 {
         struct qnx4_inode_info *ei = (struct qnx4_inode_info *) foo;
 
diff --git a/fs/quota.c b/fs/quota.c
index db1cc9f3c7aa..7f4386ebc23a 100644
--- a/fs/quota.c
+++ b/fs/quota.c
@@ -186,7 +186,7 @@ static void quota_sync_sb(struct super_block *sb, int type)
 
 void sync_dquots(struct super_block *sb, int type)
 {
-        int cnt, dirty;
+        int cnt;
 
         if (sb) {
                 if (sb->s_qcop->quota_sync)
@@ -198,11 +198,17 @@ void sync_dquots(struct super_block *sb, int type)
 restart:
         list_for_each_entry(sb, &super_blocks, s_list) {
                 /* This test just improves performance so it needn't be reliable... */
-                for (cnt = 0, dirty = 0; cnt < MAXQUOTAS; cnt++)
-                        if ((type == cnt || type == -1) && sb_has_quota_enabled(sb, cnt)
-                            && info_any_dirty(&sb_dqopt(sb)->info[cnt]))
-                                dirty = 1;
-                if (!dirty)
+                for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
+                        if (type != -1 && type != cnt)
+                                continue;
+                        if (!sb_has_quota_enabled(sb, cnt))
+                                continue;
+                        if (!info_dirty(&sb_dqopt(sb)->info[cnt]) &&
+                            list_empty(&sb_dqopt(sb)->info[cnt].dqi_dirty_list))
+                                continue;
+                        break;
+                }
+                if (cnt == MAXQUOTAS)
                         continue;
                 sb->s_count++;
                 spin_unlock(&sb_lock);
diff --git a/fs/quota_v1.c b/fs/quota_v1.c
index a6cf9269105c..5ae15b13eeb0 100644
--- a/fs/quota_v1.c
+++ b/fs/quota_v1.c
@@ -1,6 +1,7 @@
 #include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/quota.h>
+#include <linux/quotaops.h>
 #include <linux/dqblk_v1.h>
 #include <linux/quotaio_v1.h>
 #include <linux/kernel.h>
diff --git a/fs/quota_v2.c b/fs/quota_v2.c
index 234ada903633..b53827dc02d9 100644
--- a/fs/quota_v2.c
+++ b/fs/quota_v2.c
@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/quotaops.h>
 
 #include <asm/byteorder.h>
 
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 192269698a8a..5699171212ae 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -2435,7 +2435,7 @@ static int reiserfs_write_full_page(struct page *page,
                 if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) {
                         lock_buffer(bh);
                 } else {
-                        if (test_set_buffer_locked(bh)) {
+                        if (!trylock_buffer(bh)) {
                                 redirty_page_for_writepage(wbc, page);
                                 continue;
                         }
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index e396b2fa4743..c21df71943a6 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -34,15 +34,10 @@
 **                      from within kupdate, it will ignore the immediate flag
 */
 
-#include <asm/uaccess.h>
-#include <asm/system.h>
-
 #include <linux/time.h>
 #include <linux/semaphore.h>
-
 #include <linux/vmalloc.h>
 #include <linux/reiserfs_fs.h>
-
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/fcntl.h>
@@ -54,6 +49,9 @@
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
+#include <linux/uaccess.h>
+
+#include <asm/system.h>
 
 /* gets a struct reiserfs_journal_list * from a list head */
 #define JOURNAL_LIST_ENTRY(h) (list_entry((h), struct reiserfs_journal_list, \
@@ -558,13 +556,13 @@ static inline void insert_journal_hash(struct reiserfs_journal_cnode **table,
 static inline void lock_journal(struct super_block *p_s_sb)
 {
         PROC_INFO_INC(p_s_sb, journal.lock_journal);
-        down(&SB_JOURNAL(p_s_sb)->j_lock);
+        mutex_lock(&SB_JOURNAL(p_s_sb)->j_mutex);
 }
 
 /* unlock the current transaction */
 static inline void unlock_journal(struct super_block *p_s_sb)
 {
-        up(&SB_JOURNAL(p_s_sb)->j_lock);
+        mutex_unlock(&SB_JOURNAL(p_s_sb)->j_mutex);
 }
 
 static inline void get_journal_list(struct reiserfs_journal_list *jl)
@@ -629,7 +627,7 @@ static int journal_list_still_alive(struct super_block *s,
 static void release_buffer_page(struct buffer_head *bh)
 {
         struct page *page = bh->b_page;
-        if (!page->mapping && !TestSetPageLocked(page)) {
+        if (!page->mapping && trylock_page(page)) {
                 page_cache_get(page);
                 put_bh(bh);
                 if (!page->mapping)
@@ -857,7 +855,7 @@ static int write_ordered_buffers(spinlock_t * lock,
                 jh = JH_ENTRY(list->next);
                 bh = jh->bh;
                 get_bh(bh);
-                if (test_set_buffer_locked(bh)) {
+                if (!trylock_buffer(bh)) {
                         if (!buffer_dirty(bh)) {
                                 list_move(&jh->list, &tmp);
                                 goto loop_next;
@@ -1045,9 +1043,9 @@ static int flush_commit_list(struct super_block *s,
         }
 
         /* make sure nobody is trying to flush this one at the same time */
-        down(&jl->j_commit_lock);
+        mutex_lock(&jl->j_commit_mutex);
         if (!journal_list_still_alive(s, trans_id)) {
-                up(&jl->j_commit_lock);
+                mutex_unlock(&jl->j_commit_mutex);
                 goto put_jl;
         }
         BUG_ON(jl->j_trans_id == 0);
@@ -1057,7 +1055,7 @@ static int flush_commit_list(struct super_block *s,
                 if (flushall) {
                         atomic_set(&(jl->j_older_commits_done), 1);
                 }
-                up(&jl->j_commit_lock);
+                mutex_unlock(&jl->j_commit_mutex);
                 goto put_jl;
         }
 
@@ -1181,7 +1179,7 @@ static int flush_commit_list(struct super_block *s,
         if (flushall) {
                 atomic_set(&(jl->j_older_commits_done), 1);
         }
-        up(&jl->j_commit_lock);
+        mutex_unlock(&jl->j_commit_mutex);
       put_jl:
         put_journal_list(s, jl);
 
@@ -1411,8 +1409,8 @@ static int flush_journal_list(struct super_block *s,
 
         /* if flushall == 0, the lock is already held */
         if (flushall) {
-                down(&journal->j_flush_sem);
-        } else if (!down_trylock(&journal->j_flush_sem)) {
+                mutex_lock(&journal->j_flush_mutex);
+        } else if (mutex_trylock(&journal->j_flush_mutex)) {
                 BUG();
         }
 
@@ -1642,7 +1640,7 @@ static int flush_journal_list(struct super_block *s,
         jl->j_state = 0;
         put_journal_list(s, jl);
         if (flushall)
-                up(&journal->j_flush_sem);
+                mutex_unlock(&journal->j_flush_mutex);
         put_fs_excl();
         return err;
 }
@@ -1772,12 +1770,12 @@ static int kupdate_transactions(struct super_block *s,
         struct reiserfs_journal *journal = SB_JOURNAL(s);
         chunk.nr = 0;
 
-        down(&journal->j_flush_sem);
+        mutex_lock(&journal->j_flush_mutex);
         if (!journal_list_still_alive(s, orig_trans_id)) {
                 goto done;
         }
 
-        /* we've got j_flush_sem held, nobody is going to delete any
+        /* we've got j_flush_mutex held, nobody is going to delete any
          * of these lists out from underneath us
          */
         while ((num_trans && transactions_flushed < num_trans) ||
@@ -1812,7 +1810,7 @@ static int kupdate_transactions(struct super_block *s,
         }
 
       done:
-        up(&journal->j_flush_sem);
+        mutex_unlock(&journal->j_flush_mutex);
         return ret;
 }
 
@@ -2556,7 +2554,7 @@ static struct reiserfs_journal_list *alloc_journal_list(struct super_block *s)
         INIT_LIST_HEAD(&jl->j_working_list);
         INIT_LIST_HEAD(&jl->j_tail_bh_list);
         INIT_LIST_HEAD(&jl->j_bh_list);
-        sema_init(&jl->j_commit_lock, 1);
+        mutex_init(&jl->j_commit_mutex);
         SB_JOURNAL(s)->j_num_lists++;
         get_journal_list(jl);
         return jl;
@@ -2837,8 +2835,8 @@ int journal_init(struct super_block *p_s_sb, const char *j_dev_name,
         journal->j_last = NULL;
         journal->j_first = NULL;
         init_waitqueue_head(&(journal->j_join_wait));
-        sema_init(&journal->j_lock, 1);
-        sema_init(&journal->j_flush_sem, 1);
+        mutex_init(&journal->j_mutex);
+        mutex_init(&journal->j_flush_mutex);
 
         journal->j_trans_id = 10;
         journal->j_mount_id = 10;
@@ -3873,7 +3871,7 @@ int reiserfs_prepare_for_journal(struct super_block *p_s_sb,
 {
         PROC_INFO_INC(p_s_sb, journal.prepare);
 
-        if (test_set_buffer_locked(bh)) {
+        if (!trylock_buffer(bh)) {
                 if (!wait)
                         return 0;
                 lock_buffer(bh);
@@ -4030,7 +4028,7 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
          * the new transaction is fully setup, and we've already flushed the
          * ordered bh list
          */
-        down(&jl->j_commit_lock);
+        mutex_lock(&jl->j_commit_mutex);
 
         /* save the transaction id in case we need to commit it later */
         commit_trans_id = jl->j_trans_id;
@@ -4196,7 +4194,7 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
                 lock_kernel();
         }
         BUG_ON(!list_empty(&jl->j_tail_bh_list));
-        up(&jl->j_commit_lock);
+        mutex_unlock(&jl->j_commit_mutex);
 
         /* honor the flush wishes from the caller, simple commits can
          ** be done outside the journal lock, they are done below
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 1d40f2bd1970..d318c7e663fa 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -22,11 +22,11 @@
 #include <linux/blkdev.h>
 #include <linux/buffer_head.h>
 #include <linux/exportfs.h>
+#include <linux/quotaops.h>
 #include <linux/vfs.h>
 #include <linux/mnt_namespace.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
-#include <linux/quotaops.h>
 
 struct file_system_type reiserfs_fs_type;
 
@@ -182,7 +182,7 @@ static int finish_unfinished(struct super_block *s)
                         int ret = reiserfs_quota_on_mount(s, i);
                         if (ret < 0)
                                 reiserfs_warning(s,
-                                                 "reiserfs: cannot turn on journalled quota: error %d",
+                                                 "reiserfs: cannot turn on journaled quota: error %d",
                                                  ret);
                 }
         }
@@ -520,7 +520,7 @@ static void reiserfs_destroy_inode(struct inode *inode)
         kmem_cache_free(reiserfs_inode_cachep, REISERFS_I(inode));
 }
 
-static void init_once(struct kmem_cache * cachep, void *foo)
+static void init_once(void *foo)
 {
         struct reiserfs_inode_info *ei = (struct reiserfs_inode_info *)foo;
 
@@ -876,7 +876,9 @@ static int reiserfs_parse_options(struct super_block *s, char *options,	/* strin
                                      mount options were selected. */
                                   unsigned long *blocks,        /* strtol-ed from NNN of resize=NNN */
                                   char **jdev_name,
-                                  unsigned int *commit_max_age)
+                                  unsigned int *commit_max_age,
+                                  char **qf_names,
+                                  unsigned int *qfmt)
 {
         int c;
         char *arg = NULL;
@@ -992,9 +994,11 @@ static int reiserfs_parse_options(struct super_block *s, char *options,	/* strin
                 if (c == 'u' || c == 'g') {
                         int qtype = c == 'u' ? USRQUOTA : GRPQUOTA;
 
-                        if (sb_any_quota_enabled(s)) {
+                        if ((sb_any_quota_enabled(s) ||
+                             sb_any_quota_suspended(s)) &&
+                            (!*arg != !REISERFS_SB(s)->s_qf_names[qtype])) {
                                 reiserfs_warning(s,
-                                                 "reiserfs_parse_options: cannot change journalled quota options when quota turned on.");
+                                                 "reiserfs_parse_options: cannot change journaled quota options when quota turned on.");
                                 return 0;
                         }
                         if (*arg) {     /* Some filename specified? */
@@ -1011,46 +1015,54 @@ static int reiserfs_parse_options(struct super_block *s, char *options,	/* strin
                                                          "reiserfs_parse_options: quotafile must be on filesystem root.");
                                         return 0;
                                 }
-                                REISERFS_SB(s)->s_qf_names[qtype] =
+                                qf_names[qtype] =
                                     kmalloc(strlen(arg) + 1, GFP_KERNEL);
-                                if (!REISERFS_SB(s)->s_qf_names[qtype]) {
+                                if (!qf_names[qtype]) {
                                         reiserfs_warning(s,
                                                          "reiserfs_parse_options: not enough memory for storing quotafile name.");
                                         return 0;
                                 }
-                                strcpy(REISERFS_SB(s)->s_qf_names[qtype], arg);
+                                strcpy(qf_names[qtype], arg);
                                 *mount_options |= 1 << REISERFS_QUOTA;
                         } else {
-                                kfree(REISERFS_SB(s)->s_qf_names[qtype]);
-                                REISERFS_SB(s)->s_qf_names[qtype] = NULL;
+                                if (qf_names[qtype] !=
+                                    REISERFS_SB(s)->s_qf_names[qtype])
+                                        kfree(qf_names[qtype]);
+                                qf_names[qtype] = NULL;
                         }
                 }
                 if (c == 'f') {
                         if (!strcmp(arg, "vfsold"))
-                                REISERFS_SB(s)->s_jquota_fmt = QFMT_VFS_OLD;
+                                *qfmt = QFMT_VFS_OLD;
                         else if (!strcmp(arg, "vfsv0"))
-                                REISERFS_SB(s)->s_jquota_fmt = QFMT_VFS_V0;
+                                *qfmt = QFMT_VFS_V0;
                         else {
                                 reiserfs_warning(s,
                                                  "reiserfs_parse_options: unknown quota format specified.");
                                 return 0;
                         }
+                        if ((sb_any_quota_enabled(s) ||
+                             sb_any_quota_suspended(s)) &&
+                            *qfmt != REISERFS_SB(s)->s_jquota_fmt) {
+                                reiserfs_warning(s,
+                                                 "reiserfs_parse_options: cannot change journaled quota options when quota turned on.");
+                                return 0;
+                        }
                 }
 #else
                 if (c == 'u' || c == 'g' || c == 'f') {
                         reiserfs_warning(s,
-                                         "reiserfs_parse_options: journalled quota options not supported.");
+                                         "reiserfs_parse_options: journaled quota options not supported.");
                         return 0;
                 }
 #endif
         }
 
 #ifdef CONFIG_QUOTA
-        if (!REISERFS_SB(s)->s_jquota_fmt
-            && (REISERFS_SB(s)->s_qf_names[USRQUOTA]
-                || REISERFS_SB(s)->s_qf_names[GRPQUOTA])) {
+        if (!REISERFS_SB(s)->s_jquota_fmt && !*qfmt
+            && (qf_names[USRQUOTA] || qf_names[GRPQUOTA])) {
                 reiserfs_warning(s,
-                                 "reiserfs_parse_options: journalled quota format not specified.");
+                                 "reiserfs_parse_options: journaled quota format not specified.");
                 return 0;
         }
         /* This checking is not precise wrt the quota type but for our purposes it is sufficient */
@@ -1130,6 +1142,21 @@ static void handle_attrs(struct super_block *s)
         }
 }
 
+#ifdef CONFIG_QUOTA
+static void handle_quota_files(struct super_block *s, char **qf_names,
+                               unsigned int *qfmt)
+{
+        int i;
+
+        for (i = 0; i < MAXQUOTAS; i++) {
+                if (qf_names[i] != REISERFS_SB(s)->s_qf_names[i])
+                        kfree(REISERFS_SB(s)->s_qf_names[i]);
+                REISERFS_SB(s)->s_qf_names[i] = qf_names[i];
+        }
+        REISERFS_SB(s)->s_jquota_fmt = *qfmt;
+}
+#endif
+
 static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 {
         struct reiserfs_super_block *rs;
@@ -1141,23 +1168,30 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
         struct reiserfs_journal *journal = SB_JOURNAL(s);
         char *new_opts = kstrdup(arg, GFP_KERNEL);
         int err;
+        char *qf_names[MAXQUOTAS];
+        unsigned int qfmt = 0;
 #ifdef CONFIG_QUOTA
         int i;
+
+        memcpy(qf_names, REISERFS_SB(s)->s_qf_names, sizeof(qf_names));
 #endif
 
         rs = SB_DISK_SUPER_BLOCK(s);
 
         if (!reiserfs_parse_options
-            (s, arg, &mount_options, &blocks, NULL, &commit_max_age)) {
+            (s, arg, &mount_options, &blocks, NULL, &commit_max_age,
+            qf_names, &qfmt)) {
 #ifdef CONFIG_QUOTA
-                for (i = 0; i < MAXQUOTAS; i++) {
-                        kfree(REISERFS_SB(s)->s_qf_names[i]);
-                        REISERFS_SB(s)->s_qf_names[i] = NULL;
-                }
+                for (i = 0; i < MAXQUOTAS; i++)
+                        if (qf_names[i] != REISERFS_SB(s)->s_qf_names[i])
+                                kfree(qf_names[i]);
 #endif
                 err = -EINVAL;
                 goto out_err;
         }
+#ifdef CONFIG_QUOTA
+        handle_quota_files(s, qf_names, &qfmt);
+#endif
 
         handle_attrs(s);
 
@@ -1570,6 +1604,8 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
         char *jdev_name;
         struct reiserfs_sb_info *sbi;
         int errval = -EINVAL;
+        char *qf_names[MAXQUOTAS] = {};
+        unsigned int qfmt = 0;
 
         save_mount_options(s, data);
 
@@ -1597,9 +1633,12 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
         jdev_name = NULL;
         if (reiserfs_parse_options
             (s, (char *)data, &(sbi->s_mount_opt), &blocks, &jdev_name,
-             &commit_max_age) == 0) {
+             &commit_max_age, qf_names, &qfmt) == 0) {
                 goto error;
         }
+#ifdef CONFIG_QUOTA
+        handle_quota_files(s, qf_names, &qfmt);
+#endif
 
         if (blocks) {
                 SWARN(silent, s, "jmacd-7: reiserfs_fill_super: resize option "
@@ -1819,7 +1858,7 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 
         return (0);
 
-      error:
+error:
         if (jinit_done) {       /* kill the commit thread, free journal ram */
                 journal_release_error(NULL, s);
         }
@@ -1830,10 +1869,8 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 #ifdef CONFIG_QUOTA
         {
                 int j;
-                for (j = 0; j < MAXQUOTAS; j++) {
-                        kfree(sbi->s_qf_names[j]);
-                        sbi->s_qf_names[j] = NULL;
-                }
+                for (j = 0; j < MAXQUOTAS; j++)
+                        kfree(qf_names[j]);
         }
 #endif
         kfree(sbi);
@@ -1980,7 +2017,7 @@ static int reiserfs_release_dquot(struct dquot *dquot)
 
 static int reiserfs_mark_dquot_dirty(struct dquot *dquot)
 {
-        /* Are we journalling quotas? */
+        /* Are we journaling quotas? */
         if (REISERFS_SB(dquot->dq_sb)->s_qf_names[USRQUOTA] ||
             REISERFS_SB(dquot->dq_sb)->s_qf_names[GRPQUOTA]) {
                 dquot_mark_dquot_dirty(dquot);
@@ -2026,6 +2063,7 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id,
         int err;
         struct nameidata nd;
         struct inode *inode;
+        struct reiserfs_transaction_handle th;
 
         if (!(REISERFS_SB(sb)->s_mount_opt & (1 << REISERFS_QUOTA)))
                 return -EINVAL;
@@ -2037,8 +2075,8 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id,
                 return err;
         /* Quotafile not on the same filesystem? */
         if (nd.path.mnt->mnt_sb != sb) {
-                path_put(&nd.path);
-                return -EXDEV;
+                err = -EXDEV;
+                goto out;
         }
         inode = nd.path.dentry->d_inode;
         /* We must not pack tails for quota files on reiserfs for quota IO to work */
@@ -2048,24 +2086,37 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id,
                         reiserfs_warning(sb,
                                 "reiserfs: Unpacking tail of quota file failed"
                                 " (%d). Cannot turn on quotas.", err);
-                        path_put(&nd.path);
-                        return -EINVAL;
+                        err = -EINVAL;
+                        goto out;
                 }
                 mark_inode_dirty(inode);
         }
-        /* Not journalling quota? No more tests needed... */
-        if (!REISERFS_SB(sb)->s_qf_names[USRQUOTA] &&
-            !REISERFS_SB(sb)->s_qf_names[GRPQUOTA]) {
-                path_put(&nd.path);
-                return vfs_quota_on(sb, type, format_id, path, 0);
-        }
-        /* Quotafile not of fs root? */
-        if (nd.path.dentry->d_parent->d_inode != sb->s_root->d_inode)
-                reiserfs_warning(sb,
+        /* Journaling quota? */
+        if (REISERFS_SB(sb)->s_qf_names[type]) {
+                /* Quotafile not of fs root? */
+                if (nd.path.dentry->d_parent->d_inode != sb->s_root->d_inode)
+                        reiserfs_warning(sb,
                                  "reiserfs: Quota file not on filesystem root. "
                                  "Journalled quota will not work.");
+        }
+
+        /*
+         * When we journal data on quota file, we have to flush journal to see
+         * all updates to the file when we bypass pagecache...
+         */
+        if (reiserfs_file_data_log(inode)) {
+                /* Just start temporary transaction and finish it */
+                err = journal_begin(&th, sb, 1);
+                if (err)
+                        goto out;
+                err = journal_end_sync(&th, sb, 1);
+                if (err)
+                        goto out;
+        }
+        err = vfs_quota_on_path(sb, type, format_id, &nd.path);
+out:
         path_put(&nd.path);
-        return vfs_quota_on(sb, type, format_id, path, 0);
+        return err;
 }
 
 /* Read data from quotafile - avoid pagecache and such because we cannot afford
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index d7c4935c1034..bb3cb5b7cdb2 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -1250,7 +1250,7 @@ static int reiserfs_check_acl(struct inode *inode, int mask)
         return error;
 }
 
-int reiserfs_permission(struct inode *inode, int mask, struct nameidata *nd)
+int reiserfs_permission(struct inode *inode, int mask)
 {
         /*
          * We don't do permission checks on the internal objects.
diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c
index 5e90a95ad60b..056008db1377 100644
--- a/fs/reiserfs/xattr_security.c
+++ b/fs/reiserfs/xattr_security.c
@@ -6,8 +6,6 @@
 #include <linux/reiserfs_xattr.h>
 #include <asm/uaccess.h>
 
-#define XATTR_SECURITY_PREFIX "security."
-
 static int
 security_get(struct inode *inode, const char *name, void *buffer, size_t size)
 {
diff --git a/fs/reiserfs/xattr_trusted.c b/fs/reiserfs/xattr_trusted.c
index 024a938ca60f..60abe2bb1f98 100644
--- a/fs/reiserfs/xattr_trusted.c
+++ b/fs/reiserfs/xattr_trusted.c
@@ -7,8 +7,6 @@
 #include <linux/reiserfs_xattr.h>
 #include <asm/uaccess.h>
 
-#define XATTR_TRUSTED_PREFIX "trusted."
-
 static int
 trusted_get(struct inode *inode, const char *name, void *buffer, size_t size)
 {
diff --git a/fs/reiserfs/xattr_user.c b/fs/reiserfs/xattr_user.c
index 073f39364b11..1384efcb938e 100644
--- a/fs/reiserfs/xattr_user.c
+++ b/fs/reiserfs/xattr_user.c
@@ -10,8 +10,6 @@
 # include <linux/reiserfs_acl.h>
 #endif
 
-#define XATTR_USER_PREFIX "user."
-
 static int
 user_get(struct inode *inode, const char *name, void *buffer, size_t size)
 {
diff --git a/fs/romfs/inode.c b/fs/romfs/inode.c
index 3f13d491c7c7..60d2f822e87b 100644
--- a/fs/romfs/inode.c
+++ b/fs/romfs/inode.c
@@ -418,7 +418,8 @@ static int
 romfs_readpage(struct file *file, struct page * page)
 {
         struct inode *inode = page->mapping->host;
-        loff_t offset, avail, readlen;
+        loff_t offset, size;
+        unsigned long filled;
         void *buf;
         int result = -EIO;
 
@@ -430,21 +431,29 @@ romfs_readpage(struct file *file, struct page * page)
 
         /* 32 bit warning -- but not for us :) */
         offset = page_offset(page);
-        if (offset < i_size_read(inode)) {
-                avail = inode->i_size-offset;
-                readlen = min_t(unsigned long, avail, PAGE_SIZE);
-                if (romfs_copyfrom(inode, buf, ROMFS_I(inode)->i_dataoffset+offset, readlen) == readlen) {
-                        if (readlen < PAGE_SIZE) {
-                                memset(buf + readlen,0,PAGE_SIZE-readlen);
-                        }
-                        SetPageUptodate(page);
-                        result = 0;
+        size = i_size_read(inode);
+        filled = 0;
+        result = 0;
+        if (offset < size) {
+                unsigned long readlen;
+
+                size -= offset;
+                readlen = size > PAGE_SIZE ? PAGE_SIZE : size;
+
+                filled = romfs_copyfrom(inode, buf, ROMFS_I(inode)->i_dataoffset+offset, readlen);
+
+                if (filled != readlen) {
+                        SetPageError(page);
+                        filled = 0;
+                        result = -EIO;
                 }
         }
-        if (result) {
-                memset(buf, 0, PAGE_SIZE);
-                SetPageError(page);
-        }
+
+        if (filled < PAGE_SIZE)
+                memset(buf + filled, 0, PAGE_SIZE-filled);
+
+        if (!result)
+                SetPageUptodate(page);
         flush_dcache_page(page);
 
         unlock_page(page);
@@ -577,7 +586,7 @@ static void romfs_destroy_inode(struct inode *inode)
         kmem_cache_free(romfs_inode_cachep, ROMFS_I(inode));
 }
 
-static void init_once(struct kmem_cache *cachep, void *foo)
+static void init_once(void *foo)
 {
         struct romfs_inode_info *ei = foo;
 
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 3f54dbd6c49b..5d54205e486b 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -443,6 +443,20 @@ int seq_dentry(struct seq_file *m, struct dentry *dentry, char *esc)
         return -1;
 }
 
+int seq_bitmap(struct seq_file *m, unsigned long *bits, unsigned int nr_bits)
+{
+        size_t len = bitmap_scnprintf_len(nr_bits);
+
+        if (m->count + len < m->size) {
+                bitmap_scnprintf(m->buf + m->count, m->size - m->count,
+                                 bits, nr_bits);
+                m->count += len;
+                return 0;
+        }
+        m->count = m->size;
+        return -1;
+}
+
 static void *single_start(struct seq_file *p, loff_t *pos)
 {
         return NULL + (*pos == 0);
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 619725644c75..9c39bc7f8431 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -205,11 +205,19 @@ static const struct file_operations signalfd_fops = {
         .read           = signalfd_read,
 };
 
-asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemask)
+asmlinkage long sys_signalfd4(int ufd, sigset_t __user *user_mask,
+                              size_t sizemask, int flags)
 {
         sigset_t sigmask;
         struct signalfd_ctx *ctx;
 
+        /* Check the SFD_* constants for consistency.  */
+        BUILD_BUG_ON(SFD_CLOEXEC != O_CLOEXEC);
+        BUILD_BUG_ON(SFD_NONBLOCK != O_NONBLOCK);
+
+        if (flags & ~(SFD_CLOEXEC | SFD_NONBLOCK))
+                return -EINVAL;
+
         if (sizemask != sizeof(sigset_t) ||
             copy_from_user(&sigmask, user_mask, sizeof(sigmask)))
                 return -EINVAL;
@@ -227,7 +235,8 @@ asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemas
                  * When we call this, the initialization must be complete, since
                  * anon_inode_getfd() will install the fd.
                  */
-                ufd = anon_inode_getfd("[signalfd]", &signalfd_fops, ctx);
+                ufd = anon_inode_getfd("[signalfd]", &signalfd_fops, ctx,
+                                       flags & (O_CLOEXEC | O_NONBLOCK));
                 if (ufd < 0)
                         kfree(ctx);
         } else {
@@ -249,3 +258,9 @@ asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemas
 
         return ufd;
 }
+
+asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask,
+                             size_t sizemask)
+{
+        return sys_signalfd4(ufd, user_mask, sizemask, 0);
+}
diff --git a/fs/smbfs/cache.c b/fs/smbfs/cache.c
index 8182f0542a21..8c177eb7e344 100644
--- a/fs/smbfs/cache.c
+++ b/fs/smbfs/cache.c
@@ -13,7 +13,6 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
-#include <linux/dirent.h>
 #include <linux/smb_fs.h>
 #include <linux/pagemap.h>
 #include <linux/net.h>
diff --git a/fs/smbfs/file.c b/fs/smbfs/file.c
index 2294783320cb..e4f8d51a5553 100644
--- a/fs/smbfs/file.c
+++ b/fs/smbfs/file.c
@@ -408,7 +408,7 @@ smb_file_release(struct inode *inode, struct file * file)
  * privileges, so we need our own check for this.
  */
 static int
-smb_file_permission(struct inode *inode, int mask, struct nameidata *nd)
+smb_file_permission(struct inode *inode, int mask)
 {
         int mode = inode->i_mode;
         int error = 0;
@@ -417,7 +417,7 @@ smb_file_permission(struct inode *inode, int mask, struct nameidata *nd)
 
         /* Look at user permissions */
         mode >>= 6;
-        if ((mode & 7 & mask) != mask)
+        if (mask & ~mode & (MAY_READ | MAY_WRITE | MAY_EXEC))
                 error = -EACCES;
         return error;
 }
diff --git a/fs/smbfs/inode.c b/fs/smbfs/inode.c
index 376ef3ee6ed7..3528f40ffb0f 100644
--- a/fs/smbfs/inode.c
+++ b/fs/smbfs/inode.c
@@ -67,7 +67,7 @@ static void smb_destroy_inode(struct inode *inode)
         kmem_cache_free(smb_inode_cachep, SMB_I(inode));
 }
 
-static void init_once(struct kmem_cache *cachep, void *foo)
+static void init_once(void *foo)
 {
         struct smb_inode_info *ei = (struct smb_inode_info *) foo;
 
diff --git a/fs/smbfs/proc.c b/fs/smbfs/proc.c
index d517a27b7f4b..ee536e8a649a 100644
--- a/fs/smbfs/proc.c
+++ b/fs/smbfs/proc.c
@@ -16,7 +16,6 @@
 #include <linux/stat.h>
 #include <linux/fcntl.h>
 #include <linux/dcache.h>
-#include <linux/dirent.h>
 #include <linux/nls.h>
 #include <linux/smp_lock.h>
 #include <linux/net.h>
diff --git a/fs/splice.c b/fs/splice.c
index 399442179d89..1bbc6f4bb09c 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -371,7 +371,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
                          * for an in-flight io page
                          */
                         if (flags & SPLICE_F_NONBLOCK) {
-                                if (TestSetPageLocked(page)) {
+                                if (!trylock_page(page)) {
                                         error = -EAGAIN;
                                         break;
                                 }
@@ -772,7 +772,7 @@ generic_file_splice_write_nolock(struct pipe_inode_info *pipe, struct file *out,
         ssize_t ret;
         int err;
 
-        err = remove_suid(out->f_path.dentry);
+        err = file_remove_suid(out);
         if (unlikely(err))
                 return err;
 
@@ -830,7 +830,7 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
         ssize_t ret;
 
         inode_double_lock(inode, pipe->inode);
-        ret = remove_suid(out->f_path.dentry);
+        ret = file_remove_suid(out);
         if (likely(!ret))
                 ret = __splice_from_pipe(pipe, &sd, pipe_to_file);
         inode_double_unlock(inode, pipe->inode);
@@ -1161,36 +1161,6 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 }
 
 /*
- * Do a copy-from-user while holding the mmap_semaphore for reading, in a
- * manner safe from deadlocking with simultaneous mmap() (grabbing mmap_sem
- * for writing) and page faulting on the user memory pointed to by src.
- * This assumes that we will very rarely hit the partial != 0 path, or this
- * will not be a win.
- */
-static int copy_from_user_mmap_sem(void *dst, const void __user *src, size_t n)
-{
-        int partial;
-
-        if (!access_ok(VERIFY_READ, src, n))
-                return -EFAULT;
-
-        pagefault_disable();
-        partial = __copy_from_user_inatomic(dst, src, n);
-        pagefault_enable();
-
-        /*
-         * Didn't copy everything, drop the mmap_sem and do a faulting copy
-         */
-        if (unlikely(partial)) {
-                up_read(&current->mm->mmap_sem);
-                partial = copy_from_user(dst, src, n);
-                down_read(&current->mm->mmap_sem);
-        }
-
-        return partial;
-}
-
-/*
  * Map an iov into an array of pages and offset/length tupples. With the
  * partial_page structure, we can map several non-contiguous ranges into
  * our ones pages[] map instead of splitting that operation into pieces.
@@ -1203,8 +1173,6 @@ static int get_iovec_page_array(const struct iovec __user *iov,
 {
         int buffers = 0, error = 0;
 
-        down_read(&current->mm->mmap_sem);
-
         while (nr_vecs) {
                 unsigned long off, npages;
                 struct iovec entry;
@@ -1213,7 +1181,7 @@ static int get_iovec_page_array(const struct iovec __user *iov,
                 int i;
 
                 error = -EFAULT;
-                if (copy_from_user_mmap_sem(&entry, iov, sizeof(entry)))
+                if (copy_from_user(&entry, iov, sizeof(entry)))
                         break;
 
                 base = entry.iov_base;
@@ -1247,9 +1215,8 @@ static int get_iovec_page_array(const struct iovec __user *iov,
                 if (npages > PIPE_BUFFERS - buffers)
                         npages = PIPE_BUFFERS - buffers;
 
-                error = get_user_pages(current, current->mm,
-                                       (unsigned long) base, npages, 0, 0,
-                                       &pages[buffers], NULL);
+                error = get_user_pages_fast((unsigned long)base, npages,
+                                        0, &pages[buffers]);
 
                 if (unlikely(error <= 0))
                         break;
@@ -1288,8 +1255,6 @@ static int get_iovec_page_array(const struct iovec __user *iov,
                 iov++;
         }
 
-        up_read(&current->mm->mmap_sem);
-
         if (buffers)
                 return buffers;
 
diff --git a/fs/stat.c b/fs/stat.c
index 9cf41f719d50..7c46fbeb8b76 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -57,13 +57,13 @@ EXPORT_SYMBOL(vfs_getattr);
 
 int vfs_stat_fd(int dfd, char __user *name, struct kstat *stat)
 {
-        struct nameidata nd;
+        struct path path;
         int error;
 
-        error = __user_walk_fd(dfd, name, LOOKUP_FOLLOW, &nd);
+        error = user_path_at(dfd, name, LOOKUP_FOLLOW, &path);
         if (!error) {
-                error = vfs_getattr(nd.path.mnt, nd.path.dentry, stat);
-                path_put(&nd.path);
+                error = vfs_getattr(path.mnt, path.dentry, stat);
+                path_put(&path);
         }
         return error;
 }
@@ -77,13 +77,13 @@ EXPORT_SYMBOL(vfs_stat);
 
 int vfs_lstat_fd(int dfd, char __user *name, struct kstat *stat)
 {
-        struct nameidata nd;
+        struct path path;
         int error;
 
-        error = __user_walk_fd(dfd, name, 0, &nd);
+        error = user_path_at(dfd, name, 0, &path);
         if (!error) {
-                error = vfs_getattr(nd.path.mnt, nd.path.dentry, stat);
-                path_put(&nd.path);
+                error = vfs_getattr(path.mnt, path.dentry, stat);
+                path_put(&path);
         }
         return error;
 }
@@ -291,29 +291,29 @@ asmlinkage long sys_newfstat(unsigned int fd, struct stat __user *statbuf)
         return error;
 }
 
-asmlinkage long sys_readlinkat(int dfd, const char __user *path,
+asmlinkage long sys_readlinkat(int dfd, const char __user *pathname,
                                 char __user *buf, int bufsiz)
 {
-        struct nameidata nd;
+        struct path path;
         int error;
 
         if (bufsiz <= 0)
                 return -EINVAL;
 
-        error = __user_walk_fd(dfd, path, 0, &nd);
+        error = user_path_at(dfd, pathname, 0, &path);
         if (!error) {
-                struct inode *inode = nd.path.dentry->d_inode;
+                struct inode *inode = path.dentry->d_inode;
 
                 error = -EINVAL;
                 if (inode->i_op && inode->i_op->readlink) {
-                        error = security_inode_readlink(nd.path.dentry);
+                        error = security_inode_readlink(path.dentry);
                         if (!error) {
-                                touch_atime(nd.path.mnt, nd.path.dentry);
-                                error = inode->i_op->readlink(nd.path.dentry,
+                                touch_atime(path.mnt, path.dentry);
+                                error = inode->i_op->readlink(path.dentry,
                                                               buf, bufsiz);
                         }
                 }
-                path_put(&nd.path);
+                path_put(&path);
         }
         return error;
 }
diff --git a/fs/super.c b/fs/super.c
index 453877c5697b..e931ae9511fe 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -70,6 +70,7 @@ static struct super_block *alloc_super(struct file_system_type *type)
                 INIT_LIST_HEAD(&s->s_instances);
                 INIT_HLIST_HEAD(&s->s_anon);
                 INIT_LIST_HEAD(&s->s_inodes);
+                INIT_LIST_HEAD(&s->s_dentry_lru);
                 init_rwsem(&s->s_umount);
                 mutex_init(&s->s_lock);
                 lockdep_set_class(&s->s_umount, &type->s_umount_key);
diff --git a/fs/sync.c b/fs/sync.c
index 228e17b5e9ee..2967562d416f 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -139,7 +139,8 @@ asmlinkage long sys_fdatasync(unsigned int fd)
  * before performing the write.
  *
  * SYNC_FILE_RANGE_WRITE: initiate writeout of all those dirty pages in the
- * range which are not presently under writeback.
+ * range which are not presently under writeback. Note that this may block for
+ * significant periods due to exhaustion of disk request structures.
  *
  * SYNC_FILE_RANGE_WAIT_AFTER: wait upon writeout of all pages in the range
  * after performing the write.
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 8c0e4b92574f..aedaeba82ae5 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -398,7 +398,7 @@ void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
 }
 
 /**
- *      sysfs_add_one - add sysfs_dirent to parent
+ *      __sysfs_add_one - add sysfs_dirent to parent without warning
  *      @acxt: addrm context to use
  *      @sd: sysfs_dirent to be added
  *
@@ -417,7 +417,7 @@ void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
  *      0 on success, -EEXIST if entry with the given name already
  *      exists.
  */
-int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
+int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
 {
         if (sysfs_find_dirent(acxt->parent_sd, sd->s_name))
                 return -EEXIST;
@@ -435,6 +435,36 @@ int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
 }
 
 /**
+ *      sysfs_add_one - add sysfs_dirent to parent
+ *      @acxt: addrm context to use
+ *      @sd: sysfs_dirent to be added
+ *
+ *      Get @acxt->parent_sd and set sd->s_parent to it and increment
+ *      nlink of parent inode if @sd is a directory and link into the
+ *      children list of the parent.
+ *
+ *      This function should be called between calls to
+ *      sysfs_addrm_start() and sysfs_addrm_finish() and should be
+ *      passed the same @acxt as passed to sysfs_addrm_start().
+ *
+ *      LOCKING:
+ *      Determined by sysfs_addrm_start().
+ *
+ *      RETURNS:
+ *      0 on success, -EEXIST if entry with the given name already
+ *      exists.
+ */
+int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
+{
+        int ret;
+
+        ret = __sysfs_add_one(acxt, sd);
+        WARN(ret == -EEXIST, KERN_WARNING "sysfs: duplicate filename '%s' "
+                       "can not be created\n", sd->s_name);
+        return ret;
+}
+
+/**
  *      sysfs_remove_one - remove sysfs_dirent from parent
  *      @acxt: addrm context to use
  *      @sd: sysfs_dirent to be removed
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index e7735f643cd1..c9e4e5091da1 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -14,6 +14,7 @@
 #include <linux/kobject.h>
 #include <linux/kallsyms.h>
 #include <linux/slab.h>
+#include <linux/fsnotify.h>
 #include <linux/namei.h>
 #include <linux/poll.h>
 #include <linux/list.h>
@@ -336,9 +337,8 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
         if (kobj->ktype && kobj->ktype->sysfs_ops)
                 ops = kobj->ktype->sysfs_ops;
         else {
-                printk(KERN_ERR "missing sysfs attribute operations for "
+                WARN(1, KERN_ERR "missing sysfs attribute operations for "
                        "kobject: %s\n", kobject_name(kobj));
-                WARN_ON(1);
                 goto err_out;
         }
 
@@ -585,9 +585,11 @@ int sysfs_chmod_file(struct kobject *kobj, struct attribute *attr, mode_t mode)
 
         newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
         newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
-        rc = notify_change(victim, &newattrs);
+        newattrs.ia_ctime = current_fs_time(inode->i_sb);
+        rc = sysfs_setattr(victim, &newattrs);
 
         if (rc == 0) {
+                fsnotify_change(victim, newattrs.ia_valid);
                 mutex_lock(&sysfs_mutex);
                 victim_sd->s_mode = newattrs.ia_mode;
                 mutex_unlock(&sysfs_mutex);
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index eeba38417b1d..fe611949a7f7 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -134,9 +134,8 @@ void sysfs_remove_group(struct kobject * kobj,
         if (grp->name) {
                 sd = sysfs_get_dirent(dir_sd, grp->name);
                 if (!sd) {
-                        printk(KERN_WARNING "sysfs group %p not found for "
+                        WARN(!sd, KERN_WARNING "sysfs group %p not found for "
                                 "kobject '%s'\n", grp, kobject_name(kobj));
-                        WARN_ON(!sd);
                         return;
                 }
         } else
diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c
index 817f5966edca..a3ba217fbe74 100644
--- a/fs/sysfs/symlink.c
+++ b/fs/sysfs/symlink.c
@@ -19,13 +19,8 @@
 
 #include "sysfs.h"
 
-/**
- *      sysfs_create_link - create symlink between two objects.
- *      @kobj:  object whose directory we're creating the link in.
- *      @target:        object we're pointing to.
- *      @name:          name of the symlink.
- */
-int sysfs_create_link(struct kobject * kobj, struct kobject * target, const char * name)
+static int sysfs_do_create_link(struct kobject *kobj, struct kobject *target,
+                                const char *name, int warn)
 {
         struct sysfs_dirent *parent_sd = NULL;
         struct sysfs_dirent *target_sd = NULL;
@@ -65,7 +60,10 @@ int sysfs_create_link(struct kobject * kobj, struct kobject * target, const char
         target_sd = NULL;       /* reference is now owned by the symlink */
 
         sysfs_addrm_start(&acxt, parent_sd);
-        error = sysfs_add_one(&acxt, sd);
+        if (warn)
+                error = sysfs_add_one(&acxt, sd);
+        else
+                error = __sysfs_add_one(&acxt, sd);
         sysfs_addrm_finish(&acxt);
 
         if (error)
@@ -80,6 +78,33 @@ int sysfs_create_link(struct kobject * kobj, struct kobject * target, const char
 }
 
 /**
+ *      sysfs_create_link - create symlink between two objects.
+ *      @kobj:  object whose directory we're creating the link in.
+ *      @target:        object we're pointing to.
+ *      @name:          name of the symlink.
+ */
+int sysfs_create_link(struct kobject *kobj, struct kobject *target,
+                      const char *name)
+{
+        return sysfs_do_create_link(kobj, target, name, 1);
+}
+
+/**
+ *      sysfs_create_link_nowarn - create symlink between two objects.
+ *      @kobj:  object whose directory we're creating the link in.
+ *      @target:        object we're pointing to.
+ *      @name:          name of the symlink.
+ *
+ *      This function does the same as sysf_create_link(), but it
+ *      doesn't warn if the link already exists.
+ */
+int sysfs_create_link_nowarn(struct kobject *kobj, struct kobject *target,
+                             const char *name)
+{
+        return sysfs_do_create_link(kobj, target, name, 0);
+}
+
+/**
  *      sysfs_remove_link - remove symlink in object's directory.
  *      @kobj:  object we're acting for.
  *      @name:  name of the symlink to remove.
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index ce4e15f8aaeb..a5db496f71c7 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -107,6 +107,7 @@ struct sysfs_dirent *sysfs_get_active_two(struct sysfs_dirent *sd);
 void sysfs_put_active_two(struct sysfs_dirent *sd);
 void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
                        struct sysfs_dirent *parent_sd);
+int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd);
 int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd);
 void sysfs_remove_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd);
 void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt);
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index c5d60de0658f..df0d435baa48 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -326,7 +326,7 @@ static void sysv_destroy_inode(struct inode *inode)
         kmem_cache_free(sysv_inode_cachep, SYSV_I(inode));
 }
 
-static void init_once(struct kmem_cache *cachep, void *p)
+static void init_once(void *p)
 {
         struct sysv_inode_info *si = (struct sysv_inode_info *)p;
 
diff --git a/fs/timerfd.c b/fs/timerfd.c
index d87d354ec424..c502c60e4f54 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -184,7 +184,11 @@ asmlinkage long sys_timerfd_create(int clockid, int flags)
         int ufd;
         struct timerfd_ctx *ctx;
 
-        if (flags)
+        /* Check the TFD_* constants for consistency.  */
+        BUILD_BUG_ON(TFD_CLOEXEC != O_CLOEXEC);
+        BUILD_BUG_ON(TFD_NONBLOCK != O_NONBLOCK);
+
+        if (flags & ~(TFD_CLOEXEC | TFD_NONBLOCK))
                 return -EINVAL;
         if (clockid != CLOCK_MONOTONIC &&
             clockid != CLOCK_REALTIME)
@@ -198,7 +202,8 @@ asmlinkage long sys_timerfd_create(int clockid, int flags)
         ctx->clockid = clockid;
         hrtimer_init(&ctx->tmr, clockid, HRTIMER_MODE_ABS);
 
-        ufd = anon_inode_getfd("[timerfd]", &timerfd_fops, ctx);
+        ufd = anon_inode_getfd("[timerfd]", &timerfd_fops, ctx,
+                               flags & (O_CLOEXEC | O_NONBLOCK));
         if (ufd < 0)
                 kfree(ctx);
 
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 005a3b854d96..8565e586e533 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -53,6 +53,7 @@
 
 #include "ubifs.h"
 #include <linux/mount.h>
+#include <linux/namei.h>
 
 static int read_block(struct inode *inode, void *addr, unsigned int block,
                       struct ubifs_data_node *dn)
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 00eb9c68ad03..ca1e2d4e03cc 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1841,7 +1841,7 @@ static struct file_system_type ubifs_fs_type = {
 /*
  * Inode slab cache constructor.
  */
-static void inode_slab_ctor(struct kmem_cache *cachep, void *obj)
+static void inode_slab_ctor(void *obj)
 {
         struct ubifs_inode *ui = obj;
         inode_init_once(&ui->vfs_inode);
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 44cc702f96cc..5698bbf83bbf 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -148,7 +148,7 @@ static void udf_destroy_inode(struct inode *inode)
         kmem_cache_free(udf_inode_cachep, UDF_I(inode));
 }
 
-static void init_once(struct kmem_cache *cachep, void *foo)
+static void init_once(void *foo)
 {
         struct udf_inode_info *ei = (struct udf_inode_info *)foo;
 
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index 85b22b5977fa..3141969b456d 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -76,6 +76,7 @@
 
 #include <linux/errno.h>
 #include <linux/fs.h>
+#include <linux/quotaops.h>
 #include <linux/slab.h>
 #include <linux/time.h>
 #include <linux/stat.h>
@@ -1301,7 +1302,7 @@ static void ufs_destroy_inode(struct inode *inode)
         kmem_cache_free(ufs_inode_cachep, UFS_I(inode));
 }
 
-static void init_once(struct kmem_cache * cachep, void *foo)
+static void init_once(void *foo)
 {
         struct ufs_inode_info *ei = (struct ufs_inode_info *) foo;
 
diff --git a/fs/utimes.c b/fs/utimes.c
index b6b664e7145e..6929e3e91d05 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -48,66 +48,22 @@ static bool nsec_valid(long nsec)
         return nsec >= 0 && nsec <= 999999999;
 }
 
-/* If times==NULL, set access and modification to current time,
- * must be owner or have write permission.
- * Else, update from *times, must be owner or super user.
- */
-long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags)
+static int utimes_common(struct path *path, struct timespec *times)
 {
         int error;
-        struct nameidata nd;
-        struct dentry *dentry;
-        struct inode *inode;
         struct iattr newattrs;
-        struct file *f = NULL;
-        struct vfsmount *mnt;
-
-        error = -EINVAL;
-        if (times && (!nsec_valid(times[0].tv_nsec) ||
-                      !nsec_valid(times[1].tv_nsec))) {
-                goto out;
-        }
-
-        if (flags & ~AT_SYMLINK_NOFOLLOW)
-                goto out;
-
-        if (filename == NULL && dfd != AT_FDCWD) {
-                error = -EINVAL;
-                if (flags & AT_SYMLINK_NOFOLLOW)
-                        goto out;
+        struct inode *inode = path->dentry->d_inode;
 
-                error = -EBADF;
-                f = fget(dfd);
-                if (!f)
-                        goto out;
-                dentry = f->f_path.dentry;
-                mnt = f->f_path.mnt;
-        } else {
-                error = __user_walk_fd(dfd, filename, (flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW, &nd);
-                if (error)
-                        goto out;
-
-                dentry = nd.path.dentry;
-                mnt = nd.path.mnt;
-        }
-
-        inode = dentry->d_inode;
-
-        error = mnt_want_write(mnt);
+        error = mnt_want_write(path->mnt);
         if (error)
-                goto dput_and_out;
+                goto out;
 
         if (times && times[0].tv_nsec == UTIME_NOW &&
                      times[1].tv_nsec == UTIME_NOW)
                 times = NULL;
 
-        /* In most cases, the checks are done in inode_change_ok() */
         newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME;
         if (times) {
-                error = -EPERM;
-                if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
-                        goto mnt_drop_write_and_out;
-
                 if (times[0].tv_nsec == UTIME_OMIT)
                         newattrs.ia_valid &= ~ATTR_ATIME;
                 else if (times[0].tv_nsec != UTIME_NOW) {
@@ -123,21 +79,13 @@ long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags
                         newattrs.ia_mtime.tv_nsec = times[1].tv_nsec;
                         newattrs.ia_valid |= ATTR_MTIME_SET;
                 }
-
                 /*
-                 * For the UTIME_OMIT/UTIME_NOW and UTIME_NOW/UTIME_OMIT
-                 * cases, we need to make an extra check that is not done by
-                 * inode_change_ok().
+                 * Tell inode_change_ok(), that this is an explicit time
+                 * update, even if neither ATTR_ATIME_SET nor ATTR_MTIME_SET
+                 * were used.
                  */
-                if (((times[0].tv_nsec == UTIME_NOW &&
-                            times[1].tv_nsec == UTIME_OMIT)
-                     ||
-                     (times[0].tv_nsec == UTIME_OMIT &&
-                            times[1].tv_nsec == UTIME_NOW))
-                    && !is_owner_or_cap(inode))
-                        goto mnt_drop_write_and_out;
+                newattrs.ia_valid |= ATTR_TIMES_SET;
         } else {
-
                 /*
                  * If times is NULL (or both times are UTIME_NOW),
                  * then we need to check permissions, because
@@ -148,21 +96,76 @@ long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags
                         goto mnt_drop_write_and_out;
 
                 if (!is_owner_or_cap(inode)) {
-                        error = permission(inode, MAY_WRITE, NULL);
+                        error = inode_permission(inode, MAY_WRITE);
                         if (error)
                                 goto mnt_drop_write_and_out;
                 }
         }
         mutex_lock(&inode->i_mutex);
-        error = notify_change(dentry, &newattrs);
+        error = notify_change(path->dentry, &newattrs);
         mutex_unlock(&inode->i_mutex);
+
 mnt_drop_write_and_out:
-        mnt_drop_write(mnt);
-dput_and_out:
-        if (f)
-                fput(f);
-        else
-                path_put(&nd.path);
+        mnt_drop_write(path->mnt);
+out:
+        return error;
+}
+
+/*
+ * do_utimes - change times on filename or file descriptor
+ * @dfd: open file descriptor, -1 or AT_FDCWD
+ * @filename: path name or NULL
+ * @times: new times or NULL
+ * @flags: zero or more flags (only AT_SYMLINK_NOFOLLOW for the moment)
+ *
+ * If filename is NULL and dfd refers to an open file, then operate on
+ * the file.  Otherwise look up filename, possibly using dfd as a
+ * starting point.
+ *
+ * If times==NULL, set access and modification to current time,
+ * must be owner or have write permission.
+ * Else, update from *times, must be owner or super user.
+ */
+long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags)
+{
+        int error = -EINVAL;
+
+        if (times && (!nsec_valid(times[0].tv_nsec) ||
+                      !nsec_valid(times[1].tv_nsec))) {
+                goto out;
+        }
+
+        if (flags & ~AT_SYMLINK_NOFOLLOW)
+                goto out;
+
+        if (filename == NULL && dfd != AT_FDCWD) {
+                struct file *file;
+
+                if (flags & AT_SYMLINK_NOFOLLOW)
+                        goto out;
+
+                file = fget(dfd);
+                error = -EBADF;
+                if (!file)
+                        goto out;
+
+                error = utimes_common(&file->f_path, times);
+                fput(file);
+        } else {
+                struct path path;
+                int lookup_flags = 0;
+
+                if (!(flags & AT_SYMLINK_NOFOLLOW))
+                        lookup_flags |= LOOKUP_FOLLOW;
+
+                error = user_path_at(dfd, filename, lookup_flags, &path);
+                if (error)
+                        goto out;
+
+                error = utimes_common(&path, times);
+                path_put(&path);
+        }
+
 out:
         return error;
 }
diff --git a/fs/vfat/namei.c b/fs/vfat/namei.c
index b546ba69be82..155c10b4adbd 100644
--- a/fs/vfat/namei.c
+++ b/fs/vfat/namei.c
@@ -621,7 +621,7 @@ shortname:
         memcpy(de->name, msdos_name, MSDOS_NAME);
         de->attr = is_dir ? ATTR_DIR : ATTR_ARCH;
         de->lcase = lcase;
-        fat_date_unix2dos(ts->tv_sec, &time, &date);
+        fat_date_unix2dos(ts->tv_sec, &time, &date, sbi->options.tz_utc);
         de->time = de->ctime = time;
         de->date = de->cdate = de->adate = date;
         de->ctime_cs = 0;
diff --git a/fs/xattr.c b/fs/xattr.c
index 4706a8b1f495..468377e66531 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -63,7 +63,7 @@ xattr_permission(struct inode *inode, const char *name, int mask)
                         return -EPERM;
         }
 
-        return permission(inode, mask, NULL);
+        return inode_permission(inode, mask);
 }
 
 int
@@ -252,40 +252,40 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value,
 }
 
 asmlinkage long
-sys_setxattr(const char __user *path, const char __user *name,
+sys_setxattr(const char __user *pathname, const char __user *name,
              const void __user *value, size_t size, int flags)
 {
-        struct nameidata nd;
+        struct path path;
         int error;
 
-        error = user_path_walk(path, &nd);
+        error = user_path(pathname, &path);
         if (error)
                 return error;
-        error = mnt_want_write(nd.path.mnt);
+        error = mnt_want_write(path.mnt);
         if (!error) {
-                error = setxattr(nd.path.dentry, name, value, size, flags);
-                mnt_drop_write(nd.path.mnt);
+                error = setxattr(path.dentry, name, value, size, flags);
+                mnt_drop_write(path.mnt);
         }
-        path_put(&nd.path);
+        path_put(&path);
         return error;
 }
 
 asmlinkage long
-sys_lsetxattr(const char __user *path, const char __user *name,
+sys_lsetxattr(const char __user *pathname, const char __user *name,
               const void __user *value, size_t size, int flags)
 {
-        struct nameidata nd;
+        struct path path;
         int error;
 
-        error = user_path_walk_link(path, &nd);
+        error = user_lpath(pathname, &path);
         if (error)
                 return error;
-        error = mnt_want_write(nd.path.mnt);
+        error = mnt_want_write(path.mnt);
         if (!error) {
-                error = setxattr(nd.path.dentry, name, value, size, flags);
-                mnt_drop_write(nd.path.mnt);
+                error = setxattr(path.dentry, name, value, size, flags);
+                mnt_drop_write(path.mnt);
         }
-        path_put(&nd.path);
+        path_put(&path);
         return error;
 }
 
@@ -350,32 +350,32 @@ getxattr(struct dentry *d, const char __user *name, void __user *value,
 }
 
 asmlinkage ssize_t
-sys_getxattr(const char __user *path, const char __user *name,
+sys_getxattr(const char __user *pathname, const char __user *name,
              void __user *value, size_t size)
 {
-        struct nameidata nd;
+        struct path path;
         ssize_t error;
 
-        error = user_path_walk(path, &nd);
+        error = user_path(pathname, &path);
         if (error)
                 return error;
-        error = getxattr(nd.path.dentry, name, value, size);
-        path_put(&nd.path);
+        error = getxattr(path.dentry, name, value, size);
+        path_put(&path);
         return error;
 }
 
 asmlinkage ssize_t
-sys_lgetxattr(const char __user *path, const char __user *name, void __user *value,
+sys_lgetxattr(const char __user *pathname, const char __user *name, void __user *value,
               size_t size)
 {
-        struct nameidata nd;
+        struct path path;
         ssize_t error;
 
-        error = user_path_walk_link(path, &nd);
+        error = user_lpath(pathname, &path);
         if (error)
                 return error;
-        error = getxattr(nd.path.dentry, name, value, size);
-        path_put(&nd.path);
+        error = getxattr(path.dentry, name, value, size);
+        path_put(&path);
         return error;
 }
 
@@ -425,30 +425,30 @@ listxattr(struct dentry *d, char __user *list, size_t size)
 }
 
 asmlinkage ssize_t
-sys_listxattr(const char __user *path, char __user *list, size_t size)
+sys_listxattr(const char __user *pathname, char __user *list, size_t size)
 {
-        struct nameidata nd;
+        struct path path;
         ssize_t error;
 
-        error = user_path_walk(path, &nd);
+        error = user_path(pathname, &path);
         if (error)
                 return error;
-        error = listxattr(nd.path.dentry, list, size);
-        path_put(&nd.path);
+        error = listxattr(path.dentry, list, size);
+        path_put(&path);
         return error;
 }
 
 asmlinkage ssize_t
-sys_llistxattr(const char __user *path, char __user *list, size_t size)
+sys_llistxattr(const char __user *pathname, char __user *list, size_t size)
 {
-        struct nameidata nd;
+        struct path path;
         ssize_t error;
 
-        error = user_path_walk_link(path, &nd);
+        error = user_lpath(pathname, &path);
         if (error)
                 return error;
-        error = listxattr(nd.path.dentry, list, size);
-        path_put(&nd.path);
+        error = listxattr(path.dentry, list, size);
+        path_put(&path);
         return error;
 }
 
@@ -486,38 +486,38 @@ removexattr(struct dentry *d, const char __user *name)
 }
 
 asmlinkage long
-sys_removexattr(const char __user *path, const char __user *name)
+sys_removexattr(const char __user *pathname, const char __user *name)
 {
-        struct nameidata nd;
+        struct path path;
         int error;
 
-        error = user_path_walk(path, &nd);
+        error = user_path(pathname, &path);
         if (error)
                 return error;
-        error = mnt_want_write(nd.path.mnt);
+        error = mnt_want_write(path.mnt);
         if (!error) {
-                error = removexattr(nd.path.dentry, name);
-                mnt_drop_write(nd.path.mnt);
+                error = removexattr(path.dentry, name);
+                mnt_drop_write(path.mnt);
         }
-        path_put(&nd.path);
+        path_put(&path);
         return error;
 }
 
 asmlinkage long
-sys_lremovexattr(const char __user *path, const char __user *name)
+sys_lremovexattr(const char __user *pathname, const char __user *name)
 {
-        struct nameidata nd;
+        struct path path;
         int error;
 
-        error = user_path_walk_link(path, &nd);
+        error = user_lpath(pathname, &path);
         if (error)
                 return error;
-        error = mnt_want_write(nd.path.mnt);
+        error = mnt_want_write(path.mnt);
         if (!error) {
-                error = removexattr(nd.path.dentry, name);
-                mnt_drop_write(nd.path.mnt);
+                error = removexattr(path.dentry, name);
+                mnt_drop_write(path.mnt);
         }
-        path_put(&nd.path);
+        path_put(&path);
         return error;
 }
 
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 36ec614e699a..737c9a425361 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -106,7 +106,8 @@ xfs-y				+= $(addprefix $(XFS_LINUX)/, \
                                    xfs_iops.o \
                                    xfs_lrw.o \
                                    xfs_super.o \
-                                   xfs_vnode.o)
+                                   xfs_vnode.o \
+                                   xfs_xattr.o)
 
 # Objects in support/
 xfs-y                           += $(addprefix support/, \
diff --git a/fs/xfs/linux-2.6/kmem.c b/fs/xfs/linux-2.6/kmem.c
index 9b1bb17a0501..1cd3b55ee3d2 100644
--- a/fs/xfs/linux-2.6/kmem.c
+++ b/fs/xfs/linux-2.6/kmem.c
@@ -90,7 +90,7 @@ kmem_zalloc_greedy(size_t *size, size_t minsize, size_t maxsize,
 }
 
 void
-kmem_free(void *ptr, size_t size)
+kmem_free(const void *ptr)
 {
         if (!is_vmalloc_addr(ptr)) {
                 kfree(ptr);
@@ -100,7 +100,7 @@ kmem_free(void *ptr, size_t size)
 }
 
 void *
-kmem_realloc(void *ptr, size_t newsize, size_t oldsize,
+kmem_realloc(const void *ptr, size_t newsize, size_t oldsize,
              unsigned int __nocast flags)
 {
         void    *new;
@@ -110,7 +110,7 @@ kmem_realloc(void *ptr, size_t newsize, size_t oldsize,
                 if (new)
                         memcpy(new, ptr,
                                 ((oldsize < newsize) ? oldsize : newsize));
-                kmem_free(ptr, oldsize);
+                kmem_free(ptr);
         }
         return new;
 }
diff --git a/fs/xfs/linux-2.6/kmem.h b/fs/xfs/linux-2.6/kmem.h
index 5e9564902976..af6843c7ee4b 100644
--- a/fs/xfs/linux-2.6/kmem.h
+++ b/fs/xfs/linux-2.6/kmem.h
@@ -57,8 +57,8 @@ kmem_flags_convert(unsigned int __nocast flags)
 extern void *kmem_alloc(size_t, unsigned int __nocast);
 extern void *kmem_zalloc(size_t, unsigned int __nocast);
 extern void *kmem_zalloc_greedy(size_t *, size_t, size_t, unsigned int __nocast);
-extern void *kmem_realloc(void *, size_t, size_t, unsigned int __nocast);
-extern void  kmem_free(void *, size_t);
+extern void *kmem_realloc(const void *, size_t, size_t, unsigned int __nocast);
+extern void  kmem_free(const void *);
 
 /*
  * Zone interfaces
@@ -79,7 +79,7 @@ kmem_zone_init(int size, char *zone_name)
 
 static inline kmem_zone_t *
 kmem_zone_init_flags(int size, char *zone_name, unsigned long flags,
-                     void (*construct)(kmem_zone_t *, void *))
+                     void (*construct)(void *))
 {
         return kmem_cache_create(zone_name, size, 0, flags, construct);
 }
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index a55c3b26d840..fa47e43b8b41 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -409,7 +409,6 @@ xfs_start_buffer_writeback(
 STATIC void
 xfs_start_page_writeback(
         struct page             *page,
-        struct writeback_control *wbc,
         int                     clear_dirty,
         int                     buffers)
 {
@@ -676,7 +675,7 @@ xfs_probe_cluster(
                         } else
                                 pg_offset = PAGE_CACHE_SIZE;
 
-                        if (page->index == tindex && !TestSetPageLocked(page)) {
+                        if (page->index == tindex && trylock_page(page)) {
                                 pg_len = xfs_probe_page(page, pg_offset, mapped);
                                 unlock_page(page);
                         }
@@ -760,7 +759,7 @@ xfs_convert_page(
 
         if (page->index != tindex)
                 goto fail;
-        if (TestSetPageLocked(page))
+        if (!trylock_page(page))
                 goto fail;
         if (PageWriteback(page))
                 goto fail_unlock_page;
@@ -858,7 +857,7 @@ xfs_convert_page(
                                 done = 1;
                         }
                 }
-                xfs_start_page_writeback(page, wbc, !page_dirty, count);
+                xfs_start_page_writeback(page, !page_dirty, count);
         }
 
         return done;
@@ -1105,7 +1104,7 @@ xfs_page_state_convert(
                          * that we are writing into for the first time.
                          */
                         type = IOMAP_NEW;
-                        if (!test_and_set_bit(BH_Lock, &bh->b_state)) {
+                        if (trylock_buffer(bh)) {
                                 ASSERT(buffer_mapped(bh));
                                 if (iomap_valid)
                                         all_bh = 1;
@@ -1130,7 +1129,7 @@ xfs_page_state_convert(
                 SetPageUptodate(page);
 
         if (startio)
-                xfs_start_page_writeback(page, wbc, 1, count);
+                xfs_start_page_writeback(page, 1, count);
 
         if (ioend && iomap_valid) {
                 offset = (iomap.iomap_offset + iomap.iomap_bsize - 1) >>
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 98e0e86093b4..9cc8f0213095 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -310,8 +310,7 @@ _xfs_buf_free_pages(
         xfs_buf_t       *bp)
 {
         if (bp->b_pages != bp->b_page_array) {
-                kmem_free(bp->b_pages,
-                          bp->b_page_count * sizeof(struct page *));
+                kmem_free(bp->b_pages);
         }
 }
 
@@ -1398,7 +1397,7 @@ STATIC void
 xfs_free_bufhash(
         xfs_buftarg_t           *btp)
 {
-        kmem_free(btp->bt_hash, (1<<btp->bt_hashshift) * sizeof(xfs_bufhash_t));
+        kmem_free(btp->bt_hash);
         btp->bt_hash = NULL;
 }
 
@@ -1428,13 +1427,10 @@ xfs_unregister_buftarg(
 
 void
 xfs_free_buftarg(
-        xfs_buftarg_t           *btp,
-        int                     external)
+        xfs_buftarg_t           *btp)
 {
         xfs_flush_buftarg(btp, 1);
         xfs_blkdev_issue_flush(btp);
-        if (external)
-                xfs_blkdev_put(btp->bt_bdev);
         xfs_free_bufhash(btp);
         iput(btp->bt_mapping->host);
 
@@ -1444,7 +1440,7 @@ xfs_free_buftarg(
         xfs_unregister_buftarg(btp);
         kthread_stop(btp->bt_task);
 
-        kmem_free(btp, sizeof(*btp));
+        kmem_free(btp);
 }
 
 STATIC int
@@ -1575,7 +1571,7 @@ xfs_alloc_buftarg(
         return btp;
 
 error:
-        kmem_free(btp, sizeof(*btp));
+        kmem_free(btp);
         return NULL;
 }
 
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index f948ec7ba9a4..29d1d4adc078 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -429,7 +429,7 @@ static inline void xfs_bdwrite(void *mp, xfs_buf_t *bp)
  *      Handling of buftargs.
  */
 extern xfs_buftarg_t *xfs_alloc_buftarg(struct block_device *, int);
-extern void xfs_free_buftarg(xfs_buftarg_t *, int);
+extern void xfs_free_buftarg(xfs_buftarg_t *);
 extern void xfs_wait_buftarg(xfs_buftarg_t *);
 extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int, unsigned int);
 extern int xfs_flush_buftarg(xfs_buftarg_t *, int);
diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/linux-2.6/xfs_export.c
index c672b3238b14..987fe84f7b13 100644
--- a/fs/xfs/linux-2.6/xfs_export.c
+++ b/fs/xfs/linux-2.6/xfs_export.c
@@ -215,7 +215,7 @@ xfs_fs_get_parent(
         struct xfs_inode        *cip;
         struct dentry           *parent;
 
-        error = xfs_lookup(XFS_I(child->d_inode), &xfs_name_dotdot, &cip);
+        error = xfs_lookup(XFS_I(child->d_inode), &xfs_name_dotdot, &cip, NULL);
         if (unlikely(error))
                 return ERR_PTR(-error);
 
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c
index a42ba9d71156..acb978d9d085 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl.c
@@ -48,6 +48,8 @@
 #include "xfs_dfrag.h"
 #include "xfs_fsops.h"
 #include "xfs_vnodeops.h"
+#include "xfs_quota.h"
+#include "xfs_inode_item.h"
 
 #include <linux/capability.h>
 #include <linux/dcache.h>
@@ -84,17 +86,15 @@ xfs_find_handle(
         switch (cmd) {
         case XFS_IOC_PATH_TO_FSHANDLE:
         case XFS_IOC_PATH_TO_HANDLE: {
-                struct nameidata        nd;
-                int                     error;
-
-                error = user_path_walk_link((const char __user *)hreq.path, &nd);
+                struct path path;
+                int error = user_lpath((const char __user *)hreq.path, &path);
                 if (error)
                         return error;
 
-                ASSERT(nd.path.dentry);
-                ASSERT(nd.path.dentry->d_inode);
-                inode = igrab(nd.path.dentry->d_inode);
-                path_put(&nd.path);
+                ASSERT(path.dentry);
+                ASSERT(path.dentry->d_inode);
+                inode = igrab(path.dentry->d_inode);
+                path_put(&path);
                 break;
         }
 
@@ -470,6 +470,12 @@ xfs_attrlist_by_handle(
         if (al_hreq.buflen > XATTR_LIST_MAX)
                 return -XFS_ERROR(EINVAL);
 
+        /*
+         * Reject flags, only allow namespaces.
+         */
+        if (al_hreq.flags & ~(ATTR_ROOT | ATTR_SECURE))
+                return -XFS_ERROR(EINVAL);
+
         error = xfs_vget_fsop_handlereq(mp, parinode, &al_hreq.hreq, &inode);
         if (error)
                 goto out;
@@ -589,7 +595,7 @@ xfs_attrmulti_by_handle(
                 goto out;
 
         error = E2BIG;
-        size = am_hreq.opcount * sizeof(attr_multiop_t);
+        size = am_hreq.opcount * sizeof(xfs_attr_multiop_t);
         if (!size || size > 16 * PAGE_SIZE)
                 goto out_vn_rele;
 
@@ -682,9 +688,9 @@ xfs_ioc_space(
                 return -XFS_ERROR(EFAULT);
 
         if (filp->f_flags & (O_NDELAY|O_NONBLOCK))
-                attr_flags |= ATTR_NONBLOCK;
+                attr_flags |= XFS_ATTR_NONBLOCK;
         if (ioflags & IO_INVIS)
-                attr_flags |= ATTR_DMI;
+                attr_flags |= XFS_ATTR_DMI;
 
         error = xfs_change_file_space(ip, cmd, &bf, filp->f_pos,
                                               NULL, attr_flags);
@@ -875,6 +881,322 @@ xfs_ioc_fsgetxattr(
         return 0;
 }
 
+STATIC void
+xfs_set_diflags(
+        struct xfs_inode        *ip,
+        unsigned int            xflags)
+{
+        unsigned int            di_flags;
+
+        /* can't set PREALLOC this way, just preserve it */
+        di_flags = (ip->i_d.di_flags & XFS_DIFLAG_PREALLOC);
+        if (xflags & XFS_XFLAG_IMMUTABLE)
+                di_flags |= XFS_DIFLAG_IMMUTABLE;
+        if (xflags & XFS_XFLAG_APPEND)
+                di_flags |= XFS_DIFLAG_APPEND;
+        if (xflags & XFS_XFLAG_SYNC)
+                di_flags |= XFS_DIFLAG_SYNC;
+        if (xflags & XFS_XFLAG_NOATIME)
+                di_flags |= XFS_DIFLAG_NOATIME;
+        if (xflags & XFS_XFLAG_NODUMP)
+                di_flags |= XFS_DIFLAG_NODUMP;
+        if (xflags & XFS_XFLAG_PROJINHERIT)
+                di_flags |= XFS_DIFLAG_PROJINHERIT;
+        if (xflags & XFS_XFLAG_NODEFRAG)
+                di_flags |= XFS_DIFLAG_NODEFRAG;
+        if (xflags & XFS_XFLAG_FILESTREAM)
+                di_flags |= XFS_DIFLAG_FILESTREAM;
+        if ((ip->i_d.di_mode & S_IFMT) == S_IFDIR) {
+                if (xflags & XFS_XFLAG_RTINHERIT)
+                        di_flags |= XFS_DIFLAG_RTINHERIT;
+                if (xflags & XFS_XFLAG_NOSYMLINKS)
+                        di_flags |= XFS_DIFLAG_NOSYMLINKS;
+                if (xflags & XFS_XFLAG_EXTSZINHERIT)
+                        di_flags |= XFS_DIFLAG_EXTSZINHERIT;
+        } else if ((ip->i_d.di_mode & S_IFMT) == S_IFREG) {
+                if (xflags & XFS_XFLAG_REALTIME)
+                        di_flags |= XFS_DIFLAG_REALTIME;
+                if (xflags & XFS_XFLAG_EXTSIZE)
+                        di_flags |= XFS_DIFLAG_EXTSIZE;
+        }
+
+        ip->i_d.di_flags = di_flags;
+}
+
+STATIC void
+xfs_diflags_to_linux(
+        struct xfs_inode        *ip)
+{
+        struct inode            *inode = XFS_ITOV(ip);
+        unsigned int            xflags = xfs_ip2xflags(ip);
+
+        if (xflags & XFS_XFLAG_IMMUTABLE)
+                inode->i_flags |= S_IMMUTABLE;
+        else
+                inode->i_flags &= ~S_IMMUTABLE;
+        if (xflags & XFS_XFLAG_APPEND)
+                inode->i_flags |= S_APPEND;
+        else
+                inode->i_flags &= ~S_APPEND;
+        if (xflags & XFS_XFLAG_SYNC)
+                inode->i_flags |= S_SYNC;
+        else
+                inode->i_flags &= ~S_SYNC;
+        if (xflags & XFS_XFLAG_NOATIME)
+                inode->i_flags |= S_NOATIME;
+        else
+                inode->i_flags &= ~S_NOATIME;
+}
+
+#define FSX_PROJID      1
+#define FSX_EXTSIZE     2
+#define FSX_XFLAGS      4
+#define FSX_NONBLOCK    8
+
+STATIC int
+xfs_ioctl_setattr(
+        xfs_inode_t             *ip,
+        struct fsxattr          *fa,
+        int                     mask)
+{
+        struct xfs_mount        *mp = ip->i_mount;
+        struct xfs_trans        *tp;
+        unsigned int            lock_flags = 0;
+        struct xfs_dquot        *udqp = NULL, *gdqp = NULL;
+        struct xfs_dquot        *olddquot = NULL;
+        int                     code;
+
+        xfs_itrace_entry(ip);
+
+        if (mp->m_flags & XFS_MOUNT_RDONLY)
+                return XFS_ERROR(EROFS);
+        if (XFS_FORCED_SHUTDOWN(mp))
+                return XFS_ERROR(EIO);
+
+        /*
+         * If disk quotas is on, we make sure that the dquots do exist on disk,
+         * before we start any other transactions. Trying to do this later
+         * is messy. We don't care to take a readlock to look at the ids
+         * in inode here, because we can't hold it across the trans_reserve.
+         * If the IDs do change before we take the ilock, we're covered
+         * because the i_*dquot fields will get updated anyway.
+         */
+        if (XFS_IS_QUOTA_ON(mp) && (mask & FSX_PROJID)) {
+                code = XFS_QM_DQVOPALLOC(mp, ip, ip->i_d.di_uid,
+                                         ip->i_d.di_gid, fa->fsx_projid,
+                                         XFS_QMOPT_PQUOTA, &udqp, &gdqp);
+                if (code)
+                        return code;
+        }
+
+        /*
+         * For the other attributes, we acquire the inode lock and
+         * first do an error checking pass.
+         */
+        tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
+        code = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
+        if (code)
+                goto error_return;
+
+        lock_flags = XFS_ILOCK_EXCL;
+        xfs_ilock(ip, lock_flags);
+
+        /*
+         * CAP_FOWNER overrides the following restrictions:
+         *
+         * The user ID of the calling process must be equal
+         * to the file owner ID, except in cases where the
+         * CAP_FSETID capability is applicable.
+         */
+        if (current->fsuid != ip->i_d.di_uid && !capable(CAP_FOWNER)) {
+                code = XFS_ERROR(EPERM);
+                goto error_return;
+        }
+
+        /*
+         * Do a quota reservation only if projid is actually going to change.
+         */
+        if (mask & FSX_PROJID) {
+                if (XFS_IS_PQUOTA_ON(mp) &&
+                    ip->i_d.di_projid != fa->fsx_projid) {
+                        ASSERT(tp);
+                        code = XFS_QM_DQVOPCHOWNRESV(mp, tp, ip, udqp, gdqp,
+                                                capable(CAP_FOWNER) ?
+                                                XFS_QMOPT_FORCE_RES : 0);
+                        if (code)       /* out of quota */
+                                goto error_return;
+                }
+        }
+
+        if (mask & FSX_EXTSIZE) {
+                /*
+                 * Can't change extent size if any extents are allocated.
+                 */
+                if (ip->i_d.di_nextents &&
+                    ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) !=
+                     fa->fsx_extsize)) {
+                        code = XFS_ERROR(EINVAL);       /* EFBIG? */
+                        goto error_return;
+                }
+
+                /*
+                 * Extent size must be a multiple of the appropriate block
+                 * size, if set at all.
+                 */
+                if (fa->fsx_extsize != 0) {
+                        xfs_extlen_t    size;
+
+                        if (XFS_IS_REALTIME_INODE(ip) ||
+                            ((mask & FSX_XFLAGS) &&
+                            (fa->fsx_xflags & XFS_XFLAG_REALTIME))) {
+                                size = mp->m_sb.sb_rextsize <<
+                                       mp->m_sb.sb_blocklog;
+                        } else {
+                                size = mp->m_sb.sb_blocksize;
+                        }
+
+                        if (fa->fsx_extsize % size) {
+                                code = XFS_ERROR(EINVAL);
+                                goto error_return;
+                        }
+                }
+        }
+
+
+        if (mask & FSX_XFLAGS) {
+                /*
+                 * Can't change realtime flag if any extents are allocated.
+                 */
+                if ((ip->i_d.di_nextents || ip->i_delayed_blks) &&
+                    (XFS_IS_REALTIME_INODE(ip)) !=
+                    (fa->fsx_xflags & XFS_XFLAG_REALTIME)) {
+                        code = XFS_ERROR(EINVAL);       /* EFBIG? */
+                        goto error_return;
+                }
+
+                /*
+                 * If realtime flag is set then must have realtime data.
+                 */
+                if ((fa->fsx_xflags & XFS_XFLAG_REALTIME)) {
+                        if ((mp->m_sb.sb_rblocks == 0) ||
+                            (mp->m_sb.sb_rextsize == 0) ||
+                            (ip->i_d.di_extsize % mp->m_sb.sb_rextsize)) {
+                                code = XFS_ERROR(EINVAL);
+                                goto error_return;
+                        }
+                }
+
+                /*
+                 * Can't modify an immutable/append-only file unless
+                 * we have appropriate permission.
+                 */
+                if ((ip->i_d.di_flags &
+                                (XFS_DIFLAG_IMMUTABLE|XFS_DIFLAG_APPEND) ||
+                     (fa->fsx_xflags &
+                                (XFS_XFLAG_IMMUTABLE | XFS_XFLAG_APPEND))) &&
+                    !capable(CAP_LINUX_IMMUTABLE)) {
+                        code = XFS_ERROR(EPERM);
+                        goto error_return;
+                }
+        }
+
+        xfs_trans_ijoin(tp, ip, lock_flags);
+        xfs_trans_ihold(tp, ip);
+
+        /*
+         * Change file ownership.  Must be the owner or privileged.
+         * If the system was configured with the "restricted_chown"
+         * option, the owner is not permitted to give away the file,
+         * and can change the group id only to a group of which he
+         * or she is a member.
+         */
+        if (mask & FSX_PROJID) {
+                /*
+                 * CAP_FSETID overrides the following restrictions:
+                 *
+                 * The set-user-ID and set-group-ID bits of a file will be
+                 * cleared upon successful return from chown()
+                 */
+                if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
+                    !capable(CAP_FSETID))
+                        ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
+
+                /*
+                 * Change the ownerships and register quota modifications
+                 * in the transaction.
+                 */
+                if (ip->i_d.di_projid != fa->fsx_projid) {
+                        if (XFS_IS_PQUOTA_ON(mp)) {
+                                olddquot = XFS_QM_DQVOPCHOWN(mp, tp, ip,
+                                                        &ip->i_gdquot, gdqp);
+                        }
+                        ip->i_d.di_projid = fa->fsx_projid;
+
+                        /*
+                         * We may have to rev the inode as well as
+                         * the superblock version number since projids didn't
+                         * exist before DINODE_VERSION_2 and SB_VERSION_NLINK.
+                         */
+                        if (ip->i_d.di_version == XFS_DINODE_VERSION_1)
+                                xfs_bump_ino_vers2(tp, ip);
+                }
+
+        }
+
+        if (mask & FSX_EXTSIZE)
+                ip->i_d.di_extsize = fa->fsx_extsize >> mp->m_sb.sb_blocklog;
+        if (mask & FSX_XFLAGS) {
+                xfs_set_diflags(ip, fa->fsx_xflags);
+                xfs_diflags_to_linux(ip);
+        }
+
+        xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+        xfs_ichgtime(ip, XFS_ICHGTIME_CHG);
+
+        XFS_STATS_INC(xs_ig_attrchg);
+
+        /*
+         * If this is a synchronous mount, make sure that the
+         * transaction goes to disk before returning to the user.
+         * This is slightly sub-optimal in that truncates require
+         * two sync transactions instead of one for wsync filesystems.
+         * One for the truncate and one for the timestamps since we
+         * don't want to change the timestamps unless we're sure the
+         * truncate worked.  Truncates are less than 1% of the laddis
+         * mix so this probably isn't worth the trouble to optimize.
+         */
+        if (mp->m_flags & XFS_MOUNT_WSYNC)
+                xfs_trans_set_sync(tp);
+        code = xfs_trans_commit(tp, 0);
+        xfs_iunlock(ip, lock_flags);
+
+        /*
+         * Release any dquot(s) the inode had kept before chown.
+         */
+        XFS_QM_DQRELE(mp, olddquot);
+        XFS_QM_DQRELE(mp, udqp);
+        XFS_QM_DQRELE(mp, gdqp);
+
+        if (code)
+                return code;
+
+        if (DM_EVENT_ENABLED(ip, DM_EVENT_ATTRIBUTE)) {
+                XFS_SEND_NAMESP(mp, DM_EVENT_ATTRIBUTE, ip, DM_RIGHT_NULL,
+                                NULL, DM_RIGHT_NULL, NULL, NULL, 0, 0,
+                                (mask & FSX_NONBLOCK) ? DM_FLAGS_NDELAY : 0);
+        }
+
+        return 0;
+
+ error_return:
+        XFS_QM_DQRELE(mp, udqp);
+        XFS_QM_DQRELE(mp, gdqp);
+        xfs_trans_cancel(tp, 0);
+        if (lock_flags)
+                xfs_iunlock(ip, lock_flags);
+        return code;
+}
+
 STATIC int
 xfs_ioc_fssetxattr(
         xfs_inode_t             *ip,
@@ -882,31 +1204,16 @@ xfs_ioc_fssetxattr(
         void                    __user *arg)
 {
         struct fsxattr          fa;
-        struct bhv_vattr        *vattr;
-        int                     error;
-        int                     attr_flags;
+        unsigned int            mask;
 
         if (copy_from_user(&fa, arg, sizeof(fa)))
                 return -EFAULT;
 
-        vattr = kmalloc(sizeof(*vattr), GFP_KERNEL);
-        if (unlikely(!vattr))
-                return -ENOMEM;
-
-        attr_flags = 0;
+        mask = FSX_XFLAGS | FSX_EXTSIZE | FSX_PROJID;
         if (filp->f_flags & (O_NDELAY|O_NONBLOCK))
-                attr_flags |= ATTR_NONBLOCK;
-
-        vattr->va_mask = XFS_AT_XFLAGS | XFS_AT_EXTSIZE | XFS_AT_PROJID;
-        vattr->va_xflags  = fa.fsx_xflags;
-        vattr->va_extsize = fa.fsx_extsize;
-        vattr->va_projid  = fa.fsx_projid;
+                mask |= FSX_NONBLOCK;
 
-        error = -xfs_setattr(ip, vattr, attr_flags, NULL);
-        if (!error)
-                vn_revalidate(XFS_ITOV(ip));    /* update flags */
-        kfree(vattr);
-        return 0;
+        return -xfs_ioctl_setattr(ip, &fa, mask);
 }
 
 STATIC int
@@ -928,10 +1235,9 @@ xfs_ioc_setxflags(
         struct file             *filp,
         void                    __user *arg)
 {
-        struct bhv_vattr        *vattr;
+        struct fsxattr          fa;
         unsigned int            flags;
-        int                     attr_flags;
-        int                     error;
+        unsigned int            mask;
 
         if (copy_from_user(&flags, arg, sizeof(flags)))
                 return -EFAULT;
@@ -941,22 +1247,12 @@ xfs_ioc_setxflags(
                       FS_SYNC_FL))
                 return -EOPNOTSUPP;
 
-        vattr = kmalloc(sizeof(*vattr), GFP_KERNEL);
-        if (unlikely(!vattr))
-                return -ENOMEM;
-
-        attr_flags = 0;
+        mask = FSX_XFLAGS;
         if (filp->f_flags & (O_NDELAY|O_NONBLOCK))
-                attr_flags |= ATTR_NONBLOCK;
-
-        vattr->va_mask = XFS_AT_XFLAGS;
-        vattr->va_xflags = xfs_merge_ioc_xflags(flags, xfs_ip2xflags(ip));
+                mask |= FSX_NONBLOCK;
+        fa.fsx_xflags = xfs_merge_ioc_xflags(flags, xfs_ip2xflags(ip));
 
-        error = -xfs_setattr(ip, vattr, attr_flags, NULL);
-        if (likely(!error))
-                vn_revalidate(XFS_ITOV(ip));    /* update flags */
-        kfree(vattr);
-        return error;
+        return -xfs_ioctl_setattr(ip, &fa, mask);
 }
 
 STATIC int
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index 2bf287ef5489..e88f51028086 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -181,23 +181,6 @@ xfs_ichgtime_fast(
                 mark_inode_dirty_sync(inode);
 }
 
-
-/*
- * Pull the link count and size up from the xfs inode to the linux inode
- */
-STATIC void
-xfs_validate_fields(
-        struct inode            *inode)
-{
-        struct xfs_inode        *ip = XFS_I(inode);
-        loff_t size;
-
-        /* we're under i_sem so i_size can't change under us */
-        size = XFS_ISIZE(ip);
-        if (i_size_read(inode) != size)
-                i_size_write(inode, size);
-}
-
 /*
  * Hook in SELinux.  This is not quite correct yet, what we really need
  * here (as we do for default ACLs) is a mechanism by which creation of
@@ -245,8 +228,7 @@ STATIC void
 xfs_cleanup_inode(
         struct inode    *dir,
         struct inode    *inode,
-        struct dentry   *dentry,
-        int             mode)
+        struct dentry   *dentry)
 {
         struct xfs_name teardown;
 
@@ -257,10 +239,7 @@ xfs_cleanup_inode(
          */
         xfs_dentry_to_name(&teardown, dentry);
 
-        if (S_ISDIR(mode))
-                xfs_rmdir(XFS_I(dir), &teardown, XFS_I(inode));
-        else
-                xfs_remove(XFS_I(dir), &teardown, XFS_I(inode));
+        xfs_remove(XFS_I(dir), &teardown, XFS_I(inode));
         iput(inode);
 }
 
@@ -275,7 +254,7 @@ xfs_vn_mknod(
         struct xfs_inode *ip = NULL;
         xfs_acl_t       *default_acl = NULL;
         struct xfs_name name;
-        attrexists_t    test_default_acl = _ACL_DEFAULT_EXISTS;
+        int (*test_default_acl)(struct inode *) = _ACL_DEFAULT_EXISTS;
         int             error;
 
         /*
@@ -335,14 +314,11 @@ xfs_vn_mknod(
         }
 
 
-        if (S_ISDIR(mode))
-                xfs_validate_fields(inode);
         d_instantiate(dentry, inode);
-        xfs_validate_fields(dir);
         return -error;
 
  out_cleanup_inode:
-        xfs_cleanup_inode(dir, inode, dentry, mode);
+        xfs_cleanup_inode(dir, inode, dentry);
  out_free_acl:
         if (default_acl)
                 _ACL_FREE(default_acl);
@@ -382,7 +358,7 @@ xfs_vn_lookup(
                 return ERR_PTR(-ENAMETOOLONG);
 
         xfs_dentry_to_name(&name, dentry);
-        error = xfs_lookup(XFS_I(dir), &name, &cip);
+        error = xfs_lookup(XFS_I(dir), &name, &cip, NULL);
         if (unlikely(error)) {
                 if (unlikely(error != ENOENT))
                         return ERR_PTR(-error);
@@ -393,6 +369,46 @@ xfs_vn_lookup(
         return d_splice_alias(cip->i_vnode, dentry);
 }
 
+STATIC struct dentry *
+xfs_vn_ci_lookup(
+        struct inode    *dir,
+        struct dentry   *dentry,
+        struct nameidata *nd)
+{
+        struct xfs_inode *ip;
+        struct xfs_name xname;
+        struct xfs_name ci_name;
+        struct qstr     dname;
+        int             error;
+
+        if (dentry->d_name.len >= MAXNAMELEN)
+                return ERR_PTR(-ENAMETOOLONG);
+
+        xfs_dentry_to_name(&xname, dentry);
+        error = xfs_lookup(XFS_I(dir), &xname, &ip, &ci_name);
+        if (unlikely(error)) {
+                if (unlikely(error != ENOENT))
+                        return ERR_PTR(-error);
+                /*
+                 * call d_add(dentry, NULL) here when d_drop_negative_children
+                 * is called in xfs_vn_mknod (ie. allow negative dentries
+                 * with CI filesystems).
+                 */
+                return NULL;
+        }
+
+        /* if exact match, just splice and exit */
+        if (!ci_name.name)
+                return d_splice_alias(ip->i_vnode, dentry);
+
+        /* else case-insensitive match... */
+        dname.name = ci_name.name;
+        dname.len = ci_name.len;
+        dentry = d_add_ci(ip->i_vnode, dentry, &dname);
+        kmem_free(ci_name.name);
+        return dentry;
+}
+
 STATIC int
 xfs_vn_link(
         struct dentry   *old_dentry,
@@ -414,7 +430,6 @@ xfs_vn_link(
         }
 
         xfs_iflags_set(XFS_I(dir), XFS_IMODIFIED);
-        xfs_validate_fields(inode);
         d_instantiate(dentry, inode);
         return 0;
 }
@@ -424,19 +439,23 @@ xfs_vn_unlink(
         struct inode    *dir,
         struct dentry   *dentry)
 {
-        struct inode    *inode;
         struct xfs_name name;
         int             error;
 
-        inode = dentry->d_inode;
         xfs_dentry_to_name(&name, dentry);
 
-        error = xfs_remove(XFS_I(dir), &name, XFS_I(inode));
-        if (likely(!error)) {
-                xfs_validate_fields(dir);       /* size needs update */
-                xfs_validate_fields(inode);
-        }
-        return -error;
+        error = -xfs_remove(XFS_I(dir), &name, XFS_I(dentry->d_inode));
+        if (error)
+                return error;
+
+        /*
+         * With unlink, the VFS makes the dentry "negative": no inode,
+         * but still hashed. This is incompatible with case-insensitive
+         * mode, so invalidate (unhash) the dentry in CI-mode.
+         */
+        if (xfs_sb_version_hasasciici(&XFS_M(dir->i_sb)->m_sb))
+                d_invalidate(dentry);
+        return 0;
 }
 
 STATIC int
@@ -466,36 +485,15 @@ xfs_vn_symlink(
                 goto out_cleanup_inode;
 
         d_instantiate(dentry, inode);
-        xfs_validate_fields(dir);
-        xfs_validate_fields(inode);
         return 0;
 
  out_cleanup_inode:
-        xfs_cleanup_inode(dir, inode, dentry, 0);
+        xfs_cleanup_inode(dir, inode, dentry);
  out:
         return -error;
 }
 
 STATIC int
-xfs_vn_rmdir(
-        struct inode    *dir,
-        struct dentry   *dentry)
-{
-        struct inode    *inode = dentry->d_inode;
-        struct xfs_name name;
-        int             error;
-
-        xfs_dentry_to_name(&name, dentry);
-
-        error = xfs_rmdir(XFS_I(dir), &name, XFS_I(inode));
-        if (likely(!error)) {
-                xfs_validate_fields(inode);
-                xfs_validate_fields(dir);
-        }
-        return -error;
-}
-
-STATIC int
 xfs_vn_rename(
         struct inode    *odir,
         struct dentry   *odentry,
@@ -505,22 +503,13 @@ xfs_vn_rename(
         struct inode    *new_inode = ndentry->d_inode;
         struct xfs_name oname;
         struct xfs_name nname;
-        int             error;
 
         xfs_dentry_to_name(&oname, odentry);
         xfs_dentry_to_name(&nname, ndentry);
 
-        error = xfs_rename(XFS_I(odir), &oname, XFS_I(odentry->d_inode),
+        return -xfs_rename(XFS_I(odir), &oname, XFS_I(odentry->d_inode),
                            XFS_I(ndir), &nname, new_inode ?
                                                 XFS_I(new_inode) : NULL);
-        if (likely(!error)) {
-                if (new_inode)
-                        xfs_validate_fields(new_inode);
-                xfs_validate_fields(odir);
-                if (ndir != odir)
-                        xfs_validate_fields(ndir);
-        }
-        return -error;
 }
 
 /*
@@ -589,8 +578,7 @@ xfs_check_acl(
 STATIC int
 xfs_vn_permission(
         struct inode            *inode,
-        int                     mask,
-        struct nameidata        *nd)
+        int                     mask)
 {
         return generic_permission(inode, mask, xfs_check_acl);
 }
@@ -660,57 +648,9 @@ xfs_vn_getattr(
 STATIC int
 xfs_vn_setattr(
         struct dentry   *dentry,
-        struct iattr    *attr)
+        struct iattr    *iattr)
 {
-        struct inode    *inode = dentry->d_inode;
-        unsigned int    ia_valid = attr->ia_valid;
-        bhv_vattr_t     vattr = { 0 };
-        int             flags = 0;
-        int             error;
-
-        if (ia_valid & ATTR_UID) {
-                vattr.va_mask |= XFS_AT_UID;
-                vattr.va_uid = attr->ia_uid;
-        }
-        if (ia_valid & ATTR_GID) {
-                vattr.va_mask |= XFS_AT_GID;
-                vattr.va_gid = attr->ia_gid;
-        }
-        if (ia_valid & ATTR_SIZE) {
-                vattr.va_mask |= XFS_AT_SIZE;
-                vattr.va_size = attr->ia_size;
-        }
-        if (ia_valid & ATTR_ATIME) {
-                vattr.va_mask |= XFS_AT_ATIME;
-                vattr.va_atime = attr->ia_atime;
-                inode->i_atime = attr->ia_atime;
-        }
-        if (ia_valid & ATTR_MTIME) {
-                vattr.va_mask |= XFS_AT_MTIME;
-                vattr.va_mtime = attr->ia_mtime;
-        }
-        if (ia_valid & ATTR_CTIME) {
-                vattr.va_mask |= XFS_AT_CTIME;
-                vattr.va_ctime = attr->ia_ctime;
-        }
-        if (ia_valid & ATTR_MODE) {
-                vattr.va_mask |= XFS_AT_MODE;
-                vattr.va_mode = attr->ia_mode;
-                if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
-                        inode->i_mode &= ~S_ISGID;
-        }
-
-        if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET))
-                flags |= ATTR_UTIME;
-#ifdef ATTR_NO_BLOCK
-        if ((ia_valid & ATTR_NO_BLOCK))
-                flags |= ATTR_NONBLOCK;
-#endif
-
-        error = xfs_setattr(XFS_I(inode), &vattr, flags, NULL);
-        if (likely(!error))
-                vn_revalidate(vn_from_inode(inode));
-        return -error;
+        return -xfs_setattr(XFS_I(dentry->d_inode), iattr, 0, NULL);
 }
 
 /*
@@ -728,109 +668,6 @@ xfs_vn_truncate(
         WARN_ON(error);
 }
 
-STATIC int
-xfs_vn_setxattr(
-        struct dentry   *dentry,
-        const char      *name,
-        const void      *data,
-        size_t          size,
-        int             flags)
-{
-        bhv_vnode_t     *vp = vn_from_inode(dentry->d_inode);
-        char            *attr = (char *)name;
-        attrnames_t     *namesp;
-        int             xflags = 0;
-        int             error;
-
-        namesp = attr_lookup_namespace(attr, attr_namespaces, ATTR_NAMECOUNT);
-        if (!namesp)
-                return -EOPNOTSUPP;
-        attr += namesp->attr_namelen;
-        error = namesp->attr_capable(vp, NULL);
-        if (error)
-                return error;
-
-        /* Convert Linux syscall to XFS internal ATTR flags */
-        if (flags & XATTR_CREATE)
-                xflags |= ATTR_CREATE;
-        if (flags & XATTR_REPLACE)
-                xflags |= ATTR_REPLACE;
-        xflags |= namesp->attr_flag;
-        return namesp->attr_set(vp, attr, (void *)data, size, xflags);
-}
-
-STATIC ssize_t
-xfs_vn_getxattr(
-        struct dentry   *dentry,
-        const char      *name,
-        void            *data,
-        size_t          size)
-{
-        bhv_vnode_t     *vp = vn_from_inode(dentry->d_inode);
-        char            *attr = (char *)name;
-        attrnames_t     *namesp;
-        int             xflags = 0;
-        ssize_t         error;
-
-        namesp = attr_lookup_namespace(attr, attr_namespaces, ATTR_NAMECOUNT);
-        if (!namesp)
-                return -EOPNOTSUPP;
-        attr += namesp->attr_namelen;
-        error = namesp->attr_capable(vp, NULL);
-        if (error)
-                return error;
-
-        /* Convert Linux syscall to XFS internal ATTR flags */
-        if (!size) {
-                xflags |= ATTR_KERNOVAL;
-                data = NULL;
-        }
-        xflags |= namesp->attr_flag;
-        return namesp->attr_get(vp, attr, (void *)data, size, xflags);
-}
-
-STATIC ssize_t
-xfs_vn_listxattr(
-        struct dentry           *dentry,
-        char                    *data,
-        size_t                  size)
-{
-        bhv_vnode_t             *vp = vn_from_inode(dentry->d_inode);
-        int                     error, xflags = ATTR_KERNAMELS;
-        ssize_t                 result;
-
-        if (!size)
-                xflags |= ATTR_KERNOVAL;
-        xflags |= capable(CAP_SYS_ADMIN) ? ATTR_KERNFULLS : ATTR_KERNORMALS;
-
-        error = attr_generic_list(vp, data, size, xflags, &result);
-        if (error < 0)
-                return error;
-        return result;
-}
-
-STATIC int
-xfs_vn_removexattr(
-        struct dentry   *dentry,
-        const char      *name)
-{
-        bhv_vnode_t     *vp = vn_from_inode(dentry->d_inode);
-        char            *attr = (char *)name;
-        attrnames_t     *namesp;
-        int             xflags = 0;
-        int             error;
-
-        namesp = attr_lookup_namespace(attr, attr_namespaces, ATTR_NAMECOUNT);
-        if (!namesp)
-                return -EOPNOTSUPP;
-        attr += namesp->attr_namelen;
-        error = namesp->attr_capable(vp, NULL);
-        if (error)
-                return error;
-        xflags |= namesp->attr_flag;
-        return namesp->attr_remove(vp, attr, xflags);
-}
-
 STATIC long
 xfs_vn_fallocate(
         struct inode    *inode,
@@ -854,18 +691,18 @@ xfs_vn_fallocate(
 
         xfs_ilock(ip, XFS_IOLOCK_EXCL);
         error = xfs_change_file_space(ip, XFS_IOC_RESVSP, &bf,
-                                                0, NULL, ATTR_NOLOCK);
+                                      0, NULL, XFS_ATTR_NOLOCK);
         if (!error && !(mode & FALLOC_FL_KEEP_SIZE) &&
             offset + len > i_size_read(inode))
                 new_size = offset + len;
 
         /* Change file size if needed */
         if (new_size) {
-                bhv_vattr_t     va;
+                struct iattr iattr;
 
-                va.va_mask = XFS_AT_SIZE;
-                va.va_size = new_size;
-                error = xfs_setattr(ip, &va, ATTR_NOLOCK, NULL);
+                iattr.ia_valid = ATTR_SIZE;
+                iattr.ia_size = new_size;
+                error = xfs_setattr(ip, &iattr, XFS_ATTR_NOLOCK, NULL);
         }
 
         xfs_iunlock(ip, XFS_IOLOCK_EXCL);
@@ -878,10 +715,10 @@ const struct inode_operations xfs_inode_operations = {
         .truncate               = xfs_vn_truncate,
         .getattr                = xfs_vn_getattr,
         .setattr                = xfs_vn_setattr,
-        .setxattr               = xfs_vn_setxattr,
-        .getxattr               = xfs_vn_getxattr,
+        .setxattr               = generic_setxattr,
+        .getxattr               = generic_getxattr,
+        .removexattr            = generic_removexattr,
         .listxattr              = xfs_vn_listxattr,
-        .removexattr            = xfs_vn_removexattr,
         .fallocate              = xfs_vn_fallocate,
 };
 
@@ -892,16 +729,47 @@ const struct inode_operations xfs_dir_inode_operations = {
         .unlink                 = xfs_vn_unlink,
         .symlink                = xfs_vn_symlink,
         .mkdir                  = xfs_vn_mkdir,
-        .rmdir                  = xfs_vn_rmdir,
+        /*
+         * Yes, XFS uses the same method for rmdir and unlink.
+         *
+         * There are some subtile differences deeper in the code,
+         * but we use S_ISDIR to check for those.
+         */
+        .rmdir                  = xfs_vn_unlink,
+        .mknod                  = xfs_vn_mknod,
+        .rename                 = xfs_vn_rename,
+        .permission             = xfs_vn_permission,
+        .getattr                = xfs_vn_getattr,
+        .setattr                = xfs_vn_setattr,
+        .setxattr               = generic_setxattr,
+        .getxattr               = generic_getxattr,
+        .removexattr            = generic_removexattr,
+        .listxattr              = xfs_vn_listxattr,
+};
+
+const struct inode_operations xfs_dir_ci_inode_operations = {
+        .create                 = xfs_vn_create,
+        .lookup                 = xfs_vn_ci_lookup,
+        .link                   = xfs_vn_link,
+        .unlink                 = xfs_vn_unlink,
+        .symlink                = xfs_vn_symlink,
+        .mkdir                  = xfs_vn_mkdir,
+        /*
+         * Yes, XFS uses the same method for rmdir and unlink.
+         *
+         * There are some subtile differences deeper in the code,
+         * but we use S_ISDIR to check for those.
+         */
+        .rmdir                  = xfs_vn_unlink,
         .mknod                  = xfs_vn_mknod,
         .rename                 = xfs_vn_rename,
         .permission             = xfs_vn_permission,
         .getattr                = xfs_vn_getattr,
         .setattr                = xfs_vn_setattr,
-        .setxattr               = xfs_vn_setxattr,
-        .getxattr               = xfs_vn_getxattr,
+        .setxattr               = generic_setxattr,
+        .getxattr               = generic_getxattr,
+        .removexattr            = generic_removexattr,
         .listxattr              = xfs_vn_listxattr,
-        .removexattr            = xfs_vn_removexattr,
 };
 
 const struct inode_operations xfs_symlink_inode_operations = {
@@ -911,8 +779,8 @@ const struct inode_operations xfs_symlink_inode_operations = {
         .permission             = xfs_vn_permission,
         .getattr                = xfs_vn_getattr,
         .setattr                = xfs_vn_setattr,
-        .setxattr               = xfs_vn_setxattr,
-        .getxattr               = xfs_vn_getxattr,
+        .setxattr               = generic_setxattr,
+        .getxattr               = generic_getxattr,
+        .removexattr            = generic_removexattr,
         .listxattr              = xfs_vn_listxattr,
-        .removexattr            = xfs_vn_removexattr,
 };
diff --git a/fs/xfs/linux-2.6/xfs_iops.h b/fs/xfs/linux-2.6/xfs_iops.h
index 14d0deb7afff..d97ba934a2ac 100644
--- a/fs/xfs/linux-2.6/xfs_iops.h
+++ b/fs/xfs/linux-2.6/xfs_iops.h
@@ -20,12 +20,14 @@
 
 extern const struct inode_operations xfs_inode_operations;
 extern const struct inode_operations xfs_dir_inode_operations;
+extern const struct inode_operations xfs_dir_ci_inode_operations;
 extern const struct inode_operations xfs_symlink_inode_operations;
 
 extern const struct file_operations xfs_file_operations;
 extern const struct file_operations xfs_dir_file_operations;
 extern const struct file_operations xfs_invis_file_operations;
 
+extern ssize_t xfs_vn_listxattr(struct dentry *, char *data, size_t size);
 
 struct xfs_inode;
 extern void xfs_ichgtime(struct xfs_inode *, int);
diff --git a/fs/xfs/linux-2.6/xfs_linux.h b/fs/xfs/linux-2.6/xfs_linux.h
index 4edc46915b57..4d45d9351a6c 100644
--- a/fs/xfs/linux-2.6/xfs_linux.h
+++ b/fs/xfs/linux-2.6/xfs_linux.h
@@ -76,6 +76,7 @@
 #include <linux/log2.h>
 #include <linux/spinlock.h>
 #include <linux/random.h>
+#include <linux/ctype.h>
 
 #include <asm/page.h>
 #include <asm/div64.h>
@@ -299,4 +300,11 @@ static inline __uint64_t howmany_64(__uint64_t x, __uint32_t y)
         return x;
 }
 
+/* ARM old ABI has some weird alignment/padding */
+#if defined(__arm__) && !defined(__ARM_EABI__)
+#define __arch_pack __attribute__((packed))
+#else
+#define __arch_pack
+#endif
+
 #endif /* __XFS_LINUX__ */
diff --git a/fs/xfs/linux-2.6/xfs_lrw.c b/fs/xfs/linux-2.6/xfs_lrw.c
index 5e3b57516ec7..82333b3e118e 100644
--- a/fs/xfs/linux-2.6/xfs_lrw.c
+++ b/fs/xfs/linux-2.6/xfs_lrw.c
@@ -711,7 +711,7 @@ start:
              !capable(CAP_FSETID)) {
                 error = xfs_write_clear_setuid(xip);
                 if (likely(!error))
-                        error = -remove_suid(file->f_path.dentry);
+                        error = -file_remove_suid(file);
                 if (unlikely(error)) {
                         goto out_unlock_internal;
                 }
diff --git a/fs/xfs/linux-2.6/xfs_stats.c b/fs/xfs/linux-2.6/xfs_stats.c
index e480b6102051..3d5b67c075c7 100644
--- a/fs/xfs/linux-2.6/xfs_stats.c
+++ b/fs/xfs/linux-2.6/xfs_stats.c
@@ -98,12 +98,21 @@ xfs_read_xfsstats(
         return len;
 }
 
-void
+int
 xfs_init_procfs(void)
 {
         if (!proc_mkdir("fs/xfs", NULL))
-                return;
-        create_proc_read_entry("fs/xfs/stat", 0, NULL, xfs_read_xfsstats, NULL);
+                goto out;
+
+        if (!create_proc_read_entry("fs/xfs/stat", 0, NULL,
+                        xfs_read_xfsstats, NULL))
+                goto out_remove_entry;
+        return 0;
+
+ out_remove_entry:
+        remove_proc_entry("fs/xfs", NULL);
+ out:
+        return -ENOMEM;
 }
 
 void
diff --git a/fs/xfs/linux-2.6/xfs_stats.h b/fs/xfs/linux-2.6/xfs_stats.h
index afd0b0d5fdb2..e83820febc9f 100644
--- a/fs/xfs/linux-2.6/xfs_stats.h
+++ b/fs/xfs/linux-2.6/xfs_stats.h
@@ -134,7 +134,7 @@ DECLARE_PER_CPU(struct xfsstats, xfsstats);
 #define XFS_STATS_DEC(v)        (per_cpu(xfsstats, current_cpu()).v--)
 #define XFS_STATS_ADD(v, inc)   (per_cpu(xfsstats, current_cpu()).v += (inc))
 
-extern void xfs_init_procfs(void);
+extern int xfs_init_procfs(void);
 extern void xfs_cleanup_procfs(void);
 
 
@@ -144,8 +144,14 @@ extern void xfs_cleanup_procfs(void);
 # define XFS_STATS_DEC(count)
 # define XFS_STATS_ADD(count, inc)
 
-static inline void xfs_init_procfs(void) { };
-static inline void xfs_cleanup_procfs(void) { };
+static inline int xfs_init_procfs(void)
+{
+        return 0;
+}
+
+static inline void xfs_cleanup_procfs(void)
+{
+}
 
 #endif  /* !CONFIG_PROC_FS */
 
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 742b2c7852c1..30ae96397e31 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -52,6 +52,12 @@
 #include "xfs_version.h"
 #include "xfs_log_priv.h"
 #include "xfs_trans_priv.h"
+#include "xfs_filestream.h"
+#include "xfs_da_btree.h"
+#include "xfs_dir2_trace.h"
+#include "xfs_extfree_item.h"
+#include "xfs_mru_cache.h"
+#include "xfs_inode_item.h"
 
 #include <linux/namei.h>
 #include <linux/init.h>
@@ -60,6 +66,7 @@
 #include <linux/writeback.h>
 #include <linux/kthread.h>
 #include <linux/freezer.h>
+#include <linux/parser.h>
 
 static struct quotactl_ops xfs_quotactl_operations;
 static struct super_operations xfs_super_operations;
@@ -74,7 +81,10 @@ xfs_args_allocate(
 {
         struct xfs_mount_args   *args;
 
-        args = kmem_zalloc(sizeof(struct xfs_mount_args), KM_SLEEP);
+        args = kzalloc(sizeof(struct xfs_mount_args), GFP_KERNEL);
+        if (!args)
+                return NULL;
+
         args->logbufs = args->logbufsize = -1;
         strncpy(args->fsname, sb->s_id, MAXNAMELEN);
 
@@ -138,6 +148,23 @@ xfs_args_allocate(
 #define MNTOPT_XDSM     "xdsm"          /* DMI enabled (DMAPI / XDSM) */
 #define MNTOPT_DMI      "dmi"           /* DMI enabled (DMAPI / XDSM) */
 
+/*
+ * Table driven mount option parser.
+ *
+ * Currently only used for remount, but it will be used for mount
+ * in the future, too.
+ */
+enum {
+        Opt_barrier, Opt_nobarrier, Opt_err
+};
+
+static match_table_t tokens = {
+        {Opt_barrier, "barrier"},
+        {Opt_nobarrier, "nobarrier"},
+        {Opt_err, NULL}
+};
+
+
 STATIC unsigned long
 suffix_strtoul(char *s, char **endp, unsigned int base)
 {
@@ -314,6 +341,7 @@ xfs_parseargs(
                         args->flags |= XFSMNT_ATTR2;
                 } else if (!strcmp(this_char, MNTOPT_NOATTR2)) {
                         args->flags &= ~XFSMNT_ATTR2;
+                        args->flags |= XFSMNT_NOATTR2;
                 } else if (!strcmp(this_char, MNTOPT_FILESTREAM)) {
                         args->flags2 |= XFSMNT2_FILESTREAMS;
                 } else if (!strcmp(this_char, MNTOPT_NOQUOTA)) {
@@ -564,7 +592,10 @@ xfs_set_inodeops(
                 inode->i_mapping->a_ops = &xfs_address_space_operations;
                 break;
         case S_IFDIR:
-                inode->i_op = &xfs_dir_inode_operations;
+                if (xfs_sb_version_hasasciici(&XFS_M(inode->i_sb)->m_sb))
+                        inode->i_op = &xfs_dir_ci_inode_operations;
+                else
+                        inode->i_op = &xfs_dir_inode_operations;
                 inode->i_fop = &xfs_dir_file_operations;
                 break;
         case S_IFLNK:
@@ -733,14 +764,6 @@ xfs_mountfs_check_barriers(xfs_mount_t *mp)
                 return;
         }
 
-        if (mp->m_ddev_targp->bt_bdev->bd_disk->queue->ordered ==
-                                        QUEUE_ORDERED_NONE) {
-                xfs_fs_cmn_err(CE_NOTE, mp,
-                  "Disabling barriers, not supported by the underlying 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");
@@ -764,6 +787,139 @@ xfs_blkdev_issue_flush(
         blkdev_issue_flush(buftarg->bt_bdev, NULL);
 }
 
+STATIC void
+xfs_close_devices(
+        struct xfs_mount        *mp)
+{
+        if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) {
+                struct block_device *logdev = mp->m_logdev_targp->bt_bdev;
+                xfs_free_buftarg(mp->m_logdev_targp);
+                xfs_blkdev_put(logdev);
+        }
+        if (mp->m_rtdev_targp) {
+                struct block_device *rtdev = mp->m_rtdev_targp->bt_bdev;
+                xfs_free_buftarg(mp->m_rtdev_targp);
+                xfs_blkdev_put(rtdev);
+        }
+        xfs_free_buftarg(mp->m_ddev_targp);
+}
+
+/*
+ * The file system configurations are:
+ *      (1) device (partition) with data and internal log
+ *      (2) logical volume with data and log subvolumes.
+ *      (3) logical volume with data, log, and realtime subvolumes.
+ *
+ * We only have to handle opening the log and realtime volumes here if
+ * they are present.  The data subvolume has already been opened by
+ * get_sb_bdev() and is stored in sb->s_bdev.
+ */
+STATIC int
+xfs_open_devices(
+        struct xfs_mount        *mp,
+        struct xfs_mount_args   *args)
+{
+        struct block_device     *ddev = mp->m_super->s_bdev;
+        struct block_device     *logdev = NULL, *rtdev = NULL;
+        int                     error;
+
+        /*
+         * Open real time and log devices - order is important.
+         */
+        if (args->logname[0]) {
+                error = xfs_blkdev_get(mp, args->logname, &logdev);
+                if (error)
+                        goto out;
+        }
+
+        if (args->rtname[0]) {
+                error = xfs_blkdev_get(mp, args->rtname, &rtdev);
+                if (error)
+                        goto out_close_logdev;
+
+                if (rtdev == ddev || rtdev == logdev) {
+                        cmn_err(CE_WARN,
+        "XFS: Cannot mount filesystem with identical rtdev and ddev/logdev.");
+                        error = EINVAL;
+                        goto out_close_rtdev;
+                }
+        }
+
+        /*
+         * Setup xfs_mount buffer target pointers
+         */
+        error = ENOMEM;
+        mp->m_ddev_targp = xfs_alloc_buftarg(ddev, 0);
+        if (!mp->m_ddev_targp)
+                goto out_close_rtdev;
+
+        if (rtdev) {
+                mp->m_rtdev_targp = xfs_alloc_buftarg(rtdev, 1);
+                if (!mp->m_rtdev_targp)
+                        goto out_free_ddev_targ;
+        }
+
+        if (logdev && logdev != ddev) {
+                mp->m_logdev_targp = xfs_alloc_buftarg(logdev, 1);
+                if (!mp->m_logdev_targp)
+                        goto out_free_rtdev_targ;
+        } else {
+                mp->m_logdev_targp = mp->m_ddev_targp;
+        }
+
+        return 0;
+
+ out_free_rtdev_targ:
+        if (mp->m_rtdev_targp)
+                xfs_free_buftarg(mp->m_rtdev_targp);
+ out_free_ddev_targ:
+        xfs_free_buftarg(mp->m_ddev_targp);
+ out_close_rtdev:
+        if (rtdev)
+                xfs_blkdev_put(rtdev);
+ out_close_logdev:
+        if (logdev && logdev != ddev)
+                xfs_blkdev_put(logdev);
+ out:
+        return error;
+}
+
+/*
+ * Setup xfs_mount buffer target pointers based on superblock
+ */
+STATIC int
+xfs_setup_devices(
+        struct xfs_mount        *mp)
+{
+        int                     error;
+
+        error = xfs_setsize_buftarg(mp->m_ddev_targp, mp->m_sb.sb_blocksize,
+                                    mp->m_sb.sb_sectsize);
+        if (error)
+                return error;
+
+        if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) {
+                unsigned int    log_sector_size = BBSIZE;
+
+                if (xfs_sb_version_hassector(&mp->m_sb))
+                        log_sector_size = mp->m_sb.sb_logsectsize;
+                error = xfs_setsize_buftarg(mp->m_logdev_targp,
+                                            mp->m_sb.sb_blocksize,
+                                            log_sector_size);
+                if (error)
+                        return error;
+        }
+        if (mp->m_rtdev_targp) {
+                error = xfs_setsize_buftarg(mp->m_rtdev_targp,
+                                            mp->m_sb.sb_blocksize,
+                                            mp->m_sb.sb_sectsize);
+                if (error)
+                        return error;
+        }
+
+        return 0;
+}
+
 /*
  * XFS AIL push thread support
  */
@@ -843,48 +999,11 @@ xfs_fs_destroy_inode(
 
 STATIC void
 xfs_fs_inode_init_once(
-        kmem_zone_t             *zonep,
         void                    *vnode)
 {
         inode_init_once(vn_to_inode((bhv_vnode_t *)vnode));
 }
 
-STATIC int __init
-xfs_init_zones(void)
-{
-        xfs_vnode_zone = kmem_zone_init_flags(sizeof(bhv_vnode_t), "xfs_vnode",
-                                        KM_ZONE_HWALIGN | KM_ZONE_RECLAIM |
-                                        KM_ZONE_SPREAD,
-                                        xfs_fs_inode_init_once);
-        if (!xfs_vnode_zone)
-                goto out;
-
-        xfs_ioend_zone = kmem_zone_init(sizeof(xfs_ioend_t), "xfs_ioend");
-        if (!xfs_ioend_zone)
-                goto out_destroy_vnode_zone;
-
-        xfs_ioend_pool = mempool_create_slab_pool(4 * MAX_BUF_PER_PAGE,
-                                                  xfs_ioend_zone);
-        if (!xfs_ioend_pool)
-                goto out_free_ioend_zone;
-        return 0;
-
- out_free_ioend_zone:
-        kmem_zone_destroy(xfs_ioend_zone);
- out_destroy_vnode_zone:
-        kmem_zone_destroy(xfs_vnode_zone);
- out:
-        return -ENOMEM;
-}
-
-STATIC void
-xfs_destroy_zones(void)
-{
-        mempool_destroy(xfs_ioend_pool);
-        kmem_zone_destroy(xfs_vnode_zone);
-        kmem_zone_destroy(xfs_ioend_zone);
-}
-
 /*
  * Attempt to flush the inode, this will actually fail
  * if the inode is pinned, but we dirty the inode again
@@ -1074,7 +1193,7 @@ xfssyncd(
                         list_del(&work->w_list);
                         if (work == &mp->m_sync_work)
                                 continue;
-                        kmem_free(work, sizeof(struct bhv_vfs_sync_work));
+                        kmem_free(work);
                 }
         }
 
@@ -1086,14 +1205,63 @@ xfs_fs_put_super(
         struct super_block      *sb)
 {
         struct xfs_mount        *mp = XFS_M(sb);
+        struct xfs_inode        *rip = mp->m_rootip;
+        int                     unmount_event_flags = 0;
         int                     error;
 
         kthread_stop(mp->m_sync_task);
 
         xfs_sync(mp, SYNC_ATTR | SYNC_DELWRI);
-        error = xfs_unmount(mp, 0, NULL);
-        if (error)
-                printk("XFS: unmount got error=%d\n", error);
+
+#ifdef HAVE_DMAPI
+        if (mp->m_flags & XFS_MOUNT_DMAPI) {
+                unmount_event_flags =
+                        (mp->m_dmevmask & (1 << DM_EVENT_UNMOUNT)) ?
+                                0 : DM_FLAGS_UNWANTED;
+                /*
+                 * Ignore error from dmapi here, first unmount is not allowed
+                 * to fail anyway, and second we wouldn't want to fail a
+                 * unmount because of dmapi.
+                 */
+                XFS_SEND_PREUNMOUNT(mp, rip, DM_RIGHT_NULL, rip, DM_RIGHT_NULL,
+                                NULL, NULL, 0, 0, unmount_event_flags);
+        }
+#endif
+
+        /*
+         * Blow away any referenced inode in the filestreams cache.
+         * This can and will cause log traffic as inodes go inactive
+         * here.
+         */
+        xfs_filestream_unmount(mp);
+
+        XFS_bflush(mp->m_ddev_targp);
+        error = xfs_unmount_flush(mp, 0);
+        WARN_ON(error);
+
+        IRELE(rip);
+
+        /*
+         * If we're forcing a shutdown, typically because of a media error,
+         * we want to make sure we invalidate dirty pages that belong to
+         * referenced vnodes as well.
+         */
+        if (XFS_FORCED_SHUTDOWN(mp)) {
+                error = xfs_sync(mp, SYNC_WAIT | SYNC_CLOSE);
+                ASSERT(error != EFSCORRUPTED);
+        }
+
+        if (mp->m_flags & XFS_MOUNT_DMAPI) {
+                XFS_SEND_UNMOUNT(mp, rip, DM_RIGHT_NULL, 0, 0,
+                                unmount_event_flags);
+        }
+
+        xfs_unmountfs(mp);
+        xfs_icsb_destroy_counters(mp);
+        xfs_close_devices(mp);
+        xfs_qmops_put(mp);
+        xfs_dmops_put(mp);
+        kfree(mp);
 }
 
 STATIC void
@@ -1216,14 +1384,54 @@ xfs_fs_remount(
         char                    *options)
 {
         struct xfs_mount        *mp = XFS_M(sb);
-        struct xfs_mount_args   *args = xfs_args_allocate(sb, 0);
-        int                     error;
+        substring_t             args[MAX_OPT_ARGS];
+        char                    *p;
 
-        error = xfs_parseargs(mp, options, args, 1);
-        if (!error)
-                error = xfs_mntupdate(mp, flags, args);
-        kmem_free(args, sizeof(*args));
-        return -error;
+        while ((p = strsep(&options, ",")) != NULL) {
+                int token;
+
+                if (!*p)
+                        continue;
+
+                token = match_token(p, tokens, args);
+                switch (token) {
+                case Opt_barrier:
+                        mp->m_flags |= XFS_MOUNT_BARRIER;
+
+                        /*
+                         * Test if barriers are actually working if we can,
+                         * else delay this check until the filesystem is
+                         * marked writeable.
+                         */
+                        if (!(mp->m_flags & XFS_MOUNT_RDONLY))
+                                xfs_mountfs_check_barriers(mp);
+                        break;
+                case Opt_nobarrier:
+                        mp->m_flags &= ~XFS_MOUNT_BARRIER;
+                        break;
+                default:
+                        printk(KERN_INFO
+        "XFS: mount option \"%s\" not supported for remount\n", p);
+                        return -EINVAL;
+                }
+        }
+
+        /* rw/ro -> rw */
+        if ((mp->m_flags & XFS_MOUNT_RDONLY) && !(*flags & MS_RDONLY)) {
+                mp->m_flags &= ~XFS_MOUNT_RDONLY;
+                if (mp->m_flags & XFS_MOUNT_BARRIER)
+                        xfs_mountfs_check_barriers(mp);
+        }
+
+        /* rw -> ro */
+        if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (*flags & MS_RDONLY)) {
+                xfs_filestream_flush(mp);
+                xfs_sync(mp, SYNC_DATA_QUIESCE);
+                xfs_attr_quiesce(mp);
+                mp->m_flags |= XFS_MOUNT_RDONLY;
+        }
+
+        return 0;
 }
 
 /*
@@ -1300,6 +1508,225 @@ xfs_fs_setxquota(
                                    Q_XSETPQLIM), id, (caddr_t)fdq);
 }
 
+/*
+ * This function fills in xfs_mount_t fields based on mount args.
+ * Note: the superblock has _not_ yet been read in.
+ */
+STATIC int
+xfs_start_flags(
+        struct xfs_mount_args   *ap,
+        struct xfs_mount        *mp)
+{
+        /* Values are in BBs */
+        if ((ap->flags & XFSMNT_NOALIGN) != XFSMNT_NOALIGN) {
+                /*
+                 * At this point the superblock has not been read
+                 * in, therefore we do not know the block size.
+                 * Before the mount call ends we will convert
+                 * these to FSBs.
+                 */
+                mp->m_dalign = ap->sunit;
+                mp->m_swidth = ap->swidth;
+        }
+
+        if (ap->logbufs != -1 &&
+            ap->logbufs != 0 &&
+            (ap->logbufs < XLOG_MIN_ICLOGS ||
+             ap->logbufs > XLOG_MAX_ICLOGS)) {
+                cmn_err(CE_WARN,
+                        "XFS: invalid logbufs value: %d [not %d-%d]",
+                        ap->logbufs, XLOG_MIN_ICLOGS, XLOG_MAX_ICLOGS);
+                return XFS_ERROR(EINVAL);
+        }
+        mp->m_logbufs = ap->logbufs;
+        if (ap->logbufsize != -1 &&
+            ap->logbufsize !=  0 &&
+            (ap->logbufsize < XLOG_MIN_RECORD_BSIZE ||
+             ap->logbufsize > XLOG_MAX_RECORD_BSIZE ||
+             !is_power_of_2(ap->logbufsize))) {
+                cmn_err(CE_WARN,
+        "XFS: invalid logbufsize: %d [not 16k,32k,64k,128k or 256k]",
+                        ap->logbufsize);
+                return XFS_ERROR(EINVAL);
+        }
+        mp->m_logbsize = ap->logbufsize;
+        mp->m_fsname_len = strlen(ap->fsname) + 1;
+        mp->m_fsname = kmem_alloc(mp->m_fsname_len, KM_SLEEP);
+        strcpy(mp->m_fsname, ap->fsname);
+        if (ap->rtname[0]) {
+                mp->m_rtname = kmem_alloc(strlen(ap->rtname) + 1, KM_SLEEP);
+                strcpy(mp->m_rtname, ap->rtname);
+        }
+        if (ap->logname[0]) {
+                mp->m_logname = kmem_alloc(strlen(ap->logname) + 1, KM_SLEEP);
+                strcpy(mp->m_logname, ap->logname);
+        }
+
+        if (ap->flags & XFSMNT_WSYNC)
+                mp->m_flags |= XFS_MOUNT_WSYNC;
+#if XFS_BIG_INUMS
+        if (ap->flags & XFSMNT_INO64) {
+                mp->m_flags |= XFS_MOUNT_INO64;
+                mp->m_inoadd = XFS_INO64_OFFSET;
+        }
+#endif
+        if (ap->flags & XFSMNT_RETERR)
+                mp->m_flags |= XFS_MOUNT_RETERR;
+        if (ap->flags & XFSMNT_NOALIGN)
+                mp->m_flags |= XFS_MOUNT_NOALIGN;
+        if (ap->flags & XFSMNT_SWALLOC)
+                mp->m_flags |= XFS_MOUNT_SWALLOC;
+        if (ap->flags & XFSMNT_OSYNCISOSYNC)
+                mp->m_flags |= XFS_MOUNT_OSYNCISOSYNC;
+        if (ap->flags & XFSMNT_32BITINODES)
+                mp->m_flags |= XFS_MOUNT_32BITINODES;
+
+        if (ap->flags & XFSMNT_IOSIZE) {
+                if (ap->iosizelog > XFS_MAX_IO_LOG ||
+                    ap->iosizelog < XFS_MIN_IO_LOG) {
+                        cmn_err(CE_WARN,
+                "XFS: invalid log iosize: %d [not %d-%d]",
+                                ap->iosizelog, XFS_MIN_IO_LOG,
+                                XFS_MAX_IO_LOG);
+                        return XFS_ERROR(EINVAL);
+                }
+
+                mp->m_flags |= XFS_MOUNT_DFLT_IOSIZE;
+                mp->m_readio_log = mp->m_writeio_log = ap->iosizelog;
+        }
+
+        if (ap->flags & XFSMNT_IKEEP)
+                mp->m_flags |= XFS_MOUNT_IKEEP;
+        if (ap->flags & XFSMNT_DIRSYNC)
+                mp->m_flags |= XFS_MOUNT_DIRSYNC;
+        if (ap->flags & XFSMNT_ATTR2)
+                mp->m_flags |= XFS_MOUNT_ATTR2;
+        if (ap->flags & XFSMNT_NOATTR2)
+                mp->m_flags |= XFS_MOUNT_NOATTR2;
+
+        if (ap->flags2 & XFSMNT2_COMPAT_IOSIZE)
+                mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
+
+        /*
+         * no recovery flag requires a read-only mount
+         */
+        if (ap->flags & XFSMNT_NORECOVERY) {
+                if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
+                        cmn_err(CE_WARN,
+        "XFS: tried to mount a FS read-write without recovery!");
+                        return XFS_ERROR(EINVAL);
+                }
+                mp->m_flags |= XFS_MOUNT_NORECOVERY;
+        }
+
+        if (ap->flags & XFSMNT_NOUUID)
+                mp->m_flags |= XFS_MOUNT_NOUUID;
+        if (ap->flags & XFSMNT_BARRIER)
+                mp->m_flags |= XFS_MOUNT_BARRIER;
+        else
+                mp->m_flags &= ~XFS_MOUNT_BARRIER;
+
+        if (ap->flags2 & XFSMNT2_FILESTREAMS)
+                mp->m_flags |= XFS_MOUNT_FILESTREAMS;
+
+        if (ap->flags & XFSMNT_DMAPI)
+                mp->m_flags |= XFS_MOUNT_DMAPI;
+        return 0;
+}
+
+/*
+ * This function fills in xfs_mount_t fields based on mount args.
+ * Note: the superblock _has_ now been read in.
+ */
+STATIC int
+xfs_finish_flags(
+        struct xfs_mount_args   *ap,
+        struct xfs_mount        *mp)
+{
+        int                     ronly = (mp->m_flags & XFS_MOUNT_RDONLY);
+
+        /* Fail a mount where the logbuf is smaller then the log stripe */
+        if (xfs_sb_version_haslogv2(&mp->m_sb)) {
+                if ((ap->logbufsize <= 0) &&
+                    (mp->m_sb.sb_logsunit > XLOG_BIG_RECORD_BSIZE)) {
+                        mp->m_logbsize = mp->m_sb.sb_logsunit;
+                } else if (ap->logbufsize > 0 &&
+                           ap->logbufsize < mp->m_sb.sb_logsunit) {
+                        cmn_err(CE_WARN,
+        "XFS: 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 (ap->logbufsize > XLOG_BIG_RECORD_BSIZE) {
+                        cmn_err(CE_WARN,
+        "XFS: logbuf size for version 1 logs must be 16K or 32K");
+                        return XFS_ERROR(EINVAL);
+                }
+        }
+
+        /*
+         * mkfs'ed attr2 will turn on attr2 mount unless explicitly
+         * told by noattr2 to turn it off
+         */
+        if (xfs_sb_version_hasattr2(&mp->m_sb) &&
+            !(ap->flags & XFSMNT_NOATTR2))
+                mp->m_flags |= XFS_MOUNT_ATTR2;
+
+        /*
+         * 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");
+                return XFS_ERROR(EROFS);
+        }
+
+        /*
+         * check for shared mount.
+         */
+        if (ap->flags & XFSMNT_SHARED) {
+                if (!xfs_sb_version_hasshared(&mp->m_sb))
+                        return XFS_ERROR(EINVAL);
+
+                /*
+                 * For IRIX 6.5, shared mounts must have the shared
+                 * version bit set, have the persistent readonly
+                 * field set, must be version 0 and can only be mounted
+                 * read-only.
+                 */
+                if (!ronly || !(mp->m_sb.sb_flags & XFS_SBF_READONLY) ||
+                     (mp->m_sb.sb_shared_vn != 0))
+                        return XFS_ERROR(EINVAL);
+
+                mp->m_flags |= XFS_MOUNT_SHARED;
+
+                /*
+                 * Shared XFS V0 can't deal with DMI.  Return EINVAL.
+                 */
+                if (mp->m_sb.sb_shared_vn == 0 && (ap->flags & XFSMNT_DMAPI))
+                        return XFS_ERROR(EINVAL);
+        }
+
+        if (ap->flags & XFSMNT_UQUOTA) {
+                mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE);
+                if (ap->flags & XFSMNT_UQUOTAENF)
+                        mp->m_qflags |= XFS_UQUOTA_ENFD;
+        }
+
+        if (ap->flags & XFSMNT_GQUOTA) {
+                mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
+                if (ap->flags & XFSMNT_GQUOTAENF)
+                        mp->m_qflags |= XFS_OQUOTA_ENFD;
+        } else if (ap->flags & XFSMNT_PQUOTA) {
+                mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
+                if (ap->flags & XFSMNT_PQUOTAENF)
+                        mp->m_qflags |= XFS_OQUOTA_ENFD;
+        }
+
+        return 0;
+}
+
 STATIC int
 xfs_fs_fill_super(
         struct super_block      *sb,
@@ -1308,11 +1735,21 @@ xfs_fs_fill_super(
 {
         struct inode            *root;
         struct xfs_mount        *mp = NULL;
-        struct xfs_mount_args   *args = xfs_args_allocate(sb, silent);
-        int                     error;
+        struct xfs_mount_args   *args;
+        int                     flags = 0, error = ENOMEM;
+
+        args = xfs_args_allocate(sb, silent);
+        if (!args)
+                return -ENOMEM;
 
-        mp = xfs_mount_init();
+        mp = kzalloc(sizeof(struct xfs_mount), GFP_KERNEL);
+        if (!mp)
+                goto out_free_args;
 
+        spin_lock_init(&mp->m_sb_lock);
+        mutex_init(&mp->m_ilock);
+        mutex_init(&mp->m_growlock);
+        atomic_set(&mp->m_active_trans, 0);
         INIT_LIST_HEAD(&mp->m_sync_list);
         spin_lock_init(&mp->m_sync_lock);
         init_waitqueue_head(&mp->m_wait_single_sync_task);
@@ -1325,16 +1762,60 @@ xfs_fs_fill_super(
 
         error = xfs_parseargs(mp, (char *)data, args, 0);
         if (error)
-                goto fail_vfsop;
+                goto out_free_mp;
 
         sb_min_blocksize(sb, BBSIZE);
+        sb->s_xattr = xfs_xattr_handlers;
         sb->s_export_op = &xfs_export_operations;
         sb->s_qcop = &xfs_quotactl_operations;
         sb->s_op = &xfs_super_operations;
 
-        error = xfs_mount(mp, args, NULL);
+        error = xfs_dmops_get(mp, args);
         if (error)
-                goto fail_vfsop;
+                goto out_free_mp;
+        error = xfs_qmops_get(mp, args);
+        if (error)
+                goto out_put_dmops;
+
+        if (args->flags & XFSMNT_QUIET)
+                flags |= XFS_MFSI_QUIET;
+
+        error = xfs_open_devices(mp, args);
+        if (error)
+                goto out_put_qmops;
+
+        if (xfs_icsb_init_counters(mp))
+                mp->m_flags |= XFS_MOUNT_NO_PERCPU_SB;
+
+        /*
+         * Setup flags based on mount(2) options and then the superblock
+         */
+        error = xfs_start_flags(args, mp);
+        if (error)
+                goto out_destroy_counters;
+        error = xfs_readsb(mp, flags);
+        if (error)
+                goto out_destroy_counters;
+        error = xfs_finish_flags(args, mp);
+        if (error)
+                goto out_free_sb;
+
+        error = xfs_setup_devices(mp);
+        if (error)
+                goto out_free_sb;
+
+        if (mp->m_flags & XFS_MOUNT_BARRIER)
+                xfs_mountfs_check_barriers(mp);
+
+        error = xfs_filestream_mount(mp);
+        if (error)
+                goto out_free_sb;
+
+        error = xfs_mountfs(mp, flags);
+        if (error)
+                goto out_filestream_unmount;
+
+        XFS_SEND_MOUNT(mp, DM_RIGHT_NULL, args->mtpt, args->fsname);
 
         sb->s_dirt = 1;
         sb->s_magic = XFS_SB_MAGIC;
@@ -1369,10 +1850,27 @@ xfs_fs_fill_super(
 
         xfs_itrace_exit(XFS_I(sb->s_root->d_inode));
 
-        kmem_free(args, sizeof(*args));
+        kfree(args);
         return 0;
 
-fail_vnrele:
+ out_filestream_unmount:
+        xfs_filestream_unmount(mp);
+ out_free_sb:
+        xfs_freesb(mp);
+ out_destroy_counters:
+        xfs_icsb_destroy_counters(mp);
+        xfs_close_devices(mp);
+ out_put_qmops:
+        xfs_qmops_put(mp);
+ out_put_dmops:
+        xfs_dmops_put(mp);
+ out_free_mp:
+        kfree(mp);
+ out_free_args:
+        kfree(args);
+        return -error;
+
+ fail_vnrele:
         if (sb->s_root) {
                 dput(sb->s_root);
                 sb->s_root = NULL;
@@ -1380,12 +1878,22 @@ fail_vnrele:
                 iput(root);
         }
 
-fail_unmount:
-        xfs_unmount(mp, 0, NULL);
+ fail_unmount:
+        /*
+         * Blow away any referenced inode in the filestreams cache.
+         * This can and will cause log traffic as inodes go inactive
+         * here.
+         */
+        xfs_filestream_unmount(mp);
 
-fail_vfsop:
-        kmem_free(args, sizeof(*args));
-        return -error;
+        XFS_bflush(mp->m_ddev_targp);
+        error = xfs_unmount_flush(mp, 0);
+        WARN_ON(error);
+
+        IRELE(mp->m_rootip);
+
+        xfs_unmountfs(mp);
+        goto out_destroy_counters;
 }
 
 STATIC int
@@ -1430,9 +1938,235 @@ static struct file_system_type xfs_fs_type = {
         .fs_flags               = FS_REQUIRES_DEV,
 };
 
+STATIC int __init
+xfs_alloc_trace_bufs(void)
+{
+#ifdef XFS_ALLOC_TRACE
+        xfs_alloc_trace_buf = ktrace_alloc(XFS_ALLOC_TRACE_SIZE, KM_MAYFAIL);
+        if (!xfs_alloc_trace_buf)
+                goto out;
+#endif
+#ifdef XFS_BMAP_TRACE
+        xfs_bmap_trace_buf = ktrace_alloc(XFS_BMAP_TRACE_SIZE, KM_MAYFAIL);
+        if (!xfs_bmap_trace_buf)
+                goto out_free_alloc_trace;
+#endif
+#ifdef XFS_BMBT_TRACE
+        xfs_bmbt_trace_buf = ktrace_alloc(XFS_BMBT_TRACE_SIZE, KM_MAYFAIL);
+        if (!xfs_bmbt_trace_buf)
+                goto out_free_bmap_trace;
+#endif
+#ifdef XFS_ATTR_TRACE
+        xfs_attr_trace_buf = ktrace_alloc(XFS_ATTR_TRACE_SIZE, KM_MAYFAIL);
+        if (!xfs_attr_trace_buf)
+                goto out_free_bmbt_trace;
+#endif
+#ifdef XFS_DIR2_TRACE
+        xfs_dir2_trace_buf = ktrace_alloc(XFS_DIR2_GTRACE_SIZE, KM_MAYFAIL);
+        if (!xfs_dir2_trace_buf)
+                goto out_free_attr_trace;
+#endif
+
+        return 0;
+
+#ifdef XFS_DIR2_TRACE
+ out_free_attr_trace:
+#endif
+#ifdef XFS_ATTR_TRACE
+        ktrace_free(xfs_attr_trace_buf);
+ out_free_bmbt_trace:
+#endif
+#ifdef XFS_BMBT_TRACE
+        ktrace_free(xfs_bmbt_trace_buf);
+ out_free_bmap_trace:
+#endif
+#ifdef XFS_BMAP_TRACE
+        ktrace_free(xfs_bmap_trace_buf);
+ out_free_alloc_trace:
+#endif
+#ifdef XFS_ALLOC_TRACE
+        ktrace_free(xfs_alloc_trace_buf);
+ out:
+#endif
+        return -ENOMEM;
+}
+
+STATIC void
+xfs_free_trace_bufs(void)
+{
+#ifdef XFS_DIR2_TRACE
+        ktrace_free(xfs_dir2_trace_buf);
+#endif
+#ifdef XFS_ATTR_TRACE
+        ktrace_free(xfs_attr_trace_buf);
+#endif
+#ifdef XFS_BMBT_TRACE
+        ktrace_free(xfs_bmbt_trace_buf);
+#endif
+#ifdef XFS_BMAP_TRACE
+        ktrace_free(xfs_bmap_trace_buf);
+#endif
+#ifdef XFS_ALLOC_TRACE
+        ktrace_free(xfs_alloc_trace_buf);
+#endif
+}
 
 STATIC int __init
-init_xfs_fs( void )
+xfs_init_zones(void)
+{
+        xfs_vnode_zone = kmem_zone_init_flags(sizeof(bhv_vnode_t), "xfs_vnode",
+                                        KM_ZONE_HWALIGN | KM_ZONE_RECLAIM |
+                                        KM_ZONE_SPREAD,
+                                        xfs_fs_inode_init_once);
+        if (!xfs_vnode_zone)
+                goto out;
+
+        xfs_ioend_zone = kmem_zone_init(sizeof(xfs_ioend_t), "xfs_ioend");
+        if (!xfs_ioend_zone)
+                goto out_destroy_vnode_zone;
+
+        xfs_ioend_pool = mempool_create_slab_pool(4 * MAX_BUF_PER_PAGE,
+                                                  xfs_ioend_zone);
+        if (!xfs_ioend_pool)
+                goto out_destroy_ioend_zone;
+
+        xfs_log_ticket_zone = kmem_zone_init(sizeof(xlog_ticket_t),
+                                                "xfs_log_ticket");
+        if (!xfs_log_ticket_zone)
+                goto out_destroy_ioend_pool;
+
+        xfs_bmap_free_item_zone = kmem_zone_init(sizeof(xfs_bmap_free_item_t),
+                                                "xfs_bmap_free_item");
+        if (!xfs_bmap_free_item_zone)
+                goto out_destroy_log_ticket_zone;
+        xfs_btree_cur_zone = kmem_zone_init(sizeof(xfs_btree_cur_t),
+                                                "xfs_btree_cur");
+        if (!xfs_btree_cur_zone)
+                goto out_destroy_bmap_free_item_zone;
+
+        xfs_da_state_zone = kmem_zone_init(sizeof(xfs_da_state_t),
+                                                "xfs_da_state");
+        if (!xfs_da_state_zone)
+                goto out_destroy_btree_cur_zone;
+
+        xfs_dabuf_zone = kmem_zone_init(sizeof(xfs_dabuf_t), "xfs_dabuf");
+        if (!xfs_dabuf_zone)
+                goto out_destroy_da_state_zone;
+
+        xfs_ifork_zone = kmem_zone_init(sizeof(xfs_ifork_t), "xfs_ifork");
+        if (!xfs_ifork_zone)
+                goto out_destroy_dabuf_zone;
+
+        xfs_trans_zone = kmem_zone_init(sizeof(xfs_trans_t), "xfs_trans");
+        if (!xfs_trans_zone)
+                goto out_destroy_ifork_zone;
+
+        /*
+         * The size of the zone allocated buf log item is the maximum
+         * size possible under XFS.  This wastes a little bit of memory,
+         * but it is much faster.
+         */
+        xfs_buf_item_zone = kmem_zone_init((sizeof(xfs_buf_log_item_t) +
+                                (((XFS_MAX_BLOCKSIZE / XFS_BLI_CHUNK) /
+                                  NBWORD) * sizeof(int))), "xfs_buf_item");
+        if (!xfs_buf_item_zone)
+                goto out_destroy_trans_zone;
+
+        xfs_efd_zone = kmem_zone_init((sizeof(xfs_efd_log_item_t) +
+                        ((XFS_EFD_MAX_FAST_EXTENTS - 1) *
+                                 sizeof(xfs_extent_t))), "xfs_efd_item");
+        if (!xfs_efd_zone)
+                goto out_destroy_buf_item_zone;
+
+        xfs_efi_zone = kmem_zone_init((sizeof(xfs_efi_log_item_t) +
+                        ((XFS_EFI_MAX_FAST_EXTENTS - 1) *
+                                sizeof(xfs_extent_t))), "xfs_efi_item");
+        if (!xfs_efi_zone)
+                goto out_destroy_efd_zone;
+
+        xfs_inode_zone =
+                kmem_zone_init_flags(sizeof(xfs_inode_t), "xfs_inode",
+                                        KM_ZONE_HWALIGN | KM_ZONE_RECLAIM |
+                                        KM_ZONE_SPREAD, NULL);
+        if (!xfs_inode_zone)
+                goto out_destroy_efi_zone;
+
+        xfs_ili_zone =
+                kmem_zone_init_flags(sizeof(xfs_inode_log_item_t), "xfs_ili",
+                                        KM_ZONE_SPREAD, NULL);
+        if (!xfs_ili_zone)
+                goto out_destroy_inode_zone;
+
+#ifdef CONFIG_XFS_POSIX_ACL
+        xfs_acl_zone = kmem_zone_init(sizeof(xfs_acl_t), "xfs_acl");
+        if (!xfs_acl_zone)
+                goto out_destroy_ili_zone;
+#endif
+
+        return 0;
+
+#ifdef CONFIG_XFS_POSIX_ACL
+ out_destroy_ili_zone:
+#endif
+        kmem_zone_destroy(xfs_ili_zone);
+ out_destroy_inode_zone:
+        kmem_zone_destroy(xfs_inode_zone);
+ out_destroy_efi_zone:
+        kmem_zone_destroy(xfs_efi_zone);
+ out_destroy_efd_zone:
+        kmem_zone_destroy(xfs_efd_zone);
+ out_destroy_buf_item_zone:
+        kmem_zone_destroy(xfs_buf_item_zone);
+ out_destroy_trans_zone:
+        kmem_zone_destroy(xfs_trans_zone);
+ out_destroy_ifork_zone:
+        kmem_zone_destroy(xfs_ifork_zone);
+ out_destroy_dabuf_zone:
+        kmem_zone_destroy(xfs_dabuf_zone);
+ out_destroy_da_state_zone:
+        kmem_zone_destroy(xfs_da_state_zone);
+ out_destroy_btree_cur_zone:
+        kmem_zone_destroy(xfs_btree_cur_zone);
+ out_destroy_bmap_free_item_zone:
+        kmem_zone_destroy(xfs_bmap_free_item_zone);
+ out_destroy_log_ticket_zone:
+        kmem_zone_destroy(xfs_log_ticket_zone);
+ out_destroy_ioend_pool:
+        mempool_destroy(xfs_ioend_pool);
+ out_destroy_ioend_zone:
+        kmem_zone_destroy(xfs_ioend_zone);
+ out_destroy_vnode_zone:
+        kmem_zone_destroy(xfs_vnode_zone);
+ out:
+        return -ENOMEM;
+}
+
+STATIC void
+xfs_destroy_zones(void)
+{
+#ifdef CONFIG_XFS_POSIX_ACL
+        kmem_zone_destroy(xfs_acl_zone);
+#endif
+        kmem_zone_destroy(xfs_ili_zone);
+        kmem_zone_destroy(xfs_inode_zone);
+        kmem_zone_destroy(xfs_efi_zone);
+        kmem_zone_destroy(xfs_efd_zone);
+        kmem_zone_destroy(xfs_buf_item_zone);
+        kmem_zone_destroy(xfs_trans_zone);
+        kmem_zone_destroy(xfs_ifork_zone);
+        kmem_zone_destroy(xfs_dabuf_zone);
+        kmem_zone_destroy(xfs_da_state_zone);
+        kmem_zone_destroy(xfs_btree_cur_zone);
+        kmem_zone_destroy(xfs_bmap_free_item_zone);
+        kmem_zone_destroy(xfs_log_ticket_zone);
+        mempool_destroy(xfs_ioend_pool);
+        kmem_zone_destroy(xfs_ioend_zone);
+        kmem_zone_destroy(xfs_vnode_zone);
+
+}
+
+STATIC int __init
+init_xfs_fs(void)
 {
         int                     error;
         static char             message[] __initdata = KERN_INFO \
@@ -1441,42 +2175,73 @@ init_xfs_fs( void )
         printk(message);
 
         ktrace_init(64);
+        vn_init();
+        xfs_dir_startup();
 
         error = xfs_init_zones();
-        if (error < 0)
-                goto undo_zones;
+        if (error)
+                goto out;
+
+        error = xfs_alloc_trace_bufs();
+        if (error)
+                goto out_destroy_zones;
+
+        error = xfs_mru_cache_init();
+        if (error)
+                goto out_free_trace_buffers;
+
+        error = xfs_filestream_init();
+        if (error)
+                goto out_mru_cache_uninit;
 
         error = xfs_buf_init();
-        if (error < 0)
-                goto undo_buffers;
+        if (error)
+                goto out_filestream_uninit;
+
+        error = xfs_init_procfs();
+        if (error)
+                goto out_buf_terminate;
+
+        error = xfs_sysctl_register();
+        if (error)
+                goto out_cleanup_procfs;
 
-        vn_init();
-        xfs_init();
-        uuid_init();
         vfs_initquota();
 
         error = register_filesystem(&xfs_fs_type);
         if (error)
-                goto undo_register;
+                goto out_sysctl_unregister;
         return 0;
 
-undo_register:
+ out_sysctl_unregister:
+        xfs_sysctl_unregister();
+ out_cleanup_procfs:
+        xfs_cleanup_procfs();
+ out_buf_terminate:
         xfs_buf_terminate();
-
-undo_buffers:
+ out_filestream_uninit:
+        xfs_filestream_uninit();
+ out_mru_cache_uninit:
+        xfs_mru_cache_uninit();
+ out_free_trace_buffers:
+        xfs_free_trace_bufs();
+ out_destroy_zones:
         xfs_destroy_zones();
-
-undo_zones:
+ out:
         return error;
 }
 
 STATIC void __exit
-exit_xfs_fs( void )
+exit_xfs_fs(void)
 {
         vfs_exitquota();
         unregister_filesystem(&xfs_fs_type);
-        xfs_cleanup();
+        xfs_sysctl_unregister();
+        xfs_cleanup_procfs();
         xfs_buf_terminate();
+        xfs_filestream_uninit();
+        xfs_mru_cache_uninit();
+        xfs_free_trace_bufs();
         xfs_destroy_zones();
         ktrace_uninit();
 }
diff --git a/fs/xfs/linux-2.6/xfs_super.h b/fs/xfs/linux-2.6/xfs_super.h
index 3efb7c6d3303..b7d13da01bd6 100644
--- a/fs/xfs/linux-2.6/xfs_super.h
+++ b/fs/xfs/linux-2.6/xfs_super.h
@@ -107,12 +107,10 @@ extern void xfs_initialize_vnode(struct xfs_mount *mp, bhv_vnode_t *vp,
 extern void xfs_flush_inode(struct xfs_inode *);
 extern void xfs_flush_device(struct xfs_inode *);
 
-extern int  xfs_blkdev_get(struct xfs_mount *, const char *,
-                                struct block_device **);
-extern void xfs_blkdev_put(struct block_device *);
 extern void xfs_blkdev_issue_flush(struct xfs_buftarg *);
 
 extern const struct export_operations xfs_export_operations;
+extern struct xattr_handler *xfs_xattr_handlers[];
 
 #define XFS_M(sb)               ((struct xfs_mount *)((sb)->s_fs_info))
 
diff --git a/fs/xfs/linux-2.6/xfs_sysctl.c b/fs/xfs/linux-2.6/xfs_sysctl.c
index bb997d75c05c..7dacb5bbde3f 100644
--- a/fs/xfs/linux-2.6/xfs_sysctl.c
+++ b/fs/xfs/linux-2.6/xfs_sysctl.c
@@ -259,15 +259,17 @@ static ctl_table xfs_root_table[] = {
         {}
 };
 
-void
+int
 xfs_sysctl_register(void)
 {
         xfs_table_header = register_sysctl_table(xfs_root_table);
+        if (!xfs_table_header)
+                return -ENOMEM;
+        return 0;
 }
 
 void
 xfs_sysctl_unregister(void)
 {
-        if (xfs_table_header)
-                unregister_sysctl_table(xfs_table_header);
+        unregister_sysctl_table(xfs_table_header);
 }
diff --git a/fs/xfs/linux-2.6/xfs_sysctl.h b/fs/xfs/linux-2.6/xfs_sysctl.h
index 98b97e399d6f..4aadb8056c37 100644
--- a/fs/xfs/linux-2.6/xfs_sysctl.h
+++ b/fs/xfs/linux-2.6/xfs_sysctl.h
@@ -93,10 +93,10 @@ enum {
 extern xfs_param_t      xfs_params;
 
 #ifdef CONFIG_SYSCTL
-extern void xfs_sysctl_register(void);
+extern int xfs_sysctl_register(void);
 extern void xfs_sysctl_unregister(void);
 #else
-# define xfs_sysctl_register()          do { } while (0)
+# define xfs_sysctl_register()          (0)
 # define xfs_sysctl_unregister()        do { } while (0)
 #endif /* CONFIG_SYSCTL */
 
diff --git a/fs/xfs/linux-2.6/xfs_vnode.c b/fs/xfs/linux-2.6/xfs_vnode.c
index bc7afe007338..25488b6d9881 100644
--- a/fs/xfs/linux-2.6/xfs_vnode.c
+++ b/fs/xfs/linux-2.6/xfs_vnode.c
@@ -82,56 +82,6 @@ vn_ioerror(
                 xfs_do_force_shutdown(ip->i_mount, SHUTDOWN_DEVICE_REQ, f, l);
 }
 
-/*
- * Revalidate the Linux inode from the XFS inode.
- * Note: i_size _not_ updated; we must hold the inode
- * semaphore when doing that - callers responsibility.
- */
-int
-vn_revalidate(
-        bhv_vnode_t             *vp)
-{
-        struct inode            *inode = vn_to_inode(vp);
-        struct xfs_inode        *ip = XFS_I(inode);
-        struct xfs_mount        *mp = ip->i_mount;
-        unsigned long           xflags;
-
-        xfs_itrace_entry(ip);
-
-        if (XFS_FORCED_SHUTDOWN(mp))
-                return -EIO;
-
-        xfs_ilock(ip, XFS_ILOCK_SHARED);
-        inode->i_mode       = ip->i_d.di_mode;
-        inode->i_uid        = ip->i_d.di_uid;
-        inode->i_gid        = ip->i_d.di_gid;
-        inode->i_mtime.tv_sec = ip->i_d.di_mtime.t_sec;
-        inode->i_mtime.tv_nsec = ip->i_d.di_mtime.t_nsec;
-        inode->i_ctime.tv_sec = ip->i_d.di_ctime.t_sec;
-        inode->i_ctime.tv_nsec = ip->i_d.di_ctime.t_nsec;
-
-        xflags = xfs_ip2xflags(ip);
-        if (xflags & XFS_XFLAG_IMMUTABLE)
-                inode->i_flags |= S_IMMUTABLE;
-        else
-                inode->i_flags &= ~S_IMMUTABLE;
-        if (xflags & XFS_XFLAG_APPEND)
-                inode->i_flags |= S_APPEND;
-        else
-                inode->i_flags &= ~S_APPEND;
-        if (xflags & XFS_XFLAG_SYNC)
-                inode->i_flags |= S_SYNC;
-        else
-                inode->i_flags &= ~S_SYNC;
-        if (xflags & XFS_XFLAG_NOATIME)
-                inode->i_flags |= S_NOATIME;
-        else
-                inode->i_flags &= ~S_NOATIME;
-        xfs_iunlock(ip, XFS_ILOCK_SHARED);
-
-        xfs_iflags_clear(ip, XFS_IMODIFIED);
-        return 0;
-}
 
 /*
  * Add a reference to a referenced vnode.
diff --git a/fs/xfs/linux-2.6/xfs_vnode.h b/fs/xfs/linux-2.6/xfs_vnode.h
index 25eb2a9e8d9b..41ca2cec5d31 100644
--- a/fs/xfs/linux-2.6/xfs_vnode.h
+++ b/fs/xfs/linux-2.6/xfs_vnode.h
@@ -19,7 +19,6 @@
 #define __XFS_VNODE_H__
 
 struct file;
-struct bhv_vattr;
 struct xfs_iomap;
 struct attrlist_cursor_kern;
 
@@ -66,87 +65,8 @@ static inline struct inode *vn_to_inode(bhv_vnode_t *vnode)
                                            Prevent VM access to the pages until
                                            the operation completes. */
 
-/*
- * Vnode attributes.  va_mask indicates those attributes the caller
- * wants to set or extract.
- */
-typedef struct bhv_vattr {
-        int             va_mask;        /* bit-mask of attributes present */
-        mode_t          va_mode;        /* file access mode and type */
-        xfs_nlink_t     va_nlink;       /* number of references to file */
-        uid_t           va_uid;         /* owner user id */
-        gid_t           va_gid;         /* owner group id */
-        xfs_ino_t       va_nodeid;      /* file id */
-        xfs_off_t       va_size;        /* file size in bytes */
-        u_long          va_blocksize;   /* blocksize preferred for i/o */
-        struct timespec va_atime;       /* time of last access */
-        struct timespec va_mtime;       /* time of last modification */
-        struct timespec va_ctime;       /* time file changed */
-        u_int           va_gen;         /* generation number of file */
-        xfs_dev_t       va_rdev;        /* device the special file represents */
-        __int64_t       va_nblocks;     /* number of blocks allocated */
-        u_long          va_xflags;      /* random extended file flags */
-        u_long          va_extsize;     /* file extent size */
-        u_long          va_nextents;    /* number of extents in file */
-        u_long          va_anextents;   /* number of attr extents in file */
-        prid_t          va_projid;      /* project id */
-} bhv_vattr_t;
-
-/*
- * setattr or getattr attributes
- */
-#define XFS_AT_TYPE             0x00000001
-#define XFS_AT_MODE             0x00000002
-#define XFS_AT_UID              0x00000004
-#define XFS_AT_GID              0x00000008
-#define XFS_AT_FSID             0x00000010
-#define XFS_AT_NODEID           0x00000020
-#define XFS_AT_NLINK            0x00000040
-#define XFS_AT_SIZE             0x00000080
-#define XFS_AT_ATIME            0x00000100
-#define XFS_AT_MTIME            0x00000200
-#define XFS_AT_CTIME            0x00000400
-#define XFS_AT_RDEV             0x00000800
-#define XFS_AT_BLKSIZE          0x00001000
-#define XFS_AT_NBLOCKS          0x00002000
-#define XFS_AT_VCODE            0x00004000
-#define XFS_AT_MAC              0x00008000
-#define XFS_AT_UPDATIME         0x00010000
-#define XFS_AT_UPDMTIME         0x00020000
-#define XFS_AT_UPDCTIME         0x00040000
-#define XFS_AT_ACL              0x00080000
-#define XFS_AT_CAP              0x00100000
-#define XFS_AT_INF              0x00200000
-#define XFS_AT_XFLAGS           0x00400000
-#define XFS_AT_EXTSIZE          0x00800000
-#define XFS_AT_NEXTENTS         0x01000000
-#define XFS_AT_ANEXTENTS        0x02000000
-#define XFS_AT_PROJID           0x04000000
-#define XFS_AT_SIZE_NOPERM      0x08000000
-#define XFS_AT_GENCOUNT         0x10000000
-
-#define XFS_AT_ALL      (XFS_AT_TYPE|XFS_AT_MODE|XFS_AT_UID|XFS_AT_GID|\
-                XFS_AT_FSID|XFS_AT_NODEID|XFS_AT_NLINK|XFS_AT_SIZE|\
-                XFS_AT_ATIME|XFS_AT_MTIME|XFS_AT_CTIME|XFS_AT_RDEV|\
-                XFS_AT_BLKSIZE|XFS_AT_NBLOCKS|XFS_AT_VCODE|XFS_AT_MAC|\
-                XFS_AT_ACL|XFS_AT_CAP|XFS_AT_INF|XFS_AT_XFLAGS|XFS_AT_EXTSIZE|\
-                XFS_AT_NEXTENTS|XFS_AT_ANEXTENTS|XFS_AT_PROJID|XFS_AT_GENCOUNT)
-
-#define XFS_AT_STAT     (XFS_AT_TYPE|XFS_AT_MODE|XFS_AT_UID|XFS_AT_GID|\
-                XFS_AT_FSID|XFS_AT_NODEID|XFS_AT_NLINK|XFS_AT_SIZE|\
-                XFS_AT_ATIME|XFS_AT_MTIME|XFS_AT_CTIME|XFS_AT_RDEV|\
-                XFS_AT_BLKSIZE|XFS_AT_NBLOCKS|XFS_AT_PROJID)
-
-#define XFS_AT_TIMES    (XFS_AT_ATIME|XFS_AT_MTIME|XFS_AT_CTIME)
-
-#define XFS_AT_UPDTIMES (XFS_AT_UPDATIME|XFS_AT_UPDMTIME|XFS_AT_UPDCTIME)
-
-#define XFS_AT_NOSET    (XFS_AT_NLINK|XFS_AT_RDEV|XFS_AT_FSID|XFS_AT_NODEID|\
-                XFS_AT_TYPE|XFS_AT_BLKSIZE|XFS_AT_NBLOCKS|XFS_AT_VCODE|\
-                XFS_AT_NEXTENTS|XFS_AT_ANEXTENTS|XFS_AT_GENCOUNT)
 
 extern void     vn_init(void);
-extern int      vn_revalidate(bhv_vnode_t *);
 
 /*
  * Yeah, these don't take vnode anymore at all, all this should be
@@ -219,15 +139,6 @@ static inline void vn_atime_to_time_t(bhv_vnode_t *vp, time_t *tt)
 #define VN_DIRTY(vp)    mapping_tagged(vn_to_inode(vp)->i_mapping, \
                                         PAGECACHE_TAG_DIRTY)
 
-/*
- * Flags to vop_setattr/getattr.
- */
-#define ATTR_UTIME      0x01    /* non-default utime(2) request */
-#define ATTR_DMI        0x08    /* invocation from a DMI function */
-#define ATTR_LAZY       0x80    /* set/get attributes lazily */
-#define ATTR_NONBLOCK   0x100   /* return EAGAIN if operation would block */
-#define ATTR_NOLOCK     0x200   /* Don't grab any conflicting locks */
-#define ATTR_NOSIZETOK  0x400   /* Don't get the SIZE token */
 
 /*
  * Tracking vnode activity.
diff --git a/fs/xfs/linux-2.6/xfs_xattr.c b/fs/xfs/linux-2.6/xfs_xattr.c
new file mode 100644
index 000000000000..964621fde6ed
--- /dev/null
+++ b/fs/xfs/linux-2.6/xfs_xattr.c
@@ -0,0 +1,330 @@
+/*
+ * Copyright (C) 2008 Christoph Hellwig.
+ * Portions Copyright (C) 2000-2008 Silicon Graphics, Inc.
+ *
+ * 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_da_btree.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_inode.h"
+#include "xfs_attr.h"
+#include "xfs_attr_leaf.h"
+#include "xfs_acl.h"
+#include "xfs_vnodeops.h"
+
+#include <linux/posix_acl_xattr.h>
+#include <linux/xattr.h>
+
+
+/*
+ * ACL handling.  Should eventually be moved into xfs_acl.c
+ */
+
+static int
+xfs_decode_acl(const char *name)
+{
+        if (strcmp(name, "posix_acl_access") == 0)
+                return _ACL_TYPE_ACCESS;
+        else if (strcmp(name, "posix_acl_default") == 0)
+                return _ACL_TYPE_DEFAULT;
+        return -EINVAL;
+}
+
+/*
+ * Get system extended attributes which at the moment only
+ * includes Posix ACLs.
+ */
+static int
+xfs_xattr_system_get(struct inode *inode, const char *name,
+                void *buffer, size_t size)
+{
+        int acl;
+
+        acl = xfs_decode_acl(name);
+        if (acl < 0)
+                return acl;
+
+        return xfs_acl_vget(inode, buffer, size, acl);
+}
+
+static int
+xfs_xattr_system_set(struct inode *inode, const char *name,
+                const void *value, size_t size, int flags)
+{
+        int acl;
+
+        acl = xfs_decode_acl(name);
+        if (acl < 0)
+                return acl;
+        if (flags & XATTR_CREATE)
+                return -EINVAL;
+
+        if (!value)
+                return xfs_acl_vremove(inode, acl);
+
+        return xfs_acl_vset(inode, (void *)value, size, acl);
+}
+
+static struct xattr_handler xfs_xattr_system_handler = {
+        .prefix = XATTR_SYSTEM_PREFIX,
+        .get    = xfs_xattr_system_get,
+        .set    = xfs_xattr_system_set,
+};
+
+
+/*
+ * Real xattr handling.  The only difference between the namespaces is
+ * a flag passed to the low-level attr code.
+ */
+
+static int
+__xfs_xattr_get(struct inode *inode, const char *name,
+                void *value, size_t size, int xflags)
+{
+        struct xfs_inode *ip = XFS_I(inode);
+        int error, asize = size;
+
+        if (strcmp(name, "") == 0)
+                return -EINVAL;
+
+        /* Convert Linux syscall to XFS internal ATTR flags */
+        if (!size) {
+                xflags |= ATTR_KERNOVAL;
+                value = NULL;
+        }
+
+        error = -xfs_attr_get(ip, name, value, &asize, xflags);
+        if (error)
+                return error;
+        return asize;
+}
+
+static int
+__xfs_xattr_set(struct inode *inode, const char *name, const void *value,
+                size_t size, int flags, int xflags)
+{
+        struct xfs_inode *ip = XFS_I(inode);
+
+        if (strcmp(name, "") == 0)
+                return -EINVAL;
+
+        /* Convert Linux syscall to XFS internal ATTR flags */
+        if (flags & XATTR_CREATE)
+                xflags |= ATTR_CREATE;
+        if (flags & XATTR_REPLACE)
+                xflags |= ATTR_REPLACE;
+
+        if (!value)
+                return -xfs_attr_remove(ip, name, xflags);
+        return -xfs_attr_set(ip, name, (void *)value, size, xflags);
+}
+
+static int
+xfs_xattr_user_get(struct inode *inode, const char *name,
+                void *value, size_t size)
+{
+        return __xfs_xattr_get(inode, name, value, size, 0);
+}
+
+static int
+xfs_xattr_user_set(struct inode *inode, const char *name,
+                const void *value, size_t size, int flags)
+{
+        return __xfs_xattr_set(inode, name, value, size, flags, 0);
+}
+
+static struct xattr_handler xfs_xattr_user_handler = {
+        .prefix = XATTR_USER_PREFIX,
+        .get    = xfs_xattr_user_get,
+        .set    = xfs_xattr_user_set,
+};
+
+
+static int
+xfs_xattr_trusted_get(struct inode *inode, const char *name,
+                void *value, size_t size)
+{
+        return __xfs_xattr_get(inode, name, value, size, ATTR_ROOT);
+}
+
+static int
+xfs_xattr_trusted_set(struct inode *inode, const char *name,
+                const void *value, size_t size, int flags)
+{
+        return __xfs_xattr_set(inode, name, value, size, flags, ATTR_ROOT);
+}
+
+static struct xattr_handler xfs_xattr_trusted_handler = {
+        .prefix = XATTR_TRUSTED_PREFIX,
+        .get    = xfs_xattr_trusted_get,
+        .set    = xfs_xattr_trusted_set,
+};
+
+
+static int
+xfs_xattr_secure_get(struct inode *inode, const char *name,
+                void *value, size_t size)
+{
+        return __xfs_xattr_get(inode, name, value, size, ATTR_SECURE);
+}
+
+static int
+xfs_xattr_secure_set(struct inode *inode, const char *name,
+                const void *value, size_t size, int flags)
+{
+        return __xfs_xattr_set(inode, name, value, size, flags, ATTR_SECURE);
+}
+
+static struct xattr_handler xfs_xattr_security_handler = {
+        .prefix = XATTR_SECURITY_PREFIX,
+        .get    = xfs_xattr_secure_get,
+        .set    = xfs_xattr_secure_set,
+};
+
+
+struct xattr_handler *xfs_xattr_handlers[] = {
+        &xfs_xattr_user_handler,
+        &xfs_xattr_trusted_handler,
+        &xfs_xattr_security_handler,
+        &xfs_xattr_system_handler,
+        NULL
+};
+
+static unsigned int xfs_xattr_prefix_len(int flags)
+{
+        if (flags & XFS_ATTR_SECURE)
+                return sizeof("security");
+        else if (flags & XFS_ATTR_ROOT)
+                return sizeof("trusted");
+        else
+                return sizeof("user");
+}
+
+static const char *xfs_xattr_prefix(int flags)
+{
+        if (flags & XFS_ATTR_SECURE)
+                return xfs_xattr_security_handler.prefix;
+        else if (flags & XFS_ATTR_ROOT)
+                return xfs_xattr_trusted_handler.prefix;
+        else
+                return xfs_xattr_user_handler.prefix;
+}
+
+static int
+xfs_xattr_put_listent(struct xfs_attr_list_context *context, int flags,
+                char *name, int namelen, int valuelen, char *value)
+{
+        unsigned int prefix_len = xfs_xattr_prefix_len(flags);
+        char *offset;
+        int arraytop;
+
+        ASSERT(context->count >= 0);
+
+        /*
+         * Only show root namespace entries if we are actually allowed to
+         * see them.
+         */
+        if ((flags & XFS_ATTR_ROOT) && !capable(CAP_SYS_ADMIN))
+                return 0;
+
+        arraytop = context->count + prefix_len + namelen + 1;
+        if (arraytop > context->firstu) {
+                context->count = -1;    /* insufficient space */
+                return 1;
+        }
+        offset = (char *)context->alist + context->count;
+        strncpy(offset, xfs_xattr_prefix(flags), prefix_len);
+        offset += prefix_len;
+        strncpy(offset, name, namelen);                 /* real name */
+        offset += namelen;
+        *offset = '\0';
+        context->count += prefix_len + namelen + 1;
+        return 0;
+}
+
+static int
+xfs_xattr_put_listent_sizes(struct xfs_attr_list_context *context, int flags,
+                char *name, int namelen, int valuelen, char *value)
+{
+        context->count += xfs_xattr_prefix_len(flags) + namelen + 1;
+        return 0;
+}
+
+static int
+list_one_attr(const char *name, const size_t len, void *data,
+                size_t size, ssize_t *result)
+{
+        char *p = data + *result;
+
+        *result += len;
+        if (!size)
+                return 0;
+        if (*result > size)
+                return -ERANGE;
+
+        strcpy(p, name);
+        return 0;
+}
+
+ssize_t
+xfs_vn_listxattr(struct dentry *dentry, char *data, size_t size)
+{
+        struct xfs_attr_list_context context;
+        struct attrlist_cursor_kern cursor = { 0 };
+        struct inode            *inode = dentry->d_inode;
+        int                     error;
+
+        /*
+         * First read the regular on-disk attributes.
+         */
+        memset(&context, 0, sizeof(context));
+        context.dp = XFS_I(inode);
+        context.cursor = &cursor;
+        context.resynch = 1;
+        context.alist = data;
+        context.bufsize = size;
+        context.firstu = context.bufsize;
+
+        if (size)
+                context.put_listent = xfs_xattr_put_listent;
+        else
+                context.put_listent = xfs_xattr_put_listent_sizes;
+
+        xfs_attr_list_int(&context);
+        if (context.count < 0)
+                return -ERANGE;
+
+        /*
+         * Then add the two synthetic ACL attributes.
+         */
+        if (xfs_acl_vhasacl_access(inode)) {
+                error = list_one_attr(POSIX_ACL_XATTR_ACCESS,
+                                strlen(POSIX_ACL_XATTR_ACCESS) + 1,
+                                data, size, &context.count);
+                if (error)
+                        return error;
+        }
+
+        if (xfs_acl_vhasacl_default(inode)) {
+                error = list_one_attr(POSIX_ACL_XATTR_DEFAULT,
+                                strlen(POSIX_ACL_XATTR_DEFAULT) + 1,
+                                data, size, &context.count);
+                if (error)
+                        return error;
+        }
+
+        return context.count;
+}
diff --git a/fs/xfs/quota/xfs_dquot.c b/fs/xfs/quota/xfs_dquot.c
index 85df3288efd5..fc9f3fb39b7b 100644
--- a/fs/xfs/quota/xfs_dquot.c
+++ b/fs/xfs/quota/xfs_dquot.c
@@ -1435,8 +1435,7 @@ xfs_dqlock2(
 /* ARGSUSED */
 int
 xfs_qm_dqpurge(
-        xfs_dquot_t     *dqp,
-        uint            flags)
+        xfs_dquot_t     *dqp)
 {
         xfs_dqhash_t    *thishash;
         xfs_mount_t     *mp = dqp->q_mount;
diff --git a/fs/xfs/quota/xfs_dquot.h b/fs/xfs/quota/xfs_dquot.h
index 5c371a92e3e2..f7393bba4e95 100644
--- a/fs/xfs/quota/xfs_dquot.h
+++ b/fs/xfs/quota/xfs_dquot.h
@@ -164,7 +164,7 @@ extern void		xfs_qm_dqprint(xfs_dquot_t *);
 
 extern void             xfs_qm_dqdestroy(xfs_dquot_t *);
 extern int              xfs_qm_dqflush(xfs_dquot_t *, uint);
-extern int              xfs_qm_dqpurge(xfs_dquot_t *, uint);
+extern int              xfs_qm_dqpurge(xfs_dquot_t *);
 extern void             xfs_qm_dqunpin_wait(xfs_dquot_t *);
 extern int              xfs_qm_dqlock_nowait(xfs_dquot_t *);
 extern int              xfs_qm_dqflock_nowait(xfs_dquot_t *);
diff --git a/fs/xfs/quota/xfs_dquot_item.c b/fs/xfs/quota/xfs_dquot_item.c
index 36e05ca78412..08d2fc89e6a1 100644
--- a/fs/xfs/quota/xfs_dquot_item.c
+++ b/fs/xfs/quota/xfs_dquot_item.c
@@ -576,8 +576,8 @@ xfs_qm_qoffend_logitem_committed(
          * xfs_trans_delete_ail() drops the AIL lock.
          */
         xfs_trans_delete_ail(qfs->qql_item.li_mountp, (xfs_log_item_t *)qfs);
-        kmem_free(qfs, sizeof(xfs_qoff_logitem_t));
-        kmem_free(qfe, sizeof(xfs_qoff_logitem_t));
+        kmem_free(qfs);
+        kmem_free(qfe);
         return (xfs_lsn_t)-1;
 }
 
diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c
index d31cce1165c5..021934a3d456 100644
--- a/fs/xfs/quota/xfs_qm.c
+++ b/fs/xfs/quota/xfs_qm.c
@@ -192,8 +192,8 @@ xfs_qm_destroy(
                 xfs_qm_list_destroy(&(xqm->qm_usr_dqhtable[i]));
                 xfs_qm_list_destroy(&(xqm->qm_grp_dqhtable[i]));
         }
-        kmem_free(xqm->qm_usr_dqhtable, hsize * sizeof(xfs_dqhash_t));
-        kmem_free(xqm->qm_grp_dqhtable, hsize * sizeof(xfs_dqhash_t));
+        kmem_free(xqm->qm_usr_dqhtable);
+        kmem_free(xqm->qm_grp_dqhtable);
         xqm->qm_usr_dqhtable = NULL;
         xqm->qm_grp_dqhtable = NULL;
         xqm->qm_dqhashmask = 0;
@@ -201,7 +201,7 @@ xfs_qm_destroy(
 #ifdef DEBUG
         mutex_destroy(&qcheck_lock);
 #endif
-        kmem_free(xqm, sizeof(xfs_qm_t));
+        kmem_free(xqm);
 }
 
 /*
@@ -445,11 +445,11 @@ xfs_qm_unmount_quotas(
                 }
         }
         if (uqp) {
-                 XFS_PURGE_INODE(uqp);
+                 IRELE(uqp);
                  mp->m_quotainfo->qi_uquotaip = NULL;
         }
         if (gqp) {
-                XFS_PURGE_INODE(gqp);
+                IRELE(gqp);
                 mp->m_quotainfo->qi_gquotaip = NULL;
         }
 out:
@@ -631,7 +631,7 @@ xfs_qm_dqpurge_int(
                  * freelist in INACTIVE state.
                  */
                 nextdqp = dqp->MPL_NEXT;
-                nmisses += xfs_qm_dqpurge(dqp, flags);
+                nmisses += xfs_qm_dqpurge(dqp);
                 dqp = nextdqp;
         }
         xfs_qm_mplist_unlock(mp);
@@ -1134,7 +1134,7 @@ xfs_qm_init_quotainfo(
          * and change the superblock accordingly.
          */
         if ((error = xfs_qm_init_quotainos(mp))) {
-                kmem_free(qinf, sizeof(xfs_quotainfo_t));
+                kmem_free(qinf);
                 mp->m_quotainfo = NULL;
                 return error;
         }
@@ -1240,15 +1240,15 @@ xfs_qm_destroy_quotainfo(
         xfs_qm_list_destroy(&qi->qi_dqlist);
 
         if (qi->qi_uquotaip) {
-                XFS_PURGE_INODE(qi->qi_uquotaip);
+                IRELE(qi->qi_uquotaip);
                 qi->qi_uquotaip = NULL; /* paranoia */
         }
         if (qi->qi_gquotaip) {
-                XFS_PURGE_INODE(qi->qi_gquotaip);
+                IRELE(qi->qi_gquotaip);
                 qi->qi_gquotaip = NULL;
         }
         mutex_destroy(&qi->qi_quotaofflock);
-        kmem_free(qi, sizeof(xfs_quotainfo_t));
+        kmem_free(qi);
         mp->m_quotainfo = NULL;
 }
 
@@ -1394,7 +1394,7 @@ xfs_qm_qino_alloc(
          * locked exclusively and joined to the transaction already.
          */
         ASSERT(xfs_isilocked(*ip, XFS_ILOCK_EXCL));
-        VN_HOLD(XFS_ITOV((*ip)));
+        IHOLD(*ip);
 
         /*
          * Make the changes in the superblock, and log those too.
@@ -1623,7 +1623,7 @@ xfs_qm_dqiterate(
                         break;
         } while (nmaps > 0);
 
-        kmem_free(map, XFS_DQITER_MAP_SIZE * sizeof(*map));
+        kmem_free(map);
 
         return error;
 }
diff --git a/fs/xfs/quota/xfs_qm_syscalls.c b/fs/xfs/quota/xfs_qm_syscalls.c
index 768a3b27d2b6..adfb8723f65a 100644
--- a/fs/xfs/quota/xfs_qm_syscalls.c
+++ b/fs/xfs/quota/xfs_qm_syscalls.c
@@ -362,11 +362,11 @@ xfs_qm_scall_quotaoff(
          * if we don't need them anymore.
          */
         if ((dqtype & XFS_QMOPT_UQUOTA) && XFS_QI_UQIP(mp)) {
-                XFS_PURGE_INODE(XFS_QI_UQIP(mp));
+                IRELE(XFS_QI_UQIP(mp));
                 XFS_QI_UQIP(mp) = NULL;
         }
         if ((dqtype & (XFS_QMOPT_GQUOTA|XFS_QMOPT_PQUOTA)) && XFS_QI_GQIP(mp)) {
-                XFS_PURGE_INODE(XFS_QI_GQIP(mp));
+                IRELE(XFS_QI_GQIP(mp));
                 XFS_QI_GQIP(mp) = NULL;
         }
 out_error:
@@ -1449,14 +1449,14 @@ xfs_qm_internalqcheck(
                 for (d = (xfs_dqtest_t *) h1->qh_next; d != NULL; ) {
                         xfs_dqtest_cmp(d);
                         e = (xfs_dqtest_t *) d->HL_NEXT;
-                        kmem_free(d, sizeof(xfs_dqtest_t));
+                        kmem_free(d);
                         d = e;
                 }
                 h1 = &qmtest_gdqtab[i];
                 for (d = (xfs_dqtest_t *) h1->qh_next; d != NULL; ) {
                         xfs_dqtest_cmp(d);
                         e = (xfs_dqtest_t *) d->HL_NEXT;
-                        kmem_free(d, sizeof(xfs_dqtest_t));
+                        kmem_free(d);
                         d = e;
                 }
         }
@@ -1467,8 +1467,8 @@ xfs_qm_internalqcheck(
         } else {
                 cmn_err(CE_DEBUG, "******** quotacheck successful! ********");
         }
-        kmem_free(qmtest_udqtab, qmtest_hashmask * sizeof(xfs_dqhash_t));
-        kmem_free(qmtest_gdqtab, qmtest_hashmask * sizeof(xfs_dqhash_t));
+        kmem_free(qmtest_udqtab);
+        kmem_free(qmtest_gdqtab);
         mutex_unlock(&qcheck_lock);
         return (qmtest_nfails);
 }
diff --git a/fs/xfs/quota/xfs_quota_priv.h b/fs/xfs/quota/xfs_quota_priv.h
index 5e4a40b1c565..c4fcea600bc2 100644
--- a/fs/xfs/quota/xfs_quota_priv.h
+++ b/fs/xfs/quota/xfs_quota_priv.h
@@ -158,9 +158,6 @@ for ((dqp) = (qlist)->qh_next; (dqp) != (xfs_dquot_t *)(qlist); \
 #define XFS_IS_SUSER_DQUOT(dqp)         \
         (!((dqp)->q_core.d_id))
 
-#define XFS_PURGE_INODE(ip)             \
-        IRELE(ip);
-
 #define DQFLAGTO_TYPESTR(d)     (((d)->dq_flags & XFS_DQ_USER) ? "USR" : \
                                  (((d)->dq_flags & XFS_DQ_GROUP) ? "GRP" : \
                                  (((d)->dq_flags & XFS_DQ_PROJ) ? "PRJ":"???")))
diff --git a/fs/xfs/support/ktrace.c b/fs/xfs/support/ktrace.c
index 0b75d302508f..a34ef05489b1 100644
--- a/fs/xfs/support/ktrace.c
+++ b/fs/xfs/support/ktrace.c
@@ -89,7 +89,7 @@ ktrace_alloc(int nentries, unsigned int __nocast sleep)
                 if (sleep & KM_SLEEP)
                         panic("ktrace_alloc: NULL memory on KM_SLEEP request!");
 
-                kmem_free(ktp, sizeof(*ktp));
+                kmem_free(ktp);
 
                 return NULL;
         }
@@ -126,7 +126,7 @@ ktrace_free(ktrace_t *ktp)
         } else {
                 entries_size = (int)(ktp->kt_nentries * sizeof(ktrace_entry_t));
 
-                kmem_free(ktp->kt_entries, entries_size);
+                kmem_free(ktp->kt_entries);
         }
 
         kmem_zone_free(ktrace_hdr_zone, ktp);
diff --git a/fs/xfs/support/uuid.c b/fs/xfs/support/uuid.c
index 493a6ecf8590..5830c040ea7e 100644
--- a/fs/xfs/support/uuid.c
+++ b/fs/xfs/support/uuid.c
@@ -17,7 +17,7 @@
  */
 #include <xfs.h>
 
-static mutex_t  uuid_monitor;
+static DEFINE_MUTEX(uuid_monitor);
 static int      uuid_table_size;
 static uuid_t   *uuid_table;
 
@@ -132,9 +132,3 @@ uuid_table_remove(uuid_t *uuid)
         ASSERT(i < uuid_table_size);
         mutex_unlock(&uuid_monitor);
 }
-
-void __init
-uuid_init(void)
-{
-        mutex_init(&uuid_monitor);
-}
diff --git a/fs/xfs/support/uuid.h b/fs/xfs/support/uuid.h
index b6f5922199ba..cff5b607d445 100644
--- a/fs/xfs/support/uuid.h
+++ b/fs/xfs/support/uuid.h
@@ -22,7 +22,6 @@ typedef struct {
         unsigned char   __u_bits[16];
 } uuid_t;
 
-extern void uuid_init(void);
 extern void uuid_create_nil(uuid_t *uuid);
 extern int uuid_is_nil(uuid_t *uuid);
 extern int uuid_equal(uuid_t *uuid1, uuid_t *uuid2);
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index ebee3a4f703a..3e4648ad9cfc 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -341,8 +341,7 @@ xfs_acl_iaccess(
 
         /* If the file has no ACL return -1. */
         rval = sizeof(xfs_acl_t);
-        if (xfs_attr_fetch(ip, &acl_name, (char *)acl, &rval,
-                                        ATTR_ROOT | ATTR_KERNACCESS)) {
+        if (xfs_attr_fetch(ip, &acl_name, (char *)acl, &rval, ATTR_ROOT)) {
                 _ACL_FREE(acl);
                 return -1;
         }
@@ -720,7 +719,7 @@ xfs_acl_setmode(
         xfs_acl_t       *acl,
         int             *basicperms)
 {
-        bhv_vattr_t     va;
+        struct iattr    iattr;
         xfs_acl_entry_t *ap;
         xfs_acl_entry_t *gap = NULL;
         int             i, nomask = 1;
@@ -734,25 +733,25 @@ xfs_acl_setmode(
          * Copy the u::, g::, o::, and m:: bits from the ACL into the
          * mode.  The m:: bits take precedence over the g:: bits.
          */
-        va.va_mask = XFS_AT_MODE;
-        va.va_mode = xfs_vtoi(vp)->i_d.di_mode;
-        va.va_mode &= ~(S_IRWXU|S_IRWXG|S_IRWXO);
+        iattr.ia_valid = ATTR_MODE;
+        iattr.ia_mode = xfs_vtoi(vp)->i_d.di_mode;
+        iattr.ia_mode &= ~(S_IRWXU|S_IRWXG|S_IRWXO);
         ap = acl->acl_entry;
         for (i = 0; i < acl->acl_cnt; ++i) {
                 switch (ap->ae_tag) {
                 case ACL_USER_OBJ:
-                        va.va_mode |= ap->ae_perm << 6;
+                        iattr.ia_mode |= ap->ae_perm << 6;
                         break;
                 case ACL_GROUP_OBJ:
                         gap = ap;
                         break;
                 case ACL_MASK:  /* more than just standard modes */
                         nomask = 0;
-                        va.va_mode |= ap->ae_perm << 3;
+                        iattr.ia_mode |= ap->ae_perm << 3;
                         *basicperms = 0;
                         break;
                 case ACL_OTHER:
-                        va.va_mode |= ap->ae_perm;
+                        iattr.ia_mode |= ap->ae_perm;
                         break;
                 default:        /* more than just standard modes */
                         *basicperms = 0;
@@ -763,9 +762,9 @@ xfs_acl_setmode(
 
         /* Set the group bits from ACL_GROUP_OBJ if there's no ACL_MASK */
         if (gap && nomask)
-                va.va_mode |= gap->ae_perm << 3;
+                iattr.ia_mode |= gap->ae_perm << 3;
 
-        return xfs_setattr(xfs_vtoi(vp), &va, 0, sys_cred);
+        return xfs_setattr(xfs_vtoi(vp), &iattr, 0, sys_cred);
 }
 
 /*
diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h
index 332a772461c4..323ee94cf831 100644
--- a/fs/xfs/xfs_acl.h
+++ b/fs/xfs/xfs_acl.h
@@ -46,6 +46,8 @@ typedef struct xfs_acl {
 #define SGI_ACL_FILE_SIZE       (sizeof(SGI_ACL_FILE)-1)
 #define SGI_ACL_DEFAULT_SIZE    (sizeof(SGI_ACL_DEFAULT)-1)
 
+#define _ACL_TYPE_ACCESS        1
+#define _ACL_TYPE_DEFAULT       2
 
 #ifdef CONFIG_XFS_POSIX_ACL
 
@@ -66,8 +68,6 @@ extern int xfs_acl_vset(bhv_vnode_t *, void *, size_t, int);
 extern int xfs_acl_vget(bhv_vnode_t *, void *, size_t, int);
 extern int xfs_acl_vremove(bhv_vnode_t *, int);
 
-#define _ACL_TYPE_ACCESS        1
-#define _ACL_TYPE_DEFAULT       2
 #define _ACL_PERM_INVALID(perm) ((perm) & ~(ACL_READ|ACL_WRITE|ACL_EXECUTE))
 
 #define _ACL_INHERIT(c,m,d)     (xfs_acl_inherit(c,m,d))
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index df151a859186..78de80e3caa2 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -16,8 +16,6 @@
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 
-#include <linux/capability.h>
-
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_types.h"
@@ -57,11 +55,6 @@
  * Provide the external interfaces to manage attribute lists.
  */
 
-#define ATTR_SYSCOUNT   2
-static struct attrnames posix_acl_access;
-static struct attrnames posix_acl_default;
-static struct attrnames *attr_system_names[ATTR_SYSCOUNT];
-
 /*========================================================================
  * Function prototypes for the kernel.
  *========================================================================*/
@@ -116,6 +109,17 @@ xfs_attr_name_to_xname(
         return 0;
 }
 
+STATIC int
+xfs_inode_hasattr(
+        struct xfs_inode        *ip)
+{
+        if (!XFS_IFORK_Q(ip) ||
+            (ip->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS &&
+             ip->i_d.di_anextents == 0))
+                return 0;
+        return 1;
+}
+
 /*========================================================================
  * Overall external interface routines.
  *========================================================================*/
@@ -127,10 +131,8 @@ xfs_attr_fetch(xfs_inode_t *ip, struct xfs_name *name,
         xfs_da_args_t   args;
         int             error;
 
-        if ((XFS_IFORK_Q(ip) == 0) ||
-            (ip->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS &&
-             ip->i_d.di_anextents == 0))
-                return(ENOATTR);
+        if (!xfs_inode_hasattr(ip))
+                return ENOATTR;
 
         /*
          * Fill in the arg structure for this request.
@@ -148,11 +150,7 @@ xfs_attr_fetch(xfs_inode_t *ip, struct xfs_name *name,
         /*
          * Decide on what work routines to call based on the inode size.
          */
-        if (XFS_IFORK_Q(ip) == 0 ||
-            (ip->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS &&
-             ip->i_d.di_anextents == 0)) {
-                error = XFS_ERROR(ENOATTR);
-        } else if (ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
+        if (ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
                 error = xfs_attr_shortform_getvalue(&args);
         } else if (xfs_bmap_one_block(ip, XFS_ATTR_FORK)) {
                 error = xfs_attr_leaf_get(&args);
@@ -241,8 +239,7 @@ xfs_attr_set_int(xfs_inode_t *dp, struct xfs_name *name,
         args.firstblock = &firstblock;
         args.flist = &flist;
         args.whichfork = XFS_ATTR_FORK;
-        args.addname = 1;
-        args.oknoent = 1;
+        args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
 
         /*
          * Determine space new attribute will use, and if it would be
@@ -529,9 +526,7 @@ xfs_attr_remove_int(xfs_inode_t *dp, struct xfs_name *name, int flags)
         /*
          * Decide on what work routines to call based on the inode size.
          */
-        if (XFS_IFORK_Q(dp) == 0 ||
-            (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS &&
-             dp->i_d.di_anextents == 0)) {
+        if (!xfs_inode_hasattr(dp)) {
                 error = XFS_ERROR(ENOATTR);
                 goto out;
         }
@@ -601,29 +596,33 @@ xfs_attr_remove(
                 return error;
 
         xfs_ilock(dp, XFS_ILOCK_SHARED);
-        if (XFS_IFORK_Q(dp) == 0 ||
-                   (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS &&
-                    dp->i_d.di_anextents == 0)) {
+        if (!xfs_inode_hasattr(dp)) {
                 xfs_iunlock(dp, XFS_ILOCK_SHARED);
-                return(XFS_ERROR(ENOATTR));
+                return XFS_ERROR(ENOATTR);
         }
         xfs_iunlock(dp, XFS_ILOCK_SHARED);
 
         return xfs_attr_remove_int(dp, &xname, flags);
 }
 
-STATIC int
+int
 xfs_attr_list_int(xfs_attr_list_context_t *context)
 {
         int error;
         xfs_inode_t *dp = context->dp;
 
+        XFS_STATS_INC(xs_attr_list);
+
+        if (XFS_FORCED_SHUTDOWN(dp->i_mount))
+                return EIO;
+
+        xfs_ilock(dp, XFS_ILOCK_SHARED);
+        xfs_attr_trace_l_c("syscall start", context);
+
         /*
          * Decide on what work routines to call based on the inode size.
          */
-        if (XFS_IFORK_Q(dp) == 0 ||
-            (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS &&
-             dp->i_d.di_anextents == 0)) {
+        if (!xfs_inode_hasattr(dp)) {
                 error = 0;
         } else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
                 error = xfs_attr_shortform_list(context);
@@ -632,6 +631,10 @@ xfs_attr_list_int(xfs_attr_list_context_t *context)
         } else {
                 error = xfs_attr_node_list(context);
         }
+
+        xfs_iunlock(dp, XFS_ILOCK_SHARED);
+        xfs_attr_trace_l_c("syscall end", context);
+
         return error;
 }
 
@@ -648,74 +651,50 @@ xfs_attr_list_int(xfs_attr_list_context_t *context)
  */
 /*ARGSUSED*/
 STATIC int
-xfs_attr_put_listent(xfs_attr_list_context_t *context, attrnames_t *namesp,
+xfs_attr_put_listent(xfs_attr_list_context_t *context, int flags,
                      char *name, int namelen,
                      int valuelen, char *value)
 {
+        struct attrlist *alist = (struct attrlist *)context->alist;
         attrlist_ent_t *aep;
         int arraytop;
 
         ASSERT(!(context->flags & ATTR_KERNOVAL));
         ASSERT(context->count >= 0);
         ASSERT(context->count < (ATTR_MAX_VALUELEN/8));
-        ASSERT(context->firstu >= sizeof(*context->alist));
+        ASSERT(context->firstu >= sizeof(*alist));
         ASSERT(context->firstu <= context->bufsize);
 
-        arraytop = sizeof(*context->alist) +
-                        context->count * sizeof(context->alist->al_offset[0]);
+        /*
+         * Only list entries in the right namespace.
+         */
+        if (((context->flags & ATTR_SECURE) == 0) !=
+            ((flags & XFS_ATTR_SECURE) == 0))
+                return 0;
+        if (((context->flags & ATTR_ROOT) == 0) !=
+            ((flags & XFS_ATTR_ROOT) == 0))
+                return 0;
+
+        arraytop = sizeof(*alist) +
+                        context->count * sizeof(alist->al_offset[0]);
         context->firstu -= ATTR_ENTSIZE(namelen);
         if (context->firstu < arraytop) {
                 xfs_attr_trace_l_c("buffer full", context);
-                context->alist->al_more = 1;
+                alist->al_more = 1;
                 context->seen_enough = 1;
                 return 1;
         }
 
-        aep = (attrlist_ent_t *)&(((char *)context->alist)[ context->firstu ]);
+        aep = (attrlist_ent_t *)&context->alist[context->firstu];
         aep->a_valuelen = valuelen;
         memcpy(aep->a_name, name, namelen);
-        aep->a_name[ namelen ] = 0;
-        context->alist->al_offset[ context->count++ ] = context->firstu;
-        context->alist->al_count = context->count;
+        aep->a_name[namelen] = 0;
+        alist->al_offset[context->count++] = context->firstu;
+        alist->al_count = context->count;
         xfs_attr_trace_l_c("add", context);
         return 0;
 }
 
-STATIC int
-xfs_attr_kern_list(xfs_attr_list_context_t *context, attrnames_t *namesp,
-                     char *name, int namelen,
-                     int valuelen, char *value)
-{
-        char *offset;
-        int arraytop;
-
-        ASSERT(context->count >= 0);
-
-        arraytop = context->count + namesp->attr_namelen + namelen + 1;
-        if (arraytop > context->firstu) {
-                context->count = -1;    /* insufficient space */
-                return 1;
-        }
-        offset = (char *)context->alist + context->count;
-        strncpy(offset, namesp->attr_name, namesp->attr_namelen);
-        offset += namesp->attr_namelen;
-        strncpy(offset, name, namelen);                 /* real name */
-        offset += namelen;
-        *offset = '\0';
-        context->count += namesp->attr_namelen + namelen + 1;
-        return 0;
-}
-
-/*ARGSUSED*/
-STATIC int
-xfs_attr_kern_list_sizes(xfs_attr_list_context_t *context, attrnames_t *namesp,
-                     char *name, int namelen,
-                     int valuelen, char *value)
-{
-        context->count += namesp->attr_namelen + namelen + 1;
-        return 0;
-}
-
 /*
  * Generate a list of extended attribute names and optionally
  * also value lengths.  Positive return value follows the XFS
@@ -732,10 +711,9 @@ xfs_attr_list(
         attrlist_cursor_kern_t *cursor)
 {
         xfs_attr_list_context_t context;
+        struct attrlist *alist;
         int error;
 
-        XFS_STATS_INC(xs_attr_list);
-
         /*
          * Validate the cursor.
          */
@@ -756,52 +734,23 @@ xfs_attr_list(
         /*
          * Initialize the output buffer.
          */
+        memset(&context, 0, sizeof(context));
         context.dp = dp;
         context.cursor = cursor;
-        context.count = 0;
-        context.dupcnt = 0;
         context.resynch = 1;
         context.flags = flags;
-        context.seen_enough = 0;
-        context.alist = (attrlist_t *)buffer;
-        context.put_value = 0;
-
-        if (flags & ATTR_KERNAMELS) {
-                context.bufsize = bufsize;
-                context.firstu = context.bufsize;
-                if (flags & ATTR_KERNOVAL)
-                        context.put_listent = xfs_attr_kern_list_sizes;
-                else
-                        context.put_listent = xfs_attr_kern_list;
-        } else {
-                context.bufsize = (bufsize & ~(sizeof(int)-1));  /* align */
-                context.firstu = context.bufsize;
-                context.alist->al_count = 0;
-                context.alist->al_more = 0;
-                context.alist->al_offset[0] = context.bufsize;
-                context.put_listent = xfs_attr_put_listent;
-        }
+        context.alist = buffer;
+        context.bufsize = (bufsize & ~(sizeof(int)-1));  /* align */
+        context.firstu = context.bufsize;
+        context.put_listent = xfs_attr_put_listent;
 
-        if (XFS_FORCED_SHUTDOWN(dp->i_mount))
-                return EIO;
-
-        xfs_ilock(dp, XFS_ILOCK_SHARED);
-        xfs_attr_trace_l_c("syscall start", &context);
+        alist = (struct attrlist *)context.alist;
+        alist->al_count = 0;
+        alist->al_more = 0;
+        alist->al_offset[0] = context.bufsize;
 
         error = xfs_attr_list_int(&context);
-
-        xfs_iunlock(dp, XFS_ILOCK_SHARED);
-        xfs_attr_trace_l_c("syscall end", &context);
-
-        if (context.flags & (ATTR_KERNOVAL|ATTR_KERNAMELS)) {
-                /* must return negated buffer size or the error */
-                if (context.count < 0)
-                        error = XFS_ERROR(ERANGE);
-                else
-                        error = -context.count;
-        } else
-                ASSERT(error >= 0);
-
+        ASSERT(error >= 0);
         return error;
 }
 
@@ -816,12 +765,10 @@ xfs_attr_inactive(xfs_inode_t *dp)
         ASSERT(! XFS_NOT_DQATTACHED(mp, dp));
 
         xfs_ilock(dp, XFS_ILOCK_SHARED);
-        if ((XFS_IFORK_Q(dp) == 0) ||
-            (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) ||
-            (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS &&
-             dp->i_d.di_anextents == 0)) {
+        if (!xfs_inode_hasattr(dp) ||
+            dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
                 xfs_iunlock(dp, XFS_ILOCK_SHARED);
-                return(0);
+                return 0;
         }
         xfs_iunlock(dp, XFS_ILOCK_SHARED);
 
@@ -854,10 +801,8 @@ xfs_attr_inactive(xfs_inode_t *dp)
         /*
          * Decide on what work routines to call based on the inode size.
          */
-        if ((XFS_IFORK_Q(dp) == 0) ||
-            (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) ||
-            (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS &&
-             dp->i_d.di_anextents == 0)) {
+        if (!xfs_inode_hasattr(dp) ||
+            dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
                 error = 0;
                 goto out;
         }
@@ -974,7 +919,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
                         xfs_da_brelse(args->trans, bp);
                         return(retval);
                 }
-                args->rename = 1;                       /* an atomic rename */
+                args->op_flags |= XFS_DA_OP_RENAME;     /* an atomic rename */
                 args->blkno2 = args->blkno;             /* set 2nd entry info*/
                 args->index2 = args->index;
                 args->rmtblkno2 = args->rmtblkno;
@@ -1054,7 +999,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
          * so that one disappears and one appears atomically.  Then we
          * must remove the "old" attribute/value pair.
          */
-        if (args->rename) {
+        if (args->op_flags & XFS_DA_OP_RENAME) {
                 /*
                  * In a separate transaction, set the incomplete flag on the
                  * "old" attr and clear the incomplete flag on the "new" attr.
@@ -1307,7 +1252,7 @@ restart:
         } else if (retval == EEXIST) {
                 if (args->flags & ATTR_CREATE)
                         goto out;
-                args->rename = 1;                       /* atomic rename op */
+                args->op_flags |= XFS_DA_OP_RENAME;     /* atomic rename op */
                 args->blkno2 = args->blkno;             /* set 2nd entry info*/
                 args->index2 = args->index;
                 args->rmtblkno2 = args->rmtblkno;
@@ -1425,7 +1370,7 @@ restart:
          * so that one disappears and one appears atomically.  Then we
          * must remove the "old" attribute/value pair.
          */
-        if (args->rename) {
+        if (args->op_flags & XFS_DA_OP_RENAME) {
                 /*
                  * In a separate transaction, set the incomplete flag on the
                  * "old" attr and clear the incomplete flag on the "new" attr.
@@ -2300,23 +2245,7 @@ xfs_attr_rmtval_remove(xfs_da_args_t *args)
 void
 xfs_attr_trace_l_c(char *where, struct xfs_attr_list_context *context)
 {
-        xfs_attr_trace_enter(XFS_ATTR_KTRACE_L_C, where,
-                (__psunsigned_t)context->dp,
-                (__psunsigned_t)context->cursor->hashval,
-                (__psunsigned_t)context->cursor->blkno,
-                (__psunsigned_t)context->cursor->offset,
-                (__psunsigned_t)context->alist,
-                (__psunsigned_t)context->bufsize,
-                (__psunsigned_t)context->count,
-                (__psunsigned_t)context->firstu,
-                (__psunsigned_t)
-                        ((context->count > 0) &&
-                        !(context->flags & (ATTR_KERNAMELS|ATTR_KERNOVAL)))
-                                ? (ATTR_ENTRY(context->alist,
-                                              context->count-1)->a_valuelen)
-                                : 0,
-                (__psunsigned_t)context->dupcnt,
-                (__psunsigned_t)context->flags,
+        xfs_attr_trace_enter(XFS_ATTR_KTRACE_L_C, where, context,
                 (__psunsigned_t)NULL,
                 (__psunsigned_t)NULL,
                 (__psunsigned_t)NULL);
@@ -2329,23 +2258,7 @@ void
 xfs_attr_trace_l_cn(char *where, struct xfs_attr_list_context *context,
                          struct xfs_da_intnode *node)
 {
-        xfs_attr_trace_enter(XFS_ATTR_KTRACE_L_CN, where,
-                (__psunsigned_t)context->dp,
-                (__psunsigned_t)context->cursor->hashval,
-                (__psunsigned_t)context->cursor->blkno,
-                (__psunsigned_t)context->cursor->offset,
-                (__psunsigned_t)context->alist,
-                (__psunsigned_t)context->bufsize,
-                (__psunsigned_t)context->count,
-                (__psunsigned_t)context->firstu,
-                (__psunsigned_t)
-                        ((context->count > 0) &&
-                        !(context->flags & (ATTR_KERNAMELS|ATTR_KERNOVAL)))
-                                ? (ATTR_ENTRY(context->alist,
-                                              context->count-1)->a_valuelen)
-                                : 0,
-                (__psunsigned_t)context->dupcnt,
-                (__psunsigned_t)context->flags,
+        xfs_attr_trace_enter(XFS_ATTR_KTRACE_L_CN, where, context,
                 (__psunsigned_t)be16_to_cpu(node->hdr.count),
                 (__psunsigned_t)be32_to_cpu(node->btree[0].hashval),
                 (__psunsigned_t)be32_to_cpu(node->btree[
@@ -2359,23 +2272,7 @@ void
 xfs_attr_trace_l_cb(char *where, struct xfs_attr_list_context *context,
                           struct xfs_da_node_entry *btree)
 {
-        xfs_attr_trace_enter(XFS_ATTR_KTRACE_L_CB, where,
-                (__psunsigned_t)context->dp,
-                (__psunsigned_t)context->cursor->hashval,
-                (__psunsigned_t)context->cursor->blkno,
-                (__psunsigned_t)context->cursor->offset,
-                (__psunsigned_t)context->alist,
-                (__psunsigned_t)context->bufsize,
-                (__psunsigned_t)context->count,
-                (__psunsigned_t)context->firstu,
-                (__psunsigned_t)
-                        ((context->count > 0) &&
-                        !(context->flags & (ATTR_KERNAMELS|ATTR_KERNOVAL)))
-                                ? (ATTR_ENTRY(context->alist,
-                                              context->count-1)->a_valuelen)
-                                : 0,
-                (__psunsigned_t)context->dupcnt,
-                (__psunsigned_t)context->flags,
+        xfs_attr_trace_enter(XFS_ATTR_KTRACE_L_CB, where, context,
                 (__psunsigned_t)be32_to_cpu(btree->hashval),
                 (__psunsigned_t)be32_to_cpu(btree->before),
                 (__psunsigned_t)NULL);
@@ -2388,23 +2285,7 @@ void
 xfs_attr_trace_l_cl(char *where, struct xfs_attr_list_context *context,
                               struct xfs_attr_leafblock *leaf)
 {
-        xfs_attr_trace_enter(XFS_ATTR_KTRACE_L_CL, where,
-                (__psunsigned_t)context->dp,
-                (__psunsigned_t)context->cursor->hashval,
-                (__psunsigned_t)context->cursor->blkno,
-                (__psunsigned_t)context->cursor->offset,
-                (__psunsigned_t)context->alist,
-                (__psunsigned_t)context->bufsize,
-                (__psunsigned_t)context->count,
-                (__psunsigned_t)context->firstu,
-                (__psunsigned_t)
-                        ((context->count > 0) &&
-                        !(context->flags & (ATTR_KERNAMELS|ATTR_KERNOVAL)))
-                                ? (ATTR_ENTRY(context->alist,
-                                              context->count-1)->a_valuelen)
-                                : 0,
-                (__psunsigned_t)context->dupcnt,
-                (__psunsigned_t)context->flags,
+        xfs_attr_trace_enter(XFS_ATTR_KTRACE_L_CL, where, context,
                 (__psunsigned_t)be16_to_cpu(leaf->hdr.count),
                 (__psunsigned_t)be32_to_cpu(leaf->entries[0].hashval),
                 (__psunsigned_t)be32_to_cpu(leaf->entries[
@@ -2417,329 +2298,24 @@ xfs_attr_trace_l_cl(char *where, struct xfs_attr_list_context *context,
  */
 void
 xfs_attr_trace_enter(int type, char *where,
-                         __psunsigned_t a2, __psunsigned_t a3,
-                         __psunsigned_t a4, __psunsigned_t a5,
-                         __psunsigned_t a6, __psunsigned_t a7,
-                         __psunsigned_t a8, __psunsigned_t a9,
-                         __psunsigned_t a10, __psunsigned_t a11,
-                         __psunsigned_t a12, __psunsigned_t a13,
-                         __psunsigned_t a14, __psunsigned_t a15)
+                         struct xfs_attr_list_context *context,
+                         __psunsigned_t a13, __psunsigned_t a14,
+                         __psunsigned_t a15)
 {
         ASSERT(xfs_attr_trace_buf);
         ktrace_enter(xfs_attr_trace_buf, (void *)((__psunsigned_t)type),
-                                         (void *)where,
-                                         (void *)a2,  (void *)a3,  (void *)a4,
-                                         (void *)a5,  (void *)a6,  (void *)a7,
-                                         (void *)a8,  (void *)a9,  (void *)a10,
-                                         (void *)a11, (void *)a12, (void *)a13,
-                                         (void *)a14, (void *)a15);
+                (void *)((__psunsigned_t)where),
+                (void *)((__psunsigned_t)context->dp),
+                (void *)((__psunsigned_t)context->cursor->hashval),
+                (void *)((__psunsigned_t)context->cursor->blkno),
+                (void *)((__psunsigned_t)context->cursor->offset),
+                (void *)((__psunsigned_t)context->alist),
+                (void *)((__psunsigned_t)context->bufsize),
+                (void *)((__psunsigned_t)context->count),
+                (void *)((__psunsigned_t)context->firstu),
+                NULL,
+                (void *)((__psunsigned_t)context->dupcnt),
+                (void *)((__psunsigned_t)context->flags),
+                (void *)a13, (void *)a14, (void *)a15);
 }
 #endif  /* XFS_ATTR_TRACE */
-
-
-/*========================================================================
- * System (pseudo) namespace attribute interface routines.
- *========================================================================*/
-
-STATIC int
-posix_acl_access_set(
-        bhv_vnode_t *vp, char *name, void *data, size_t size, int xflags)
-{
-        return xfs_acl_vset(vp, data, size, _ACL_TYPE_ACCESS);
-}
-
-STATIC int
-posix_acl_access_remove(
-        bhv_vnode_t *vp, char *name, int xflags)
-{
-        return xfs_acl_vremove(vp, _ACL_TYPE_ACCESS);
-}
-
-STATIC int
-posix_acl_access_get(
-        bhv_vnode_t *vp, char *name, void *data, size_t size, int xflags)
-{
-        return xfs_acl_vget(vp, data, size, _ACL_TYPE_ACCESS);
-}
-
-STATIC int
-posix_acl_access_exists(
-        bhv_vnode_t *vp)
-{
-        return xfs_acl_vhasacl_access(vp);
-}
-
-STATIC int
-posix_acl_default_set(
-        bhv_vnode_t *vp, char *name, void *data, size_t size, int xflags)
-{
-        return xfs_acl_vset(vp, data, size, _ACL_TYPE_DEFAULT);
-}
-
-STATIC int
-posix_acl_default_get(
-        bhv_vnode_t *vp, char *name, void *data, size_t size, int xflags)
-{
-        return xfs_acl_vget(vp, data, size, _ACL_TYPE_DEFAULT);
-}
-
-STATIC int
-posix_acl_default_remove(
-        bhv_vnode_t *vp, char *name, int xflags)
-{
-        return xfs_acl_vremove(vp, _ACL_TYPE_DEFAULT);
-}
-
-STATIC int
-posix_acl_default_exists(
-        bhv_vnode_t *vp)
-{
-        return xfs_acl_vhasacl_default(vp);
-}
-
-static struct attrnames posix_acl_access = {
-        .attr_name      = "posix_acl_access",
-        .attr_namelen   = sizeof("posix_acl_access") - 1,
-        .attr_get       = posix_acl_access_get,
-        .attr_set       = posix_acl_access_set,
-        .attr_remove    = posix_acl_access_remove,
-        .attr_exists    = posix_acl_access_exists,
-};
-
-static struct attrnames posix_acl_default = {
-        .attr_name      = "posix_acl_default",
-        .attr_namelen   = sizeof("posix_acl_default") - 1,
-        .attr_get       = posix_acl_default_get,
-        .attr_set       = posix_acl_default_set,
-        .attr_remove    = posix_acl_default_remove,
-        .attr_exists    = posix_acl_default_exists,
-};
-
-static struct attrnames *attr_system_names[] =
-        { &posix_acl_access, &posix_acl_default };
-
-
-/*========================================================================
- * Namespace-prefix-style attribute name interface routines.
- *========================================================================*/
-
-STATIC int
-attr_generic_set(
-        bhv_vnode_t *vp, char *name, void *data, size_t size, int xflags)
-{
-        return -xfs_attr_set(xfs_vtoi(vp), name, data, size, xflags);
-}
-
-STATIC int
-attr_generic_get(
-        bhv_vnode_t *vp, char *name, void *data, size_t size, int xflags)
-{
-        int     error, asize = size;
-
-        error = xfs_attr_get(xfs_vtoi(vp), name, data, &asize, xflags);
-        if (!error)
-                return asize;
-        return -error;
-}
-
-STATIC int
-attr_generic_remove(
-        bhv_vnode_t *vp, char *name, int xflags)
-{
-        return -xfs_attr_remove(xfs_vtoi(vp), name, xflags);
-}
-
-STATIC int
-attr_generic_listadd(
-        attrnames_t             *prefix,
-        attrnames_t             *namesp,
-        void                    *data,
-        size_t                  size,
-        ssize_t                 *result)
-{
-        char                    *p = data + *result;
-
-        *result += prefix->attr_namelen;
-        *result += namesp->attr_namelen + 1;
-        if (!size)
-                return 0;
-        if (*result > size)
-                return -ERANGE;
-        strcpy(p, prefix->attr_name);
-        p += prefix->attr_namelen;
-        strcpy(p, namesp->attr_name);
-        p += namesp->attr_namelen + 1;
-        return 0;
-}
-
-STATIC int
-attr_system_list(
-        bhv_vnode_t             *vp,
-        void                    *data,
-        size_t                  size,
-        ssize_t                 *result)
-{
-        attrnames_t             *namesp;
-        int                     i, error = 0;
-
-        for (i = 0; i < ATTR_SYSCOUNT; i++) {
-                namesp = attr_system_names[i];
-                if (!namesp->attr_exists || !namesp->attr_exists(vp))
-                        continue;
-                error = attr_generic_listadd(&attr_system, namesp,
-                                                data, size, result);
-                if (error)
-                        break;
-        }
-        return error;
-}
-
-int
-attr_generic_list(
-        bhv_vnode_t *vp, void *data, size_t size, int xflags, ssize_t *result)
-{
-        attrlist_cursor_kern_t  cursor = { 0 };
-        int                     error;
-
-        error = xfs_attr_list(xfs_vtoi(vp), data, size, xflags, &cursor);
-        if (error > 0)
-                return -error;
-        *result = -error;
-        return attr_system_list(vp, data, size, result);
-}
-
-attrnames_t *
-attr_lookup_namespace(
-        char                    *name,
-        struct attrnames        **names,
-        int                     nnames)
-{
-        int                     i;
-
-        for (i = 0; i < nnames; i++)
-                if (!strncmp(name, names[i]->attr_name, names[i]->attr_namelen))
-                        return names[i];
-        return NULL;
-}
-
-/*
- * Some checks to prevent people abusing EAs to get over quota:
- * - Don't allow modifying user EAs on devices/symlinks;
- * - Don't allow modifying user EAs if sticky bit set;
- */
-STATIC int
-attr_user_capable(
-        bhv_vnode_t     *vp,
-        cred_t          *cred)
-{
-        struct inode    *inode = vn_to_inode(vp);
-
-        if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
-                return -EPERM;
-        if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode) &&
-            !capable(CAP_SYS_ADMIN))
-                return -EPERM;
-        if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) &&
-            (current_fsuid(cred) != inode->i_uid) && !capable(CAP_FOWNER))
-                return -EPERM;
-        return 0;
-}
-
-STATIC int
-attr_trusted_capable(
-        bhv_vnode_t     *vp,
-        cred_t          *cred)
-{
-        struct inode    *inode = vn_to_inode(vp);
-
-        if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
-                return -EPERM;
-        if (!capable(CAP_SYS_ADMIN))
-                return -EPERM;
-        return 0;
-}
-
-STATIC int
-attr_system_set(
-        bhv_vnode_t *vp, char *name, void *data, size_t size, int xflags)
-{
-        attrnames_t     *namesp;
-        int             error;
-
-        if (xflags & ATTR_CREATE)
-                return -EINVAL;
-
-        namesp = attr_lookup_namespace(name, attr_system_names, ATTR_SYSCOUNT);
-        if (!namesp)
-                return -EOPNOTSUPP;
-        error = namesp->attr_set(vp, name, data, size, xflags);
-        if (!error)
-                error = vn_revalidate(vp);
-        return error;
-}
-
-STATIC int
-attr_system_get(
-        bhv_vnode_t *vp, char *name, void *data, size_t size, int xflags)
-{
-        attrnames_t     *namesp;
-
-        namesp = attr_lookup_namespace(name, attr_system_names, ATTR_SYSCOUNT);
-        if (!namesp)
-                return -EOPNOTSUPP;
-        return namesp->attr_get(vp, name, data, size, xflags);
-}
-
-STATIC int
-attr_system_remove(
-        bhv_vnode_t *vp, char *name, int xflags)
-{
-        attrnames_t     *namesp;
-
-        namesp = attr_lookup_namespace(name, attr_system_names, ATTR_SYSCOUNT);
-        if (!namesp)
-                return -EOPNOTSUPP;
-        return namesp->attr_remove(vp, name, xflags);
-}
-
-struct attrnames attr_system = {
-        .attr_name      = "system.",
-        .attr_namelen   = sizeof("system.") - 1,
-        .attr_flag      = ATTR_SYSTEM,
-        .attr_get       = attr_system_get,
-        .attr_set       = attr_system_set,
-        .attr_remove    = attr_system_remove,
-        .attr_capable   = (attrcapable_t)fs_noerr,
-};
-
-struct attrnames attr_trusted = {
-        .attr_name      = "trusted.",
-        .attr_namelen   = sizeof("trusted.") - 1,
-        .attr_flag      = ATTR_ROOT,
-        .attr_get       = attr_generic_get,
-        .attr_set       = attr_generic_set,
-        .attr_remove    = attr_generic_remove,
-        .attr_capable   = attr_trusted_capable,
-};
-
-struct attrnames attr_secure = {
-        .attr_name      = "security.",
-        .attr_namelen   = sizeof("security.") - 1,
-        .attr_flag      = ATTR_SECURE,
-        .attr_get       = attr_generic_get,
-        .attr_set       = attr_generic_set,
-        .attr_remove    = attr_generic_remove,
-        .attr_capable   = (attrcapable_t)fs_noerr,
-};
-
-struct attrnames attr_user = {
-        .attr_name      = "user.",
-        .attr_namelen   = sizeof("user.") - 1,
-        .attr_get       = attr_generic_get,
-        .attr_set       = attr_generic_set,
-        .attr_remove    = attr_generic_remove,
-        .attr_capable   = attr_user_capable,
-};
-
-struct attrnames *attr_namespaces[] =
-        { &attr_system, &attr_trusted, &attr_secure, &attr_user };
diff --git a/fs/xfs/xfs_attr.h b/fs/xfs/xfs_attr.h
index 6cfc9384fe35..8b2d31c19e4d 100644
--- a/fs/xfs/xfs_attr.h
+++ b/fs/xfs/xfs_attr.h
@@ -18,9 +18,11 @@
 #ifndef __XFS_ATTR_H__
 #define __XFS_ATTR_H__
 
+struct xfs_inode;
+struct xfs_da_args;
+struct xfs_attr_list_context;
+
 /*
- * xfs_attr.h
- *
  * Large attribute lists are structured around Btrees where all the data
  * elements are in the leaf nodes.  Attribute names are hashed into an int,
  * then that int is used as the index into the Btree.  Since the hashval
@@ -35,35 +37,6 @@
  * External interfaces
  *========================================================================*/
 
-struct cred;
-struct xfs_attr_list_context;
-
-typedef int (*attrset_t)(bhv_vnode_t *, char *, void *, size_t, int);
-typedef int (*attrget_t)(bhv_vnode_t *, char *, void *, size_t, int);
-typedef int (*attrremove_t)(bhv_vnode_t *, char *, int);
-typedef int (*attrexists_t)(bhv_vnode_t *);
-typedef int (*attrcapable_t)(bhv_vnode_t *, struct cred *);
-
-typedef struct attrnames {
-        char *          attr_name;
-        unsigned int    attr_namelen;
-        unsigned int    attr_flag;
-        attrget_t       attr_get;
-        attrset_t       attr_set;
-        attrremove_t    attr_remove;
-        attrexists_t    attr_exists;
-        attrcapable_t   attr_capable;
-} attrnames_t;
-
-#define ATTR_NAMECOUNT  4
-extern struct attrnames attr_user;
-extern struct attrnames attr_secure;
-extern struct attrnames attr_system;
-extern struct attrnames attr_trusted;
-extern struct attrnames *attr_namespaces[ATTR_NAMECOUNT];
-
-extern attrnames_t *attr_lookup_namespace(char *, attrnames_t **, int);
-extern int attr_generic_list(bhv_vnode_t *, void *, size_t, int, ssize_t *);
 
 #define ATTR_DONTFOLLOW 0x0001  /* -- unused, from IRIX -- */
 #define ATTR_ROOT       0x0002  /* use attrs in root (trusted) namespace */
@@ -71,16 +44,9 @@ extern int attr_generic_list(bhv_vnode_t *, void *, size_t, int, ssize_t *);
 #define ATTR_SECURE     0x0008  /* use attrs in security namespace */
 #define ATTR_CREATE     0x0010  /* pure create: fail if attr already exists */
 #define ATTR_REPLACE    0x0020  /* pure set: fail if attr does not exist */
-#define ATTR_SYSTEM     0x0100  /* use attrs in system (pseudo) namespace */
 
-#define ATTR_KERNACCESS 0x0400  /* [kernel] iaccess, inode held io-locked */
 #define ATTR_KERNOTIME  0x1000  /* [kernel] don't update inode timestamps */
 #define ATTR_KERNOVAL   0x2000  /* [kernel] get attr size only, not value */
-#define ATTR_KERNAMELS  0x4000  /* [kernel] list attr names (simple list) */
-
-#define ATTR_KERNORMALS 0x0800  /* [kernel] normal attr list: user+secure */
-#define ATTR_KERNROOTLS 0x8000  /* [kernel] include root in the attr list */
-#define ATTR_KERNFULLS  (ATTR_KERNORMALS|ATTR_KERNROOTLS)
 
 /*
  * The maximum size (into the kernel or returned from the kernel) of an
@@ -119,22 +85,6 @@ typedef struct attrlist_ent {	/* data from attr_list() */
          &((char *)buffer)[ ((attrlist_t *)(buffer))->al_offset[index] ])
 
 /*
- * Multi-attribute operation vector.
- */
-typedef struct attr_multiop {
-        int     am_opcode;      /* operation to perform (ATTR_OP_GET, etc.) */
-        int     am_error;       /* [out arg] result of this sub-op (an errno) */
-        char    *am_attrname;   /* attribute name to work with */
-        char    *am_attrvalue;  /* [in/out arg] attribute value (raw bytes) */
-        int     am_length;      /* [in/out arg] length of value */
-        int     am_flags;       /* bitwise OR of attr API flags defined above */
-} attr_multiop_t;
-
-#define ATTR_OP_GET     1       /* return the indicated attr's value */
-#define ATTR_OP_SET     2       /* set/create the indicated attr/value pair */
-#define ATTR_OP_REMOVE  3       /* remove the indicated attr */
-
-/*
  * Kernel-internal version of the attrlist cursor.
  */
 typedef struct attrlist_cursor_kern {
@@ -148,20 +98,40 @@ typedef struct attrlist_cursor_kern {
 
 
 /*========================================================================
- * Function prototypes for the kernel.
+ * Structure used to pass context around among the routines.
  *========================================================================*/
 
-struct xfs_inode;
-struct attrlist_cursor_kern;
-struct xfs_da_args;
+
+typedef int (*put_listent_func_t)(struct xfs_attr_list_context *, int,
+                                      char *, int, int, char *);
+
+typedef struct xfs_attr_list_context {
+        struct xfs_inode                *dp;            /* inode */
+        struct attrlist_cursor_kern     *cursor;        /* position in list */
+        char                            *alist;         /* output buffer */
+        int                             seen_enough;    /* T/F: seen enough of list? */
+        ssize_t                         count;          /* num used entries */
+        int                             dupcnt;         /* count dup hashvals seen */
+        int                             bufsize;        /* total buffer size */
+        int                             firstu;         /* first used byte in buffer */
+        int                             flags;          /* from VOP call */
+        int                             resynch;        /* T/F: resynch with cursor */
+        int                             put_value;      /* T/F: need value for listent */
+        put_listent_func_t              put_listent;    /* list output fmt function */
+        int                             index;          /* index into output buffer */
+} xfs_attr_list_context_t;
+
+
+/*========================================================================
+ * Function prototypes for the kernel.
+ *========================================================================*/
 
 /*
  * Overall external interface routines.
  */
 int xfs_attr_inactive(struct xfs_inode *dp);
-
-int xfs_attr_shortform_getvalue(struct xfs_da_args *);
 int xfs_attr_fetch(struct xfs_inode *, struct xfs_name *, char *, int *, int);
 int xfs_attr_rmtval_get(struct xfs_da_args *args);
+int xfs_attr_list_int(struct xfs_attr_list_context *);
 
 #endif  /* __XFS_ATTR_H__ */
diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c
index 303d41e4217b..23ef5d7c87e1 100644
--- a/fs/xfs/xfs_attr_leaf.c
+++ b/fs/xfs/xfs_attr_leaf.c
@@ -94,13 +94,6 @@ STATIC int xfs_attr_leaf_entsize(xfs_attr_leafblock_t *leaf, int index);
  * Namespace helper routines
  *========================================================================*/
 
-STATIC_INLINE attrnames_t *
-xfs_attr_flags_namesp(int flags)
-{
-        return ((flags & XFS_ATTR_SECURE) ? &attr_secure:
-                  ((flags & XFS_ATTR_ROOT) ? &attr_trusted : &attr_user));
-}
-
 /*
  * If namespace bits don't match return 0.
  * If all match then return 1.
@@ -111,25 +104,6 @@ xfs_attr_namesp_match(int arg_flags, int ondisk_flags)
         return XFS_ATTR_NSP_ONDISK(ondisk_flags) == XFS_ATTR_NSP_ARGS_TO_ONDISK(arg_flags);
 }
 
-/*
- * If namespace bits don't match and we don't have an override for it
- * then return 0.
- * If all match or are overridable then return 1.
- */
-STATIC_INLINE int
-xfs_attr_namesp_match_overrides(int arg_flags, int ondisk_flags)
-{
-        if (((arg_flags & ATTR_SECURE) == 0) !=
-            ((ondisk_flags & XFS_ATTR_SECURE) == 0) &&
-            !(arg_flags & ATTR_KERNORMALS))
-                return 0;
-        if (((arg_flags & ATTR_ROOT) == 0) !=
-            ((ondisk_flags & XFS_ATTR_ROOT) == 0) &&
-            !(arg_flags & ATTR_KERNROOTLS))
-                return 0;
-        return 1;
-}
-
 
 /*========================================================================
  * External routines when attribute fork size < XFS_LITINO(mp).
@@ -369,9 +343,10 @@ xfs_attr_shortform_remove(xfs_da_args_t *args)
          * Fix up the start offset of the attribute fork
          */
         totsize -= size;
-        if (totsize == sizeof(xfs_attr_sf_hdr_t) && !args->addname &&
-            (mp->m_flags & XFS_MOUNT_ATTR2) && 
-            (dp->i_d.di_format != XFS_DINODE_FMT_BTREE)) {
+        if (totsize == sizeof(xfs_attr_sf_hdr_t) &&
+                                !(args->op_flags & XFS_DA_OP_ADDNAME) &&
+                                (mp->m_flags & XFS_MOUNT_ATTR2) &&
+                                (dp->i_d.di_format != XFS_DINODE_FMT_BTREE)) {
                 /*
                  * Last attribute now removed, revert to original
                  * inode format making all literal area available
@@ -389,9 +364,10 @@ xfs_attr_shortform_remove(xfs_da_args_t *args)
                 xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
                 dp->i_d.di_forkoff = xfs_attr_shortform_bytesfit(dp, totsize);
                 ASSERT(dp->i_d.di_forkoff);
-                ASSERT(totsize > sizeof(xfs_attr_sf_hdr_t) || args->addname ||
-                        !(mp->m_flags & XFS_MOUNT_ATTR2) ||
-                        dp->i_d.di_format == XFS_DINODE_FMT_BTREE);
+                ASSERT(totsize > sizeof(xfs_attr_sf_hdr_t) ||
+                                (args->op_flags & XFS_DA_OP_ADDNAME) ||
+                                !(mp->m_flags & XFS_MOUNT_ATTR2) ||
+                                dp->i_d.di_format == XFS_DINODE_FMT_BTREE);
                 dp->i_afp->if_ext_max =
                         XFS_IFORK_ASIZE(dp) / (uint)sizeof(xfs_bmbt_rec_t);
                 dp->i_df.if_ext_max =
@@ -531,7 +507,7 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args)
         nargs.total = args->total;
         nargs.whichfork = XFS_ATTR_FORK;
         nargs.trans = args->trans;
-        nargs.oknoent = 1;
+        nargs.op_flags = XFS_DA_OP_OKNOENT;
 
         sfe = &sf->list[0];
         for (i = 0; i < sf->hdr.count; i++) {
@@ -555,7 +531,7 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args)
 out:
         if(bp)
                 xfs_da_buf_done(bp);
-        kmem_free(tmpbuffer, size);
+        kmem_free(tmpbuffer);
         return(error);
 }
 
@@ -624,15 +600,8 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context)
             (XFS_ISRESET_CURSOR(cursor) &&
              (dp->i_afp->if_bytes + sf->hdr.count * 16) < context->bufsize)) {
                 for (i = 0, sfe = &sf->list[0]; i < sf->hdr.count; i++) {
-                        attrnames_t     *namesp;
-
-                        if (!xfs_attr_namesp_match_overrides(context->flags, sfe->flags)) {
-                                sfe = XFS_ATTR_SF_NEXTENTRY(sfe);
-                                continue;
-                        }
-                        namesp = xfs_attr_flags_namesp(sfe->flags);
                         error = context->put_listent(context,
-                                           namesp,
+                                           sfe->flags,
                                            (char *)sfe->nameval,
                                            (int)sfe->namelen,
                                            (int)sfe->valuelen,
@@ -676,13 +645,10 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context)
                                              XFS_ERRLEVEL_LOW,
                                              context->dp->i_mount, sfe);
                         xfs_attr_trace_l_c("sf corrupted", context);
-                        kmem_free(sbuf, sbsize);
+                        kmem_free(sbuf);
                         return XFS_ERROR(EFSCORRUPTED);
                 }
-                if (!xfs_attr_namesp_match_overrides(context->flags, sfe->flags)) {
-                        sfe = XFS_ATTR_SF_NEXTENTRY(sfe);
-                        continue;
-                }
+
                 sbp->entno = i;
                 sbp->hash = xfs_da_hashname((char *)sfe->nameval, sfe->namelen);
                 sbp->name = (char *)sfe->nameval;
@@ -717,7 +683,7 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context)
                 }
         }
         if (i == nsbuf) {
-                kmem_free(sbuf, sbsize);
+                kmem_free(sbuf);
                 xfs_attr_trace_l_c("blk end", context);
                 return(0);
         }
@@ -726,16 +692,12 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context)
          * Loop putting entries into the user buffer.
          */
         for ( ; i < nsbuf; i++, sbp++) {
-                attrnames_t     *namesp;
-
-                namesp = xfs_attr_flags_namesp(sbp->flags);
-
                 if (cursor->hashval != sbp->hash) {
                         cursor->hashval = sbp->hash;
                         cursor->offset = 0;
                 }
                 error = context->put_listent(context,
-                                        namesp,
+                                        sbp->flags,
                                         sbp->name,
                                         sbp->namelen,
                                         sbp->valuelen,
@@ -747,7 +709,7 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context)
                 cursor->offset++;
         }
 
-        kmem_free(sbuf, sbsize);
+        kmem_free(sbuf);
         xfs_attr_trace_l_c("sf E-O-F", context);
         return(0);
 }
@@ -853,7 +815,7 @@ xfs_attr_leaf_to_shortform(xfs_dabuf_t *bp, xfs_da_args_t *args, int forkoff)
         nargs.total = args->total;
         nargs.whichfork = XFS_ATTR_FORK;
         nargs.trans = args->trans;
-        nargs.oknoent = 1;
+        nargs.op_flags = XFS_DA_OP_OKNOENT;
         entry = &leaf->entries[0];
         for (i = 0; i < be16_to_cpu(leaf->hdr.count); entry++, i++) {
                 if (entry->flags & XFS_ATTR_INCOMPLETE)
@@ -873,7 +835,7 @@ xfs_attr_leaf_to_shortform(xfs_dabuf_t *bp, xfs_da_args_t *args, int forkoff)
         error = 0;
 
 out:
-        kmem_free(tmpbuffer, XFS_LBSIZE(dp->i_mount));
+        kmem_free(tmpbuffer);
         return(error);
 }
 
@@ -1155,7 +1117,7 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex)
         entry->hashval = cpu_to_be32(args->hashval);
         entry->flags = tmp ? XFS_ATTR_LOCAL : 0;
         entry->flags |= XFS_ATTR_NSP_ARGS_TO_ONDISK(args->flags);
-        if (args->rename) {
+        if (args->op_flags & XFS_DA_OP_RENAME) {
                 entry->flags |= XFS_ATTR_INCOMPLETE;
                 if ((args->blkno2 == args->blkno) &&
                     (args->index2 <= args->index)) {
@@ -1271,7 +1233,7 @@ xfs_attr_leaf_compact(xfs_trans_t *trans, xfs_dabuf_t *bp)
                                 be16_to_cpu(hdr_s->count), mp);
         xfs_da_log_buf(trans, bp, 0, XFS_LBSIZE(mp) - 1);
 
-        kmem_free(tmpbuffer, XFS_LBSIZE(mp));
+        kmem_free(tmpbuffer);
 }
 
 /*
@@ -1921,7 +1883,7 @@ xfs_attr_leaf_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk,
                                 be16_to_cpu(drop_hdr->count), mp);
                 }
                 memcpy((char *)save_leaf, (char *)tmp_leaf, state->blocksize);
-                kmem_free(tmpbuffer, state->blocksize);
+                kmem_free(tmpbuffer);
         }
 
         xfs_da_log_buf(state->args->trans, save_blk->bp, 0,
@@ -2400,8 +2362,6 @@ xfs_attr_leaf_list_int(xfs_dabuf_t *bp, xfs_attr_list_context_t *context)
          */
         retval = 0;
         for (  ; (i < be16_to_cpu(leaf->hdr.count)); entry++, i++) {
-                attrnames_t *namesp;
-
                 if (be32_to_cpu(entry->hashval) != cursor->hashval) {
                         cursor->hashval = be32_to_cpu(entry->hashval);
                         cursor->offset = 0;
@@ -2409,17 +2369,13 @@ xfs_attr_leaf_list_int(xfs_dabuf_t *bp, xfs_attr_list_context_t *context)
 
                 if (entry->flags & XFS_ATTR_INCOMPLETE)
                         continue;               /* skip incomplete entries */
-                if (!xfs_attr_namesp_match_overrides(context->flags, entry->flags))
-                        continue;
-
-                namesp = xfs_attr_flags_namesp(entry->flags);
 
                 if (entry->flags & XFS_ATTR_LOCAL) {
                         xfs_attr_leaf_name_local_t *name_loc =
                                 XFS_ATTR_LEAF_NAME_LOCAL(leaf, i);
 
                         retval = context->put_listent(context,
-                                                namesp,
+                                                entry->flags,
                                                 (char *)name_loc->nameval,
                                                 (int)name_loc->namelen,
                                                 be16_to_cpu(name_loc->valuelen),
@@ -2446,16 +2402,15 @@ xfs_attr_leaf_list_int(xfs_dabuf_t *bp, xfs_attr_list_context_t *context)
                                 if (retval)
                                         return retval;
                                 retval = context->put_listent(context,
-                                                namesp,
+                                                entry->flags,
                                                 (char *)name_rmt->name,
                                                 (int)name_rmt->namelen,
                                                 valuelen,
                                                 (char*)args.value);
-                                kmem_free(args.value, valuelen);
-                        }
-                        else {
+                                kmem_free(args.value);
+                        } else {
                                 retval = context->put_listent(context,
-                                                namesp,
+                                                entry->flags,
                                                 (char *)name_rmt->name,
                                                 (int)name_rmt->namelen,
                                                 valuelen,
@@ -2954,7 +2909,7 @@ xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp)
                         error = tmp;    /* save only the 1st errno */
         }
 
-        kmem_free((xfs_caddr_t)list, size);
+        kmem_free((xfs_caddr_t)list);
         return(error);
 }
 
diff --git a/fs/xfs/xfs_attr_leaf.h b/fs/xfs/xfs_attr_leaf.h
index 040f732ce1e2..5ecf437b7825 100644
--- a/fs/xfs/xfs_attr_leaf.h
+++ b/fs/xfs/xfs_attr_leaf.h
@@ -30,7 +30,7 @@
 
 struct attrlist;
 struct attrlist_cursor_kern;
-struct attrnames;
+struct xfs_attr_list_context;
 struct xfs_dabuf;
 struct xfs_da_args;
 struct xfs_da_state;
@@ -204,33 +204,6 @@ static inline int xfs_attr_leaf_entsize_local_max(int bsize)
         return (((bsize) >> 1) + ((bsize) >> 2));
 }
 
-
-/*========================================================================
- * Structure used to pass context around among the routines.
- *========================================================================*/
-
-
-struct xfs_attr_list_context;
-
-typedef int (*put_listent_func_t)(struct xfs_attr_list_context *, struct attrnames *,
-                                      char *, int, int, char *);
-
-typedef struct xfs_attr_list_context {
-        struct xfs_inode                *dp;            /* inode */
-        struct attrlist_cursor_kern     *cursor;        /* position in list */
-        struct attrlist                 *alist;         /* output buffer */
-        int                             seen_enough;    /* T/F: seen enough of list? */
-        int                             count;          /* num used entries */
-        int                             dupcnt;         /* count dup hashvals seen */
-        int                             bufsize;        /* total buffer size */
-        int                             firstu;         /* first used byte in buffer */
-        int                             flags;          /* from VOP call */
-        int                             resynch;        /* T/F: resynch with cursor */
-        int                             put_value;      /* T/F: need value for listent */
-        put_listent_func_t              put_listent;    /* list output fmt function */
-        int                             index;          /* index into output buffer */
-} xfs_attr_list_context_t;
-
 /*
  * Used to keep a list of "remote value" extents when unlinking an inode.
  */
diff --git a/fs/xfs/xfs_attr_sf.h b/fs/xfs/xfs_attr_sf.h
index f67f917803b1..ea22839caed2 100644
--- a/fs/xfs/xfs_attr_sf.h
+++ b/fs/xfs/xfs_attr_sf.h
@@ -97,13 +97,9 @@ void xfs_attr_trace_l_cb(char *where, struct xfs_attr_list_context *context,
 void xfs_attr_trace_l_cl(char *where, struct xfs_attr_list_context *context,
                               struct xfs_attr_leafblock *leaf);
 void xfs_attr_trace_enter(int type, char *where,
-                             __psunsigned_t a2, __psunsigned_t a3,
-                             __psunsigned_t a4, __psunsigned_t a5,
-                             __psunsigned_t a6, __psunsigned_t a7,
-                             __psunsigned_t a8, __psunsigned_t a9,
-                             __psunsigned_t a10, __psunsigned_t a11,
-                             __psunsigned_t a12, __psunsigned_t a13,
-                             __psunsigned_t a14, __psunsigned_t a15);
+                             struct xfs_attr_list_context *context,
+                             __psunsigned_t a13, __psunsigned_t a14,
+                             __psunsigned_t a15);
 #else
 #define xfs_attr_trace_l_c(w,c)
 #define xfs_attr_trace_l_cn(w,c,n)
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 53c259f5a5af..3c4beb3a4326 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -428,7 +428,8 @@ xfs_bmap_add_attrfork_btree(
                 cur->bc_private.b.firstblock = *firstblock;
                 if ((error = xfs_bmbt_lookup_ge(cur, 0, 0, 0, &stat)))
                         goto error0;
-                ASSERT(stat == 1);      /* must be at least one entry */
+                /* must be at least one entry */
+                XFS_WANT_CORRUPTED_GOTO(stat == 1, error0);
                 if ((error = xfs_bmbt_newroot(cur, flags, &stat)))
                         goto error0;
                 if (stat == 0) {
@@ -816,13 +817,13 @@ xfs_bmap_add_extent_delay_real(
                                         RIGHT.br_startblock,
                                         RIGHT.br_blockcount, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_delete(cur, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_decrement(cur, 0, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_update(cur, LEFT.br_startoff,
                                         LEFT.br_startblock,
                                         LEFT.br_blockcount +
@@ -860,7 +861,7 @@ xfs_bmap_add_extent_delay_real(
                                         LEFT.br_startblock, LEFT.br_blockcount,
                                         &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_update(cur, LEFT.br_startoff,
                                         LEFT.br_startblock,
                                         LEFT.br_blockcount +
@@ -895,7 +896,7 @@ xfs_bmap_add_extent_delay_real(
                                         RIGHT.br_startblock,
                                         RIGHT.br_blockcount, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_update(cur, PREV.br_startoff,
                                         new->br_startblock,
                                         PREV.br_blockcount +
@@ -928,11 +929,11 @@ xfs_bmap_add_extent_delay_real(
                                         new->br_startblock, new->br_blockcount,
                                         &i)))
                                 goto done;
-                        ASSERT(i == 0);
+                        XFS_WANT_CORRUPTED_GOTO(i == 0, done);
                         cur->bc_rec.b.br_state = XFS_EXT_NORM;
                         if ((error = xfs_bmbt_insert(cur, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                 }
                 *dnew = 0;
                 /* DELTA: The in-core extent described by new changed type. */
@@ -963,7 +964,7 @@ xfs_bmap_add_extent_delay_real(
                                         LEFT.br_startblock, LEFT.br_blockcount,
                                         &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_update(cur, LEFT.br_startoff,
                                         LEFT.br_startblock,
                                         LEFT.br_blockcount +
@@ -1004,11 +1005,11 @@ xfs_bmap_add_extent_delay_real(
                                         new->br_startblock, new->br_blockcount,
                                         &i)))
                                 goto done;
-                        ASSERT(i == 0);
+                        XFS_WANT_CORRUPTED_GOTO(i == 0, done);
                         cur->bc_rec.b.br_state = XFS_EXT_NORM;
                         if ((error = xfs_bmbt_insert(cur, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                 }
                 if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
                     ip->i_d.di_nextents > ip->i_df.if_ext_max) {
@@ -1054,7 +1055,7 @@ xfs_bmap_add_extent_delay_real(
                                         RIGHT.br_startblock,
                                         RIGHT.br_blockcount, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_update(cur, new->br_startoff,
                                         new->br_startblock,
                                         new->br_blockcount +
@@ -1094,11 +1095,11 @@ xfs_bmap_add_extent_delay_real(
                                         new->br_startblock, new->br_blockcount,
                                         &i)))
                                 goto done;
-                        ASSERT(i == 0);
+                        XFS_WANT_CORRUPTED_GOTO(i == 0, done);
                         cur->bc_rec.b.br_state = XFS_EXT_NORM;
                         if ((error = xfs_bmbt_insert(cur, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                 }
                 if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
                     ip->i_d.di_nextents > ip->i_df.if_ext_max) {
@@ -1149,11 +1150,11 @@ xfs_bmap_add_extent_delay_real(
                                         new->br_startblock, new->br_blockcount,
                                         &i)))
                                 goto done;
-                        ASSERT(i == 0);
+                        XFS_WANT_CORRUPTED_GOTO(i == 0, done);
                         cur->bc_rec.b.br_state = XFS_EXT_NORM;
                         if ((error = xfs_bmbt_insert(cur, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                 }
                 if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
                     ip->i_d.di_nextents > ip->i_df.if_ext_max) {
@@ -1377,19 +1378,19 @@ xfs_bmap_add_extent_unwritten_real(
                                         RIGHT.br_startblock,
                                         RIGHT.br_blockcount, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_delete(cur, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_decrement(cur, 0, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_delete(cur, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_decrement(cur, 0, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_update(cur, LEFT.br_startoff,
                                 LEFT.br_startblock,
                                 LEFT.br_blockcount + PREV.br_blockcount +
@@ -1426,13 +1427,13 @@ xfs_bmap_add_extent_unwritten_real(
                                         PREV.br_startblock, PREV.br_blockcount,
                                         &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_delete(cur, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_decrement(cur, 0, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_update(cur, LEFT.br_startoff,
                                 LEFT.br_startblock,
                                 LEFT.br_blockcount + PREV.br_blockcount,
@@ -1469,13 +1470,13 @@ xfs_bmap_add_extent_unwritten_real(
                                         RIGHT.br_startblock,
                                         RIGHT.br_blockcount, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_delete(cur, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_decrement(cur, 0, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_update(cur, new->br_startoff,
                                 new->br_startblock,
                                 new->br_blockcount + RIGHT.br_blockcount,
@@ -1508,7 +1509,7 @@ xfs_bmap_add_extent_unwritten_real(
                                         new->br_startblock, new->br_blockcount,
                                         &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_update(cur, new->br_startoff,
                                 new->br_startblock, new->br_blockcount,
                                 newext)))
@@ -1549,7 +1550,7 @@ xfs_bmap_add_extent_unwritten_real(
                                         PREV.br_startblock, PREV.br_blockcount,
                                         &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_update(cur,
                                 PREV.br_startoff + new->br_blockcount,
                                 PREV.br_startblock + new->br_blockcount,
@@ -1596,7 +1597,7 @@ xfs_bmap_add_extent_unwritten_real(
                                         PREV.br_startblock, PREV.br_blockcount,
                                         &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_update(cur,
                                 PREV.br_startoff + new->br_blockcount,
                                 PREV.br_startblock + new->br_blockcount,
@@ -1606,7 +1607,7 @@ xfs_bmap_add_extent_unwritten_real(
                         cur->bc_rec.b = *new;
                         if ((error = xfs_bmbt_insert(cur, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                 }
                 /* DELTA: One in-core extent is split in two. */
                 temp = PREV.br_startoff;
@@ -1640,7 +1641,7 @@ xfs_bmap_add_extent_unwritten_real(
                                         PREV.br_startblock,
                                         PREV.br_blockcount, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_update(cur, PREV.br_startoff,
                                 PREV.br_startblock,
                                 PREV.br_blockcount - new->br_blockcount,
@@ -1682,7 +1683,7 @@ xfs_bmap_add_extent_unwritten_real(
                                         PREV.br_startblock, PREV.br_blockcount,
                                         &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_update(cur, PREV.br_startoff,
                                 PREV.br_startblock,
                                 PREV.br_blockcount - new->br_blockcount,
@@ -1692,11 +1693,11 @@ xfs_bmap_add_extent_unwritten_real(
                                         new->br_startblock, new->br_blockcount,
                                         &i)))
                                 goto done;
-                        ASSERT(i == 0);
+                        XFS_WANT_CORRUPTED_GOTO(i == 0, done);
                         cur->bc_rec.b.br_state = XFS_EXT_NORM;
                         if ((error = xfs_bmbt_insert(cur, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                 }
                 /* DELTA: One in-core extent is split in two. */
                 temp = PREV.br_startoff;
@@ -1732,27 +1733,34 @@ xfs_bmap_add_extent_unwritten_real(
                                         PREV.br_startblock, PREV.br_blockcount,
                                         &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         /* new right extent - oldext */
                         if ((error = xfs_bmbt_update(cur, r[1].br_startoff,
                                 r[1].br_startblock, r[1].br_blockcount,
                                 r[1].br_state)))
                                 goto done;
                         /* new left extent - oldext */
-                        PREV.br_blockcount =
-                                new->br_startoff - PREV.br_startoff;
                         cur->bc_rec.b = PREV;
+                        cur->bc_rec.b.br_blockcount =
+                                new->br_startoff - PREV.br_startoff;
                         if ((error = xfs_bmbt_insert(cur, &i)))
                                 goto done;
-                        ASSERT(i == 1);
-                        if ((error = xfs_bmbt_increment(cur, 0, &i)))
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
+                        /*
+                         * Reset the cursor to the position of the new extent
+                         * we are about to insert as we can't trust it after
+                         * the previous insert.
+                         */
+                        if ((error = xfs_bmbt_lookup_eq(cur, new->br_startoff,
+                                        new->br_startblock, new->br_blockcount,
+                                        &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 0, done);
                         /* new middle extent - newext */
-                        cur->bc_rec.b = *new;
+                        cur->bc_rec.b.br_state = new->br_state;
                         if ((error = xfs_bmbt_insert(cur, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                 }
                 /* DELTA: One in-core extent is split in three. */
                 temp = PREV.br_startoff;
@@ -2097,13 +2105,13 @@ xfs_bmap_add_extent_hole_real(
                                         right.br_startblock,
                                         right.br_blockcount, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_delete(cur, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_decrement(cur, 0, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_update(cur, left.br_startoff,
                                         left.br_startblock,
                                         left.br_blockcount +
@@ -2139,7 +2147,7 @@ xfs_bmap_add_extent_hole_real(
                                         left.br_startblock,
                                         left.br_blockcount, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_update(cur, left.br_startoff,
                                         left.br_startblock,
                                         left.br_blockcount +
@@ -2174,7 +2182,7 @@ xfs_bmap_add_extent_hole_real(
                                         right.br_startblock,
                                         right.br_blockcount, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         if ((error = xfs_bmbt_update(cur, new->br_startoff,
                                         new->br_startblock,
                                         new->br_blockcount +
@@ -2208,11 +2216,11 @@ xfs_bmap_add_extent_hole_real(
                                         new->br_startblock,
                                         new->br_blockcount, &i)))
                                 goto done;
-                        ASSERT(i == 0);
+                        XFS_WANT_CORRUPTED_GOTO(i == 0, done);
                         cur->bc_rec.b.br_state = new->br_state;
                         if ((error = xfs_bmbt_insert(cur, &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                 }
                 /* DELTA: A new extent was added in a hole. */
                 temp = new->br_startoff;
@@ -3131,7 +3139,7 @@ xfs_bmap_del_extent(
                                         got.br_startblock, got.br_blockcount,
                                         &i)))
                                 goto done;
-                        ASSERT(i == 1);
+                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                 }
                 da_old = da_new = 0;
         } else {
@@ -3164,7 +3172,7 @@ xfs_bmap_del_extent(
                 }
                 if ((error = xfs_bmbt_delete(cur, &i)))
                         goto done;
-                ASSERT(i == 1);
+                XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                 break;
 
         case 2:
@@ -3268,7 +3276,7 @@ xfs_bmap_del_extent(
                                                         got.br_startblock,
                                                         temp, &i)))
                                                 goto done;
-                                        ASSERT(i == 1);
+                                        XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                                         /*
                                          * Update the btree record back
                                          * to the original value.
@@ -3289,7 +3297,7 @@ xfs_bmap_del_extent(
                                         error = XFS_ERROR(ENOSPC);
                                         goto done;
                                 }
-                                ASSERT(i == 1);
+                                XFS_WANT_CORRUPTED_GOTO(i == 1, done);
                         } else
                                 flags |= XFS_ILOG_FEXT(whichfork);
                         XFS_IFORK_NEXT_SET(ip, whichfork,
@@ -5970,7 +5978,7 @@ unlock_and_return:
         xfs_iunlock_map_shared(ip, lock);
         xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 
-        kmem_free(map, subnex * sizeof(*map));
+        kmem_free(map);
 
         return error;
 }
diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h
index 6ff70cda451c..9f3e3a836d15 100644
--- a/fs/xfs/xfs_bmap.h
+++ b/fs/xfs/xfs_bmap.h
@@ -54,12 +54,23 @@ typedef struct xfs_bmap_free_item
 
 /*
  * Header for free extent list.
+ *
+ * xbf_low is used by the allocator to activate the lowspace algorithm -
+ * when free space is running low the extent allocator may choose to
+ * allocate an extent from an AG without leaving sufficient space for
+ * a btree split when inserting the new extent.  In this case the allocator
+ * will enable the lowspace algorithm which is supposed to allow further
+ * allocations (such as btree splits and newroots) to allocate from
+ * sequential AGs.  In order to avoid locking AGs out of order the lowspace
+ * algorithm will start searching for free space from AG 0.  If the correct
+ * transaction reservations have been made then this algorithm will eventually
+ * find all the space it needs.
  */
 typedef struct xfs_bmap_free
 {
         xfs_bmap_free_item_t    *xbf_first;     /* list of to-be-free extents */
         int                     xbf_count;      /* count of items on list */
-        int                     xbf_low;        /* kludge: alloc in low mode */
+        int                     xbf_low;        /* alloc in low mode */
 } xfs_bmap_free_t;
 
 #define XFS_BMAP_MAX_NMAP       4
diff --git a/fs/xfs/xfs_bmap_btree.c b/fs/xfs/xfs_bmap_btree.c
index 4f0e849d973e..23efad29a5cd 100644
--- a/fs/xfs/xfs_bmap_btree.c
+++ b/fs/xfs/xfs_bmap_btree.c
@@ -1493,12 +1493,27 @@ xfs_bmbt_split(
         left = XFS_BUF_TO_BMBT_BLOCK(lbp);
         args.fsbno = cur->bc_private.b.firstblock;
         args.firstblock = args.fsbno;
+        args.minleft = 0;
         if (args.fsbno == NULLFSBLOCK) {
                 args.fsbno = lbno;
                 args.type = XFS_ALLOCTYPE_START_BNO;
-        } else
+                /*
+                 * Make sure there is sufficient room left in the AG to
+                 * complete a full tree split for an extent insert.  If
+                 * we are converting the middle part of an extent then
+                 * we may need space for two tree splits.
+                 *
+                 * We are relying on the caller to make the correct block
+                 * reservation for this operation to succeed.  If the
+                 * reservation amount is insufficient then we may fail a
+                 * block allocation here and corrupt the filesystem.
+                 */
+                args.minleft = xfs_trans_get_block_res(args.tp);
+        } else if (cur->bc_private.b.flist->xbf_low)
+                args.type = XFS_ALLOCTYPE_START_BNO;
+        else
                 args.type = XFS_ALLOCTYPE_NEAR_BNO;
-        args.mod = args.minleft = args.alignment = args.total = args.isfl =
+        args.mod = args.alignment = args.total = args.isfl =
                 args.userdata = args.minalignslop = 0;
         args.minlen = args.maxlen = args.prod = 1;
         args.wasdel = cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL;
@@ -1510,6 +1525,21 @@ xfs_bmbt_split(
                 XFS_BMBT_TRACE_CURSOR(cur, ERROR);
                 return error;
         }
+        if (args.fsbno == NULLFSBLOCK && args.minleft) {
+                /*
+                 * Could not find an AG with enough free space to satisfy
+                 * a full btree split.  Try again without minleft and if
+                 * successful activate the lowspace algorithm.
+                 */
+                args.fsbno = 0;
+                args.type = XFS_ALLOCTYPE_FIRST_AG;
+                args.minleft = 0;
+                if ((error = xfs_alloc_vextent(&args))) {
+                        XFS_BMBT_TRACE_CURSOR(cur, ERROR);
+                        return error;
+                }
+                cur->bc_private.b.flist->xbf_low = 1;
+        }
         if (args.fsbno == NULLFSBLOCK) {
                 XFS_BMBT_TRACE_CURSOR(cur, EXIT);
                 *stat = 0;
@@ -2029,22 +2059,8 @@ xfs_bmbt_increment(
  * Insert the current record at the point referenced by cur.
  *
  * A multi-level split of the tree on insert will invalidate the original
- * cursor. It appears, however, that some callers assume that the cursor is
- * always valid. Hence if we do a multi-level split we need to revalidate the
- * cursor.
- *
- * When a split occurs, we will see a new cursor returned. Use that as a
- * trigger to determine if we need to revalidate the original cursor. If we get
- * a split, then use the original irec to lookup up the path of the record we
- * just inserted.
- *
- * Note that the fact that the btree root is in the inode means that we can
- * have the level of the tree change without a "split" occurring at the root
- * level. What happens is that the root is migrated to an allocated block and
- * the inode root is pointed to it. This means a single split can change the
- * level of the tree (level 2 -> level 3) and invalidate the old cursor. Hence
- * the level change should be accounted as a split so as to correctly trigger a
- * revalidation of the old cursor.
+ * cursor.  All callers of this function should assume that the cursor is
+ * no longer valid and revalidate it.
  */
 int                                     /* error */
 xfs_bmbt_insert(
@@ -2057,14 +2073,11 @@ xfs_bmbt_insert(
         xfs_fsblock_t   nbno;
         xfs_btree_cur_t *ncur;
         xfs_bmbt_rec_t  nrec;
-        xfs_bmbt_irec_t oirec;          /* original irec */
         xfs_btree_cur_t *pcur;
-        int             splits = 0;
 
         XFS_BMBT_TRACE_CURSOR(cur, ENTRY);
         level = 0;
         nbno = NULLFSBLOCK;
-        oirec = cur->bc_rec.b;
         xfs_bmbt_disk_set_all(&nrec, &cur->bc_rec.b);
         ncur = NULL;
         pcur = cur;
@@ -2073,13 +2086,11 @@ xfs_bmbt_insert(
                                 &i))) {
                         if (pcur != cur)
                                 xfs_btree_del_cursor(pcur, XFS_BTREE_ERROR);
-                        goto error0;
+                        XFS_BMBT_TRACE_CURSOR(cur, ERROR);
+                        return error;
                 }
                 XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
                 if (pcur != cur && (ncur || nbno == NULLFSBLOCK)) {
-                        /* allocating a new root is effectively a split */
-                        if (cur->bc_nlevels != pcur->bc_nlevels)
-                                splits++;
                         cur->bc_nlevels = pcur->bc_nlevels;
                         cur->bc_private.b.allocated +=
                                 pcur->bc_private.b.allocated;
@@ -2093,21 +2104,10 @@ xfs_bmbt_insert(
                         xfs_btree_del_cursor(pcur, XFS_BTREE_NOERROR);
                 }
                 if (ncur) {
-                        splits++;
                         pcur = ncur;
                         ncur = NULL;
                 }
         } while (nbno != NULLFSBLOCK);
-
-        if (splits > 1) {
-                /* revalidate the old cursor as we had a multi-level split */
-                error = xfs_bmbt_lookup_eq(cur, oirec.br_startoff,
-                                oirec.br_startblock, oirec.br_blockcount, &i);
-                if (error)
-                        goto error0;
-                ASSERT(i == 1);
-        }
-
         XFS_BMBT_TRACE_CURSOR(cur, EXIT);
         *stat = i;
         return 0;
@@ -2254,7 +2254,9 @@ xfs_bmbt_newroot(
 #endif
                 args.fsbno = be64_to_cpu(*pp);
                 args.type = XFS_ALLOCTYPE_START_BNO;
-        } else
+        } else if (cur->bc_private.b.flist->xbf_low)
+                args.type = XFS_ALLOCTYPE_START_BNO;
+        else
                 args.type = XFS_ALLOCTYPE_NEAR_BNO;
         if ((error = xfs_alloc_vextent(&args))) {
                 XFS_BMBT_TRACE_CURSOR(cur, ERROR);
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 53a71c62025d..d86ca2c03a70 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -889,9 +889,9 @@ xfs_buf_item_relse(
         }
 
 #ifdef XFS_TRANS_DEBUG
-        kmem_free(bip->bli_orig, XFS_BUF_COUNT(bp));
+        kmem_free(bip->bli_orig);
         bip->bli_orig = NULL;
-        kmem_free(bip->bli_logged, XFS_BUF_COUNT(bp) / NBBY);
+        kmem_free(bip->bli_logged);
         bip->bli_logged = NULL;
 #endif /* XFS_TRANS_DEBUG */
 
@@ -1138,9 +1138,9 @@ xfs_buf_iodone(
         xfs_trans_delete_ail(mp, (xfs_log_item_t *)bip);
 
 #ifdef XFS_TRANS_DEBUG
-        kmem_free(bip->bli_orig, XFS_BUF_COUNT(bp));
+        kmem_free(bip->bli_orig);
         bip->bli_orig = NULL;
-        kmem_free(bip->bli_logged, XFS_BUF_COUNT(bp) / NBBY);
+        kmem_free(bip->bli_logged);
         bip->bli_logged = NULL;
 #endif /* XFS_TRANS_DEBUG */
 
diff --git a/fs/xfs/xfs_clnt.h b/fs/xfs/xfs_clnt.h
index d5d1e60ee224..d2ce5dd70d87 100644
--- a/fs/xfs/xfs_clnt.h
+++ b/fs/xfs/xfs_clnt.h
@@ -78,6 +78,7 @@ struct xfs_mount_args {
 #define XFSMNT_IOSIZE           0x00002000      /* optimize for I/O size */
 #define XFSMNT_OSYNCISOSYNC     0x00004000      /* o_sync is REALLY o_sync */
                                                 /* (osyncisdsync is default) */
+#define XFSMNT_NOATTR2          0x00008000      /* turn off ATTR2 EA format */
 #define XFSMNT_32BITINODES      0x00200000      /* restrict inodes to 32
                                                  * bits of address space */
 #define XFSMNT_GQUOTA           0x00400000      /* group quota accounting */
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index 021a8f7e563f..9e561a9cefca 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -1431,7 +1431,7 @@ xfs_da_path_shift(xfs_da_state_t *state, xfs_da_state_path_t *path,
         }
         if (level < 0) {
                 *result = XFS_ERROR(ENOENT);    /* we're out of our tree */
-                ASSERT(args->oknoent);
+                ASSERT(args->op_flags & XFS_DA_OP_OKNOENT);
                 return(0);
         }
 
@@ -1530,6 +1530,28 @@ xfs_da_hashname(const uchar_t *name, int namelen)
         }
 }
 
+enum xfs_dacmp
+xfs_da_compname(
+        struct xfs_da_args *args,
+        const char      *name,
+        int             len)
+{
+        return (args->namelen == len && memcmp(args->name, name, len) == 0) ?
+                                        XFS_CMP_EXACT : XFS_CMP_DIFFERENT;
+}
+
+static xfs_dahash_t
+xfs_default_hashname(
+        struct xfs_name *name)
+{
+        return xfs_da_hashname(name->name, name->len);
+}
+
+const struct xfs_nameops xfs_default_nameops = {
+        .hashname       = xfs_default_hashname,
+        .compname       = xfs_da_compname
+};
+
 /*
  * Add a block to the btree ahead of the file.
  * Return the new block number to the caller.
@@ -1598,7 +1620,7 @@ xfs_da_grow_inode(xfs_da_args_t *args, xfs_dablk_t *new_blkno)
                                         args->firstblock, args->total,
                                         &mapp[mapi], &nmap, args->flist,
                                         NULL))) {
-                                kmem_free(mapp, sizeof(*mapp) * count);
+                                kmem_free(mapp);
                                 return error;
                         }
                         if (nmap < 1)
@@ -1620,11 +1642,11 @@ xfs_da_grow_inode(xfs_da_args_t *args, xfs_dablk_t *new_blkno)
             mapp[mapi - 1].br_startoff + mapp[mapi - 1].br_blockcount !=
             bno + count) {
                 if (mapp != &map)
-                        kmem_free(mapp, sizeof(*mapp) * count);
+                        kmem_free(mapp);
                 return XFS_ERROR(ENOSPC);
         }
         if (mapp != &map)
-                kmem_free(mapp, sizeof(*mapp) * count);
+                kmem_free(mapp);
         *new_blkno = (xfs_dablk_t)bno;
         return 0;
 }
@@ -2090,10 +2112,10 @@ xfs_da_do_buf(
                 }
         }
         if (bplist) {
-                kmem_free(bplist, sizeof(*bplist) * nmap);
+                kmem_free(bplist);
         }
         if (mapp != &map) {
-                kmem_free(mapp, sizeof(*mapp) * nfsb);
+                kmem_free(mapp);
         }
         if (bpp)
                 *bpp = rbp;
@@ -2102,11 +2124,11 @@ exit1:
         if (bplist) {
                 for (i = 0; i < nbplist; i++)
                         xfs_trans_brelse(trans, bplist[i]);
-                kmem_free(bplist, sizeof(*bplist) * nmap);
+                kmem_free(bplist);
         }
 exit0:
         if (mapp != &map)
-                kmem_free(mapp, sizeof(*mapp) * nfsb);
+                kmem_free(mapp);
         if (bpp)
                 *bpp = NULL;
         return error;
@@ -2218,7 +2240,7 @@ xfs_da_state_free(xfs_da_state_t *state)
 
 #ifdef XFS_DABUF_DEBUG
 xfs_dabuf_t     *xfs_dabuf_global_list;
-spinlock_t      xfs_dabuf_global_lock;
+static DEFINE_SPINLOCK(xfs_dabuf_global_lock);
 #endif
 
 /*
@@ -2315,7 +2337,7 @@ xfs_da_buf_done(xfs_dabuf_t *dabuf)
         if (dabuf->dirty)
                 xfs_da_buf_clean(dabuf);
         if (dabuf->nbuf > 1)
-                kmem_free(dabuf->data, BBTOB(dabuf->bbcount));
+                kmem_free(dabuf->data);
 #ifdef XFS_DABUF_DEBUG
         {
                 spin_lock(&xfs_dabuf_global_lock);
@@ -2332,7 +2354,7 @@ xfs_da_buf_done(xfs_dabuf_t *dabuf)
         if (dabuf->nbuf == 1)
                 kmem_zone_free(xfs_dabuf_zone, dabuf);
         else
-                kmem_free(dabuf, XFS_DA_BUF_SIZE(dabuf->nbuf));
+                kmem_free(dabuf);
 }
 
 /*
@@ -2403,7 +2425,7 @@ xfs_da_brelse(xfs_trans_t *tp, xfs_dabuf_t *dabuf)
         for (i = 0; i < nbuf; i++)
                 xfs_trans_brelse(tp, bplist[i]);
         if (bplist != &bp)
-                kmem_free(bplist, nbuf * sizeof(*bplist));
+                kmem_free(bplist);
 }
 
 /*
@@ -2429,7 +2451,7 @@ xfs_da_binval(xfs_trans_t *tp, xfs_dabuf_t *dabuf)
         for (i = 0; i < nbuf; i++)
                 xfs_trans_binval(tp, bplist[i]);
         if (bplist != &bp)
-                kmem_free(bplist, nbuf * sizeof(*bplist));
+                kmem_free(bplist);
 }
 
 /*
diff --git a/fs/xfs/xfs_da_btree.h b/fs/xfs/xfs_da_btree.h
index 7facf86f74f9..8be0b00ede9a 100644
--- a/fs/xfs/xfs_da_btree.h
+++ b/fs/xfs/xfs_da_btree.h
@@ -99,6 +99,15 @@ typedef struct xfs_da_node_entry xfs_da_node_entry_t;
  *========================================================================*/
 
 /*
+ * Search comparison results
+ */
+enum xfs_dacmp {
+        XFS_CMP_DIFFERENT,      /* names are completely different */
+        XFS_CMP_EXACT,          /* names are exactly the same */
+        XFS_CMP_CASE            /* names are same but differ in case */
+};
+
+/*
  * Structure to ease passing around component names.
  */
 typedef struct xfs_da_args {
@@ -123,13 +132,20 @@ typedef struct xfs_da_args {
         int             index2;         /* index of 2nd attr in blk */
         xfs_dablk_t     rmtblkno2;      /* remote attr value starting blkno */
         int             rmtblkcnt2;     /* remote attr value block count */
-        unsigned char   justcheck;      /* T/F: check for ok with no space */
-        unsigned char   rename;         /* T/F: this is an atomic rename op */
-        unsigned char   addname;        /* T/F: this is an add operation */
-        unsigned char   oknoent;        /* T/F: ok to return ENOENT, else die */
+        int             op_flags;       /* operation flags */
+        enum xfs_dacmp  cmpresult;      /* name compare result for lookups */
 } xfs_da_args_t;
 
 /*
+ * Operation flags:
+ */
+#define XFS_DA_OP_JUSTCHECK     0x0001  /* check for ok with no space */
+#define XFS_DA_OP_RENAME        0x0002  /* this is an atomic rename op */
+#define XFS_DA_OP_ADDNAME       0x0004  /* this is an add operation */
+#define XFS_DA_OP_OKNOENT       0x0008  /* lookup/add op, ENOENT ok, else die */
+#define XFS_DA_OP_CILOOKUP      0x0010  /* lookup to return CI name if found */
+
+/*
  * Structure to describe buffer(s) for a block.
  * This is needed in the directory version 2 format case, when
  * multiple non-contiguous fsblocks might be needed to cover one
@@ -201,6 +217,14 @@ typedef struct xfs_da_state {
                 (uint)(XFS_DA_LOGOFF(BASE, ADDR)), \
                 (uint)(XFS_DA_LOGOFF(BASE, ADDR)+(SIZE)-1)
 
+/*
+ * Name ops for directory and/or attr name operations
+ */
+struct xfs_nameops {
+        xfs_dahash_t    (*hashname)(struct xfs_name *);
+        enum xfs_dacmp  (*compname)(struct xfs_da_args *, const char *, int);
+};
+
 
 #ifdef __KERNEL__
 /*========================================================================
@@ -249,6 +273,10 @@ int	xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
                                           xfs_dabuf_t *dead_buf);
 
 uint xfs_da_hashname(const uchar_t *name_string, int name_length);
+enum xfs_dacmp xfs_da_compname(struct xfs_da_args *args,
+                                const char *name, int len);
+
+
 xfs_da_state_t *xfs_da_state_alloc(void);
 void xfs_da_state_free(xfs_da_state_t *state);
 
diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c
index 5f3647cb9885..2211e885ef24 100644
--- a/fs/xfs/xfs_dfrag.c
+++ b/fs/xfs/xfs_dfrag.c
@@ -116,7 +116,7 @@ xfs_swapext(
  out_put_file:
         fput(file);
  out_free_sxp:
-        kmem_free(sxp, sizeof(xfs_swapext_t));
+        kmem_free(sxp);
  out:
         return error;
 }
@@ -381,6 +381,6 @@ xfs_swap_extents(
                 xfs_iunlock(tip, lock_flags);
         }
         if (tempifp != NULL)
-                kmem_free(tempifp, sizeof(xfs_ifork_t));
+                kmem_free(tempifp);
         return error;
 }
diff --git a/fs/xfs/xfs_dir2.c b/fs/xfs/xfs_dir2.c
index 7cb26529766b..80e0dc51361c 100644
--- a/fs/xfs/xfs_dir2.c
+++ b/fs/xfs/xfs_dir2.c
@@ -46,6 +46,54 @@
 
 struct xfs_name xfs_name_dotdot = {"..", 2};
 
+extern const struct xfs_nameops xfs_default_nameops;
+
+/*
+ * ASCII case-insensitive (ie. A-Z) support for directories that was
+ * used in IRIX.
+ */
+STATIC xfs_dahash_t
+xfs_ascii_ci_hashname(
+        struct xfs_name *name)
+{
+        xfs_dahash_t    hash;
+        int             i;
+
+        for (i = 0, hash = 0; i < name->len; i++)
+                hash = tolower(name->name[i]) ^ rol32(hash, 7);
+
+        return hash;
+}
+
+STATIC enum xfs_dacmp
+xfs_ascii_ci_compname(
+        struct xfs_da_args *args,
+        const char      *name,
+        int             len)
+{
+        enum xfs_dacmp  result;
+        int             i;
+
+        if (args->namelen != len)
+                return XFS_CMP_DIFFERENT;
+
+        result = XFS_CMP_EXACT;
+        for (i = 0; i < len; i++) {
+                if (args->name[i] == name[i])
+                        continue;
+                if (tolower(args->name[i]) != tolower(name[i]))
+                        return XFS_CMP_DIFFERENT;
+                result = XFS_CMP_CASE;
+        }
+
+        return result;
+}
+
+static struct xfs_nameops xfs_ascii_ci_nameops = {
+        .hashname       = xfs_ascii_ci_hashname,
+        .compname       = xfs_ascii_ci_compname,
+};
+
 void
 xfs_dir_mount(
         xfs_mount_t     *mp)
@@ -65,6 +113,10 @@ xfs_dir_mount(
                 (mp->m_dirblksize - (uint)sizeof(xfs_da_node_hdr_t)) /
                 (uint)sizeof(xfs_da_node_entry_t);
         mp->m_dir_magicpct = (mp->m_dirblksize * 37) / 100;
+        if (xfs_sb_version_hasasciici(&mp->m_sb))
+                mp->m_dirnameops = &xfs_ascii_ci_nameops;
+        else
+                mp->m_dirnameops = &xfs_default_nameops;
 }
 
 /*
@@ -162,9 +214,10 @@ xfs_dir_createname(
                 return rval;
         XFS_STATS_INC(xs_dir_create);
 
+        memset(&args, 0, sizeof(xfs_da_args_t));
         args.name = name->name;
         args.namelen = name->len;
-        args.hashval = xfs_da_hashname(name->name, name->len);
+        args.hashval = dp->i_mount->m_dirnameops->hashname(name);
         args.inumber = inum;
         args.dp = dp;
         args.firstblock = first;
@@ -172,8 +225,7 @@ xfs_dir_createname(
         args.total = total;
         args.whichfork = XFS_DATA_FORK;
         args.trans = tp;
-        args.justcheck = 0;
-        args.addname = args.oknoent = 1;
+        args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
 
         if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL)
                 rval = xfs_dir2_sf_addname(&args);
@@ -191,14 +243,43 @@ xfs_dir_createname(
 }
 
 /*
+ * If doing a CI lookup and case-insensitive match, dup actual name into
+ * args.value. Return EEXIST for success (ie. name found) or an error.
+ */
+int
+xfs_dir_cilookup_result(
+        struct xfs_da_args *args,
+        const char      *name,
+        int             len)
+{
+        if (args->cmpresult == XFS_CMP_DIFFERENT)
+                return ENOENT;
+        if (args->cmpresult != XFS_CMP_CASE ||
+                                        !(args->op_flags & XFS_DA_OP_CILOOKUP))
+                return EEXIST;
+
+        args->value = kmem_alloc(len, KM_MAYFAIL);
+        if (!args->value)
+                return ENOMEM;
+
+        memcpy(args->value, name, len);
+        args->valuelen = len;
+        return EEXIST;
+}
+
+/*
  * Lookup a name in a directory, give back the inode number.
+ * If ci_name is not NULL, returns the actual name in ci_name if it differs
+ * to name, or ci_name->name is set to NULL for an exact match.
  */
+
 int
 xfs_dir_lookup(
         xfs_trans_t     *tp,
         xfs_inode_t     *dp,
         struct xfs_name *name,
-        xfs_ino_t       *inum)          /* out: inode number */
+        xfs_ino_t       *inum,          /* out: inode number */
+        struct xfs_name *ci_name)       /* out: actual name if CI match */
 {
         xfs_da_args_t   args;
         int             rval;
@@ -206,15 +287,17 @@ xfs_dir_lookup(
 
         ASSERT((dp->i_d.di_mode & S_IFMT) == S_IFDIR);
         XFS_STATS_INC(xs_dir_lookup);
-        memset(&args, 0, sizeof(xfs_da_args_t));
 
+        memset(&args, 0, sizeof(xfs_da_args_t));
         args.name = name->name;
         args.namelen = name->len;
-        args.hashval = xfs_da_hashname(name->name, name->len);
+        args.hashval = dp->i_mount->m_dirnameops->hashname(name);
         args.dp = dp;
         args.whichfork = XFS_DATA_FORK;
         args.trans = tp;
-        args.oknoent = 1;
+        args.op_flags = XFS_DA_OP_OKNOENT;
+        if (ci_name)
+                args.op_flags |= XFS_DA_OP_CILOOKUP;
 
         if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL)
                 rval = xfs_dir2_sf_lookup(&args);
@@ -230,8 +313,13 @@ xfs_dir_lookup(
                 rval = xfs_dir2_node_lookup(&args);
         if (rval == EEXIST)
                 rval = 0;
-        if (rval == 0)
+        if (!rval) {
                 *inum = args.inumber;
+                if (ci_name) {
+                        ci_name->name = args.value;
+                        ci_name->len = args.valuelen;
+                }
+        }
         return rval;
 }
 
@@ -255,9 +343,10 @@ xfs_dir_removename(
         ASSERT((dp->i_d.di_mode & S_IFMT) == S_IFDIR);
         XFS_STATS_INC(xs_dir_remove);
 
+        memset(&args, 0, sizeof(xfs_da_args_t));
         args.name = name->name;
         args.namelen = name->len;
-        args.hashval = xfs_da_hashname(name->name, name->len);
+        args.hashval = dp->i_mount->m_dirnameops->hashname(name);
         args.inumber = ino;
         args.dp = dp;
         args.firstblock = first;
@@ -265,7 +354,6 @@ xfs_dir_removename(
         args.total = total;
         args.whichfork = XFS_DATA_FORK;
         args.trans = tp;
-        args.justcheck = args.addname = args.oknoent = 0;
 
         if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL)
                 rval = xfs_dir2_sf_removename(&args);
@@ -338,9 +426,10 @@ xfs_dir_replace(
         if ((rval = xfs_dir_ino_validate(tp->t_mountp, inum)))
                 return rval;
 
+        memset(&args, 0, sizeof(xfs_da_args_t));
         args.name = name->name;
         args.namelen = name->len;
-        args.hashval = xfs_da_hashname(name->name, name->len);
+        args.hashval = dp->i_mount->m_dirnameops->hashname(name);
         args.inumber = inum;
         args.dp = dp;
         args.firstblock = first;
@@ -348,7 +437,6 @@ xfs_dir_replace(
         args.total = total;
         args.whichfork = XFS_DATA_FORK;
         args.trans = tp;
-        args.justcheck = args.addname = args.oknoent = 0;
 
         if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL)
                 rval = xfs_dir2_sf_replace(&args);
@@ -384,15 +472,16 @@ xfs_dir_canenter(
                 return 0;
 
         ASSERT((dp->i_d.di_mode & S_IFMT) == S_IFDIR);
-        memset(&args, 0, sizeof(xfs_da_args_t));
 
+        memset(&args, 0, sizeof(xfs_da_args_t));
         args.name = name->name;
         args.namelen = name->len;
-        args.hashval = xfs_da_hashname(name->name, name->len);
+        args.hashval = dp->i_mount->m_dirnameops->hashname(name);
         args.dp = dp;
         args.whichfork = XFS_DATA_FORK;
         args.trans = tp;
-        args.justcheck = args.addname = args.oknoent = 1;
+        args.op_flags = XFS_DA_OP_JUSTCHECK | XFS_DA_OP_ADDNAME |
+                                                        XFS_DA_OP_OKNOENT;
 
         if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL)
                 rval = xfs_dir2_sf_addname(&args);
@@ -493,7 +582,7 @@ xfs_dir2_grow_inode(
                                         args->firstblock, args->total,
                                         &mapp[mapi], &nmap, args->flist,
                                         NULL))) {
-                                kmem_free(mapp, sizeof(*mapp) * count);
+                                kmem_free(mapp);
                                 return error;
                         }
                         if (nmap < 1)
@@ -525,14 +614,14 @@ xfs_dir2_grow_inode(
             mapp[mapi - 1].br_startoff + mapp[mapi - 1].br_blockcount !=
             bno + count) {
                 if (mapp != &map)
-                        kmem_free(mapp, sizeof(*mapp) * count);
+                        kmem_free(mapp);
                 return XFS_ERROR(ENOSPC);
         }
         /*
          * Done with the temporary mapping table.
          */
         if (mapp != &map)
-                kmem_free(mapp, sizeof(*mapp) * count);
+                kmem_free(mapp);
         *dbp = xfs_dir2_da_to_db(mp, (xfs_dablk_t)bno);
         /*
          * Update file's size if this is the data space and it grew.
diff --git a/fs/xfs/xfs_dir2.h b/fs/xfs/xfs_dir2.h
index 6392f939029f..1d9ef96f33aa 100644
--- a/fs/xfs/xfs_dir2.h
+++ b/fs/xfs/xfs_dir2.h
@@ -74,7 +74,8 @@ extern int xfs_dir_createname(struct xfs_trans *tp, struct xfs_inode *dp,
                                 xfs_fsblock_t *first,
                                 struct xfs_bmap_free *flist, xfs_extlen_t tot);
 extern int xfs_dir_lookup(struct xfs_trans *tp, struct xfs_inode *dp,
-                                struct xfs_name *name, xfs_ino_t *inum);
+                                struct xfs_name *name, xfs_ino_t *inum,
+                                struct xfs_name *ci_name);
 extern int xfs_dir_removename(struct xfs_trans *tp, struct xfs_inode *dp,
                                 struct xfs_name *name, xfs_ino_t ino,
                                 xfs_fsblock_t *first,
@@ -99,4 +100,7 @@ extern int xfs_dir2_isleaf(struct xfs_trans *tp, struct xfs_inode *dp,
 extern int xfs_dir2_shrink_inode(struct xfs_da_args *args, xfs_dir2_db_t db,
                                 struct xfs_dabuf *bp);
 
+extern int xfs_dir_cilookup_result(struct xfs_da_args *args, const char *name,
+                                int len);
+
 #endif  /* __XFS_DIR2_H__ */
diff --git a/fs/xfs/xfs_dir2_block.c b/fs/xfs/xfs_dir2_block.c
index fb5a556725b3..e2fa0a1d8e96 100644
--- a/fs/xfs/xfs_dir2_block.c
+++ b/fs/xfs/xfs_dir2_block.c
@@ -215,7 +215,7 @@ xfs_dir2_block_addname(
         /*
          * If this isn't a real add, we're done with the buffer.
          */
-        if (args->justcheck)
+        if (args->op_flags & XFS_DA_OP_JUSTCHECK)
                 xfs_da_brelse(tp, bp);
         /*
          * If we don't have space for the new entry & leaf ...
@@ -225,7 +225,7 @@ xfs_dir2_block_addname(
                  * Not trying to actually do anything, or don't have
                  * a space reservation: return no-space.
                  */
-                if (args->justcheck || args->total == 0)
+                if ((args->op_flags & XFS_DA_OP_JUSTCHECK) || args->total == 0)
                         return XFS_ERROR(ENOSPC);
                 /*
                  * Convert to the next larger format.
@@ -240,7 +240,7 @@ xfs_dir2_block_addname(
         /*
          * Just checking, and it would work, so say so.
          */
-        if (args->justcheck)
+        if (args->op_flags & XFS_DA_OP_JUSTCHECK)
                 return 0;
         needlog = needscan = 0;
         /*
@@ -610,14 +610,15 @@ xfs_dir2_block_lookup(
         /*
          * Get the offset from the leaf entry, to point to the data.
          */
-        dep = (xfs_dir2_data_entry_t *)
-              ((char *)block + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(blp[ent].address)));
+        dep = (xfs_dir2_data_entry_t *)((char *)block +
+                xfs_dir2_dataptr_to_off(mp, be32_to_cpu(blp[ent].address)));
         /*
-         * Fill in inode number, release the block.
+         * Fill in inode number, CI name if appropriate, release the block.
          */
         args->inumber = be64_to_cpu(dep->inumber);
+        error = xfs_dir_cilookup_result(args, dep->name, dep->namelen);
         xfs_da_brelse(args->trans, bp);
-        return XFS_ERROR(EEXIST);
+        return XFS_ERROR(error);
 }
 
 /*
@@ -643,6 +644,7 @@ xfs_dir2_block_lookup_int(
         int                     mid;            /* binary search current idx */
         xfs_mount_t             *mp;            /* filesystem mount point */
         xfs_trans_t             *tp;            /* transaction pointer */
+        enum xfs_dacmp          cmp;            /* comparison result */
 
         dp = args->dp;
         tp = args->trans;
@@ -673,7 +675,7 @@ xfs_dir2_block_lookup_int(
                 else
                         high = mid - 1;
                 if (low > high) {
-                        ASSERT(args->oknoent);
+                        ASSERT(args->op_flags & XFS_DA_OP_OKNOENT);
                         xfs_da_brelse(tp, bp);
                         return XFS_ERROR(ENOENT);
                 }
@@ -697,20 +699,31 @@ xfs_dir2_block_lookup_int(
                 dep = (xfs_dir2_data_entry_t *)
                         ((char *)block + xfs_dir2_dataptr_to_off(mp, addr));
                 /*
-                 * Compare, if it's right give back buffer & entry number.
+                 * Compare name and if it's an exact match, return the index
+                 * and buffer. If it's the first case-insensitive match, store
+                 * the index and buffer and continue looking for an exact match.
                  */
-                if (dep->namelen == args->namelen &&
-                    dep->name[0] == args->name[0] &&
-                    memcmp(dep->name, args->name, args->namelen) == 0) {
+                cmp = mp->m_dirnameops->compname(args, dep->name, dep->namelen);
+                if (cmp != XFS_CMP_DIFFERENT && cmp != args->cmpresult) {
+                        args->cmpresult = cmp;
                         *bpp = bp;
                         *entno = mid;
-                        return 0;
+                        if (cmp == XFS_CMP_EXACT)
+                                return 0;
                 }
-        } while (++mid < be32_to_cpu(btp->count) && be32_to_cpu(blp[mid].hashval) == hash);
+        } while (++mid < be32_to_cpu(btp->count) &&
+                        be32_to_cpu(blp[mid].hashval) == hash);
+
+        ASSERT(args->op_flags & XFS_DA_OP_OKNOENT);
+        /*
+         * Here, we can only be doing a lookup (not a rename or replace).
+         * If a case-insensitive match was found earlier, return success.
+         */
+        if (args->cmpresult == XFS_CMP_CASE)
+                return 0;
         /*
          * No match, release the buffer and return ENOENT.
          */
-        ASSERT(args->oknoent);
         xfs_da_brelse(tp, bp);
         return XFS_ERROR(ENOENT);
 }
@@ -1033,6 +1046,7 @@ xfs_dir2_sf_to_block(
         xfs_dir2_sf_t           *sfp;           /* shortform structure */
         __be16                  *tagp;          /* end of data entry */
         xfs_trans_t             *tp;            /* transaction pointer */
+        struct xfs_name         name;
 
         xfs_dir2_trace_args("sf_to_block", args);
         dp = args->dp;
@@ -1071,7 +1085,7 @@ xfs_dir2_sf_to_block(
          */
         error = xfs_dir2_grow_inode(args, XFS_DIR2_DATA_SPACE, &blkno);
         if (error) {
-                kmem_free(buf, buf_len);
+                kmem_free(buf);
                 return error;
         }
         /*
@@ -1079,7 +1093,7 @@ xfs_dir2_sf_to_block(
          */
         error = xfs_dir2_data_init(args, blkno, &bp);
         if (error) {
-                kmem_free(buf, buf_len);
+                kmem_free(buf);
                 return error;
         }
         block = bp->data;
@@ -1187,8 +1201,10 @@ xfs_dir2_sf_to_block(
                 tagp = xfs_dir2_data_entry_tag_p(dep);
                 *tagp = cpu_to_be16((char *)dep - (char *)block);
                 xfs_dir2_data_log_entry(tp, bp, dep);
-                blp[2 + i].hashval = cpu_to_be32(xfs_da_hashname(
-                                        (char *)sfep->name, sfep->namelen));
+                name.name = sfep->name;
+                name.len = sfep->namelen;
+                blp[2 + i].hashval = cpu_to_be32(mp->m_dirnameops->
+                                                        hashname(&name));
                 blp[2 + i].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
                                                  (char *)dep - (char *)block));
                 offset = (int)((char *)(tagp + 1) - (char *)block);
@@ -1198,7 +1214,7 @@ xfs_dir2_sf_to_block(
                         sfep = xfs_dir2_sf_nextentry(sfp, sfep);
         }
         /* Done with the temporary buffer */
-        kmem_free(buf, buf_len);
+        kmem_free(buf);
         /*
          * Sort the leaf entries by hash value.
          */
diff --git a/fs/xfs/xfs_dir2_data.c b/fs/xfs/xfs_dir2_data.c
index fb8c9e08b23d..498f8d694330 100644
--- a/fs/xfs/xfs_dir2_data.c
+++ b/fs/xfs/xfs_dir2_data.c
@@ -65,6 +65,7 @@ xfs_dir2_data_check(
         xfs_mount_t             *mp;            /* filesystem mount point */
         char                    *p;             /* current data position */
         int                     stale;          /* count of stale leaves */
+        struct xfs_name         name;
 
         mp = dp->i_mount;
         d = bp->data;
@@ -140,7 +141,9 @@ xfs_dir2_data_check(
                         addr = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
                                 (xfs_dir2_data_aoff_t)
                                 ((char *)dep - (char *)d));
-                        hash = xfs_da_hashname((char *)dep->name, dep->namelen);
+                        name.name = dep->name;
+                        name.len = dep->namelen;
+                        hash = mp->m_dirnameops->hashname(&name);
                         for (i = 0; i < be32_to_cpu(btp->count); i++) {
                                 if (be32_to_cpu(lep[i].address) == addr &&
                                     be32_to_cpu(lep[i].hashval) == hash)
diff --git a/fs/xfs/xfs_dir2_leaf.c b/fs/xfs/xfs_dir2_leaf.c
index bc52b803d79b..93535992cb60 100644
--- a/fs/xfs/xfs_dir2_leaf.c
+++ b/fs/xfs/xfs_dir2_leaf.c
@@ -263,20 +263,21 @@ xfs_dir2_leaf_addname(
          * If we don't have enough free bytes but we can make enough
          * by compacting out stale entries, we'll do that.
          */
-        if ((char *)bestsp - (char *)&leaf->ents[be16_to_cpu(leaf->hdr.count)] < needbytes &&
-            be16_to_cpu(leaf->hdr.stale) > 1) {
+        if ((char *)bestsp - (char *)&leaf->ents[be16_to_cpu(leaf->hdr.count)] <
+                                needbytes && be16_to_cpu(leaf->hdr.stale) > 1) {
                 compact = 1;
         }
         /*
          * Otherwise if we don't have enough free bytes we need to
          * convert to node form.
          */
-        else if ((char *)bestsp - (char *)&leaf->ents[be16_to_cpu(leaf->hdr.count)] <
-                 needbytes) {
+        else if ((char *)bestsp - (char *)&leaf->ents[be16_to_cpu(
+                                                leaf->hdr.count)] < needbytes) {
                 /*
                  * Just checking or no space reservation, give up.
                  */
-                if (args->justcheck || args->total == 0) {
+                if ((args->op_flags & XFS_DA_OP_JUSTCHECK) ||
+                                                        args->total == 0) {
                         xfs_da_brelse(tp, lbp);
                         return XFS_ERROR(ENOSPC);
                 }
@@ -301,7 +302,7 @@ xfs_dir2_leaf_addname(
          * If just checking, then it will fit unless we needed to allocate
          * a new data block.
          */
-        if (args->justcheck) {
+        if (args->op_flags & XFS_DA_OP_JUSTCHECK) {
                 xfs_da_brelse(tp, lbp);
                 return use_block == -1 ? XFS_ERROR(ENOSPC) : 0;
         }
@@ -1110,7 +1111,7 @@ xfs_dir2_leaf_getdents(
                 *offset = XFS_DIR2_MAX_DATAPTR;
         else
                 *offset = xfs_dir2_byte_to_dataptr(mp, curoff);
-        kmem_free(map, map_size * sizeof(*map));
+        kmem_free(map);
         if (bp)
                 xfs_da_brelse(NULL, bp);
         return error;
@@ -1298,12 +1299,13 @@ xfs_dir2_leaf_lookup(
               ((char *)dbp->data +
                xfs_dir2_dataptr_to_off(dp->i_mount, be32_to_cpu(lep->address)));
         /*
-         * Return the found inode number.
+         * Return the found inode number & CI name if appropriate
          */
         args->inumber = be64_to_cpu(dep->inumber);
+        error = xfs_dir_cilookup_result(args, dep->name, dep->namelen);
         xfs_da_brelse(tp, dbp);
         xfs_da_brelse(tp, lbp);
-        return XFS_ERROR(EEXIST);
+        return XFS_ERROR(error);
 }
 
 /*
@@ -1319,8 +1321,8 @@ xfs_dir2_leaf_lookup_int(
         int                     *indexp,        /* out: index in leaf block */
         xfs_dabuf_t             **dbpp)         /* out: data buffer */
 {
-        xfs_dir2_db_t           curdb;          /* current data block number */
-        xfs_dabuf_t             *dbp;           /* data buffer */
+        xfs_dir2_db_t           curdb = -1;     /* current data block number */
+        xfs_dabuf_t             *dbp = NULL;    /* data buffer */
         xfs_dir2_data_entry_t   *dep;           /* data entry */
         xfs_inode_t             *dp;            /* incore directory inode */
         int                     error;          /* error return code */
@@ -1331,6 +1333,8 @@ xfs_dir2_leaf_lookup_int(
         xfs_mount_t             *mp;            /* filesystem mount point */
         xfs_dir2_db_t           newdb;          /* new data block number */
         xfs_trans_t             *tp;            /* transaction pointer */
+        xfs_dir2_db_t           cidb = -1;      /* case match data block no. */
+        enum xfs_dacmp          cmp;            /* name compare result */
 
         dp = args->dp;
         tp = args->trans;
@@ -1338,11 +1342,10 @@ xfs_dir2_leaf_lookup_int(
         /*
          * Read the leaf block into the buffer.
          */
-        if ((error =
-            xfs_da_read_buf(tp, dp, mp->m_dirleafblk, -1, &lbp,
-                    XFS_DATA_FORK))) {
+        error = xfs_da_read_buf(tp, dp, mp->m_dirleafblk, -1, &lbp,
+                                                        XFS_DATA_FORK);
+        if (error)
                 return error;
-        }
         *lbpp = lbp;
         leaf = lbp->data;
         xfs_dir2_leaf_check(dp, lbp);
@@ -1354,9 +1357,9 @@ xfs_dir2_leaf_lookup_int(
          * Loop over all the entries with the right hash value
          * looking to match the name.
          */
-        for (lep = &leaf->ents[index], dbp = NULL, curdb = -1;
-             index < be16_to_cpu(leaf->hdr.count) && be32_to_cpu(lep->hashval) == args->hashval;
-             lep++, index++) {
+        for (lep = &leaf->ents[index]; index < be16_to_cpu(leaf->hdr.count) &&
+                                be32_to_cpu(lep->hashval) == args->hashval;
+                                lep++, index++) {
                 /*
                  * Skip over stale leaf entries.
                  */
@@ -1373,10 +1376,10 @@ xfs_dir2_leaf_lookup_int(
                 if (newdb != curdb) {
                         if (dbp)
                                 xfs_da_brelse(tp, dbp);
-                        if ((error =
-                            xfs_da_read_buf(tp, dp,
-                                    xfs_dir2_db_to_da(mp, newdb), -1, &dbp,
-                                    XFS_DATA_FORK))) {
+                        error = xfs_da_read_buf(tp, dp,
+                                                xfs_dir2_db_to_da(mp, newdb),
+                                                -1, &dbp, XFS_DATA_FORK);
+                        if (error) {
                                 xfs_da_brelse(tp, lbp);
                                 return error;
                         }
@@ -1386,24 +1389,50 @@ xfs_dir2_leaf_lookup_int(
                 /*
                  * Point to the data entry.
                  */
-                dep = (xfs_dir2_data_entry_t *)
-                      ((char *)dbp->data +
-                       xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address)));
+                dep = (xfs_dir2_data_entry_t *)((char *)dbp->data +
+                        xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address)));
                 /*
-                 * If it matches then return it.
+                 * Compare name and if it's an exact match, return the index
+                 * and buffer. If it's the first case-insensitive match, store
+                 * the index and buffer and continue looking for an exact match.
                  */
-                if (dep->namelen == args->namelen &&
-                    dep->name[0] == args->name[0] &&
-                    memcmp(dep->name, args->name, args->namelen) == 0) {
-                        *dbpp = dbp;
+                cmp = mp->m_dirnameops->compname(args, dep->name, dep->namelen);
+                if (cmp != XFS_CMP_DIFFERENT && cmp != args->cmpresult) {
+                        args->cmpresult = cmp;
                         *indexp = index;
-                        return 0;
+                        /* case exact match: return the current buffer. */
+                        if (cmp == XFS_CMP_EXACT) {
+                                *dbpp = dbp;
+                                return 0;
+                        }
+                        cidb = curdb;
                 }
         }
+        ASSERT(args->op_flags & XFS_DA_OP_OKNOENT);
+        /*
+         * Here, we can only be doing a lookup (not a rename or remove).
+         * If a case-insensitive match was found earlier, re-read the
+         * appropriate data block if required and return it.
+         */
+        if (args->cmpresult == XFS_CMP_CASE) {
+                ASSERT(cidb != -1);
+                if (cidb != curdb) {
+                        xfs_da_brelse(tp, dbp);
+                        error = xfs_da_read_buf(tp, dp,
+                                                xfs_dir2_db_to_da(mp, cidb),
+                                                -1, &dbp, XFS_DATA_FORK);
+                        if (error) {
+                                xfs_da_brelse(tp, lbp);
+                                return error;
+                        }
+                }
+                *dbpp = dbp;
+                return 0;
+        }
         /*
          * No match found, return ENOENT.
          */
-        ASSERT(args->oknoent);
+        ASSERT(cidb == -1);
         if (dbp)
                 xfs_da_brelse(tp, dbp);
         xfs_da_brelse(tp, lbp);
diff --git a/fs/xfs/xfs_dir2_node.c b/fs/xfs/xfs_dir2_node.c
index 8dade711f099..fa6c3a5ddbc6 100644
--- a/fs/xfs/xfs_dir2_node.c
+++ b/fs/xfs/xfs_dir2_node.c
@@ -226,7 +226,7 @@ xfs_dir2_leafn_add(
         ASSERT(index == be16_to_cpu(leaf->hdr.count) ||
                be32_to_cpu(leaf->ents[index].hashval) >= args->hashval);
 
-        if (args->justcheck)
+        if (args->op_flags & XFS_DA_OP_JUSTCHECK)
                 return 0;
 
         /*
@@ -387,28 +387,26 @@ xfs_dir2_leafn_lasthash(
 }
 
 /*
- * Look up a leaf entry in a node-format leaf block.
- * If this is an addname then the extrablk in state is a freespace block,
- * otherwise it's a data block.
+ * Look up a leaf entry for space to add a name in a node-format leaf block.
+ * The extrablk in state is a freespace block.
  */
-int
-xfs_dir2_leafn_lookup_int(
+STATIC int
+xfs_dir2_leafn_lookup_for_addname(
         xfs_dabuf_t             *bp,            /* leaf buffer */
         xfs_da_args_t           *args,          /* operation arguments */
         int                     *indexp,        /* out: leaf entry index */
         xfs_da_state_t          *state)         /* state to fill in */
 {
-        xfs_dabuf_t             *curbp;         /* current data/free buffer */
-        xfs_dir2_db_t           curdb;          /* current data block number */
-        xfs_dir2_db_t           curfdb;         /* current free block number */
-        xfs_dir2_data_entry_t   *dep;           /* data block entry */
+        xfs_dabuf_t             *curbp = NULL;  /* current data/free buffer */
+        xfs_dir2_db_t           curdb = -1;     /* current data block number */
+        xfs_dir2_db_t           curfdb = -1;    /* current free block number */
         xfs_inode_t             *dp;            /* incore directory inode */
         int                     error;          /* error return value */
         int                     fi;             /* free entry index */
-        xfs_dir2_free_t         *free=NULL;     /* free block structure */
+        xfs_dir2_free_t         *free = NULL;   /* free block structure */
         int                     index;          /* leaf entry index */
         xfs_dir2_leaf_t         *leaf;          /* leaf structure */
-        int                     length=0;       /* length of new data entry */
+        int                     length;         /* length of new data entry */
         xfs_dir2_leaf_entry_t   *lep;           /* leaf entry */
         xfs_mount_t             *mp;            /* filesystem mount point */
         xfs_dir2_db_t           newdb;          /* new data block number */
@@ -431,33 +429,20 @@ xfs_dir2_leafn_lookup_int(
         /*
          * Do we have a buffer coming in?
          */
-        if (state->extravalid)
+        if (state->extravalid) {
+                /* If so, it's a free block buffer, get the block number. */
                 curbp = state->extrablk.bp;
-        else
-                curbp = NULL;
-        /*
-         * For addname, it's a free block buffer, get the block number.
-         */
-        if (args->addname) {
-                curfdb = curbp ? state->extrablk.blkno : -1;
-                curdb = -1;
-                length = xfs_dir2_data_entsize(args->namelen);
-                if ((free = (curbp ? curbp->data : NULL)))
-                        ASSERT(be32_to_cpu(free->hdr.magic) == XFS_DIR2_FREE_MAGIC);
-        }
-        /*
-         * For others, it's a data block buffer, get the block number.
-         */
-        else {
-                curfdb = -1;
-                curdb = curbp ? state->extrablk.blkno : -1;
+                curfdb = state->extrablk.blkno;
+                free = curbp->data;
+                ASSERT(be32_to_cpu(free->hdr.magic) == XFS_DIR2_FREE_MAGIC);
         }
+        length = xfs_dir2_data_entsize(args->namelen);
         /*
          * Loop over leaf entries with the right hash value.
          */
-        for (lep = &leaf->ents[index];
-             index < be16_to_cpu(leaf->hdr.count) && be32_to_cpu(lep->hashval) == args->hashval;
-             lep++, index++) {
+        for (lep = &leaf->ents[index]; index < be16_to_cpu(leaf->hdr.count) &&
+                                be32_to_cpu(lep->hashval) == args->hashval;
+                                lep++, index++) {
                 /*
                  * Skip stale leaf entries.
                  */
@@ -471,161 +456,244 @@ xfs_dir2_leafn_lookup_int(
                  * For addname, we're looking for a place to put the new entry.
                  * We want to use a data block with an entry of equal
                  * hash value to ours if there is one with room.
+                 *
+                 * If this block isn't the data block we already have
+                 * in hand, take a look at it.
                  */
-                if (args->addname) {
+                if (newdb != curdb) {
+                        curdb = newdb;
                         /*
-                         * If this block isn't the data block we already have
-                         * in hand, take a look at it.
+                         * Convert the data block to the free block
+                         * holding its freespace information.
                          */
-                        if (newdb != curdb) {
-                                curdb = newdb;
-                                /*
-                                 * Convert the data block to the free block
-                                 * holding its freespace information.
-                                 */
-                                newfdb = xfs_dir2_db_to_fdb(mp, newdb);
-                                /*
-                                 * If it's not the one we have in hand,
-                                 * read it in.
-                                 */
-                                if (newfdb != curfdb) {
-                                        /*
-                                         * If we had one before, drop it.
-                                         */
-                                        if (curbp)
-                                                xfs_da_brelse(tp, curbp);
-                                        /*
-                                         * Read the free block.
-                                         */
-                                        if ((error = xfs_da_read_buf(tp, dp,
-                                                        xfs_dir2_db_to_da(mp,
-                                                                newfdb),
-                                                        -1, &curbp,
-                                                        XFS_DATA_FORK))) {
-                                                return error;
-                                        }
-                                        free = curbp->data;
-                                        ASSERT(be32_to_cpu(free->hdr.magic) ==
-                                               XFS_DIR2_FREE_MAGIC);
-                                        ASSERT((be32_to_cpu(free->hdr.firstdb) %
-                                                XFS_DIR2_MAX_FREE_BESTS(mp)) ==
-                                               0);
-                                        ASSERT(be32_to_cpu(free->hdr.firstdb) <= curdb);
-                                        ASSERT(curdb <
-                                               be32_to_cpu(free->hdr.firstdb) +
-                                               be32_to_cpu(free->hdr.nvalid));
-                                }
-                                /*
-                                 * Get the index for our entry.
-                                 */
-                                fi = xfs_dir2_db_to_fdindex(mp, curdb);
-                                /*
-                                 * If it has room, return it.
-                                 */
-                                if (unlikely(be16_to_cpu(free->bests[fi]) == NULLDATAOFF)) {
-                                        XFS_ERROR_REPORT("xfs_dir2_leafn_lookup_int",
-                                                         XFS_ERRLEVEL_LOW, mp);
-                                        if (curfdb != newfdb)
-                                                xfs_da_brelse(tp, curbp);
-                                        return XFS_ERROR(EFSCORRUPTED);
-                                }
-                                curfdb = newfdb;
-                                if (be16_to_cpu(free->bests[fi]) >= length) {
-                                        *indexp = index;
-                                        state->extravalid = 1;
-                                        state->extrablk.bp = curbp;
-                                        state->extrablk.blkno = curfdb;
-                                        state->extrablk.index = fi;
-                                        state->extrablk.magic =
-                                                XFS_DIR2_FREE_MAGIC;
-                                        ASSERT(args->oknoent);
-                                        return XFS_ERROR(ENOENT);
-                                }
-                        }
-                }
-                /*
-                 * Not adding a new entry, so we really want to find
-                 * the name given to us.
-                 */
-                else {
+                        newfdb = xfs_dir2_db_to_fdb(mp, newdb);
                         /*
-                         * If it's a different data block, go get it.
+                         * If it's not the one we have in hand, read it in.
                          */
-                        if (newdb != curdb) {
+                        if (newfdb != curfdb) {
                                 /*
-                                 * If we had a block before, drop it.
+                                 * If we had one before, drop it.
                                  */
                                 if (curbp)
                                         xfs_da_brelse(tp, curbp);
                                 /*
-                                 * Read the data block.
+                                 * Read the free block.
                                  */
-                                if ((error =
-                                    xfs_da_read_buf(tp, dp,
-                                            xfs_dir2_db_to_da(mp, newdb), -1,
-                                            &curbp, XFS_DATA_FORK))) {
+                                error = xfs_da_read_buf(tp, dp,
+                                                xfs_dir2_db_to_da(mp, newfdb),
+                                                -1, &curbp, XFS_DATA_FORK);
+                                if (error)
                                         return error;
-                                }
-                                xfs_dir2_data_check(dp, curbp);
-                                curdb = newdb;
+                                free = curbp->data;
+                                ASSERT(be32_to_cpu(free->hdr.magic) ==
+                                        XFS_DIR2_FREE_MAGIC);
+                                ASSERT((be32_to_cpu(free->hdr.firstdb) %
+                                        XFS_DIR2_MAX_FREE_BESTS(mp)) == 0);
+                                ASSERT(be32_to_cpu(free->hdr.firstdb) <= curdb);
+                                ASSERT(curdb < be32_to_cpu(free->hdr.firstdb) +
+                                        be32_to_cpu(free->hdr.nvalid));
                         }
                         /*
-                         * Point to the data entry.
+                         * Get the index for our entry.
                          */
-                        dep = (xfs_dir2_data_entry_t *)
-                              ((char *)curbp->data +
-                               xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address)));
+                        fi = xfs_dir2_db_to_fdindex(mp, curdb);
                         /*
-                         * Compare the entry, return it if it matches.
+                         * If it has room, return it.
                          */
-                        if (dep->namelen == args->namelen &&
-                            dep->name[0] == args->name[0] &&
-                            memcmp(dep->name, args->name, args->namelen) == 0) {
-                                args->inumber = be64_to_cpu(dep->inumber);
-                                *indexp = index;
-                                state->extravalid = 1;
-                                state->extrablk.bp = curbp;
-                                state->extrablk.blkno = curdb;
-                                state->extrablk.index =
-                                        (int)((char *)dep -
-                                              (char *)curbp->data);
-                                state->extrablk.magic = XFS_DIR2_DATA_MAGIC;
-                                return XFS_ERROR(EEXIST);
+                        if (unlikely(be16_to_cpu(free->bests[fi]) == NULLDATAOFF)) {
+                                XFS_ERROR_REPORT("xfs_dir2_leafn_lookup_int",
+                                                        XFS_ERRLEVEL_LOW, mp);
+                                if (curfdb != newfdb)
+                                        xfs_da_brelse(tp, curbp);
+                                return XFS_ERROR(EFSCORRUPTED);
                         }
+                        curfdb = newfdb;
+                        if (be16_to_cpu(free->bests[fi]) >= length)
+                                goto out;
                 }
         }
+        /* Didn't find any space */
+        fi = -1;
+out:
+        ASSERT(args->op_flags & XFS_DA_OP_OKNOENT);
+        if (curbp) {
+                /* Giving back a free block. */
+                state->extravalid = 1;
+                state->extrablk.bp = curbp;
+                state->extrablk.index = fi;
+                state->extrablk.blkno = curfdb;
+                state->extrablk.magic = XFS_DIR2_FREE_MAGIC;
+        } else {
+                state->extravalid = 0;
+        }
         /*
-         * Didn't find a match.
-         * If we are holding a buffer, give it back in case our caller
-         * finds it useful.
+         * Return the index, that will be the insertion point.
          */
-        if ((state->extravalid = (curbp != NULL))) {
-                state->extrablk.bp = curbp;
-                state->extrablk.index = -1;
+        *indexp = index;
+        return XFS_ERROR(ENOENT);
+}
+
+/*
+ * Look up a leaf entry in a node-format leaf block.
+ * The extrablk in state a data block.
+ */
+STATIC int
+xfs_dir2_leafn_lookup_for_entry(
+        xfs_dabuf_t             *bp,            /* leaf buffer */
+        xfs_da_args_t           *args,          /* operation arguments */
+        int                     *indexp,        /* out: leaf entry index */
+        xfs_da_state_t          *state)         /* state to fill in */
+{
+        xfs_dabuf_t             *curbp = NULL;  /* current data/free buffer */
+        xfs_dir2_db_t           curdb = -1;     /* current data block number */
+        xfs_dir2_data_entry_t   *dep;           /* data block entry */
+        xfs_inode_t             *dp;            /* incore directory inode */
+        int                     error;          /* error return value */
+        int                     index;          /* leaf entry index */
+        xfs_dir2_leaf_t         *leaf;          /* leaf structure */
+        xfs_dir2_leaf_entry_t   *lep;           /* leaf entry */
+        xfs_mount_t             *mp;            /* filesystem mount point */
+        xfs_dir2_db_t           newdb;          /* new data block number */
+        xfs_trans_t             *tp;            /* transaction pointer */
+        enum xfs_dacmp          cmp;            /* comparison result */
+
+        dp = args->dp;
+        tp = args->trans;
+        mp = dp->i_mount;
+        leaf = bp->data;
+        ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC);
+#ifdef __KERNEL__
+        ASSERT(be16_to_cpu(leaf->hdr.count) > 0);
+#endif
+        xfs_dir2_leafn_check(dp, bp);
+        /*
+         * Look up the hash value in the leaf entries.
+         */
+        index = xfs_dir2_leaf_search_hash(args, bp);
+        /*
+         * Do we have a buffer coming in?
+         */
+        if (state->extravalid) {
+                curbp = state->extrablk.bp;
+                curdb = state->extrablk.blkno;
+        }
+        /*
+         * Loop over leaf entries with the right hash value.
+         */
+        for (lep = &leaf->ents[index]; index < be16_to_cpu(leaf->hdr.count) &&
+                                be32_to_cpu(lep->hashval) == args->hashval;
+                                lep++, index++) {
                 /*
-                 * For addname, giving back a free block.
+                 * Skip stale leaf entries.
                  */
-                if (args->addname) {
-                        state->extrablk.blkno = curfdb;
-                        state->extrablk.magic = XFS_DIR2_FREE_MAGIC;
+                if (be32_to_cpu(lep->address) == XFS_DIR2_NULL_DATAPTR)
+                        continue;
+                /*
+                 * Pull the data block number from the entry.
+                 */
+                newdb = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address));
+                /*
+                 * Not adding a new entry, so we really want to find
+                 * the name given to us.
+                 *
+                 * If it's a different data block, go get it.
+                 */
+                if (newdb != curdb) {
+                        /*
+                         * If we had a block before that we aren't saving
+                         * for a CI name, drop it
+                         */
+                        if (curbp && (args->cmpresult == XFS_CMP_DIFFERENT ||
+                                                curdb != state->extrablk.blkno))
+                                xfs_da_brelse(tp, curbp);
+                        /*
+                         * If needing the block that is saved with a CI match,
+                         * use it otherwise read in the new data block.
+                         */
+                        if (args->cmpresult != XFS_CMP_DIFFERENT &&
+                                        newdb == state->extrablk.blkno) {
+                                ASSERT(state->extravalid);
+                                curbp = state->extrablk.bp;
+                        } else {
+                                error = xfs_da_read_buf(tp, dp,
+                                                xfs_dir2_db_to_da(mp, newdb),
+                                                -1, &curbp, XFS_DATA_FORK);
+                                if (error)
+                                        return error;
+                        }
+                        xfs_dir2_data_check(dp, curbp);
+                        curdb = newdb;
                 }
                 /*
-                 * For other callers, giving back a data block.
+                 * Point to the data entry.
                  */
-                else {
+                dep = (xfs_dir2_data_entry_t *)((char *)curbp->data +
+                        xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address)));
+                /*
+                 * Compare the entry and if it's an exact match, return
+                 * EEXIST immediately. If it's the first case-insensitive
+                 * match, store the block & inode number and continue looking.
+                 */
+                cmp = mp->m_dirnameops->compname(args, dep->name, dep->namelen);
+                if (cmp != XFS_CMP_DIFFERENT && cmp != args->cmpresult) {
+                        /* If there is a CI match block, drop it */
+                        if (args->cmpresult != XFS_CMP_DIFFERENT &&
+                                                curdb != state->extrablk.blkno)
+                                xfs_da_brelse(tp, state->extrablk.bp);
+                        args->cmpresult = cmp;
+                        args->inumber = be64_to_cpu(dep->inumber);
+                        *indexp = index;
+                        state->extravalid = 1;
+                        state->extrablk.bp = curbp;
                         state->extrablk.blkno = curdb;
+                        state->extrablk.index = (int)((char *)dep -
+                                                        (char *)curbp->data);
                         state->extrablk.magic = XFS_DIR2_DATA_MAGIC;
+                        if (cmp == XFS_CMP_EXACT)
+                                return XFS_ERROR(EEXIST);
                 }
         }
-        /*
-         * Return the final index, that will be the insertion point.
-         */
+        ASSERT(index == be16_to_cpu(leaf->hdr.count) ||
+                                        (args->op_flags & XFS_DA_OP_OKNOENT));
+        if (curbp) {
+                if (args->cmpresult == XFS_CMP_DIFFERENT) {
+                        /* Giving back last used data block. */
+                        state->extravalid = 1;
+                        state->extrablk.bp = curbp;
+                        state->extrablk.index = -1;
+                        state->extrablk.blkno = curdb;
+                        state->extrablk.magic = XFS_DIR2_DATA_MAGIC;
+                } else {
+                        /* If the curbp is not the CI match block, drop it */
+                        if (state->extrablk.bp != curbp)
+                                xfs_da_brelse(tp, curbp);
+                }
+        } else {
+                state->extravalid = 0;
+        }
         *indexp = index;
-        ASSERT(index == be16_to_cpu(leaf->hdr.count) || args->oknoent);
         return XFS_ERROR(ENOENT);
 }
 
 /*
+ * Look up a leaf entry in a node-format leaf block.
+ * If this is an addname then the extrablk in state is a freespace block,
+ * otherwise it's a data block.
+ */
+int
+xfs_dir2_leafn_lookup_int(
+        xfs_dabuf_t             *bp,            /* leaf buffer */
+        xfs_da_args_t           *args,          /* operation arguments */
+        int                     *indexp,        /* out: leaf entry index */
+        xfs_da_state_t          *state)         /* state to fill in */
+{
+        if (args->op_flags & XFS_DA_OP_ADDNAME)
+                return xfs_dir2_leafn_lookup_for_addname(bp, args, indexp,
+                                                        state);
+        return xfs_dir2_leafn_lookup_for_entry(bp, args, indexp, state);
+}
+
+/*
  * Move count leaf entries from source to destination leaf.
  * Log entries and headers.  Stale entries are preserved.
  */
@@ -823,9 +891,10 @@ xfs_dir2_leafn_rebalance(
          */
         if (!state->inleaf)
                 blk2->index = blk1->index - be16_to_cpu(leaf1->hdr.count);
-        
-        /* 
-         * Finally sanity check just to make sure we are not returning a negative index 
+
+        /*
+         * Finally sanity check just to make sure we are not returning a
+         * negative index
          */
         if(blk2->index < 0) {
                 state->inleaf = 1;
@@ -1332,7 +1401,7 @@ xfs_dir2_node_addname(
                 /*
                  * It worked, fix the hash values up the btree.
                  */
-                if (!args->justcheck)
+                if (!(args->op_flags & XFS_DA_OP_JUSTCHECK))
                         xfs_da_fixhashpath(state, &state->path);
         } else {
                 /*
@@ -1515,7 +1584,8 @@ xfs_dir2_node_addname_int(
                 /*
                  * Not allowed to allocate, return failure.
                  */
-                if (args->justcheck || args->total == 0) {
+                if ((args->op_flags & XFS_DA_OP_JUSTCHECK) ||
+                                                        args->total == 0) {
                         /*
                          * Drop the freespace buffer unless it came from our
                          * caller.
@@ -1661,7 +1731,7 @@ xfs_dir2_node_addname_int(
                 /*
                  * If just checking, we succeeded.
                  */
-                if (args->justcheck) {
+                if (args->op_flags & XFS_DA_OP_JUSTCHECK) {
                         if ((fblk == NULL || fblk->bp == NULL) && fbp != NULL)
                                 xfs_da_buf_done(fbp);
                         return 0;
@@ -1767,6 +1837,14 @@ xfs_dir2_node_lookup(
         error = xfs_da_node_lookup_int(state, &rval);
         if (error)
                 rval = error;
+        else if (rval == ENOENT && args->cmpresult == XFS_CMP_CASE) {
+                /* If a CI match, dup the actual name and return EEXIST */
+                xfs_dir2_data_entry_t   *dep;
+
+                dep = (xfs_dir2_data_entry_t *)((char *)state->extrablk.bp->
+                                                data + state->extrablk.index);
+                rval = xfs_dir_cilookup_result(args, dep->name, dep->namelen);
+        }
         /*
          * Release the btree blocks and leaf block.
          */
@@ -1810,9 +1888,8 @@ xfs_dir2_node_removename(
          * Look up the entry we're deleting, set up the cursor.
          */
         error = xfs_da_node_lookup_int(state, &rval);
-        if (error) {
+        if (error)
                 rval = error;
-        }
         /*
          * Didn't find it, upper layer screwed up.
          */
@@ -1829,9 +1906,8 @@ xfs_dir2_node_removename(
          */
         error = xfs_dir2_leafn_remove(args, blk->bp, blk->index,
                 &state->extrablk, &rval);
-        if (error) {
+        if (error)
                 return error;
-        }
         /*
          * Fix the hash values up the btree.
          */
diff --git a/fs/xfs/xfs_dir2_sf.c b/fs/xfs/xfs_dir2_sf.c
index 919d275a1cef..b46af0013ec9 100644
--- a/fs/xfs/xfs_dir2_sf.c
+++ b/fs/xfs/xfs_dir2_sf.c
@@ -255,7 +255,7 @@ xfs_dir2_block_to_sf(
         xfs_dir2_sf_check(args);
 out:
         xfs_trans_log_inode(args->trans, dp, logflags);
-        kmem_free(block, mp->m_dirblksize);
+        kmem_free(block);
         return error;
 }
 
@@ -332,7 +332,7 @@ xfs_dir2_sf_addname(
                 /*
                  * Just checking or no space reservation, it doesn't fit.
                  */
-                if (args->justcheck || args->total == 0)
+                if ((args->op_flags & XFS_DA_OP_JUSTCHECK) || args->total == 0)
                         return XFS_ERROR(ENOSPC);
                 /*
                  * Convert to block form then add the name.
@@ -345,7 +345,7 @@ xfs_dir2_sf_addname(
         /*
          * Just checking, it fits.
          */
-        if (args->justcheck)
+        if (args->op_flags & XFS_DA_OP_JUSTCHECK)
                 return 0;
         /*
          * Do it the easy way - just add it at the end.
@@ -512,7 +512,7 @@ xfs_dir2_sf_addname_hard(
                 sfep = xfs_dir2_sf_nextentry(sfp, sfep);
                 memcpy(sfep, oldsfep, old_isize - nbytes);
         }
-        kmem_free(buf, old_isize);
+        kmem_free(buf);
         dp->i_d.di_size = new_isize;
         xfs_dir2_sf_check(args);
 }
@@ -812,8 +812,11 @@ xfs_dir2_sf_lookup(
 {
         xfs_inode_t             *dp;            /* incore directory inode */
         int                     i;              /* entry index */
+        int                     error;
         xfs_dir2_sf_entry_t     *sfep;          /* shortform directory entry */
         xfs_dir2_sf_t           *sfp;           /* shortform structure */
+        enum xfs_dacmp          cmp;            /* comparison result */
+        xfs_dir2_sf_entry_t     *ci_sfep;       /* case-insens. entry */
 
         xfs_dir2_trace_args("sf_lookup", args);
         xfs_dir2_sf_check(args);
@@ -836,6 +839,7 @@ xfs_dir2_sf_lookup(
          */
         if (args->namelen == 1 && args->name[0] == '.') {
                 args->inumber = dp->i_ino;
+                args->cmpresult = XFS_CMP_EXACT;
                 return XFS_ERROR(EEXIST);
         }
         /*
@@ -844,28 +848,41 @@ xfs_dir2_sf_lookup(
         if (args->namelen == 2 &&
             args->name[0] == '.' && args->name[1] == '.') {
                 args->inumber = xfs_dir2_sf_get_inumber(sfp, &sfp->hdr.parent);
+                args->cmpresult = XFS_CMP_EXACT;
                 return XFS_ERROR(EEXIST);
         }
         /*
          * Loop over all the entries trying to match ours.
          */
-        for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp);
-             i < sfp->hdr.count;
-             i++, sfep = xfs_dir2_sf_nextentry(sfp, sfep)) {
-                if (sfep->namelen == args->namelen &&
-                    sfep->name[0] == args->name[0] &&
-                    memcmp(args->name, sfep->name, args->namelen) == 0) {
-                        args->inumber =
-                                xfs_dir2_sf_get_inumber(sfp,
-                                        xfs_dir2_sf_inumberp(sfep));
-                        return XFS_ERROR(EEXIST);
+        ci_sfep = NULL;
+        for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); i < sfp->hdr.count;
+                                i++, sfep = xfs_dir2_sf_nextentry(sfp, sfep)) {
+                /*
+                 * Compare name and if it's an exact match, return the inode
+                 * number. If it's the first case-insensitive match, store the
+                 * inode number and continue looking for an exact match.
+                 */
+                cmp = dp->i_mount->m_dirnameops->compname(args, sfep->name,
+                                                                sfep->namelen);
+                if (cmp != XFS_CMP_DIFFERENT && cmp != args->cmpresult) {
+                        args->cmpresult = cmp;
+                        args->inumber = xfs_dir2_sf_get_inumber(sfp,
+                                                xfs_dir2_sf_inumberp(sfep));
+                        if (cmp == XFS_CMP_EXACT)
+                                return XFS_ERROR(EEXIST);
+                        ci_sfep = sfep;
                 }
         }
+        ASSERT(args->op_flags & XFS_DA_OP_OKNOENT);
         /*
-         * Didn't find it.
+         * Here, we can only be doing a lookup (not a rename or replace).
+         * If a case-insensitive match was not found, return ENOENT.
          */
-        ASSERT(args->oknoent);
-        return XFS_ERROR(ENOENT);
+        if (!ci_sfep)
+                return XFS_ERROR(ENOENT);
+        /* otherwise process the CI match as required by the caller */
+        error = xfs_dir_cilookup_result(args, ci_sfep->name, ci_sfep->namelen);
+        return XFS_ERROR(error);
 }
 
 /*
@@ -904,24 +921,21 @@ xfs_dir2_sf_removename(
          * Loop over the old directory entries.
          * Find the one we're deleting.
          */
-        for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp);
-             i < sfp->hdr.count;
-             i++, sfep = xfs_dir2_sf_nextentry(sfp, sfep)) {
-                if (sfep->namelen == args->namelen &&
-                    sfep->name[0] == args->name[0] &&
-                    memcmp(sfep->name, args->name, args->namelen) == 0) {
+        for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); i < sfp->hdr.count;
+                                i++, sfep = xfs_dir2_sf_nextentry(sfp, sfep)) {
+                if (xfs_da_compname(args, sfep->name, sfep->namelen) ==
+                                                                XFS_CMP_EXACT) {
                         ASSERT(xfs_dir2_sf_get_inumber(sfp,
-                                        xfs_dir2_sf_inumberp(sfep)) ==
-                                args->inumber);
+                                                xfs_dir2_sf_inumberp(sfep)) ==
+                                                                args->inumber);
                         break;
                 }
         }
         /*
          * Didn't find it.
          */
-        if (i == sfp->hdr.count) {
+        if (i == sfp->hdr.count)
                 return XFS_ERROR(ENOENT);
-        }
         /*
          * Calculate sizes.
          */
@@ -1042,11 +1056,10 @@ xfs_dir2_sf_replace(
          */
         else {
                 for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp);
-                     i < sfp->hdr.count;
-                     i++, sfep = xfs_dir2_sf_nextentry(sfp, sfep)) {
-                        if (sfep->namelen == args->namelen &&
-                            sfep->name[0] == args->name[0] &&
-                            memcmp(args->name, sfep->name, args->namelen) == 0) {
+                                i < sfp->hdr.count;
+                                i++, sfep = xfs_dir2_sf_nextentry(sfp, sfep)) {
+                        if (xfs_da_compname(args, sfep->name, sfep->namelen) ==
+                                                                XFS_CMP_EXACT) {
 #if XFS_BIG_INUMS || defined(DEBUG)
                                 ino = xfs_dir2_sf_get_inumber(sfp,
                                         xfs_dir2_sf_inumberp(sfep));
@@ -1061,7 +1074,7 @@ xfs_dir2_sf_replace(
                  * Didn't find it.
                  */
                 if (i == sfp->hdr.count) {
-                        ASSERT(args->oknoent);
+                        ASSERT(args->op_flags & XFS_DA_OP_OKNOENT);
 #if XFS_BIG_INUMS
                         if (i8elevated)
                                 xfs_dir2_sf_toino4(args);
@@ -1174,7 +1187,7 @@ xfs_dir2_sf_toino4(
         /*
          * Clean up the inode.
          */
-        kmem_free(buf, oldsize);
+        kmem_free(buf);
         dp->i_d.di_size = newsize;
         xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA);
 }
@@ -1251,7 +1264,7 @@ xfs_dir2_sf_toino8(
         /*
          * Clean up the inode.
          */
-        kmem_free(buf, oldsize);
+        kmem_free(buf);
         dp->i_d.di_size = newsize;
         xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA);
 }
diff --git a/fs/xfs/xfs_dir2_sf.h b/fs/xfs/xfs_dir2_sf.h
index 005629d702d2..deecc9d238f8 100644
--- a/fs/xfs/xfs_dir2_sf.h
+++ b/fs/xfs/xfs_dir2_sf.h
@@ -62,7 +62,7 @@ typedef union {
  * Normalized offset (in a data block) of the entry, really xfs_dir2_data_off_t.
  * Only need 16 bits, this is the byte offset into the single block form.
  */
-typedef struct { __uint8_t i[2]; } xfs_dir2_sf_off_t;
+typedef struct { __uint8_t i[2]; } __arch_pack xfs_dir2_sf_off_t;
 
 /*
  * The parent directory has a dedicated field, and the self-pointer must
@@ -76,14 +76,14 @@ typedef struct xfs_dir2_sf_hdr {
         __uint8_t               count;          /* count of entries */
         __uint8_t               i8count;        /* count of 8-byte inode #s */
         xfs_dir2_inou_t         parent;         /* parent dir inode number */
-} xfs_dir2_sf_hdr_t;
+} __arch_pack xfs_dir2_sf_hdr_t;
 
 typedef struct xfs_dir2_sf_entry {
         __uint8_t               namelen;        /* actual name length */
         xfs_dir2_sf_off_t       offset;         /* saved offset */
         __uint8_t               name[1];        /* name, variable size */
         xfs_dir2_inou_t         inumber;        /* inode number, var. offset */
-} xfs_dir2_sf_entry_t;
+} __arch_pack xfs_dir2_sf_entry_t; 
 
 typedef struct xfs_dir2_sf {
         xfs_dir2_sf_hdr_t       hdr;            /* shortform header */
diff --git a/fs/xfs/xfs_dir2_trace.c b/fs/xfs/xfs_dir2_trace.c
index f3fb2ffd6f5c..6cc7c0c681ac 100644
--- a/fs/xfs/xfs_dir2_trace.c
+++ b/fs/xfs/xfs_dir2_trace.c
@@ -85,7 +85,8 @@ xfs_dir2_trace_args(
                 (void *)((unsigned long)(args->inumber >> 32)),
                 (void *)((unsigned long)(args->inumber & 0xFFFFFFFF)),
                 (void *)args->dp, (void *)args->trans,
-                (void *)(unsigned long)args->justcheck, NULL, NULL);
+                (void *)(unsigned long)(args->op_flags & XFS_DA_OP_JUSTCHECK),
+                NULL, NULL);
 }
 
 void
@@ -100,7 +101,7 @@ xfs_dir2_trace_args_b(
                 (void *)((unsigned long)(args->inumber >> 32)),
                 (void *)((unsigned long)(args->inumber & 0xFFFFFFFF)),
                 (void *)args->dp, (void *)args->trans,
-                (void *)(unsigned long)args->justcheck,
+                (void *)(unsigned long)(args->op_flags & XFS_DA_OP_JUSTCHECK),
                 (void *)(bp ? bp->bps[0] : NULL), NULL);
 }
 
@@ -117,7 +118,7 @@ xfs_dir2_trace_args_bb(
                 (void *)((unsigned long)(args->inumber >> 32)),
                 (void *)((unsigned long)(args->inumber & 0xFFFFFFFF)),
                 (void *)args->dp, (void *)args->trans,
-                (void *)(unsigned long)args->justcheck,
+                (void *)(unsigned long)(args->op_flags & XFS_DA_OP_JUSTCHECK),
                 (void *)(lbp ? lbp->bps[0] : NULL),
                 (void *)(dbp ? dbp->bps[0] : NULL));
 }
@@ -157,8 +158,8 @@ xfs_dir2_trace_args_db(
                 (void *)((unsigned long)(args->inumber >> 32)),
                 (void *)((unsigned long)(args->inumber & 0xFFFFFFFF)),
                 (void *)args->dp, (void *)args->trans,
-                (void *)(unsigned long)args->justcheck, (void *)(long)db,
-                (void *)dbp);
+                (void *)(unsigned long)(args->op_flags & XFS_DA_OP_JUSTCHECK),
+                (void *)(long)db, (void *)dbp);
 }
 
 void
@@ -173,7 +174,7 @@ xfs_dir2_trace_args_i(
                 (void *)((unsigned long)(args->inumber >> 32)),
                 (void *)((unsigned long)(args->inumber & 0xFFFFFFFF)),
                 (void *)args->dp, (void *)args->trans,
-                (void *)(unsigned long)args->justcheck,
+                (void *)(unsigned long)(args->op_flags & XFS_DA_OP_JUSTCHECK),
                 (void *)((unsigned long)(i >> 32)),
                 (void *)((unsigned long)(i & 0xFFFFFFFF)));
 }
@@ -190,7 +191,8 @@ xfs_dir2_trace_args_s(
                 (void *)((unsigned long)(args->inumber >> 32)),
                 (void *)((unsigned long)(args->inumber & 0xFFFFFFFF)),
                 (void *)args->dp, (void *)args->trans,
-                (void *)(unsigned long)args->justcheck, (void *)(long)s, NULL);
+                (void *)(unsigned long)(args->op_flags & XFS_DA_OP_JUSTCHECK),
+                (void *)(long)s, NULL);
 }
 
 void
@@ -208,7 +210,7 @@ xfs_dir2_trace_args_sb(
                 (void *)((unsigned long)(args->inumber >> 32)),
                 (void *)((unsigned long)(args->inumber & 0xFFFFFFFF)),
                 (void *)args->dp, (void *)args->trans,
-                (void *)(unsigned long)args->justcheck, (void *)(long)s,
-                (void *)dbp);
+                (void *)(unsigned long)(args->op_flags & XFS_DA_OP_JUSTCHECK),
+                (void *)(long)s, (void *)dbp);
 }
 #endif  /* XFS_DIR2_TRACE */
diff --git a/fs/xfs/xfs_dmapi.h b/fs/xfs/xfs_dmapi.h
index f71784ab6a60..cdc2d3464a1a 100644
--- a/fs/xfs/xfs_dmapi.h
+++ b/fs/xfs/xfs_dmapi.h
@@ -166,6 +166,6 @@ typedef enum {
 
 #define FILP_DELAY_FLAG(filp) ((filp->f_flags&(O_NDELAY|O_NONBLOCK)) ? \
                         DM_FLAGS_NDELAY : 0)
-#define AT_DELAY_FLAG(f) ((f&ATTR_NONBLOCK) ? DM_FLAGS_NDELAY : 0)
+#define AT_DELAY_FLAG(f) ((f & XFS_ATTR_NONBLOCK) ? DM_FLAGS_NDELAY : 0)
 
 #endif  /* __XFS_DMAPI_H__ */
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index 05e5365d3c31..f66756cfb5e8 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -66,14 +66,6 @@ int	xfs_etest[XFS_NUM_INJECT_ERROR];
 int64_t xfs_etest_fsid[XFS_NUM_INJECT_ERROR];
 char *  xfs_etest_fsname[XFS_NUM_INJECT_ERROR];
 
-void
-xfs_error_test_init(void)
-{
-        memset(xfs_etest, 0, sizeof(xfs_etest));
-        memset(xfs_etest_fsid, 0, sizeof(xfs_etest_fsid));
-        memset(xfs_etest_fsname, 0, sizeof(xfs_etest_fsname));
-}
-
 int
 xfs_error_test(int error_tag, int *fsidp, char *expression,
                int line, char *file, unsigned long randfactor)
@@ -150,8 +142,7 @@ xfs_errortag_clearall(xfs_mount_t *mp, int loud)
                                 xfs_etest[i]);
                         xfs_etest[i] = 0;
                         xfs_etest_fsid[i] = 0LL;
-                        kmem_free(xfs_etest_fsname[i],
-                                  strlen(xfs_etest_fsname[i]) + 1);
+                        kmem_free(xfs_etest_fsname[i]);
                         xfs_etest_fsname[i] = NULL;
                 }
         }
@@ -175,7 +166,7 @@ xfs_fs_vcmn_err(int level, xfs_mount_t *mp, char *fmt, va_list ap)
                 newfmt = kmem_alloc(len, KM_SLEEP);
                 sprintf(newfmt, "Filesystem \"%s\": %s", mp->m_fsname, fmt);
                 icmn_err(level, newfmt, ap);
-                kmem_free(newfmt, len);
+                kmem_free(newfmt);
         } else {
                 icmn_err(level, fmt, ap);
         }
diff --git a/fs/xfs/xfs_error.h b/fs/xfs/xfs_error.h
index 6490d2a9f8e1..d8559d132efa 100644
--- a/fs/xfs/xfs_error.h
+++ b/fs/xfs/xfs_error.h
@@ -127,7 +127,6 @@ extern void xfs_corruption_error(char *tag, int level, struct xfs_mount *mp,
 
 #if (defined(DEBUG) || defined(INDUCE_IO_ERROR))
 extern int xfs_error_test(int, int *, char *, int, char *, unsigned long);
-extern void xfs_error_test_init(void);
 
 #define XFS_NUM_INJECT_ERROR                            10
 
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index 132bd07b9bb8..8aa28f751b2a 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -41,8 +41,7 @@ xfs_efi_item_free(xfs_efi_log_item_t *efip)
         int nexts = efip->efi_format.efi_nextents;
 
         if (nexts > XFS_EFI_MAX_FAST_EXTENTS) {
-                kmem_free(efip, sizeof(xfs_efi_log_item_t) +
-                                (nexts - 1) * sizeof(xfs_extent_t));
+                kmem_free(efip);
         } else {
                 kmem_zone_free(xfs_efi_zone, efip);
         }
@@ -374,8 +373,7 @@ xfs_efd_item_free(xfs_efd_log_item_t *efdp)
         int nexts = efdp->efd_format.efd_nextents;
 
         if (nexts > XFS_EFD_MAX_FAST_EXTENTS) {
-                kmem_free(efdp, sizeof(xfs_efd_log_item_t) +
-                                (nexts - 1) * sizeof(xfs_extent_t));
+                kmem_free(efdp);
         } else {
                 kmem_zone_free(xfs_efd_zone, efdp);
         }
diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c
index 3f3785b10804..c38fd14fca29 100644
--- a/fs/xfs/xfs_filestream.c
+++ b/fs/xfs/xfs_filestream.c
@@ -397,10 +397,12 @@ int
 xfs_filestream_init(void)
 {
         item_zone = kmem_zone_init(sizeof(fstrm_item_t), "fstrm_item");
+        if (!item_zone)
+                return -ENOMEM;
 #ifdef XFS_FILESTREAMS_TRACE
         xfs_filestreams_trace_buf = ktrace_alloc(XFS_FSTRM_KTRACE_SIZE, KM_SLEEP);
 #endif
-        return item_zone ? 0 : -ENOMEM;
+        return 0;
 }
 
 /*
diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/xfs_fs.h
index 3bed6433d050..01c0cc88d3f3 100644
--- a/fs/xfs/xfs_fs.h
+++ b/fs/xfs/xfs_fs.h
@@ -239,6 +239,7 @@ typedef struct xfs_fsop_resblks {
 #define XFS_FSOP_GEOM_FLAGS_LOGV2       0x0100  /* log format version 2 */
 #define XFS_FSOP_GEOM_FLAGS_SECTOR      0x0200  /* sector sizes >1BB    */
 #define XFS_FSOP_GEOM_FLAGS_ATTR2       0x0400  /* inline attributes rework */
+#define XFS_FSOP_GEOM_FLAGS_DIRV2CI     0x1000  /* ASCII only CI names */
 #define XFS_FSOP_GEOM_FLAGS_LAZYSB      0x4000  /* lazy superblock counters */
 
 
@@ -371,6 +372,9 @@ typedef struct xfs_fsop_attrlist_handlereq {
 
 typedef struct xfs_attr_multiop {
         __u32           am_opcode;
+#define ATTR_OP_GET     1       /* return the indicated attr's value */
+#define ATTR_OP_SET     2       /* set/create the indicated attr/value pair */
+#define ATTR_OP_REMOVE  3       /* remove the indicated attr */
         __s32           am_error;
         void            __user *am_attrname;
         void            __user *am_attrvalue;
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 381ebda4f7bc..84583cf73db3 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -95,6 +95,8 @@ xfs_fs_geometry(
                                 XFS_FSOP_GEOM_FLAGS_DIRV2 : 0) |
                         (xfs_sb_version_hassector(&mp->m_sb) ?
                                 XFS_FSOP_GEOM_FLAGS_SECTOR : 0) |
+                        (xfs_sb_version_hasasciici(&mp->m_sb) ?
+                                XFS_FSOP_GEOM_FLAGS_DIRV2CI : 0) |
                         (xfs_sb_version_haslazysbcount(&mp->m_sb) ?
                                 XFS_FSOP_GEOM_FLAGS_LAZYSB : 0) |
                         (xfs_sb_version_hasattr2(&mp->m_sb) ?
@@ -625,7 +627,7 @@ xfs_fs_goingdown(
                         xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT);
                         thaw_bdev(sb->s_bdev, sb);
                 }
-        
+
                 break;
         }
         case XFS_FSOP_GOING_FLAGS_LOGFLUSH:
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index e569bf5d6cf0..bedc66163176 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1763,67 +1763,6 @@ xfs_itruncate_finish(
         return 0;
 }
 
-
-/*
- * xfs_igrow_start
- *
- * Do the first part of growing a file: zero any data in the last
- * block that is beyond the old EOF.  We need to do this before
- * the inode is joined to the transaction to modify the i_size.
- * That way we can drop the inode lock and call into the buffer
- * cache to get the buffer mapping the EOF.
- */
-int
-xfs_igrow_start(
-        xfs_inode_t     *ip,
-        xfs_fsize_t     new_size,
-        cred_t          *credp)
-{
-        ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
-        ASSERT(new_size > ip->i_size);
-
-        /*
-         * Zero any pages that may have been created by
-         * xfs_write_file() beyond the end of the file
-         * and any blocks between the old and new file sizes.
-         */
-        return xfs_zero_eof(ip, new_size, ip->i_size);
-}
-
-/*
- * xfs_igrow_finish
- *
- * This routine is called to extend the size of a file.
- * The inode must have both the iolock and the ilock locked
- * for update and it must be a part of the current transaction.
- * The xfs_igrow_start() function must have been called previously.
- * If the change_flag is not zero, the inode change timestamp will
- * be updated.
- */
-void
-xfs_igrow_finish(
-        xfs_trans_t     *tp,
-        xfs_inode_t     *ip,
-        xfs_fsize_t     new_size,
-        int             change_flag)
-{
-        ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
-        ASSERT(ip->i_transp == tp);
-        ASSERT(new_size > ip->i_size);
-
-        /*
-         * Update the file size.  Update the inode change timestamp
-         * if change_flag set.
-         */
-        ip->i_d.di_size = new_size;
-        ip->i_size = new_size;
-        if (change_flag)
-                xfs_ichgtime(ip, XFS_ICHGTIME_CHG);
-        xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-
-}
-
-
 /*
  * This is called when the inode's link count goes to 0.
  * We place the on-disk inode on a list in the AGI.  It
@@ -2258,7 +2197,7 @@ xfs_ifree_cluster(
                 xfs_trans_binval(tp, bp);
         }
 
-        kmem_free(ip_found, ninodes * sizeof(xfs_inode_t *));
+        kmem_free(ip_found);
         xfs_put_perag(mp, pag);
 }
 
@@ -2470,7 +2409,7 @@ xfs_iroot_realloc(
                                                      (int)new_size);
                 memcpy(np, op, new_max * (uint)sizeof(xfs_dfsbno_t));
         }
-        kmem_free(ifp->if_broot, ifp->if_broot_bytes);
+        kmem_free(ifp->if_broot);
         ifp->if_broot = new_broot;
         ifp->if_broot_bytes = (int)new_size;
         ASSERT(ifp->if_broot_bytes <=
@@ -2514,7 +2453,7 @@ xfs_idata_realloc(
 
         if (new_size == 0) {
                 if (ifp->if_u1.if_data != ifp->if_u2.if_inline_data) {
-                        kmem_free(ifp->if_u1.if_data, ifp->if_real_bytes);
+                        kmem_free(ifp->if_u1.if_data);
                 }
                 ifp->if_u1.if_data = NULL;
                 real_size = 0;
@@ -2529,7 +2468,7 @@ xfs_idata_realloc(
                         ASSERT(ifp->if_real_bytes != 0);
                         memcpy(ifp->if_u2.if_inline_data, ifp->if_u1.if_data,
                               new_size);
-                        kmem_free(ifp->if_u1.if_data, ifp->if_real_bytes);
+                        kmem_free(ifp->if_u1.if_data);
                         ifp->if_u1.if_data = ifp->if_u2.if_inline_data;
                 }
                 real_size = 0;
@@ -2636,7 +2575,7 @@ xfs_idestroy_fork(
 
         ifp = XFS_IFORK_PTR(ip, whichfork);
         if (ifp->if_broot != NULL) {
-                kmem_free(ifp->if_broot, ifp->if_broot_bytes);
+                kmem_free(ifp->if_broot);
                 ifp->if_broot = NULL;
         }
 
@@ -2650,7 +2589,7 @@ xfs_idestroy_fork(
                 if ((ifp->if_u1.if_data != ifp->if_u2.if_inline_data) &&
                     (ifp->if_u1.if_data != NULL)) {
                         ASSERT(ifp->if_real_bytes != 0);
-                        kmem_free(ifp->if_u1.if_data, ifp->if_real_bytes);
+                        kmem_free(ifp->if_u1.if_data);
                         ifp->if_u1.if_data = NULL;
                         ifp->if_real_bytes = 0;
                 }
@@ -3058,7 +2997,7 @@ xfs_iflush_cluster(
 
 out_free:
         read_unlock(&pag->pag_ici_lock);
-        kmem_free(ilist, ilist_size);
+        kmem_free(ilist);
         return 0;
 
 
@@ -3102,7 +3041,7 @@ cluster_corrupt_out:
          * Unlocks the flush lock
          */
         xfs_iflush_abort(iq);
-        kmem_free(ilist, ilist_size);
+        kmem_free(ilist);
         return XFS_ERROR(EFSCORRUPTED);
 }
 
@@ -3143,8 +3082,6 @@ xfs_iflush(
          * flush lock and do nothing.
          */
         if (xfs_inode_clean(ip)) {
-                ASSERT((iip != NULL) ?
-                         !(iip->ili_item.li_flags & XFS_LI_IN_AIL) : 1);
                 xfs_ifunlock(ip);
                 return 0;
         }
@@ -3836,7 +3773,7 @@ xfs_iext_add_indirect_multi(
                         erp = xfs_iext_irec_new(ifp, erp_idx);
                 }
                 memmove(&erp->er_extbuf[i], nex2_ep, byte_diff);
-                kmem_free(nex2_ep, byte_diff);
+                kmem_free(nex2_ep);
                 erp->er_extcount += nex2;
                 xfs_iext_irec_update_extoffs(ifp, erp_idx + 1, nex2);
         }
@@ -4112,7 +4049,7 @@ xfs_iext_direct_to_inline(
          */
         memcpy(ifp->if_u2.if_inline_ext, ifp->if_u1.if_extents,
                 nextents * sizeof(xfs_bmbt_rec_t));
-        kmem_free(ifp->if_u1.if_extents, ifp->if_real_bytes);
+        kmem_free(ifp->if_u1.if_extents);
         ifp->if_u1.if_extents = ifp->if_u2.if_inline_ext;
         ifp->if_real_bytes = 0;
 }
@@ -4186,7 +4123,7 @@ xfs_iext_indirect_to_direct(
         ASSERT(ifp->if_real_bytes == XFS_IEXT_BUFSZ);
 
         ep = ifp->if_u1.if_ext_irec->er_extbuf;
-        kmem_free(ifp->if_u1.if_ext_irec, sizeof(xfs_ext_irec_t));
+        kmem_free(ifp->if_u1.if_ext_irec);
         ifp->if_flags &= ~XFS_IFEXTIREC;
         ifp->if_u1.if_extents = ep;
         ifp->if_bytes = size;
@@ -4212,7 +4149,7 @@ xfs_iext_destroy(
                 }
                 ifp->if_flags &= ~XFS_IFEXTIREC;
         } else if (ifp->if_real_bytes) {
-                kmem_free(ifp->if_u1.if_extents, ifp->if_real_bytes);
+                kmem_free(ifp->if_u1.if_extents);
         } else if (ifp->if_bytes) {
                 memset(ifp->if_u2.if_inline_ext, 0, XFS_INLINE_EXTS *
                         sizeof(xfs_bmbt_rec_t));
@@ -4483,7 +4420,7 @@ xfs_iext_irec_remove(
         if (erp->er_extbuf) {
                 xfs_iext_irec_update_extoffs(ifp, erp_idx + 1,
                         -erp->er_extcount);
-                kmem_free(erp->er_extbuf, XFS_IEXT_BUFSZ);
+                kmem_free(erp->er_extbuf);
         }
         /* Compact extent records */
         erp = ifp->if_u1.if_ext_irec;
@@ -4501,8 +4438,7 @@ xfs_iext_irec_remove(
                 xfs_iext_realloc_indirect(ifp,
                         nlists * sizeof(xfs_ext_irec_t));
         } else {
-                kmem_free(ifp->if_u1.if_ext_irec,
-                        sizeof(xfs_ext_irec_t));
+                kmem_free(ifp->if_u1.if_ext_irec);
         }
         ifp->if_real_bytes = nlists * XFS_IEXT_BUFSZ;
 }
@@ -4571,7 +4507,7 @@ xfs_iext_irec_compact_pages(
                          * so er_extoffs don't get modified in
                          * xfs_iext_irec_remove.
                          */
-                        kmem_free(erp_next->er_extbuf, XFS_IEXT_BUFSZ);
+                        kmem_free(erp_next->er_extbuf);
                         erp_next->er_extbuf = NULL;
                         xfs_iext_irec_remove(ifp, erp_idx + 1);
                         nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
@@ -4596,40 +4532,63 @@ xfs_iext_irec_compact_full(
         int             nlists;                 /* number of irec's (ex lists) */
 
         ASSERT(ifp->if_flags & XFS_IFEXTIREC);
+
         nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
         erp = ifp->if_u1.if_ext_irec;
         ep = &erp->er_extbuf[erp->er_extcount];
         erp_next = erp + 1;
         ep_next = erp_next->er_extbuf;
+
         while (erp_idx < nlists - 1) {
+                /*
+                 * Check how many extent records are available in this irec.
+                 * If there is none skip the whole exercise.
+                 */
                 ext_avail = XFS_LINEAR_EXTS - erp->er_extcount;
-                ext_diff = MIN(ext_avail, erp_next->er_extcount);
-                memcpy(ep, ep_next, ext_diff * sizeof(xfs_bmbt_rec_t));
-                erp->er_extcount += ext_diff;
-                erp_next->er_extcount -= ext_diff;
-                /* Remove next page */
-                if (erp_next->er_extcount == 0) {
+                if (ext_avail) {
+
                         /*
-                         * Free page before removing extent record
-                         * so er_extoffs don't get modified in
-                         * xfs_iext_irec_remove.
+                         * Copy over as many as possible extent records into
+                         * the previous page.
                          */
-                        kmem_free(erp_next->er_extbuf,
-                                erp_next->er_extcount * sizeof(xfs_bmbt_rec_t));
-                        erp_next->er_extbuf = NULL;
-                        xfs_iext_irec_remove(ifp, erp_idx + 1);
-                        erp = &ifp->if_u1.if_ext_irec[erp_idx];
-                        nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
-                /* Update next page */
-                } else {
-                        /* Move rest of page up to become next new page */
-                        memmove(erp_next->er_extbuf, ep_next,
-                                erp_next->er_extcount * sizeof(xfs_bmbt_rec_t));
-                        ep_next = erp_next->er_extbuf;
-                        memset(&ep_next[erp_next->er_extcount], 0,
-                                (XFS_LINEAR_EXTS - erp_next->er_extcount) *
-                                sizeof(xfs_bmbt_rec_t));
+                        ext_diff = MIN(ext_avail, erp_next->er_extcount);
+                        memcpy(ep, ep_next, ext_diff * sizeof(xfs_bmbt_rec_t));
+                        erp->er_extcount += ext_diff;
+                        erp_next->er_extcount -= ext_diff;
+
+                        /*
+                         * If the next irec is empty now we can simply
+                         * remove it.
+                         */
+                        if (erp_next->er_extcount == 0) {
+                                /*
+                                 * Free page before removing extent record
+                                 * so er_extoffs don't get modified in
+                                 * xfs_iext_irec_remove.
+                                 */
+                                kmem_free(erp_next->er_extbuf);
+                                erp_next->er_extbuf = NULL;
+                                xfs_iext_irec_remove(ifp, erp_idx + 1);
+                                erp = &ifp->if_u1.if_ext_irec[erp_idx];
+                                nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
+
+                        /*
+                         * If the next irec is not empty move up the content
+                         * that has not been copied to the previous page to
+                         * the beggining of this one.
+                         */
+                        } else {
+                                memmove(erp_next->er_extbuf, &ep_next[ext_diff],
+                                        erp_next->er_extcount *
+                                        sizeof(xfs_bmbt_rec_t));
+                                ep_next = erp_next->er_extbuf;
+                                memset(&ep_next[erp_next->er_extcount], 0,
+                                        (XFS_LINEAR_EXTS -
+                                                erp_next->er_extcount) *
+                                        sizeof(xfs_bmbt_rec_t));
+                        }
                 }
+
                 if (erp->er_extcount == XFS_LINEAR_EXTS) {
                         erp_idx++;
                         if (erp_idx < nlists)
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 0a999fee4f03..17a04b6321ed 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -507,9 +507,6 @@ int		xfs_itruncate_start(xfs_inode_t *, uint, xfs_fsize_t);
 int             xfs_itruncate_finish(struct xfs_trans **, xfs_inode_t *,
                                      xfs_fsize_t, int, int);
 int             xfs_iunlink(struct xfs_trans *, xfs_inode_t *);
-int             xfs_igrow_start(xfs_inode_t *, xfs_fsize_t, struct cred *);
-void            xfs_igrow_finish(struct xfs_trans *, xfs_inode_t *,
-                                 xfs_fsize_t, int);
 
 void            xfs_idestroy_fork(xfs_inode_t *, int);
 void            xfs_idestroy(xfs_inode_t *);
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 167b33f15772..0eee08a32c26 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -686,7 +686,7 @@ xfs_inode_item_unlock(
                 ASSERT(ip->i_d.di_nextents > 0);
                 ASSERT(iip->ili_format.ilf_fields & XFS_ILOG_DEXT);
                 ASSERT(ip->i_df.if_bytes > 0);
-                kmem_free(iip->ili_extents_buf, ip->i_df.if_bytes);
+                kmem_free(iip->ili_extents_buf);
                 iip->ili_extents_buf = NULL;
         }
         if (iip->ili_aextents_buf != NULL) {
@@ -694,7 +694,7 @@ xfs_inode_item_unlock(
                 ASSERT(ip->i_d.di_anextents > 0);
                 ASSERT(iip->ili_format.ilf_fields & XFS_ILOG_AEXT);
                 ASSERT(ip->i_afp->if_bytes > 0);
-                kmem_free(iip->ili_aextents_buf, ip->i_afp->if_bytes);
+                kmem_free(iip->ili_aextents_buf);
                 iip->ili_aextents_buf = NULL;
         }
 
@@ -957,8 +957,7 @@ xfs_inode_item_destroy(
 {
 #ifdef XFS_TRANS_DEBUG
         if (ip->i_itemp->ili_root_size != 0) {
-                kmem_free(ip->i_itemp->ili_orig_root,
-                          ip->i_itemp->ili_root_size);
+                kmem_free(ip->i_itemp->ili_orig_root);
         }
 #endif
         kmem_zone_free(xfs_ili_zone, ip->i_itemp);
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 7edcde691d1a..67f22b2b44b3 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -889,6 +889,16 @@ xfs_iomap_write_unwritten(
         count_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
         count_fsb = (xfs_filblks_t)(count_fsb - offset_fsb);
 
+        /*
+         * Reserve enough blocks in this transaction for two complete extent
+         * btree splits.  We may be converting the middle part of an unwritten
+         * extent and in this case we will insert two new extents in the btree
+         * each of which could cause a full split.
+         *
+         * This reservation amount will be used in the first call to
+         * xfs_bmbt_split() to select an AG with enough space to satisfy the
+         * rest of the operation.
+         */
         resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0) << 1;
 
         do {
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 419de15aeb43..9a3ef9dcaeb9 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -257,7 +257,7 @@ xfs_bulkstat_one(
                 *ubused = error;
 
  out_free:
-        kmem_free(buf, sizeof(*buf));
+        kmem_free(buf);
         return error;
 }
 
@@ -708,7 +708,7 @@ xfs_bulkstat(
         /*
          * Done, we're either out of filesystem or space to put the data.
          */
-        kmem_free(irbuf, irbsize);
+        kmem_free(irbuf);
         *ubcountp = ubelem;
         /*
          * Found some inodes, return them now and return the error next time.
@@ -914,7 +914,7 @@ xfs_inumbers(
                 }
                 *lastino = XFS_AGINO_TO_INO(mp, agno, agino);
         }
-        kmem_free(buffer, bcount * sizeof(*buffer));
+        kmem_free(buffer);
         if (cur)
                 xfs_btree_del_cursor(cur, (error ? XFS_BTREE_ERROR :
                                            XFS_BTREE_NOERROR));
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index ad3d26ddfe31..91b00a5686cd 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -226,20 +226,24 @@ xlog_grant_sub_space(struct log *log, int bytes)
 static void
 xlog_grant_add_space_write(struct log *log, int bytes)
 {
-        log->l_grant_write_bytes += bytes;
-        if (log->l_grant_write_bytes > log->l_logsize) {
-                log->l_grant_write_bytes -= log->l_logsize;
+        int tmp = log->l_logsize - log->l_grant_write_bytes;
+        if (tmp > bytes)
+                log->l_grant_write_bytes += bytes;
+        else {
                 log->l_grant_write_cycle++;
+                log->l_grant_write_bytes = bytes - tmp;
         }
 }
 
 static void
 xlog_grant_add_space_reserve(struct log *log, int bytes)
 {
-        log->l_grant_reserve_bytes += bytes;
-        if (log->l_grant_reserve_bytes > log->l_logsize) {
-                log->l_grant_reserve_bytes -= log->l_logsize;
+        int tmp = log->l_logsize - log->l_grant_reserve_bytes;
+        if (tmp > bytes)
+                log->l_grant_reserve_bytes += bytes;
+        else {
                 log->l_grant_reserve_cycle++;
+                log->l_grant_reserve_bytes = bytes - tmp;
         }
 }
 
@@ -1228,7 +1232,7 @@ xlog_alloc_log(xfs_mount_t	*mp,
 
         spin_lock_init(&log->l_icloglock);
         spin_lock_init(&log->l_grant_lock);
-        initnsema(&log->l_flushsema, 0, "ic-flush");
+        sv_init(&log->l_flush_wait, 0, "flush_wait");
 
         /* log record size must be multiple of BBSIZE; see xlog_rec_header_t */
         ASSERT((XFS_BUF_SIZE(bp) & BBMASK) == 0);
@@ -1570,10 +1574,9 @@ xlog_dealloc_log(xlog_t *log)
                 }
 #endif
                 next_iclog = iclog->ic_next;
-                kmem_free(iclog, sizeof(xlog_in_core_t));
+                kmem_free(iclog);
                 iclog = next_iclog;
         }
-        freesema(&log->l_flushsema);
         spinlock_destroy(&log->l_icloglock);
         spinlock_destroy(&log->l_grant_lock);
 
@@ -1587,7 +1590,7 @@ xlog_dealloc_log(xlog_t *log)
         }
 #endif
         log->l_mp->m_log = NULL;
-        kmem_free(log, sizeof(xlog_t));
+        kmem_free(log);
 }       /* xlog_dealloc_log */
 
 /*
@@ -2097,6 +2100,7 @@ xlog_state_do_callback(
         int                funcdidcallbacks; /* flag: function did callbacks */
         int                repeats;     /* for issuing console warnings if
                                          * looping too many times */
+        int                wake = 0;
 
         spin_lock(&log->l_icloglock);
         first_iclog = iclog = log->l_iclog;
@@ -2278,15 +2282,13 @@ xlog_state_do_callback(
         }
 #endif
 
-        flushcnt = 0;
-        if (log->l_iclog->ic_state & (XLOG_STATE_ACTIVE|XLOG_STATE_IOERROR)) {
-                flushcnt = log->l_flushcnt;
-                log->l_flushcnt = 0;
-        }
+        if (log->l_iclog->ic_state & (XLOG_STATE_ACTIVE|XLOG_STATE_IOERROR))
+                wake = 1;
         spin_unlock(&log->l_icloglock);
-        while (flushcnt--)
-                vsema(&log->l_flushsema);
-}       /* xlog_state_do_callback */
+
+        if (wake)
+                sv_broadcast(&log->l_flush_wait);
+}
 
 
 /*
@@ -2384,16 +2386,15 @@ restart:
         }
 
         iclog = log->l_iclog;
-        if (! (iclog->ic_state == XLOG_STATE_ACTIVE)) {
-                log->l_flushcnt++;
-                spin_unlock(&log->l_icloglock);
+        if (iclog->ic_state != XLOG_STATE_ACTIVE) {
                 xlog_trace_iclog(iclog, XLOG_TRACE_SLEEP_FLUSH);
                 XFS_STATS_INC(xs_log_noiclogs);
-                /* Ensure that log writes happen */
-                psema(&log->l_flushsema, PINOD);
+
+                /* Wait for log writes to have flushed */
+                sv_wait(&log->l_flush_wait, 0, &log->l_icloglock, 0);
                 goto restart;
         }
-        ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE);
+
         head = &iclog->ic_header;
 
         atomic_inc(&iclog->ic_refcnt);  /* prevents sync */
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index 8952a392b5f3..6245913196b4 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -423,10 +423,8 @@ typedef struct log {
         int                     l_logBBsize;    /* size of log in BB chunks */
 
         /* The following block of fields are changed while holding icloglock */
-        sema_t                  l_flushsema ____cacheline_aligned_in_smp;
-                                                /* iclog flushing semaphore */
-        int                     l_flushcnt;     /* # of procs waiting on this
-                                                 * sema */
+        sv_t                    l_flush_wait ____cacheline_aligned_in_smp;
+                                                /* waiting for iclog flush */
         int                     l_covered_state;/* state of "covering disk
                                                  * log entries" */
         xlog_in_core_t          *l_iclog;       /* head log queue       */
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index e65ab4af0955..9eb722ec744e 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1715,8 +1715,7 @@ xlog_check_buffer_cancelled(
                                         } else {
                                                 prevp->bc_next = bcp->bc_next;
                                         }
-                                        kmem_free(bcp,
-                                                  sizeof(xfs_buf_cancel_t));
+                                        kmem_free(bcp);
                                 }
                         }
                         return 1;
@@ -2519,7 +2518,7 @@ write_inode_buffer:
 
 error:
         if (need_free)
-                kmem_free(in_f, sizeof(*in_f));
+                kmem_free(in_f);
         return XFS_ERROR(error);
 }
 
@@ -2830,16 +2829,14 @@ xlog_recover_free_trans(
                 item = item->ri_next;
                  /* Free the regions in the item. */
                 for (i = 0; i < free_item->ri_cnt; i++) {
-                        kmem_free(free_item->ri_buf[i].i_addr,
-                                  free_item->ri_buf[i].i_len);
+                        kmem_free(free_item->ri_buf[i].i_addr);
                 }
                 /* Free the item itself */
-                kmem_free(free_item->ri_buf,
-                          (free_item->ri_total * sizeof(xfs_log_iovec_t)));
-                kmem_free(free_item, sizeof(xlog_recover_item_t));
+                kmem_free(free_item->ri_buf);
+                kmem_free(free_item);
         } while (first_item != item);
         /* Free the transaction recover structure */
-        kmem_free(trans, sizeof(xlog_recover_t));
+        kmem_free(trans);
 }
 
 STATIC int
@@ -3786,8 +3783,7 @@ xlog_do_log_recovery(
         error = xlog_do_recovery_pass(log, head_blk, tail_blk,
                                       XLOG_RECOVER_PASS1);
         if (error != 0) {
-                kmem_free(log->l_buf_cancel_table,
-                          XLOG_BC_TABLE_SIZE * sizeof(xfs_buf_cancel_t*));
+                kmem_free(log->l_buf_cancel_table);
                 log->l_buf_cancel_table = NULL;
                 return error;
         }
@@ -3806,8 +3802,7 @@ xlog_do_log_recovery(
         }
 #endif  /* DEBUG */
 
-        kmem_free(log->l_buf_cancel_table,
-                  XLOG_BC_TABLE_SIZE * sizeof(xfs_buf_cancel_t*));
+        kmem_free(log->l_buf_cancel_table);
         log->l_buf_cancel_table = NULL;
 
         return error;
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index da3988453b71..6c5d1325e7f6 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -47,12 +47,10 @@
 
 STATIC int      xfs_mount_log_sb(xfs_mount_t *, __int64_t);
 STATIC int      xfs_uuid_mount(xfs_mount_t *);
-STATIC void     xfs_uuid_unmount(xfs_mount_t *mp);
 STATIC void     xfs_unmountfs_wait(xfs_mount_t *);
 
 
 #ifdef HAVE_PERCPU_SB
-STATIC void     xfs_icsb_destroy_counters(xfs_mount_t *);
 STATIC void     xfs_icsb_balance_counter(xfs_mount_t *, xfs_sb_field_t,
                                                 int);
 STATIC void     xfs_icsb_balance_counter_locked(xfs_mount_t *, xfs_sb_field_t,
@@ -63,7 +61,6 @@ STATIC void	xfs_icsb_disable_counter(xfs_mount_t *, xfs_sb_field_t);
 
 #else
 
-#define xfs_icsb_destroy_counters(mp)                   do { } while (0)
 #define xfs_icsb_balance_counter(mp, a, b)              do { } while (0)
 #define xfs_icsb_balance_counter_locked(mp, a, b)       do { } while (0)
 #define xfs_icsb_modify_counters(mp, a, b, c)           do { } while (0)
@@ -126,33 +123,11 @@ static const struct {
 };
 
 /*
- * Return a pointer to an initialized xfs_mount structure.
- */
-xfs_mount_t *
-xfs_mount_init(void)
-{
-        xfs_mount_t *mp;
-
-        mp = kmem_zalloc(sizeof(xfs_mount_t), KM_SLEEP);
-
-        if (xfs_icsb_init_counters(mp)) {
-                mp->m_flags |= XFS_MOUNT_NO_PERCPU_SB;
-        }
-
-        spin_lock_init(&mp->m_sb_lock);
-        mutex_init(&mp->m_ilock);
-        mutex_init(&mp->m_growlock);
-        atomic_set(&mp->m_active_trans, 0);
-
-        return mp;
-}
-
-/*
  * Free up the resources associated with a mount structure.  Assume that
  * the structure was initially zeroed, so we can tell which fields got
  * initialized.
  */
-void
+STATIC void
 xfs_mount_free(
         xfs_mount_t     *mp)
 {
@@ -161,11 +136,8 @@ xfs_mount_free(
 
                 for (agno = 0; agno < mp->m_maxagi; agno++)
                         if (mp->m_perag[agno].pagb_list)
-                                kmem_free(mp->m_perag[agno].pagb_list,
-                                                sizeof(xfs_perag_busy_t) *
-                                                        XFS_PAGB_NUM_SLOTS);
-                kmem_free(mp->m_perag,
-                          sizeof(xfs_perag_t) * mp->m_sb.sb_agcount);
+                                kmem_free(mp->m_perag[agno].pagb_list);
+                kmem_free(mp->m_perag);
         }
 
         spinlock_destroy(&mp->m_ail_lock);
@@ -176,13 +148,11 @@ xfs_mount_free(
                 XFS_QM_DONE(mp);
 
         if (mp->m_fsname != NULL)
-                kmem_free(mp->m_fsname, mp->m_fsname_len);
+                kmem_free(mp->m_fsname);
         if (mp->m_rtname != NULL)
-                kmem_free(mp->m_rtname, strlen(mp->m_rtname) + 1);
+                kmem_free(mp->m_rtname);
         if (mp->m_logname != NULL)
-                kmem_free(mp->m_logname, strlen(mp->m_logname) + 1);
-
-        xfs_icsb_destroy_counters(mp);
+                kmem_free(mp->m_logname);
 }
 
 /*
@@ -288,6 +258,19 @@ xfs_mount_validate_sb(
                 return XFS_ERROR(EFSCORRUPTED);
         }
 
+        /*
+         * 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);
+                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,
@@ -309,19 +292,6 @@ xfs_mount_validate_sb(
                 return XFS_ERROR(ENOSYS);
         }
 
-        /*
-         * 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);
-                return XFS_ERROR(ENOSYS);
-        }
-
         return 0;
 }
 
@@ -994,9 +964,19 @@ xfs_mountfs(
                  * Re-check for ATTR2 in case it was found in bad_features2
                  * slot.
                  */
-                if (xfs_sb_version_hasattr2(&mp->m_sb))
+                if (xfs_sb_version_hasattr2(&mp->m_sb) &&
+                   !(mp->m_flags & XFS_MOUNT_NOATTR2))
                         mp->m_flags |= XFS_MOUNT_ATTR2;
+        }
+
+        if (xfs_sb_version_hasattr2(&mp->m_sb) &&
+           (mp->m_flags & XFS_MOUNT_NOATTR2)) {
+                xfs_sb_version_removeattr2(&mp->m_sb);
+                update_flags |= XFS_SB_FEATURES2;
 
+                /* update sb_versionnum for the clearing of the morebits */
+                if (!sbp->sb_features2)
+                        update_flags |= XFS_SB_VERSIONNUM;
         }
 
         /*
@@ -1255,15 +1235,13 @@ xfs_mountfs(
  error2:
         for (agno = 0; agno < sbp->sb_agcount; agno++)
                 if (mp->m_perag[agno].pagb_list)
-                        kmem_free(mp->m_perag[agno].pagb_list,
-                          sizeof(xfs_perag_busy_t) * XFS_PAGB_NUM_SLOTS);
-        kmem_free(mp->m_perag, sbp->sb_agcount * sizeof(xfs_perag_t));
+                        kmem_free(mp->m_perag[agno].pagb_list);
+        kmem_free(mp->m_perag);
         mp->m_perag = NULL;
         /* FALLTHROUGH */
  error1:
         if (uuid_mounted)
-                xfs_uuid_unmount(mp);
-        xfs_freesb(mp);
+                uuid_table_remove(&mp->m_sb.sb_uuid);
         return error;
 }
 
@@ -1274,7 +1252,7 @@ xfs_mountfs(
  * log and makes sure that incore structures are freed.
  */
 int
-xfs_unmountfs(xfs_mount_t *mp, struct cred *cr)
+xfs_unmountfs(xfs_mount_t *mp)
 {
         __uint64_t      resblks;
         int             error = 0;
@@ -1341,9 +1319,8 @@ xfs_unmountfs(xfs_mount_t *mp, struct cred *cr)
          */
         ASSERT(mp->m_inodes == NULL);
 
-        xfs_unmountfs_close(mp, cr);
         if ((mp->m_flags & XFS_MOUNT_NOUUID) == 0)
-                xfs_uuid_unmount(mp);
+                uuid_table_remove(&mp->m_sb.sb_uuid);
 
 #if defined(DEBUG) || defined(INDUCE_IO_ERROR)
         xfs_errortag_clearall(mp, 0);
@@ -1352,16 +1329,6 @@ xfs_unmountfs(xfs_mount_t *mp, struct cred *cr)
         return 0;
 }
 
-void
-xfs_unmountfs_close(xfs_mount_t *mp, struct cred *cr)
-{
-        if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
-                xfs_free_buftarg(mp->m_logdev_targp, 1);
-        if (mp->m_rtdev_targp)
-                xfs_free_buftarg(mp->m_rtdev_targp, 1);
-        xfs_free_buftarg(mp->m_ddev_targp, 0);
-}
-
 STATIC void
 xfs_unmountfs_wait(xfs_mount_t *mp)
 {
@@ -1905,16 +1872,6 @@ xfs_uuid_mount(
 }
 
 /*
- * Remove filesystem from the UUID table.
- */
-STATIC void
-xfs_uuid_unmount(
-        xfs_mount_t     *mp)
-{
-        uuid_table_remove(&mp->m_sb.sb_uuid);
-}
-
-/*
  * Used to log changes to the superblock unit and width fields which could
  * be altered by the mount options, as well as any potential sb_features2
  * fixup. Only the first superblock is updated.
@@ -1928,7 +1885,8 @@ xfs_mount_log_sb(
         int             error;
 
         ASSERT(fields & (XFS_SB_UNIT | XFS_SB_WIDTH | XFS_SB_UUID |
-                         XFS_SB_FEATURES2 | XFS_SB_BAD_FEATURES2));
+                         XFS_SB_FEATURES2 | XFS_SB_BAD_FEATURES2 |
+                         XFS_SB_VERSIONNUM));
 
         tp = xfs_trans_alloc(mp, XFS_TRANS_SB_UNIT);
         error = xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0,
@@ -2109,7 +2067,7 @@ xfs_icsb_reinit_counters(
         xfs_icsb_unlock(mp);
 }
 
-STATIC void
+void
 xfs_icsb_destroy_counters(
         xfs_mount_t     *mp)
 {
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 63e0693a358a..5269bd6e3df0 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -61,6 +61,7 @@ struct xfs_bmap_free;
 struct xfs_extdelta;
 struct xfs_swapext;
 struct xfs_mru_cache;
+struct xfs_nameops;
 
 /*
  * Prototypes and functions for the Data Migration subsystem.
@@ -210,12 +211,14 @@ typedef struct xfs_icsb_cnts {
 
 extern int      xfs_icsb_init_counters(struct xfs_mount *);
 extern void     xfs_icsb_reinit_counters(struct xfs_mount *);
+extern void     xfs_icsb_destroy_counters(struct xfs_mount *);
 extern void     xfs_icsb_sync_counters(struct xfs_mount *, int);
 extern void     xfs_icsb_sync_counters_locked(struct xfs_mount *, int);
 
 #else
-#define xfs_icsb_init_counters(mp)      (0)
-#define xfs_icsb_reinit_counters(mp)    do { } while (0)
+#define xfs_icsb_init_counters(mp)              (0)
+#define xfs_icsb_destroy_counters(mp)           do { } while (0)
+#define xfs_icsb_reinit_counters(mp)            do { } while (0)
 #define xfs_icsb_sync_counters(mp, flags)       do { } while (0)
 #define xfs_icsb_sync_counters_locked(mp, flags) do { } while (0)
 #endif
@@ -313,6 +316,7 @@ typedef struct xfs_mount {
         __uint8_t               m_inode_quiesce;/* call quiesce on new inodes.
                                                    field governed by m_ilock */
         __uint8_t               m_sectbb_log;   /* sectlog - BBSHIFT */
+        const struct xfs_nameops *m_dirnameops; /* vector of dir name ops */
         int                     m_dirblksize;   /* directory block sz--bytes */
         int                     m_dirblkfsbs;   /* directory block sz--fsbs */
         xfs_dablk_t             m_dirdatablk;   /* blockno of dir data v2 */
@@ -378,6 +382,7 @@ typedef struct xfs_mount {
                                                    counters */
 #define XFS_MOUNT_FILESTREAMS   (1ULL << 24)    /* enable the filestreams
                                                    allocator */
+#define XFS_MOUNT_NOATTR2       (1ULL << 25)    /* disable use of attr2 format */
 
 
 /*
@@ -510,15 +515,12 @@ typedef struct xfs_mod_sb {
 #define XFS_MOUNT_ILOCK(mp)     mutex_lock(&((mp)->m_ilock))
 #define XFS_MOUNT_IUNLOCK(mp)   mutex_unlock(&((mp)->m_ilock))
 
-extern xfs_mount_t *xfs_mount_init(void);
 extern void     xfs_mod_sb(xfs_trans_t *, __int64_t);
 extern int      xfs_log_sbcount(xfs_mount_t *, uint);
-extern void     xfs_mount_free(xfs_mount_t *mp);
 extern int      xfs_mountfs(xfs_mount_t *mp, int);
 extern void     xfs_mountfs_check_barriers(xfs_mount_t *mp);
 
-extern int      xfs_unmountfs(xfs_mount_t *, struct cred *);
-extern void     xfs_unmountfs_close(xfs_mount_t *, struct cred *);
+extern int      xfs_unmountfs(xfs_mount_t *);
 extern int      xfs_unmountfs_writesb(xfs_mount_t *);
 extern int      xfs_unmount_flush(xfs_mount_t *, int);
 extern int      xfs_mod_incore_sb(xfs_mount_t *, xfs_sb_field_t, int64_t, int);
@@ -544,9 +546,6 @@ extern void	xfs_qmops_put(struct xfs_mount *);
 
 extern struct xfs_dmops xfs_dmcore_xfs;
 
-extern int      xfs_init(void);
-extern void     xfs_cleanup(void);
-
 #endif  /* __KERNEL__ */
 
 #endif  /* __XFS_MOUNT_H__ */
diff --git a/fs/xfs/xfs_mru_cache.c b/fs/xfs/xfs_mru_cache.c
index a0b2c0a2589a..afee7eb24323 100644
--- a/fs/xfs/xfs_mru_cache.c
+++ b/fs/xfs/xfs_mru_cache.c
@@ -307,15 +307,18 @@ xfs_mru_cache_init(void)
         xfs_mru_elem_zone = kmem_zone_init(sizeof(xfs_mru_cache_elem_t),
                                          "xfs_mru_cache_elem");
         if (!xfs_mru_elem_zone)
-                return ENOMEM;
+                goto out;
 
         xfs_mru_reap_wq = create_singlethread_workqueue("xfs_mru_cache");
-        if (!xfs_mru_reap_wq) {
-                kmem_zone_destroy(xfs_mru_elem_zone);
-                return ENOMEM;
-        }
+        if (!xfs_mru_reap_wq)
+                goto out_destroy_mru_elem_zone;
 
         return 0;
+
+ out_destroy_mru_elem_zone:
+        kmem_zone_destroy(xfs_mru_elem_zone);
+ out:
+        return -ENOMEM;
 }
 
 void
@@ -382,9 +385,9 @@ xfs_mru_cache_create(
 
 exit:
         if (err && mru && mru->lists)
-                kmem_free(mru->lists, mru->grp_count * sizeof(*mru->lists));
+                kmem_free(mru->lists);
         if (err && mru)
-                kmem_free(mru, sizeof(*mru));
+                kmem_free(mru);
 
         return err;
 }
@@ -424,8 +427,8 @@ xfs_mru_cache_destroy(
 
         xfs_mru_cache_flush(mru);
 
-        kmem_free(mru->lists, mru->grp_count * sizeof(*mru->lists));
-        kmem_free(mru, sizeof(*mru));
+        kmem_free(mru->lists);
+        kmem_free(mru);
 }
 
 /*
diff --git a/fs/xfs/xfs_rename.c b/fs/xfs/xfs_rename.c
index d8063e1ad298..d700dacdb10e 100644
--- a/fs/xfs/xfs_rename.c
+++ b/fs/xfs/xfs_rename.c
@@ -336,22 +336,18 @@ xfs_rename(
                 ASSERT(error != EEXIST);
                 if (error)
                         goto abort_return;
-                xfs_ichgtime(src_ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
-
-        } else {
-                /*
-                 * We always want to hit the ctime on the source inode.
-                 * We do it in the if clause above for the 'new_parent &&
-                 * src_is_directory' case, and here we get all the other
-                 * cases.  This isn't strictly required by the standards
-                 * since the source inode isn't really being changed,
-                 * but old unix file systems did it and some incremental
-                 * backup programs won't work without it.
-                 */
-                xfs_ichgtime(src_ip, XFS_ICHGTIME_CHG);
         }
 
         /*
+         * We always want to hit the ctime on the source inode.
+         *
+         * This isn't strictly required by the standards since the source
+         * inode isn't really being changed, but old unix file systems did
+         * it and some incremental backup programs won't work without it.
+         */
+        xfs_ichgtime(src_ip, XFS_ICHGTIME_CHG);
+
+        /*
          * Adjust the link count on src_dp.  This is necessary when
          * renaming a directory, either within one parent when
          * the target existed, or across two parent directories.
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index a0dc6e5bc5b9..bf87a5913504 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -2062,7 +2062,7 @@ xfs_growfs_rt(
         /*
          * Free the fake mp structure.
          */
-        kmem_free(nmp, sizeof(*nmp));
+        kmem_free(nmp);
 
         return error;
 }
diff --git a/fs/xfs/xfs_sb.h b/fs/xfs/xfs_sb.h
index d904efe7f871..3f8cf1587f4c 100644
--- a/fs/xfs/xfs_sb.h
+++ b/fs/xfs/xfs_sb.h
@@ -46,10 +46,12 @@ struct xfs_mount;
 #define XFS_SB_VERSION_SECTORBIT        0x0800
 #define XFS_SB_VERSION_EXTFLGBIT        0x1000
 #define XFS_SB_VERSION_DIRV2BIT         0x2000
+#define XFS_SB_VERSION_BORGBIT          0x4000  /* ASCII only case-insens. */
 #define XFS_SB_VERSION_MOREBITSBIT      0x8000
 #define XFS_SB_VERSION_OKSASHFBITS      \
         (XFS_SB_VERSION_EXTFLGBIT | \
-         XFS_SB_VERSION_DIRV2BIT)
+         XFS_SB_VERSION_DIRV2BIT | \
+         XFS_SB_VERSION_BORGBIT)
 #define XFS_SB_VERSION_OKREALFBITS      \
         (XFS_SB_VERSION_ATTRBIT | \
          XFS_SB_VERSION_NLINKBIT | \
@@ -437,6 +439,12 @@ static inline int xfs_sb_version_hassector(xfs_sb_t *sbp)
                 ((sbp)->sb_versionnum & XFS_SB_VERSION_SECTORBIT);
 }
 
+static inline int xfs_sb_version_hasasciici(xfs_sb_t *sbp)
+{
+        return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) && \
+                (sbp->sb_versionnum & XFS_SB_VERSION_BORGBIT);
+}
+
 static inline int xfs_sb_version_hasmorebits(xfs_sb_t *sbp)
 {
         return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) && \
@@ -473,6 +481,13 @@ static inline void xfs_sb_version_addattr2(xfs_sb_t *sbp)
                 ((sbp)->sb_features2 | XFS_SB_VERSION2_ATTR2BIT)));
 }
 
+static inline void xfs_sb_version_removeattr2(xfs_sb_t *sbp)
+{
+        sbp->sb_features2 &= ~XFS_SB_VERSION2_ATTR2BIT;
+        if (!sbp->sb_features2)
+                sbp->sb_versionnum &= ~XFS_SB_VERSION_MOREBITSBIT;
+}
+
 /*
  * end of superblock version macros
  */
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 140386434aa3..e4ebddd3c500 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -889,7 +889,7 @@ shut_us_down:
 
         tp->t_commit_lsn = commit_lsn;
         if (nvec > XFS_TRANS_LOGVEC_COUNT) {
-                kmem_free(log_vector, nvec * sizeof(xfs_log_iovec_t));
+                kmem_free(log_vector);
         }
 
         /*
@@ -1265,7 +1265,7 @@ xfs_trans_committed(
                 ASSERT(!XFS_LIC_ARE_ALL_FREE(licp));
                 xfs_trans_chunk_committed(licp, tp->t_lsn, abortflag);
                 next_licp = licp->lic_next;
-                kmem_free(licp, sizeof(xfs_log_item_chunk_t));
+                kmem_free(licp);
                 licp = next_licp;
         }
 
diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c
index 4c70bf5e9985..2a1c0f071f91 100644
--- a/fs/xfs/xfs_trans_inode.c
+++ b/fs/xfs/xfs_trans_inode.c
@@ -291,7 +291,7 @@ xfs_trans_inode_broot_debug(
         iip = ip->i_itemp;
         if (iip->ili_root_size != 0) {
                 ASSERT(iip->ili_orig_root != NULL);
-                kmem_free(iip->ili_orig_root, iip->ili_root_size);
+                kmem_free(iip->ili_orig_root);
                 iip->ili_root_size = 0;
                 iip->ili_orig_root = NULL;
         }
diff --git a/fs/xfs/xfs_trans_item.c b/fs/xfs/xfs_trans_item.c
index 66a09f0d894b..db5c83595526 100644
--- a/fs/xfs/xfs_trans_item.c
+++ b/fs/xfs/xfs_trans_item.c
@@ -161,7 +161,7 @@ xfs_trans_free_item(xfs_trans_t	*tp, xfs_log_item_desc_t *lidp)
                         licpp = &((*licpp)->lic_next);
                 }
                 *licpp = licp->lic_next;
-                kmem_free(licp, sizeof(xfs_log_item_chunk_t));
+                kmem_free(licp);
                 tp->t_items_free -= XFS_LIC_NUM_SLOTS;
         }
 }
@@ -314,7 +314,7 @@ xfs_trans_free_items(
                 ASSERT(!XFS_LIC_ARE_ALL_FREE(licp));
                 (void) xfs_trans_unlock_chunk(licp, 1, abort, NULLCOMMITLSN);
                 next_licp = licp->lic_next;
-                kmem_free(licp, sizeof(xfs_log_item_chunk_t));
+                kmem_free(licp);
                 licp = next_licp;
         }
 
@@ -363,7 +363,7 @@ xfs_trans_unlock_items(xfs_trans_t *tp, xfs_lsn_t commit_lsn)
                 next_licp = licp->lic_next;
                 if (XFS_LIC_ARE_ALL_FREE(licp)) {
                         *licpp = next_licp;
-                        kmem_free(licp, sizeof(xfs_log_item_chunk_t));
+                        kmem_free(licp);
                         freed -= XFS_LIC_NUM_SLOTS;
                 } else {
                         licpp = &(licp->lic_next);
@@ -530,7 +530,7 @@ xfs_trans_free_busy(xfs_trans_t *tp)
         lbcp = tp->t_busy.lbc_next;
         while (lbcp != NULL) {
                 lbcq = lbcp->lbc_next;
-                kmem_free(lbcp, sizeof(xfs_log_busy_chunk_t));
+                kmem_free(lbcp);
                 lbcp = lbcq;
         }
 
diff --git a/fs/xfs/xfs_vfsops.c b/fs/xfs/xfs_vfsops.c
index 30bacd8bb0e5..4a9a43315a86 100644
--- a/fs/xfs/xfs_vfsops.c
+++ b/fs/xfs/xfs_vfsops.c
@@ -58,586 +58,6 @@
 #include "xfs_utils.h"
 
 
-int __init
-xfs_init(void)
-{
-#ifdef XFS_DABUF_DEBUG
-        extern spinlock_t        xfs_dabuf_global_lock;
-        spin_lock_init(&xfs_dabuf_global_lock);
-#endif
-
-        /*
-         * Initialize all of the zone allocators we use.
-         */
-        xfs_log_ticket_zone = kmem_zone_init(sizeof(xlog_ticket_t),
-                                                "xfs_log_ticket");
-        xfs_bmap_free_item_zone = kmem_zone_init(sizeof(xfs_bmap_free_item_t),
-                                                "xfs_bmap_free_item");
-        xfs_btree_cur_zone = kmem_zone_init(sizeof(xfs_btree_cur_t),
-                                                "xfs_btree_cur");
-        xfs_da_state_zone = kmem_zone_init(sizeof(xfs_da_state_t),
-                                                "xfs_da_state");
-        xfs_dabuf_zone = kmem_zone_init(sizeof(xfs_dabuf_t), "xfs_dabuf");
-        xfs_ifork_zone = kmem_zone_init(sizeof(xfs_ifork_t), "xfs_ifork");
-        xfs_trans_zone = kmem_zone_init(sizeof(xfs_trans_t), "xfs_trans");
-        xfs_acl_zone_init(xfs_acl_zone, "xfs_acl");
-        xfs_mru_cache_init();
-        xfs_filestream_init();
-
-        /*
-         * The size of the zone allocated buf log item is the maximum
-         * size possible under XFS.  This wastes a little bit of memory,
-         * but it is much faster.
-         */
-        xfs_buf_item_zone =
-                kmem_zone_init((sizeof(xfs_buf_log_item_t) +
-                                (((XFS_MAX_BLOCKSIZE / XFS_BLI_CHUNK) /
-                                  NBWORD) * sizeof(int))),
-                               "xfs_buf_item");
-        xfs_efd_zone =
-                kmem_zone_init((sizeof(xfs_efd_log_item_t) +
-                               ((XFS_EFD_MAX_FAST_EXTENTS - 1) *
-                                 sizeof(xfs_extent_t))),
-                                      "xfs_efd_item");
-        xfs_efi_zone =
-                kmem_zone_init((sizeof(xfs_efi_log_item_t) +
-                               ((XFS_EFI_MAX_FAST_EXTENTS - 1) *
-                                 sizeof(xfs_extent_t))),
-                                      "xfs_efi_item");
-
-        /*
-         * These zones warrant special memory allocator hints
-         */
-        xfs_inode_zone =
-                kmem_zone_init_flags(sizeof(xfs_inode_t), "xfs_inode",
-                                        KM_ZONE_HWALIGN | KM_ZONE_RECLAIM |
-                                        KM_ZONE_SPREAD, NULL);
-        xfs_ili_zone =
-                kmem_zone_init_flags(sizeof(xfs_inode_log_item_t), "xfs_ili",
-                                        KM_ZONE_SPREAD, NULL);
-
-        /*
-         * Allocate global trace buffers.
-         */
-#ifdef XFS_ALLOC_TRACE
-        xfs_alloc_trace_buf = ktrace_alloc(XFS_ALLOC_TRACE_SIZE, KM_SLEEP);
-#endif
-#ifdef XFS_BMAP_TRACE
-        xfs_bmap_trace_buf = ktrace_alloc(XFS_BMAP_TRACE_SIZE, KM_SLEEP);
-#endif
-#ifdef XFS_BMBT_TRACE
-        xfs_bmbt_trace_buf = ktrace_alloc(XFS_BMBT_TRACE_SIZE, KM_SLEEP);
-#endif
-#ifdef XFS_ATTR_TRACE
-        xfs_attr_trace_buf = ktrace_alloc(XFS_ATTR_TRACE_SIZE, KM_SLEEP);
-#endif
-#ifdef XFS_DIR2_TRACE
-        xfs_dir2_trace_buf = ktrace_alloc(XFS_DIR2_GTRACE_SIZE, KM_SLEEP);
-#endif
-
-        xfs_dir_startup();
-
-#if (defined(DEBUG) || defined(INDUCE_IO_ERROR))
-        xfs_error_test_init();
-#endif /* DEBUG || INDUCE_IO_ERROR */
-
-        xfs_init_procfs();
-        xfs_sysctl_register();
-        return 0;
-}
-
-void __exit
-xfs_cleanup(void)
-{
-        extern kmem_zone_t      *xfs_inode_zone;
-        extern kmem_zone_t      *xfs_efd_zone;
-        extern kmem_zone_t      *xfs_efi_zone;
-
-        xfs_cleanup_procfs();
-        xfs_sysctl_unregister();
-        xfs_filestream_uninit();
-        xfs_mru_cache_uninit();
-        xfs_acl_zone_destroy(xfs_acl_zone);
-
-#ifdef XFS_DIR2_TRACE
-        ktrace_free(xfs_dir2_trace_buf);
-#endif
-#ifdef XFS_ATTR_TRACE
-        ktrace_free(xfs_attr_trace_buf);
-#endif
-#ifdef XFS_BMBT_TRACE
-        ktrace_free(xfs_bmbt_trace_buf);
-#endif
-#ifdef XFS_BMAP_TRACE
-        ktrace_free(xfs_bmap_trace_buf);
-#endif
-#ifdef XFS_ALLOC_TRACE
-        ktrace_free(xfs_alloc_trace_buf);
-#endif
-
-        kmem_zone_destroy(xfs_bmap_free_item_zone);
-        kmem_zone_destroy(xfs_btree_cur_zone);
-        kmem_zone_destroy(xfs_inode_zone);
-        kmem_zone_destroy(xfs_trans_zone);
-        kmem_zone_destroy(xfs_da_state_zone);
-        kmem_zone_destroy(xfs_dabuf_zone);
-        kmem_zone_destroy(xfs_buf_item_zone);
-        kmem_zone_destroy(xfs_efd_zone);
-        kmem_zone_destroy(xfs_efi_zone);
-        kmem_zone_destroy(xfs_ifork_zone);
-        kmem_zone_destroy(xfs_ili_zone);
-        kmem_zone_destroy(xfs_log_ticket_zone);
-}
-
-/*
- * xfs_start_flags
- *
- * This function fills in xfs_mount_t fields based on mount args.
- * Note: the superblock has _not_ yet been read in.
- */
-STATIC int
-xfs_start_flags(
-        struct xfs_mount_args   *ap,
-        struct xfs_mount        *mp)
-{
-        /* Values are in BBs */
-        if ((ap->flags & XFSMNT_NOALIGN) != XFSMNT_NOALIGN) {
-                /*
-                 * At this point the superblock has not been read
-                 * in, therefore we do not know the block size.
-                 * Before the mount call ends we will convert
-                 * these to FSBs.
-                 */
-                mp->m_dalign = ap->sunit;
-                mp->m_swidth = ap->swidth;
-        }
-
-        if (ap->logbufs != -1 &&
-            ap->logbufs != 0 &&
-            (ap->logbufs < XLOG_MIN_ICLOGS ||
-             ap->logbufs > XLOG_MAX_ICLOGS)) {
-                cmn_err(CE_WARN,
-                        "XFS: invalid logbufs value: %d [not %d-%d]",
-                        ap->logbufs, XLOG_MIN_ICLOGS, XLOG_MAX_ICLOGS);
-                return XFS_ERROR(EINVAL);
-        }
-        mp->m_logbufs = ap->logbufs;
-        if (ap->logbufsize != -1 &&
-            ap->logbufsize !=  0 &&
-            (ap->logbufsize < XLOG_MIN_RECORD_BSIZE ||
-             ap->logbufsize > XLOG_MAX_RECORD_BSIZE ||
-             !is_power_of_2(ap->logbufsize))) {
-                cmn_err(CE_WARN,
-        "XFS: invalid logbufsize: %d [not 16k,32k,64k,128k or 256k]",
-                        ap->logbufsize);
-                return XFS_ERROR(EINVAL);
-        }
-        mp->m_logbsize = ap->logbufsize;
-        mp->m_fsname_len = strlen(ap->fsname) + 1;
-        mp->m_fsname = kmem_alloc(mp->m_fsname_len, KM_SLEEP);
-        strcpy(mp->m_fsname, ap->fsname);
-        if (ap->rtname[0]) {
-                mp->m_rtname = kmem_alloc(strlen(ap->rtname) + 1, KM_SLEEP);
-                strcpy(mp->m_rtname, ap->rtname);
-        }
-        if (ap->logname[0]) {
-                mp->m_logname = kmem_alloc(strlen(ap->logname) + 1, KM_SLEEP);
-                strcpy(mp->m_logname, ap->logname);
-        }
-
-        if (ap->flags & XFSMNT_WSYNC)
-                mp->m_flags |= XFS_MOUNT_WSYNC;
-#if XFS_BIG_INUMS
-        if (ap->flags & XFSMNT_INO64) {
-                mp->m_flags |= XFS_MOUNT_INO64;
-                mp->m_inoadd = XFS_INO64_OFFSET;
-        }
-#endif
-        if (ap->flags & XFSMNT_RETERR)
-                mp->m_flags |= XFS_MOUNT_RETERR;
-        if (ap->flags & XFSMNT_NOALIGN)
-                mp->m_flags |= XFS_MOUNT_NOALIGN;
-        if (ap->flags & XFSMNT_SWALLOC)
-                mp->m_flags |= XFS_MOUNT_SWALLOC;
-        if (ap->flags & XFSMNT_OSYNCISOSYNC)
-                mp->m_flags |= XFS_MOUNT_OSYNCISOSYNC;
-        if (ap->flags & XFSMNT_32BITINODES)
-                mp->m_flags |= XFS_MOUNT_32BITINODES;
-
-        if (ap->flags & XFSMNT_IOSIZE) {
-                if (ap->iosizelog > XFS_MAX_IO_LOG ||
-                    ap->iosizelog < XFS_MIN_IO_LOG) {
-                        cmn_err(CE_WARN,
-                "XFS: invalid log iosize: %d [not %d-%d]",
-                                ap->iosizelog, XFS_MIN_IO_LOG,
-                                XFS_MAX_IO_LOG);
-                        return XFS_ERROR(EINVAL);
-                }
-
-                mp->m_flags |= XFS_MOUNT_DFLT_IOSIZE;
-                mp->m_readio_log = mp->m_writeio_log = ap->iosizelog;
-        }
-
-        if (ap->flags & XFSMNT_IKEEP)
-                mp->m_flags |= XFS_MOUNT_IKEEP;
-        if (ap->flags & XFSMNT_DIRSYNC)
-                mp->m_flags |= XFS_MOUNT_DIRSYNC;
-        if (ap->flags & XFSMNT_ATTR2)
-                mp->m_flags |= XFS_MOUNT_ATTR2;
-
-        if (ap->flags2 & XFSMNT2_COMPAT_IOSIZE)
-                mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
-
-        /*
-         * no recovery flag requires a read-only mount
-         */
-        if (ap->flags & XFSMNT_NORECOVERY) {
-                if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
-                        cmn_err(CE_WARN,
-        "XFS: tried to mount a FS read-write without recovery!");
-                        return XFS_ERROR(EINVAL);
-                }
-                mp->m_flags |= XFS_MOUNT_NORECOVERY;
-        }
-
-        if (ap->flags & XFSMNT_NOUUID)
-                mp->m_flags |= XFS_MOUNT_NOUUID;
-        if (ap->flags & XFSMNT_BARRIER)
-                mp->m_flags |= XFS_MOUNT_BARRIER;
-        else
-                mp->m_flags &= ~XFS_MOUNT_BARRIER;
-
-        if (ap->flags2 & XFSMNT2_FILESTREAMS)
-                mp->m_flags |= XFS_MOUNT_FILESTREAMS;
-
-        if (ap->flags & XFSMNT_DMAPI)
-                mp->m_flags |= XFS_MOUNT_DMAPI;
-        return 0;
-}
-
-/*
- * This function fills in xfs_mount_t fields based on mount args.
- * Note: the superblock _has_ now been read in.
- */
-STATIC int
-xfs_finish_flags(
-        struct xfs_mount_args   *ap,
-        struct xfs_mount        *mp)
-{
-        int                     ronly = (mp->m_flags & XFS_MOUNT_RDONLY);
-
-        /* Fail a mount where the logbuf is smaller then the log stripe */
-        if (xfs_sb_version_haslogv2(&mp->m_sb)) {
-                if ((ap->logbufsize <= 0) &&
-                    (mp->m_sb.sb_logsunit > XLOG_BIG_RECORD_BSIZE)) {
-                        mp->m_logbsize = mp->m_sb.sb_logsunit;
-                } else if (ap->logbufsize > 0 &&
-                           ap->logbufsize < mp->m_sb.sb_logsunit) {
-                        cmn_err(CE_WARN,
-        "XFS: 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 (ap->logbufsize > XLOG_BIG_RECORD_BSIZE) {
-                        cmn_err(CE_WARN,
-        "XFS: logbuf size for version 1 logs must be 16K or 32K");
-                        return XFS_ERROR(EINVAL);
-                }
-        }
-
-        if (xfs_sb_version_hasattr2(&mp->m_sb))
-                mp->m_flags |= XFS_MOUNT_ATTR2;
-
-        /*
-         * 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");
-                return XFS_ERROR(EROFS);
-        }
-
-        /*
-         * check for shared mount.
-         */
-        if (ap->flags & XFSMNT_SHARED) {
-                if (!xfs_sb_version_hasshared(&mp->m_sb))
-                        return XFS_ERROR(EINVAL);
-
-                /*
-                 * For IRIX 6.5, shared mounts must have the shared
-                 * version bit set, have the persistent readonly
-                 * field set, must be version 0 and can only be mounted
-                 * read-only.
-                 */
-                if (!ronly || !(mp->m_sb.sb_flags & XFS_SBF_READONLY) ||
-                     (mp->m_sb.sb_shared_vn != 0))
-                        return XFS_ERROR(EINVAL);
-
-                mp->m_flags |= XFS_MOUNT_SHARED;
-
-                /*
-                 * Shared XFS V0 can't deal with DMI.  Return EINVAL.
-                 */
-                if (mp->m_sb.sb_shared_vn == 0 && (ap->flags & XFSMNT_DMAPI))
-                        return XFS_ERROR(EINVAL);
-        }
-
-        if (ap->flags & XFSMNT_UQUOTA) {
-                mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE);
-                if (ap->flags & XFSMNT_UQUOTAENF)
-                        mp->m_qflags |= XFS_UQUOTA_ENFD;
-        }
-
-        if (ap->flags & XFSMNT_GQUOTA) {
-                mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
-                if (ap->flags & XFSMNT_GQUOTAENF)
-                        mp->m_qflags |= XFS_OQUOTA_ENFD;
-        } else if (ap->flags & XFSMNT_PQUOTA) {
-                mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
-                if (ap->flags & XFSMNT_PQUOTAENF)
-                        mp->m_qflags |= XFS_OQUOTA_ENFD;
-        }
-
-        return 0;
-}
-
-/*
- * xfs_mount
- *
- * The file system configurations are:
- *      (1) device (partition) with data and internal log
- *      (2) logical volume with data and log subvolumes.
- *      (3) logical volume with data, log, and realtime subvolumes.
- *
- * We only have to handle opening the log and realtime volumes here if
- * they are present.  The data subvolume has already been opened by
- * get_sb_bdev() and is stored in vfsp->vfs_super->s_bdev.
- */
-int
-xfs_mount(
-        struct xfs_mount        *mp,
-        struct xfs_mount_args   *args,
-        cred_t                  *credp)
-{
-        struct block_device     *ddev, *logdev, *rtdev;
-        int                     flags = 0, error;
-
-        ddev = mp->m_super->s_bdev;
-        logdev = rtdev = NULL;
-
-        error = xfs_dmops_get(mp, args);
-        if (error)
-                return error;
-        error = xfs_qmops_get(mp, args);
-        if (error)
-                return error;
-
-        if (args->flags & XFSMNT_QUIET)
-                flags |= XFS_MFSI_QUIET;
-
-        /*
-         * Open real time and log devices - order is important.
-         */
-        if (args->logname[0]) {
-                error = xfs_blkdev_get(mp, args->logname, &logdev);
-                if (error)
-                        return error;
-        }
-        if (args->rtname[0]) {
-                error = xfs_blkdev_get(mp, args->rtname, &rtdev);
-                if (error) {
-                        xfs_blkdev_put(logdev);
-                        return error;
-                }
-
-                if (rtdev == ddev || rtdev == logdev) {
-                        cmn_err(CE_WARN,
-        "XFS: Cannot mount filesystem with identical rtdev and ddev/logdev.");
-                        xfs_blkdev_put(logdev);
-                        xfs_blkdev_put(rtdev);
-                        return EINVAL;
-                }
-        }
-
-        /*
-         * Setup xfs_mount buffer target pointers
-         */
-        error = ENOMEM;
-        mp->m_ddev_targp = xfs_alloc_buftarg(ddev, 0);
-        if (!mp->m_ddev_targp) {
-                xfs_blkdev_put(logdev);
-                xfs_blkdev_put(rtdev);
-                return error;
-        }
-        if (rtdev) {
-                mp->m_rtdev_targp = xfs_alloc_buftarg(rtdev, 1);
-                if (!mp->m_rtdev_targp) {
-                        xfs_blkdev_put(logdev);
-                        xfs_blkdev_put(rtdev);
-                        goto error0;
-                }
-        }
-        mp->m_logdev_targp = (logdev && logdev != ddev) ?
-                                xfs_alloc_buftarg(logdev, 1) : mp->m_ddev_targp;
-        if (!mp->m_logdev_targp) {
-                xfs_blkdev_put(logdev);
-                xfs_blkdev_put(rtdev);
-                goto error0;
-        }
-
-        /*
-         * Setup flags based on mount(2) options and then the superblock
-         */
-        error = xfs_start_flags(args, mp);
-        if (error)
-                goto error1;
-        error = xfs_readsb(mp, flags);
-        if (error)
-                goto error1;
-        error = xfs_finish_flags(args, mp);
-        if (error)
-                goto error2;
-
-        /*
-         * Setup xfs_mount buffer target pointers based on superblock
-         */
-        error = xfs_setsize_buftarg(mp->m_ddev_targp, mp->m_sb.sb_blocksize,
-                                    mp->m_sb.sb_sectsize);
-        if (!error && logdev && logdev != ddev) {
-                unsigned int    log_sector_size = BBSIZE;
-
-                if (xfs_sb_version_hassector(&mp->m_sb))
-                        log_sector_size = mp->m_sb.sb_logsectsize;
-                error = xfs_setsize_buftarg(mp->m_logdev_targp,
-                                            mp->m_sb.sb_blocksize,
-                                            log_sector_size);
-        }
-        if (!error && rtdev)
-                error = xfs_setsize_buftarg(mp->m_rtdev_targp,
-                                            mp->m_sb.sb_blocksize,
-                                            mp->m_sb.sb_sectsize);
-        if (error)
-                goto error2;
-
-        if (mp->m_flags & XFS_MOUNT_BARRIER)
-                xfs_mountfs_check_barriers(mp);
-
-        if ((error = xfs_filestream_mount(mp)))
-                goto error2;
-
-        error = xfs_mountfs(mp, flags);
-        if (error)
-                goto error2;
-
-        XFS_SEND_MOUNT(mp, DM_RIGHT_NULL, args->mtpt, args->fsname);
-
-        return 0;
-
-error2:
-        if (mp->m_sb_bp)
-                xfs_freesb(mp);
-error1:
-        xfs_binval(mp->m_ddev_targp);
-        if (logdev && logdev != ddev)
-                xfs_binval(mp->m_logdev_targp);
-        if (rtdev)
-                xfs_binval(mp->m_rtdev_targp);
-error0:
-        xfs_unmountfs_close(mp, credp);
-        xfs_qmops_put(mp);
-        xfs_dmops_put(mp);
-        return error;
-}
-
-int
-xfs_unmount(
-        xfs_mount_t     *mp,
-        int             flags,
-        cred_t          *credp)
-{
-        xfs_inode_t     *rip;
-        bhv_vnode_t     *rvp;
-        int             unmount_event_wanted = 0;
-        int             unmount_event_flags = 0;
-        int             xfs_unmountfs_needed = 0;
-        int             error;
-
-        rip = mp->m_rootip;
-        rvp = XFS_ITOV(rip);
-
-#ifdef HAVE_DMAPI
-        if (mp->m_flags & XFS_MOUNT_DMAPI) {
-                error = XFS_SEND_PREUNMOUNT(mp,
-                                rip, DM_RIGHT_NULL, rip, DM_RIGHT_NULL,
-                                NULL, NULL, 0, 0,
-                                (mp->m_dmevmask & (1<<DM_EVENT_PREUNMOUNT))?
-                                        0:DM_FLAGS_UNWANTED);
-                        if (error)
-                                return XFS_ERROR(error);
-                unmount_event_wanted = 1;
-                unmount_event_flags = (mp->m_dmevmask & (1<<DM_EVENT_UNMOUNT))?
-                                        0 : DM_FLAGS_UNWANTED;
-        }
-#endif
-
-        /*
-         * Blow away any referenced inode in the filestreams cache.
-         * This can and will cause log traffic as inodes go inactive
-         * here.
-         */
-        xfs_filestream_unmount(mp);
-
-        XFS_bflush(mp->m_ddev_targp);
-        error = xfs_unmount_flush(mp, 0);
-        if (error)
-                goto out;
-
-        ASSERT(vn_count(rvp) == 1);
-
-        /*
-         * Drop the reference count
-         */
-        IRELE(rip);
-
-        /*
-         * If we're forcing a shutdown, typically because of a media error,
-         * we want to make sure we invalidate dirty pages that belong to
-         * referenced vnodes as well.
-         */
-        if (XFS_FORCED_SHUTDOWN(mp)) {
-                error = xfs_sync(mp, SYNC_WAIT | SYNC_CLOSE);
-                ASSERT(error != EFSCORRUPTED);
-        }
-        xfs_unmountfs_needed = 1;
-
-out:
-        /*      Send DMAPI event, if required.
-         *      Then do xfs_unmountfs() if needed.
-         *      Then return error (or zero).
-         */
-        if (unmount_event_wanted) {
-                /* Note: mp structure must still exist for
-                 * XFS_SEND_UNMOUNT() call.
-                 */
-                XFS_SEND_UNMOUNT(mp, error == 0 ? rip : NULL,
-                        DM_RIGHT_NULL, 0, error, unmount_event_flags);
-        }
-        if (xfs_unmountfs_needed) {
-                /*
-                 * Call common unmount function to flush to disk
-                 * and free the super block buffer & mount structures.
-                 */
-                xfs_unmountfs(mp, credp);
-                xfs_qmops_put(mp);
-                xfs_dmops_put(mp);
-                kmem_free(mp, sizeof(xfs_mount_t));
-        }
-
-        return XFS_ERROR(error);
-}
-
 STATIC void
 xfs_quiesce_fs(
         xfs_mount_t             *mp)
@@ -694,30 +114,6 @@ xfs_attr_quiesce(
         xfs_unmountfs_writesb(mp);
 }
 
-int
-xfs_mntupdate(
-        struct xfs_mount                *mp,
-        int                             *flags,
-        struct xfs_mount_args           *args)
-{
-        if (!(*flags & MS_RDONLY)) {                    /* rw/ro -> rw */
-                if (mp->m_flags & XFS_MOUNT_RDONLY)
-                        mp->m_flags &= ~XFS_MOUNT_RDONLY;
-                if (args->flags & XFSMNT_BARRIER) {
-                        mp->m_flags |= XFS_MOUNT_BARRIER;
-                        xfs_mountfs_check_barriers(mp);
-                } else {
-                        mp->m_flags &= ~XFS_MOUNT_BARRIER;
-                }
-        } else if (!(mp->m_flags & XFS_MOUNT_RDONLY)) { /* rw -> ro */
-                xfs_filestream_flush(mp);
-                xfs_sync(mp, SYNC_DATA_QUIESCE);
-                xfs_attr_quiesce(mp);
-                mp->m_flags |= XFS_MOUNT_RDONLY;
-        }
-        return 0;
-}
-
 /*
  * xfs_unmount_flush implements a set of flush operation on special
  * inodes, which are needed as a separate set of operations so that
@@ -1048,7 +444,7 @@ xfs_sync_inodes(
 
                 if (XFS_FORCED_SHUTDOWN(mp) && !(flags & SYNC_CLOSE)) {
                         XFS_MOUNT_IUNLOCK(mp);
-                        kmem_free(ipointer, sizeof(xfs_iptr_t));
+                        kmem_free(ipointer);
                         return 0;
                 }
 
@@ -1194,7 +590,7 @@ xfs_sync_inodes(
                         }
                         XFS_MOUNT_IUNLOCK(mp);
                         ASSERT(ipointer_in == B_FALSE);
-                        kmem_free(ipointer, sizeof(xfs_iptr_t));
+                        kmem_free(ipointer);
                         return XFS_ERROR(error);
                 }
 
@@ -1224,7 +620,7 @@ xfs_sync_inodes(
 
         ASSERT(ipointer_in == B_FALSE);
 
-        kmem_free(ipointer, sizeof(xfs_iptr_t));
+        kmem_free(ipointer);
         return XFS_ERROR(last_error);
 }
 
diff --git a/fs/xfs/xfs_vfsops.h b/fs/xfs/xfs_vfsops.h
index 1688817c55ed..a74b05087da4 100644
--- a/fs/xfs/xfs_vfsops.h
+++ b/fs/xfs/xfs_vfsops.h
@@ -8,11 +8,6 @@ struct kstatfs;
 struct xfs_mount;
 struct xfs_mount_args;
 
-int xfs_mount(struct xfs_mount *mp, struct xfs_mount_args *args,
-                struct cred *credp);
-int xfs_unmount(struct xfs_mount *mp, int flags, struct cred *credp);
-int xfs_mntupdate(struct xfs_mount *mp, int *flags,
-                struct xfs_mount_args *args);
 int xfs_sync(struct xfs_mount *mp, int flags);
 void xfs_do_force_shutdown(struct xfs_mount *mp, int flags, char *fname,
                 int lnnum);
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index e475e3717eb3..76a1166af822 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -75,26 +75,23 @@ xfs_open(
         return 0;
 }
 
-/*
- * xfs_setattr
- */
 int
 xfs_setattr(
-        xfs_inode_t             *ip,
-        bhv_vattr_t             *vap,
+        struct xfs_inode        *ip,
+        struct iattr            *iattr,
         int                     flags,
         cred_t                  *credp)
 {
         xfs_mount_t             *mp = ip->i_mount;
+        struct inode            *inode = XFS_ITOV(ip);
+        int                     mask = iattr->ia_valid;
         xfs_trans_t             *tp;
-        int                     mask;
         int                     code;
         uint                    lock_flags;
         uint                    commit_flags=0;
         uid_t                   uid=0, iuid=0;
         gid_t                   gid=0, igid=0;
         int                     timeflags = 0;
-        xfs_prid_t              projid=0, iprojid=0;
         struct xfs_dquot        *udqp, *gdqp, *olddquot1, *olddquot2;
         int                     file_owner;
         int                     need_iolock = 1;
@@ -104,30 +101,9 @@ xfs_setattr(
         if (mp->m_flags & XFS_MOUNT_RDONLY)
                 return XFS_ERROR(EROFS);
 
-        /*
-         * Cannot set certain attributes.
-         */
-        mask = vap->va_mask;
-        if (mask & XFS_AT_NOSET) {
-                return XFS_ERROR(EINVAL);
-        }
-
         if (XFS_FORCED_SHUTDOWN(mp))
                 return XFS_ERROR(EIO);
 
-        /*
-         * Timestamps do not need to be logged and hence do not
-         * need to be done within a transaction.
-         */
-        if (mask & XFS_AT_UPDTIMES) {
-                ASSERT((mask & ~XFS_AT_UPDTIMES) == 0);
-                timeflags = ((mask & XFS_AT_UPDATIME) ? XFS_ICHGTIME_ACC : 0) |
-                            ((mask & XFS_AT_UPDCTIME) ? XFS_ICHGTIME_CHG : 0) |
-                            ((mask & XFS_AT_UPDMTIME) ? XFS_ICHGTIME_MOD : 0);
-                xfs_ichgtime(ip, timeflags);
-                return 0;
-        }
-
         olddquot1 = olddquot2 = NULL;
         udqp = gdqp = NULL;
 
@@ -139,28 +115,22 @@ xfs_setattr(
          * If the IDs do change before we take the ilock, we're covered
          * because the i_*dquot fields will get updated anyway.
          */
-        if (XFS_IS_QUOTA_ON(mp) &&
-            (mask & (XFS_AT_UID|XFS_AT_GID|XFS_AT_PROJID))) {
+        if (XFS_IS_QUOTA_ON(mp) && (mask & (ATTR_UID|ATTR_GID))) {
                 uint    qflags = 0;
 
-                if ((mask & XFS_AT_UID) && XFS_IS_UQUOTA_ON(mp)) {
-                        uid = vap->va_uid;
+                if ((mask & ATTR_UID) && XFS_IS_UQUOTA_ON(mp)) {
+                        uid = iattr->ia_uid;
                         qflags |= XFS_QMOPT_UQUOTA;
                 } else {
                         uid = ip->i_d.di_uid;
                 }
-                if ((mask & XFS_AT_GID) && XFS_IS_GQUOTA_ON(mp)) {
-                        gid = vap->va_gid;
+                if ((mask & ATTR_GID) && XFS_IS_GQUOTA_ON(mp)) {
+                        gid = iattr->ia_gid;
                         qflags |= XFS_QMOPT_GQUOTA;
                 }  else {
                         gid = ip->i_d.di_gid;
                 }
-                if ((mask & XFS_AT_PROJID) && XFS_IS_PQUOTA_ON(mp)) {
-                        projid = vap->va_projid;
-                        qflags |= XFS_QMOPT_PQUOTA;
-                }  else {
-                        projid = ip->i_d.di_projid;
-                }
+
                 /*
                  * We take a reference when we initialize udqp and gdqp,
                  * so it is important that we never blindly double trip on
@@ -168,8 +138,8 @@ xfs_setattr(
                  */
                 ASSERT(udqp == NULL);
                 ASSERT(gdqp == NULL);
-                code = XFS_QM_DQVOPALLOC(mp, ip, uid, gid, projid, qflags,
-                                         &udqp, &gdqp);
+                code = XFS_QM_DQVOPALLOC(mp, ip, uid, gid, ip->i_d.di_projid,
+                                         qflags, &udqp, &gdqp);
                 if (code)
                         return code;
         }
@@ -180,10 +150,10 @@ xfs_setattr(
          */
         tp = NULL;
         lock_flags = XFS_ILOCK_EXCL;
-        if (flags & ATTR_NOLOCK)
+        if (flags & XFS_ATTR_NOLOCK)
                 need_iolock = 0;
-        if (!(mask & XFS_AT_SIZE)) {
-                if ((mask != (XFS_AT_CTIME|XFS_AT_ATIME|XFS_AT_MTIME)) ||
+        if (!(mask & ATTR_SIZE)) {
+                if ((mask != (ATTR_CTIME|ATTR_ATIME|ATTR_MTIME)) ||
                     (mp->m_flags & XFS_MOUNT_WSYNC)) {
                         tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
                         commit_flags = 0;
@@ -196,10 +166,10 @@ xfs_setattr(
                 }
         } else {
                 if (DM_EVENT_ENABLED(ip, DM_EVENT_TRUNCATE) &&
-                    !(flags & ATTR_DMI)) {
+                    !(flags & XFS_ATTR_DMI)) {
                         int dmflags = AT_DELAY_FLAG(flags) | DM_SEM_FLAG_WR;
                         code = XFS_SEND_DATA(mp, DM_EVENT_TRUNCATE, ip,
-                                vap->va_size, 0, dmflags, NULL);
+                                iattr->ia_size, 0, dmflags, NULL);
                         if (code) {
                                 lock_flags = 0;
                                 goto error_return;
@@ -219,9 +189,7 @@ xfs_setattr(
          * Only the owner or users with CAP_FOWNER
          * capability may do these things.
          */
-        if (mask &
-            (XFS_AT_MODE|XFS_AT_XFLAGS|XFS_AT_EXTSIZE|XFS_AT_UID|
-             XFS_AT_GID|XFS_AT_PROJID)) {
+        if (mask & (ATTR_MODE|ATTR_UID|ATTR_GID)) {
                 /*
                  * CAP_FOWNER overrides the following restrictions:
                  *
@@ -245,21 +213,21 @@ xfs_setattr(
                  * IDs of the calling process shall match the group owner of
                  * the file when setting the set-group-ID bit on that file
                  */
-                if (mask & XFS_AT_MODE) {
+                if (mask & ATTR_MODE) {
                         mode_t m = 0;
 
-                        if ((vap->va_mode & S_ISUID) && !file_owner)
+                        if ((iattr->ia_mode & S_ISUID) && !file_owner)
                                 m |= S_ISUID;
-                        if ((vap->va_mode & S_ISGID) &&
+                        if ((iattr->ia_mode & S_ISGID) &&
                             !in_group_p((gid_t)ip->i_d.di_gid))
                                 m |= S_ISGID;
 #if 0
                         /* Linux allows this, Irix doesn't. */
-                        if ((vap->va_mode & S_ISVTX) && !S_ISDIR(ip->i_d.di_mode))
+                        if ((iattr->ia_mode & S_ISVTX) && !S_ISDIR(ip->i_d.di_mode))
                                 m |= S_ISVTX;
 #endif
                         if (m && !capable(CAP_FSETID))
-                                vap->va_mode &= ~m;
+                                iattr->ia_mode &= ~m;
                 }
         }
 
@@ -270,7 +238,7 @@ xfs_setattr(
          * and can change the group id only to a group of which he
          * or she is a member.
          */
-        if (mask & (XFS_AT_UID|XFS_AT_GID|XFS_AT_PROJID)) {
+        if (mask & (ATTR_UID|ATTR_GID)) {
                 /*
                  * These IDs could have changed since we last looked at them.
                  * But, we're assured that if the ownership did change
@@ -278,12 +246,9 @@ xfs_setattr(
                  * would have changed also.
                  */
                 iuid = ip->i_d.di_uid;
-                iprojid = ip->i_d.di_projid;
                 igid = ip->i_d.di_gid;
-                gid = (mask & XFS_AT_GID) ? vap->va_gid : igid;
-                uid = (mask & XFS_AT_UID) ? vap->va_uid : iuid;
-                projid = (mask & XFS_AT_PROJID) ? (xfs_prid_t)vap->va_projid :
-                         iprojid;
+                gid = (mask & ATTR_GID) ? iattr->ia_gid : igid;
+                uid = (mask & ATTR_UID) ? iattr->ia_uid : iuid;
 
                 /*
                  * CAP_CHOWN overrides the following restrictions:
@@ -303,11 +268,10 @@ xfs_setattr(
                         goto error_return;
                 }
                 /*
-                 * Do a quota reservation only if uid/projid/gid is actually
+                 * Do a quota reservation only if uid/gid is actually
                  * going to change.
                  */
                 if ((XFS_IS_UQUOTA_ON(mp) && iuid != uid) ||
-                    (XFS_IS_PQUOTA_ON(mp) && iprojid != projid) ||
                     (XFS_IS_GQUOTA_ON(mp) && igid != gid)) {
                         ASSERT(tp);
                         code = XFS_QM_DQVOPCHOWNRESV(mp, tp, ip, udqp, gdqp,
@@ -321,13 +285,13 @@ xfs_setattr(
         /*
          * Truncate file.  Must have write permission and not be a directory.
          */
-        if (mask & XFS_AT_SIZE) {
+        if (mask & ATTR_SIZE) {
                 /* Short circuit the truncate case for zero length files */
-                if ((vap->va_size == 0) &&
-                   (ip->i_size == 0) && (ip->i_d.di_nextents == 0)) {
+                if (iattr->ia_size == 0 &&
+                    ip->i_size == 0 && ip->i_d.di_nextents == 0) {
                         xfs_iunlock(ip, XFS_ILOCK_EXCL);
                         lock_flags &= ~XFS_ILOCK_EXCL;
-                        if (mask & XFS_AT_CTIME)
+                        if (mask & ATTR_CTIME)
                                 xfs_ichgtime(ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
                         code = 0;
                         goto error_return;
@@ -350,9 +314,9 @@ xfs_setattr(
         /*
          * Change file access or modified times.
          */
-        if (mask & (XFS_AT_ATIME|XFS_AT_MTIME)) {
+        if (mask & (ATTR_ATIME|ATTR_MTIME)) {
                 if (!file_owner) {
-                        if ((flags & ATTR_UTIME) &&
+                        if ((mask & (ATTR_MTIME_SET|ATTR_ATIME_SET)) &&
                             !capable(CAP_FOWNER)) {
                                 code = XFS_ERROR(EPERM);
                                 goto error_return;
@@ -361,90 +325,23 @@ xfs_setattr(
         }
 
         /*
-         * Change extent size or realtime flag.
-         */
-        if (mask & (XFS_AT_EXTSIZE|XFS_AT_XFLAGS)) {
-                /*
-                 * Can't change extent size if any extents are allocated.
-                 */
-                if (ip->i_d.di_nextents && (mask & XFS_AT_EXTSIZE) &&
-                    ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) !=
-                     vap->va_extsize) ) {
-                        code = XFS_ERROR(EINVAL);       /* EFBIG? */
-                        goto error_return;
-                }
-
-                /*
-                 * Can't change realtime flag if any extents are allocated.
-                 */
-                if ((ip->i_d.di_nextents || ip->i_delayed_blks) &&
-                    (mask & XFS_AT_XFLAGS) &&
-                    (XFS_IS_REALTIME_INODE(ip)) !=
-                    (vap->va_xflags & XFS_XFLAG_REALTIME)) {
-                        code = XFS_ERROR(EINVAL);       /* EFBIG? */
-                        goto error_return;
-                }
-                /*
-                 * Extent size must be a multiple of the appropriate block
-                 * size, if set at all.
-                 */
-                if ((mask & XFS_AT_EXTSIZE) && vap->va_extsize != 0) {
-                        xfs_extlen_t    size;
-
-                        if (XFS_IS_REALTIME_INODE(ip) ||
-                            ((mask & XFS_AT_XFLAGS) &&
-                            (vap->va_xflags & XFS_XFLAG_REALTIME))) {
-                                size = mp->m_sb.sb_rextsize <<
-                                       mp->m_sb.sb_blocklog;
-                        } else {
-                                size = mp->m_sb.sb_blocksize;
-                        }
-                        if (vap->va_extsize % size) {
-                                code = XFS_ERROR(EINVAL);
-                                goto error_return;
-                        }
-                }
-                /*
-                 * If realtime flag is set then must have realtime data.
-                 */
-                if ((mask & XFS_AT_XFLAGS) &&
-                    (vap->va_xflags & XFS_XFLAG_REALTIME)) {
-                        if ((mp->m_sb.sb_rblocks == 0) ||
-                            (mp->m_sb.sb_rextsize == 0) ||
-                            (ip->i_d.di_extsize % mp->m_sb.sb_rextsize)) {
-                                code = XFS_ERROR(EINVAL);
-                                goto error_return;
-                        }
-                }
-
-                /*
-                 * Can't modify an immutable/append-only file unless
-                 * we have appropriate permission.
-                 */
-                if ((mask & XFS_AT_XFLAGS) &&
-                    (ip->i_d.di_flags &
-                                (XFS_DIFLAG_IMMUTABLE|XFS_DIFLAG_APPEND) ||
-                     (vap->va_xflags &
-                                (XFS_XFLAG_IMMUTABLE | XFS_XFLAG_APPEND))) &&
-                    !capable(CAP_LINUX_IMMUTABLE)) {
-                        code = XFS_ERROR(EPERM);
-                        goto error_return;
-                }
-        }
-
-        /*
          * Now we can make the changes.  Before we join the inode
-         * to the transaction, if XFS_AT_SIZE is set then take care of
+         * to the transaction, if ATTR_SIZE is set then take care of
          * the part of the truncation that must be done without the
          * inode lock.  This needs to be done before joining the inode
          * to the transaction, because the inode cannot be unlocked
          * once it is a part of the transaction.
          */
-        if (mask & XFS_AT_SIZE) {
+        if (mask & ATTR_SIZE) {
                 code = 0;
-                if ((vap->va_size > ip->i_size) &&
-                    (flags & ATTR_NOSIZETOK) == 0) {
-                        code = xfs_igrow_start(ip, vap->va_size, credp);
+                if (iattr->ia_size > ip->i_size) {
+                        /*
+                         * Do the first part of growing a file: zero any data
+                         * in the last block that is beyond the old EOF.  We
+                         * need to do this before the inode is joined to the
+                         * transaction to modify the i_size.
+                         */
+                        code = xfs_zero_eof(ip, iattr->ia_size, ip->i_size);
                 }
                 xfs_iunlock(ip, XFS_ILOCK_EXCL);
 
@@ -461,10 +358,10 @@ xfs_setattr(
                  * not within the range we care about here.
                  */
                 if (!code &&
-                    (ip->i_size != ip->i_d.di_size) &&
-                    (vap->va_size > ip->i_d.di_size)) {
+                    ip->i_size != ip->i_d.di_size &&
+                    iattr->ia_size > ip->i_d.di_size) {
                         code = xfs_flush_pages(ip,
-                                        ip->i_d.di_size, vap->va_size,
+                                        ip->i_d.di_size, iattr->ia_size,
                                         XFS_B_ASYNC, FI_NONE);
                 }
 
@@ -472,7 +369,7 @@ xfs_setattr(
                 vn_iowait(ip);
 
                 if (!code)
-                        code = xfs_itruncate_data(ip, vap->va_size);
+                        code = xfs_itruncate_data(ip, iattr->ia_size);
                 if (code) {
                         ASSERT(tp == NULL);
                         lock_flags &= ~XFS_ILOCK_EXCL;
@@ -501,28 +398,30 @@ xfs_setattr(
         /*
          * Truncate file.  Must have write permission and not be a directory.
          */
-        if (mask & XFS_AT_SIZE) {
+        if (mask & ATTR_SIZE) {
                 /*
                  * Only change the c/mtime if we are changing the size
                  * or we are explicitly asked to change it. This handles
                  * the semantic difference between truncate() and ftruncate()
                  * as implemented in the VFS.
                  */
-                if (vap->va_size != ip->i_size || (mask & XFS_AT_CTIME))
+                if (iattr->ia_size != ip->i_size || (mask & ATTR_CTIME))
                         timeflags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
 
-                if (vap->va_size > ip->i_size) {
-                        xfs_igrow_finish(tp, ip, vap->va_size,
-                            !(flags & ATTR_DMI));
-                } else if ((vap->va_size <= ip->i_size) ||
-                           ((vap->va_size == 0) && ip->i_d.di_nextents)) {
+                if (iattr->ia_size > ip->i_size) {
+                        ip->i_d.di_size = iattr->ia_size;
+                        ip->i_size = iattr->ia_size;
+                        if (!(flags & XFS_ATTR_DMI))
+                                xfs_ichgtime(ip, XFS_ICHGTIME_CHG);
+                        xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+                } else if (iattr->ia_size <= ip->i_size ||
+                           (iattr->ia_size == 0 && ip->i_d.di_nextents)) {
                         /*
                          * signal a sync transaction unless
                          * we're truncating an already unlinked
                          * file on a wsync filesystem
                          */
-                        code = xfs_itruncate_finish(&tp, ip,
-                                            (xfs_fsize_t)vap->va_size,
+                        code = xfs_itruncate_finish(&tp, ip, iattr->ia_size,
                                             XFS_DATA_FORK,
                                             ((ip->i_d.di_nlink != 0 ||
                                               !(mp->m_flags & XFS_MOUNT_WSYNC))
@@ -544,9 +443,12 @@ xfs_setattr(
         /*
          * Change file access modes.
          */
-        if (mask & XFS_AT_MODE) {
+        if (mask & ATTR_MODE) {
                 ip->i_d.di_mode &= S_IFMT;
-                ip->i_d.di_mode |= vap->va_mode & ~S_IFMT;
+                ip->i_d.di_mode |= iattr->ia_mode & ~S_IFMT;
+
+                inode->i_mode &= S_IFMT;
+                inode->i_mode |= iattr->ia_mode & ~S_IFMT;
 
                 xfs_trans_log_inode (tp, ip, XFS_ILOG_CORE);
                 timeflags |= XFS_ICHGTIME_CHG;
@@ -559,7 +461,7 @@ xfs_setattr(
          * and can change the group id only to a group of which he
          * or she is a member.
          */
-        if (mask & (XFS_AT_UID|XFS_AT_GID|XFS_AT_PROJID)) {
+        if (mask & (ATTR_UID|ATTR_GID)) {
                 /*
                  * CAP_FSETID overrides the following restrictions:
                  *
@@ -577,39 +479,24 @@ xfs_setattr(
                  */
                 if (iuid != uid) {
                         if (XFS_IS_UQUOTA_ON(mp)) {
-                                ASSERT(mask & XFS_AT_UID);
+                                ASSERT(mask & ATTR_UID);
                                 ASSERT(udqp);
                                 olddquot1 = XFS_QM_DQVOPCHOWN(mp, tp, ip,
                                                         &ip->i_udquot, udqp);
                         }
                         ip->i_d.di_uid = uid;
+                        inode->i_uid = uid;
                 }
                 if (igid != gid) {
                         if (XFS_IS_GQUOTA_ON(mp)) {
                                 ASSERT(!XFS_IS_PQUOTA_ON(mp));
-                                ASSERT(mask & XFS_AT_GID);
+                                ASSERT(mask & ATTR_GID);
                                 ASSERT(gdqp);
                                 olddquot2 = XFS_QM_DQVOPCHOWN(mp, tp, ip,
                                                         &ip->i_gdquot, gdqp);
                         }
                         ip->i_d.di_gid = gid;
-                }
-                if (iprojid != projid) {
-                        if (XFS_IS_PQUOTA_ON(mp)) {
-                                ASSERT(!XFS_IS_GQUOTA_ON(mp));
-                                ASSERT(mask & XFS_AT_PROJID);
-                                ASSERT(gdqp);
-                                olddquot2 = XFS_QM_DQVOPCHOWN(mp, tp, ip,
-                                                        &ip->i_gdquot, gdqp);
-                        }
-                        ip->i_d.di_projid = projid;
-                        /*
-                         * We may have to rev the inode as well as
-                         * the superblock version number since projids didn't
-                         * exist before DINODE_VERSION_2 and SB_VERSION_NLINK.
-                         */
-                        if (ip->i_d.di_version == XFS_DINODE_VERSION_1)
-                                xfs_bump_ino_vers2(tp, ip);
+                        inode->i_gid = gid;
                 }
 
                 xfs_trans_log_inode (tp, ip, XFS_ILOG_CORE);
@@ -620,82 +507,34 @@ xfs_setattr(
         /*
          * Change file access or modified times.
          */
-        if (mask & (XFS_AT_ATIME|XFS_AT_MTIME)) {
-                if (mask & XFS_AT_ATIME) {
-                        ip->i_d.di_atime.t_sec = vap->va_atime.tv_sec;
-                        ip->i_d.di_atime.t_nsec = vap->va_atime.tv_nsec;
+        if (mask & (ATTR_ATIME|ATTR_MTIME)) {
+                if (mask & ATTR_ATIME) {
+                        inode->i_atime = iattr->ia_atime;
+                        ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec;
+                        ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec;
                         ip->i_update_core = 1;
                         timeflags &= ~XFS_ICHGTIME_ACC;
                 }
-                if (mask & XFS_AT_MTIME) {
-                        ip->i_d.di_mtime.t_sec = vap->va_mtime.tv_sec;
-                        ip->i_d.di_mtime.t_nsec = vap->va_mtime.tv_nsec;
+                if (mask & ATTR_MTIME) {
+                        inode->i_mtime = iattr->ia_mtime;
+                        ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
+                        ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
                         timeflags &= ~XFS_ICHGTIME_MOD;
                         timeflags |= XFS_ICHGTIME_CHG;
                 }
-                if (tp && (flags & ATTR_UTIME))
+                if (tp && (mask & (ATTR_MTIME_SET|ATTR_ATIME_SET)))
                         xfs_trans_log_inode (tp, ip, XFS_ILOG_CORE);
         }
 
         /*
-         * Change XFS-added attributes.
-         */
-        if (mask & (XFS_AT_EXTSIZE|XFS_AT_XFLAGS)) {
-                if (mask & XFS_AT_EXTSIZE) {
-                        /*
-                         * Converting bytes to fs blocks.
-                         */
-                        ip->i_d.di_extsize = vap->va_extsize >>
-                                mp->m_sb.sb_blocklog;
-                }
-                if (mask & XFS_AT_XFLAGS) {
-                        uint    di_flags;
-
-                        /* can't set PREALLOC this way, just preserve it */
-                        di_flags = (ip->i_d.di_flags & XFS_DIFLAG_PREALLOC);
-                        if (vap->va_xflags & XFS_XFLAG_IMMUTABLE)
-                                di_flags |= XFS_DIFLAG_IMMUTABLE;
-                        if (vap->va_xflags & XFS_XFLAG_APPEND)
-                                di_flags |= XFS_DIFLAG_APPEND;
-                        if (vap->va_xflags & XFS_XFLAG_SYNC)
-                                di_flags |= XFS_DIFLAG_SYNC;
-                        if (vap->va_xflags & XFS_XFLAG_NOATIME)
-                                di_flags |= XFS_DIFLAG_NOATIME;
-                        if (vap->va_xflags & XFS_XFLAG_NODUMP)
-                                di_flags |= XFS_DIFLAG_NODUMP;
-                        if (vap->va_xflags & XFS_XFLAG_PROJINHERIT)
-                                di_flags |= XFS_DIFLAG_PROJINHERIT;
-                        if (vap->va_xflags & XFS_XFLAG_NODEFRAG)
-                                di_flags |= XFS_DIFLAG_NODEFRAG;
-                        if (vap->va_xflags & XFS_XFLAG_FILESTREAM)
-                                di_flags |= XFS_DIFLAG_FILESTREAM;
-                        if ((ip->i_d.di_mode & S_IFMT) == S_IFDIR) {
-                                if (vap->va_xflags & XFS_XFLAG_RTINHERIT)
-                                        di_flags |= XFS_DIFLAG_RTINHERIT;
-                                if (vap->va_xflags & XFS_XFLAG_NOSYMLINKS)
-                                        di_flags |= XFS_DIFLAG_NOSYMLINKS;
-                                if (vap->va_xflags & XFS_XFLAG_EXTSZINHERIT)
-                                        di_flags |= XFS_DIFLAG_EXTSZINHERIT;
-                        } else if ((ip->i_d.di_mode & S_IFMT) == S_IFREG) {
-                                if (vap->va_xflags & XFS_XFLAG_REALTIME)
-                                        di_flags |= XFS_DIFLAG_REALTIME;
-                                if (vap->va_xflags & XFS_XFLAG_EXTSIZE)
-                                        di_flags |= XFS_DIFLAG_EXTSIZE;
-                        }
-                        ip->i_d.di_flags = di_flags;
-                }
-                xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-                timeflags |= XFS_ICHGTIME_CHG;
-        }
-
-        /*
-         * Change file inode change time only if XFS_AT_CTIME set
+         * Change file inode change time only if ATTR_CTIME set
          * AND we have been called by a DMI function.
          */
 
-        if ( (flags & ATTR_DMI) && (mask & XFS_AT_CTIME) ) {
-                ip->i_d.di_ctime.t_sec = vap->va_ctime.tv_sec;
-                ip->i_d.di_ctime.t_nsec = vap->va_ctime.tv_nsec;
+        if ((flags & XFS_ATTR_DMI) && (mask & ATTR_CTIME)) {
+                inode->i_ctime = iattr->ia_ctime;
+                ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;
+                ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec;
                 ip->i_update_core = 1;
                 timeflags &= ~XFS_ICHGTIME_CHG;
         }
@@ -704,7 +543,7 @@ xfs_setattr(
          * Send out timestamp changes that need to be set to the
          * current time.  Not done when called by a DMI function.
          */
-        if (timeflags && !(flags & ATTR_DMI))
+        if (timeflags && !(flags & XFS_ATTR_DMI))
                 xfs_ichgtime(ip, timeflags);
 
         XFS_STATS_INC(xs_ig_attrchg);
@@ -742,7 +581,7 @@ xfs_setattr(
         }
 
         if (DM_EVENT_ENABLED(ip, DM_EVENT_ATTRIBUTE) &&
-            !(flags & ATTR_DMI)) {
+            !(flags & XFS_ATTR_DMI)) {
                 (void) XFS_SEND_NAMESP(mp, DM_EVENT_ATTRIBUTE, ip, DM_RIGHT_NULL,
                                         NULL, DM_RIGHT_NULL, NULL, NULL,
                                         0, 0, AT_DELAY_FLAG(flags));
@@ -1601,12 +1440,18 @@ xfs_inactive(
         return VN_INACTIVE_CACHE;
 }
 
-
+/*
+ * Lookups up an inode from "name". If ci_name is not NULL, then a CI match
+ * is allowed, otherwise it has to be an exact match. If a CI match is found,
+ * ci_name->name will point to a the actual name (caller must free) or
+ * will be set to NULL if an exact match is found.
+ */
 int
 xfs_lookup(
         xfs_inode_t             *dp,
         struct xfs_name         *name,
-        xfs_inode_t             **ipp)
+        xfs_inode_t             **ipp,
+        struct xfs_name         *ci_name)
 {
         xfs_ino_t               inum;
         int                     error;
@@ -1618,7 +1463,7 @@ xfs_lookup(
                 return XFS_ERROR(EIO);
 
         lock_mode = xfs_ilock_map_shared(dp);
-        error = xfs_dir_lookup(NULL, dp, name, &inum);
+        error = xfs_dir_lookup(NULL, dp, name, &inum, ci_name);
         xfs_iunlock_map_shared(dp, lock_mode);
 
         if (error)
@@ -1626,12 +1471,15 @@ xfs_lookup(
 
         error = xfs_iget(dp->i_mount, NULL, inum, 0, 0, ipp, 0);
         if (error)
-                goto out;
+                goto out_free_name;
 
         xfs_itrace_ref(*ipp);
         return 0;
 
- out:
+out_free_name:
+        if (ci_name)
+                kmem_free(ci_name->name);
+out:
         *ipp = NULL;
         return error;
 }
@@ -2098,13 +1946,6 @@ again:
 #endif
 }
 
-#ifdef  DEBUG
-#define REMOVE_DEBUG_TRACE(x)   {remove_which_error_return = (x);}
-int remove_which_error_return = 0;
-#else /* ! DEBUG */
-#define REMOVE_DEBUG_TRACE(x)
-#endif  /* ! DEBUG */
-
 int
 xfs_remove(
         xfs_inode_t             *dp,
@@ -2113,6 +1954,7 @@ xfs_remove(
 {
         xfs_mount_t             *mp = dp->i_mount;
         xfs_trans_t             *tp = NULL;
+        int                     is_dir = S_ISDIR(ip->i_d.di_mode);
         int                     error = 0;
         xfs_bmap_free_t         free_list;
         xfs_fsblock_t           first_block;
@@ -2120,8 +1962,10 @@ xfs_remove(
         int                     committed;
         int                     link_zero;
         uint                    resblks;
+        uint                    log_count;
 
         xfs_itrace_entry(dp);
+        xfs_itrace_entry(ip);
 
         if (XFS_FORCED_SHUTDOWN(mp))
                 return XFS_ERROR(EIO);
@@ -2134,19 +1978,23 @@ xfs_remove(
                         return error;
         }
 
-        xfs_itrace_entry(ip);
-        xfs_itrace_ref(ip);
-
         error = XFS_QM_DQATTACH(mp, dp, 0);
-        if (!error)
-                error = XFS_QM_DQATTACH(mp, ip, 0);
-        if (error) {
-                REMOVE_DEBUG_TRACE(__LINE__);
+        if (error)
+                goto std_return;
+
+        error = XFS_QM_DQATTACH(mp, ip, 0);
+        if (error)
                 goto std_return;
-        }
 
-        tp = xfs_trans_alloc(mp, XFS_TRANS_REMOVE);
+        if (is_dir) {
+                tp = xfs_trans_alloc(mp, XFS_TRANS_RMDIR);
+                log_count = XFS_DEFAULT_LOG_COUNT;
+        } else {
+                tp = xfs_trans_alloc(mp, XFS_TRANS_REMOVE);
+                log_count = XFS_REMOVE_LOG_COUNT;
+        }
         cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
+
         /*
          * We try to get the real space reservation first,
          * allowing for directory btree deletion(s) implying
@@ -2158,25 +2006,21 @@ xfs_remove(
          */
         resblks = XFS_REMOVE_SPACE_RES(mp);
         error = xfs_trans_reserve(tp, resblks, XFS_REMOVE_LOG_RES(mp), 0,
-                        XFS_TRANS_PERM_LOG_RES, XFS_REMOVE_LOG_COUNT);
+                                  XFS_TRANS_PERM_LOG_RES, log_count);
         if (error == ENOSPC) {
                 resblks = 0;
                 error = xfs_trans_reserve(tp, 0, XFS_REMOVE_LOG_RES(mp), 0,
-                                XFS_TRANS_PERM_LOG_RES, XFS_REMOVE_LOG_COUNT);
+                                          XFS_TRANS_PERM_LOG_RES, log_count);
         }
         if (error) {
                 ASSERT(error != ENOSPC);
-                REMOVE_DEBUG_TRACE(__LINE__);
-                xfs_trans_cancel(tp, 0);
-                return error;
+                cancel_flags = 0;
+                goto out_trans_cancel;
         }
 
         error = xfs_lock_dir_and_entry(dp, ip);
-        if (error) {
-                REMOVE_DEBUG_TRACE(__LINE__);
-                xfs_trans_cancel(tp, cancel_flags);
-                goto std_return;
-        }
+        if (error)
+                goto out_trans_cancel;
 
         /*
          * At this point, we've gotten both the directory and the entry
@@ -2189,6 +2033,21 @@ xfs_remove(
         xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
         /*
+         * If we're removing a directory perform some additional validation.
+         */
+        if (is_dir) {
+                ASSERT(ip->i_d.di_nlink >= 2);
+                if (ip->i_d.di_nlink != 2) {
+                        error = XFS_ERROR(ENOTEMPTY);
+                        goto out_trans_cancel;
+                }
+                if (!xfs_dir_isempty(ip)) {
+                        error = XFS_ERROR(ENOTEMPTY);
+                        goto out_trans_cancel;
+                }
+        }
+
+        /*
          * Entry must exist since we did a lookup in xfs_lock_dir_and_entry.
          */
         XFS_BMAP_INIT(&free_list, &first_block);
@@ -2196,39 +2055,64 @@ xfs_remove(
                                         &first_block, &free_list, resblks);
         if (error) {
                 ASSERT(error != ENOENT);
-                REMOVE_DEBUG_TRACE(__LINE__);
-                goto error1;
+                goto out_bmap_cancel;
         }
         xfs_ichgtime(dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 
+        /*
+         * Bump the in memory generation count on the parent
+         * directory so that other can know that it has changed.
+         */
         dp->i_gen++;
         xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
 
-        error = xfs_droplink(tp, ip);
-        if (error) {
-                REMOVE_DEBUG_TRACE(__LINE__);
-                goto error1;
+        if (is_dir) {
+                /*
+                 * Drop the link from ip's "..".
+                 */
+                error = xfs_droplink(tp, dp);
+                if (error)
+                        goto out_bmap_cancel;
+
+                /*
+                 * Drop the link from dp to ip.
+                 */
+                error = xfs_droplink(tp, ip);
+                if (error)
+                        goto out_bmap_cancel;
+        } else {
+                /*
+                 * When removing a non-directory we need to log the parent
+                 * inode here for the i_gen update.  For a directory this is
+                 * done implicitly by the xfs_droplink call for the ".." entry.
+                 */
+                xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
         }
 
-        /* Determine if this is the last link while
+        /*
+         * Drop the "." link from ip to self.
+         */
+        error = xfs_droplink(tp, ip);
+        if (error)
+                goto out_bmap_cancel;
+
+        /*
+         * Determine if this is the last link while
          * we are in the transaction.
          */
-        link_zero = (ip)->i_d.di_nlink==0;
+        link_zero = (ip->i_d.di_nlink == 0);
 
         /*
          * If this is a synchronous mount, make sure that the
          * remove transaction goes to disk before returning to
          * the user.
          */
-        if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) {
+        if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
                 xfs_trans_set_sync(tp);
-        }
 
         error = xfs_bmap_finish(&tp, &free_list, &committed);
-        if (error) {
-                REMOVE_DEBUG_TRACE(__LINE__);
-                goto error_rele;
-        }
+        if (error)
+                goto out_bmap_cancel;
 
         error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
         if (error)
@@ -2240,38 +2124,26 @@ xfs_remove(
          * will get killed on last close in xfs_close() so we don't
          * have to worry about that.
          */
-        if (link_zero && xfs_inode_is_filestream(ip))
+        if (!is_dir && link_zero && xfs_inode_is_filestream(ip))
                 xfs_filestream_deassociate(ip);
 
         xfs_itrace_exit(ip);
+        xfs_itrace_exit(dp);
 
-/*      Fall through to std_return with error = 0 */
  std_return:
         if (DM_EVENT_ENABLED(dp, DM_EVENT_POSTREMOVE)) {
-                (void) XFS_SEND_NAMESP(mp, DM_EVENT_POSTREMOVE,
-                                dp, DM_RIGHT_NULL,
-                                NULL, DM_RIGHT_NULL,
-                                name->name, NULL, ip->i_d.di_mode, error, 0);
+                XFS_SEND_NAMESP(mp, DM_EVENT_POSTREMOVE, dp, DM_RIGHT_NULL,
+                                NULL, DM_RIGHT_NULL, name->name, NULL,
+                                ip->i_d.di_mode, error, 0);
         }
-        return error;
 
- error1:
-        xfs_bmap_cancel(&free_list);
-        cancel_flags |= XFS_TRANS_ABORT;
-        xfs_trans_cancel(tp, cancel_flags);
-        goto std_return;
+        return error;
 
- error_rele:
-        /*
-         * In this case make sure to not release the inode until after
-         * the current transaction is aborted.  Releasing it beforehand
-         * can cause us to go to xfs_inactive and start a recursive
-         * transaction which can easily deadlock with the current one.
-         */
+ out_bmap_cancel:
         xfs_bmap_cancel(&free_list);
         cancel_flags |= XFS_TRANS_ABORT;
+ out_trans_cancel:
         xfs_trans_cancel(tp, cancel_flags);
-
         goto std_return;
 }
 
@@ -2638,186 +2510,6 @@ std_return:
 }
 
 int
-xfs_rmdir(
-        xfs_inode_t             *dp,
-        struct xfs_name         *name,
-        xfs_inode_t             *cdp)
-{
-        xfs_mount_t             *mp = dp->i_mount;
-        xfs_trans_t             *tp;
-        int                     error;
-        xfs_bmap_free_t         free_list;
-        xfs_fsblock_t           first_block;
-        int                     cancel_flags;
-        int                     committed;
-        int                     last_cdp_link;
-        uint                    resblks;
-
-        xfs_itrace_entry(dp);
-
-        if (XFS_FORCED_SHUTDOWN(mp))
-                return XFS_ERROR(EIO);
-
-        if (DM_EVENT_ENABLED(dp, DM_EVENT_REMOVE)) {
-                error = XFS_SEND_NAMESP(mp, DM_EVENT_REMOVE,
-                                        dp, DM_RIGHT_NULL,
-                                        NULL, DM_RIGHT_NULL, name->name,
-                                        NULL, cdp->i_d.di_mode, 0, 0);
-                if (error)
-                        return XFS_ERROR(error);
-        }
-
-        /*
-         * Get the dquots for the inodes.
-         */
-        error = XFS_QM_DQATTACH(mp, dp, 0);
-        if (!error)
-                error = XFS_QM_DQATTACH(mp, cdp, 0);
-        if (error) {
-                REMOVE_DEBUG_TRACE(__LINE__);
-                goto std_return;
-        }
-
-        tp = xfs_trans_alloc(mp, XFS_TRANS_RMDIR);
-        cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
-        /*
-         * We try to get the real space reservation first,
-         * allowing for directory btree deletion(s) implying
-         * possible bmap insert(s).  If we can't get the space
-         * reservation then we use 0 instead, and avoid the bmap
-         * btree insert(s) in the directory code by, if the bmap
-         * insert tries to happen, instead trimming the LAST
-         * block from the directory.
-         */
-        resblks = XFS_REMOVE_SPACE_RES(mp);
-        error = xfs_trans_reserve(tp, resblks, XFS_REMOVE_LOG_RES(mp), 0,
-                        XFS_TRANS_PERM_LOG_RES, XFS_DEFAULT_LOG_COUNT);
-        if (error == ENOSPC) {
-                resblks = 0;
-                error = xfs_trans_reserve(tp, 0, XFS_REMOVE_LOG_RES(mp), 0,
-                                XFS_TRANS_PERM_LOG_RES, XFS_DEFAULT_LOG_COUNT);
-        }
-        if (error) {
-                ASSERT(error != ENOSPC);
-                cancel_flags = 0;
-                goto error_return;
-        }
-        XFS_BMAP_INIT(&free_list, &first_block);
-
-        /*
-         * Now lock the child directory inode and the parent directory
-         * inode in the proper order.  This will take care of validating
-         * that the directory entry for the child directory inode has
-         * not changed while we were obtaining a log reservation.
-         */
-        error = xfs_lock_dir_and_entry(dp, cdp);
-        if (error) {
-                xfs_trans_cancel(tp, cancel_flags);
-                goto std_return;
-        }
-
-        IHOLD(dp);
-        xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
-
-        IHOLD(cdp);
-        xfs_trans_ijoin(tp, cdp, XFS_ILOCK_EXCL);
-
-        ASSERT(cdp->i_d.di_nlink >= 2);
-        if (cdp->i_d.di_nlink != 2) {
-                error = XFS_ERROR(ENOTEMPTY);
-                goto error_return;
-        }
-        if (!xfs_dir_isempty(cdp)) {
-                error = XFS_ERROR(ENOTEMPTY);
-                goto error_return;
-        }
-
-        error = xfs_dir_removename(tp, dp, name, cdp->i_ino,
-                                        &first_block, &free_list, resblks);
-        if (error)
-                goto error1;
-
-        xfs_ichgtime(dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
-
-        /*
-         * Bump the in memory generation count on the parent
-         * directory so that other can know that it has changed.
-         */
-        dp->i_gen++;
-
-        /*
-         * Drop the link from cdp's "..".
-         */
-        error = xfs_droplink(tp, dp);
-        if (error) {
-                goto error1;
-        }
-
-        /*
-         * Drop the link from dp to cdp.
-         */
-        error = xfs_droplink(tp, cdp);
-        if (error) {
-                goto error1;
-        }
-
-        /*
-         * Drop the "." link from cdp to self.
-         */
-        error = xfs_droplink(tp, cdp);
-        if (error) {
-                goto error1;
-        }
-
-        /* Determine these before committing transaction */
-        last_cdp_link = (cdp)->i_d.di_nlink==0;
-
-        /*
-         * If this is a synchronous mount, make sure that the
-         * rmdir transaction goes to disk before returning to
-         * the user.
-         */
-        if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) {
-                xfs_trans_set_sync(tp);
-        }
-
-        error = xfs_bmap_finish (&tp, &free_list, &committed);
-        if (error) {
-                xfs_bmap_cancel(&free_list);
-                xfs_trans_cancel(tp, (XFS_TRANS_RELEASE_LOG_RES |
-                                 XFS_TRANS_ABORT));
-                goto std_return;
-        }
-
-        error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
-        if (error) {
-                goto std_return;
-        }
-
-
-        /* Fall through to std_return with error = 0 or the errno
-         * from xfs_trans_commit. */
- std_return:
-        if (DM_EVENT_ENABLED(dp, DM_EVENT_POSTREMOVE)) {
-                (void) XFS_SEND_NAMESP(mp, DM_EVENT_POSTREMOVE,
-                                        dp, DM_RIGHT_NULL,
-                                        NULL, DM_RIGHT_NULL,
-                                        name->name, NULL, cdp->i_d.di_mode,
-                                        error, 0);
-        }
-        return error;
-
- error1:
-        xfs_bmap_cancel(&free_list);
-        cancel_flags |= XFS_TRANS_ABORT;
-        /* FALLTHROUGH */
-
- error_return:
-        xfs_trans_cancel(tp, cancel_flags);
-        goto std_return;
-}
-
-int
 xfs_symlink(
         xfs_inode_t             *dp,
         struct xfs_name         *link_name,
@@ -3242,7 +2934,6 @@ xfs_finish_reclaim(
 {
         xfs_perag_t     *pag = xfs_get_perag(ip->i_mount, ip->i_ino);
         bhv_vnode_t     *vp = XFS_ITOV_NULL(ip);
-        int             error;
 
         if (vp && VN_BAD(vp))
                 goto reclaim;
@@ -3285,29 +2976,16 @@ xfs_finish_reclaim(
                 xfs_iflock(ip);
         }
 
-        if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
-                if (ip->i_update_core ||
-                    ((ip->i_itemp != NULL) &&
-                     (ip->i_itemp->ili_format.ilf_fields != 0))) {
-                        error = xfs_iflush(ip, sync_mode);
-                        /*
-                         * If we hit an error, typically because of filesystem
-                         * shutdown, we don't need to let vn_reclaim to know
-                         * because we're gonna reclaim the inode anyway.
-                         */
-                        if (error) {
-                                xfs_iunlock(ip, XFS_ILOCK_EXCL);
-                                goto reclaim;
-                        }
-                        xfs_iflock(ip); /* synchronize with xfs_iflush_done */
-                }
-
-                ASSERT(ip->i_update_core == 0);
-                ASSERT(ip->i_itemp == NULL ||
-                       ip->i_itemp->ili_format.ilf_fields == 0);
+        /*
+         * In the case of a forced shutdown we rely on xfs_iflush() to
+         * wait for the inode to be unpinned before returning an error.
+         */
+        if (xfs_iflush(ip, sync_mode) == 0) {
+                /* synchronize with xfs_iflush_done */
+                xfs_iflock(ip);
+                xfs_ifunlock(ip);
         }
 
-        xfs_ifunlock(ip);
         xfs_iunlock(ip, XFS_ILOCK_EXCL);
 
  reclaim:
@@ -3418,7 +3096,7 @@ xfs_alloc_file_space(
 
         /*      Generate a DMAPI event if needed.       */
         if (alloc_type != 0 && offset < ip->i_size &&
-                        (attr_flags&ATTR_DMI) == 0  &&
+                        (attr_flags & XFS_ATTR_DMI) == 0  &&
                         DM_EVENT_ENABLED(ip, DM_EVENT_WRITE)) {
                 xfs_off_t           end_dmi_offset;
 
@@ -3532,7 +3210,7 @@ retry:
                 allocatesize_fsb -= allocated_fsb;
         }
 dmapi_enospc_check:
-        if (error == ENOSPC && (attr_flags & ATTR_DMI) == 0 &&
+        if (error == ENOSPC && (attr_flags & XFS_ATTR_DMI) == 0 &&
             DM_EVENT_ENABLED(ip, DM_EVENT_NOSPACE)) {
                 error = XFS_SEND_NAMESP(mp, DM_EVENT_NOSPACE,
                                 ip, DM_RIGHT_NULL,
@@ -3679,7 +3357,7 @@ xfs_free_file_space(
         end_dmi_offset = offset + len;
         endoffset_fsb = XFS_B_TO_FSBT(mp, end_dmi_offset);
 
-        if (offset < ip->i_size && (attr_flags & ATTR_DMI) == 0 &&
+        if (offset < ip->i_size && (attr_flags & XFS_ATTR_DMI) == 0 &&
             DM_EVENT_ENABLED(ip, DM_EVENT_WRITE)) {
                 if (end_dmi_offset > ip->i_size)
                         end_dmi_offset = ip->i_size;
@@ -3690,7 +3368,7 @@ xfs_free_file_space(
                         return error;
         }
 
-        if (attr_flags & ATTR_NOLOCK)
+        if (attr_flags & XFS_ATTR_NOLOCK)
                 need_iolock = 0;
         if (need_iolock) {
                 xfs_ilock(ip, XFS_IOLOCK_EXCL);
@@ -3867,7 +3545,7 @@ xfs_change_file_space(
         xfs_off_t       startoffset;
         xfs_off_t       llen;
         xfs_trans_t     *tp;
-        bhv_vattr_t     va;
+        struct iattr    iattr;
 
         xfs_itrace_entry(ip);
 
@@ -3941,10 +3619,10 @@ xfs_change_file_space(
                                 break;
                 }
 
-                va.va_mask = XFS_AT_SIZE;
-                va.va_size = startoffset;
+                iattr.ia_valid = ATTR_SIZE;
+                iattr.ia_size = startoffset;
 
-                error = xfs_setattr(ip, &va, attr_flags, credp);
+                error = xfs_setattr(ip, &iattr, attr_flags, credp);
 
                 if (error)
                         return error;
@@ -3974,7 +3652,7 @@ xfs_change_file_space(
         xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
         xfs_trans_ihold(tp, ip);
 
-        if ((attr_flags & ATTR_DMI) == 0) {
+        if ((attr_flags & XFS_ATTR_DMI) == 0) {
                 ip->i_d.di_mode &= ~S_ISUID;
 
                 /*
diff --git a/fs/xfs/xfs_vnodeops.h b/fs/xfs/xfs_vnodeops.h
index 57335ba4ce53..e932a96bec54 100644
--- a/fs/xfs/xfs_vnodeops.h
+++ b/fs/xfs/xfs_vnodeops.h
@@ -2,9 +2,9 @@
 #define _XFS_VNODEOPS_H 1
 
 struct attrlist_cursor_kern;
-struct bhv_vattr;
 struct cred;
 struct file;
+struct iattr;
 struct inode;
 struct iovec;
 struct kiocb;
@@ -15,14 +15,18 @@ struct xfs_iomap;
 
 
 int xfs_open(struct xfs_inode *ip);
-int xfs_setattr(struct xfs_inode *ip, struct bhv_vattr *vap, int flags,
+int xfs_setattr(struct xfs_inode *ip, struct iattr *vap, int flags,
                 struct cred *credp);
+#define XFS_ATTR_DMI            0x01    /* invocation from a DMI function */
+#define XFS_ATTR_NONBLOCK       0x02    /* return EAGAIN if operation would block */
+#define XFS_ATTR_NOLOCK         0x04    /* Don't grab any conflicting locks */
+
 int xfs_readlink(struct xfs_inode *ip, char *link);
 int xfs_fsync(struct xfs_inode *ip);
 int xfs_release(struct xfs_inode *ip);
 int xfs_inactive(struct xfs_inode *ip);
 int xfs_lookup(struct xfs_inode *dp, struct xfs_name *name,
-                struct xfs_inode **ipp);
+                struct xfs_inode **ipp, struct xfs_name *ci_name);
 int xfs_create(struct xfs_inode *dp, struct xfs_name *name, mode_t mode,
                 xfs_dev_t rdev, struct xfs_inode **ipp, struct cred *credp);
 int xfs_remove(struct xfs_inode *dp, struct xfs_name *name,
@@ -31,8 +35,6 @@ int xfs_link(struct xfs_inode *tdp, struct xfs_inode *sip,
                 struct xfs_name *target_name);
 int xfs_mkdir(struct xfs_inode *dp, struct xfs_name *dir_name,
                 mode_t mode, struct xfs_inode **ipp, struct cred *credp);
-int xfs_rmdir(struct xfs_inode *dp, struct xfs_name *name,
-                struct xfs_inode *cdp);
 int xfs_readdir(struct xfs_inode        *dp, void *dirent, size_t bufsize,
                        xfs_off_t *offset, filldir_t filldir);
 int xfs_symlink(struct xfs_inode *dp, struct xfs_name *link_name,